WO2015176825A1 - System and method for content recommendation and discovery over messaging technology - Google Patents

System and method for content recommendation and discovery over messaging technology Download PDF

Info

Publication number
WO2015176825A1
WO2015176825A1 PCT/EP2015/001068 EP2015001068W WO2015176825A1 WO 2015176825 A1 WO2015176825 A1 WO 2015176825A1 EP 2015001068 W EP2015001068 W EP 2015001068W WO 2015176825 A1 WO2015176825 A1 WO 2015176825A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
computer
content
implemented method
content items
Prior art date
Application number
PCT/EP2015/001068
Other languages
French (fr)
Inventor
Guillermo DIEZ CANAS
Original Assignee
Diez Canas Guillermo
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Diez Canas Guillermo filed Critical Diez Canas Guillermo
Publication of WO2015176825A1 publication Critical patent/WO2015176825A1/en

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/4508Management of client data or end-user data
    • H04N21/4532Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/335Filtering based on additional data, e.g. user or group profiles
    • G06F16/337Profile generation, learning or modification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
    • H04L51/21Monitoring or handling of messages
    • H04L51/214Monitoring or handling of messages using selective forwarding
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4667Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/475End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
    • H04N21/4756End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/478Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/4786Supplemental services, e.g. displaying phone caller identification, shopping application e-mailing

