CN104361109A - Method and device for determining picture screening result - Google Patents
Method and device for determining picture screening result Download PDFInfo
- Publication number
- CN104361109A CN104361109A CN201410708056.2A CN201410708056A CN104361109A CN 104361109 A CN104361109 A CN 104361109A CN 201410708056 A CN201410708056 A CN 201410708056A CN 104361109 A CN104361109 A CN 104361109A
- Authority
- CN
- China
- Prior art keywords
- search
- information
- sequence
- picture
- represent
- 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
- 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
Abstract
The invention provides a method and device for determining a picture screening result. The method comprises the steps: selecting inquiry sequences of a predetermined number before the sequencing as a screening inquiry sequence according to a screening result of a plurality of inquiry sequences which are sequenced on the basis of heat degree information; determining corresponding search display picture information according to the screening inquiry sequence, and determining the display correlation information of the search display picture information based on the inquiry sequence; determining the picture screening result according to the display correlation information. Since the user attention of the screening inquiry sequence in recent time is guaranteed by the hot information, and the correlation between the search display picture information and the inquiry sequence is reflected by the display correlation information, the picture screening result screened on the basis of the hot information and the display correlation information meets the retrieve correlation requirement of a search engine and the user requirement. Furthermore, the screening and warehousing of high-quality picture data by the search engine on a vast data set can be reliably guaranteed.
Description
Technical field
The present invention relates to search engine technique field, specifically, the present invention relates to a kind of method and apparatus determining picture the selection result.
Background technology
Along with the development of Internet technology and the continuous expansion of information, people are more and more higher for the user demand of the network information, and search engine becomes the important tool that people obtain the network information.When after user input query sequence (query), the page be associated with this search sequence can be included in Search Results and return to user by search engine usually.
In prior art, search engine follows the tracks of link by spider to crawl into webpage, and the page data grabbed creeping is stored in search database.Because the page data grabbed by creeping becomes 10,000,000,000 ranks, therefore, the storage pressure of search engine memory device is huge, and safeguards that huge data also need to spend higher human cost, such as picture-type files etc. are comparatively large, even if it is more to use compression algorithm still to take storage; Meanwhile, the page data amount newly grabbed every day is also continuing to increase, but the storage resources of search engine memory device is limited, cannot unrestrictedly expand, and therefore, the storage capacity of search engine is subject to serious challenge.
Summary of the invention
In view of the above problems, propose the present invention to provide a kind of a kind of method determining picture the selection result overcoming the problems referred to above or solve the problem at least in part, comprising:
According to the ranking results sorted based on temperature information to multiple queries sequence, before choosing sequence, the search sequence of predetermined quantity is as screening search sequence;
Determine that corresponding search represents pictorial information according to screening search sequence, that determines to represent pictorial information based on the search of search sequence represents relevant information;
According to representing relevant information, determine picture the selection result.
Present invention also offers a kind of device determining picture the selection result, comprising:
Sequence determination module, for according to the ranking results sorted based on temperature information to multiple queries sequence, chooses the search sequence of the front predetermined quantity of sequence as screening search sequence;
Presenting information determination module, for determining that corresponding search represents pictorial information according to screening search sequence, that determines to represent pictorial information based on the search of search sequence represents relevant information;
Screening module, for according to representing relevant information, determines picture the selection result.
In the present embodiment, the search obtaining its correspondence according to the screening search sequence chosen based on temperature information represents pictorial information, to represent pictorial information and determines picture the selection result subsequently based on representing relevant information from search; User's attention rate of screening search sequence recent a period of time due to temperature information assurance, and represent relevant information and embody and search for the correlativity that represents between pictorial information and search sequence, therefore, based on temperature information and represent relevant information and screen correlation requirement and the user's request that the picture the selection result obtained meets search engine retrieving.Further, because picture the selection result is represent from other search of 10,000,000,000 data levels the pictorial information meeting predetermined preferred standard filtered out pictorial information, thus for search engine carry out on huge data set high-quality image data screening warehouse-in provide Reliable guarantee, ensure that the high-quality image data of screening warehouse-in meets the degree of correlation requirement of search engine retrieving, the object that finally can realize the memory data output of minimizing search engine, save the storage space of search engine memory device, alleviate search engine data processing load and reduction machine and human cost.
The aspect that the present invention adds and advantage will part provide in the following description, and these will become obvious from the following description, or be recognized by practice of the present invention.
Accompanying drawing explanation
The present invention above-mentioned and/or additional aspect and advantage will become obvious and easy understand from the following description of the accompanying drawings of embodiments, wherein:
Fig. 1 is the process flow diagram of a method embodiment of determination picture the selection result in the present invention;
Fig. 2 is the process flow diagram of a method preferred embodiment of determination picture the selection result in the present invention;
Fig. 3 is the structural representation of a device embodiment of determination picture the selection result in the present invention;
Fig. 4 is the structural representation of a device preferred embodiment of determination picture the selection result in the present invention.
Embodiment
Be described below in detail embodiments of the invention, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar element or has element that is identical or similar functions from start to finish.Being exemplary below by the embodiment be described with reference to the drawings, only for explaining the present invention, and can not limitation of the present invention being interpreted as.
