Patent Application
20110218946
Within the field of computing, many scenarios involve a presentation to a user of content items selected from a social content item set, such as news items from a news source, images from an image database, and social items from a social network. However, some of these content item sets may be frequently updated, and presenting all of the latest content items may overwhelm the user. Some techniques may involve presenting to the user a subset of content items, such as those generated by associate users who have a relationship with the user, or by presenting the newest content items of the content item set.
This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key factors or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
While some techniques for selecting a subset of content items for presentation to the user may be advantageous, it may be difficult to select content items that are potentially interesting to the user. For example, if the user is associated with various associate users based on shared interests, limiting the presented content items to those generated by the associate users may promote the interestingness of different content items. However, a user may have relationships with many associate users who each generate a large set of content items relating to many diverse interests, and this volume and diversity may diminish the potentially interesting selectivity among the content items.
Techniques may be devised and utilized that may improve the selectivity to content items that are of potential interest to the user. Such techniques involve the selection of content items that relate to a topic that is of interest to the user, and that have a positive trending popularity, which may be indicative, e.g., of a consensus determination of interestingness and/or significance to the user. By selecting content items based on both the topical relevance to the user and the positive trending popularity of the content item, the presentation of content items may be adjusted to improve the selectivity of content items from the content item set that the user may find potentially interesting.
To the accomplishment of the foregoing and related ends, the following description and annexed drawings set forth certain illustrative aspects and implementations. These are indicative of but a few of the various ways in which one or more aspects may be employed. Other aspects, advantages, and novel features of the disclosure will become apparent from the following detailed description when considered in conjunction with the annexed drawings.
The claimed subject matter is now described with reference to the drawings, wherein like reference numerals are used to refer to like elements throughout. In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the claimed subject matter. It may be evident, however, that the claimed subject matter may be practiced without these specific details. In other instances, structures and devices are shown in block diagram form in order to facilitate describing the claimed subject matter.
Within the field of computing, many scenarios involve a presentation to a user of content items selected from a content item set. As a first example, a news source may generate a set of news items, and may select a set of such news items from the news item set for presentation to a user. As a second example, an image database may store an image collection comprising images generated by various users, and may present for a user a set of such images. As a third example, a conversation forum may store a set of threads, comprising a post about a particular topic and a set of replies, and may present to a user a set of such threads. As a fourth example, a social network may store a set of comments generated by users (such as a status), and may present to a first user a set of comments submitted by other users who are associates (such as friends, family members, acquaintances, and colleagues) of the first user.
In these and other scenarios, the content server 26 of the content item set 18 is requested to select a subset of content items 20 for inclusion in the presentation 24 to the user 12. However, it may be undesirable to present an arbitrary selection of content items 20. As a first example, the content item set 18 may be voluminous and diverse, and an arbitrary selection of content items 20 may include many content items 20 that are of little or no use or interest to the user 12. As a second example, the content item set 18 may include content items 20 that are authored or submitted at various times, and content items 20 that are newer or that have been more recently submitted may be of greater value to the user 12 than older content items 20; therefore, an arbitrary selection of content items 20 may include many that are stale, outdated, or superseded by a newer version of the same content item 20.
In order to improve the value of the presentation 24 to the user 12, the selection of content items 20 from the content item set 18 may be performed in view of various considerations. As a first example, the content items 20 may be selected according to the date of creation or addition to the content item set 18, such that recent content items 20 are preferentially selected and presented over less recent content items 20. As a second example, where content items 20 are generated by various authors 22, respective content items 20 may be preferentially selected according to the relationship of the author 22 to the user 12. In one such embodiment, a social network may include a map of association of the user 12 with associate users, such as first-order relationships with close friends and family members, second-order relationships with other friends and colleagues, and third-order relationships with casual acquaintances; and content items 20 generated by these associate users (as authors 22) may be preferentially selected based on the order of the relationship of the author 22 with the user 12. As a third example, the content server 26 may track the popularity of various content items 20 among users 12, and may select for inclusion in the presentation 24 to the user 12 content items 20 that are generally popular among users 12. Other considerations may also be included in the selection of content items 20 for inclusion in the presentation 24 to the user 12, such as the removal of duplicate content items 20 (e.g., multiple associate users submitting links to the same resource) and of content items 20 that have previously been presented to the user 12.
However, the inclusion of these comparatively simple aspects in the selection of content items 20 may still be inadequate for improving the value of the presentation 24 of selected content items 20 to the user 12, due in part to the rate at which content items 20 that may be added to the content item set 18.