Definitions

  • aspects of the disclosure relate to providing content recommendations. More specifically, aspects of the disclosure are directed to providing content recommendations over messaging technology.
  • recommendation systems [8] .
  • Relevant prior uses of recommendation systems include the use of content recommendation technology for recommending music to users from a database of songs [2], the use of browser toolbars or extensions to provide users with recommendations and gather explicit webpage ratings from users [9], and the use of explicit and imphcit viewing preferences for recommending television programs [4].
  • [6] Perhaps closer to our invention is the work of [6], which makes use of the fact that, whenever two users are part of the same social network, the relation between them in the social network can be used to inform content recommendations.
  • the recommendation system makes use of information gathered during the normal use of a messaging system, such as which messages a user reads or deletes.
  • a messaging system such as which messages a user reads or deletes.
  • DISCLOSURE OF INVENTION Motivation Many communication problems are well served by modern means of electronic communication. For instance, email systems provide efficient asynchronous communication, in which the recipient doesn't need to be connected to the delivery system, or to any network, in order to receive messages, which are stored and can be viewed at a later time.
  • Other communication technologies such as Instant Messaging (IM), require both communicating parties to be simultaneously connected to the same system to ensure that reception and viewing of messages by the user occurs rapidly.
  • IM Instant Messaging
  • DVB Digital Video Broadcasting
  • DVA Digital Audio Broadcasting
  • Information that is of interest to a user may not arrive to that user.
  • the sender may not have included the interested user in the list of recipients for any of a number of reasons, for instance because the sender is unaware of the existence of this user.
  • Spam filtering addresses drawback number 2 by filtering email messages incoming to a user, trying to detect and discard or quarantine those that are unsolicited or undesired (spam).
  • Electronic mailing lists [3] allow users to subscribe to group communication channels, partly addressing drawback 1: a user subscribed to a mailing list will receive information from other users in the list, and some of those users may be unknown to him/her. Since mailing lists, or subscriptions fists in general, require users to explicit subscribe, participating users must first be aware of the existence of the list, and therefore this only partially addresses drawback 1 above.
  • Twitter from “Twitter Inc.”
  • Facebook from “Facebook, Inc.”
  • a natural approach to alleviating the above two drawbacks is to use a recommendation system [8] to inform the content item delivery decisions.
  • recommendation systems require feedback from users in the form of ratings
  • many content delivery systems already provide at least basic means of managing content items, and this is sufficient to generate content rating information to be used by the recommendation system.
  • the system may decide to deliver a content item to any of the users, independently of whether the original content item creator included the address of
  • the system may add to the original recipient list an address that was not in the original recipient list, and was not in any group fist referenced in the original recipient list.
  • the decision of which content items are delivered to which users is made by the system based on its prediction of the interest the potential 100 recipients may have in the content item.
  • This prediction which may be performed for instance using machine learning, or recommendation algorithms, is informed by, among other possible signals of interest, the user's history of actions in the system (such as which content items the user chooses to delete, open, read, flag, replay to, forward, mark as draft, or archive). Since the recommendation system also attempts to filter out undesired 105 content, we argue that this approach attempts to address both of the drawbacks listed in the motivation section.
  • the described system is, in its more general form, a content delivery system in which content items can be sent to the system from either a user of the system or from a user of an external system, content items are transmitted to
  • the user and content items can be managed by the user: the user may for instance open, delete, flag, reply to content items, forward content items, mark content items as drafts, or save content items to an archive, among others.
  • the system gathers information about the user's operations on the content items, and these are treated as implicit signals of interest in the content item. Note that, by requiring no additional effort from the user than was
  • IMAP 120 Access Protocol
  • timers may be applied with respect to the handling of content items. We mention here two timers of particular importance. One is related to the time passing from
  • Sources of information to the recommendation system A number of sources of information may be used by the system, in order to inform its recommendations. These include, but are not limited to, the users' settings in the system, how frequently users access
  • the system 140 for how long they remain connected, the time of day, or the day of the week, or other information regarding the time at which content items may be delivered.
  • Another source of information to the recommendation system may be the number of unread (or perhaps not marked as "Seen") content items associated with a user.
  • the recommendation system may for instance choose to deliver only a limited number of content
  • a source of information to the recommendation system may be whether a user requests (follows) a URL present in a content item. Note that, in order for the system to detect such a URL request, the system has to first replace the actual URL by a URL of the system,
  • 155 URLs may be an indication by the user of interest in the content, and therefore knowledge of the request of such URLs can be useful to the recommendation system.
  • Example of the operation of the system Consider, as an example of the operation of the system and its functionality, a user A who receives content items from two other users, B and C, and often deletes those from B, but rarely deletes those from C.
  • the system receives
  • the system may then use this information to infer that user A may be more interested in receiving content items from C than from B, and adjust accordingly its recommendation system to favor content items authored by C over those authored by B. Note that none of the above content items delivered to A necessarily had to initially include an address of A as a recipient in order for A to receive them, since
  • the system can make delivery decisions that replace or simply modifying a content item's original recipient list.
  • the recommendation system herein described makes use of an underlying messaging technology, and at least a very basic means of content item manipulation, for in-
  • the recommendation and messaging subsystems can relate in any of a number of ways.
  • a specially-implemented email server may perform the tasks of content item delivery, management, and recommendation. Whether the recommendation and messaging subsystems are loosely or tightly integrated, their functionality from the point of view of the user is equivalent.
  • FIG. 180 Figure 1 depicts the general structure of a content recommendation and discovery system based on a messaging technology.
  • the system (105) communicates with the end users (101) via a chent, which acts on behalf of the user (102).
  • the client may send content items to the system (103), and it may receive and manage content items by communicating with the system (104).
  • the chent may send notification of the management signals to the system.
  • FIG 2 depicts an embodiment of the system using email technology, and more in particular using the Simple Mail Transfer Protocol (SMTP), and the Internet Message Access Protocol (IMAP).
  • SMTP Simple Mail Transfer Protocol
  • IMAP Internet Message Access Protocol
  • the system (205) communicates with the end users (201) via 190 a client, or Mail User Agent (MUA), which acts on behalf of the user (202).
  • the client may send messages to the system using the SMTP protocol (203), and it may receive and manage content items by communicating with the system using the IMAP protocol (204).
  • SMTP Simple Mail Transfer Protocol
  • IMAP Internet Message Access Protocol
  • Email is a communication technology that has been in wide use for a several decades, and relies on well-stablished standard protocols of communication, such as SMTP, POP3, or IMAP.
  • the role of an email messaging system is to receive, transmit, and manage messages.
  • a message is a communication technology that has been in wide use for a several decades, and relies on well-stablished standard protocols of communication, such as SMTP, POP3, or IMAP.
  • 205 contains a list of one or more intended recipients, and part of the task of the messaging system is to attempt delivery of the message to its intended recipients.
  • the recommendation system described in this document can be implemented using email communication technology as its underlying messaging technology.
  • email communication technology we describe here an implementation that uses SMTP and IMAP as communication protocols between user
  • an end-user (201) makes use of a client, which is also referred to as a Mail User Agent (MUA) (202).
  • the MUA communicates with the system on behalf of the user.
  • the MUA may send messages to the system (205) through the Simple Mail Transfer Protocol (SMTP) (203).
  • SMTP Simple Mail Transfer Protocol
  • the SMTP protocol requires that these messages have an associated recipient list.
  • the MUA receives
  • IMAP Internet Message Access Protocol
  • the MUA may request messages delivered to the user to be fetched on behalf of the user, and these fetching operations may change the Seen flag of a message.
  • the user 220 may execute management operations on the messages, such as opening, reading, flagging, replying, forwarding, deleting messages, or marking messages as drafts. Each of these operations have corresponding IMAP commands which the MUA sends to the messaging subsystem. The system then executes these operations, and keeps note of them for use in its recommendation subsystem.
  • the IMAP protocol has a number of features for managing messages that may be useful to the recommendation system.
  • the recommendation system can keep track of these operations, as requested by the MUA, and incorporate this information to its computations in order to perform its task. Among these features may be the following:
  • Messages may have internal flags (so-called system flags [1]) which can be set, cleared, 230 or fetched, and may include the following: Seen (the message has been read) , Answered
  • Flagged the message is "flagged” for urgent /special attention
  • Deleted the message is marked “deleted” for later removal
  • Draft the message has not completed composition: is marked as a draft.
  • the "Flagged” flag is commonly depicted in clients (MUAs) as a flag icon or a star icon, and the flag itself 235 is sometimes referred to as "Starred” .
  • Messages may have user or client-defined internal flags.
  • the IMAP protocol supports the definition of new message flags other than the ones listed above (servers supporting new message flags advertise this fact to clients by sending " ⁇ *" in a "PERMANENTFLAGS” response [1]). Manipulation of these flags may be used as
  • a client may define and use a
  • the client may provide a special button to mark any message as “positively-rated” , effectively providing the user with a means to explicitly rate messages.
  • Messages may be copied to, moved to, or erased from a number of folders.
  • Certain 245 folders have special designations in the IMAP protocol using the "Special-Use Mailboxes" extension [5].
  • the specially designated mailboxes may include those tagged in [5] as: All (typically a virtual mailbox including all messages, perhaps excluding those in Trash or Spam folders) , Archive (for archiving messages), Drafts (typically used to store or list messages marked as Draft), Flagged (typically used
  • Example recommendation subsystem 255
  • the recommendation subsystem simply receives information on user's actions in the system, and recommends content items to users.
  • A, B, and C be users of the system, using separate clients on behalf of each.
  • the users may be physical persons or computers programs, but this makes no difference to the
  • N B ⁇ A be the total number of content items authored by B that have been delivered so far to A.
  • NQ ⁇ A be the total number of content items authored by C that have been delivered so far to A.
  • DB ⁇ A be the total number of content items authored by B that A has opened and deleted, and let D C ⁇ A be the total number of content items authored by C that A has opened and deleted.
  • the system estimates the
  • PB ⁇ A (N B ⁇ A + 1 - D B ⁇ A )/(NB ⁇ A + 1), and similarly for C. This number is always between 0 and 1, with 0 representing no interest, and 1 representing very high interest.
  • the system Given the arrival of a content item authored by B, the system chooses to deliver this content item to A with probability P B ⁇ A - This probability of delivery will be low when the 275 system believes that A is not very interested in receiving content items from B, and high when it believes that A is very interested in receiving content items from B.
  • User B begins by sending a content item
  • A connects to the system and fetches content items MB1 and MCI.
  • A reads 285 both content items and deletes MB1.
  • the system has noticed that A deleted the content item authored by B but not 290 the one authored by C, and adjusted its estimates of interests accordingly, favoring C over B.
  • the system will have more information on which to base its estimates of interest, and consequently to inform its delivery decisions.
  • SMS Short Message Service
  • Multimedia Message Service
  • SMS 300 Service
  • MMS 300 Service
  • the recommendation system can use the recommendation method described in the above section entitled "Recommendation system based on email technology" , in combination with signals obtained as a side-effect of the users' management of messages (such as viewing, and deleting messages).

