CN108197331B - User interest exploration method and device - Google Patents
User interest exploration method and device Download PDFInfo
- Publication number
- CN108197331B CN108197331B CN201810148356.8A CN201810148356A CN108197331B CN 108197331 B CN108197331 B CN 108197331B CN 201810148356 A CN201810148356 A CN 201810148356A CN 108197331 B CN108197331 B CN 108197331B
- Authority
- CN
- China
- Prior art keywords
- user
- interest
- tags
- tag
- content
- 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.)
- Active
Links
Images
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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a device for exploring user interests. The user interest exploration method comprises the following steps: obtaining an interest tag, wherein the interest tag is used for identifying recommended content which is possibly interested by a first user; acquiring content needing to be recommended currently; recommending the interest tag and the content needing to be recommended currently to a client of a first user; and exploring the interest degree of the first user in the recommended content identified by the interest tag according to the click condition of the interest tag on the client. By the method and the device, the problem that in the prior art, even if the website provides an interest exploration entrance, the user must actively search the content which is interested in the user is solved.
Description
Technical Field
The invention relates to the field of Internet, in particular to a method and a device for exploring user interests.
Background
Nowadays, when a user browses videos and news, purchases and listens to music on a client side, some recommended contents may be received, and the recommended contents may contain parts which are interested by the user. For example, video recommendations for video websites, news recommendations for news clients, merchandise recommendations for e-commerce websites, and music recommendations for music websites, among others. Currently, for news recommendation of a news client, a mainstream recommendation method is to insert some extended content which is interested by a user into recommended content.
For example, when a user browses news, if the click rate of the user on news content related to science ratio or yaoming is large, the website background considers that the user is interested in sports celebrities, and therefore when news is recommended, the website background recommends the news content related to sports celebrities such as science ratio or yaoming to the user. However, this recommendation method directly inserts the interested contents, and if the interested contents are not properly selected, the experience effect of the user may be affected. In addition, the recommendation method cannot determine other contents that the user is interested in, that is, the range of the contents recommended by the recommendation method is too narrow and lacks of variation, and further, the search for the contents that the user is interested in is limited.
In order to further overcome the problem that the search of the content which is interested by the user is limited due to the recommendation mode, the background of the website provides an interest search entrance for the user, so that when the user is tired of the existing recommended content, the user can enter the entrance to search for other content which is interested by the user. However, although the technical solution overcomes the problem of limited content exploration which is interested by the user, the user must actively search for the content which is interested by the user, and most users are relatively passive when exploring the content which is interested by the user, so that the user cannot flexibly recommend the content which is interested by the user.
Aiming at the problem that in the prior art, even though a website provides an interest exploration entrance, a user must actively search for interested contents, and an effective solution is not provided at present.
Disclosure of Invention
The invention mainly aims to provide a method and a device for exploring user interests, so as to solve the problem that in the prior art, even if a website recommends an interest exploration entrance, a user must actively search for interested contents.
In order to achieve the above object, according to an aspect of an embodiment of the present invention, there is provided a method for exploring user interests. The method for exploring the user interest comprises the following steps: obtaining an interest tag, wherein the interest tag is used for identifying recommended content which is possibly interested by a first user; acquiring content needing to be recommended currently; recommending the interest tag and the content needing to be recommended currently to the client of the first user; and exploring the interest degree of the first user in the recommended content identified by the interest tag according to the click condition of the interest tag on the client.
Further, before obtaining the interest tag, the exploration method further includes: after receiving the recommendation request of the first user, acquiring recommendation content historically recommended to the first user; and acquiring a click record of the first user on the recommended content historically recommended to the first user, wherein the interest tag is acquired according to the click record.
Further, the above-mentioned click condition is the number of clicks of the interest tag on the client, where the interest tag whose number of clicks on the client is greater than a preset number is a tag in which the first user is interested, and the interest tag whose number of clicks on the client is not greater than the preset number is a tag in which it is unknown whether the first user is interested, and acquiring the interest tag includes: randomly selecting a preset number of associated tags from the associated tags of the tags interested by the first user, and using the preset number of associated tags as the interested tags, or randomly selecting a preset number of tags from the associated tags of the tags interested by the first user and the tags not interested by the unknown first user, and using the preset number of tags as the interested tags.
Further, the associated tag of the tags of interest to the first user is determined by: acquiring a first label which is interesting to a second user and a second label which is interesting to the second user, wherein the first label which is interesting to the second user is the same as the label which is interesting to the first user, and the second user comprises a plurality of labels; judging whether the number of the second users is larger than a preset value or not; and if the number of the second users is judged to be larger than the preset value, determining that the second label interested by the second users is the associated label of the label interested by the first users.
Further, before obtaining the interest tag, the exploration method further includes: collecting the website contents clicked by the first user on the client; and marking corresponding interest tags for the website contents clicked by the first user.
In order to achieve the above object, according to another aspect of the embodiments of the present invention, there is provided an exploration apparatus of user interest. The user interest exploration device according to the present invention comprises: a first obtaining unit, configured to obtain an interest tag, where the interest tag is used to identify recommended content that may be of interest to a first user; the second acquisition unit is used for acquiring the content which needs to be recommended currently; a recommending unit, configured to recommend the interest tag and the content to be recommended currently to a client of the first user; and the searching unit is used for searching the interest degree of the first user in the recommended content identified by the interest tag according to the clicking condition of the interest tag on the client.
Further, the search device further includes: a third obtaining unit, configured to obtain, before obtaining the interest tag, recommended content historically recommended to the first user after receiving the recommendation request of the first user; and a fourth obtaining unit, configured to obtain a click record of the first user on the recommended content historically recommended to the first user, where the interest tag is obtained according to the click record.
Further, the click condition is the number of clicks of the interest tag on the client, where an interest tag whose number of clicks on the client is greater than a preset number is a tag in which a first user is interested, and an interest tag whose number of clicks on the client is not greater than the preset number is a tag in which it is unknown whether the first user is interested, and the first obtaining unit includes: a first selecting module, configured to randomly select a preset number of associated tags from the associated tags of the tags interested by the first user, and use the preset number of associated tags as the interest tags, or a second selecting module, configured to randomly select a preset number of tags from the associated tags of the tags interested by the first user and the tags not interested by the unknown first user, and use the preset number of tags as the interest tags.