In view of these scenarios, techniques may be devised to generate presentations 24 of the content item set 18 for the user 12 that may include content items 20 of potential interest to the user 12. In particular, two aspects may be identified and utilized in the selection of content items 20 from the content item set 18. A first aspect relates to the topical relevance of a content item 20 to the interests of the user 12. If one or more topics of potential interest to the user 12 may be identified, and if respective content items 20 may be identified as associated with one or more topics, then the presentation 24 may be generated by selecting content items 20 associated with topics that are of potential interest to the user 12. A second aspect relates to the trending popularity of a content item 20, as indicated by the number of users 12 who (in various ways) express a measure of interest in the content item 20. Content items 20 that have a positive trending popularity, e.g., that are measured as having an increase in popularity over a comparatively short period of time, may be considered potentially interesting to users at large, and in particular to the user 12 to whom the content item set 18 is presented. If content items 20 may be selected from the content item set 18 that demonstrate both an association with topics that are of potential interest to the user 12 and a positive trending popularity, the resulting presentation 24 is likely to be of significant interest to the user 12, thereby improving the interest level of the presentation 24 to the user 12.
Within this exemplary scenario 40, a set of content items 20 of potential interest to the user 12 may be selected and presented to the user 12 in the following manner. The topics 42 of interest to the user 12 may be identified, which may be indicative of content items 20 relating to such topics 42 that may be of potential interest to the user 12. Additionally, for respective content items 20, the topics 20 associated with the content item 20 and the trending popularity 44 of the content item 20 may be identified. Based on this information, content items 22 may be selected that are associated with topics 42 of interest to the user 12, and that demonstrate a positive trending popularity 44. These content items 20 may then be presented to the user, e.g., in a presentation 24 displayed on a display 16 attached to the device 14 of the user 12. In this manner, the content item set 18 may be presented to the user 12 with content of potential interest to the user 12. Additional processing may also be applied to improve further the potential interest of the content; e.g., in the exemplary scenario 40 of
Still another embodiment involves a computer-readable medium comprising processor-executable instructions configured to apply the techniques presented herein. An exemplary computer-readable medium that may be devised in these ways is illustrated in
The techniques discussed herein may be devised with variations in many aspects, and some variations may present additional advantages and/or reduce disadvantages with respect to other variations of these and other techniques. Moreover, some variations may be implemented in combination, and some combinations may feature additional advantages and/or reduced disadvantages through synergistic cooperation. The variations may be incorporated in various embodiments (e.g., the exemplary method 50 of
A first aspect that may vary among embodiments of these techniques relates to the scenarios wherein these techniques may be utilized. As a first example, the content item set 18 may comprise many types of content items 20, such as news items posted by a news source, images in an image database, threads of conversation in a forum, and status messages in a social network. As a second example, the techniques may be implemented in many types of devices 72 having access to the content item set 18, such as the machine storing the content item set 18 or a separate machine that accesses the content item set 18. As a third set, the content items 20 may be presented to the user 12 on many types of devices 14, including a workstation or notebook computer having a display component 16, a tablet or other portable device having a small liquid crystal display (LCD), or a mobile phone presenting content items 20 as audio (e.g., by rendering text through a speech engine.) Those of ordinary skill in the art may devise many scenarios wherein the techniques presented herein may be utilized.
A second aspect that may vary among embodiments of these techniques relates to the manner of identifying topics 42 of potential interest to the user 12 (as may be performed, e.g., by the topical interest identifying component 78 in the exemplary system 76 of
As a fourth example of this second aspect, various artificial intelligence techniques may be invoked to identify topics 42 of interest to the user in an automated manner. In one such embodiment, an automated classifier, such as a Bayesian classifier, may be trained to identify topics 42 of potential interest to various users 12, and may be invoked (e.g., as the topical interest identifying component 78 in the exemplary system 76 of
A third aspect that may vary among embodiments of these techniques relates to the manner of identifying one or more topics 42 associated with a content item 20 (as may be performed, e.g., by the content item evaluating component 80 in the exemplary system 76 of
As a fifth example of this third aspect, the topics 42 associated with a content item 20 may be circumstantially identified. For example, a content item 20 comprising a photo may include a geocode indicating the location of the photo and a date on which the photo was captured, and one or more topics 42 that are likely to be linked with this content item 20 (such as landmarks that are often photographed and that are located near the location of the photo, or an event occurring at the location and time matching the location and date of the photo) may be selected and associated with the content item 20. As a sixth example of this third aspect, a first content item 20 may be compared to a second content item 20 that is already associated with a topic 42, and comparative similarities between these content items 20 may be identified to associate the first content item 20 with the same topic 42 as the second content item 20. For example, a content item 20 comprising a first news article about a particular incident may be compared with other news articles, and if a comparatively similar news article (e.g., written on the same date, sharing particular names and keywords, and linking to the same resources) is identified that relates to one or more topics 42, such topics 42 may also be associated with the first news article.
