CN114302156A - Anchor dynamic information recommendation method, device, system and storage medium - Google Patents
Anchor dynamic information recommendation method, device, system and storage medium Download PDFInfo
- Publication number
- CN114302156A CN114302156A CN202111512008.2A CN202111512008A CN114302156A CN 114302156 A CN114302156 A CN 114302156A CN 202111512008 A CN202111512008 A CN 202111512008A CN 114302156 A CN114302156 A CN 114302156A
- Authority
- CN
- China
- Prior art keywords
- anchor
- dynamic information
- client
- live
- recommendation
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012550 audit Methods 0.000 claims abstract description 21
- 230000003993 interaction Effects 0.000 claims abstract description 14
- 230000000875 corresponding effect Effects 0.000 claims description 9
- 230000002596 correlated effect Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000002452 interceptive effect Effects 0.000 description 5
- 230000001149 cognitive effect Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000014759 maintenance of location Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000019771 cognition Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241000238557 Decapoda Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Abstract
The application relates to a method, equipment, a system and a storage medium for recommending anchor dynamic information, wherein the method comprises the following steps: acquiring a plurality of pieces of anchor dynamic information released within a preset time length; acquiring at least one piece of reference information of each piece of anchor dynamic information; the reference information comprises interaction data, release duration or validity audit score of the anchor dynamic information; determining a recommendation score of the live broadcast dynamic information according to at least one reference information of the main broadcast dynamic information; recommending the anchor dynamic information with the recommendation score larger than a first preset value to the client. The realization can automatically recommend hot or high-timeliness anchor dynamic information to the client.
Description
Technical Field
The present application relates to the field of internet information interaction, and in particular, to a method, device, system, and storage medium for recommending anchor dynamic information.
Background
Live broadcast is increasingly popular with users and is becoming one of the mainstream expressions of the internet. For online live broadcasting, a live broadcasting channel can be established by an anchor client, the anchor client uploads online live broadcasting content to a server, and the server broadcasts the online live broadcasting content to audience clients logged in the live broadcasting channel for the audiences of the audience clients to watch.
In a related live broadcast platform, besides live broadcast activities, a anchor can also release some dynamic information according to actual conditions, and the dynamic information can be displayed in a related interface (such as an anchor recommendation interface). At present, the anchor dynamic information displayed on a related interface (such as an anchor recommendation interface) is configured manually by an operator, so that the configuration efficiency is low and the recommendation effect is poor.
Disclosure of Invention
Based on the above, the application provides a method, a device, a system and a storage medium for recommending anchor dynamic information.
According to a first aspect of an embodiment of the present application, there is provided a method for recommending anchor dynamic information, including:
acquiring a plurality of pieces of anchor dynamic information released within a preset time length;
acquiring at least one piece of reference information of each piece of anchor dynamic information; the reference information comprises interaction data, release duration or validity audit score of the anchor dynamic information;
determining a recommendation score of the live broadcast dynamic information according to at least one reference information of the main broadcast dynamic information;
recommending the anchor dynamic information with the recommendation score larger than a first preset value to the client.
Optionally, the interaction data includes the number of viewers, the number of shares, the number of praises, and/or the number of comments of the anchor dynamic information;
the recommendation score is in positive correlation with the number of watching people, the number of sharing, the number of praise and/or the number of comments of the anchor dynamic information;
the recommendation score and the release time growth form a negative correlation relationship; and
the recommendation score is positively correlated with the validity audit score.
Optionally, the method further comprises:
acquiring historical viewing data of the client according to viewing trigger related to the live broadcast dynamic information in the client, wherein the historical viewing data comprises anchor broadcast dynamic information viewed in the client;
the recommending the anchor dynamic information of which the recommendation score is greater than a first preset value to the client comprises the following steps:
recommending anchor dynamic information to the client, wherein the recommendation score is larger than a first preset value and does not belong to the historical viewing data.
Optionally, the method further comprises:
acquiring live broadcast watching data of the client in a live broadcast platform;
determining the intimacy between the client and a main broadcast indicated by the live viewing data according to the live viewing data;
the recommending the anchor dynamic information of which the recommendation score is greater than a first preset value to the client comprises the following steps:
recommending anchor dynamic information to the client, wherein the recommendation score is larger than a first preset value, and the anchor dynamic information is issued by an anchor with the intimacy degree larger than a second preset value.
Optionally, the live viewing data comprises at least one of: a live viewing duration or a live viewing time point related to one or more anchor;
wherein the affinity is positively correlated with the live viewing time; and
the intimacy is in negative correlation with the time difference between the live viewing time point and the current time point.
Optionally, the recommending, to the client, the anchor dynamic information whose recommendation score is greater than the first preset value includes:
determining the anchor to be recommended and the category thereof corresponding to the anchor dynamic information with the recommendation score larger than a first preset value;
inputting the live broadcast viewing data of the client and the category to which the anchor to be recommended belongs into a pre-trained anchor recommendation model, and predicting the intimacy between the client and the anchor to be recommended by the anchor recommendation model according to the relationship between the live broadcast viewing data and the category to which the anchor to be recommended belongs to obtain an intimacy prediction result;
recommending anchor dynamic information issued by the anchor to be recommended, of which the intimacy prediction result is greater than a second preset value, to the client.