Further, the search device further includes: a determining unit, configured to determine a tag associated with the tag that is of interest to the first user, wherein the determining unit has: the device comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a first label which is interesting to a second user and a second label which is interesting to the second user, the first label which is interesting to the second user is the same as the label which is interesting to the first user, and the second user comprises a plurality of labels; the judging module is used for judging whether the number of the second users is larger than a preset value or not; and a determining module, configured to determine that the second tag interested by the second user is an associated tag of the tags interested by the first user if it is determined that the number of the second users is greater than the preset value.
Further, the search device further includes: the acquisition unit is used for acquiring website contents clicked by the first user on the client before the interest tag is acquired; and the marking unit is used for marking the corresponding interest tag for the website contents clicked by the first user.
According to the embodiment of the invention, by obtaining the interest tag, the interest tag is used for identifying recommended content which is possibly interested by the first user; acquiring content needing to be recommended currently; recommending the interest tag and the content needing to be recommended currently to a client of a first user; and exploring the interest degree of the first user in the recommended content identified by the interest tag according to the click condition of the interest tag on the client, so that the problem that the user needs to actively search the content which is interested by the user even if an interest exploration entrance is provided for the website in the prior art is solved, and the effect of recommending the content which is interested by the user without depending on the initiative of searching the content which is interested by the user is achieved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow diagram of a method for exploration of user interests in accordance with an embodiment of the present invention;
FIG. 2 is a schematic diagram of an interest tag map according to an embodiment of the present invention; and
FIG. 3 is a schematic diagram of an exploration apparatus of user interests, according to an embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged under appropriate circumstances in order to facilitate the description of the embodiments of the invention herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiment of the invention provides an exploration method of user interests.
FIG. 1 is a flow chart of a method for exploring user interests in accordance with an embodiment of the present invention. As shown in fig. 1, the method for exploring user interest includes the following steps:
step S102, obtaining an interest label, wherein the interest label is used for identifying recommended content which is possibly interested by the first user.
And step S104, acquiring the content which needs to be recommended currently.
And step S106, recommending the interest tag and the content needing to be recommended currently to the client of the first user.
And step S108, exploring the interest degree of the first user in the recommended content identified by the interest tag according to the click condition of the interest tag on the client.
When the content interested by the user is recommended to the user, a user interest exploring device arranged in a background server acquires the interest tag and the content which needs to be recommended currently, and recommends the interest tag and the content to the client of the first user, and further explores the interest degree of the first user in the recommended content identified by the interest tag according to the click condition of the interest tag on the client, wherein the click condition can be the number of clicks or the click rate of the first user on the interest tag.
The interest tags are used to identify recommended content that the first user may be interested in, and specifically, one interest tag may include one or more recommended content that the first user may be interested in, and specifically, in one interest tag, one or more similar recommended content that the user may be interested in may be included, for example, recommended content corresponding to basketball, football, and track and field, respectively, are all sports-related content, and then the recommended content corresponding to them may all be included in one interest tag entitled "sports". The content to be recommended currently may be the content recommended for the first user and of interest, or may be the same content recommended to the general users, where the content to be recommended currently is preferably the content recommended for the first user and of interest. In the present invention, the interest tag and the content that needs to be recommended currently may be recommendations about content such as music, video, news, or shopping.
In practice, it may be determined whether the first user is satisfied with the recommended content by analyzing user short-term behavior data (e.g., the number of clicks the first user has made on the recommended content on the last few days), and if it is determined that the first user is not satisfied with the content previously recommended for the first user, the interest tag recommendation function is activated. After the interest tag recommendation function is activated, recommending interest tags which may be interested in the first user to the first user according to historical behavior data of the first user or external data, wherein the historical behavior data can be the number of clicks of the first user on the previously recommended interest tags for the first user in the last weeks; the external data may be other website content that the first user clicked on, paid attention to, or searched while browsing the other website content (e.g., content such as a microblog, blog, etc.). When recommending interest tags to a first user, the interest tags and the content currently needing to be recommended can be recommended to the client of the user at the same time, and the recommendation forms of the interest tags can be one interest tag at a time or a plurality of interest tags at a time. The interest tag can be displayed in the form of a card, one card content can include a tag name of the interest tag and content corresponding to the interest tag, and a title representing recommended content can be displayed under the tag name of the card, so that the type of the content contained in the interest tag is clear to the first user. When a plurality of interest tags are recommended, the interest tags correspond to a plurality of card contents one by one. When recommending one or more cards, the one or more cards may have an overall title (e.g., recommendations that you may be interested in). Therefore, through the display mode of the interest tag, the first user can directly know whether the content contained in the interest tag is the content which is interested by the first user, and decide whether to click, add or collect the interest tag, and after clicking the interest tag, the first user can browse more contents under the interest tag, wherein the first user can browse the contents after clicking the interest tag, or can add the interest tag corresponding to the contents after browsing the contents, and further recommend more related contents of the contents clicked, added, collected or browsed by the first user.
On the one hand, after the first user adds the interest tags of the first user, the new interest tags can be recorded with higher weight, wherein the new interest tags can also be recommended by assisting with the interest tags mined according to the reading behavior of the user. On the other hand, since it is not always guaranteed that the related content of the newly added interest tags is recommended in the subsequent recommendation of the user by changing the user interest model (the original interest tags of the user are still valid), a certain amount of related content of the newly added interest tags can be forcibly inserted in the subsequent recommendations, so that the user can obviously perceive that the recommendation effect is actually influenced by the newly added interest tags.