As a sixth example of this third aspect, artificial intelligence techniques may be utilized to identify topics 42 associated with various content items 20. For example, an automated topical classifier, such as a Bayesian classifier, may be trained to identify topics associated with various content items 20, and following training, may be invoked to identify the topics 42 associated with a particular content item 20. Those of ordinary skill in the art may devise many ways of identifying one or more topics 42 associated with a content item 20 while implementing the techniques presented herein.
A fourth aspect that may vary among embodiments of these techniques relates to the manner of identifying a trending popularity of a content item 20 (as may be performed, e.g., by the content item evaluating component 80 in the exemplary system 76 of
As a second example of this fourth aspect, an embodiment might identify the popularity of a content item 20 based on more active or explicit indicators of user activity. In a first such embodiment, after presenting a content item 20 to a user 12, the embodiment may detect a dwell period of the user 12 on the content item 20 (e.g., by monitoring the amount of time that the user 12 spends reviewing the content item 20, or the extent to which the user 12 reviews the content item 20, such as the amount of an article through which the user 12 may scroll), and may record the dwell period of the user 12 on the content item 20. The popularity of the content item 20 may then be determined according to the dwell periods of one or more users 12 on the content item 20. In a second such embodiment, when presenting a content item 20 to the user 12, the embodiment may present with the content item 20 a popularity selector, such as “Like” and “Do Not Like” buttons associated with the content item 20, which the user 12 may activate to indicate the user's view of the popularity of the content item 20. Upon receiving from the user 12 a user selection of the popularity selector (such as an indication that the user 12 has clicked a “Like” button), the embodiment may record the user selection for the content item 20, and the popularity of the content item 20 may be determined according to the recorded user selections of the popularity selectors for the content item 20. In a third such embodiment, one or more content items 20 may be the subject of a transaction (e.g., a viewing, a downloading or use of a software object, or a purchasing of a resource, and the popularity of the content item 20 may be measured according to the number or rate of such transactions. In a fourth such embodiment, popularity may be identified based on a transfer of content items 20 among users 12, such as a recommendation of the content item 20 by a user 12 to an associate user, or a copying by the user 12 of a content item 20 presented by an associate user 12. For example, an associate user may generate a user content item set, such as a set of content items 20 that are of particular interest to the associate user, and that the associate user wishes to share with others. An embodiment of these techniques may, upon the request of the user 12, present the user content item set of the associate user, and the popularity of respective content items 20 of the user content item set may be identified by detecting a transfer of the content item from the associate user to the user 12 (e.g., the user 12 may select the content item 20 for inclusion in his or her own user content item set.) Moreover, an embodiment of these techniques may also use these metrics to identify a potential interest of the user 12 in one or more topics 42 that are associated with the content items 20 with which the user 12 interacts.
As a third example of this fourth aspect, the metrics of popularity of a particular content item 20 (including those discussed in previous examples of this fourth aspect) may be used in various ways to identify the trending popularity of a content item 20. In a first such embodiment, the trending popularity 44 of a particular content item 20 may be determined by tracking the popularity of the content item 20 over time, e.g., by identifying a first popularity of the content item 20 at a first time, identifying a second popularity of the content item 20 at a second time, and comparing the first popularity and the second popularity to identify the trending popularity 44 of the content item 20. In a second such embodiment, a set of highly popular content items 20 at a particular time may be identified, and content items 20 appearing in the list that have not appeared in a previous list may be identified as having a positive trending popularity. Those of ordinary skill in the art may devise many ways of identifying the trending popularities of various content items 20 while implementing the techniques presented herein.
A fifth aspect that may vary among embodiments of these techniques relates to the manner of selecting content items 20 for inclusion in the presentation 24 to the user 12. While, in accordance with these techniques, the content items 20 selected for inclusion are associated with one or more topics 42 of potential interest to the user 12 and demonstrate a positive trending popularity 44, many ways of selecting content items 20 from the content item set 18 in accordance with these criteria may be devised. As a first example of this fifth aspect, a simple heuristic may be utilized; e.g., all content items 20 meeting these criteria may be selected for presentation to the user 12. As a second example of this fifth aspect, a subset of these content items may be selected 20 in a simple manner; e.g., a particular number of newest content items 20 matching these criteria may be selected, and/or content items 20 that have previously been presented to the user 12 may be removed from the presentation 24.
Other variations of this fifth aspect may demonstrate additional selectivity that may further improve the potential interest of the presentation 24 to the user 12. As a third example of this fifth aspect, mathematical formulae or logical heuristics may be utilized to identify and select content items 20 that are of higher potential interest to the user 12 among all content items 20 meeting these criteria. For example, scores may be attributed to the potential interest of the user 12 in various topics 42 (e.g., topics 42 of great interest to the user 12 having higher scores), to the association of a particular content item 20 with a particular topic 20 (e.g., content items 20 relating predominantly to the topic 20 having higher scores than content items 20 only passingly related to the topic 20), and/or to the trending popularity of the content item 20 (e.g., content items having a higher positive trending popularity having higher scores.) For content items 20 meeting the criteria of the techniques presented herein, a content item score may be computed as a product of these three scores, and the content items 20 having the highest scores may be selected for presentation to the user 12.
As a fourth example of this fifth aspect, various artificial intelligence techniques may be utilized to select content items 20 of potential interest to a user 12. In a first such embodiment, an artificial neural network may be configured (e.g., via training on sample data sets and feedback training mechanisms) to select content items 20 of potential interest to various types of users 12, and the artificial neural network may be invoked to select content items 20 from the content item set 18 for presentation 24 to a particular user 12. In a second such embodiment, an automated classifier, such as a Bayesian classifier, may be trained to classify topics 42 according to a potential interest level of the user 12, e.g., by classifying content items 20 as of high potential interest, medium potential interest, and low potential interest to the user 12, based on the details of the content item 20 (including the topics 42 associated therewith) and the details of the user 12 (including the descriptors of the user 12 stored in a user profile.) An embodiment of these techniques (such as the content item selecting component 82 of the exemplary system 76 of
A sixth aspect that may vary among embodiments of these techniques relates to the manner of presenting the selected content items to the user 12. As a first example, the selected content items may simply be presented as a collection, such as a horizontal or vertical list of textual content items 20 or a tiled thumbnail gallery of image content items 20. In these presentations, the content items 20 may be sorted according to at least one sorting criterion; e.g., the content items 20 may be sorted by date (including a specific moment in time) according to a date sorting criterion (e.g., with newer content items 20 presented before older content items 20); by author 22 according to a content item author sorting criterion (e.g., with content items 20 generated by authors 22 having closer associations with the user 12, such as family members, presented before content items generated by authors 22 having more distant associations with the user 12, such as passing acquaintances); by popularity according to a popularity sorting criterion (e.g., with content items 20 of great popularity presented before content items 20 of less popularity); and/or by trending popularity based on a trending popularity sorting criterion (e.g., with content items 20 having a higher positive trending popularity presented before content items having a lower positive trending popularity.)
As a second example, the selected content items may be presented in view of an association of the user 12 with at least one associate user who may generate and maintain a user content item set, such as a subset of content items 20 that the associate user wishes to share with other users. In a first such embodiment, the device 14 of the user 12 may present the content items 20 of the user content item set of the associate user in a first region of a display 16 attached to the device 14, and may concurrently present the content items 20 selected by the techniques presented herein in a second region of the display 16. For example, the device 14 may display a first column of content items 20 comprising the user content item set of an associate user of the user 12, and a second column, adjacent to the first column, comprising the selected content items that are of potential interest to the user 12. In a second such embodiment, the device 14 may present the selected content items within the user content item set of the associate user of the user 12, e.g., by filtering the user content item set to those content items 20 that also match the criteria of the techniques discussed herein (e.g., associated with at least one topic 20 of potential interest to the user 12 and also having a positive trending popularity), and/or by inserting the selected items into the user content item set of the associate user of the user 12. Those of ordinary skill in the art may devise many ways of presenting the selected content items to the user 12 while implementing the techniques presented herein.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
As used in this application, the terms “component,” “module,” “system”, “interface”, and the like are generally intended to refer to a computer-related entity, either hardware, a combination of hardware and software, software, or software in execution. For example, a component may be, but is not limited to being, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of illustration, both an application running on a controller and the controller can be a component. One or more components may reside within a process and/or thread of execution and a component may be localized on one computer and/or distributed between two or more computers.
Furthermore, the claimed subject matter may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques to produce software, firmware, hardware, or any combination thereof to control a computer to implement the disclosed subject matter. The term “article of manufacture” as used herein is intended to encompass a computer program accessible from any computer-readable device, carrier, or media. Of course, those skilled in the art will recognize many modifications may be made to this configuration without departing from the scope or spirit of the claimed subject matter.
Although not required, embodiments are described in the general context of “computer readable instructions” being executed by one or more computing devices. Computer readable instructions may be distributed via computer readable media (discussed below). Computer readable instructions may be implemented as program modules, such as functions, objects, Application Programming Interfaces (APIs), data structures, and the like, that perform particular tasks or implement particular abstract data types. Typically, the functionality of the computer readable instructions may be combined or distributed as desired in various environments.