Optionally, the anchor recommendation model is trained by:
acquiring live broadcast viewing data of a plurality of clients, a category to which a anchor indicated by the live broadcast viewing data belongs, and a truth value of intimacy between the clients and the anchor determined according to the live broadcast viewing data;
inputting the live broadcast viewing data of the plurality of clients and the category to which the anchor belongs into a preset model, and determining an intimacy degree predicted value of the clients and the anchor by the preset model according to the relationship between the live broadcast viewing data and the category to which the anchor belongs;
and adjusting parameters of the preset model according to the difference between the intimacy degree true value and the intimacy degree predicted value to obtain the anchor recommendation model.
Optionally, the live viewing data is data of the client within the preset time period.
According to a second aspect of embodiments herein, there is provided an electronic device comprising a memory for storing executable instructions and a processor;
wherein the processor, when executing the executable instructions, performs the steps of the method of any one of the first aspect.
According to a third aspect of the embodiments of the present application, a recommendation system is provided, which includes a server and a client;
the server is configured to execute the method of any one of the first aspect;
and the client is used for displaying the anchor dynamic information recommended by the server in a display interface.
According to a fourth aspect of embodiments herein, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of any one of the first aspects.
The method for recommending the dynamic anchor information can acquire a plurality of pieces of dynamic anchor information issued within a preset time length, comprehensively evaluates the dynamic anchor information according to at least one piece of reference information (such as interactive data, issuing time length or validity auditing score) of the dynamic anchor information, determines the recommendation score of each piece of dynamic anchor information, and can recommend the dynamic anchor information of which the recommendation score is greater than a first preset value to a client. According to the method and the device, hot or high-timeliness anchor dynamic information can be automatically recommended to the client, the recommendation efficiency and the recommendation effect are improved, and the user viscosity, the user retention rate and the user cognition degree of the anchor can be further effectively improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
Fig. 1 is a schematic structural diagram illustrating a live network architecture according to an embodiment.
Fig. 2 is a diagram illustrating a display of anchor dynamic information, according to an embodiment.
Fig. 3 is a flowchart illustrating a method for recommending anchor dynamic information according to an embodiment.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment.
Fig. 5 is a schematic structural diagram of a recommendation system according to an embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
In order to explain the anchor dynamic information recommendation method provided by the embodiment of the present application, an exemplary description is first performed on a live network architecture of a live platform: as shown in fig. 1, fig. 1 is a schematic diagram of a live network architecture according to an exemplary embodiment of the present application. The live network architecture may include a server 100 and a plurality of terminals 200. The server 100 may be referred to as a background server, a component server, or the like, and is configured to provide a background service of live webcasting. The server 100 may include a server, a server cluster, or a cloud platform, and may also be a program for executing a service. The terminal may be a smart terminal having a live webcast function, for example, the smart terminal may be a smart phone, a tablet computer, a PDA (personal digital assistant), a multimedia player, a wearable device, and the like.
In a live network configuration, terminals 200 may be divided into anchor terminals 201 and viewer terminals 202. The anchor terminal 201 has an anchor client installed therein, and the viewer terminal 202 has a viewer client installed therein. The anchor client and the viewer client may be the same live video application, i.e. the live video application has both live mode and viewer mode, e.g. "YY live"; the anchor client and viewer client may also be different types of live video applications. For the case that the anchor client and the viewer client are the same video live application, when the video live application enters the anchor mode, the video live application may be referred to as an anchor client (hereinafter referred to as "anchor"); when a live video application enters viewer mode, the live video application may be referred to as a viewer client (hereinafter "viewer side"). The viewer terminal 202, in which the viewer client is installed, may view live video uploaded by the anchor client. The anchor terminal 201 and the viewer terminal 202 may be connected to the server 100 through a wired network, a wireless network, or a data transmission line.
In the live network architecture, a viewer can log in to the server 100 of the live network architecture through a viewer client on the viewer terminal 202, an anchor can log in to the server 100 of the live network architecture through an anchor client on the anchor terminal 201, and the viewer and the anchor enter into the same live channel. The anchor client uploads the online live content to the server 100, and the server 100 sends the online live content to the audience client logged into the online live channel for the audience of the audience client to watch. The audience at the audience client may not only view the live content uploaded by the anchor client, but also interact with the anchor of the live channel or other audiences through the server 100, and in order to increase the interest of the interaction between the anchor and the audience, for example, a virtual gift giving function is provided, and the audience may give a virtual gift to the anchor through the virtual gift giving function.
In a related live broadcast platform, in addition to live broadcast activities, the anchor may also issue some dynamic information according to an actual situation, and the dynamic information may be displayed in a related interface (such as an anchor recommendation interface), for example, in the anchor recommendation interface shown in fig. 2, the anchor dynamic information may be displayed in the dynamic information display area 11, and the anchor to be recommended and a live broadcast channel entry thereof are displayed in other areas, for example, when a user clicks on the anchor to be recommended, the anchor may enter a live broadcast channel corresponding to the anchor. At present, the anchor dynamic information displayed on a related interface (such as an anchor recommendation interface) is configured manually by an operator, so that the configuration efficiency is low and the recommendation effect is poor.
For the problems in the related art, an embodiment of the present application provides a method for recommending anchor dynamic information, which can obtain a plurality of pieces of anchor dynamic information published within a preset time length, perform comprehensive evaluation on the anchor dynamic information according to at least one reference information (such as interactive data, publication time length, or validity check score) of the anchor dynamic information, determine a recommendation score of each piece of anchor dynamic information, and further recommend the anchor dynamic information of which the recommendation score is greater than a first preset value to a client. According to the method and the device, hot or high-timeliness anchor dynamic information can be automatically recommended to the client, the recommendation efficiency and the recommendation effect are improved, and the user viscosity, the user retention rate and the user cognition degree of the anchor can be further effectively improved.