Abstract

Systems for recommending content can be implemented over messaging technology. Many instances of messaging technology support the ability of users to fetch and delete content items, and this is sufficient to provide information about the user's interest, or lack of interest in the received content, to a recommendation system. Oftentimes, the underlying messaging technology provides further signals. For instance, the electronic mail protocol IMAP (Internet Message Access Protocol) further allows users to mark content items as seen, flagged, answered, and forwarded. Given an incoming content item, with an associated intended recipient list, the system can make use of its knowledge of the users' interests, gathered through signals such as the aforementioned ones, to inform decisions on which of the intended recipients, or even new potential recipients not listed in the original recipient list, are to receive the content item.

Description

System and Method for Content Recommendation and Discovery Over Messaging Technology
CROSS-REFERENCE TO RELATED APPLICATIONS
This application is a continuation application of and claims the benefit of priority from EPO application number 14001810.2/EP14001810, entitled "A SYSTEM FOR CONTENT RECOMMENDATION AND DISCOVERY OVER MESSAGE COMMUNICATION TECHNOLOGY" , and filed on May 23, 2014. The content of the aforementioned application is incorporated herein by reference in its entirety.
TECHNICAL FIELD
Aspects of the disclosure relate to providing content recommendations. More specifically, aspects of the disclosure are directed to providing content recommendations over messaging technology.
BACKGROUND ART
A number of solutions have been proposed in the past to address the problems of finding potentially interesting content on behalf of a user, and/or filtering some of the content delivered to a user in order to avoid unsolicited, or undesired content. Among the earlier efforts are electronic mailing lists [3], to which users can subscribe to receive content from other users, and spam filters [7], which attempt to avoid delivering unwanted email messages to users.
Both problems cited above are addressed by recommendation systems [8] . Relevant prior uses of recommendation systems include the use of content recommendation technology for recommending music to users from a database of songs [2], the use of browser toolbars or extensions to provide users with recommendations and gather explicit webpage ratings from users [9], and the use of explicit and imphcit viewing preferences for recommending television programs [4]. Perhaps closer to our invention is the work of [6], which makes use of the fact that, whenever two users are part of the same social network, the relation between them in the social network can be used to inform content recommendations.
In our invention, there is no need for users to belong to the same social network, and the signals used to inform the recommendation system do not have to be provided by explicit rating of items. Instead, the recommendation system makes use of information gathered during the normal use of a messaging system, such as which messages a user reads or deletes. DISCLOSURE OF INVENTION Motivation. Many communication problems are well served by modern means of electronic communication. For instance, email systems provide efficient asynchronous communication, in which the recipient doesn't need to be connected to the delivery system, or to any network, in order to receive messages, which are stored and can be viewed at a later time. Other communication technologies, such as Instant Messaging (IM), require both communicating parties to be simultaneously connected to the same system to ensure that reception and viewing of messages by the user occurs rapidly. Other means of communication, such as Multimedia Messaging Service (MMS) are akin to email, but operate over mobile networks. In a similar vein, Digital Video Broadcasting (DVB), and Digital Audio Broadcasting (DVA) technologies provide communication channels between distributors of video and audio, or simply audio content, and users, with similar goals of efficiency of delivery.
Although the above modes of communication may vary in their priorities in terms of quality of delivery, such as prioritizing efficiency of transmission, or rehabihty, their common feature is that, for each content item, once one or more intended recipients of the information are identified by the sender, the goal of the system is to deliver that information to the intended recipients.
By placing the choice of recipient often fully under the control of the sender, the above communication systems can suffer from two drawbacks:
1. Information that is of interest to a user may not arrive to that user. In this case the sender may not have included the interested user in the list of recipients for any of a number of reasons, for instance because the sender is unaware of the existence of this user.
2. Information that is not of interest to a user may nevertheless arrive to that user.
Note, however, that for personal communications between known parties, the above draw- backs typically become irrelevant, and many types of existing communication systems already serve this form of communication well.
There have been a number of attempts to alleviate the above problems. Spam filtering [7] addresses drawback number 2 by filtering email messages incoming to a user, trying to detect and discard or quarantine those that are unsolicited or undesired (spam). Electronic mailing lists [3] allow users to subscribe to group communication channels, partly addressing drawback 1: a user subscribed to a mailing list will receive information from other users in the list, and some of those users may be unknown to him/her. Since mailing lists, or subscriptions fists in general, require users to explicit subscribe, participating users must first be aware of the existence of the list, and therefore this only partially addresses drawback 1 above. Other communication services, such as Twitter (from "Twitter Inc.") and Facebook (from "Facebook, Inc."), share some of the above problems when trying to alleviate the above drawbacks. Twitter is a service very much akin in spirit to subscription mailing lists, requiring explicit subscription to receive messages from a user. Facebook delivers informa-
75 tion from confirmed contacts or other subscription-like sources requiring prior knowledge of their existence, and niters incoming content using a number of signals of interest in the information, including the user's behavior in the system (for instance signals of interest in the information previously received from each of the contacts). This addresses drawback 2 above, but not drawback 1.