According to the embodiment of the invention, because the content and the interest tag which need to be recommended currently are recommended to the client of the user at the same time, the interest degree of the user in the recommended content identified by the interest tag can be explored according to the click condition of the interest tag on the client, the exploration range of the user interest is large, and the interest exploration efficiency is obviously improved compared with that based on a single content. After the interest degree of the user in the recommended interest tag is known, the content interested by the user can be recommended to the user better, so that the experience degree of the user can be improved when the content interested by the user is recommended to the user flexibly, and the user can be guided to explore the content interested by the user subtly. The initiative of searching for the content interested by the user is achieved, and the effect of recommending the content interested by the user is achieved.
Preferably, in an embodiment of the present invention, before obtaining the interest tag, the exploring method may further include:
s2, after receiving the recommendation request of the first user, acquires recommended content historically recommended to the first user.
S4, obtaining a click record of the first user on the recommended content historically recommended to the first user, wherein the interest tag is obtained according to the click record.
Before obtaining the interest tag, a recommendation request of a first user may be received, after the recommendation request of the first user is received, recommended contents historically recommended to the user may be obtained, and according to a click record of the user on the historically recommended contents, the click record may be a click number, a click rate, a click number of the user, or whether the user clicks or not. And then obtaining the interest tag according to the click record. In practice, each time the first user initiates a recommendation request, the recommended contents received by the user last several times and the click records of the recommended contents may be analyzed, and some predefined rules may be used to detect whether the user is not satisfied with the recommendation effect. These rules may be:
rule one, the user's last few recommendation requests are very concentrated in time, but either do not click on the content recommended for them or the click-through rate is below a predefined threshold: this is typically an unsatisfactory response to the recommendation. The user initiates requests continuously, proving to be recommendation demanding, continuous requests but with fewer clicks proving to be less than satisfactory for recommending content, rather than bothering or interrupting the use of the recommendation service for something else.
Rule two, the recommended contents received by the user in the last few times are similar, such as entertainment news or football news, and the click rate of the user is higher, and the click rate of the later few times of recommendations is obviously reduced: this is typically a case where the recommendation is not very diverse. In this case, even if the recommended content meets the user's interest, when the user browses the content too much, it is easy to feel tired about the same type of content.
Rule three, the time interval of the user's last few recommendation requests is significantly increased from usual: this is a typical user churn signal. Assuming that users usually use the recommendation service twice a day, and recently become once every two days, this means that the user's dependency on the recommendation service is reduced, and if some content that the user has not browsed before or some fresh content that the user may be interested in is not recommended, the usage frequency of the user is likely to be further reduced until the user resources are completely lost.
The above are just the most common rules, and more rules can be summarized according to the analysis of the user behavior data. Once the user is found to be not satisfied with the recommendation service through the rules, the interest tag recommendation function can be activated, and the user is actively guided to explore new interests.
And judging the satisfaction degree of the first user to the recommended content according to the rule, and if the satisfaction degree of the first user to the recommended content is not high or is reduced, acquiring the interest tag according to the click record of the first user to the recommended content.
According to the embodiment of the invention, after the recommendation request of the user is received, the interest tag is obtained according to the click record of the user on the historical recommended content, so that better experience can be provided for the user, and the situation that the user recommends too much content when the recommendation request of the user is not available is avoided, so that the user dislikes the too much recommended content.
Preferably, in this embodiment of the present invention, the click condition may be a number of clicks of an interest tag on the client, where an interest tag whose number of clicks on the client is greater than a preset number is a tag interested by the first user, and an interest tag whose number of clicks on the client is not greater than the preset number is a tag unknown whether the first user is interested in, and acquiring the interest tag may include:
s6, randomly selecting a preset number of associated labels from the associated labels of the labels which are interested by the first user, and taking the preset number of associated labels as interest labels.
And S8, randomly selecting a preset number of tags from the associated tags of the tags which are interested by the first user and the tags which are unknown whether the first user is interested in, and taking the preset number of tags as the interest tags.
By comparing the number of clicks of the interest tag on the client with the preset number, the interest tag can be found to be the tag in which the first user is interested or the tag in which whether the first user is interested or not is unknown. When the interest tags are obtained, a preset number of associated tags can be randomly selected from the associated tags of the tags which are interested by the first user, or a preset number of tags can be randomly selected from the associated tags of the tags which are interested by the first user and the tags which are not known whether the first user is interested or not as the interest tags recommended to the user. The purpose of recommending the associated tag of the tag which is interested by the first user is to avoid recommending other interested contents of the interest tag which has high attention of the user, so that the user feels aversion to the repeatedly recommended contents, and more importantly, the associated tag is recommended, so that the exploration range of the user for the interested contents can be expanded, and the user is guided to actively explore other interested contents.
Preferably, in the embodiment of the present invention, the associated tag of the tags of interest to the first user may be determined by:
s10, acquiring a first label which is interesting to a second user and a second label which is interesting to the second user, wherein the first label which is interesting to the second user is the same as the label which is interesting to the first user, and the second user comprises a plurality of labels.
And S12, judging whether the number of the second users is larger than a preset value.
And S14, if the number of the second users is judged to be larger than the preset value, determining that the second label interested by the second users is the associated label of the label interested by the first users.
The second user is different from the first user in the foregoing embodiment, and the second user includes a plurality of users, and the first user is a specific user for whom content and interest tags which need to be recommended currently are recommended. The first label and the second label of the second user are both interesting labels, the first label interesting the second user is the same as the first label interesting the first user, whether the number of the second user is larger than a preset value or not is judged, and if the number of the second user is judged to be larger than the preset value, the second label interesting the second user is determined to be the associated label of the label interesting the first user.