Those skilled in the art of the present technique are appreciated that unless expressly stated, and singulative used herein " ", " one ", " described " and " being somebody's turn to do " also can comprise plural form.Should be further understood that, the wording used in instructions of the present invention " comprises " and refers to there is described feature, integer, step, operation, element and/or assembly, but does not get rid of and exist or add other features one or more, integer, step, operation, element, assembly and/or their group.Should be appreciated that, when we claim element to be " connected " or " coupling " to another element time, it can be directly connected or coupled to other elements, or also can there is intermediary element.In addition, " connection " used herein or " coupling " can comprise wireless connections or wirelessly to couple.Wording "and/or" used herein comprises one or more whole or arbitrary unit listing item be associated and all combinations.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, and all terms used herein (comprising technical term and scientific terminology), have the meaning identical with the general understanding of the those of ordinary skill in field belonging to the present invention.It should also be understood that, those terms defined in such as general dictionary, should be understood to that there is the meaning consistent with the meaning in the context of prior art, unless and by specific definitions as here, otherwise can not explain by idealized or too formal implication.
Fig. 1 is the process flow diagram of a method embodiment of determination picture the selection result in the present invention.
In step s 110, according to the ranking results sorted based on temperature information to multiple queries sequence, before choosing sequence, the search sequence of predetermined quantity is as screening search sequence; In the step s 120, determine that corresponding search represents pictorial information according to screening search sequence, that determines to represent pictorial information based on the search of search sequence represents relevant information; In step s 130, which, according to representing relevant information, determine picture the selection result.
Wherein, picture the selection result is represent from multiple search the pictorial information meeting predetermined preferred standard filtered out pictorial information, predetermined preferred standard is determined by configuring the formula calculating temperature information and represent relevant information, make predetermined preferred standard comprise screening search sequence and can embody the standard of user's attention rate of recent a period of time, and comprise search and represent the standard between pictorial information and search sequence with high correlation.
In the present embodiment, the search obtaining its correspondence according to the screening search sequence chosen based on temperature information represents pictorial information, to represent pictorial information and determines picture the selection result subsequently based on representing relevant information from search; User's attention rate of screening search sequence recent a period of time due to temperature information assurance, and represent relevant information and embody and search for the correlativity that represents between pictorial information and search sequence, therefore, based on temperature information and represent relevant information and screen the picture the selection result obtained and meet search engine retrieving correlation requirement and user's request.Further, because picture the selection result is represent from other search of 10,000,000,000 data levels the pictorial information meeting predetermined preferred standard filtered out pictorial information, thus for search engine carry out on huge data set high-quality image data screening warehouse-in provide Reliable guarantee, ensure that the high-quality image data of screening warehouse-in meets the degree of correlation requirement of search engine retrieving, the object that finally can realize the memory data output of minimizing search engine, save the storage space of search engine memory device, alleviate search engine data processing load and reduction machine and human cost.
Particularly, in step s 110, according to the ranking results sorted based on temperature information to multiple queries sequence, before choosing sequence, the search sequence of predetermined quantity is as screening search sequence.
Step S110 comprises step S111 (not shown) and step S112 (not shown); In step S111, according to user search recorded information, determine the temperature information of multiple queries sequence; In step S112, according to temperature information, multiple queries sequence is sorted.
Wherein, record multiple user searching record for each search sequence in query search process in user search recorded information, include but not limited to:
The search rate that each search sequence is corresponding, as the inquiry times of each search sequence within the unit interval;
The page turning frequency that each search sequence is corresponding, as carried out searching for the page turning number of times of result of page searching within the unit interval obtained based on each search sequence;
The click frequency that each search sequence is corresponding, as carried out searching for the number of clicks of multiple Search Results within the unit interval obtained based on each search sequence.
In one example, according to search rate, page turning frequency and click frequency that the multiple queries sequence pair recorded in user search recorded information is answered, by predetermined temperature computing formula, calculate the hot value determining multiple queries sequence; Subsequently, according to the hot value of multiple queries sequence, sort to multiple queries sequence, before choosing sequence, the search sequence of predetermined quantity is as screening search sequence.
In the present embodiment, determine to screen search sequence based on temperature information, can guarantee that screening search sequence is the current attention rate of user and the higher search sequence of interest-degree in search engine, therefore can embody user's attention rate of recent a period of time, can be the follow-up temperature guarantee that picture the selection result provides strong of determining.
In the step s 120, determine that corresponding search represents pictorial information according to screening search sequence, that determines to represent pictorial information based on the search of search sequence represents relevant information.
Wherein, search represents pictorial information is that user carries out searching for the pictorial information shown in the result of page searching of acquisition according to screening search sequence; According to screening search sequence, in search history record, determine that the search of screening search sequence corresponding represents pictorial information.
Particularly, when representing the relevant information search comprised based on multiple queries sequence and representing the first diversity parameters of pictorial information; Step S120 (with reference to Fig. 1) comprises step S121 (not shown);
In step S121, according to the search sequence quantity in the search each search being represented to the search sequence that pictorial information represents, determine the first diversity parameters representing pictorial information based on the search of multiple queries sequence.