80 A natural approach to alleviating the above two drawbacks is to use a recommendation system [8] to inform the content item delivery decisions. We note that while recommendation systems require feedback from users in the form of ratings, many content delivery systems already provide at least basic means of managing content items, and this is sufficient to generate content rating information to be used by the recommendation system.
85 Description of the invention. Many content delivery systems, for example many email systems, provide means to fetch and to delete or archive content items, and possibly to flag -them— These basic operations can be used as indicators of interest by a recommendation system. The recommendation system can provide content recommendations to users by having some control over the content item delivery decisions, for instance by replacing part
90 or all of the original recipient list of a content item in favor of recommended recipients.
Note that the recommended new recipients of a content item do not have to have any relation with the sender (in particular, there is no requirement for them to subscribe to any source of content). The system may decide to deliver a content item to any of the users, independently of whether the original content item creator included the address of
95 that particular user as a recipient. In particular, this means that the system may add to the original recipient list an address that was not in the original recipient list, and was not in any group fist referenced in the original recipient list. The decision of which content items are delivered to which users (possibly apart from the recipients that the content item author specifies) is made by the system based on its prediction of the interest the potential 100 recipients may have in the content item. This prediction, which may be performed for instance using machine learning, or recommendation algorithms, is informed by, among other possible signals of interest, the user's history of actions in the system (such as which content items the user chooses to delete, open, read, flag, replay to, forward, mark as draft, or archive). Since the recommendation system also attempts to filter out undesired 105 content, we argue that this approach attempts to address both of the drawbacks listed in the motivation section.
From the point of view of the user, the described system is, in its more general form, a content delivery system in which content items can be sent to the system from either a user of the system or from a user of an external system, content items are transmitted to
110 the user, and content items can be managed by the user: the user may for instance open, delete, flag, reply to content items, forward content items, mark content items as drafts, or save content items to an archive, among others. The system gathers information about the user's operations on the content items, and these are treated as implicit signals of interest in the content item. Note that, by requiring no additional effort from the user than was
115 already employed to manage content items, the gathering of so-called implicit ratings can be more convenient to the user, when compared to the requirement or suggestion that the user explicitly rate content items. Note, however, that we do not limit the described system to so-called implicit signals. As an example, we describe in section "Recommendation system based on email technology" a mechanism by which a system using the Internet Message
120 Access Protocol (IMAP) can make use of special, chent-defined message flags to allow users to explicit rate emails.
The skilled person should be aware that, for the analysis of the use of the system by a user, several timers may be applied with respect to the handling of content items. We mention here two timers of particular importance. One is related to the time passing from
125 the moment that a user reads or fetches a content item, and a second one is related to the time between the reading or fetching of a content item, and the deleting, or other significant operation on the content item is performed.
Distinction between content items stored at the client and at the server. We note that different messaging systems may store the content items corresponding to a user in the
130 system's servers, or in the user's client, or both. Whenever content items are stored in a user's client, and content item management (e.g. deleting a content item) is performed solely in the client, the client must be modified so that it notifies the system's servers of these user operations. In this case, the arrow numbered 104 in Figure 1 does not represent the communication between client and system's servers needed for the management of content
135 items, but rather the notification from the client to the system's servers that the user has performed certain content item management operations.
Sources of information to the recommendation system. A number of sources of information may be used by the system, in order to inform its recommendations. These include, but are not limited to, the users' settings in the system, how frequently users access
140 the system, for how long they remain connected, the time of day, or the day of the week, or other information regarding the time at which content items may be delivered.
Another source of information to the recommendation system may be the number of unread (or perhaps not marked as "Seen") content items associated with a user. The recommendation system may for instance choose to deliver only a limited number of content
145 items to a user that has a sufficiently large number of unseen content items, with the aim to avoid overwhelming the user with too many unseen content items. A source of information to the recommendation system may be whether a user requests (follows) a URL present in a content item. Note that, in order for the system to detect such a URL request, the system has to first replace the actual URL by a URL of the system,
150 with an appropriate encoding of sufficient data to recover the original URL, as well as to identify the user, and possibly which content item the URL was placed in. The goal of such URL replacement is to intercept the request event, and send notification of the request to the recommendation system before redirecting the user to the actual destination URL. Since content items can often contain URLs that point to external content, requesting these
155 URLs may be an indication by the user of interest in the content, and therefore knowledge of the request of such URLs can be useful to the recommendation system.
Example of the operation of the system. Consider, as an example of the operation of the system and its functionality, a user A who receives content items from two other users, B and C, and often deletes those from B, but rarely deletes those from C. The system receives