Specifically, the number of second users may be set according to a preset value. The preset value may not be a constant but a function of the distance of the interest tag. As shown in fig. 2, in order to recommend an interest tag, a hierarchical interest tag map needs to be defined first, and fig. 2 shows an example of an interest tag map: for each recommended content, a corresponding tag needs to be found at each level of the tag hierarchy. For example, a recommended content for the business may be labeled as a series of "sports", "football", "international football", which may be manually labeled or automatically labeled by a machine. Multimedia information (such as music and video) can be labeled in advance in a programming mode. If the distance between the first tag and the second tag on the interest tag map is close, the distance may be the number of nodes between the first tag and the second tag, for example, the number of nodes between the tags corresponding to basketball and football is 1, and in the case of close distance, the preset value may be smaller, because in this case, the semantic relevance between the first tag and the second tag is high, and even if only a small number of users are interested in the first tag and the second tag at the same time, the reliability is strong. On the contrary, if the first tag and the second tag are far away from each other in the interest tag graph, the preset value can be larger, because the semantic relevance between the first tag and the second tag is not high enough, and it is necessary to refer to the situation that more users are interested in the first interest tag and the second interest tag at the same time to ensure that the two interest tags are really related, otherwise, the unrelated tags are easily introduced due to the abnormal behaviors of a small number of users. Specifically, let a ═ b × d (t1, t2), where a is the aforementioned preset value, b is a constant, and d (t1, t2) represents the distance between the first label and the second label in the interest label graph, that is, the number of nodes on the shortest path in the label graph.
According to the embodiment of the invention, because the second user is introduced, whether the associated tag of the first tag interested by the first user is the second tag can be judged according to whether the number of the second users paying attention to the first tag and the second tag is larger than the preset value, wherein the first tag is the tag interested by both the first user and the second user. And because the interest label map is introduced, the preset value can be set according to the number of nodes of the first label and the second label on the shortest path in the interest label map. In this way, the found associated interest tags can be made more accurate.
Preferably, in an embodiment of the present invention, before obtaining the interest tag, the exploring method may further include:
and S16, collecting the website contents clicked by the first user on the client.
And S18, marking the corresponding interest tags for the website contents clicked by the first user.
The website content may be content such as a microblog, a blog and the like that is clicked, attended or searched by the first user on the client, and the website content is collected and marked with a corresponding interest tag. In this way, the content recommended for the user can be more diversified, and the recommended content can be more appropriate to the content in which the user is interested.
The embodiment of the invention also provides an exploration device of the user interest. The device can realize the functions thereof through the background server. It should be noted that the user interest exploring apparatus according to the embodiment of the present invention may be used to execute the user interest exploring method provided by the embodiment of the present invention, and the user interest exploring method according to the embodiment of the present invention may also be executed by the user interest exploring apparatus provided by the embodiment of the present invention.
FIG. 3 is a schematic diagram of an exploration apparatus of user interests, according to an embodiment of the present invention. As shown in fig. 3, the user interest exploration apparatus includes: a first acquisition unit 10, a second acquisition unit 20, a recommendation unit 30 and an exploration unit 40.
The first obtaining unit 10 is configured to obtain an interest tag, where the interest tag is used to identify recommended content that is likely to be of interest to the first user.
The second obtaining unit 20 is used for obtaining the content which needs to be recommended currently.
The recommending unit 30 is used for recommending the interest tag and the content which needs to be recommended currently to the client of the first user.
The exploring unit 40 is configured to explore a degree of interest of the first user in the recommended content identified by the interest tag according to a click situation of the interest tag on the client.
When the content interested by the user is recommended to the user, a user interest exploring device arranged in a background server acquires the interest tag and the content which needs to be recommended currently, and recommends the interest tag and the content to the client of the first user, and further explores the interest degree of the first user in the recommended content identified by the interest tag according to the click condition of the interest tag on the client, wherein the click condition can be the number of clicks or the click rate of the first user on the interest tag.
The interest tags are used to identify recommended content that the first user may be interested in, and specifically, one interest tag may include one or more recommended content that the first user may be interested in, and specifically, in one interest tag, one or more similar recommended content that the user may be interested in may be included, for example, recommended content corresponding to basketball, football, and track and field, respectively, are all sports-related content, and then the recommended content corresponding to them may all be included in one interest tag entitled "sports". The content to be recommended currently may be the content recommended for the first user and of interest, or may be the same content recommended to the general users, where the content to be recommended currently is preferably the content recommended for the first user and of interest. In the present invention, the interest tag and the content that needs to be recommended currently may be recommendations about content such as music, video, news, or shopping.
In practice, it may be determined whether the first user is satisfied with the recommended content by analyzing user short-term behavior data (e.g., the number of clicks the first user has made on the recommended content on the last few days), and if it is determined that the first user is not satisfied with the content previously recommended for the first user, the interest tag recommendation function is activated. After the interest tag recommendation function is activated, recommending interest tags which may be interested in the first user to the first user according to historical behavior data of the first user or external data, wherein the historical behavior data can be the number of clicks of the first user on the previously recommended interest tags for the first user in the last weeks; the external data may be other website content that the first user clicked on, paid attention to, or searched while browsing the other website content (e.g., content such as a microblog, blog, etc.). When recommending interest tags to a first user, the interest tags and the content currently needing to be recommended can be recommended to the client of the user at the same time, and the recommendation forms of the interest tags can be one interest tag at a time or a plurality of interest tags at a time. The interest tag can be displayed in the form of a card, one card content can include a tag name of the interest tag and content corresponding to the interest tag, and a title representing recommended content can be displayed under the tag name of the card, so that the type of the content contained in the interest tag is clear to the first user. When a plurality of interest tags are recommended, the interest tags correspond to a plurality of card contents one by one. When recommending one or more cards, the one or more cards may have an overall title (e.g., recommendations that you may be interested in). Therefore, through the display mode of the interest tag, the first user can directly know whether the content contained in the interest tag is the content which is interested by the first user, and decide whether to click, add or collect the interest tag, and after clicking the interest tag, the first user can browse more contents under the interest tag, wherein the first user can browse the contents after clicking the interest tag, or can add the interest tag corresponding to the contents after browsing the contents, and further recommend more related contents of the contents clicked, added, collected or browsed by the first user.
On the one hand, after the first user adds the interest tags of the first user, the new interest tags can be recorded with higher weight, wherein the new interest tags can also be recommended by assisting with the interest tags mined according to the reading behavior of the user. On the other hand, since it is not always guaranteed that the related content of the newly added interest tags is recommended in the subsequent recommendation of the user by changing the user interest model (the original interest tags of the user are still valid), a certain amount of related content of the newly added interest tags can be forcibly inserted in the subsequent recommendations, so that the user can obviously perceive that the recommendation effect is actually influenced by the newly added interest tags.