In some embodiments, the anchor dynamic information recommendation method provided in the embodiment of the present application may be executed by an electronic device, for example, the electronic device may be a server 100 in a live network architecture, or may also be a terminal 200 in the live network architecture, or may also be another computing device different from the server 100 or the terminal 200, such as an intelligent terminal, a computer, a server, or a cloud server, and the other computing device may be connected to the server 100 so as to obtain related information (such as anchor dynamic information and reference information thereof).
Illustratively, the anchor dynamic information recommendation method may be a computer software product integrated in the electronic device. Illustratively, the electronic device includes at least a memory and a processor, and the processor in the electronic device may execute executable instructions stored in the memory that indicate the anchor dynamic information recommendation method.
It should be noted that, in the embodiment of the present application, the relevant data (such as the anchor dynamic information, the reference information of the anchor dynamic information, and the like) to be acquired is published by the user or acquired when the user allows it.
Referring to fig. 3, fig. 3 is a schematic flowchart of a anchor dynamic information recommendation method according to an embodiment of the present application, which is described by taking an example that the anchor dynamic information recommendation method is executed by a server 100 in a live broadcast network architecture, where the method includes:
in step S101, a plurality of pieces of anchor dynamic information issued within a preset duration are acquired.
In step S102, at least one piece of reference information of each piece of anchor dynamic information is acquired; the reference information comprises interaction data, release duration or validity audit score of the anchor dynamic information.
In step S103, a recommendation score of the live dynamic information is determined according to at least one reference information of the anchor dynamic information.
In step S104, anchor dynamic information with the recommendation score greater than a first preset value is recommended to the client.
It can be understood that the specific value of the preset duration may be specifically set according to an actual application scenario, and this embodiment does not limit this, for example, the preset duration may be anchor dynamic information released within the last 10 days, 20 days, or 30 days. The anchor dynamic information includes, but is not limited to, text information, audio information, image information, or video information. The anchor dynamic information is issued by an anchor account (or anchor client), and non-anchor accounts such as audience accounts (or audience clients) cannot issue the anchor dynamic information.
When the server side obtains a plurality of pieces of anchor dynamic information released within a preset time length, at least one piece of reference information of each piece of anchor dynamic information can be obtained together, wherein the reference information includes but is not limited to interaction data, releasing time length or validity auditing score of the anchor dynamic information.
Illustratively, the interaction data includes, but is not limited to, at least one of: the interactive data can be used as a reference of the user for the interest degree and the wonderful degree of the content, and can reflect the popularity degree of the anchor dynamic information to a certain extent, for example, the more the number of the users viewing the anchor dynamic information, the more the number of the users sharing the anchor dynamic information, the more the number of the users likes the anchor dynamic information, the more the anchor dynamic information, and the more the anchor dynamic information.
The release duration represents a time difference between the release time point of the anchor dynamic information and the current time point, the release duration can reflect the timeliness of the anchor dynamic information to a certain extent, and the shorter the release duration, the higher the timeliness of the anchor dynamic information.
The validity audit score represents the recommendable degree of the anchor dynamic information on the basis of illegal contents which do not violate the regulations of a live broadcast platform; in an example, the validity audit score may be obtained by a server evaluating the anchor dynamic information according to a preset audit rule, for example, the audit rule may include illegal content specified by the live broadcast platform, and the server may match the illegal content with the anchor dynamic information to determine similarity between the illegal content and the anchor dynamic information, where the higher the similarity is, the higher the probability indicating that the anchor dynamic information is violated is, the lower the validity audit score is, the lower the similarity is, the lower the probability indicating that the anchor dynamic information is violated is, or even no violation is present, the higher the validity audit score is. In another example, the validity audit score may also be manually scored by an operator based on the content of violations specified by the live platform. The higher the validity audit score is, the higher the recommendability degree of the anchor dynamic information is.
In some embodiments, after obtaining a plurality of pieces of anchor dynamic information and at least one piece of reference information thereof, the server may determine a recommendation score of the live dynamic information according to the at least one piece of reference information of each piece of anchor dynamic information (interactive data, distribution duration, and/or validity audit score of the anchor dynamic information).
Illustratively, the interaction data includes the number of viewers, the number of shares, the number of likes or the number of comments of the anchor dynamic information, and it is mentioned above that, the larger the number of viewers, the number of shares, the number of likes or the number of comments of the anchor dynamic information is, the more popular the anchor dynamic information is, the more worthy the anchor dynamic information is to be recommended, so that the recommendation score may be in positive correlation with the number of viewers, the number of shares, the number of likes and/or the number of comments of the anchor dynamic information, that is, the larger the number of viewers, the number of shares, the number of likes and/or the number of comments of the anchor dynamic information is, the higher the recommendation score is.
For example, as mentioned above, the shorter the release time length of the anchor dynamic information is, the higher the timeliness of the anchor dynamic information is, the more worthwhile to be recommended, so the recommendation score may have a negative correlation with the release time length, that is, the shorter the release time length is, the higher the recommendation score is.
For example, as mentioned above, the higher the validity audit score of the anchor dynamic information is, the higher the recommendable degree of the anchor dynamic information is, the more worthwhile the recommendation is, so that the recommendation score may have a positive correlation with the validity audit score, that is, the higher the validity audit score is, the higher the recommendation score is.