160 notification of these deletion operations. The system may then use this information to infer that user A may be more interested in receiving content items from C than from B, and adjust accordingly its recommendation system to favor content items authored by C over those authored by B. Note that none of the above content items delivered to A necessarily had to initially include an address of A as a recipient in order for A to receive them, since
165 the system can make delivery decisions that replace or simply modifying a content item's original recipient list.
Relation between recommendation and messaging subsystems. As has already been pointed out, the recommendation system herein described makes use of an underlying messaging technology, and at least a very basic means of content item manipulation, for in-
170 stance fetching and deleting content items. The recommendation and messaging subsystems can relate in any of a number of ways.
It is possible to implement separate recommendation and communication and content item management systems, which communicate among themselves. In other instances, the two may be closely integrated. For instance, in the case that the underlying messaging
175 technology is email, a specially-implemented email server may perform the tasks of content item delivery, management, and recommendation. Whether the recommendation and messaging subsystems are loosely or tightly integrated, their functionality from the point of view of the user is equivalent.
BRIEF DESCRIPTION OF DRAWINGS
180 Figure 1 depicts the general structure of a content recommendation and discovery system based on a messaging technology. The system (105) communicates with the end users (101) via a chent, which acts on behalf of the user (102). The client may send content items to the system (103), and it may receive and manage content items by communicating with the system (104). In some cases in which content items are managed locally by a client 185 on behalf of the user, the chent may send notification of the management signals to the system.
Figure 2 depicts an embodiment of the system using email technology, and more in particular using the Simple Mail Transfer Protocol (SMTP), and the Internet Message Access Protocol (IMAP). The system (205) communicates with the end users (201) via 190 a client, or Mail User Agent (MUA), which acts on behalf of the user (202). The client may send messages to the system using the SMTP protocol (203), and it may receive and manage content items by communicating with the system using the IMAP protocol (204).
BEST MODES FOR CARRYING OUT THE INVENTION
The examples and described embodiments are not limiting, but merely illustrative. The 195 invention is defined by the provided claims and equivalents thereof. It should be noted that the described embodiments may be combined in any way, i.e. the embodiments described in this document are not mutually exclusive, and features described in connection with a certain embodiment may be combined with features described in connection with another embodiment. The best mode for carrying out the invention is the one described in the 200 section below ("Recommendation system based on email technology").
Recommendation system based on email technology. Email is a communication technology that has been in wide use for a several decades, and relies on well-stablished standard protocols of communication, such as SMTP, POP3, or IMAP. The role of an email messaging system is to receive, transmit, and manage messages. Crucially, a message
205 contains a list of one or more intended recipients, and part of the task of the messaging system is to attempt delivery of the message to its intended recipients.
The recommendation system described in this document can be implemented using email communication technology as its underlying messaging technology. We describe here an implementation that uses SMTP and IMAP as communication protocols between user
210 and system. We make reference to Figure 2. In this case, an end-user (201) makes use of a client, which is also referred to as a Mail User Agent (MUA) (202). The MUA communicates with the system on behalf of the user. The MUA may send messages to the system (205) through the Simple Mail Transfer Protocol (SMTP) (203). The SMTP protocol requires that these messages have an associated recipient list. The MUA receives
215 and manages messages through the Internet Message Access Protocol (IMAP) (204). Note that the user may be a person or a computer, but this may be unknown to the messaging and recommendation system, which interacts with users only through the MUA.
The MUA may request messages delivered to the user to be fetched on behalf of the user, and these fetching operations may change the Seen flag of a message. The user 220 may execute management operations on the messages, such as opening, reading, flagging, replying, forwarding, deleting messages, or marking messages as drafts. Each of these operations have corresponding IMAP commands which the MUA sends to the messaging subsystem. The system then executes these operations, and keeps note of them for use in its recommendation subsystem.
225 The IMAP protocol has a number of features for managing messages that may be useful to the recommendation system. The recommendation system can keep track of these operations, as requested by the MUA, and incorporate this information to its computations in order to perform its task. Among these features may be the following:
• Messages may have internal flags (so-called system flags [1]) which can be set, cleared, 230 or fetched, and may include the following: Seen (the message has been read) , Answered
(the message has been answered), Flagged (the message is "flagged" for urgent /special attention), Deleted (the message is marked "deleted" for later removal), Draft (the message has not completed composition: is marked as a draft). The "Flagged" flag is commonly depicted in clients (MUAs) as a flag icon or a star icon, and the flag itself 235 is sometimes referred to as "Starred" .
• Messages may have user or client-defined internal flags. The IMAP protocol supports the definition of new message flags other than the ones listed above (servers supporting new message flags advertise this fact to clients by sending "\*" in a "PERMANENTFLAGS" response [1]). Manipulation of these flags may be used as
240 signals by the recommendation system. As an example, a client may define and use a
"positively-rated" flag. The client may provide a special button to mark any message as "positively-rated" , effectively providing the user with a means to explicitly rate messages.
• Messages may be copied to, moved to, or erased from a number of folders. Certain 245 folders have special designations in the IMAP protocol using the "Special-Use Mailboxes" extension [5]. For instance, the specially designated mailboxes may include those tagged in [5] as: All (typically a virtual mailbox including all messages, perhaps excluding those in Trash or Spam folders) , Archive (for archiving messages), Drafts (typically used to store or list messages marked as Draft), Flagged (typically used