According to the embodiment of the invention, because the content and the interest tag which need to be recommended currently are recommended to the client of the user at the same time, the interest degree of the user in the recommended content identified by the interest tag can be explored according to the click condition of the interest tag on the client, the exploration range of the user interest is large, and the interest exploration efficiency is obviously improved compared with that based on a single content. After the interest degree of the user in the recommended interest tag is known, the content interested by the user can be recommended to the user better, so that the experience degree of the user can be improved when the content interested by the user is recommended to the user flexibly, and the user can be guided to explore the content interested by the user subtly. The initiative of searching for the content interested by the user is achieved, and the effect of recommending the content interested by the user is achieved.
Preferably, in an embodiment of the present invention, the aforementioned exploring apparatus may further include: a third acquisition unit and a fourth acquisition unit.
The third obtaining unit is used for obtaining the recommended content historically recommended to the first user after receiving the recommendation request of the first user before obtaining the interest tag.
The fourth obtaining unit is used for obtaining a click record of the first user on recommended content historically recommended to the first user, wherein the interest tag is obtained according to the click record.
Before obtaining the interest tag, a recommendation request of a first user may be received, after the recommendation request of the first user is received, recommended contents historically recommended to the user may be obtained, and according to a click record of the user on the historically recommended contents, the click record may be a click number, a click rate, a click number of the user, or whether the user clicks or not. And then obtaining the interest tag according to the click record. In practice, each time the first user initiates a recommendation request, the recommended contents received by the user last several times and the click records of the recommended contents may be analyzed, and some predefined rules may be used to detect whether the user is not satisfied with the recommendation effect. These rules may be:
rule one, the user's last few recommendation requests are very concentrated in time, but either do not click on the content recommended for them or the click-through rate is below a predefined threshold: this is typically an unsatisfactory response to the recommendation. The user initiates requests continuously, proving to be recommendation demanding, continuous requests but with fewer clicks proving to be less than satisfactory for recommending content, rather than bothering or interrupting the use of the recommendation service for something else.
Rule two, the recommended contents received by the user in the last few times are similar, such as entertainment news or football news, and the click rate of the user is higher, and the click rate of the later few times of recommendations is obviously reduced: this is typically a case where the recommendation is not very diverse. In this case, even if the recommended content meets the user's interest, when the user browses the content too much, it is easy to feel tired about the same type of content.
Rule three, the time interval of the user's last few recommendation requests is significantly increased from usual: this is a typical user churn signal. Assuming that users usually use the recommendation service twice a day, and recently become once every two days, this means that the user's dependency on the recommendation service is reduced, and if some content that the user has not browsed before or some fresh content that the user may be interested in is not recommended, the usage frequency of the user is likely to be further reduced until the user resources are completely lost.
The above are just the most common rules, and more rules can be summarized according to the analysis of the user behavior data. Once the user is found to be not satisfied with the recommendation service through the rules, the interest tag recommendation function can be activated, and the user is actively guided to explore new interests.
And judging the satisfaction degree of the first user to the recommended content according to the rule, and if the satisfaction degree of the first user to the recommended content is not high or is reduced, acquiring the interest tag according to the click record of the first user to the recommended content.
According to the embodiment of the invention, after the recommendation request of the user is received, the interest tag is obtained according to the click record of the user on the historical recommended content, so that better experience can be provided for the user, and the situation that the user recommends too much content when the recommendation request of the user is not available is avoided, so that the user dislikes the too much recommended content.
Preferably, in this embodiment of the present invention, the click condition is a number of clicks of an interest tag on the client, where an interest tag whose number of clicks on the client is greater than a preset number is a tag in which the first user is interested, and an interest tag whose number of clicks on the client is not greater than the preset number is a tag in which it is unknown whether the first user is interested, and the first obtaining unit may include: the device comprises a first selection module and a second selection module.
The first selection module is used for randomly selecting a preset number of associated tags from the associated tags of the tags which are interested by the first user, and taking the preset number of associated tags as the interest tags.
The second selection module is used for randomly selecting a preset number of tags from the associated tags of the tags which are interested by the first user and the tags which are unknown whether the first user is interested in, and taking the preset number of tags as the interest tags.
By comparing the number of clicks of the interest tag on the client with the preset number, the interest tag can be found to be the tag in which the first user is interested or the tag in which whether the first user is interested or not is unknown. When the interest tags are obtained, a preset number of associated tags can be randomly selected from the associated tags of the tags which are interested by the first user, or a preset number of tags can be randomly selected from the associated tags of the tags which are interested by the first user and the tags which are not known whether the first user is interested or not as the interest tags recommended to the user. The purpose of recommending the associated tag of the tag which is interested by the first user is to avoid recommending other interested contents of the interest tag which has high attention of the user, so that the user feels aversion to the repeatedly recommended contents, and more importantly, the associated tag is recommended, so that the exploration range of the user for the interested contents can be expanded, and the user is guided to actively explore other interested contents.
Preferably, in an embodiment of the present invention, the aforementioned exploring apparatus may further include: a determination unit for determining an associated tag of the tags of interest to the first user by: the device comprises an acquisition module, a judgment module and a determination module.
The obtaining module is used for obtaining a first label which is interesting to a second user and a second label which is interesting to the second user, wherein the first label which is interesting to the second user is the same as the label which is interesting to the first user, and the second user comprises a plurality of labels.
The judging module is used for judging whether the number of the second users is larger than a preset value.
The determining module is used for determining that the second label interested by the second user is the associated label of the label interested by the first user if the number of the second users is judged to be larger than the preset value.
The second user is different from the first user in the foregoing embodiment, and the second user includes a plurality of users, and the first user is a specific user for whom content and interest tags which need to be recommended currently are recommended. The first label and the second label of the second user are both interesting labels, the first label interesting the second user is the same as the first label interesting the first user, whether the number of the second user is larger than a preset value or not is judged, and if the number of the second user is judged to be larger than the preset value, the second label interesting the second user is determined to be the associated label of the label interesting the first user.