In other embodiments, device 102 may include additional features and/or functionality. For example, device 102 may also include additional storage (e.g., removable and/or non-removable) including, but not limited to, magnetic storage, optical storage, and the like. Such additional storage is illustrated in
The term “computer readable media” as used herein includes computer storage media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions or other data. Memory 108 and storage 110 are examples of computer storage media. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVDs) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by device 102. Any such computer storage media may be part of device 102.
Device 102 may also include communication connection(s) 116 that allows device 102 to communicate with other devices. Communication connection(s) 116 may include, but is not limited to, a modem, a Network Interface Card (NIC), an integrated network interface, a radio frequency transmitter/receiver, an infrared port, a USB connection, or other interfaces for connecting computing device 102 to other computing devices. Communication connection(s) 116 may include a wired connection or a wireless connection. Communication connection(s) 116 may transmit and/or receive communication media.
The term “computer readable media” may include communication media. Communication media typically embodies computer readable instructions or other data in a “modulated data signal” such as a carrier wave or other transport mechanism and includes any information delivery media. The term “modulated data signal” may include a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal.
Device 102 may include input device(s) 114 such as keyboard, mouse, pen, voice input device, touch input device, infrared cameras, video input devices, and/or any other input device. Output device(s) 112 such as one or more displays, speakers, printers, and/or any other output device may also be included in device 102. Input device(s) 114 and output device(s) 112 may be connected to device 102 via a wired connection, wireless connection, or any combination thereof. In one embodiment, an input device or an output device from another computing device may be used as input device(s) 114 or output device(s) 112 for computing device 102.
Components of computing device 102 may be connected by various interconnects, such as a bus. Such interconnects may include a Peripheral Component Interconnect (PCI), such as PCI Express, a Universal Serial Bus (USB), firewire (IEEE 1394), an optical bus structure, and the like. In another embodiment, components of computing device 102 may be interconnected by a network. For example, memory 108 may be comprised of multiple physical memory units located in different physical locations interconnected by a network.
Those skilled in the art will realize that storage devices utilized to store computer readable instructions may be distributed across a network. For example, a computing device 120 accessible via network 118 may store computer readable instructions to implement one or more embodiments provided herein. Computing device 102 may access computing device 120 and download a part or all of the computer readable instructions for execution. Alternatively, computing device 102 may download pieces of the computer readable instructions, as needed, or some instructions may be executed at computing device 102 and some at computing device 120.
Various operations of embodiments are provided herein. In one embodiment, one or more of the operations described may constitute computer readable instructions stored on one or more computer readable media, which if executed by a computing device, will cause the computing device to perform the operations described. The order in which some or all of the operations are described should not be construed as to imply that these operations are necessarily order dependent. Alternative ordering will be appreciated by one skilled in the art having the benefit of this description. Further, it will be understood that not all operations are necessarily present in each embodiment provided herein.
Moreover, the word “exemplary” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “exemplary” is not necessarily to be construed as advantageous over other aspects or designs. Rather, use of the word exemplary is intended to present concepts in a concrete fashion. As used in this application, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or”. That is, unless specified otherwise, or clear from context, “X employs A or B” is intended to mean any of the natural inclusive permutations. That is, if X employs A; X employs B; or X employs both A and B, then “X employs A or B” is satisfied under any of the foregoing instances. In addition, the articles “a” and “an” as used in this application and the appended claims may generally be construed to mean “one or more” unless specified otherwise or clear from context to be directed to a singular form.
Also, although the disclosure has been shown and described with respect to one or more implementations, equivalent alterations and modifications will occur to others skilled in the art based upon a reading and understanding of this specification and the annexed drawings. The disclosure includes all such modifications and alterations and is limited only by the scope of the following claims. In particular regard to the various functions performed by the above described components (e.g., elements, resources, etc.), the terms used to describe such components are intended to correspond, unless otherwise indicated, to any component which performs the specified function of the described component (e.g., that is functionally equivalent), even though not structurally equivalent to the disclosed structure which performs the function in the herein illustrated exemplary implementations of the disclosure. In addition, while a particular feature of the disclosure may have been disclosed with respect to only one of several implementations, such feature may be combined with one or more other features of the other implementations as may be desired and advantageous for any given or particular application. Furthermore, to the extent that the terms “includes”, “having”, “has”, “with”, or variants thereof are used in either the detailed description or the claims, such terms are intended to be inclusive in a manner similar to the term “comprising.”
