CN114065051A

CN114065051A - Private domain platform video recommendation method and device, electronic equipment and medium

Info

Publication number: CN114065051A
Application number: CN202111417414.0A
Authority: CN
Inventors: 杨扬
Original assignee: China Construction Bank Corp
Current assignee: China Construction Bank Corp
Priority date: 2021-11-25
Filing date: 2021-11-25
Publication date: 2022-02-18

Abstract

The disclosure provides a private domain platform video recommendation method. The method and the device can be used in the technical field of Internet or the financial field. The method comprises the following steps: acquiring a video to be recommended; generating a video classification label based on a preset classification rule; marking the videos to be recommended based on the video classification labels; generating a user picture based on user data, wherein the user data is obtained from user registration information and user behaviors, the user registration information is registration information of a user on the private domain platform, and the registration information at least comprises mechanism information of the user and post information of the user; distributing the videos to be recommended to different video recommendation pools based on the video classification labels and the user portraits; generating a video recommendation list based on the video recommendation pool; and making the video recommendation based on the video recommendation list.

Description

Private domain platform video recommendation method and device, electronic equipment and medium

Technical Field

The present disclosure relates to the field of internet technologies, and in particular, to a method, an apparatus, an electronic device, and a medium.

Background

The recommended patent of the existing public domain flow platform is mainly based on big data recommendation of user behaviors, data analysis is carried out on video watching types of users and searching behaviors of the users, and interest tags of the users are guessed.

In the course of implementing the disclosed concept, the inventors found that there are at least the following problems in the prior art: in a private domain flow platform, particularly an internal company platform, hierarchical recommendation according to company mechanisms is not achieved, and a mechanism for realizing targeted recommendation by considering user post factors is not achieved. Therefore, a method for recommending videos meeting the requirements of private-domain platforms, such as internal platforms of companies, needs to be designed by considering the difference between the private-domain platform and the public-domain platform.

Disclosure of Invention

In view of this, embodiments of the present disclosure provide a method, an apparatus, an electronic device, and a medium for recommending a private domain platform video.

One aspect of the present disclosure provides a method for recommending a private domain platform video, which includes: acquiring a video to be recommended; generating a video classification label based on a preset classification rule; marking the videos to be recommended based on the video classification labels; generating a user image based on user data, wherein the user data is obtained from user registration information and user behaviors, and the user registration information is registration information of a user on the private domain platform; distributing the videos to be recommended to different video recommendation pools based on the video classification labels and the user portraits; generating a video recommendation list based on the video recommendation pool; and making the video recommendation based on the video recommendation list.

In some embodiments, the video category tags include at least one of a subject video tag, a release time tag, a publisher level tag, an organization tag, and a content tag.

In some embodiments, the theme video tag comprises at least one of a platform theme video and a post theme video; the release time tag comprises one of a new generation video, a middle generation video and an old generation video; the publisher level tags include large V users or general users.

In some embodiments, the user representation includes at least a user interest tag and a user attribute tag, the user attribute tag obtained from user enrollment information.

In some embodiments, the assigning the video to be recommended to different video recommendation pools based on the video classification tags and the user representation comprises: forming a video recommendation mapping based on the video classification label and the user image; and allocating the videos to be recommended to different video recommendation pools based on the video recommendation mapping, wherein the video recommendation pools comprise at least two of a subject recommendation pool, a level-time recommendation pool, an organization recommendation pool and a non-interest pool.

In some embodiments, the generating a video recommendation list based on the video recommendation pool comprises: the method comprises the steps of sequencing video recommendation pools based on preset rules, sequentially obtaining quasi-recommendation videos from different video recommendation pools, and adding the quasi-recommendation videos to a video recommendation list, wherein when the quasi-recommendation videos from a grade-time recommendation pool and a non-interest pool are obtained, the method further comprises the following steps: acquiring a heat value of the video to be recommended based on a heat value algorithm; sorting the videos to be recommended based on the heat value; and acquiring a video to be recommended based on the result of the ranking of the heat value.

In certain embodiments, the heat value algorithm comprises: acquiring video playing data to be recommended; and analyzing the video playing data to be recommended to obtain the popularity parameter of the video to be recommended. The popularity parameters comprise at least two of a praise rate, a comment rate and an average playing progress; and calculating the heat value of the video to be recommended based on the heat parameter of the video to be recommended.

In some embodiments, after adding the to-be-recommended video to the video recommendation list, the method further comprises: and when the number of the videos to be recommended reaches a recommendation threshold value or the videos to be recommended all come from the uninteresting pool, stopping adding the video recommendation list.

Another aspect of the present disclosure provides a private domain platform video recommendation apparatus, including an obtaining module configured to obtain a video to be recommended; the first generation module is configured to generate a video classification label based on a preset classification rule; the marking module is configured to mark the video to be recommended based on the video classification label; the second generation module is configured to generate a user image based on user data, wherein the user data is obtained from user registration information and user behaviors, and the user registration information is registration information of a user on the private domain platform; the distribution module is configured to distribute the videos to be recommended to different video recommendation pools based on the video classification labels and the user portrait; a third generation module configured to generate a video recommendation list based on the video recommendation pool; and the recommendation module is configured to recommend the video based on the video recommendation list.

Another aspect of the present disclosure provides an electronic device comprising one or more processors and a storage, wherein the storage is configured to store executable instructions that, when executed by the processors, implement the method as described above.

Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions for implementing the method as described above when executed.

Another aspect of the disclosure provides a computer program comprising computer executable instructions for implementing the method as described above when executed.

According to the video recommendation method provided by the embodiment of the disclosure, the difference between the private domain platform and the public domain platform is fully considered, the hierarchical video recommendation of the private domain platform, especially the internal platform of a company, based on the mechanism and the post where the user is located can be realized, and the pertinence and the recommendation effect of the video recommendation of the private domain platform are improved.

Drawings

The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments of the present disclosure with reference to the accompanying drawings, in which:

fig. 1 schematically illustrates an exemplary system architecture to which the methods, apparatus, and methods may be applied, in accordance with an embodiment of the present disclosure;

FIG. 2 schematically illustrates a flow chart of a private domain platform video recommendation method according to an embodiment of the disclosure;

FIG. 3 schematically shows a flowchart of a method of assigning videos to be recommended to different video recommendation pools according to an embodiment of the present disclosure;

FIG. 4 schematically illustrates a flowchart of a method for obtaining a heat value of a video to be recommended based on a heat value algorithm according to an embodiment of the present disclosure;

FIG. 5 schematically illustrates a block diagram of a private domain platform video recommendation apparatus according to an embodiment of the disclosure;

fig. 6 schematically shows a block diagram of an electronic device according to an embodiment of the disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

Where a convention analogous to "A, B or at least one of C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B or C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features.

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, necessary security measures are taken, and the customs of the public order is not violated.

Nowadays, video push of a public domain traffic platform mainly depends on analyzing search and viewing behaviors of users, extracting interest tags of the users and directionally pushing video contents which the users are interested in. However, in a private domain traffic platform, such as a platform inside a company, the push video needs to consider not only the behavior of the user but also the organization and the position of the user. Therefore, a video recommendation method for the private domain platform is constructed, so that oriented accurate recommendation is achieved based on factors such as the mechanism where the user is located and the post where the user belongs, and pertinence and recommendation effect of video recommendation for the private domain platform user are improved.

The embodiment of the disclosure provides a method and a device for recommending a private domain platform video, electronic equipment and a medium. The method comprises the following steps: acquiring a video to be recommended; generating a video classification label based on a preset classification rule; marking the videos to be recommended based on the video classification labels; generating a user picture based on user data, wherein the user data is obtained from user registration information and user behaviors, the user registration information is registration information of a user on the private domain platform, and the registration information at least comprises mechanism information of the user and post information of the user; distributing the videos to be recommended to different video recommendation pools based on the video classification labels and the user portraits; generating a video recommendation list based on the video recommendation pool; and making the video recommendation based on the video recommendation list.

It should be noted that the method, the apparatus, the system and the electronic device for recommending a private domain platform video provided by the embodiment of the present disclosure can be used in the field of internet technology, and can also be used in various fields other than internet technology, such as financial field and the like. The method, the device and the system for recommending the private domain platform video and the application field of the electronic equipment are not limited.

Fig. 1 schematically shows an exemplary system architecture to which the method, apparatus, according to an embodiment of the present disclosure, may be applied. It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.

As shown in fig. 1, the system architecture 100 according to this embodiment may include

terminal devices

101, 102, 103, a network 104 and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

A user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or transmit information or the like. The

terminal devices

101, 102, and 103 may have functions of entering user information, acquiring and viewing videos, and approving, evaluating, and forwarding videos, and may also have a function of uploading videos. In addition, various communication client applications, such as shopping applications, web browser applications, search applications, instant messaging tools, mailbox clients, social platform software, and the like (for example only), may also be installed on the

terminal devices

101, 102, 103.

The

terminal devices

101, 102, 103 include, but are not limited to, smart phones, tablet computers, laptop portable computers, and the like.

The server 105 may parse the user information data set to obtain user information data and record user behavior, and may generate a video recommendation list based on a recommendation algorithm. Server 105 may be a database server, a back office server, a cluster of servers, or the like. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., recommended video) to the terminal device.

It should be noted that the method provided by the embodiment of the present disclosure may be generally executed by the server 105. Accordingly, the apparatus provided by the embodiments of the present disclosure may be generally disposed in the server 105.

It should be understood that the number of terminal devices, networks, and servers are merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Fig. 2 schematically shows a flowchart of a private domain platform video recommendation method according to an embodiment of the present disclosure.

As shown in fig. 2, the method may include operations S201 to S207.

In operation S201, a video to be recommended is acquired.

According to embodiments of the present disclosure, the private domain platform may be an enterprise/institutional internal platform, wherein the enterprise/institutional internal platform may contain branches, such as branches of a bank, branches, and the like. The video to be recommended can be uploaded by a user, and can also be formed and uploaded by a video platform manager according to the theme activity of the private domain platform in a specific time period. It is understood that the video to be recommended may be determined after preliminary screening, for example, screening out the video with lower quality.

In operation S202, a video classification tag is generated based on a preset classification rule.

According to an embodiment of the present disclosure, the preset classification rule may include: the classification is based on the theme type of the video, and can be divided into a theme video and a daily video, wherein the theme video can comprise a platform theme video and a post theme video. The platform theme video can be a theme activity video of a platform in a specific time period, and the post theme video can comprise types such as professional skills, institutional processes and employee styles facing a specific post. The daily video may include daily life-type video, such as types of fitness, singing, cooking, and the like. The classification may be based on a video-based form of the video, which may include, for example, types of live, animation, lecture, and so on. The classification may be based on video style and may include, for example, a fun type, a feeling of mind type, and a dry goods type. The videos can be classified based on video release time, for example, the videos can be classified into new generation videos, middle generation videos and old generation videos, wherein the categories of the videos with different release times can be preset according to factors such as platform video uploading speed, uploading quantity, user use frequency and the like, for example, the videos with the release time of 0-2 days can be classified into the new generation videos, the videos with the release time of 3-30 days can be classified into the middle generation videos, and the videos with the release time exceeding 30 days can be classified into the old generation videos. Classification may also be based on publisher rank. According to the embodiment of the disclosure, when a user is created by a video system, a set of user growth system can be formed, all users are marked as ordinary users during registration, after the user accumulates certain points through operations of video publishing, praise, comment and the like in a platform, the user can apply for upgrading to become a large V user with a large V identification through a private area platform, the large V user belongs to an active user group of a company, and the rest users are still the ordinary users. Based on the above rules, videos may be classified based on whether the video publisher is a large V user. In order to improve the pertinence of video recommendation of the private area platform, videos can be classified based on the institutions of the publishers, for example, a bank private area platform can be classified as coming from a certain province or city branch, and can be further classified as coming from a certain county branch. Further, organization classification subdivision can be performed according to the joining years of the publishers and the job levels of the publishers. It will be appreciated that finer classification facilitates more accurate recommendations, and that classification rules may be adjusted based on user feedback.

Based on the above classification rules, a series of classification tags can be generated, including but not limited to a topic video tag, a publishing time tag, a publisher level tag, an organization tag, etc., and it is understood that the video should at least further include a content tag, i.e., a corresponding tag is created based on the specific content of the video. The theme video tag comprises at least one of a platform theme video and a post theme video; the release time tag comprises one of a new generation video, a middle generation video and an old generation video; the publisher level tags include large V users or general users. It will be appreciated that a video may be classified into different categories based on the one or more classification criteria, and accordingly, the video may have one or more video classification tags.

In operation S203, the video to be recommended is marked based on the video classification tag.

In operation S204, a user image is generated based on user data, where the user data is obtained from user registration information and user behavior, and the user registration information is registration information of a user on the private domain platform.

According to an embodiment of the disclosure, based on specific requirements of private domain platform video recommendation, a user representation can be generated by extracting and processing user data. The user registration information can be obtained based on the registration information of the user on the private domain platform, for example, employee information entered into a human resource system. It can be understood that, in order to implement accurate recommendation of the private domain platform, the user registration information at least may include information of an organization to which the user belongs and information of a post to which the user belongs. In addition, behavior data can be obtained based on behaviors of the user in the process of watching the video, and the user portrait can be constructed after the behavior data are processed and analyzed.

In an embodiment of the present disclosure, a user tag may be extracted based on user data and a user portrait may be generated based on the user tag. The user tags may include user interest tags, user attribute tags, user activity tags, and the like. The interest tag can be determined based on the type of the interested video recorded in the video system by the user, or can be determined based on analyzing the behavior of the user in the process of watching the video, for example, the interest tag can be extracted based on the preference of a video content tag, the preference of a video style, the preference of a video form, the preference of a video duration and the preference of a video watching time period viewed by the user. The attribute tags may include user age, user gender, user post information, user equipment type, user job level, user organization, etc. The attribute tags may be obtained based on employee information registered by the user in the human resources system, or based on the system detecting the type of device currently being used by the user. The user activity label can be obtained by analyzing the user grade, the time length of the user using the video recommendation system and the watching behavior data of the user in a certain time period. For example, the system can automatically collect user behavior data and analyze whether the current user is a new user, the user class, whether the user has behaviors of logging in, watching, commenting, reviewing, collecting, sharing, releasing, newly paying attention, searching videos and live broadcasting in the near term and the frequency of the behaviors. Wherein whether it is a large V user can be inferred based on the user rating category. Further, it is also possible for active users to analyze their activity type, e.g. the current active user belongs to the author or is a king of people, to refine the tags. It will be appreciated that tag generation may be further refined based on user feedback to update the user representation.

In one particular example, user tags for the King of the user may include active users, user class five, 32 year old, male, product manager, using android system equipment, Beijing division, swimming, fitness, basketball, short video, king of the population, etc., which tags combine to generate a user representation.

After the user image is generated, the operation returns to operation S205.

In operation S205, the videos to be recommended are allocated to different video recommendation pools based on the video classification tags and the user figures.

Fig. 3 schematically shows a flowchart of a method for allocating videos to be recommended to different video recommendation pools according to an embodiment of the present disclosure.

As shown in fig. 3, the method may include operations S301 to S302.

In operation S301, a video recommendation map is formed based on the video classification tags and the user images.

In operation S302, the video to be recommended is allocated to different video recommendation pools based on a video recommendation mapping.

According to an embodiment of the present disclosure, the video recommendation pool includes at least two of a topic recommendation pool, a level-time recommendation pool, an organization recommendation pool, and a non-interest pool. After the video classification label and the user portrait are generated, the video classification label and the user label can be associated to form a video recommendation mapping. For example, a video is a post topic video with tags including "professional skills" and a content tag is "web page development" whereby an association can be established with a user whose user tag includes "programmer" to form a video recommendation map. After the mapping is formed, the videos may be assigned to a topic recommendation pool. The level-time recommendation pool is associated with the publisher level tags and the publication time tags at the same time, and correspondingly, the recommendation pool may include a large-V new generation recommendation pool, a common new generation recommendation pool, a large-V middle generation recommendation pool, a common middle generation recommendation pool, a large-V old generation recommendation pool, a common old generation recommendation pool, and the like. The organization recommends that the pool be an allocation rule based on whether the video is from the same organization. The private domain platform is gradually huge in the development process, different branches are formed, some branches are distributed in different regions, colleagues of different branches do not know the branches, and in order to expose works of people who can be known to a greater degree, the attribution sense of users is improved, and an organization recommendation pool can be introduced. The organization recommendation pool can be further subdivided, for example, a recommendation sub-pool can be constructed according to the job level of the video publisher added to the organization, so as to perform recommendation priority ranking based on the matching degree of the attribute tags such as the user added year and job level and the organization tags. According to the embodiment of the disclosure, in order to increase the video popularity, expand the audience range and widen the user visual field, a non-interest pool can be constructed. Videos which do not belong to a certain user interest label but have higher heat can be distributed to the uninteresting pool, so that the exposure of the videos is further improved, and the user is guided to explore new interest points.

After the videos to be recommended are allocated to different video recommendation pools, the operation returns to operation S206.

In operation S206, a video recommendation list is generated based on the video recommendation pool.

According to the embodiment of the disclosure, the video recommendation pools can be sorted based on preset rules, quasi-recommendation videos from different video recommendation pools are obtained in sequence, and the quasi-recommendation videos are added to the video recommendation list. The method comprises the steps of presetting a sorting rule for a video recommendation pool based on the video recommendation requirement of a private domain platform. In some examples, the topic recommendation pool may be arranged first, then the rank-time recommendation pool with publisher user rank from high to low and publication time from near to far may be arranged, then the institutional recommendation pool videos of the same institution may be arranged, and then the uninteresting pool may be arranged based on platform promotion demand. It can be understood that, in order to improve the exposure of videos in the topic recommendation pool, the user-institution recommendation pool and the uninteresting pool, the three recommendation pools can be arranged alternately to the levels of users of different publishers and between the level-time recommendation pools of different publication times. In a typical example, in a round of recommendation, the recommendation pools may be arranged in the following order: the system comprises a theme recommendation pool 1, a large V new generation recommendation pool, a common new generation recommendation pool, an organization recommendation pool 1, a non-interest pool 1, a theme recommendation pool 2, a large V middle generation recommendation pool, a common middle generation recommendation pool, an organization recommendation pool 2, a non-interest pool 2, a theme recommendation pool 3, a large V old generation recommendation pool, a common old generation recommendation pool, an organization recommendation pool 3 and a non-interest pool 3. The videos in the topic recommendation pools 1, 2 and 3 are different videos randomly extracted in a certain number from the original topic recommendation pool. The institution recommendation pools 1, 2, 3 and the uninteresting pools 1, 2, 3 may be constructed based on a similar approach. According to the embodiment of the disclosure, for each recommendation pool, the recommendation number can be set based on a preset rule or after analyzing the user watching behavior. When videos from the theme recommendation pool and the mechanism recommendation pool are obtained, a preset number of videos can be recommended randomly.

According to an embodiment of the present disclosure, when obtaining the quasi-recommended videos from the level-time recommendation pool and the uninteresting pool, the method further includes: acquiring a heat value of the video to be recommended based on a heat value algorithm; sorting the videos to be recommended based on the heat value; and acquiring a video to be recommended based on the result of the ranking of the heat value.

Fig. 4 schematically shows a flowchart of a method for obtaining a heat value of a video to be recommended based on a heat value algorithm according to an embodiment of the present disclosure.

As shown in fig. 4, the method may include operations S401 to S404.

In operation S401, video playing data to be recommended is acquired.

In operation S402, the video playing data to be recommended is analyzed, and the popularity parameter of the video to be recommended is obtained.

In operation S403, a heat value of the video to be recommended is calculated based on the heat parameter of the video to be recommended.

According to the embodiment of the disclosure, the popularity parameters of the videos to be recommended, which are allocated to the recommendation pool, can be obtained based on the user behavior, and the popularity parameters can include at least two of a praise rate, a comment rate and an average playing progress.

In some specific embodiments, the video popularity parameter to be recommended may be obtained by the following algorithm: the praise rate is equal to the praise number of short video points and the total number of players; the comment rate is short video comment number of people (including comments and replies) ÷ total number of people playing; the average playing progress is the sum of the short video playing progress and the total playing times; the short video playing progress is the playing time length and the video time length. The statistical period may be an accumulated value from the release time to the time of calculating the heat degree. The total playing times can be counted according to the following rules: once playing from the beginning and recording as one time, and automatically circularly playing and recording as a plurality of times; after the playing is started, quickly marking the playing as one time; the video is not played, and is directly drawn, and the times are not counted; the user watches own video and does not count the times; starting after pausing, and counting the times; the people who do not log in watch the program and do not count the times. The total number of players can be counted according to the following rules: one person watches the same video for many times and marks as one person; people who do not log in watch the system and do not count the number of people. The playing time can be counted according to the following rules: under the condition of normal playing, the actual watching time length is taken as the standard, and the dragging part does not count the playing time length; pausing in the midway, wherein the pausing time does not account for the playing time length; and taking the normal playing time of the video as the playing time length. Wherein 0-1 second is recorded as 1 second.

According to the embodiment of the disclosure, after the video heat parameter to be recommended is obtained, different weights can be given to different parameters, and a final video heat value is obtained through calculation. The parameter weight can be set based on the requirements of video exposure, topic discussion degree and user recognition degree. In one example, the video heat value may be calculated based on the following formula:

the video heat value is 30% × a like rate + 20% × a comment rate + 50% × an average play progress.

In operation S404, a to-be-recommended video is acquired based on the hotness value sorting result.

According to the specific embodiment of the disclosure, when the videos to be recommended from the level-time recommendation pool are acquired, the video with the highest heat value under the user interest tag can be selected based on the preset heat value threshold and the recommendation number. For example, the user interest tags include "fitness", "dancing", "swimming", and 2 to 5 videos with the highest heat degree in the videos of the corresponding content tags in the certain level-time recommendation pool may be selected, and the 2 to 5 videos with the highest heat degree may be set to be greater than a certain heat degree threshold value to ensure the recommendation quality.

In some embodiments, if the two video heat values are equal, the two video heat values may be sorted according to the average playing progress, the like rate, and the comment rate in turn according to the consideration of the user recognition.

According to further embodiments of the present disclosure, after adding the to-be-recommended video to the video recommendation list, the method further comprises: and when the number of the videos to be recommended reaches a recommendation threshold value or the videos to be recommended all come from the uninteresting pool, stopping adding the video recommendation list.

In other embodiments of the present disclosure, a round of video recommendation lists may be obtained by applying the method of the embodiments of the present disclosure. After all the videos in the current round are watched, a video recommendation list in the next round can be generated based on the same method. In order to ensure the recommendation quality and balance the number of videos in the recommendation pool and the user experience, a recommendation threshold value can be set, and the recommendation is stopped when the number of videos to be recommended in the current round reaches the recommendation threshold value. The recommendation threshold may be determined based on the total amount of platform video. On the other hand, if the video recommendation list generation method generates the proposed video in the current round, the video source is only the uninteresting pool, and in order to improve the user experience, the addition of the video recommendation list can be stopped, and then the current round of recommendation is ended.

After the video recommendation list is generated, return is made to operation S207.

In operation S207, the video recommendation is made based on the video recommendation list.

According to the method, user labels such as the mechanism and the post of the user are introduced into the user portrait, the user portrait suitable for video recommendation of the private area platform is constructed, a mapping relation is formed between the user portrait and the video classification labels, a video recommendation list fully considering the characteristics of the private area platform is formed, a user recommendation mode based on the characteristics of the private area platform and hierarchical is achieved, and the accuracy of video recommendation for the private area platform is improved.

Fig. 5 schematically illustrates a block diagram of a private domain platform video recommendation apparatus according to an embodiment of the disclosure.

As shown in fig. 5, the private domain platform video recommendation apparatus 500 may include: the system comprises an acquisition module 501, a first generation module 502, a marking module 503, a second generation module 504, an allocation module 505, a third generation module 506 and a recommendation module 507.

Wherein, the obtaining module 501 is configured to obtain a video to be recommended.

The first generation module 502 is configured to generate video classification tags based on preset classification rules.

The labeling module 503 is configured to label the video to be recommended based on the video classification label.

A second generation module 504 is configured to generate a user representation based on the user data. The user data is obtained from user registration information and user behaviors, and the user registration information is registration information of a user on the private domain platform.

The assignment module 505 is configured to assign the videos to be recommended to different video recommendation pools based on the video classification tags and the user representation.

The third generation module 506 is configured to generate a video recommendation list based on the video recommendation pool.

Recommendation module 507 is configured to make the video recommendation based on the video recommendation list.

It should be noted that the implementation, solved technical problems, implemented functions, and achieved technical effects of each module/unit/subunit and the like in the apparatus part embodiment are respectively the same as or similar to the implementation, solved technical problems, implemented functions, and achieved technical effects of each corresponding step in the method part embodiment.

Any of the modules, units, or at least part of the functionality of any of them according to embodiments of the present disclosure may be implemented in one module. Any one or more of the modules and units according to the embodiments of the present disclosure may be implemented by being split into a plurality of modules. Any one or more of the modules, units according to the embodiments of the present disclosure may be implemented at least partially as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by any other reasonable means of hardware or firmware by integrating or packaging the circuits, or in any one of three implementations of software, hardware and firmware, or in any suitable combination of any of them. Alternatively, one or more of the modules, units according to embodiments of the present disclosure may be implemented at least partly as computer program modules, which, when executed, may perform the respective functions.

For example, any of the obtaining module 501, the first generating module 502, the marking module 503, the second generating module 504, the allocating module 505, the third generating module 506 and the recommending module 507 may be combined into one module to be implemented, or any one of the modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to the embodiment of the present disclosure, at least one of the obtaining module 501, the first generating module 502, the marking module 503, the second generating module 504, the allocating module 505, the third generating module 506, and the recommending module 507 may be at least partially implemented as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or implemented by any one of three implementation manners of software, hardware, and firmware, or in a suitable combination of any of them. Alternatively, at least one of the obtaining module 501, the first generating module 502, the marking module 503, the second generating module 504, the assigning module 505, the third generating module 506, and the recommending module 507 may be at least partially implemented as a computer program module which, when executed, may perform a corresponding function.

Fig. 6 schematically shows a block diagram of an electronic device according to an embodiment of the disclosure. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 6, an electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. Processor 601 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 601 may also include onboard memory for caching purposes. Processor 601 may include a single processing unit or multiple processing units for performing different actions of a method flow according to embodiments of the disclosure.

In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 600 are stored. The processor 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. The processor 601 performs various operations of the method flows according to the embodiments of the present disclosure by executing programs in the ROM 602 and/or RAM 603. It is to be noted that the programs may also be stored in one or more memories other than the ROM 602 and RAM 603. The processor 601 may also perform various operations of the method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.

Electronic device 600 may also include input/output (I/O) interface 605, input/output (I/O) interface 605 also connected to bus 604, according to an embodiment of the disclosure. The electronic device 600 may also include one or more of the following components connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.

According to embodiments of the present disclosure, method flows according to embodiments of the present disclosure may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable storage medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program, when executed by the processor 601, performs the above-described functions defined in the system of the embodiments of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include the ROM 602 and/or RAM 603 described above and/or one or more memories other than the ROM 602 and RAM 603.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The present disclosure also provides a computer program comprising one or more programs. The above-described method may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable storage medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program, when executed by the processor 601, performs the above-described functions defined in the system of the embodiments of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.

The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.

Claims

1. A method for recommending a private domain platform video is characterized by comprising the following steps:

acquiring a video to be recommended;

generating a video classification label based on a preset classification rule;

marking the videos to be recommended based on the video classification labels;

generating a user image based on user data, wherein the user data is obtained from user registration information and user behaviors, and the user registration information is registration information of a user on the private domain platform;

distributing the videos to be recommended to different video recommendation pools based on the video classification labels and the user portraits;

generating a video recommendation list based on the video recommendation pool; and

and performing the video recommendation based on the video recommendation list.

2. The video recommendation method of claim 1, wherein the video category labels include at least one of a subject video label, a release time label, a publisher level label, an organization label, and a content label.

3. The video recommendation method of claim 2, wherein the theme video tag comprises at least one of a platform theme video and a post theme video; the release time tag comprises one of a new generation video, a middle generation video and an old generation video; the publisher level tags include large V users or general users.

4. The video recommendation method of claim 1, wherein the user representation includes at least a user interest tag and a user attribute tag, the user attribute tag obtained from user registration information.

5. The video recommendation method of claim 1, wherein said assigning the video to be recommended to different video recommendation pools based on the video classification tags and the user representation comprises:

forming a video recommendation mapping based on the video classification label and the user image;

and allocating the videos to be recommended to different video recommendation pools based on the video recommendation mapping, wherein the video recommendation pools comprise at least two of a subject recommendation pool, a level-time recommendation pool, an organization recommendation pool and a non-interest pool.

6. The video recommendation method of claim 5, wherein the generating a video recommendation list based on the video recommendation pool comprises:

sequencing video recommendation pools based on preset rules, sequentially acquiring quasi-recommendation videos from different video recommendation pools, adding the quasi-recommendation videos to the video recommendation list,

wherein, when obtaining the quasi-recommended videos from the level-time recommendation pool and the uninteresting pool, the method further comprises:

acquiring a heat value of the video to be recommended based on a heat value algorithm;

sorting the videos to be recommended based on the heat value; and

and acquiring a video to be recommended based on the result of the ranking of the heat values.

7. The video recommendation method of claim 6, wherein the heat value algorithm comprises:

acquiring video playing data to be recommended;

analyzing the video playing data to be recommended to obtain popularity parameters of the video to be recommended, wherein the popularity parameters comprise at least two of a praise rate, a comment rate and an average playing progress; and

and calculating the heat value of the video to be recommended based on the heat parameter of the video to be recommended.

8. The video recommendation method of claim 6 or 7, wherein after adding the to-be-recommended video to the video recommendation list, the method further comprises:

and when the number of the videos to be recommended reaches a recommendation threshold value or the videos to be recommended all come from the uninteresting pool, stopping adding the video recommendation list.

9. A private domain platform video recommendation device, comprising:

the acquisition module is configured to acquire a video to be recommended;

the first generation module is configured to generate a video classification label based on a preset classification rule;

the marking module is configured to mark the video to be recommended based on the video classification label;

the second generation module is configured to generate a user image based on user data, wherein the user data is obtained from user registration information and user behaviors, and the user registration information is registration information of a user on the private domain platform;

the distribution module is configured to distribute the videos to be recommended to different video recommendation pools based on the video classification labels and the user portrait;

a third generation module configured to generate a video recommendation list based on the video recommendation pool;

and the recommendation module is configured to recommend the video based on the video recommendation list.

10. An electronic device, comprising:

one or more processors;

storage means for storing executable instructions which, when executed by the processor, implement a data monitoring method according to any one of claims 1 to 8.

11. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, implement a data monitoring method according to any one of claims 1 to 8.

12. A computer program comprising one or more executable instructions which, when executed by a processor, implement the method of any one of claims 1 to 8.