Specifically, the number of second users may be set according to a preset value. The preset value may not be a constant but a function of the distance of the interest tag. As shown in fig. 2, in order to recommend an interest tag, a hierarchical interest tag map needs to be defined first, and fig. 2 shows an example of an interest tag map: for each recommended content, a corresponding tag needs to be found at each level of the tag hierarchy. For example, a recommended content for the business may be labeled as a series of "sports", "football", "international football", which may be manually labeled or automatically labeled by a machine. Multimedia information (such as music and video) can be labeled in advance in a programming mode. If the distance between the first tag and the second tag on the interest tag map is close, the distance may be the number of nodes between the first tag and the second tag, for example, the number of nodes between the tags corresponding to basketball and football is 1, and in the case of close distance, the preset value may be smaller, because in this case, the semantic relevance between the first tag and the second tag is high, and even if only a small number of users are interested in the first tag and the second tag at the same time, the reliability is strong. On the contrary, if the first tag and the second tag are far away from each other in the interest tag graph, the preset value can be larger, because the semantic relevance between the first tag and the second tag is not high enough, and it is necessary to refer to the situation that more users are interested in the first interest tag and the second interest tag at the same time to ensure that the two interest tags are really related, otherwise, the unrelated tags are easily introduced due to the abnormal behaviors of a small number of users. Specifically, let a ═ b × d (t1, t2), where a is the aforementioned preset value, b is a constant, and d (t1, t2) represents the distance between the first label and the second label in the interest label graph, that is, the number of nodes on the shortest path in the label graph.
According to the embodiment of the invention, because the second user is introduced, whether the associated tag of the first tag interested by the first user is the second tag can be judged according to whether the number of the second users paying attention to the first tag and the second tag is larger than the preset value, wherein the first tag is the tag interested by both the first user and the second user. And because the interest label map is introduced, the preset value can be set according to the number of nodes of the first label and the second label on the shortest path in the interest label map. In this way, the found associated interest tags can be made more accurate.
Preferably, in an embodiment of the present invention, the aforementioned exploring apparatus may further include: the device comprises a collecting unit and a marking unit.
The acquisition unit acquires website contents clicked by a first user on the client before acquiring the interest tag.
The marking unit is used for marking the corresponding interest tag for the website contents clicked by the first user.
The website content may be content such as a microblog, a blog and the like that is clicked, attended or searched by the first user on the client, and the website content is collected and marked with a corresponding interest tag. In this way, the content recommended for the user can be more diversified, and the recommended content can be more appropriate to the content in which the user is interested.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implementing, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a mobile terminal, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A method for exploring user interests, comprising:
obtaining an interest tag, wherein the interest tag is used for identifying recommended content which is possibly interested by a first user;
acquiring content needing to be recommended currently;
recommending the interest tag and the content needing to be recommended currently to a client of the first user; and
exploring the interest degree of the first user in the recommended content identified by the interest tag according to the click condition of the interest tag on the client;
after detecting that the first user browses or collects a first interest tag, setting a weight higher than a threshold value for the first interest tag, and forcibly inserting content corresponding to the first interest tag when recommending content for a subsequent preset number of times;
the click condition is the click times of the interest tag on the client, wherein the interest tag with the click times larger than the preset times on the client is a tag which is interested by the first user, the interest tag with the click times not larger than the preset times on the client is a tag which is unknown whether the first user is interested in, and the obtaining of the interest tag comprises the following steps: randomly selecting a preset number of associated tags from the associated tags of the tags interested by the first user, and using the preset number of associated tags as the interest tags, or randomly selecting a preset number of tags from the associated tags of the tags interested by the first user and the tags not interested by the unknown first user, and using the preset number of tags as the interest tags.
2. The method of claim 1, wherein prior to obtaining the interest tags, the method further comprises:
after receiving a recommendation request of the first user, acquiring recommendation content historically recommended to the first user; and
acquiring a click record of the first user on the recommended content historically recommended to the first user,
and obtaining the interest tag according to the click record.
3. The method of claim 1, wherein the associated tags of the tags of interest to the first user are determined by:
acquiring a first label which is interesting to a second user and a second label which is interesting to the second user, wherein the first label which is interesting to the second user is the same as the label which is interesting to the first user, and the second user comprises a plurality of labels;
judging whether the number of the second users is larger than a preset value or not; and
and if the number of the second users is judged to be larger than the preset value, determining that the second tags interested by the second users are the associated tags of the tags interested by the first users.
4. The method of claim 1, wherein prior to obtaining the interest tags, the method further comprises:
collecting website contents clicked by the first user on the client; and
and marking the corresponding interest tags for the website contents clicked by the first user.
5. An apparatus for exploring user interests, comprising:
a first obtaining unit configured to obtain an interest tag for identifying recommended content that is likely to be of interest to a first user;
the second acquisition unit is used for acquiring the content which needs to be recommended currently;
the recommending unit is used for recommending the interest tag and the content needing to be recommended currently to the client of the first user; and
the searching unit is used for searching the interest degree of the first user in the recommended content identified by the interest tag according to the clicking condition of the interest tag on the client;
after detecting that the first user browses or collects a first interest tag, setting a weight higher than a threshold value for the first interest tag, and forcibly inserting content corresponding to the first interest tag when recommending content for a subsequent preset number of times;
the click condition is the click times of the interest tag on the client, wherein the interest tag with the click times larger than a preset number on the client is a tag which is interested by a first user, and the interest tag with the click times not larger than the preset number on the client is a tag which is unknown whether the first user is interested or not, and the first obtaining unit includes: the first selection module is configured to randomly select a preset number of associated tags from the associated tags of the tags interested by the first user, and use the preset number of associated tags as the interest tags, or the second selection module is configured to randomly select a preset number of tags from the associated tags of the tags interested by the first user and the tags not interested by the unknown first user, and use the preset number of tags as the interest tags.
6. The apparatus for exploring user interest of claim 5, further comprising:
a third obtaining unit, configured to obtain, before obtaining the interest tag, recommended content historically recommended to the first user after receiving a recommendation request of the first user; and
a fourth obtaining unit configured to obtain a click record of the first user on recommended content historically recommended to the first user,
and obtaining the interest tag according to the click record.
7. The apparatus for exploring user interest of claim 5, further comprising: a determination unit configured to determine an associated tag of the tags of interest to the first user by:
the device comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a first label which is interesting to a second user and a second label which is interesting to the second user, the first label which is interesting to the second user is the same as the label which is interesting to the first user, and the second user comprises a plurality of labels;
the judging module is used for judging whether the number of the second users is larger than a preset value or not; and
and the determining module is used for determining that the second label interested by the second user is the associated label of the label interested by the first user if the number of the second users is judged to be larger than the preset value.
8. The apparatus for exploring user interest of claim 5, further comprising:
the acquisition unit is used for acquiring website contents clicked by the first user on the client before the interest tag is acquired; and
and the marking unit is used for marking the corresponding interest tag for the website contents clicked by the first user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810148356.8A CN108197331B (en) | 2015-01-21 | 2015-01-21 | User interest exploration method and device |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810148356.8A CN108197331B (en) | 2015-01-21 | 2015-01-21 | User interest exploration method and device |
| CN201510031206.5A CN104537115B (en) | 2015-01-21 | 2015-01-21 | The heuristic approach and device of user interest |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510031206.5A Division CN104537115B (en) | 2015-01-21 | 2015-01-21 | The heuristic approach and device of user interest |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108197331A CN108197331A (en) | 2018-06-22 |
| CN108197331B true CN108197331B (en) | 2020-02-04 |
Family
ID=52852643
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510031206.5A Active CN104537115B (en) | 2015-01-21 | 2015-01-21 | The heuristic approach and device of user interest |
| CN201810148356.8A Active CN108197331B (en) | 2015-01-21 | 2015-01-21 | User interest exploration method and device |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510031206.5A Active CN104537115B (en) | 2015-01-21 | 2015-01-21 | The heuristic approach and device of user interest |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN104537115B (en) |
Families Citing this family (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106445969B (en) * | 2015-08-11 | 2019-03-05 | 北京字节跳动科技有限公司 | A kind of overall situation interest explores recommended method and device |
| CN106469392A (en) * | 2015-08-20 | 2017-03-01 | 阿里巴巴集团控股有限公司 | Select and recommend to show the method and device of object |
| CN105303398B (en) * | 2015-09-29 | 2020-03-27 | 努比亚技术有限公司 | Information display method and system |
| CN107408116B (en) * | 2015-12-14 | 2021-02-02 | 微软技术许可有限责任公司 | Using dynamic knowledge graphs to facilitate discovery of information items |
| WO2017128076A1 (en) * | 2016-01-26 | 2017-08-03 | 段春燕 | Information display method for news pushing technology, and pushing system |
| CN105827690A (en) * | 2016-03-04 | 2016-08-03 | 乐视网信息技术（北京）股份有限公司 | Information push method according to user preferences and information push server thereof |
| CN106530015B (en) * | 2016-12-08 | 2020-02-11 | 腾讯科技（深圳）有限公司 | Information delivery control method and device |
| CN106649677B (en) * | 2016-12-15 | 2019-11-08 | 天脉聚源(北京)传媒科技有限公司 | A kind of news sending method and device |
| CN107229666B (en) * | 2016-12-30 | 2019-02-26 | 北京字节跳动科技有限公司 | A kind of interest heuristic approach and device based on recommender system |
| CN110235525B (en) * | 2017-01-27 | 2022-04-12 | 昕诺飞控股有限公司 | Recommendation engine for lighting systems |
| CN108255900A (en) | 2017-03-22 | 2018-07-06 | 广州市动景计算机科技有限公司 | Recommend news rendering method, equipment, browser and electronic equipment |
| CN107222566B (en) * | 2017-07-06 | 2020-09-04 | 阿里巴巴（中国）有限公司 | Information pushing method and device and server |
| CN109388760B (en) * | 2017-08-03 | 2023-04-07 | 腾讯科技（北京）有限公司 | Recommendation label obtaining method, media content recommendation method, device and storage medium |
| CN107483256B (en) * | 2017-08-24 | 2020-02-18 | 合肥工业大学 | Label extraction method for networked data stream |
| CN108182254A (en) * | 2017-12-29 | 2018-06-19 | 北京奇虎科技有限公司 | A kind of recommendation treating method and apparatus |
| CN108052666A (en) * | 2017-12-29 | 2018-05-18 | 北京奇虎科技有限公司 | A kind of content recommendation method and device |
| CN108073719A (en) * | 2017-12-29 | 2018-05-25 | 北京奇虎科技有限公司 | A kind of content recommendation method and device |
| CN108230101B (en) * | 2017-12-29 | 2022-05-17 | 百度在线网络技术（北京）有限公司 | Information recommendation method and device |
| CN108595461B (en) * | 2018-01-05 | 2021-03-16 | 武汉斗鱼网络科技有限公司 | Interest exploration method, storage medium, electronic device and system |
| CN109189899A (en) * | 2018-08-01 | 2019-01-11 | 优视科技新加坡有限公司 | Content interest acquisition and content-data recommended method, device, equipment/terminal/server and storage medium |
| CN109189954B (en) * | 2018-09-07 | 2021-04-16 | 网易传媒科技（北京）有限公司 | Content recommendation method and device |
| CN110969222A (en) * | 2018-09-29 | 2020-04-07 | 西门子股份公司 | Information providing method and system |
| CN109684548B (en) * | 2018-11-30 | 2024-02-09 | 索信达(深圳)软件技术有限公司 | Data recommendation method based on user map |
| CN110097397B (en) * | 2019-04-04 | 2022-09-13 | 北京字节跳动网络技术有限公司 | Feedback-based information pushing method and device and electronic equipment |