It can be understood that the server may determine the recommendation score of the live dynamic information according to one of the reference information of the anchor dynamic information, or may determine the recommendation score of the live dynamic information comprehensively according to two or three reference information, which is not limited in this embodiment.
In an exemplary embodiment, in a case that the recommendation score of the live broadcast dynamic information is determined comprehensively according to at least two pieces of reference information of the anchor dynamic information, a corresponding weight may be set for each piece of reference information based on an actual application scenario, for example, the weight of the validity audit score is higher than the weight of the interaction data, and then the server may calculate the recommendation score according to each piece of reference information and the corresponding weight.
For whatThe specific calculation method of the recommendation score is not limited in this embodiment. In one example, the server may use a sum of products of the respective reference information and the corresponding weights as the recommendation score. In another example, the recommended score is S, S + X + Y, where X is a validity check score q, and Y is (the number of prawns + the number of comments + the number of shares)/the number of views m, and considering that the timeliness of the anchor dynamic information gradually decreases as the distribution time length shifts, a newton cooling formula Z is used here-k*Issuing time length, and carrying out time attenuation calculation on the issuing time length; q is a weight coefficient of the validity check score, m is a weight coefficient of the interactive data, k is a weight coefficient of the release duration, and values of q, m, and k may be specifically set according to an actual application scenario, for example, q is set to 1000, m is set to 100, and k is set to 0.0064.
After obtaining the recommendation score of each anchor dynamic information, the server may recommend the anchor dynamic information of which the recommendation score is greater than a first preset value to the client, where a specific value of the first preset value may be specifically set according to an actual application scenario, and this embodiment does not limit this, for example, the first preset value is 0, that is, the anchor dynamic information of which the recommendation score is greater than 0 is recommended to the client. For example, the server may send anchor dynamic information of which the recommendation score is greater than a first preset value to the client, and the client displays the anchor dynamic information of which the recommendation score is greater than the first preset value on a display interface. According to the method and the device, the anchor dynamic information which is hot, high in timeliness or free of illegal contents can be automatically recommended to the client, the recommendation efficiency and the recommendation effect are improved, and the user viscosity, the user retention rate and the user cognitive degree of the anchor can be further effectively improved.
In some embodiments, the server may periodically execute the anchor dynamic information recommendation method provided in the embodiment of the present application to update the anchor dynamic information whose recommendation score is greater than the first preset value, for example, the anchor dynamic information may be updated every 1 hour or 5 hours, so as to automatically recommend anchor dynamic information with hot, high timeliness or no illegal content to the client, and improve recommendation accuracy of the anchor dynamic information.
In some embodiments, the server may further obtain, according to a viewing trigger related to the live dynamic information in the client, historical viewing data of the client, where the historical viewing data includes anchor dynamic information that has been viewed in the client. For example, the client may respond to the viewing trigger of the live broadcast dynamic information, display the complete content of the live broadcast dynamic information, and report the viewing behavior of the user to the server, so that the server may obtain the historical viewing data of the client, and further, when recommending the anchor dynamic information, the server may recommend the anchor dynamic information, of which the recommendation score is greater than a first preset value and which does not belong to the historical viewing data, to the client, that is, when recommending, the anchor dynamic information watched by the user is removed, so that repeated recommendation is avoided, and thus, the recommendation effect is improved.
In some embodiments, the server may obtain live viewing data of the client in a live platform, and then determine, according to the live viewing data, an affinity of the client with a anchor indicated by the live viewing data. The higher the affinity is, the higher the attention degree of the user belonging to the client to the anchor is, and the high possibility that the anchor dynamic information issued by the anchor is seen is very high. The server can recommend the anchor dynamic information issued by the anchor of which the recommendation score is greater than a first preset value and the intimacy is greater than a second preset value to the client. The method and the device for recommending the anchor dynamic information aim at the live broadcast viewing data of the client to achieve personalized recommendation of the anchor dynamic information, can recommend the anchor dynamic information issued by the anchor concerned by the user to the client, improve recommendation accuracy of the anchor dynamic information, and are also beneficial to improving the cognitive degree of the user on the anchor concerned by the user.
It can be understood that the specific value of the second preset value may be specifically set according to an actual application scenario, and this embodiment does not limit this.
For example, the live viewing data may include live viewing durations or live viewing time points of one or more anchor broadcasts viewed by the user, and the affinity may be set to have a positive correlation with the live viewing duration in consideration of that the closer viewing duration can reflect the favorite degree of the user to which the client belongs to the anchor broadcast, and the longer the live viewing duration, the higher the affinity; and the intimacy degree can be set to be in a negative correlation relation with the time difference between the live viewing time point and the current time point, namely the greater the time difference is, the lower the intimacy degree is. The server side can determine the intimacy between the client side and the anchor indicated by the live viewing data according to the live viewing duration or the live viewing time point related to one or more anchors in the live viewing data.
In a possible implementation manner, it is considered that the live viewing time length may interfere with the affinity determination process, so that the affinity of the multiple anchor viewed by the client is greatly different, which is not favorable for statistical analysis. Therefore, it may be set that the user looks at a certain anchor for N minutes to indicate that the anchor likes very much, and then accumulates more time lengths to not reflect the change of the intimacy degree, where N is an integer greater than 0, that is, in the case that the live viewing time length is less than or equal to N, the intimacy degree has a positive correlation with the live viewing time length, and in the case that the live viewing time length is greater than N, the intimacy degree remains unchanged, for example, the intimacy degree is the intimacy degree when the live viewing time length is equal to N.
In a possible implementation manner, it is considered that if the affinity of the plurality of anchor viewed by the client, which is determined by the server, has a wide value range, statistical analysis may not be facilitated. Therefore, in order to improve recommendation efficiency, the intimacy degree between the client and the anchor indicated by the live viewing data can be normalized, so that the value range of the intimacy degree is within a preset range, for example, within an interval of 0-1, the server side can conveniently perform statistical analysis on the magnitude relation between the intimacy degree and the second preset value, and the recommendation efficiency of anchor dynamic information can be improved. For example, the intimacy degree can be normalized to be within the range of 0-1 by using an arctangent formula.
In a possible implementation manner, considering that the reference value of live viewing data closer to the current time point is higher, and the reference value of live viewing data farther from the current time point is possibly lower, the server may obtain the live viewing data of the client in the live platform within a preset time period, and may set the duration of the preset time period from the current time point to be shorter, for example, the live viewing data within 15 days or 30 days may be obtained, so as to be beneficial to improving the recommendation accuracy of the anchor dynamic information.
In some embodiments, anchor dynamic information issued by other anchors similar to the anchor concerned by the user can be recommended to the client, so that the recommendation range is expanded, the accurate recommendation process is realized, and the cognitive degree of the user on the other anchors is improved.
In a possible implementation manner, the server may further determine, from the anchor dynamic information whose recommendation score is greater than the first preset value, anchor dynamic information issued by other anchors belonging to the same category as the anchor whose intimacy is greater than the second preset value, and recommend the anchor dynamic information to the client. The embodiment can recommend anchor dynamic information issued by other anchors which the user may be interested in to the client based on the intimacy, and the personalized accurate recommendation process is realized while the recommendation range is expanded.
In another possible implementation manner, the server may obtain a training sample, where the training sample includes live viewing data of a plurality of clients, a category to which a anchor indicated by the live viewing data belongs, and a truth value of intimacy between the client and the anchor determined according to the live viewing data. Then, the server may perform model training based on the training sample, for example, live viewing data of a plurality of clients and the category to which the anchor belongs may be input into a preset model, the preset model determines an affinity predicted value of the client and the anchor according to a relationship between the live viewing data and the category to which the anchor belongs, and then parameters of the preset model may be reversely adjusted according to a difference between the affinity true value and the affinity predicted value, so as to obtain the anchor recommendation model.
The live broadcast viewing data of the client can reflect the preference degree of the user to which the client belongs to a certain category of anchor to a certain extent, so that the preset model can learn the mapping relation among the live broadcast viewing data of the client, the category to which the anchor indicated by the live broadcast viewing data belongs, and the truth value of the affinity between the client and the anchor to obtain the anchor recommendation model, and the interest degree of the client to the anchor belonging to the certain category can be reflected through the numerical value of the affinity predicted by the anchor recommendation model.
It can be understood that, in the embodiment of the present application, no limitation is imposed on the structure of the preset model, and specific setting may be performed according to an actual application scenario. For example, in order to improve the accuracy of the anchor recommendation model, data updated in a preset time period may be obtained every other preset time period, where the updated data includes live viewing data of a plurality of clients in the preset time period, a category to which an anchor indicated by the live viewing data belongs, and a truth value of intimacy between the client and the anchor determined according to the live viewing data, and then the anchor recommendation model is optimized using the updated data, parameters of the anchor recommendation model are readjusted, and the accuracy of the anchor recommendation model is improved.
For example, considering that the reference value of live viewing data closer to the current time point is higher, and the reference value of live viewing data farther from the current time point may be lower, the live viewing data of the plurality of clients acquired by the server may be data within a preset time period, and the duration of the preset time period from the current time point may be set to be shorter, for example, live viewing data within 15 days or 30 days of the plurality of clients may be acquired, so as to facilitate improving the accuracy of the anchor recommendation model.
In the process of recommending anchor dynamic information, the server side can determine an anchor to be recommended and a category thereof corresponding to anchor dynamic information with a recommendation score larger than a first preset value, and obtain live broadcast viewing data of a client side to be recommended; the anchor to be recommended is an anchor in which the user does not watch the live content of the user, and does not include an anchor watched by the user in a historical time period. Then the server side inputs live broadcast viewing data of the client side and the category of the anchor to be recommended into a pre-trained anchor recommendation model, the anchor recommendation model predicts the intimacy between the client side and the anchor to be recommended according to the relationship between the live broadcast viewing data and the category of the anchor to be recommended, and an intimacy prediction result is obtained, and the intimacy prediction result can reflect the interest degree of the client side to the anchor to be recommended; and the server can recommend anchor dynamic information issued by the anchor to be recommended, of which the intimacy prediction result is greater than a second preset value, to the client. According to the embodiment, anchor dynamic information issued by other anchors which the user may be interested in can be recommended to the client based on the affinity, so that the recommendation range is expanded, the personalized accurate recommendation process is realized, and the improvement of the cognitive degree of the user to the other anchors by the client is facilitated.
Illustratively, the server may predetermine the anchor to be recommended with the affinity prediction result greater than the second preset value in an offline state, so as to avoid occupying too much online resources, and to improve the recommendation efficiency.
In one example, the server may recommend anchor dynamic information with the recommendation score greater than a first preset value to the client.
In one example, to avoid repeated recommendation, the server may recommend, to the client, anchor dynamic information that the recommendation score is greater than a first preset value and that does not belong to the historical viewing data.
In one example, to implement personalized recommendation, the server may recommend, to the client, anchor dynamic information that is issued by an anchor whose affinity is greater than a second preset value, where the recommendation score is greater than a first preset value and does not belong to the historical viewing data.
In an example, in order to expand the recommendation range of personalized recommendation, the server may recommend, to the client, anchor dynamic information that is issued by an anchor whose affinity is greater than a second preset value and/or anchor dynamic information that is issued by an anchor to be recommended whose affinity prediction result is greater than a second preset value, and that does not belong to the historical viewing data.
The various technical features in the above embodiments can be arbitrarily combined, so long as there is no conflict or contradiction between the combinations of the features, but the combination is limited by the space and is not described one by one, and therefore, any combination of the various technical features in the above embodiments also belongs to the scope disclosed in the present specification.
Accordingly, referring to fig. 4, the present application further provides an electronic device 20, which includes a memory 22 for storing executable instructions and a processor 21; wherein the processor 21, when executing the executable instructions, implements the steps of any of the methods described above.
The processor 21 executes executable instructions included in the memory 22, and the processor 21 may be a Central Processing Unit (CPU), other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 22 stores executable instructions applied to the anchor recommendation method, and the memory 22 may include at least one type of storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. Also, the apparatus may cooperate with a network storage device that performs a storage function of the memory through a network connection. The storage 22 may be an internal storage unit of the device 20, such as a hard disk or a memory of the device 20. The memory 22 may also be an external storage device of the device 20, such as a plug-in hard disk provided on the device 20, a Smart Memory Card (SMC), a Secure Digital (SD) card, a flash card (FlashCard), and the like. Further, memory 22 may also include both internal and external storage units of device 20. The memory 22 is used to store executable instructions and other programs and data required by the device. The memory 22 may also be used to temporarily store data that has been output or is to be output.
In some embodiments, the processor 21, when executing the executable instructions, is configured to:
acquiring a plurality of pieces of anchor dynamic information released within a preset time length;
acquiring at least one piece of reference information of each piece of anchor dynamic information; the reference information comprises interaction data, release duration or validity audit score of the anchor dynamic information;
determining a recommendation score of the live broadcast dynamic information according to at least one reference information of the main broadcast dynamic information;
recommending the anchor dynamic information with the recommendation score larger than a first preset value to the client.
Illustratively, the interaction data includes the number of viewers, the number of shares, the number of praises, and/or the number of comments of the anchor dynamic information; the recommendation score is in positive correlation with the number of watching people, the number of sharing, the number of praise and/or the number of comments of the anchor dynamic information; the recommendation score and the release time growth form a negative correlation relationship; and the recommendation score is positively correlated with the effectiveness audit score.
Illustratively, the processor 21 is further configured to obtain historical viewing data of the client according to a viewing trigger related to the live dynamic information in the client, where the historical viewing data includes anchor dynamic information viewed in the client; recommending anchor dynamic information to the client, wherein the recommendation score is larger than a first preset value and does not belong to the historical viewing data.
Illustratively, the processor 21 is further configured to: acquiring live broadcast watching data of the client in a live broadcast platform; determining the intimacy between the client and a main broadcast indicated by the live viewing data according to the live viewing data; recommending anchor dynamic information to the client, wherein the recommendation score is larger than a first preset value, and the anchor dynamic information is issued by an anchor with the intimacy degree larger than a second preset value.
Illustratively, the live viewing data includes at least one of: a live viewing duration or a live viewing time point related to one or more anchor; wherein the affinity is positively correlated with the live viewing time; and the intimacy is in negative correlation with the time difference between the live viewing time point and the current time point.
Illustratively, the processor 21 is further configured to determine a anchor to be recommended and a category to which the anchor dynamic information corresponding to the anchor dynamic information with the recommendation score being greater than a first preset value belongs; inputting the live broadcast viewing data of the client and the category to which the anchor to be recommended belongs into a pre-trained anchor recommendation model, and predicting the intimacy between the client and the anchor to be recommended by the anchor recommendation model according to the relationship between the live broadcast viewing data and the category to which the anchor to be recommended belongs to obtain an intimacy prediction result; recommending anchor dynamic information issued by the anchor to be recommended, of which the intimacy prediction result is greater than a second preset value, to the client.
Illustratively, the processor 21 is further configured to: acquiring live broadcast viewing data of a plurality of clients, a category to which a anchor indicated by the live broadcast viewing data belongs, and a truth value of intimacy between the clients and the anchor determined according to the live broadcast viewing data; inputting the live broadcast viewing data of the plurality of clients and the category to which the anchor belongs into a preset model, and determining an intimacy degree predicted value of the clients and the anchor by the preset model according to the relationship between the live broadcast viewing data and the category to which the anchor belongs; and adjusting parameters of the preset model according to the difference between the intimacy degree true value and the intimacy degree predicted value to obtain the anchor recommendation model.
Illustratively, the live viewing data is data of the client within the preset time period.
The various embodiments described herein may be implemented using a computer-readable medium such as computer software, hardware, or any combination thereof. For a hardware implementation, the embodiments described herein may be implemented using at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a processor, a controller, a microcontroller, a microprocessor, and an electronic unit designed to perform the functions described herein. For a software implementation, the implementation such as a process or a function may be implemented with a separate software module that allows performing at least one function or operation. The software codes may be implemented by software applications (or programs) written in any suitable programming language, which may be stored in memory and executed by the controller.
The electronic device 20 may be a desktop computer, a notebook, a palm top computer, a server, a mobile phone, or other computing device. The device may include, but is not limited to, a processor 21, a memory 22. Those skilled in the art will appreciate that fig. 4 is merely an example of the electronic device 20 and does not constitute a limitation of the electronic device 20 and may include more or fewer components than shown, or combine certain components, or different components, e.g., the device may also include input-output devices, network access devices, buses, etc.
The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
In an embodiment, please refer to fig. 5, an embodiment of the present application further provides a recommendation system, which includes a server 100 and a client 101;
the server 100 is configured to execute any one of the above methods, and recommend anchor dynamic information to the client;
the client 101 is configured to display anchor dynamic information recommended by the server 100 in a display interface.
In one embodiment, the present application further provides a computer-readable storage medium having a computer program stored thereon, which when executed by a processor, performs the steps of the method of any of the above embodiments.
This application may take the form of a computer program product embodied on one or more storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having program code embodied therein. Computer-usable storage media include permanent and non-permanent, removable and non-removable media, and information storage may be implemented by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of the storage medium of the computer include, but are not limited to: phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technologies, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic tape storage or other magnetic storage devices, or any other non-transmission medium, may be used to store information that may be accessed by a computing device.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (11)
1. A method for recommending anchor dynamic information is characterized by comprising the following steps:
acquiring a plurality of pieces of anchor dynamic information released within a preset time length;
acquiring at least one piece of reference information of each piece of anchor dynamic information; the reference information comprises interaction data, release duration or validity audit score of the anchor dynamic information;
determining a recommendation score of the live broadcast dynamic information according to at least one reference information of the main broadcast dynamic information;
recommending the anchor dynamic information with the recommendation score larger than a first preset value to the client.
2. The method of claim 1, wherein the interaction data comprises a number of viewers, a number of shares, a number of likes, and/or a number of comments of the anchor dynamic information;
the recommendation score is in positive correlation with the number of watching people, the number of sharing, the number of praise and/or the number of comments of the anchor dynamic information;
the recommendation score and the release time growth form a negative correlation relationship; and
the recommendation score is positively correlated with the validity audit score.
3. The method of claim 1, further comprising:
acquiring historical viewing data of the client according to viewing trigger related to the live broadcast dynamic information in the client, wherein the historical viewing data comprises anchor broadcast dynamic information viewed in the client;
the recommending the anchor dynamic information of which the recommendation score is greater than a first preset value to the client comprises the following steps:
recommending anchor dynamic information to the client, wherein the recommendation score is larger than a first preset value and does not belong to the historical viewing data.
4. The method of claim 1, further comprising:
acquiring live broadcast watching data of the client in a live broadcast platform;
determining the intimacy between the client and a main broadcast indicated by the live viewing data according to the live viewing data;
the recommending the anchor dynamic information of which the recommendation score is greater than a first preset value to the client comprises the following steps:
recommending anchor dynamic information to the client, wherein the recommendation score is larger than a first preset value, and the anchor dynamic information is issued by an anchor with the intimacy degree larger than a second preset value.
5. The method of claim 4, wherein the live viewing data comprises at least one of: a live viewing duration or a live viewing time point related to one or more anchor;
wherein the affinity is positively correlated with the live viewing time; and
the intimacy is in negative correlation with the time difference between the live viewing time point and the current time point.
6. The method of claim 1, wherein recommending the anchor dynamic information to the client with the recommendation score greater than a first preset value comprises:
determining the anchor to be recommended and the category thereof corresponding to the anchor dynamic information with the recommendation score larger than a first preset value;
inputting the live broadcast viewing data of the client and the category to which the anchor to be recommended belongs into a pre-trained anchor recommendation model, and predicting the intimacy between the client and the anchor to be recommended by the anchor recommendation model according to the relationship between the live broadcast viewing data and the category to which the anchor to be recommended belongs to obtain an intimacy prediction result;
recommending anchor dynamic information issued by the anchor to be recommended, of which the intimacy prediction result is greater than a second preset value, to the client.
7. The method of claim 6, wherein the anchor recommendation model is trained by:
acquiring live broadcast viewing data of a plurality of clients, a category to which a anchor indicated by the live broadcast viewing data belongs, and a truth value of intimacy between the clients and the anchor determined according to the live broadcast viewing data;
inputting the live broadcast viewing data of the plurality of clients and the category to which the anchor belongs into a preset model, and determining an intimacy degree predicted value of the clients and the anchor by the preset model according to the relationship between the live broadcast viewing data and the category to which the anchor belongs;
and adjusting parameters of the preset model according to the difference between the intimacy degree true value and the intimacy degree predicted value to obtain the anchor recommendation model.
8. The method according to any one of claims 4 to 7, wherein the live viewing data is data of the client within the preset time period.
9. An electronic device comprising a memory for storing executable instructions and a processor;
wherein the processor, when executing the executable instructions, performs the steps of the method of any one of claims 1 to 8.
10. A recommendation system is characterized by comprising a server and a client;
the server is used for executing the method of any one of claims 1 to 8;
and the client is used for displaying the anchor dynamic information recommended by the server in a display interface.
11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111512008.2A CN114302156A (en) | 2021-12-07 | 2021-12-07 | Anchor dynamic information recommendation method, device, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111512008.2A CN114302156A (en) | 2021-12-07 | 2021-12-07 | Anchor dynamic information recommendation method, device, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114302156A true CN114302156A (en) | 2022-04-08 |
Family
ID=80968445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111512008.2A Pending CN114302156A (en) | 2021-12-07 | 2021-12-07 | Anchor dynamic information recommendation method, device, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114302156A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102841908A (en) * | 2011-06-21 | 2012-12-26 | 富士通株式会社 | Micro-blog content ordering method and micro-blog content ordering device |
| CN108322829A (en) * | 2018-03-02 | 2018-07-24 | 北京奇艺世纪科技有限公司 | Personalized main broadcaster recommends method, apparatus and electronic equipment |
| CN109905723A (en) * | 2019-03-04 | 2019-06-18 | 武汉斗鱼鱼乐网络科技有限公司 | A kind of recommended method of main broadcaster, server and readable storage medium storing program for executing |
| WO2019134294A1 (en) * | 2018-01-02 | 2019-07-11 | 武汉斗鱼网络科技有限公司 | Method and apparatus for processing recommendation information of live stream |
| CN110602514A (en) * | 2019-09-12 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Live channel recommendation method and device, electronic equipment and storage medium |
| CN110602518A (en) * | 2019-09-18 | 2019-12-20 | 广州虎牙科技有限公司 | Live broadcast recommendation method and device, electronic equipment and readable storage medium |
| CN111083512A (en) * | 2019-12-24 | 2020-04-28 | 北京达佳互联信息技术有限公司 | Switching method and device of live broadcast room, electronic equipment and storage medium |
| CN111770365A (en) * | 2020-07-03 | 2020-10-13 | 广州酷狗计算机科技有限公司 | Anchor recommendation method and device, computer equipment and computer-readable storage medium |
-
2021
- 2021-12-07 CN CN202111512008.2A patent/CN114302156A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102841908A (en) * | 2011-06-21 | 2012-12-26 | 富士通株式会社 | Micro-blog content ordering method and micro-blog content ordering device |
| WO2019134294A1 (en) * | 2018-01-02 | 2019-07-11 | 武汉斗鱼网络科技有限公司 | Method and apparatus for processing recommendation information of live stream |
| CN108322829A (en) * | 2018-03-02 | 2018-07-24 | 北京奇艺世纪科技有限公司 | Personalized main broadcaster recommends method, apparatus and electronic equipment |
| CN109905723A (en) * | 2019-03-04 | 2019-06-18 | 武汉斗鱼鱼乐网络科技有限公司 | A kind of recommended method of main broadcaster, server and readable storage medium storing program for executing |
| CN110602514A (en) * | 2019-09-12 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Live channel recommendation method and device, electronic equipment and storage medium |
| CN110602518A (en) * | 2019-09-18 | 2019-12-20 | 广州虎牙科技有限公司 | Live broadcast recommendation method and device, electronic equipment and readable storage medium |
| CN111083512A (en) * | 2019-12-24 | 2020-04-28 | 北京达佳互联信息技术有限公司 | Switching method and device of live broadcast room, electronic equipment and storage medium |
| CN111770365A (en) * | 2020-07-03 | 2020-10-13 | 广州酷狗计算机科技有限公司 | Anchor recommendation method and device, computer equipment and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11409792B2 (en) | System and method for streaming individualized media content | |
| CN110781321B (en) | Multimedia content recommendation method and device | |
| CN103649981B (en) | Method and apparatus for delivering targeted content | |
| CN108337563B (en) | Video evaluation method, device, equipment and storage medium | |
| US20130035989A1 (en) | Conducting market research using social games | |
| JP6469244B2 (en) | Event-based content distribution | |
| US10402465B1 (en) | Content authority ranking using browsing behavior | |
| CN106202393B (en) | Media information pushing method and device | |
| US20130035981A1 (en) | Social networks games configured to elicit research data as part of game play | |
| WO2018133566A1 (en) | Method and device for determining freshness of promotional information, electronic device, and storage medium | |
| CN113656681B (en) | Object evaluation method, device, equipment and storage medium | |
| CN113535991B (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| Chester et al. | The digital commercialisation of US politics—2020 and beyond | |
| CN104967690A (en) | Information push method and device | |
| CN113055745B (en) | Video playing processing method, device, equipment and storage medium | |
| Mohammad et al. | The Effect of Total Views and Total Videos on Super Chat Earnings with Total Subscribers as Intervening Variable among Virtual YouTubers in Vietnam and Thailand | |
| CN112733014A (en) | Recommendation method, device, equipment and storage medium | |
| CN110351581B (en) | Data request processing method and device, terminal equipment and storage medium | |
| CN114302156A (en) | Anchor dynamic information recommendation method, device, system and storage medium | |
| CN111629236B (en) | Friend relationship establishing method, device, equipment and computer readable storage medium | |
| CN109299351B (en) | Content recommendation method and device, electronic equipment and computer readable medium | |
| CN113139083A (en) | Video recommendation method and device, terminal equipment and storage medium | |
| KR20080095926A (en) | On-line advertisement and prosumer marketing service system and method using realtime evaluation of ucc | |
| CN104506892A (en) | Data adjustment method and device | |
| KR20130096610A (en) | System for evaluating broadcasting contents |
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 |