Particularly, based on search history record, pictorial information represented to multiple search and inverted index is set up to the multiple queries sequence that it represents, by inverted index, determining the search sequence quantity each search being represented to the search sequence that pictorial information represents in historical search process; Represent search sequence quantity corresponding to pictorial information according to each search, by the first predetermined diversity computing formula, calculate and determine the first diversity parameters representing pictorial information based on the search of multiple queries sequence.
In the present embodiment, more owing to searching for the search sequence quantity representing pictorial information corresponding, can illustrate and this search represent pictorial information to meet the diversity of search sequence better, reflecting this search, to represent pictorial information higher for the value of search engine, therefore, determine to represent relevant information according to searching for each the search sequence quantity representing the search sequence that pictorial information represents in the search, ensure represent relevant information can fully demonstrate search represent the multifarious satisfaction degree of pictorial information for multiple queries sequence, thus determine that picture the selection result provides strong guarantee for follow-up.
When represent that the relevant information described search comprised based on each search sequence represents pictorial information accumulative represent number of times and accumulative represent position time, step S120 (with reference to Fig. 1) comprises step S122 (not shown).
In step S122, represent pictorial information according to search and represent number of times based on each search sequence accumulative and accumulatively represent position, determine to search for represent pictorial information represent relevant information.
Particularly, based on search history record, pictorial information is represented to multiple search and inverted index is set up to the multiple queries sequence that it represents, pass through inverted index, determine in predetermined time interval, based on showing in the result of page searching that the search of each search sequence obtains that each search represents the accumulative of pictorial information and represents number of times and add up to represent position; Represent pictorial information according to search to represent number of times based on each search sequence accumulative and accumulatively represent position, represent computing formula by predetermined, calculate determine to search for represent pictorial information represent relevant information.
In the present embodiment, for search engine, there is higher value owing to being represented pictorial information by the search fully shown, then represent number of times by search being represented pictorial information based on the accumulative of each search sequence and add up to represent position as the influence factor determining to represent relevant information, ensure that and represent pictorial information for by the search fully shown, it represents relevant information accordingly can corresponding lifting.
Preferably, can according to the search sequence quantity in the search each search being represented to the search sequence that pictorial information represents, and represent pictorial information in conjunction with each search and represent number of times based on each search sequence accumulative and accumulatively represent position, that determines that each search represents pictorial information represents relevant information.
In step s 130, which, according to representing relevant information, determine picture the selection result.Particularly, step comprised step S131 (not shown) and step S132 (not shown) at 130 (with reference to Fig. 1); In step S131, pictorial information is represented to search sort according to representing relevant information, determine ranking results; In step S132, according to ranking results, the search of predetermined quantity before sequence is represented pictorial information and is defined as picture the selection result.
Particularly, according to the parameter value representing relevant information calculating multiple search of determining and represent pictorial information, pictorial information is represented to multiple search and sorts, determine ranking results; Choose sequence from this ranking results before, the search of predetermined quantity represents pictorial information, as picture the selection result.
Preferably, first, determine to search for and represent picture quality information corresponding to pictorial information, in step S131, according to representing relevant information, and combine search and represent picture quality information corresponding to pictorial information and pictorial information is represented to search sort.
More preferably (with reference to Fig. 1), the method also comprises step 150 (for illustrating in figure), in step S150, represents the dimension information of picture in pictorial information, determine picture quality information according to search.
Particularly, size and the length breadth ratio of picture in pictorial information is represented according to search, by predetermined picture quality formulae discovery determination picture quality information.
In the present embodiment, search due to concrete better quality represents pictorial information and has higher value for search engine, therefore using picture quality information as the influence factor choosing picture the selection result, ensure that the search with higher picture quality represents pictorial information and can screenedly put in storage.
Fig. 2 is the process flow diagram of a method preferred embodiment of determination picture the selection result in the present invention.
In step S210, according to the ranking results sorted based on temperature information to multiple queries sequence, before choosing sequence, the search sequence of predetermined quantity is as screening search sequence; In step S220, determine that corresponding search represents pictorial information according to screening search sequence, that determines to represent pictorial information based on the search of search sequence represents relevant information; In step S240, determine to search for the second diversity parameters representing pictorial information and comprise text message; In step S230, according to representing relevant information, and in conjunction with the second diversity parameters, determine picture the selection result.
Wherein, second diversity parameters is determined by the text feature of the text message that search represents in pictorial information, reflect richness degree and the degree of scarcity of text message, the richness degree that search represents the text message that pictorial information comprises is higher, the action value that this search represents pictorial information is higher, other quantity of searching for the text message representing pictorial information representing text message that pictorial information comprises similar to a certain search are fewer, namely similarity is lower, the degree of scarcity that this search represents the text message that pictorial information comprises is higher, the action value that this search represents pictorial information is higher.
In the present embodiment, search for the Anchor Text etc. that the text message representing pictorial information comprises picture header, picture description information, picture.
Particularly, step S240 (with reference to Fig. 2) comprises step S241 (not shown) and step S242 (not shown); In step S241, the text message that pictorial information comprises is represented to search and carries out word segmentation processing, to extract participle fragment; In step S241, represent representing frequency and representing position in pictorial information based on participle fragment in its search affiliated separately, determine to search for the second diversity parameters representing pictorial information and comprise text message.
In one example, first, point word technology such as morphology are divided by Forward Maximum Method method, oppositely maximum matching method, two-way maximum matching method, shortest path, to searching for the text message representing pictorial information and comprise, as the Anchor Text of picture header and picture, carry out word segmentation processing, extract participle fragment; Subsequently, inverted index is set up to participle fragment, pass through inverted index, determine that the search of multiple participle fragment belonging to separately represents representing frequency and representing position in pictorial information, then, represent representing frequency and representing position in pictorial information based on participle fragment in its search affiliated separately, by the second predetermined diversity computing formula, calculate and determine to search for the second diversity parameters representing pictorial information and comprise text message.
In step S230, according to representing relevant information, and in conjunction with the second diversity parameters, determine picture the selection result.
Particularly, first, according to representing relevant information, represent pictorial information from search the picture the selection result determining the first quantitative value; Subsequently, by the difference of predetermined picture the selection result quantity total value and fixed first quantitative value, the second quantitative value of the picture the selection result also needing to determine is determined; Subsequently, according to the second diversity parameters, represent pictorial information from search the picture the selection result determining the second quantitative value.
Alternatively, will represent relevant information and combine with the second diversity parameters, and search be represented to pictorial information is unified to carry out sequence and process, the search of front tentation data total value of determining to sort represents pictorial information, and as picture the selection result.
In the present embodiment, second diversity parameters of richness degree and degree of scarcity that reflection search is represented the text message in pictorial information is as the influence factor determining to represent relevant information, can guarantee text message richness degree and the higher search of degree of scarcity represent pictorial information can screened go out, further ensuring to be search engine screening high-quality data on huge data set exactly.
Fig. 3 is the structural representation of a device embodiment of determination picture the selection result in the present invention.
Wherein, determine that the device of picture the selection result is contained in the network equipment.
The described network equipment includes but not limited to the server group that single network server, multiple webserver form or the cloud be made up of a large amount of main frame or the webserver based on cloud computing (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.
First, sequence determination module 310 is according to the ranking results sorted based on temperature information to multiple queries sequence, and before choosing sequence, the search sequence of predetermined quantity is as screening search sequence; Subsequently, according to screening search sequence, presenting information determination module 320 determines that corresponding search represents pictorial information, and that determines to represent pictorial information based on the search of search sequence represents relevant information; Screening module 330, according to representing relevant information, determines picture the selection result.
Wherein, picture the selection result is represent from multiple search the pictorial information meeting predetermined preferred standard filtered out pictorial information, predetermined preferred standard is determined by configuring the formula calculating temperature information and represent relevant information, make predetermined preferred standard comprise screening search sequence and can embody the standard of user's attention rate of recent a period of time, and comprise search and represent the standard between pictorial information and search sequence with high correlation.
In the present embodiment, the search obtaining its correspondence according to the screening search sequence chosen based on temperature information represents pictorial information, to represent pictorial information and determines picture the selection result subsequently based on representing relevant information from search; Screening search sequence meets user's attention rate of recent a period of time due to temperature information assurance, and represent relevant information and embody and search for the correlativity that represents between pictorial information and search sequence, therefore, based on temperature information and represent relevant information and screen the picture the selection result obtained and meet search engine retrieving correlation requirement and user's request.Further, because picture the selection result is represent from other search of 10,000,000,000 data levels the pictorial information meeting predetermined preferred standard filtered out pictorial information, thus for search engine carry out on huge data set high-quality data screening warehouse-in provide Reliable guarantee, ensure that the degree of correlation requirement of the high-quality data fit search engine retrieving of screening warehouse-in, the object that finally can realize the memory data output of minimizing search engine, save the storage space of search engine memory device, alleviate search engine data processing load and reduction machine and human cost.
Particularly, sequence determination module 310 is according to the ranking results sorted based on temperature information to multiple queries sequence, and before choosing sequence, the search sequence of predetermined quantity is as screening search sequence.
Sequence determination module 310 comprises temperature determining unit (not shown) and the first sequencing unit (not shown); First, temperature determining unit, according to user search recorded information, determines the temperature information of multiple queries sequence; Subsequently, the first sequencing unit, according to temperature information, sorts to multiple queries sequence.
Wherein, record multiple user searching record for each search sequence in query search process in user search recorded information, include but not limited to:
The search rate that each search sequence is corresponding, as the inquiry times of each search sequence within the unit interval;
The page turning frequency that each search sequence is corresponding, as carried out searching for the page turning number of times of result of page searching within the unit interval obtained based on each search sequence;
The click frequency that each search sequence is corresponding, as carried out searching for the number of clicks of multiple Search Results within the unit interval obtained based on each search sequence.
In one example, according to search rate, page turning frequency and click frequency that the multiple queries sequence pair recorded in user search recorded information is answered, by predetermined temperature computing formula, calculate the hot value determining multiple queries sequence; Subsequently, according to the hot value of multiple queries sequence, sort to multiple queries sequence, before choosing sequence, the search sequence of predetermined quantity is as screening search sequence.
In the present embodiment, determine to screen search sequence based on temperature information, can guarantee that screening search sequence is the current attention rate of user and the higher search sequence of interest-degree in search engine, therefore meet user's attention rate of recent a period of time, can be the follow-up temperature guarantee that picture the selection result provides strong of determining.
According to screening search sequence, presenting information determination module 320 determines that corresponding search represents pictorial information, that determines to represent pictorial information based on the search of search sequence represents relevant information.
Wherein, search represents pictorial information is that user carries out searching for the pictorial information shown in the result of page searching of acquisition according to screening search sequence; According to screening search sequence, in search history record, determine that the search of screening search sequence corresponding represents pictorial information.
Particularly, when representing the relevant information search comprised based on multiple queries sequence and representing the first diversity parameters of pictorial information; Presenting information determination module 320, according to the search sequence quantity in the search each search being represented to the search sequence that pictorial information represents, determines the first diversity parameters representing pictorial information based on the search of multiple queries sequence.
Particularly, based on search history record, pictorial information represented to multiple search and inverted index is set up to the multiple queries sequence that it represents, by inverted index, determining the search sequence quantity each search being represented to the search sequence that pictorial information represents in historical search process; Represent search sequence quantity corresponding to pictorial information according to each search, by the first predetermined diversity computing formula, calculate and determine the first diversity parameters representing pictorial information based on the search of multiple queries sequence.
In the present embodiment, more owing to searching for the search sequence quantity representing pictorial information corresponding, can illustrate and this search represent pictorial information to meet the diversity of search sequence better, reflecting this search, to represent pictorial information higher for the value of search engine, therefore, determine to represent relevant information according to searching for each the search sequence quantity representing the search sequence that pictorial information represents in the search, ensure represent relevant information can fully demonstrate search represent the multifarious satisfaction degree of pictorial information for multiple queries sequence, thus determine that picture the selection result provides strong guarantee for follow-up.
When represent that the relevant information described search comprised based on each search sequence represents pictorial information accumulative represent number of times and accumulative represent position time, presenting information determination module 320 represents pictorial information according to search and represents number of times based on each search sequence accumulative and accumulatively represent position, determine to search for represent pictorial information represent relevant information.
Particularly, based on search history record, pictorial information is represented to multiple search and inverted index is set up to the multiple queries sequence that it represents, pass through inverted index, determine in predetermined time interval, based on showing in the result of page searching that the search of each search sequence obtains that each search represents the accumulative of pictorial information and represents number of times and add up to represent position; Represent pictorial information according to search to represent number of times based on each search sequence accumulative and accumulatively represent position, represent computing formula by predetermined, calculate determine to search for represent pictorial information represent relevant information.
In the present embodiment, for search engine, there is higher value owing to being represented pictorial information by the search fully shown, then represent number of times by search being represented pictorial information based on the accumulative of each search sequence and add up to represent position as the influence factor determining to represent relevant information, ensure that and represent pictorial information for by the search fully shown, it represents relevant information accordingly can corresponding lifting.
Preferably, can according to the search sequence quantity in the search each search being represented to the search sequence that pictorial information represents, and represent pictorial information in conjunction with each search and represent number of times based on each search sequence accumulative and accumulatively represent position, that determines that each search represents pictorial information represents relevant information.
Screening module 330, according to representing relevant information, determines picture the selection result.Particularly, screen module 330 (with reference to Fig. 3) and comprise the second sequencing unit (not shown) and the selection result determining unit (not shown); First, the second sequencing unit represents pictorial information to search sort according to representing relevant information, determines ranking results; Subsequently, the search of predetermined quantity before sequence, according to ranking results, is represented pictorial information and is defined as picture the selection result by the selection result determining unit.
Particularly, according to the parameter value representing relevant information calculating multiple search of determining and represent pictorial information, pictorial information is represented to multiple search and sorts, determine ranking results; Choose sequence from this ranking results before, the search of predetermined quantity represents pictorial information, as picture the selection result.
Preferably, first, determine to search for and represent picture quality information corresponding to pictorial information, subsequently, the second sequencing unit according to representing relevant information, and combines search and represents picture quality information corresponding to pictorial information and represent pictorial information to search and sort.
More preferably (with reference to Fig. 3), determine that the device of picture the selection result also comprises picture quality determining device (not shown), picture quality determining device represents the dimension information of picture in pictorial information according to search, determines picture quality information.
Particularly, size and the length breadth ratio of picture in pictorial information is represented according to search, by predetermined picture quality formulae discovery determination picture quality information.
In the present embodiment, search due to concrete better quality represents pictorial information and has higher value for search engine, therefore using picture quality information as the influence factor choosing picture the selection result, ensure that the search with higher picture quality represents pictorial information and can screenedly put in storage.
Fig. 4 is the structural representation of a device preferred embodiment of determination picture the selection result in the present invention.
First, sequence determination module 410 is according to the ranking results sorted based on temperature information to multiple queries sequence, and before choosing sequence, the search sequence of predetermined quantity is as screening search sequence; Subsequently, according to screening search sequence, presenting information determination module 420 determines that corresponding search represents pictorial information, and that determines to represent pictorial information based on the search of search sequence represents relevant information; Text diversity determination module 440 determines to search for the second diversity parameters representing pictorial information and comprise text message; Subsequently, screening module 430 according to representing relevant information, and in conjunction with the second diversity parameters, determines picture the selection result.
Wherein, second diversity parameters is determined by the text feature of the text message that search represents in pictorial information, reflect richness degree and the degree of scarcity of text message, the richness degree that search represents the text message that pictorial information comprises is higher, the action value that this search represents pictorial information is higher, other quantity of searching for the text message representing pictorial information representing text message that pictorial information comprises similar to a certain search are fewer, namely similarity is lower, the degree of scarcity that this search represents the text message that pictorial information comprises is higher, the action value that this search represents pictorial information is higher.
In the present embodiment, search for the Anchor Text etc. that the text message representing pictorial information comprises picture header, picture description information, picture.
Particularly, screen module 430 (with reference to Fig. 4) and comprise participle unit (not shown) and text diversity determining unit (not shown); First, participle unit represents to search the text message that pictorial information comprises and carries out word segmentation processing, to extract participle fragment; Subsequently, text diversity determining unit represents representing frequency and representing position in pictorial information based on participle fragment in its search affiliated separately, determines to search for the second diversity parameters representing pictorial information and comprise text message.
In one example, first, point word technology such as morphology are divided by Forward Maximum Method method, oppositely maximum matching method, two-way maximum matching method, shortest path, to searching for the text message representing pictorial information and comprise, as the Anchor Text of picture header and picture, carry out word segmentation processing, extract participle fragment; Subsequently, inverted index is set up to participle fragment, pass through inverted index, determine that the search of multiple participle fragment belonging to separately represents representing frequency and representing position in pictorial information, then, represent representing frequency and representing position in pictorial information based on participle fragment in its search affiliated separately, by the second predetermined diversity computing formula, calculate and determine to search for the second diversity parameters representing pictorial information and comprise text message.
Screening module 430 according to representing relevant information, and in conjunction with the second diversity parameters, determines picture the selection result.
Particularly, first, according to representing relevant information, represent pictorial information from search the picture the selection result determining the first quantitative value; Subsequently, by the difference of predetermined picture the selection result quantity total value and fixed first quantitative value, the second quantitative value of the picture the selection result also needing to determine is determined; Subsequently, according to the second diversity parameters, represent pictorial information from search the picture the selection result determining the second quantitative value.
Alternatively, will represent relevant information and combine with the second diversity parameters, and search be represented to pictorial information is unified to carry out sequence and process, the search of front tentation data total value of determining to sort represents pictorial information, and as picture the selection result.
In the present embodiment, second diversity parameters of richness degree and degree of scarcity that reflection search is represented the text message in pictorial information is as the influence factor determining to represent relevant information, can guarantee text message richness degree and the higher search of degree of scarcity represent pictorial information can screened go out, further ensuring to be search engine screening high-quality data on huge data set exactly.
Those skilled in the art of the present technique are appreciated that the one or more equipment that the present invention includes and relate to for performing in operation described in the application.These equipment for required object and specialized designs and manufacture, or also can comprise the known device in multi-purpose computer.These equipment have storage computer program within it, and these computer programs optionally activate or reconstruct.Such computer program can be stored in equipment (such as, computing machine) in computer-readable recording medium or be stored in and be suitable for store electrons instruction and be coupled in the medium of any type of bus respectively, described computer-readable medium includes but not limited to that the dish of any type (comprises floppy disk, hard disk, CD, CD-ROM, and magneto-optic disk), ROM (Read-Only Memory, ROM (read-only memory)), RAM (Random Access Memory, storer immediately), EPROM (Erasable Programmable Read-Only Memory, Erarable Programmable Read only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory, EEPROM (Electrically Erasable Programmable Read Only Memo)), flash memory, magnetic card or light card.Namely, computer-readable recording medium comprises and being stored or any medium of transmission information with the form that can read by equipment (such as, computing machine).
Those skilled in the art of the present technique are appreciated that the combination that can realize the frame in each frame in these structural drawing and/or block diagram and/or flow graph and these structural drawing and/or block diagram and/or flow graph with computer program instructions.Those skilled in the art of the present technique are appreciated that, the processor that these computer program instructions can be supplied to multi-purpose computer, special purpose computer or other programmable data disposal routes realizes, thus is performed the scheme of specifying in the frame of structural drawing disclosed by the invention and/or block diagram and/or flow graph or multiple frame by the processor of computing machine or other programmable data disposal routes.
Those skilled in the art of the present technique are appreciated that various operations, method, the step in flow process, measure, the scheme discussed in the present invention can be replaced, changes, combines or delete.Further, there is various operations, method, other steps in flow process, measure, the scheme discussed in the present invention also can be replaced, change, reset, decompose, combine or delete.Further, of the prior art have also can be replaced with the step in operation various disclosed in the present invention, method, flow process, measure, scheme, changed, reset, decomposed, combined or deleted.
The above is only some embodiments of the present invention; it should be pointed out that for those skilled in the art, under the premise without departing from the principles of the invention; can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.
Claims (10)
1. determine a method for picture the selection result, it is characterized in that, comprising:
According to the ranking results sorted based on temperature information to multiple queries sequence, before choosing sequence, the search sequence of predetermined quantity is as screening search sequence;
Determine that corresponding search represents pictorial information according to described screening search sequence, that determines to represent pictorial information based on the described search of described search sequence represents relevant information;
Represent relevant information according to described, determine picture the selection result.
2. the method determining picture the selection result according to claim 1, is characterized in that, sorts, specifically comprise multiple queries sequence based on temperature information:
According to user search recorded information, determine the temperature information of described multiple queries sequence;
According to described temperature information, described multiple queries sequence is sorted.
3. the method for the determination picture the selection result according to any one of claim 1-2, is characterized in that, described user search recorded information comprises following at least any one:
The search rate that each search sequence is corresponding;
The page turning frequency that each search sequence is corresponding;
The click frequency that each search sequence is corresponding.
4. the method for the determination picture the selection result according to any one of claim 1-3, is characterized in that, described in represent the first diversity parameters that the relevant information described search comprised based on multiple queries sequence represents pictorial information;
Wherein, that determines to represent pictorial information based on the described search of described search sequence represents relevant information, specifically comprises:
According to the search sequence quantity in the search each search being represented to the search sequence that pictorial information represents, determine that the described search based on multiple queries sequence represents the first diversity parameters of pictorial information.
5. the method for the determination picture the selection result according to any one of claim 1-4, is characterized in that, described in represent that the relevant information described search comprised based on each search sequence represents pictorial information accumulatively represent number of times and accumulatively represent position;
Wherein, that determines to represent pictorial information based on the described search of described search sequence represents relevant information, specifically comprises:
Represent pictorial information according to described search to represent number of times based on each search sequence accumulative and accumulatively represent position, that determines that described search represents pictorial information represents relevant information.
6. the method for the determination picture the selection result according to any one of claim 1-5, is characterized in that, represent relevant information according to described, determine picture the selection result, specifically comprise:
Pictorial information is represented to described search sort according to the described relevant information that represents, determine ranking results;
According to described ranking results, the search of predetermined quantity before sequence is represented pictorial information and is defined as picture the selection result.
7. the method for the determination picture the selection result according to any one of claim 1-6, is characterized in that, represents pictorial information and sorts, comprising according to the described relevant information that represents to described search:
Represent relevant information according to described, and represent picture quality information corresponding to pictorial information in conjunction with described search and pictorial information is represented to described search sort.
8. the method for the determination picture the selection result according to any one of claim 1-7, is characterized in that, also comprise:
Represent the dimension information of picture in pictorial information according to described search, determine described picture quality information.
9. determine a device for picture the selection result, it is characterized in that, comprising:
Sequence determination module, for according to the ranking results sorted based on temperature information to multiple queries sequence, chooses the search sequence of the front predetermined quantity of sequence as screening search sequence;
Presenting information determination module, for determining that according to described screening search sequence corresponding search represents pictorial information, that determines to represent pictorial information based on the described search of described search sequence represents relevant information;
Screening module, represents relevant information for described in basis, determines picture the selection result.
10. the device determining picture the selection result according to claim 9, is characterized in that, described sequence determination module comprises:
Temperature determining unit, for according to user search recorded information, determines the temperature information of described multiple queries sequence;
First sequencing unit, for according to described temperature information, sorts to described multiple queries sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410708056.2A CN104361109B (en) | 2014-11-27 | 2014-11-27 | The method and apparatus for determining picture the selection result |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410708056.2A CN104361109B (en) | 2014-11-27 | 2014-11-27 | The method and apparatus for determining picture the selection result |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104361109A true CN104361109A (en) | 2015-02-18 |
| CN104361109B CN104361109B (en) | 2019-05-10 |
Family
ID=52528369
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410708056.2A Active CN104361109B (en) | 2014-11-27 | 2014-11-27 | The method and apparatus for determining picture the selection result |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104361109B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105721606A (en) * | 2016-03-28 | 2016-06-29 | 北京小米移动软件有限公司 | Automatic setting method and apparatus for avatar |
| CN106547808A (en) * | 2015-09-23 | 2017-03-29 | 阿里巴巴集团控股有限公司 | Picture update method, classification sort method and device |
| CN110310057A (en) * | 2019-04-08 | 2019-10-08 | 顺丰科技有限公司 | Kinds of goods sequence and goods yard processing method, device, equipment and its storage medium |
| CN110825897A (en) * | 2019-10-29 | 2020-02-21 | 维沃移动通信有限公司 | Image screening method and device and mobile terminal |
| CN110858210A (en) * | 2018-08-17 | 2020-03-03 | 阿里巴巴集团控股有限公司 | Data query method and device |
| CN115966206A (en) * | 2022-11-23 | 2023-04-14 | 中创科技(广州)有限公司 | Intelligent picture generation method, device, equipment and medium for AI voice recognition |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080195645A1 (en) * | 2006-10-17 | 2008-08-14 | Silverbrook Research Pty Ltd | Method of providing information via context searching of a printed graphic image |
| CN102236710A (en) * | 2011-06-30 | 2011-11-09 | 百度在线网络技术（北京）有限公司 | Method and equipment for displaying news information in query result |
| CN102521258A (en) * | 2011-11-18 | 2012-06-27 | 百度在线网络技术（北京）有限公司 | Method and device for providing wallpaper picture |
| CN102682095A (en) * | 2012-04-27 | 2012-09-19 | 百度在线网络技术（北京）有限公司 | Method for searching paired pictures and searching system for providing the paired pictures |
| CN103365858A (en) * | 2012-03-28 | 2013-10-23 | 百度在线网络技术（北京）有限公司 | Method and device for acquiring searching results from multiple source devices and based on one inquiry sequence |
| CN103914545A (en) * | 2014-04-08 | 2014-07-09 | 百度在线网络技术（北京）有限公司 | Search display method and device |
| CN103942272A (en) * | 2014-03-27 | 2014-07-23 | 北京百度网讯科技有限公司 | Image search method and device |
-
2014
- 2014-11-27 CN CN201410708056.2A patent/CN104361109B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080195645A1 (en) * | 2006-10-17 | 2008-08-14 | Silverbrook Research Pty Ltd | Method of providing information via context searching of a printed graphic image |
| CN102236710A (en) * | 2011-06-30 | 2011-11-09 | 百度在线网络技术（北京）有限公司 | Method and equipment for displaying news information in query result |
| CN102521258A (en) * | 2011-11-18 | 2012-06-27 | 百度在线网络技术（北京）有限公司 | Method and device for providing wallpaper picture |
| CN103365858A (en) * | 2012-03-28 | 2013-10-23 | 百度在线网络技术（北京）有限公司 | Method and device for acquiring searching results from multiple source devices and based on one inquiry sequence |
| CN102682095A (en) * | 2012-04-27 | 2012-09-19 | 百度在线网络技术（北京）有限公司 | Method for searching paired pictures and searching system for providing the paired pictures |
| CN103942272A (en) * | 2014-03-27 | 2014-07-23 | 北京百度网讯科技有限公司 | Image search method and device |
| CN103914545A (en) * | 2014-04-08 | 2014-07-09 | 百度在线网络技术（北京）有限公司 | Search display method and device |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106547808A (en) * | 2015-09-23 | 2017-03-29 | 阿里巴巴集团控股有限公司 | Picture update method, classification sort method and device |
| CN105721606A (en) * | 2016-03-28 | 2016-06-29 | 北京小米移动软件有限公司 | Automatic setting method and apparatus for avatar |
| CN110858210A (en) * | 2018-08-17 | 2020-03-03 | 阿里巴巴集团控股有限公司 | Data query method and device |
| CN110858210B (en) * | 2018-08-17 | 2023-11-21 | 阿里巴巴集团控股有限公司 | Data query method and device |
| CN110310057A (en) * | 2019-04-08 | 2019-10-08 | 顺丰科技有限公司 | Kinds of goods sequence and goods yard processing method, device, equipment and its storage medium |
| CN110310057B (en) * | 2019-04-08 | 2023-05-09 | 顺丰科技有限公司 | Goods sorting and goods location processing method, device, equipment and storage medium thereof |
| CN110825897A (en) * | 2019-10-29 | 2020-02-21 | 维沃移动通信有限公司 | Image screening method and device and mobile terminal |
| CN115966206A (en) * | 2022-11-23 | 2023-04-14 | 中创科技(广州)有限公司 | Intelligent picture generation method, device, equipment and medium for AI voice recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104361109B (en) | 2019-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104361109A (en) | Method and device for determining picture screening result | |
| CN102667761B (en) | Scalable cluster database | |
| US8332775B2 (en) | Adaptive user feedback window | |
| CN103324718B (en) | Method and system based on humongous search Web log mining topic venation | |
| CN102609441B (en) | Local-sensitive hash high-dimensional indexing method based on distribution entropy | |
| CN110291518A (en) | Merge tree garbage index | |
| CN103593371B (en) | Recommend the method and apparatus of search keyword | |
| AU2014259978B2 (en) | Tagged search result maintenance | |
| WO2017096892A1 (en) | Index construction method, search method, and corresponding device, apparatus, and computer storage medium | |
| US9558270B2 (en) | Search result organizing based upon tagging | |
| CN105760443B (en) | Item recommendation system, project recommendation device and item recommendation method | |
| CN103279486B (en) | It is a kind of that the method and apparatus of relevant search are provided | |
| US20150356137A1 (en) | Systems and Methods for Optimizing Data Analysis | |
| CN104598583A (en) | Method and device for generating query sentence recommendation list | |
| CN106294661A (en) | A kind of extended search method and device | |
| CN104778237A (en) | Individual recommending method and system based on key users | |
| US20140324826A1 (en) | Targeted content provisioning based upon tagged search results | |
| US20070233532A1 (en) | Business process analysis apparatus | |
| CN103186666A (en) | Method, device and equipment for searching based on favorites | |
| CN102419773B (en) | Method, device and equipment used for sequencing resource items | |
| CN103279529A (en) | Unstructured data retrieval method and system | |
| CN103559307A (en) | Caching method and device for query | |
| US9547713B2 (en) | Search result tagging | |
| CN110851708B (en) | Negative sample extraction method, device, computer equipment and storage medium | |
| CN107169082A (en) | A kind of information push method based on zone location |
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 | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220727 Address after: Room 801, 8th floor, No. 104, floors 1-19, building 2, yard 6, Jiuxianqiao Road, Chaoyang District, Beijing 100015 Patentee after: BEIJING QIHOO TECHNOLOGY Co.,Ltd. Address before: 100088 room 112, block D, 28 new street, new street, Xicheng District, Beijing (Desheng Park) Patentee before: BEIJING QIHOO TECHNOLOGY Co.,Ltd. Patentee before: Qizhi software (Beijing) Co.,Ltd. |
|
| TR01 | Transfer of patent right |