250 to store or list messages marked as Flagged), Junk (typically used to store or list undesired or unsolicited messages, or those filtered by a spam filter), Sent (typically used to store or list sent messages), Trash (typically used to store or list messages that have been deleted or marked for deletion).
Example recommendation subsystem. 255 Consider the following, extremely simplified example implementation of a recommendation subsystem, and example use case. The recommendation subsystem simply receives information on user's actions in the system, and recommends content items to users.
Let A, B, and C be users of the system, using separate clients on behalf of each. The users may be physical persons or computers programs, but this makes no difference to the
260 system, since it only communicates directly with the clients. Whenever we speak of a user executing an operation, it is understood that it's the user's client that communicates with the system in order to execute the operation.
We will consider how the system can make a decision on which content items to deliver to user A, with the understanding that similar decisions will be made for all other users.
265 Let NB→A be the total number of content items authored by B that have been delivered so far to A. Similarly, let NQ→A be the total number of content items authored by C that have been delivered so far to A. Let DB→A be the total number of content items authored by B that A has opened and deleted, and let DC→A be the total number of content items authored by C that A has opened and deleted. In this example, the system estimates the
270 interest that A has in receiving a content item from B to be
PB→A = (NB→A + 1 - DB→A)/(NB→A + 1), and similarly for C. This number is always between 0 and 1, with 0 representing no interest, and 1 representing very high interest.
Given the arrival of a content item authored by B, the system chooses to deliver this content item to A with probability PBA- This probability of delivery will be low when the 275 system believes that A is not very interested in receiving content items from B, and high when it believes that A is very interested in receiving content items from B.
Consider now the following sequence of events. User B begins by sending a content item
MB1 to the system, and user C then sends content item MCI to the system. Since at first it is NBA - 0, NC→A = 0, and DB→A = 0, DC→A = 0, the initial system estimates of 280 interest for A are PB→A = (0 + 1 - 0)/(0 + 1) = 1 and PC→A = (0 + 1 - 0)/(0 + 1) = 1, and therefore the system estimates that A is very interested in receiving content items from both B and C. Due to the high estimated interest, content items MB1 and MCI are delivered to A.
Later on, A connects to the system and fetches content items MB1 and MCI. A reads 285 both content items and deletes MB1. The system updates its internal counts to NB→A = 1, NcA = 1, and DB→A ' 1, DCA = 0 (A received so far one content item from B and one from C, and deleted one content item from B and none from C), which leads to new estimates of interest PB→A = (1 + 1 - 1)/(1 + 1) = 0.5 and PC→A = (1 + 1 - 0)/(l + 1) = 1. Effectively, the system has noticed that A deleted the content item authored by B but not 290 the one authored by C, and adjusted its estimates of interests accordingly, favoring C over B.
As a consequence of A's behavior, future content items considered for delivery to A will be treated differently depending on whether they are authored by B or C. Content items from B will only be delivered to A with probability PBA = 0 5 (on average only 50% of 295 them will be delivered to A) , while all content items from C will be delivered to A.
As the users continue to use the system, the system will have more information on which to base its estimates of interest, and consequently to inform its delivery decisions.
Recommendation system based on Short Message Service and Multimedia Message Service technology. Both Short Message Service (SMS) and Multimedia Message
300 Service (MMS) technology provide means for communication between mobile devices that is not based on voice, including sending text, images, and or audio or video files. While SMS and MMS technologies focus on the specification of recipients and delivery of messages, clients typically store the received messages and allow users to delete messages. As described above, this ability to receive, view, and delete messages is sufficient to imple-
305 ment a recommendation system that is based on an underlying message communication technology such as SMS or MMS. For example, the recommendation system can use the recommendation method described in the above section entitled "Recommendation system based on email technology" , in combination with signals obtained as a side-effect of the users' management of messages (such as viewing, and deleting messages).
310 Note that, while email services based on the IMAP protocol typically store messages in the server and allow users to manage messages by use of the IMAP protocol, SMS and MMS services typically rely on the client to store and manage messages. Whenever a MMS user deletes a message, the deletion typically happens in the user's mobile client. This means that interest signals to be used in the recommendation system may need to be sent
315 from the mobile client to the recommendation system, whenever this system is external to the mobile client, as would typically be the case.
References
[1] M. Crispin. INTERNET MESSAGE ACCESS PROTOCOL - VERSION 4revl. RFC 3501 (Proposed Standard), March 2003. Updated by RFCs 4466, 4469, 4551, 5032, 320 5182, 5738.
[2] J. Eggink, T. Kemp, W. Hagg, T. Zimmer, and T. Feduszczak. Method for content recommendation, April 1 2014. US Patent 8,688,699.
[3] E. Krol. Hitchhikers guide to the Internet. RFC 1118 (Informational), September 1989. [4] K. Kurapati, J.D. Schaffer, and S. Gutta. Method and apparatus for generating recommendation scores using implicit and explicit viewing preferences, September 23 2014. US Patent 8,843,965.
[5] M. Leiba and J. Nicolson. IMAP LIST Extension for Special-Use Mailboxes. RFC 6154 (Proposed Standard), March 2011.
[6] A. Mathur. Social network based recommendation method and system, November 11 2010. US Patent App. 12/437,682.
[7] Mehran Sahami, Susan Dumais, David Heckerman, and Eric Horvitz. A bayesian approach to filtering junk E-mail. In Learning for Text Categorization: Papers from the 1998 Workshop, Madison, Wisconsin, 1998. AAAI Technical Report WS-98-05.
[8] J. Ben Schafer, Dan Frankowski, Jon Herlocker, and Shilad Sen. The adaptive web. chapter Collaborative Filtering Recommender Systems, pages 291-324. Springer- Verlag, Berlin, Heidelberg, 2007.
[9] G. Smith, G. Camp, E. Boyd, and J. LaPrance. Method and system for single-action personalized recommendation and display of internet content, December 13 2011. US Patent 8,078,615.

Claims

We claim:
1. A computer-implemented method for dehvering content items to a first user comprising:
receiving, by a computing device, a content item sent by a second user;
identifying, by the computing device, a list containing one or more addresses of intended recipients of the content item, wherein the list does not contain an address of the first user;
adding, by the computing device, to the list of intended recipient addresses, an address of the first user;
delivering, by the computing device, the content item to each of the addresses in the modified list of recipient addresses, whether directly sending the content item to the corresponding user's client, or by sending the content item to another system for ultimate delivery to that address.
2. The computer-implemented method of claim 1, wherein the adding of an address of a user to the original list of intended recipients depends on the user's settings in the system.
3. The computer-implemented method of claim 1, wherein the adding of an address of a user to the original list of intended recipients depends on at least one of the following: the time of day, or the day of the week.
4. The computer-implemented method of claim 1, wherein the adding of an address of a user to the original list of intended recipients depends on at least one of the following: the frequency with which the user uses the system, or the number of times that the user uses the system over a predefined period of time.
5. The computer-implemented method of claim 1, wherein the adding of an address of a user to the original list of intended recipients depends on at least one of the following: information gathered by the system about whether that user follows one or more URL links referenced in a previously received content item.
6. The computer- implemented method of claim 1, wherein the adding of an address of a user to the original list of intended recipients depends on at least one of the following: information gathered by the system about the number of unread content items associated with the user, or the number of content items received and read over a predefined period of time.
7. The computer-implemented method of claim 1, wherein the second user is not a user of the content delivery system.
8. The computer-implemented method of claim 1, wherein the underlying content delivery technology of the system is email technology.
9. The computer-implemented method of claim 1, wherein the underlying content delivery technology of the system is Instant Messaging technology.
10. The computer-implemented method of claim 1, wherein the underlying content delivery technology of the system is Short Message Service technology or Multimedia Messaging Service.
11. The computer-implemented method of claim 1, wherein the underlying content delivery technology of the system is Digital Video Broadcasting technology.
12. The computer-implemented method of claim 1, wherein the underlying content delivery technology of the system is Digital Audio Broadcasting technology.
13. The computer-implemented method of claim 8, wherein the adding of an address of a user to the original list of intended recipients depends on information gathered by the system about the user's use history in the system, such as which content items users fetched, or which content items were marked as seen, or flagged, or deleted, or answered, or drafted, or forwarded, or which content items users copied or moved to the Inbox folder, or to folders with the attributes Archive, Drafts, Flagged, Junk, Sent, or Trash.
14. The computer-implemented method of claim 8, wherein the adding of an address of a user to the original list of intended recipients depends on information gathered by the system about the user's use history in the system, such as which content items the user marked using client-defined flags.
15. A computer system adapted to implement any of the preceding claims.
PCT/EP2015/001068 2014-05-23 2015-05-26 System and method for content recommendation and discovery over messaging technology WO2015176825A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP14001810.2 2014-05-23
EP14001810 2014-05-23

Publications (1)

Publication Number Publication Date
WO2015176825A1 true WO2015176825A1 (en) 2015-11-26

Family

ID=53373385

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2015/001068 WO2015176825A1 (en) 2014-05-23 2015-05-26 System and method for content recommendation and discovery over messaging technology

Country Status (1)

Country Link
WO (1) WO2015176825A1 (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080071872A1 (en) * 2006-09-20 2008-03-20 John Nicholas Gross Document Distribution Recommender System & Method
US20090234876A1 (en) * 2008-03-14 2009-09-17 Timothy Schigel Systems and methods for content sharing
US20140067942A1 (en) * 2012-09-06 2014-03-06 International Business Machines Corporation Determining recommended recipients of a communication

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080071872A1 (en) * 2006-09-20 2008-03-20 John Nicholas Gross Document Distribution Recommender System & Method
US20090234876A1 (en) * 2008-03-14 2009-09-17 Timothy Schigel Systems and methods for content sharing
US20140067942A1 (en) * 2012-09-06 2014-03-06 International Business Machines Corporation Determining recommended recipients of a communication

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
BIELENBERG K ET AL: "Groups in Social Software: Utilizing Tagging to Integrate Individual Contexts for Social Navigatio", 16 August 2005 (2005-08-16), pages 1 - 120, XP001562272, Retrieved from the Internet <URL:http://users.cs.fiu.edu/~yzhan004/rectangularPacking/tagcloudRoud.pdf> *

Similar Documents

Publication Publication Date Title
US10185479B2 (en) Declassifying of suspicious messages
US7644126B2 (en) Message thread handling
US9438554B2 (en) Cross platform messaging
US10462085B2 (en) Message distribution groups
US8725811B2 (en) Message organization and spam filtering based on user interaction
US8438225B2 (en) Traversing between electronic mail and real time communications
JP4886446B2 (en) System, method and program for controlling the presentation of e-mail messages after delivery (easy to present and monitor e-mail messages including replies for each constraint)
US8327445B2 (en) Time travelling email messages after delivery
US9143478B2 (en) Email with social attributes
US20150081825A1 (en) Method for Automatically Unsubscribing an Address from a Subscription
US20080235335A1 (en) Method, system, and computer program product for changing the status of an existing email in a recipient email client inbox
CN106470149B (en) Message sending method and device
US20050198171A1 (en) Managing electronic messages using contact information
US10075408B2 (en) Managing messaging sessions among multiple participants
US20130219296A1 (en) Real time editing for electronic mail
US9002952B2 (en) Messaging system, a messenger server, a method and a computer program product
US7673002B1 (en) System and method for e-mail message action requests
US9288173B2 (en) Geo-data spam filter
JP2009169866A (en) Electronic mail client and its control method, and computer program
WO2015176825A1 (en) System and method for content recommendation and discovery over messaging technology
US8635292B2 (en) Method for reduction of disk space usage of electronic messages in a network
US7606935B1 (en) Systems and methods of automatic retransmission of electronic mail
WO2017088977A1 (en) System and method for content distribution and discovery over message communication technology
EP2045986B1 (en) Method and device for collaborative electronic mail filtering
McFedries et al. Overcoming Email Glitches

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15727876

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15727876

Country of ref document: EP

Kind code of ref document: A1