| CN110996142B (en) * | 2019-11-08 | 2021-12-07 | 北京奇艺世纪科技有限公司 | Video recall method and device, electronic equipment and storage medium |
| CN110929052B (en) * | 2019-12-03 | 2023-04-18 | 北京奇艺世纪科技有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
| CN111008869A (en) * | 2019-12-05 | 2020-04-14 | 秒针信息技术有限公司 | Advertisement recommendation method and device, electronic equipment and storage medium |
| CN111291220B (en) * | 2020-01-20 | 2021-07-13 | 北京字节跳动网络技术有限公司 | Label display method and device, electronic equipment and computer readable medium |
| CN111339418B (en) * | 2020-02-26 | 2023-07-18 | 抖音视界有限公司 | Page display method, page display device, electronic equipment and computer readable medium |
| CN111680219B (en) * | 2020-06-09 | 2023-10-20 | 深圳市雅阅科技有限公司 | Content recommendation method, device, equipment and readable storage medium |
| CN113486244A (en) * | 2021-07-14 | 2021-10-08 | 深圳市点购电子商务控股股份有限公司 | User interest exploration method and device |
| CN114036403B (en) * | 2022-01-07 | 2022-03-25 | 智者四海（北京）技术有限公司 | User interest detection method, device and storage medium |
| CN116628313A (en) * | 2023-03-31 | 2023-08-22 | 北京百度网讯科技有限公司 | Content recommendation method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102917269A (en) * | 2012-09-29 | 2013-02-06 | 青岛海信电器股份有限公司 | Television program recommendation system and method |
| CN103399883A (en) * | 2013-07-19 | 2013-11-20 | 百度在线网络技术（北京）有限公司 | Method and system for performing personalized recommendation according to user interest points/concerns |
| CN103729360A (en) * | 2012-10-12 | 2014-04-16 | 腾讯科技（深圳）有限公司 | Interest label recommendation method and system |
| CN104111941A (en) * | 2013-04-18 | 2014-10-22 | 阿里巴巴集团控股有限公司 | Method and equipment for information display |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101770480A (en) * | 2008-12-29 | 2010-07-07 | 北京搜狗科技发展有限公司 | Method and device for generating channel and method and system for advertising |
| CN101477556B (en) * | 2009-01-22 | 2010-09-15 | 苏州智讯科技有限公司 | Method for discovering hot spot in internet mass information |
| US20140180760A1 (en) * | 2011-03-18 | 2014-06-26 | Telefonica, S.A. | Method for context-aware recommendations based on implicit user feedback |
| CN102693248A (en) * | 2011-04-14 | 2012-09-26 | 天脉聚源(北京)传媒科技有限公司 | Network information searching method and system |
| CN104239571B (en) * | 2014-09-30 | 2018-04-24 | 北京奇虎科技有限公司 | It is a kind of to carry out using the method and apparatus recommended |
-
2015
- 2015-01-21 CN CN201510031206.5A patent/CN104537115B/en active Active
- 2015-01-21 CN CN201810148356.8A patent/CN108197331B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102917269A (en) * | 2012-09-29 | 2013-02-06 | 青岛海信电器股份有限公司 | Television program recommendation system and method |
| CN103729360A (en) * | 2012-10-12 | 2014-04-16 | 腾讯科技（深圳）有限公司 | Interest label recommendation method and system |
| CN104111941A (en) * | 2013-04-18 | 2014-10-22 | 阿里巴巴集团控股有限公司 | Method and equipment for information display |
| CN103399883A (en) * | 2013-07-19 | 2013-11-20 | 百度在线网络技术（北京）有限公司 | Method and system for performing personalized recommendation according to user interest points/concerns |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104537115A (en) | 2015-04-22 |
| CN104537115B (en) | 2019-07-16 |
| CN108197331A (en) | 2018-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108197331B (en) | User interest exploration method and device | |
| US10095771B1 (en) | Clustering and recommending items based upon keyword analysis | |
| US9300755B2 (en) | System and method for determining information reliability | |
| TWI636416B (en) | Method and system for multi-phase ranking for content personalization | |
| KR101060487B1 (en) | Apparatus and method for content recommendation using tag cloud | |
| CN103229169B (en) | Content providing and system | |
| US8566315B1 (en) | Sequenced video segment mix | |
| CN101999121B (en) | Recommendation information evaluation apparatus and recommendation information evaluation method | |
| CN108960975A (en) | Personalized Precision Marketing Method, server and storage medium based on user's portrait | |
| US9354790B2 (en) | Dynamically selecting and ordering facets and facet values in a user interface based on user preference | |
| CN109977296B (en) | Information pushing method, device, equipment and storage medium | |
| CN106610988B (en) | Webpage recommendation method and recommendation device | |
| JP2009181468A (en) | Image search log collection system, image search log collection method and program | |
| CN104462336A (en) | Information pushing method and device | |
| CN105915956A (en) | Video content recommendation method, device, server and system | |
| US20150213136A1 (en) | Method and System for Providing a Personalized Search List | |
| CN103207917A (en) | Method for marking multimedia content and method and system for generating recommended content | |
| CN105027123A (en) | Recommending content based on proxy-based preference indications | |
| KR100987058B1 (en) | Method and system for providing advertising service using the keywords of internet contents and program recording medium | |
| CN114417157B (en) | Data pushing method and device, computer equipment and computer medium | |
| US20140214541A1 (en) | Method and system for user-controlled rendering of mobile advertisements | |
| JP6424194B2 (en) | Information processing apparatus, information processing method, and information processing program | |
| JP2002304568A (en) | Correlation item detecting method and its device and recommendation item introducing method and its device and correlation item detecting program and recommendation item introducing program | |
| CN112288516A (en) | Information recommendation method and device, storage medium and electronic equipment | |
| KR102187135B1 (en) | Method for recommending book and service device supporting the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Room 10a, building 2, No. 48, Zhichun Road, Haidian District, Beijing 100098 Patentee after: Beijing Douyin Information Service Co.,Ltd. Address before: Room 10a, building 2, No. 48, Zhichun Road, Haidian District, Beijing 100098 Patentee before: BEIJING BYTEDANCE TECHNOLOGY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |