CN110856003A - Live list pushing method and device, electronic equipment and storage medium - Google Patents

Live list pushing method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN110856003A
CN110856003A CN201910989582.3A CN201910989582A CN110856003A CN 110856003 A CN110856003 A CN 110856003A CN 201910989582 A CN201910989582 A CN 201910989582A CN 110856003 A CN110856003 A CN 110856003A
Authority
CN
China
Prior art keywords
resource
live broadcast
recommendation
live
user
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.)
Granted
Application number
CN201910989582.3A
Other languages
Chinese (zh)
Other versions
CN110856003B (en
Inventor
李峰
邓贤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Netease Hangzhou Network Co Ltd
Original Assignee
Netease Hangzhou Network Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Netease Hangzhou Network Co Ltd filed Critical Netease Hangzhou Network Co Ltd
Priority to CN201910989582.3A priority Critical patent/CN110856003B/en
Publication of CN110856003A publication Critical patent/CN110856003A/en
Application granted granted Critical
Publication of CN110856003B publication Critical patent/CN110856003B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/2187—Live feed
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
    • H04N21/26258—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists for generating a list of items to be played back in a given order, e.g. playlist, or scheduling item distribution according to such list
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/482—End-user interface for program selection
    • H04N21/4826—End-user interface for program selection using recommendation lists, e.g. of programs or channels sorted out according to their score

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Human Computer Interaction (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

According to the live broadcast list pushing method and device, the electronic device and the storage medium, the browsing request triggered by the user is received, the browsing request comprises a target display resource position to be browsed and a user identification, the live broadcast resource recommendation strategy in the target display resource position is determined according to the user identification, the recommended live broadcast resource of the target display resource position is determined by adopting the live broadcast resource recommendation strategy, the recommended live broadcast resource is inserted into the current live broadcast list of the target display resource position to form a new live broadcast list and is pushed to the user, so that all live broadcast resources have the opportunity to be pushed under different recommendation strategies and are pushed out, the whole conversion rate of the live broadcast resources is improved, and benign competition among the live broadcast resources is facilitated.

Description

Live list pushing method and device, electronic equipment and storage medium
Technical Field
The present disclosure relates to computer technologies, and in particular, to a method and an apparatus for pushing a live list, an electronic device, and a storage medium.
Background
With the development of electronic technology and cultural industry, live broadcast watching based on a live broadcast platform has become a daily life style of choice for people.
In the prior art, in order to improve the traffic conversion rate of live broadcast resources, some live broadcast resources are often used as recommended live broadcast resources according to the priority of the live broadcast resources, and a live broadcast list including the recommended live broadcast resources is generated based on a resource display position in a browsing request triggered by a user and is pushed to the user, so that the user selects live broadcast resources to be browsed from the live broadcast list and browses the live broadcast resources.
However, when the live broadcast resources are pushed based on the priority, the live broadcast resources with higher priority are generally pushed preferentially, and the live broadcast resources with lower priority are difficult to obtain a push opportunity, which is not favorable for effective push of the live broadcast resources, has lower overall conversion rate of the live broadcast resources, and is also not favorable for benign competition among the live broadcast resources.
Disclosure of Invention
In view of the above-mentioned problems, the present disclosure provides a live list push method, apparatus, electronic device, and storage medium.
In a first aspect, the present disclosure provides a method for pushing a live list, including:
receiving a browsing request triggered by a user, wherein the browsing request comprises a target display resource position to be browsed and a user identifier;
determining a live broadcast resource recommendation strategy in the target display resource position according to the user identification, and determining recommended live broadcast resources of the target display resource position by adopting the live broadcast resource recommendation strategy;
and inserting the recommended live broadcast resource into a current live broadcast list of the target display resource position to form a new live broadcast list and pushing the new live broadcast list to a user.
Illustratively, the number of the live resource recommendation strategies is multiple;
the determining, according to the user identifier, a recommendation policy for live resources in the target display resource slot includes:
and determining a recommendation strategy of the browsing request from a plurality of live broadcast resource recommendation strategies according to the tail identification value of the user identification.
Illustratively, the live resource recommendation policy includes a recommendation pool recommendation policy; the display resource position corresponds to a plurality of recommendation pools, and each recommendation pool comprises a plurality of live broadcast resources;
the method for determining the recommended live broadcast resources of the target display resource bit by adopting the live broadcast resource recommendation strategy comprises the following steps:
determining resource pool information of a target display resource position, wherein the resource pool information comprises the display probability of each recommendation pool and the resource quality of each live broadcast resource in each recommendation pool;
selecting a target recommendation pool according to the display probability of each recommendation pool in the resource pool information;
and selecting at least one live broadcast resource from the live broadcast resources corresponding to the target recommendation pool as a recommended live broadcast resource according to the resource quality of the live broadcast resources in the recommendation pools.
Before determining the resource pool information of the target display resource bit, the method further includes:
and determining the display probability of each recommendation pool in the resource pool information of the target display resource position according to the priority of each recommendation pool corresponding to the target display resource position and the proportion weight of each recommendation pool in the target display resource position.
Illustratively, the live resource recommendation policy includes a similarity recommendation policy;
the method for determining the recommended live broadcast resources of the target display resource bit by adopting the live broadcast resource recommendation strategy comprises the following steps:
acquiring a browsing record of a user according to the user identification, wherein the browsing record comprises each live broadcast resource browsed by the user in a first preset time period and corresponding browsing time;
determining the preference degree of each live broadcast resource according to each live broadcast resource browsed by the user in a first preset time period and corresponding browsing time, and selecting a plurality of live broadcast resources with the preference degrees larger than a preset preference degree threshold value as first direct broadcast resources;
determining the similarity between each first direct broadcast resource and each current direct broadcast resource, and selecting the direct broadcast resource with the highest similarity with each first direct broadcast resource from the current direct broadcast resources as a second direct broadcast resource corresponding to each first direct broadcast resource;
sequencing the second live broadcast resources according to the user preference of each first live broadcast resource and the similarity between each first live broadcast resource and the corresponding second live broadcast resource;
and determining at least one second live broadcast resource as a recommended live broadcast resource according to the sequencing result.
Illustratively, the obtaining a browsing record of the user according to the user identifier, where the browsing record includes live resources browsed by the user within a first preset time period and before corresponding browsing time, further includes:
collecting browsing records of other users except the user within a first preset time period;
inputting each live broadcast resource and corresponding browsing time in the browsing records of the other users into a machine learning model, and determining a representation vector of each current live broadcast resource;
calculating the distance between the characterization vectors of any two live broadcast resources according to a preset characterization vector distance formula;
correspondingly, the determining the similarity between each first live broadcast resource and each current live broadcast resource, and selecting the live broadcast resource with the highest similarity with each first live broadcast resource from the current live broadcast resources as the second live broadcast resource corresponding to each first live broadcast resource includes:
and determining each similarity according to the distance between each first direct broadcast resource and the characterization vector of each current direct broadcast resource, and selecting the direct broadcast resource with the highest similarity with each first direct broadcast resource from the current direct broadcast resources as a second direct broadcast resource corresponding to each first direct broadcast resource.
In a second aspect, the present disclosure provides a push device for a live list, including:
the system comprises a receiving module, a browsing module and a display module, wherein the receiving module is used for receiving a browsing request triggered by a user, and the browsing request comprises a target display resource position to be browsed and a user identifier;
the first processing module is used for determining a live broadcast resource recommendation strategy in the target display resource position according to the user identification and determining recommended live broadcast resources of the target display resource position by adopting the live broadcast resource recommendation strategy;
and the second processing module is used for inserting the recommended live broadcast resources into the current live broadcast list of the target display resource position to form a new live broadcast list and pushing the new live broadcast list to the user.
Illustratively, the number of the live resource recommendation strategies is multiple;
the first processing module is specifically configured to determine a recommendation policy of the current browsing request from a plurality of live broadcast resource recommendation policies according to the value of the tail identifier of the user identifier.
Illustratively, the live resource recommendation policy includes a recommendation pool recommendation policy; the display resource position corresponds to a plurality of recommendation pools, and each recommendation pool comprises a plurality of live broadcast resources;
the first processing module is specifically configured to determine resource pool information of a target display resource bit, where the resource pool information includes a display probability of each recommendation pool and a resource quality of each live broadcast resource in each recommendation pool; selecting a target recommendation pool according to the display probability of each recommendation pool in the resource pool information; and selecting at least one live broadcast resource from the live broadcast resources corresponding to the target recommendation pool as a recommended live broadcast resource according to the resource quality of the live broadcast resources in the recommendation pools.
For example, before the first processing module determines the resource pool information of the target display resource bit, the first processing module is further configured to determine the display probability of each recommendation pool in the resource pool information of the target display resource bit according to the priority of each recommendation pool corresponding to the target display resource bit and the proportion weight of each recommendation pool in the target display resource bit.
Illustratively, the live resource recommendation policy includes a similarity recommendation policy;
the first processing module is specifically configured to obtain a browsing record of a user according to the user identifier, where the browsing record includes each live broadcast resource browsed by the user within a first preset time period and corresponding browsing time; determining the preference degree of each live broadcast resource according to each live broadcast resource browsed by the user in a first preset time period and corresponding browsing time, and selecting a plurality of live broadcast resources with the preference degrees larger than a preset preference degree threshold value as first direct broadcast resources; determining the similarity between each first direct broadcast resource and each current direct broadcast resource, and selecting the direct broadcast resource with the highest similarity with each first direct broadcast resource from the current direct broadcast resources as a second direct broadcast resource corresponding to each first direct broadcast resource; sequencing the second live broadcast resources according to the user preference of each first live broadcast resource and the similarity between each first live broadcast resource and the corresponding second live broadcast resource; and determining at least one second live broadcast resource as a recommended live broadcast resource according to the sequencing result.
Illustratively, the first processing module is further configured to, before obtaining a browsing record of the user according to the user identifier, where the browsing record includes live resources browsed by the user within a first preset time period and corresponding browsing time, further:
collecting browsing records of other users except the user within a first preset time period;
inputting each live broadcast resource and corresponding browsing time in the browsing records of the other users into a machine learning model, and determining a representation vector of each current live broadcast resource;
calculating the distance between the characterization vectors of any two live broadcast resources according to a preset characterization vector distance formula;
correspondingly, the determining the similarity between each first live broadcast resource and each current live broadcast resource, and selecting the live broadcast resource with the highest similarity with each first live broadcast resource from the current live broadcast resources as the second live broadcast resource corresponding to each first live broadcast resource includes:
and determining each similarity according to the distance between each first direct broadcast resource and the characterization vector of each current direct broadcast resource, and selecting the direct broadcast resource with the highest similarity with each first direct broadcast resource from the current direct broadcast resources as a second direct broadcast resource corresponding to each first direct broadcast resource.
In a third aspect, the present disclosure provides an electronic device, comprising:
a processor and a memory;
wherein the memory is configured to store executable instructions of the processor;
when the processor executes the executable instructions, the push method of the live list described in any one of the above items may be executed.
In a fourth aspect, the present disclosure provides a storage medium comprising instructions which, when executed on a computer, the computer may perform the method of any of the above.
According to the live broadcast list pushing method and device, the electronic device and the storage medium, the browsing request triggered by the user is received, the browsing request comprises a target display resource position to be browsed and a user identification, the live broadcast resource recommendation strategy in the target display resource position is determined according to the user identification, the recommended live broadcast resource of the target display resource position is determined by adopting the live broadcast resource recommendation strategy, the recommended live broadcast resource is inserted into the current live broadcast list of the target display resource position to form a new live broadcast list and is pushed to the user, so that all live broadcast resources have the opportunity to be pushed under different recommendation strategies and are pushed out, the whole conversion rate of the live broadcast resources is improved, and benign competition among the live broadcast resources is facilitated.
Drawings
Explicit examples of the present disclosure have been shown by the above figures and will be described in more detail later. These drawings and written description are not intended to limit the scope of the disclosed concepts in any manner, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific examples.
FIG. 1 is a schematic diagram of a network architecture upon which the present disclosure is based;
fig. 2 is a schematic view of a push interface of a push method for a live list provided by the present disclosure;
fig. 3 is an interface schematic diagram of a push method of a live list provided by the present disclosure;
fig. 4 is a schematic structural diagram of a push apparatus for a live list provided in the present disclosure;
fig. 5 is a schematic diagram of a hardware structure of an electronic device provided in the present disclosure.
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate examples consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
Detailed Description
To make the purpose, technical solutions and advantages of the disclosed examples clearer, the technical solutions in the disclosed examples will be clearly and completely described below with reference to the drawings in the disclosed examples.
In the prior art, in order to improve the traffic conversion rate of live broadcast resources, some live broadcast resources are often used as recommended live broadcast resources according to the priority of the live broadcast resources, and a live broadcast list including the recommended live broadcast resources is generated based on a resource display position in a browsing request triggered by a user and is pushed to the user, so that the user selects live broadcast resources to be browsed from the live broadcast list and browses the live broadcast resources.
Typically, the live platform sets multiple categories of presentation asset bits. The browsing volumes of the users of the resource positions are different in different categories, that is, the user traffic is different. In order to increase the exposure rate of some live broadcast resources, it is a common practice to distribute some live broadcast resources according to priority, that is, to insert the live broadcast resources into a live broadcast list of a resource display position currently browsed by a user.
However, when the live broadcast resources are pushed based on the priority, it is generally adopted that the live broadcast resources with higher priority are preferentially pushed, and if and only if the live broadcast resources with higher priority are in an unopened invalid state, the live broadcast resources with lower priority may be inserted into the live broadcast list for pushing. This will be unfavorable for the effective propelling movement of each live broadcast resource, and its whole conversion rate of live broadcast resource is lower, also is unfavorable for benign competition between each live broadcast resource.
In order to solve the technical problem, the present disclosure provides a live broadcast resource pushing method, by setting a plurality of live broadcast resource recommendation strategies, various live broadcast resources are all inserted into a live broadcast list at an opportunity and pushed to a user, so that the overall conversion rate of the live broadcast resources is improved, and benign competition of the live broadcast resources is facilitated.
Fig. 1 is a schematic diagram of a network architecture on which the present disclosure is based, and as shown in fig. 1, the network architecture on which the present disclosure is based includes a push device 1 of a live list and a terminal 2; the push device 1 of the live broadcast list can be a server or a server cluster arranged at the cloud end, and the terminal 2 can be an intelligent television, an intelligent mobile phone, a desktop computer and the like used by a user; the push device 1 of the live broadcast list can perform data interaction and signaling interaction with the terminal 2 through a network to provide live broadcast browsing service based on a live broadcast platform for the terminal 2. That is to say, the server or the server cluster of the cloud based on which the push device 1 of the live broadcast list is based can also be provided with a live broadcast platform, and the live broadcast platform is loaded with live broadcast resources, and through the live broadcast platform, the user can utilize the terminal 2 to realize the acquisition of the live broadcast platform and the live broadcast resources loaded.
Fig. 2 is a schematic view of a push interface of a push method for a live broadcast list provided by the present disclosure, as shown in fig. 2, in a target display resource slot of a live broadcast platform, a plurality of live broadcast resources are displayed according to the live broadcast list.
In a first aspect, the present disclosure provides a push method for a live list.
Fig. 2 is a schematic flow chart of a live list push method provided by the present disclosure.
As shown in fig. 2, the push method of the live list includes:
step 101, receiving a browsing request triggered by a user, wherein the browsing request comprises a target display resource position to be browsed and a user identifier;
step 102, determining a direct broadcast resource recommendation strategy in the target display resource position according to the user identification, and determining a recommended direct broadcast resource of the target display resource position by adopting the direct broadcast resource recommendation strategy;
and 103, inserting the recommended live broadcast resources into a current live broadcast list of the target display resource position to form a new live broadcast list and pushing the new live broadcast list to a user.
The execution subject of the live list push method provided by the present disclosure may specifically be a live list push device, and the live list push device may specifically be integrated on an electronic device such as a server or a server cluster bearing a live platform.
Firstly, a push device of a live broadcast list receives a browse request triggered by a user, wherein the browse request is triggered by the user according to the self requirement on a live broadcast platform, the browse request can be generated when the user clicks a link of each display resource position provided on the live broadcast platform, and can also be generated when the user inputs the name, the identification, the label and the like of the display resource position in a search bar or a search box on the live broadcast platform.
In addition, in the examples provided by the present disclosure, the browsing request further includes a target display resource bit to be browsed and a user identifier; the target presentation resource bit is user-triggered, and the user identifier includes information, which is generally composed of a character string, that can be used to indicate a network address of the user, a user equipment identifier, and the like, which can be used to represent a user identity.
In order to improve the overall conversion rate of live broadcast resources and enable more live broadcast resources to be inserted into a display resource position as recommended live broadcast resources, in the disclosed example, multiple live broadcast resource recommendation strategies are provided, including but not limited to recommendation pool recommendation strategies and similarity recommendation strategies, according to the incidence relation between a user identifier and each live broadcast resource recommendation strategy, so that after a push device of a live broadcast list receives a browsing request of a user, a live broadcast resource recommendation strategy corresponding to the user identifier is determined from the multiple live broadcast resource recommendation strategies, the live broadcast resource recommendation strategy is adopted to determine the recommended live broadcast resources placed in a live broadcast list of a target display resource position, and the determined recommended live broadcast resources can be inserted into the live broadcast list to be pushed to the user.
The association relationship between the user identifier and the live broadcast resource recommendation policy may be determined based on traffic configuration requirements, for example, the traffic configuration requirement for the recommendation pool recommendation policy is half of the total traffic, and the traffic configuration requirement for the similarity recommendation policy is half of the total traffic. And when the tail mark value of the user mark is 0-4, a recommendation pool recommendation strategy is adopted for displaying the live list of the target display resource bit in the browsing request triggered by the user, and when the tail mark value indicated by the user is 5-9, similarity recommendation is adopted for displaying the live list of the target display resource bit in the browsing request triggered by the user. That is, the push device may determine the recommendation policy of the current browsing request from the plurality of live broadcast resource recommendation policies according to the value of the end identifier of the user identifier.
It should be noted that, in an alternative example, the types and the numbers of the recommendation pool recommendation policy and the similarity recommendation policy may be multiple, and the traffic proportion of each policy may be based on the traffic configuration requirement, which is not limited by the present disclosure.
According to the push method of the live broadcast list, the browse request triggered by the user is received, the browse request comprises a target display resource position to be browsed and a user identification, a live broadcast resource recommendation strategy in the target display resource position is determined according to the user identification, the recommended live broadcast resource of the target display resource position is determined by adopting the live broadcast resource recommendation strategy, the recommended live broadcast resource is inserted into the current live broadcast list of the target display resource position to form a new live broadcast list and is pushed to the user, so that each live broadcast resource has an opportunity to be pushed and is pushed out under different recommendation strategies, the improvement of the integral conversion rate of the live broadcast resource is facilitated, and benign competition among live broadcast resources is facilitated.
The following examples will further describe a determination method for recommending live broadcast resources and a generation method for a live broadcast list for different recommendation strategies:
in one optional example, the live resource recommendation policy comprises a recommendation pool recommendation policy; the display resource position corresponds to a plurality of recommendation pools, and each recommendation pool comprises a plurality of live broadcast resources.
In this example, the recommendation pool refers to a combination of a set of live resources satisfying a certain rule, and a set of multiple live resources will form a recommendation pool. For example, for a display asset bit of a certain football top level event type, the display asset bit may correspond to a recommendation pool including live broadcast resources of a plurality of sports commentary anchor, may correspond to a recommendation pool including a plurality of football secondary event types, and may even correspond to a recommendation pool including a plurality of basketball top level event types.
And the relationship between the display resource position and the recommendation pools can be stored in the resource pool information of the display resource position, and meanwhile, the resource pool information also comprises the display probability of each recommendation pool in the plurality of recommendation pools corresponding to the resource pool information and the resource quality of each live broadcast resource in each recommendation pool.
Therefore, when determining the recommended live broadcast resources of the target display resource position by using the live broadcast resource recommendation strategy, the resource pool information of the target display resource position can be determined firstly, wherein the resource pool information comprises the display probability of each recommendation pool and the resource quality of each live broadcast resource in each recommendation pool; then, selecting a target recommendation pool according to the display probability of each recommendation pool in the resource pool information; and finally, selecting at least one live broadcast resource from the live broadcast resources corresponding to the target recommendation pool as a recommended live broadcast resource according to the resource quality of the live broadcast resources in the recommendation pools.
In the above process, the display probabilities of the multiple recommendation pools corresponding to the display resource bit are different, and generally, the display probability of each recommendation pool in the resource pool information of the target display resource bit can be determined according to the priority of each recommendation pool corresponding to the target display resource bit and the proportion weight of each recommendation pool in the target display resource bit.
For example, the proportion weight of the target display resource bit is an empirically set value, generally defaults to 0, and can be used to control the display probability of the recommendation pool.
Further, when the proportion weight of all recommendation pools in the resource allocation is 0, it is assumed that n recommendation pools currently in effect and having live resources are present. At this time, the process of the present invention,
the priority 1 recommendation pool, show probability P1 ═ 80%
The priority 2 recommendation pool, show a probability of P2 ═ 1-P1 × (80) × (20) × (80) × (16%
The priority 3 recommendation pool, show probability of P3 ═ (1-P1-P2) × 80 ═ 3.2%
……
The recommended pool of priority (n) showing the probability of Pn ═ 1- (P1+ P2+ … … + Pn-1)
In addition, when a resource position has a recommendation pool showing that the proportion weight is not 0, it is assumed that there are m recommendation pools which are currently active and show that the proportion weight is not 0 and have live broadcast resources, and the values of the proportion weight shown are a1, a2 and A3 … … Am respectively;
then, the display probability P1 for the 1 st recommended pool is a1/(a1+ a2+ … … + Am);
the display probability P2 of the 2 nd recommended pool is a2/(a1+ a2+ … … + Am);
……
the display probability Pm of the mth recommended pool is Am/(a1+ a2+ … … + Am).
Therefore, based on the display probability of each recommendation pool, the target resource pool can be selected from the recommendation pools corresponding to the target display resource bits according to the principle of probability distribution. And then, selecting at least one live broadcast resource as a recommended live broadcast resource according to the resource quality of each live broadcast resource in the target resource pool. For example, for the aforementioned recommendation pool including live resources of a plurality of sports commentators, the resource quality can be expressed as popularity, praise, gift number, and so on of each sports commentator. And sequencing the resource quality to enable at least one live broadcast resource with better resource quality to be used as a recommended live broadcast resource. And inserting the selected recommended live broadcast resource into a current live broadcast list of the target display resource position to form a new live broadcast list and pushing the new live broadcast list to the user.
The priority and the proportion weight of each corresponding recommendation pool are different.
By adopting the method, the live broadcast resources in each recommendation pool can possibly enter a live broadcast list of the target display resource position as the recommended live broadcast resources and are pushed to the user.
In another optional example, the live resource recommendation policy includes a similarity recommendation policy;
determining recommended live broadcast resources of the target display resource position by adopting the live broadcast resource recommendation strategy comprises the following steps:
acquiring a browsing record of a user according to the user identification, wherein the browsing record comprises each live broadcast resource browsed by the user in a first preset time period and corresponding browsing time; determining the preference degree of each live broadcast resource according to each live broadcast resource browsed by the user in a first preset time period and corresponding browsing time, and selecting a plurality of live broadcast resources with the preference degrees larger than a preset preference degree threshold value as first direct broadcast resources; determining the similarity between each first direct broadcast resource and each current direct broadcast resource, and selecting the direct broadcast resource with the highest similarity with each first direct broadcast resource from the current direct broadcast resources as a second direct broadcast resource corresponding to each first direct broadcast resource; sequencing the second live broadcast resources according to the user preference of each first live broadcast resource and the similarity between each first live broadcast resource and the corresponding second live broadcast resource; and determining at least one second live broadcast resource as a recommended live broadcast resource according to the sequencing result.
Specifically, when the similarity recommendation strategy is adopted to determine to recommend the live broadcast resources, the live broadcast resources which are possibly preferred by the user are selected from a large number of live broadcast resources based on the preference of the user to serve as the recommended live broadcast resources.
Further, a machine learning model may be relied upon in this process. That is to say, before obtaining the browsing record of the user according to the user identifier, the method further includes:
and collecting browsing records of other users except the user within a first preset time period.
And inputting each live broadcast resource and corresponding browsing time in the browsing records of the other users into a machine learning model, and determining the characterization vector of each current live broadcast resource.
And calculating the distance between the characterization vectors of any two live broadcast resources according to a preset characterization vector distance formula (1)).
Figure RE-GDA0002367679540000111
Wherein score1 represents similarity between live broadcasts, Vec represents a live broadcast characterization vector, and Vec represents a live broadcast characterization vectoriRepresenting the characterization vector, Vec, of the ith live broadcastjRepresenting the characterization vector, Vec, of the jth live broadcast roomi*VecjRepresents the dot product of the characterization vectors of the ith live broadcast room and the jth live broadcast room, | VeciI represents the modulus of the characterization vector of the ith live broadcast room, | VecjAnd | represents the modulus of the jth live room characterization vector.
Therefore, the method for determining the similarity between each first live broadcast resource and each current live broadcast resource and selecting the live broadcast resource with the highest similarity with each first live broadcast resource from the current live broadcast resources as the second live broadcast resource corresponding to each first live broadcast resource can adopt the following mode:
and determining each similarity according to the distance between each first direct broadcast resource and the characterization vector of each current direct broadcast resource, and selecting the direct broadcast resource with the highest similarity with each first direct broadcast resource from the current direct broadcast resources as a second direct broadcast resource corresponding to each first direct broadcast resource.
In addition, the user's preference for each live broadcast resource browsed in the first preset time period can be obtained by calculating according to formula (2):
Figure RE-GDA0002367679540000112
where score2 represents the user's preference for live rooms, WatchiIndicating the duration of the user's viewing of the live room i,
Figure RE-GDA0002367679540000113
representing the total duration of m watching live rooms in the user history, PayiRepresenting the amount of payment made by the user to the live room i,
Figure RE-GDA0002367679540000114
indicating the total amount of n live-air-room payments in the user history, ChatiIndicating the number of barrages released by the user to the live room i,representing the user history the total number of p live room postings, α the weight of the viewing duration, β the weight of the payment, and γ the weight of the postings.
Meanwhile, according to the user's preference for each first live broadcast resource and the similarity between each first live broadcast resource and its corresponding second live broadcast resource, in the process of sorting each second live broadcast resource, a score can be determined based on the preference and the similarity so as to facilitate sorting, wherein the score can be obtained by calculation with a formula (3):
score1 score2 formula (3)
score1 represents the similarity of live rooms and score2 represents the user's preference for live rooms.
By adopting the method, the live broadcast resources in each recommendation pool can possibly enter a live broadcast list of the target display resource position as the recommended live broadcast resources and are pushed to the user.
Fig. 3 is an interface schematic diagram of a live broadcast list pushing method provided by the present disclosure, as shown in fig. 3, a current live broadcast list exists on an interface of the live broadcast platform, the current live broadcast list includes a live broadcast resource a, a live broadcast resource B, a live broadcast resource D, and a live broadcast resource F, and a recommended live broadcast resource C and a recommended live broadcast resource E obtained in the above manner are inserted into the current live broadcast list to form a current live broadcast list including the live broadcast resource a, the live broadcast resource B, the recommended live broadcast resource C, the live broadcast resource D, the recommended live broadcast resource E, and the live broadcast resource F to be pushed to a user.
The live broadcast list pushing method comprises the steps of receiving a browsing request triggered by a user, wherein the browsing request comprises a target display resource position to be browsed and a user identification, determining a live broadcast resource recommendation strategy in the target display resource position according to the user identification, determining a recommended live broadcast resource of the target display resource position by adopting the live broadcast resource recommendation strategy, inserting the recommended live broadcast resource into a current live broadcast list of the target display resource position to form a new live broadcast list and push the new live broadcast list to the user, so that each live broadcast resource has an opportunity to be pushed out under different recommendation strategies, the whole conversion rate of the live broadcast resource is improved, and benign competition among live broadcast resources is facilitated.
Fig. 4 is a schematic structural diagram of a push apparatus for live listings provided in the present disclosure, as shown in fig. 4, the push apparatus for live listings includes:
the system comprises a receiving module 10, a display module and a display module, wherein the receiving module is used for receiving a browsing request triggered by a user, and the browsing request comprises a target display resource position to be browsed and a user identifier;
the first processing module 20 is configured to determine, according to the user identifier, a live broadcast resource recommendation policy for the target display resource location, and determine, by using the live broadcast resource recommendation policy, a recommended live broadcast resource of the target display resource location;
and the second processing module 30 is configured to insert the recommended live broadcast resource into the current live broadcast list of the target display resource location, form a new live broadcast list, and push the new live broadcast list to the user.
Illustratively, the number of the live resource recommendation strategies is multiple;
the first processing module 20 is specifically configured to determine, according to the value of the tail identifier of the user identifier, a recommendation policy of the current browsing request from a plurality of live broadcast resource recommendation policies.
Illustratively, the live resource recommendation policy includes a recommendation pool recommendation policy; the display resource position corresponds to a plurality of recommendation pools, and each recommendation pool comprises a plurality of live broadcast resources;
the first processing module 20 is specifically configured to determine resource pool information of a target display resource location, where the resource pool information includes a display probability of each recommendation pool and a resource quality of each live resource in each recommendation pool; selecting a target recommendation pool according to the display probability of each recommendation pool in the resource pool information; and selecting at least one live broadcast resource from the live broadcast resources corresponding to the target recommendation pool as a recommended live broadcast resource according to the resource quality of the live broadcast resources in the recommendation pools.
For example, before the first processing module 20 determines the resource pool information of the target display resource bit, the first processing module is further configured to determine the display probability of each recommendation pool in the resource pool information of the target display resource bit according to the priority of each recommendation pool corresponding to the target display resource bit and the proportion weight of each recommendation pool in the target display resource bit.
Illustratively, the live resource recommendation policy includes a similarity recommendation policy;
the first processing module 20 is specifically configured to obtain a browsing record of the user according to the user identifier, where the browsing record includes each live broadcast resource browsed by the user within a first preset time period and corresponding browsing time; determining the preference degree of each live broadcast resource according to each live broadcast resource browsed by the user in a first preset time period and corresponding browsing time, and selecting a plurality of live broadcast resources with the preference degrees larger than a preset preference degree threshold value as first direct broadcast resources; determining the similarity between each first direct broadcast resource and each current direct broadcast resource, and selecting the direct broadcast resource with the highest similarity with each first direct broadcast resource from the current direct broadcast resources as a second direct broadcast resource corresponding to each first direct broadcast resource; sequencing the second live broadcast resources according to the user preference of each first live broadcast resource and the similarity between each first live broadcast resource and the corresponding second live broadcast resource; and determining at least one second live broadcast resource as a recommended live broadcast resource according to the sequencing result.
Illustratively, the first processing module 20, after obtaining a browsing record of the user according to the user identifier, where the browsing record includes live resources browsed by the user within a first preset time period and corresponding browsing time, is further configured to:
collecting browsing records of other users except the user within a first preset time period;
inputting each live broadcast resource and corresponding browsing time in the browsing records of the other users into a machine learning model, and determining a representation vector of each current live broadcast resource;
calculating the distance between the characterization vectors of any two live broadcast resources according to a preset characterization vector distance formula;
correspondingly, the determining the similarity between each first live broadcast resource and each current live broadcast resource, and selecting the live broadcast resource with the highest similarity with each first live broadcast resource from the current live broadcast resources as the second live broadcast resource corresponding to each first live broadcast resource includes:
and determining each similarity according to the distance between each first direct broadcast resource and the characterization vector of each current direct broadcast resource, and selecting the direct broadcast resource with the highest similarity with each first direct broadcast resource from the current direct broadcast resources as a second direct broadcast resource corresponding to each first direct broadcast resource.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process and corresponding beneficial effects of the system described above may refer to the corresponding process in the foregoing method example, and are not described herein again.
The utility model provides a push device of live broadcast list, through receiving the browse request that the user triggered, browse request includes target show resource position and the user identification of waiting to browse, according to the user identification confirms right live broadcast resource recommendation strategy in the target show resource position, and adopt this live broadcast resource recommendation strategy to confirm the live broadcast resource of recommendation of target show resource position, will recommend live broadcast resource insert the current live broadcast list of target show resource position forms new live broadcast list and propelling movement to the user to each live broadcast resource all has the opportunity of getting the propelling movement under the recommendation strategy of difference and is pushed away, is favorable to the improvement of the whole conversion rate of live broadcast resource, also does benefit to benign competition between in the live broadcast resource.
Fig. 5 is a schematic diagram of a hardware structure of an electronic device provided in the present disclosure. As shown in fig. 5, the electronic device may specifically include:
a processor 42;
a memory 41 for storing processor-executable instructions;
wherein the memory 41 is configured to store instructions executable by the processor 42;
the processor 42, when executing the executable instructions, may perform any of the live list push methods described above.
The memory 41 may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like. And processor 42 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital signal processor architectures (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessor architectures or other electronic components.
The above instructions may be written in languages such as C/C + +, Java, Shell, Python, etc., and this example is not intended to be limiting.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process and corresponding beneficial effects of the system described above may refer to the corresponding process in the foregoing method example, and are not described herein again.
The electronic equipment provided by the disclosure receives a browsing request triggered by a user, wherein the browsing request comprises a target display resource position to be browsed and a user identifier, a live broadcast resource recommendation strategy in the target display resource position is determined according to the user identifier, the recommended live broadcast resource of the target display resource position is determined by adopting the live broadcast resource recommendation strategy, the recommended live broadcast resource is inserted into a current live broadcast list of the target display resource position to form a new live broadcast list and is pushed to the user, so that each live broadcast resource has an opportunity to be pushed out under different recommendation strategies, the whole conversion rate of the live broadcast resource is improved, and benign competition among the live broadcast resources is facilitated.
The present disclosure provides a storage medium comprising instructions which, when executed on the computer, may carry out any of the methods described above.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure 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 present disclosure is limited only by the appended claims.

Claims (14)

1. A live list pushing method is characterized by comprising the following steps:
receiving a browsing request triggered by a user, wherein the browsing request comprises a target display resource position to be browsed and a user identifier;
determining a live broadcast resource recommendation strategy in the target display resource position according to the user identification, and determining recommended live broadcast resources of the target display resource position by adopting the live broadcast resource recommendation strategy;
and inserting the recommended live broadcast resource into a current live broadcast list of the target display resource position to form a new live broadcast list and pushing the new live broadcast list to a user.
2. The push method according to claim 1, wherein the number of the live resource recommendation strategies is plural;
the determining, according to the user identifier, a recommendation policy for live resources in the target display resource slot includes:
and determining a recommendation strategy of the browsing request from a plurality of live broadcast resource recommendation strategies according to the tail identification value of the user identification.
3. The push method of claim 1, wherein the live resource recommendation policy comprises a recommendation pool recommendation policy; the display resource position corresponds to a plurality of recommendation pools, and each recommendation pool comprises a plurality of live broadcast resources;
the method for determining the recommended live broadcast resources of the target display resource bit by adopting the live broadcast resource recommendation strategy comprises the following steps:
determining resource pool information of a target display resource position, wherein the resource pool information comprises the display probability of each recommendation pool and the resource quality of each live broadcast resource in each recommendation pool;
selecting a target recommendation pool according to the display probability of each recommendation pool in the resource pool information;
and selecting at least one live broadcast resource from the live broadcast resources corresponding to the target recommendation pool as a recommended live broadcast resource according to the resource quality of the live broadcast resources in the recommendation pools.
4. The push method according to claim 3, wherein before determining the resource pool information of the target show resource bit, further comprising:
and determining the display probability of each recommendation pool in the resource pool information of the target display resource position according to the priority of each recommendation pool corresponding to the target display resource position and the proportion weight of each recommendation pool in the target display resource position.
5. The push method of claim 1, wherein the live resource recommendation policy comprises a similarity recommendation policy;
the method for determining the recommended live broadcast resources of the target display resource bit by adopting the live broadcast resource recommendation strategy comprises the following steps:
acquiring a browsing record of a user according to the user identification, wherein the browsing record comprises each live broadcast resource browsed by the user in a first preset time period and corresponding browsing time;
determining the preference degree of each live broadcast resource according to each live broadcast resource browsed by the user in a first preset time period and corresponding browsing time, and selecting a plurality of live broadcast resources with the preference degrees larger than a preset preference degree threshold value as first direct broadcast resources;
determining the similarity between each first direct broadcast resource and each current direct broadcast resource, and selecting the direct broadcast resource with the highest similarity with each first direct broadcast resource from the current direct broadcast resources as a second direct broadcast resource corresponding to each first direct broadcast resource;
sequencing the second live broadcast resources according to the user preference of each first live broadcast resource and the similarity between each first live broadcast resource and the corresponding second live broadcast resource;
and determining at least one second live broadcast resource as a recommended live broadcast resource according to the sequencing result.
6. The push method according to claim 5, wherein the obtaining of the browsing record of the user according to the user identifier, where the browsing record includes live resources browsed by the user within a first preset time period and a corresponding browsing time, further includes:
collecting browsing records of other users except the user within a first preset time period;
inputting each live broadcast resource and corresponding browsing time in the browsing records of the other users into a machine learning model, and determining a representation vector of each current live broadcast resource;
calculating the distance between the characterization vectors of any two live broadcast resources according to a preset characterization vector distance formula;
correspondingly, the determining the similarity between each first live broadcast resource and each current live broadcast resource, and selecting the live broadcast resource with the highest similarity with each first live broadcast resource from the current live broadcast resources as the second live broadcast resource corresponding to each first live broadcast resource includes:
and determining each similarity according to the distance between each first direct broadcast resource and the characterization vector of each current direct broadcast resource, and selecting the direct broadcast resource with the highest similarity with each first direct broadcast resource from the current direct broadcast resources as a second direct broadcast resource corresponding to each first direct broadcast resource.
7. A push device for live listings, comprising:
the system comprises a receiving module, a browsing module and a display module, wherein the receiving module is used for receiving a browsing request triggered by a user, and the browsing request comprises a target display resource position to be browsed and a user identifier;
the first processing module is used for determining a live broadcast resource recommendation strategy in the target display resource position according to the user identification and determining recommended live broadcast resources of the target display resource position by adopting the live broadcast resource recommendation strategy;
and the second processing module is used for inserting the recommended live broadcast resources into the current live broadcast list of the target display resource position to form a new live broadcast list and pushing the new live broadcast list to the user.
8. The pushing device according to claim 7, wherein the number of the live resource recommendation strategies is plural;
the first processing module is specifically configured to determine a recommendation policy of the current browsing request from a plurality of live broadcast resource recommendation policies according to the value of the tail identifier of the user identifier.
9. The push device of claim 7, wherein the live resource recommendation policy comprises a recommendation pool recommendation policy; the display resource position corresponds to a plurality of recommendation pools, and each recommendation pool comprises a plurality of live broadcast resources;
the first processing module is specifically configured to determine resource pool information of a target display resource bit, where the resource pool information includes a display probability of each recommendation pool and a resource quality of each live broadcast resource in each recommendation pool; selecting a target recommendation pool according to the display probability of each recommendation pool in the resource pool information; and selecting at least one live broadcast resource from the live broadcast resources corresponding to the target recommendation pool as a recommended live broadcast resource according to the resource quality of the live broadcast resources in the recommendation pools.
10. The pushing device of claim 9, wherein before the first processing module determines the resource pool information of the target display resource bit, the first processing module is further configured to determine a display probability of each recommendation pool in the resource pool information of the target display resource bit according to a priority of each recommendation pool corresponding to the target display resource bit and a proportion weight of each recommendation pool in the target display resource bit.
11. The push device of claim 7, wherein the live resource recommendation policy comprises a similarity recommendation policy;
the first processing module is specifically configured to obtain a browsing record of a user according to the user identifier, where the browsing record includes each live broadcast resource browsed by the user within a first preset time period and corresponding browsing time; determining the preference degree of each live broadcast resource according to each live broadcast resource browsed by the user in a first preset time period and corresponding browsing time, and selecting a plurality of live broadcast resources with the preference degrees larger than a preset preference degree threshold value as first direct broadcast resources; determining the similarity between each first direct broadcast resource and each current direct broadcast resource, and selecting the direct broadcast resource with the highest similarity with each first direct broadcast resource from the current direct broadcast resources as a second direct broadcast resource corresponding to each first direct broadcast resource; sequencing the second live broadcast resources according to the user preference of each first live broadcast resource and the similarity between each first live broadcast resource and the corresponding second live broadcast resource; and determining at least one second live broadcast resource as a recommended live broadcast resource according to the sequencing result.
12. The pushing device of claim 11, wherein the first processing module, before obtaining a browsing record of the user according to the user identifier, where the browsing record includes live resources browsed by the user within a first preset time period and corresponding browsing time, is further configured to:
collecting browsing records of other users except the user within a first preset time period;
inputting each live broadcast resource and corresponding browsing time in the browsing records of the other users into a machine learning model, and determining a representation vector of each current live broadcast resource;
calculating the distance between the characterization vectors of any two live broadcast resources according to a preset characterization vector distance formula;
correspondingly, the determining the similarity between each first live broadcast resource and each current live broadcast resource, and selecting the live broadcast resource with the highest similarity with each first live broadcast resource from the current live broadcast resources as the second live broadcast resource corresponding to each first live broadcast resource includes:
and determining each similarity according to the distance between each first direct broadcast resource and the characterization vector of each current direct broadcast resource, and selecting the direct broadcast resource with the highest similarity with each first direct broadcast resource from the current direct broadcast resources as a second direct broadcast resource corresponding to each first direct broadcast resource.
13. A terminal device, comprising:
a processor and a memory;
wherein the memory is configured to store executable instructions of the processor;
the processor, when executing the executable instructions, may perform a push method of a live list of any of the above claims 1-6.
14. A storage medium comprising instructions which, when executed on a computer, cause the computer to perform the method of any one of claims 1 to 6.
CN201910989582.3A 2019-10-17 2019-10-17 Live list pushing method and device, electronic equipment and storage medium Active CN110856003B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910989582.3A CN110856003B (en) 2019-10-17 2019-10-17 Live list pushing method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910989582.3A CN110856003B (en) 2019-10-17 2019-10-17 Live list pushing method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN110856003A true CN110856003A (en) 2020-02-28
CN110856003B CN110856003B (en) 2021-11-02

Family

ID=69597591

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910989582.3A Active CN110856003B (en) 2019-10-17 2019-10-17 Live list pushing method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN110856003B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111881353A (en) * 2020-07-28 2020-11-03 北京达佳互联信息技术有限公司 Display resource pushing method and device, electronic equipment and storage medium
CN111970528A (en) * 2020-08-20 2020-11-20 广州华多网络科技有限公司 Live broadcast recommendation method and device, computer equipment and readable storage medium
CN112261423A (en) * 2020-10-16 2021-01-22 北京百度网讯科技有限公司 Method, device, equipment and storage medium for pushing information
CN113365095A (en) * 2021-06-15 2021-09-07 北京百度网讯科技有限公司 Live broadcast resource recommendation method and device, electronic equipment and storage medium
CN113609332A (en) * 2021-08-11 2021-11-05 上海众源网络有限公司 Method, system and device for recommending video live broadcast resources
CN114697688A (en) * 2020-12-29 2022-07-01 阿里巴巴集团控股有限公司 Live broadcast strategy recommendation method, interaction method, device, equipment and storage medium
CN115291503A (en) * 2022-09-29 2022-11-04 北京达佳互联信息技术有限公司 Recommendation method, recommendation device, electronic device and storage medium
CN115967839A (en) * 2022-12-30 2023-04-14 北京华心维联网络科技有限公司 Live broadcast gift recommendation method and device

Citations (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020143763A1 (en) * 2001-04-03 2002-10-03 Martin James L. System and method for analyzing a database for on-line reorganization
US20140025554A1 (en) * 2006-06-29 2014-01-23 Itg Software Solutions, Inc. Systems, methods, and computer program products for providing real time analytic widgets in a financial trading system
CN103646070A (en) * 2013-12-06 2014-03-19 北京趣拿软件科技有限公司 Data processing method and device for search engine
CN106658074A (en) * 2016-11-21 2017-05-10 武汉斗鱼网络科技有限公司 Method for evaluating live broadcasting room recommendation strategy, user equipment (UE) and server system
CN107818166A (en) * 2017-11-07 2018-03-20 暴风集团股份有限公司 A kind of information recommends method, apparatus, server and system
CN107948740A (en) * 2017-10-30 2018-04-20 广州虎牙信息科技有限公司 Video playing control method, device and terminal
CN107948326A (en) * 2017-12-29 2018-04-20 暴风集团股份有限公司 Commending contents adjustment method and device, electronic equipment, storage medium, program
CN108462900A (en) * 2017-02-22 2018-08-28 合网络技术（北京）有限公司 Video recommendation method and device
CN108712379A (en) * 2018-04-08 2018-10-26 北京奇艺世纪科技有限公司 Data push method and device
CN109241431A (en) * 2018-09-07 2019-01-18 腾讯科技（深圳）有限公司 A kind of resource recommendation method and device
CN109819002A (en) * 2017-11-22 2019-05-28 腾讯科技（深圳）有限公司 Data push method and device, storage medium and electronic device
CN109862013A (en) * 2019-01-31 2019-06-07 武汉斗鱼网络科技有限公司 A kind of direct broadcasting room recommended method, storage medium, electronic equipment and system
CN110012356A (en) * 2019-04-16 2019-07-12 腾讯科技（深圳）有限公司 Video recommendation method, device and equipment and computer storage medium
CN110020143A (en) * 2017-11-20 2019-07-16 北京京东尚科信息技术有限公司 A kind of landing page generation method and device
CN110020102A (en) * 2017-09-01 2019-07-16 阿里巴巴集团控股有限公司 Object recommendation method, apparatus, storage medium, processor and system
CN110020122A (en) * 2017-10-16 2019-07-16 Tcl集团股份有限公司 A kind of video recommendation method, system and computer readable storage medium
CN110162690A (en) * 2018-10-23 2019-08-23 腾讯科技（深圳）有限公司 Determine user to the method and apparatus of the interest-degree of article, equipment and storage medium
CN110162664A (en) * 2018-12-17 2019-08-23 腾讯科技（深圳）有限公司 Video recommendation method, device, computer equipment and storage medium

Patent Citations (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020143763A1 (en) * 2001-04-03 2002-10-03 Martin James L. System and method for analyzing a database for on-line reorganization
US20140025554A1 (en) * 2006-06-29 2014-01-23 Itg Software Solutions, Inc. Systems, methods, and computer program products for providing real time analytic widgets in a financial trading system
CN103646070A (en) * 2013-12-06 2014-03-19 北京趣拿软件科技有限公司 Data processing method and device for search engine
CN106658074A (en) * 2016-11-21 2017-05-10 武汉斗鱼网络科技有限公司 Method for evaluating live broadcasting room recommendation strategy, user equipment (UE) and server system
CN108462900A (en) * 2017-02-22 2018-08-28 合网络技术（北京）有限公司 Video recommendation method and device
CN110020102A (en) * 2017-09-01 2019-07-16 阿里巴巴集团控股有限公司 Object recommendation method, apparatus, storage medium, processor and system
CN110020122A (en) * 2017-10-16 2019-07-16 Tcl集团股份有限公司 A kind of video recommendation method, system and computer readable storage medium
CN107948740A (en) * 2017-10-30 2018-04-20 广州虎牙信息科技有限公司 Video playing control method, device and terminal
CN107818166A (en) * 2017-11-07 2018-03-20 暴风集团股份有限公司 A kind of information recommends method, apparatus, server and system
CN110020143A (en) * 2017-11-20 2019-07-16 北京京东尚科信息技术有限公司 A kind of landing page generation method and device
CN109819002A (en) * 2017-11-22 2019-05-28 腾讯科技（深圳）有限公司 Data push method and device, storage medium and electronic device
CN107948326A (en) * 2017-12-29 2018-04-20 暴风集团股份有限公司 Commending contents adjustment method and device, electronic equipment, storage medium, program
CN108712379A (en) * 2018-04-08 2018-10-26 北京奇艺世纪科技有限公司 Data push method and device
CN109241431A (en) * 2018-09-07 2019-01-18 腾讯科技（深圳）有限公司 A kind of resource recommendation method and device
CN110162690A (en) * 2018-10-23 2019-08-23 腾讯科技（深圳）有限公司 Determine user to the method and apparatus of the interest-degree of article, equipment and storage medium
CN110162664A (en) * 2018-12-17 2019-08-23 腾讯科技（深圳）有限公司 Video recommendation method, device, computer equipment and storage medium
CN109862013A (en) * 2019-01-31 2019-06-07 武汉斗鱼网络科技有限公司 A kind of direct broadcasting room recommended method, storage medium, electronic equipment and system
CN110012356A (en) * 2019-04-16 2019-07-12 腾讯科技（深圳）有限公司 Video recommendation method, device and equipment and computer storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
管宇男: "IPTV推荐系统研究", 《中国优秀硕士学位论文全文数据库》 *

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111881353A (en) * 2020-07-28 2020-11-03 北京达佳互联信息技术有限公司 Display resource pushing method and device, electronic equipment and storage medium
CN111881353B (en) * 2020-07-28 2023-10-31 北京达佳互联信息技术有限公司 Method and device for pushing display resources, electronic equipment and storage medium
CN111970528A (en) * 2020-08-20 2020-11-20 广州华多网络科技有限公司 Live broadcast recommendation method and device, computer equipment and readable storage medium
CN111970528B (en) * 2020-08-20 2022-04-26 广州方硅信息技术有限公司 Live broadcast recommendation method and device, computer equipment and readable storage medium
CN112261423A (en) * 2020-10-16 2021-01-22 北京百度网讯科技有限公司 Method, device, equipment and storage medium for pushing information
CN114697688A (en) * 2020-12-29 2022-07-01 阿里巴巴集团控股有限公司 Live broadcast strategy recommendation method, interaction method, device, equipment and storage medium
CN113365095A (en) * 2021-06-15 2021-09-07 北京百度网讯科技有限公司 Live broadcast resource recommendation method and device, electronic equipment and storage medium
CN113609332A (en) * 2021-08-11 2021-11-05 上海众源网络有限公司 Method, system and device for recommending video live broadcast resources
CN113609332B (en) * 2021-08-11 2024-03-08 上海众源网络有限公司 Video live broadcast resource recommendation method, system and device
CN115291503A (en) * 2022-09-29 2022-11-04 北京达佳互联信息技术有限公司 Recommendation method, recommendation device, electronic device and storage medium
CN115967839A (en) * 2022-12-30 2023-04-14 北京华心维联网络科技有限公司 Live broadcast gift recommendation method and device

Also Published As

Publication number Publication date
CN110856003B (en) 2021-11-02

Similar Documents

Publication Publication Date Title
CN110856003B (en) Live list pushing method and device, electronic equipment and storage medium
US10949744B2 (en) Recurrent neural network architectures which provide text describing images
US20100034466A1 (en) Object Identification in Images
US9990101B2 (en) Managing GUI control auto-advancing
CN108959558B (en) Information pushing method and device, computer equipment and storage medium
US20080281709A1 (en) Advertising method and method of sharing advertisement revenue
CN110264268B (en) Advertisement putting device, method, equipment and storage medium thereof
CN109582904B (en) Published content modification method, device, server, terminal and storage medium
CN109255070B (en) Recommendation information processing method and device, computer equipment and storage medium
CN112269917A (en) Media resource display method, device, equipment, system and storage medium
US9600165B2 (en) Evaluating portions of content in an online community
CN114140162A (en) Advertisement putting method and device, electronic equipment and computer readable storage medium
CN114554257A (en) Resource allocation method, device, electronic equipment and storage medium
CN113515336B (en) Live room joining method, creation method, device, equipment and storage medium
CN111353455A (en) Video content determination method and device, storage medium and electronic equipment
CN114257873B (en) Information pushing method and card display method in network live broadcast scene
WO2022022075A1 (en) Video processing method, living streaming processing method, live streaming system, electronic device, terminal, and medium
US20220207918A1 (en) Information obtain method, information push method, and terminal device
CN114943005A (en) Picture display processing method and device
US20160371753A1 (en) Method, apparatus, and system for controlling publication of network media information
CN113068060A (en) Video account matching method and device and electronic equipment
CN112200614A (en) Advertisement text implanting and displaying method and corresponding device, equipment and medium
CN111954013A (en) Live broadcast interaction method and device, terminal equipment, server and storage medium
CN111144067B (en) E-book-based reading task processing method, computing device and storage medium
KR102391640B1 (en) Method and Apparatus for VOD Content Recommendation

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant