CN104503997A - Peer positioning method and device as well as computer equipment - Google Patents
Peer positioning method and device as well as computer equipment Download PDFInfo
- Publication number
- CN104503997A CN104503997A CN201410740960.1A CN201410740960A CN104503997A CN 104503997 A CN104503997 A CN 104503997A CN 201410740960 A CN201410740960 A CN 201410740960A CN 104503997 A CN104503997 A CN 104503997A
- Authority
- CN
- China
- Prior art keywords
- client
- advertisement putting
- correlation
- degree
- colleague
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0244—Optimization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Abstract
The invention provides a peer positioning method and device as well as computer equipment. The method comprises the following steps: determining numerous clients in a same search result according to advertising display data; determining the correlation degree betweenevery two of the clients according to the advertising effect information of the clients, and creating a related client group according to the correlation degree between every two of the clients; determining subgroups in the related client group based on data mining; determining benchmark peers in the subgroups according to advertising business indexes. Due to the adoption of the technical scheme, the peer positioning reasonability and accuracy are improved, and further, the service for providing information with relatively high reference value for the clients based on the benchmark peers becomes possible.
Description
Technical field
The present invention relates to Internet technical field, especially relate to a kind of colleague localization method, device and computer equipment.
Background technology
May be there is the demand of colleague location in the main bodys such as individual or unit, need to carry out colleague location as the competitive power in order to improve product or service in routine work process.
Existing colleague's localization method mainly comprises three kinds: one, utilize three grades of industry systems to carry out colleague location, three grades of industries belonging to client's first are X, then other clients in X industry are positioned as the colleague of first; Two, the keyword paid close attention to by client carries out colleague location, as first is substantially identical with the keyword that second is thrown in, then first can be orientated as the colleague of second; Three, colleague location is carried out based on multiple dimensions such as industry, keyword, region and consumption.
Inventor is realizing finding in process of the present invention, utilizes three grades of industry systems to carry out the location problem that often existence colleague orientation range is excessive of going together; Although utilize keyword carry out colleague location can exist be service class seemingly, as there is not direct competitive relation between the two in not related problem between the two; And utilize multiple dimension location of carrying out going together probably to exist and get rid of the problem at same line range by cross-region with across the client of the type such as between consumption area.
Summary of the invention
One of technical matters that the present invention solves improves rationality and the accuracy of colleague location.
An embodiment according to an aspect of the present invention, provide a kind of colleague's localization method, the method comprises: determine the multiple clients occurred in same Search Results according to advertisement putting demonstrating data; Determine the degree of correlation in described multiple client between two between client according to client's advertisement delivery effect information, and build relative clients group according to described degree of correlation between two between client; The subgroup existed in described relative clients group is determined based on data mining; The mark post colleague in described subgroup is determined according to advertisement putting operational indicator.
An embodiment according to a further aspect of the invention, provide a kind of colleague's locating device, this device comprises: determine Client Model, is suitable for determining according to advertisement putting demonstrating data multiple clients of occurring in same Search Results; Determine degree of correlation module, be suitable for the degree of correlation determining in described multiple client between two between client according to client's advertisement delivery effect information; Determine customers and subgroup module, be suitable for building relative clients group according to described degree of correlation between two between client, and determine the subgroup existed in described relative clients group based on data mining; Determine mark post colleague module, be suitable for the mark post colleague determined according to advertisement putting operational indicator in described subgroup.
An embodiment according to a further aspect in the invention, additionally provides a kind of computer equipment, comprises aforementioned colleague's locating device.
The present invention is by building relative clients group according to the degree of correlation in the multiple clients occurred in same Search Results between two between client, and excavate the subgroup existed in relative clients group, the scope of going together making location can not excessive while, can also realize, to search keyword, cross-region and the abundant measurement across the multiple correlation factors such as between consumption area, there is between each client in the same line range that Primary Location is gone out stronger correlativity; Finally determine that by utilizing advertisement putting operational indicator the mark post in subgroup is gone together, high-quality colleague can be oriented more targetedly for other clients in the same line range oriented, the high-quality colleague oriented more easily pay close attention to by client, thus make client can improve self advertisement serving policy etc. with reference to the relevant information of high-quality colleague; It can thus be appreciated that technical scheme provided by the invention improves rationality and the accuracy of colleague location, and can provide for client the information more having reference value.
Those of ordinary skill in the art will understand, although detailed description is below carried out with reference to illustrated embodiment and accompanying drawing, the present invention is not limited in these embodiments.But scope of the present invention is widely, and be intended to limit scope of the present invention by means of only accompanying claim.
Accompanying drawing explanation
By reading the detailed description done non-limiting example done with reference to the following drawings, other features, objects and advantages of the present invention will become more obvious:
Fig. 1 is the process flow diagram of localization method of going together according to an embodiment of the invention;
Fig. 2 is location schematic diagram of going together in accordance with another embodiment of the present invention;
Fig. 3 is the schematic diagram of the mark post colleague oriented in accordance with another embodiment of the present invention;
Fig. 4 is the colleague's locating device schematic diagram according to another embodiment of the present invention.
In accompanying drawing, same or analogous Reference numeral represents same or analogous parts.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail.
Fig. 1 and Fig. 2 is the process flow diagram of the localization method of going together of the embodiment of the present invention one and embodiment two respectively.The method of embodiment one and embodiment two has mainly been come by the operating system in computer equipment or processing controller.Operating system in computer equipment or processing controller can be called colleague's locating device.This computer equipment include but not limited to following at least one: the calculating unit of single computer, multiple stage computing machine composition, single network server, the server group of multiple webserver composition and the cloud be made up of a large amount of computing machine or the webserver based on cloud computing; Wherein, cloud computing is the one of Distributed Calculation, the super virtual machine be made up of a group loosely-coupled computing machine collection.
Embodiment one, colleague's localization method.
In Fig. 1, S100, determine multiple clients of occurring in same Search Results according to advertisement putting demonstrating data.
Concrete, advertisement putting demonstrating data in the present embodiment refers to the information of the concrete condition of the advertisement putting that network side shows to user, such as, user inputs keyword in the search column of its search engine client, network side is after the keyword receiving user's input, corresponding search result information is built according to keyword, and search result information is pushed to search engine client, search result information is shown to user by search engine client, in this search procedure, advertisement putting demonstrating data derives from the search result information that network side builds.The search result information quantity at network side being this search structure of user is more, when needing to use multipage Pagination Display, advertisement putting demonstrating data in the present embodiment can derive from the search result information belonging to first page that network side builds, as advertisement putting demonstrating data derives from all advertising messages belonged in first page of network side structure.
Advertisement putting demonstrating data in the present embodiment can comprise advertisement putting and represent daily record.Advertisement putting in a period of time scope (as month or a season or half a year even a year etc.) can be represented the basic data of daily record as colleague location by the present embodiment.
S110, determine the degree of correlation in above-mentioned multiple client between two between client according to client's advertisement delivery effect information.
Concrete, the advertisement delivery effect information in the present embodiment can be the sorting position of client in same ad queue, also can be ad click rate, can also comprise the sorting position of client in same ad queue and ad click rate simultaneously.Certainly, advertisement delivery effect information can also for reflecting other information of advertisement delivery effect.
An object lesson of the degree of correlation determined in above-mentioned multiple client between two between client according to client's advertisement delivery effect information of the present embodiment is: for the client's first occurred in the Search Results first page of same search keyword and client's second simultaneously, the single degree of correlation between client's first and client's second is determined according to the sorting position of client's first in ad queue and the sorting position of client's second in ad queue, after the multiple single degrees of correlation (the single degree of correlation as obtained all client's first in certain month or in certain season and the single degree of correlation between client's second or acquisition reaches pre-determined number) utilizing such method to obtain between client's first and client's second, the degree of correlation between client's first and client's second is calculated based on all single degrees of correlation obtained, as can using the aggregate-value of all single degrees of correlation as the degree of correlation etc. between client's first and client's second.
Another object lesson of the degree of correlation determined in above-mentioned multiple client between two between client according to client's advertisement delivery effect information of the present embodiment is: for the client's first occurred in the Search Results first page of same search keyword and client's second simultaneously, the single degree of correlation between client's first and client's second is determined according to the ad click rate of client's first and the ad click rate of client's second, after the multiple single degrees of correlation (the single degree of correlation as obtained all client's first in certain month or in certain season and the single degree of correlation between client's second or acquisition reaches pre-determined number) utilizing such method to obtain between client's first and client's second, the degree of correlation between client's first and client's second is calculated based on all single degrees of correlation obtained, as can using the aggregate-value of all single degrees of correlation as the degree of correlation etc. between client's first and client's second.
Another object lesson of the degree of correlation determined in above-mentioned multiple client between two between client according to client's advertisement delivery effect information of the present embodiment is: for the client's first occurred in the Search Results first page of same search keyword and client's second simultaneously, the single degree of correlation between client's first and client's second is determined according to sorting position in ad queue of the sorting position of client's first in ad queue and client's second and the ad click rate of client's first and the ad click rate of client's second, after the multiple single degrees of correlation (the single degree of correlation as obtained all client's first in certain month or in certain season and the single degree of correlation between client's second or acquisition reaches pre-determined number) utilizing such method to obtain between client's first and client's second, the degree of correlation between client's first and client's second is calculated based on all single degrees of correlation obtained, as can using the aggregate-value of all single degrees of correlation as the degree of correlation etc. between client's first and client's second.
S120, the degree of correlation of basis between two between client build relative clients group, and determine the subgroup existed in relative clients group based on data mining.
Concrete, the relative clients group that the present embodiment builds can adopt the form of relative clients network to embody, and certainly, the customers that the present embodiment builds also can adopt other forms such as array or chained list to embody.The present embodiment does not limit the concrete manifestation form of relative clients group.
When relative clients mine massively embody by the form of relative clients network, a network node in relative clients network represents a client, and namely client is a network node in relative clients network; If there is line between two nodes in relative clients network, then represent, between the client that these two nodes are representative respectively, there is correlativity, and numeral corresponding to line between two nodes can for these two the internodal degrees of correlation utilizing above-mentioned steps to calculate; If there is not line between two nodes in relative clients network, then represent not there is correlativity between the client that these two nodes are representative respectively.
In the relative clients group of the present embodiment, the correlativity between a part of client may by force, but the correlativity between this portions of client and other clients can be more weak; Like this, the situation that there is multiple client subgroup (also can be called to there is multiple custom partitioning) may be presented in relative clients group, between (namely in group) client, there is higher correlativity in subgroup, namely there is higher condensation degree, and between client across subgroup (namely across group), there is lower correlativity, namely there is lower condensation degree.The present embodiment can utilize existing data mining technology to find the subgroup that exists in relative clients group.
The present embodiment determines that based on data mining one of the subgroup existed in relative clients group concrete example is: when relative clients mine massively embody by the form of relative clients network, subgroup is the corporations existed in relative clients network; The present embodiment can excavate according to existing community discovery algorithm the corporations existed in relative clients network; Afterwards, in order to ensure the reliability of the corporations of aforementioned discovery, can detect the condensation degree of community structure, if detect that the condensation degree of community structure does not meet predetermined coherence condition, then can dismiss such corporations, if detect that the condensation degree of community structure meets predetermined coherence condition, then can retain such corporations.The condensation degree of the community structure in this object lesson can utilize based on the degree of correlation between the client of corporations inside corresponding algorithm to calculate and obtain.Whether the condensation degree of specific implementation process and detection community structure that this object lesson does not limit community discovery algorithm meets the specific implementation of predetermined coherence condition.
The present embodiment determines that based on data mining another the concrete example of the subgroup existed in relative clients group is: when relative clients mine massively embody by the form of relative clients network, subgroup is the corporations existed in relative clients network; The present embodiment can excavate according to existing community discovery algorithm the corporations existed in relative clients network; Afterwards, not excessive in order to ensure the scale of the corporations of aforementioned discovery, the customer quantity that corporations comprise can be detected, if the customer quantity that these corporations comprise does not exceed intended client threshold value, then can retain these corporations, if the customer quantity that these corporations comprise exceedes intended client threshold value, then can using these corporations as current relative clients network, and the corporations existed in current relative clients network are again excavated according to community discovery algorithm, afterwards, the step that the above-mentioned customer quantity comprised corporations detects is turned back to.This shows, in this object lesson, to there is an iterative process, by utilizing this iterative process, each corporations finally remained can be made all to comprise the client of fair amount.This object lesson does not limit the specific implementation process of community discovery algorithm.
The present embodiment determines that based on data mining another the concrete example of the subgroup existed in relative clients group is: when relative clients mine massively embody by the form of relative clients network, subgroup is the corporations existed in relative clients network, the present embodiment can excavate according to existing community discovery algorithm the corporations existed in relative clients network, afterwards, in order to ensure the reliability of the corporations of aforementioned discovery, can detect the condensation degree of community structure, if detect that the condensation degree of community structure does not meet predetermined coherence condition, then can dismiss these corporations, if detect that the condensation degree of certain community structure meets predetermined coherence condition, then can detect the customer quantity comprised in these corporations further, if the customer quantity that these corporations comprise does not exceed intended client threshold value, then can retain these corporations, if the customer quantity that these corporations comprise exceedes intended client threshold value, then can using these corporations as current relative clients network, and the corporations existed in current relative clients network are again excavated according to existing community discovery algorithm, afterwards, turn back to the above-mentioned step that the condensation degree of community structure is detected.Can finding out, in this object lesson, to there is an iterative process thus, by utilizing this iterative process, the corporations finally remained can be made all to have higher condensation degree and all comprise the client of fair amount.The condensation degree of the community structure in this object lesson can utilize based on the degree of correlation between the client of corporations inside corresponding algorithm to calculate and obtain.This object lesson does not limit the specific implementation process of community discovery algorithm and detects the specific implementation whether community structure condensation degree meet predetermined coherence condition.
The present embodiment only can perform for the corporations at certain specific client place the operation that above-mentioned community structure condensation degree detects and corporations internal customer quantity controls, and the present embodiment also can perform the operation that above-mentioned community structure condensation degree detects and corporations internal customer quantity controls for all corporations in relative clients network.
S130, according to advertisement putting operational indicator determine in subgroup mark post colleague.
Concrete, the advertisement putting operational indicator in the present embodiment can comprise: at least one in advertisement putting consumption Input factors, the ad quality factor, the advertising conversion factor and the Website quality factor.
The present embodiment more meets the objects such as the concern direction of client to make the mark post colleague oriented, can determine in the process that the mark post in subgroup is gone together, further consider that advertisement putting client pays close attention to information, specifically, the concern direction of different advertisement putting clients may be different, in the process of the colleague of positioning mark pole from subgroup, the party mark post colleague upwards can be oriented respectively for the concern direction of different advertisement putting client; That is, the present embodiment first can be paid close attention to information according to advertisement putting client and pick out from subgroup and meet the client that advertisement putting client pays close attention to direction, then, from the client that these are picked out, orient mark post colleague according to advertisement putting operational indicator again, thus the mark post oriented colleague more can meet the concern direction of advertisement putting client.Advertisement putting client in the present embodiment pays close attention to information can comprise advertisement putting scene, also can comprise and be concerned customer type, can also comprise advertisement putting scene simultaneously and be concerned customer type.Advertisement putting client pays close attention to information and normally wishes to know what the information of certain type customer carried out arranging for client.
Advertisement putting scene in the present embodiment can comprise: search is promoted scene, wireless popularization scene and net alliance and promoted scene etc.; Being concerned customer type and can comprising in the present embodiment: equal scale of operation client and industry-leading client etc.Advertisement putting scene in the present embodiment can change along with promoting the change of scene in the future thereupon, in like manner, is concerned customer type and also can changes along with the change of advertisement putting client focus thereupon.
The present embodiment is in the process carrying out positioning mark pole colleague according to advertisement putting operational indicator, and the advertisement putting operational indicator used for different advertisement putting scenes can not be identical; Such as, promote scene for search, advertisement putting operational indicator can select advertisement putting to consume Input factors (promoting consumption accounting etc. as search popularization consumption or search), the ad quality factor (as ad click rate etc.) and the advertising conversion factor (as business's bridge consulting amount and/or off-line treasured phone amount etc.); Again such as, for wireless popularization scene, advertisement putting operational indicator can select advertisement putting to consume Input factors (as wireless popularization consumption or wireless popularization consumption accounting etc.), the ad quality factor (as ad click rate etc.) and the Website quality factor (rate and/or website average access duration etc. are jumped out in ad click turnover rate and/or website); Again such as, for net, alliance promotes scene, and advertisement putting operational indicator can select advertisement putting to consume Input factors (as the popularization consumption of net alliance or net alliance promote consumption accounting etc.) and the ad quality factor (as ad click rate etc.).The present embodiment also can consider the contents such as the sorting position of client in each ad queue in the process carrying out positioning mark pole colleague according to advertisement putting operational indicator, such as, after being normalized advertisement putting operational indicator and sorting position etc., utilize the modes such as weighted scoring to determine that mark post is gone together.The present embodiment does not limit the specific implementation process determining that mark post is gone together.
The present embodiment can only perform for the corporations at certain specific client place above-mentionedly determines the operation that mark post is gone together; The present embodiment also above-mentionedly for all corporations execution in relative clients network can determine the operation that mark post is gone together.
In addition, the present embodiment, can based on mark post colleague further for client provides valuable reference information, as provided the reference information that can improve its investment in advertising strategy for client after determining mark post colleague.The present embodiment is not restricted to the particular content of the reference information that client provides.
Embodiment two, colleague's localization method.
The present embodiment carries out analysis build competition network (i.e. above-mentioned relative clients network) by representing large data (as advertisement putting represents daily record) to advertisement putting, then, competition son group (i.e. corporations) residing for location client, afterwards, and customer type can be concerned the client in competition group is further become more meticulous differentiations based on different advertisement putting scenes, finally can excavate a small amount of mark post that client pays close attention to most and go together (i.e. mark post client); Further, the mark post oriented synchronously can bring the information of reference value for other clients, as the advertisement promotion scheme that the advertisement promotion scheme by analyzing client self and mark post are gone together, advertisement promotion scheme Problems existing and the weak point of client self can be found, thus the perfect further of the advertisement promotion scheme of client can be realized.
In Fig. 2, first, from the daily record of phoenix nest showing advertisement, obtain recent showing advertisement data (the showing advertisement data as in month), and build competition network according to the recent showing advertisement data obtained.Concrete, when the advertisement promotion information of two clients represents (namely representing on the same stage) in same Search Results, represent that these two clients there occurs once to compete (namely these two clients are correlated with), the present embodiment can based on the position of these two clients in ad queue and this competition intensity of ad click rate COMPREHENSIVE CALCULATING (namely above-mentioned single degree of correlation), this competition intensity that in accumulative one month, these two clients represent at every turn on the same stage, thus the competition intensity of these two clients can be obtained.
When two clients occur representing phenomenon on the same stage, can illustrate that two clients have purchased the keyword of basic simlarity, thus when being searched for by a certain keyword, trigger the advertisement that this two clients throw in; In addition, two clients can also be further illustrated and all thrown in advertisement in identical region, thus trigger by a certain keyword the advertisement that this two clients throw in when same region is searched for; Further, can also further illustrate, the advertisement that two clients throw in has the identical time period, thus triggers by a certain keyword the advertisement that this two clients throw in when searching for sometime simultaneously.
The present embodiment, in colleague's position fixing process, represents by using the competition intensity measured between client on the same stage, for the accuracy significantly improving colleague location provides guarantee.
Afterwards, community discovery operation is carried out for competition network.Concrete, community discovery algorithm (as Louvain community discovery algorithm) can be used to excavate the corporations existed in competition network, and the parameters such as modularity Q index (corresponding above-mentioned condensation degree) can be passed through the corporations excavated are assessed, to determine whether dismiss corporations, meanwhile, can also determine whether according to the customer quantity comprised in corporations carrying out the excavation of further corporations to corporations.Being between the client in same corporations is opponent firm mutually, and the client in same corporations can form opponent firm's list.
Finally, from opponent firm, find out mark post colleague.Concrete, the advertisement putting scene information of opponent firm can be obtained, such as, from phoenix nest database and net alliance database, obtain the advertisement putting scene information of opponent firm; Afterwards, according to advertisement putting scene information judge opponent firm be belong to search promote, still belong to wireless popularization, also or belong to net alliance promote, namely judge opponent firm whether have search for promotional features, wireless promotional features and/or network promotion feature; Opponent firm for above-mentioned acquisition throws in scene information and advertisement putting client focus (namely advertisement putting client pays close attention to information) based on advertising business and to become more meticulous further differentiation to opponent firm, and from all kinds of opponent firms after differentiation, selects a small amount of top-tier customer (as 5) respectively go together as mark post; Thus the present embodiment can obtain the mark post colleague of 6 types as shown in Figure 3, namely go together based on searching for the optimum mark post of the same industry promoted under scene, based on the same scale optimum mark post colleague under search popularization scene, based on the same industry optimum mark post colleague under wireless popularization scene, based on the same scale optimum mark post colleague under wireless popularization scene, go together based on the optimum mark post of the same industry under net alliance popularization scene and promote the same scale optimum mark post colleague under scene based on net alliance.The mark post colleague of six types that the present embodiment is finally determined is the mark post colleague of other clients in its place corporations, the mark post colleague that information determines its corresponding types can be paid close attention to according to the advertisement putting client of other clients, by comparing the advertisement promotion scheme that other clients mark post corresponding with it is gone together, the weak point existing for advertisement promotion scheme of other clients can be found out, be conducive to the advertisement promotion scheme improving other clients, as the advertisement marketing scheme etc. of optimization can be generated for other clients.
Embodiment three, colleague's locating device.The structure of this device as shown in Figure 4.
In Fig. 4, colleague's locating device mainly comprises: determine Client Model 400, determine degree of correlation module 410, determine customers and subgroup module 420 and determine mark post colleague module 430.
Determine that Client Model 400 is mainly suitable for determining according to advertisement putting demonstrating data multiple clients of occurring in same Search Results.
Concrete, determine that advertisement putting demonstrating data that Client Model 400 uses refers to the information of the concrete condition of the advertisement putting that network side shows to user, such as, user inputs keyword in the search column of its search engine client, network side is after the keyword receiving user's input, corresponding search result information is built according to keyword, and search result information is pushed to search engine client, search result information is shown to user by search engine client, in this search procedure, advertisement putting demonstrating data derives from the search result information that network side builds.The search result information quantity at network side being this search structure of user is more, when needing to use multipage Pagination Display, determine the search result information belonging to first page that advertisement putting demonstrating data that Client Model 400 uses can derive from network side and builds, as determine Client Model 400 the advertisement putting demonstrating data that uses derive from all advertising messages belonged in first page that network side builds.
Determine that advertisement putting demonstrating data that Client Model 400 uses can comprise advertisement putting and represent daily record.Determine that the advertisement putting in a period of time scope (as month or a season or half a year even a year etc.) can be represented the basic data of daily record as colleague location by Client Model 400.
Determine that degree of correlation module 410 is mainly suitable for the degree of correlation determining in multiple client between two between client according to client's advertisement delivery effect information.
Concrete, determine that the advertisement delivery effect information that degree of correlation module 410 uses can be the sorting position of client in same ad queue, also can be ad click rate, the sorting position of client in same ad queue and ad click rate can also be comprised simultaneously.Certainly, degree of correlation module 410 uses as advertisement delivery effect information can to reflect that other information of advertisement delivery effect also can be determined.
Determine that an object lesson of the degree of correlation that degree of correlation module 410 is determined in above-mentioned multiple client between two between client according to client's advertisement delivery effect information is: for the client's first occurred in the Search Results first page of same search keyword and client's second simultaneously, determine that degree of correlation module 410 determines the single degree of correlation between client's first and client's second according to the sorting position of client's first in ad queue and the sorting position of client's second in ad queue, after the multiple single degrees of correlation (the single degree of correlation as obtained all client's first in certain month or in certain season and the single degree of correlation between client's second or acquisition reaches pre-determined number) utilizing such method to obtain between client's first and client's second, determine that degree of correlation module 410 calculates the degree of correlation between client's first and client's second based on all single degrees of correlation obtained, as determined, degree of correlation module 410 can using the aggregate-value of all single degrees of correlation as the degree of correlation etc. between client's first and client's second.
Determine that another object lesson of the degree of correlation that degree of correlation module 410 is determined in above-mentioned multiple client between two between client according to client's advertisement delivery effect information is: for the client's first occurred in the Search Results first page of same search keyword and client's second simultaneously, determine that degree of correlation module 410 determines the single degree of correlation between client's first and client's second according to the ad click rate of the ad click rate of client's first and client's second, after the multiple single degrees of correlation (the single degree of correlation as obtained all client's first in certain month or in certain season and the single degree of correlation between client's second or acquisition reaches pre-determined number) utilizing such method to obtain between client's first and client's second, determine that degree of correlation module 410 calculates the degree of correlation between client's first and client's second based on all single degrees of correlation obtained, as determined, degree of correlation module 410 can using the aggregate-value of all single degrees of correlation as the degree of correlation etc. between client's first and client's second.
Determine that another object lesson of the degree of correlation that degree of correlation module 410 is determined in above-mentioned multiple client between two between client according to client's advertisement delivery effect information is: for the client's first occurred in the Search Results first page of same search keyword and client's second simultaneously, determine that degree of correlation module 410 determines the single degree of correlation between client's first and client's second according to sorting position in ad queue of the sorting position of client's first in ad queue and client's second and the ad click rate of client's first and the ad click rate of client's second, after the multiple single degrees of correlation (the single degree of correlation as obtained all client's first in certain month or in certain season and the single degree of correlation between client's second or acquisition reaches pre-determined number) utilizing such method to obtain between client's first and client's second, determine that degree of correlation module 410 calculates the degree of correlation between client's first and client's second based on all single degrees of correlation obtained, as determined, degree of correlation module 410 can using the aggregate-value of all single degrees of correlation as the degree of correlation etc. between client's first and client's second.
Determine that customers and subgroup module 420 are mainly suitable for building relative clients group according to the degree of correlation between two between client, and determine the subgroup existed in relative clients group based on data mining.
Concrete, determine that the relative clients group that customers and subgroup module 420 build can adopt the form of relative clients network to embody, certainly, determine that the customers that customers and subgroup module 420 build also can adopt other forms such as array or chained list to embody.The present embodiment does not limit the concrete manifestation form determining the relative clients group that customers and subgroup module 420 build.
When determining customers and subgroup module 420 adopts the form of relative clients network to embody relative clients group, a network node in relative clients network represents a client, and namely client is a network node in relative clients network; If there is line between two nodes in relative clients network, then represent, between the client that these two nodes are representative respectively, there is correlativity, and numeral corresponding to line between two nodes can for these two the internodal degrees of correlation utilizing above-mentioned steps to calculate; If there is not line between two nodes in relative clients network, then represent not there is correlativity between the client that these two nodes are representative respectively.
Determine that correlativity between a part of client in customers and the relative clients group constructed by subgroup module 420 may by force, but the correlativity between this portions of client and other clients can be more weak; Like this, the situation that there is multiple client subgroup (also can be called to there is multiple custom partitioning) may be presented in relative clients group, between (namely in group) client, there is higher correlativity in subgroup, namely there is higher condensation degree, and between client across subgroup (namely across group), there is lower correlativity, namely there is lower condensation degree.Determine that customers and subgroup module 420 can utilize existing data mining technology to find the subgroup that exists in relative clients group.
Determine that customers and subgroup module 420 determine that based on data mining one of the subgroup existed in relative clients group concrete example is: when determining that customers and subgroup module 420 adopt the form of relative clients network to embody relative clients group, subgroup is the corporations existed in relative clients network; Determine that customers and subgroup module 420 can excavate according to existing community discovery algorithm the corporations existed in relative clients network; Afterwards, in order to ensure the reliability of the corporations of aforementioned discovery, determine that customers and subgroup module 420 can detect the condensation degree of community structure, if detect that the condensation degree of community structure does not meet predetermined coherence condition, then determine that customers and subgroup module 420 can dismiss such corporations, if detect that the condensation degree of community structure meets predetermined coherence condition, then determine that customers and subgroup module 420 can retain such corporations.The condensation degree of the community structure in this object lesson can utilize based on the degree of correlation between the client of corporations inside corresponding algorithm to calculate and obtain.This object lesson does not limit the specific implementation process of determining the community discovery algorithm that customers and subgroup module 420 adopt and determines whether condensation degree that customers and subgroup module 420 detect community structure meets the specific implementation of predetermined coherence condition.
Determine that customers and subgroup module 420 determine that based on data mining another the concrete example of the subgroup existed in relative clients group is: when determining that customers and subgroup module 420 adopt the form of relative clients network to embody relative clients group, subgroup is the corporations existed in relative clients network, determine that customers and subgroup module 420 can excavate according to existing community discovery algorithm the corporations existed in relative clients network, afterwards, not excessive in order to ensure the scale of the corporations determining customers and the current discovery of subgroup module 420, determine that customers and subgroup module 420 can detect the customer quantity that corporations comprise, if the customer quantity that these corporations comprise does not exceed intended client threshold value, then determine that customers and subgroup module 420 can retain these corporations, if the customer quantity that these corporations comprise exceedes intended client threshold value, then determine that customers and subgroup module 420 can using these corporations as current relative clients networks, and the corporations existed in current relative clients network are again excavated according to community discovery algorithm, afterwards, turn back to the step that the above-mentioned customer quantity determining that customers and subgroup module 420 pairs of corporations comprise detects.This shows, in the above-mentioned implementation determining customers and subgroup module 420, there is an iterative process, determining that customers and subgroup module 420 are by utilizing this iterative process, can make each corporations finally remained all comprise the client of fair amount.This object lesson does not limit the specific implementation process determining the community discovery algorithm that customers and subgroup module 420 adopt.
Determine that customers and subgroup module 420 determine that based on data mining another the concrete example of the subgroup existed in relative clients group is: when determining that customers and subgroup module 420 adopt the form of relative clients network to embody relative clients group, subgroup is the corporations existed in relative clients network, determine that customers and subgroup module 420 can excavate according to existing community discovery algorithm the corporations existed in relative clients network, afterwards, in order to ensure the reliability of the corporations of aforementioned discovery, determine that customers and subgroup module 420 can detect the condensation degree of community structure, if detect that the condensation degree of community structure does not meet predetermined coherence condition, then determine that customers and subgroup module 420 can dismiss these corporations, if detect that the condensation degree of certain community structure meets predetermined coherence condition, then determine that customers and subgroup module 420 can detect the customer quantity comprised in these corporations further, if the customer quantity that these corporations comprise does not exceed intended client threshold value, then determine that customers and subgroup module 420 can retain these corporations, if the customer quantity that these corporations comprise exceedes intended client threshold value, then determine that customers and subgroup module 420 can using these corporations as current relative clients networks, and the corporations existed in current relative clients network are again excavated according to existing community discovery algorithm, afterwards, determine the step that the condensation degree that customers and subgroup module 420 turn back to above-mentioned all clients to corporations inside detects.Can find out thus, in the implementation determining customers and subgroup module 420, there is an iterative process, determining that customers and subgroup module 420 are by utilizing this iterative process, can make the corporations finally remained all have higher condensation degree and all comprise the client of fair amount.The condensation degree of the community structure in this object lesson can utilize based on the degree of correlation between the client of corporations inside corresponding algorithm to calculate and obtain.This object lesson does not limit the specific implementation process of determining the community discovery algorithm that customers and subgroup module 420 adopt and determines whether condensation degree that customers and subgroup module 420 detect community structure meets the specific implementation of predetermined coherence condition.
Determine that customers and subgroup module 420 only can perform the condensation degree detection of above-mentioned community structure and the operation of corporations internal customer quantity control for the corporations at certain specific client place, determine that customers and subgroup module 420 also can perform the operation that condensation degree detects and corporations internal customer quantity controls of above-mentioned community structure for all corporations in relative clients network.
Determine that mark post colleague module 430 is mainly suitable for the mark post colleague determined according to advertisement putting operational indicator in subgroup.
Concrete, determine that the advertisement putting operational indicator that mark post colleague module 430 adopts can specifically comprise: at least one in advertisement putting consumption Input factors, the ad quality factor, the advertising conversion factor and the Website quality factor.
Determine that mark post colleague module 430 more meets the objects such as the concern direction of client to make the mark post colleague oriented, can determine in the process that the mark post in subgroup is gone together, further consider that advertisement putting client pays close attention to information, specifically, the concern direction of different advertisement putting clients may be different, in the process determining mark post colleague module 430 positioning mark pole colleague from subgroup, determine that mark post colleague module 430 can orient the party's mark post colleague (one or more) upwards respectively for the concern direction of different advertisement putting client; That is, determine that mark post colleague module 430 first can be paid close attention to information according to advertisement putting client and pick out from subgroup and meet the client that advertisement putting client pays close attention to direction, then, determine that mark post colleague module 430 orients mark post colleague according to advertisement putting operational indicator again from the client that these are picked out, thus determine that the mark post colleague that mark post colleague module 430 is oriented more can meet the concern direction of advertisement putting client.Determine that the advertisement putting client that adopts of mark post colleague module 430 pays close attention to information and can comprise advertisement putting scene, also can comprise and be concerned customer type, advertisement putting scene can also be comprised simultaneously and be concerned customer type.Determine that the advertisement putting client that adopts of mark post colleague module 430 pays close attention to information and normally wishes to know what the information of certain type customer carried out arranging for client.
Determine that the advertisement putting scene that mark post colleague module 430 adopts can comprise: search is promoted scene, wireless popularization scene and net alliance and promoted scene etc.; That determines that mark post colleague module 430 adopts is concerned customer type and can comprises: equal scale of operation client and industry-leading client etc.Determine that the advertisement putting scene that mark post colleague module 430 adopts can change along with promoting the change of scene in the future thereupon, in like manner, that determines that mark post colleague module 430 adopts is concerned customer type and also can changes along with the change of advertisement putting client focus thereupon.
Determine that mark post colleague module 430 is in the process carrying out positioning mark pole colleague according to advertisement putting operational indicator, the advertisement putting operational indicator used for different advertisement putting scene determination mark posts colleague module 430 can not be identical; Such as, promote scene for search, determine that mark post colleague module 430 can select advertisement putting consumption Input factors (as consumption or search popularization consumption accounting etc. are promoted in search), the ad quality factor (as ad click rate etc.) and the advertising conversion factor (as business's bridge consulting amount and/or the precious phone amount of off-line etc.) as advertisement putting operational indicator; Again such as, for wireless popularization scene, determine that mark post colleague module 430 can select advertisement putting to consume Input factors (as wireless popularization consumption or wireless popularization consumption accounting etc.), the ad quality factor (as ad click rate etc.) and the Website quality factor (rate and/or website average access duration etc. are jumped out in ad click turnover rate and/or website) as advertisement putting operational indicator; Again such as, for net, alliance promotes scene, determines that mark post colleague module 430 can select advertisement putting consumption Input factors (as net alliance promotes consumption or net alliance popularization consumption accounting etc.) and the ad quality factor (as ad click rate etc.) as advertisement putting operational indicator.Determine that mark post colleague module 430 also can consider the contents such as the sorting position of client in each ad queue in the process carrying out positioning mark pole colleague according to advertisement putting operational indicator, such as, determine that mark post colleague module 430 is by after being normalized advertisement putting operational indicator and sorting position etc., utilizes the modes such as weighted scoring to determine that mark post is gone together.The present embodiment does not limit determines that mark post colleague module 430 determines the specific implementation process that mark post is gone together.
Determine that mark post colleague module 430 can only perform for the corporations at certain specific client place and above-mentionedly determine the operation that mark post is gone together; Determine that mark post colleague module 430 also above-mentionedly for all corporations execution in relative clients network can determine the operation that mark post is gone together.
In addition, determine that mark post colleague module 430 is after determining mark post colleague, can based on mark post colleague further for client provide valuable reference information, as determined, mark post colleague module 430 can provide the reference information that can improve its investment in advertising strategy for client.The present embodiment does not limit the particular content determining the reference information that mark post colleague module 430 provides for client.
Embodiment four, computer equipment.
This computer equipment can be the calculating unit of single computer, multiple stage computing machine composition, single network server, the server group of multiple webserver composition or the cloud be made up of a large amount of computing machine/webserver based on cloud computing.The computer equipment of the present embodiment comprises the colleague's locating device described in above-described embodiment three, no longer describes in detail at this.
It should be noted that the present invention can be implemented in the assembly of software and/or software restraint, such as, special IC (ASIC), general object computing machine or any other similar hardware device can be adopted to realize.In one embodiment, software program of the present invention can perform to realize step mentioned above or function by processor.Similarly, software program of the present invention (comprising relevant data structure) can be stored in computer readable recording medium storing program for performing, such as, and RAM storer, magnetic or CD-ROM driver or flexible plastic disc and similar devices.In addition, steps more of the present invention or function can adopt hardware to realize, such as, as coordinating with processor thus performing the circuit of each step or function.
In addition, a part of the present invention can be applied to computer program, such as computer program instructions, when it is performed by computing machine, by the operation of this computing machine, can call or provide according to method of the present invention and/or technical scheme.And call the programmed instruction of method of the present invention, may be stored in fixing or moveable recording medium, and/or be transmitted by the data stream in broadcast or other signal bearing medias, and/or be stored in the working storage of the computer equipment run according to described programmed instruction.At this, comprise a device according to one embodiment of present invention, this device comprises the storer for storing computer program instructions and the processor for execution of program instructions, wherein, when this computer program instructions is performed by this processor, trigger this plant running based on the aforementioned method according to multiple embodiment of the present invention and/or technical scheme.
To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned one exemplary embodiment, and when not deviating from spirit of the present invention or essential characteristic, the present invention can be realized in other specific forms.Therefore, no matter from which point, all should embodiment be regarded as exemplary, and be nonrestrictive, scope of the present invention is limited by claims instead of above-mentioned explanation, and all changes be therefore intended in the implication of the equivalency by dropping on claim and scope are included in the present invention.Any Reference numeral in claim should be considered as the claim involved by limiting.In addition, obviously " comprising " one word do not get rid of other unit or step, odd number does not get rid of plural number.Multiple unit of stating in system claims or device also can be realized by software or hardware by a unit or device.First, second word such as grade is used for representing title, and does not represent any specific order.
Claims (19)
1. colleague's localization method, comprising:
The multiple clients occurred in same Search Results are determined according to advertisement putting demonstrating data;
The degree of correlation in described multiple client between two between client is determined according to client's advertisement delivery effect information;
Build relative clients group according to described degree of correlation between two between client, and determine the subgroup existed in described relative clients group based on data mining;
The mark post colleague in described subgroup is determined according to advertisement putting operational indicator.
2. method according to claim 1, wherein, describedly determine that the multiple clients occurred in same Search Results comprise according to advertisement putting demonstrating data:
The all clients occurred in the first page of same Search Results are determined according to advertisement putting demonstrating data.
3. method according to claim 1, wherein, described advertisement delivery effect information comprises: the sorting position of client in same ad queue and/or ad click rate.
4. method according to claim 1, wherein, describedly determine that the degree of correlation in described multiple client between two between client comprises according to client's advertisement delivery effect information:
For Search Results each time, all determine the single degree of correlation in described multiple client between two between client according to the advertisement delivery effect information of client;
According to the multiple single degree of correlation within the scope of the schedule time or determine the degree of correlation in described multiple client between two between client according to the single degree of correlation of predetermined quantity.
5. method according to claim 1, wherein, described relative clients group is relative clients network; And describedly determine that the subgroup existed in described relative clients group comprises based on data mining:
The corporations existed in described relative clients network are excavated according to community discovery algorithm;
Detect the condensation degree of described corporations, and dismiss the corporations that condensation degree does not meet predetermined coherence condition.
6. method according to claim 5, wherein, describedly determine that the subgroup existed in described relative clients group also comprises based on data mining:
Exceed the corporations of intended client threshold value for customer quantity, excavate the corporations existed in group according to community discovery algorithm.
7. the method according to claim arbitrary in claim 1 to 6, the wherein said mark post colleague determined in described subgroup according to advertisement putting operational indicator comprises:
Determine in described subgroup, to meet the mark post colleague that advertisement putting client pays close attention to information according to advertisement putting operational indicator; Wherein, described advertisement putting client pays close attention to information and comprises: advertisement putting scene and/or be concerned customer type.
8. method according to claim 7, wherein: described advertisement putting scene comprises: search is promoted scene, wireless popularization scene and net alliance and promoted scene; And/or, described in be concerned customer type and comprise: equal scale of operation client and industry-leading client.
9. method according to claim 8, wherein:
Promote scene for search, described advertisement putting operational indicator comprises: advertisement putting consumption Input factors, the ad quality factor and the advertising conversion factor;
For wireless popularization scene, described advertisement putting operational indicator comprises: advertisement putting consumption Input factors, the ad quality factor and the Website quality factor;
For net, alliance promotes scene, and described advertisement putting operational indicator comprises: advertisement putting consumption Input factors and the ad quality factor.
10. colleague's locating device, comprising:
Determine Client Model, be suitable for determining according to advertisement putting demonstrating data multiple clients of occurring in same Search Results;
Determine degree of correlation module, be suitable for the degree of correlation determining in described multiple client between two between client according to client's advertisement delivery effect information;
Determine customers and subgroup module, be suitable for building relative clients group according to described degree of correlation between two between client, and determine the subgroup existed in described relative clients group based on data mining;
Determine mark post colleague module, be suitable for the mark post colleague determined according to advertisement putting operational indicator in described subgroup.
11. devices according to claim 10, wherein, describedly determine that Client Model is specifically suitable for: determine all clients occurred in the first page of same Search Results according to advertisement putting demonstrating data.
12. devices according to claim 10, wherein, described advertisement delivery effect information comprises: the sorting position of client in same ad queue and/or ad click rate.
13. devices according to claim 10, wherein, describedly determine that degree of correlation module is specifically suitable for: for Search Results each time, all determine the single degree of correlation in described multiple client between two between client according to the advertisement delivery effect information of client; According to the multiple single degree of correlation within the scope of the schedule time or determine the degree of correlation in described multiple client between two between client according to the single degree of correlation of predetermined quantity.
14. devices according to claim 10, wherein, described relative clients group is relative clients network; And describedly determine that customers and subgroup module are specifically suitable for: the corporations existed in described relative clients network are excavated according to community discovery algorithm; Detect the condensation degree of described corporations, and dismiss the corporations that condensation degree does not meet predetermined coherence condition.
15. devices according to claim 14, wherein, describedly determine that customers and subgroup module are specifically suitable for: the corporations exceeding intended client threshold value for customer quantity, excavate the corporations existed in group according to community discovery algorithm.
16. according to claim 10 to the device described in arbitrary claim in 15, wherein saidly determines that mark post colleague module is specifically suitable for:
Determine in described subgroup, to meet the mark post colleague that advertisement putting client pays close attention to information according to advertisement putting operational indicator; Wherein, described advertisement putting client pays close attention to information and comprises: advertisement putting scene and/or be concerned customer type.
17. devices according to claim 16, wherein: described advertisement putting scene comprises: search is promoted scene, wireless popularization scene and net alliance and promoted scene; And/or, described in be concerned customer type and comprise: equal scale of operation client and industry-leading client.
18. devices according to claim 17, wherein:
Promote scene for search, described advertisement putting operational indicator comprises: advertisement putting consumption Input factors, the ad quality factor and the advertising conversion factor;
For wireless popularization scene, described advertisement putting operational indicator comprises: advertisement putting consumption Input factors, the ad quality factor and the Website quality factor;
For net, alliance promotes scene: described advertisement putting operational indicator comprises: advertisement putting consumption Input factors and the ad quality factor.
19. 1 kinds of computer equipments, comprise the colleague's locating device in claim 10-18 described in arbitrary claim.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410740960.1A CN104503997B (en) | 2014-12-05 | 2014-12-05 | Colleague's localization method, device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410740960.1A CN104503997B (en) | 2014-12-05 | 2014-12-05 | Colleague's localization method, device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104503997A true CN104503997A (en) | 2015-04-08 |
| CN104503997B CN104503997B (en) | 2017-12-26 |
Family
ID=52945395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410740960.1A Active CN104503997B (en) | 2014-12-05 | 2014-12-05 | Colleague's localization method, device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104503997B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017092601A1 (en) * | 2015-12-04 | 2017-06-08 | 阿里巴巴集团控股有限公司 | Data processing method and device |
| CN108734493A (en) * | 2017-04-20 | 2018-11-02 | 腾讯科技（北京）有限公司 | A kind of advertisement orientation launches control method, monitoring method and device |
| CN109325791A (en) * | 2017-07-31 | 2019-02-12 | 北京国双科技有限公司 | A kind of SEM advertisement competition analysis method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080071767A1 (en) * | 2006-08-25 | 2008-03-20 | Semdirector, Inc. | System and method for measuring the effectiveness of an on-line advertisement campaign |
| CN102194149A (en) * | 2010-03-01 | 2011-09-21 | 中国人民解放军国防科学技术大学 | Community discovery method |
| CN104077290A (en) * | 2013-03-26 | 2014-10-01 | 腾讯科技（深圳）有限公司 | Method and device for generating promoted accounts |
-
2014
- 2014-12-05 CN CN201410740960.1A patent/CN104503997B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080071767A1 (en) * | 2006-08-25 | 2008-03-20 | Semdirector, Inc. | System and method for measuring the effectiveness of an on-line advertisement campaign |
| CN102194149A (en) * | 2010-03-01 | 2011-09-21 | 中国人民解放军国防科学技术大学 | Community discovery method |
| CN104077290A (en) * | 2013-03-26 | 2014-10-01 | 腾讯科技（深圳）有限公司 | Method and device for generating promoted accounts |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017092601A1 (en) * | 2015-12-04 | 2017-06-08 | 阿里巴巴集团控股有限公司 | Data processing method and device |
| CN106844402A (en) * | 2015-12-04 | 2017-06-13 | 阿里巴巴集团控股有限公司 | Data processing method and device |
| CN106844402B (en) * | 2015-12-04 | 2020-08-28 | 阿里巴巴集团控股有限公司 | Data processing method and device |
| CN108734493A (en) * | 2017-04-20 | 2018-11-02 | 腾讯科技（北京）有限公司 | A kind of advertisement orientation launches control method, monitoring method and device |
| CN108734493B (en) * | 2017-04-20 | 2022-02-08 | 腾讯科技（北京）有限公司 | Advertisement targeted delivery control method, monitoring method and device |
| CN109325791A (en) * | 2017-07-31 | 2019-02-12 | 北京国双科技有限公司 | A kind of SEM advertisement competition analysis method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104503997B (en) | 2017-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102205096B1 (en) | Transaction risk detection method and apparatus | |
| US10037607B2 (en) | Topology determination for non-overlapping camera network | |
| Heitz et al. | Heterogeneity of logistics facilities: an issue for a better understanding and planning of the location of logistics facilities | |
| CN106303955B (en) | For carrying out matched method and apparatus to hotspot and POI | |
| Liu et al. | Finding the optimal social trust path for the selection of trustworthy service providers in complex social networks | |
| CN103795613B (en) | Method for predicting friend relationships in online social network | |
| CN104050196A (en) | Point of interest (POI) data redundancy detection method and device | |
| CN107424043A (en) | A kind of Products Show method and device, electronic equipment | |
| CN105023165A (en) | Method, device and system for controlling release tasks in social networking platform | |
| US20150363700A1 (en) | Discovering Functional Groups of an Area | |
| CN108604347A (en) | The system and method that target for the Dynamic Geographic fence based on performance driving positions | |
| CN111949834A (en) | Site selection method and site selection platform | |
| US8896604B2 (en) | Producing optimization graphs in online advertising systems | |
| CN105956878A (en) | Network advertisement pushing method and network advertisement pushing device | |
| JP2014531649A (en) | Understand the effectiveness of communications propagated through social networking systems | |
| US20170126822A1 (en) | Determining Seeds for Targeted Notifications Through Online Social Networks in Conjunction with User Mobility Data | |
| CN104679864A (en) | Intelligent tracking method and intelligent tracking device for suspected target based on GIS (Geographic Information System) | |
| CN101986299A (en) | Multi-task personalized web service method based on hypergraph | |
| CN103745384A (en) | Method and device for providing information to user equipment | |
| US20140188607A1 (en) | Advertising exposure method based on event occurrence, server for performing the advertising exposure method, and computer-readable recording medium having recorded thereon program for executing the advertising exposure method | |
| CN111383051B (en) | Physical object addressing method, physical object addressing device, computing equipment and computer storage medium | |
| CN105260913A (en) | CTR estimation method and system, and DSP server used for Internet advertisement putting | |
| JP7285521B2 (en) | System and method for predicting similar mobile devices | |
| CN103207900B (en) | Position-based information provides the method and apparatus of inquiry solicited message to targeted customer | |
| TW201310986A (en) | Virtual advertising platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |