CN113365095B

CN113365095B - Live broadcast resource recommendation method and device, electronic equipment and storage medium

Info

Publication number: CN113365095B
Application number: CN202110663495.6A
Authority: CN
Inventors: 赵彬
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2021-06-15
Filing date: 2021-06-15
Publication date: 2023-03-03
Anticipated expiration: 2041-06-15
Also published as: CN113365095A

Abstract

The disclosure discloses a live broadcast resource recommendation method and device, electronic equipment and a storage medium, and relates to the technical field of computers, in particular to the field of intelligent search. The specific implementation scheme is as follows: a first ordering result for a plurality of first direct broadcast resources is obtained. The first sorting result is obtained by sorting the plurality of first direct-broadcast resources according to the first attribute information. And determining the weight value of each first direct broadcast resource according to the first attribute value of the second attribute information of each first direct broadcast resource. And determining a second sorting result aiming at the plurality of first direct-playing resources according to the weight value and the first sorting result. And determining the live broadcast resources to be recommended according to the second sequencing result.

Description

Live broadcast resource recommendation method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of computer technology, and more particularly, to the field of intelligent search.

Background

With the development of internet technology, network resource platforms such as a video playing platform, an e-commerce platform or a news platform at present all bear massive network resources, such as live broadcast resources. In order to meet the fast browsing requirement of the user, the network resource platform needs to select appropriate network resources from the mass data to recommend to the user.

Disclosure of Invention

The disclosure provides a live broadcast resource recommendation method and device, electronic equipment and a storage medium.

According to an aspect of the present disclosure, a live broadcast resource recommendation method is provided, including: obtaining a first sequencing result aiming at a plurality of first direct-playing resources, wherein the first sequencing result is obtained by sequencing the plurality of first direct-playing resources according to first attribute information; determining a weight value of each first direct broadcast resource according to a first attribute value of second attribute information of each first direct broadcast resource; determining a second sorting result for the plurality of first direct broadcast resources according to the weight values and the first sorting result; and determining the live broadcast resources to be recommended according to the second sequencing result.

According to another aspect of the present disclosure, a live resource recommendation apparatus is provided, including: a first obtaining module, configured to obtain a first ordering result for a plurality of first direct-broadcast resources, where the first ordering result is obtained by ordering the plurality of first direct-broadcast resources according to first attribute information; the first determining module is used for determining a weight value of each first direct broadcast resource according to a first attribute value of second attribute information of each first direct broadcast resource; a second determining module, configured to determine a second ranking result for the plurality of first direct broadcast resources according to the weight value and the first ranking result; and a third determining module, configured to determine, according to the second sorting result, a live resource to be recommended.

According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a live resource recommendation method as described above.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to execute the live resource recommendation method as described above.

According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a live resource recommendation method as described above.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

fig. 1 schematically illustrates an exemplary system architecture to which a live resource recommendation method and apparatus may be applied, according to an embodiment of the present disclosure;

fig. 2 schematically shows a flow chart of a live resource recommendation method according to an embodiment of the present disclosure;

fig. 3 schematically shows a flow chart of a live resource recommendation method according to another embodiment of the present disclosure;

fig. 4 schematically illustrates an implementation flowchart of a live resource recommendation method according to an embodiment of the present disclosure;

fig. 5 schematically shows a block diagram of a live resource recommendation apparatus according to an embodiment of the present disclosure; and

FIG. 6 illustrates a schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

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.

Under the live broadcast scene, the real-time online number of people in the live broadcast room can reflect the heat of live broadcast resources to a certain extent. If live broadcast resources with a large number of online people exist, the live broadcast resources can be considered to attract users to a certain extent and are high-quality live broadcast resources.

The inventor discovers that the real-time number of people in the live broadcast room is influenced by factors such as categories of live broadcast resources, the broadcasting time, the current broadcasting time and the like in the process of realizing the concept disclosed by the invention, and the deviation of the hot live broadcast is determined only according to the online number of people in the live broadcast room. For example, the number of people on line in jade and live broadcast rooms with goods resources is generally high. In addition, the hot of live broadcast is affected by the duration of the broadcast. For example, the number of live online people just started is small. Within a certain broadcasting time, the number of online people increases along with the increase of the broadcasting time.

Therefore, the deviation caused by factors such as the category of the live broadcast resources and the playing time is eliminated, and the live broadcast resources are pulled to the same dimension for comparison, which becomes the key point.

Fig. 1 schematically shows an exemplary system architecture to which the live resource recommendation method and apparatus may be applied according to an embodiment of the present disclosure.

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. For example, in another embodiment, an exemplary system architecture to which the live resource recommendation method and apparatus may be applied may include a terminal device, but the terminal device may implement the live resource recommendation method and apparatus provided in the embodiments of the present disclosure without interacting with a server.

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 and/or wireless communication links, and so forth.

The user may use the

terminal devices

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

terminal devices

101, 102, 103 may have installed thereon various communication client applications, such as a knowledge reading-type application, a web browser application, a search-type application, an instant messaging tool, a mailbox client, and/or social platform software, etc. (by way of example only).

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (for example only) providing support for live resources sought by users with the

terminal devices

101, 102, 103. 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., a webpage, information, or data obtained or generated according to the user request) to the terminal device.

It should be noted that the live resource recommendation method provided by the embodiment of the present disclosure may be generally executed by the

terminal device

101, 102, or 103. Correspondingly, the live resource recommendation device provided by the embodiment of the present disclosure may also be disposed in the

terminal device

101, 102, or 103.

Alternatively, the live resource recommendation method provided by the embodiment of the present disclosure may also be generally executed by the server 105. Accordingly, the live resource recommendation device provided by the embodiment of the present disclosure may be generally disposed in the server 105. The live resource recommendation method provided by the embodiment of the present disclosure may also be executed by a server or a server cluster that is different from the server 105 and is capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105. Correspondingly, the live resource recommendation device provided by the embodiment of the present disclosure may also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105.

For example, when a user needs to request a live resource, the

terminal device

101, 102, 103 may obtain all relevant live resources in response to the user request. And then sending the acquired plurality of live broadcast resources to the server 105, and processing the plurality of live broadcast resources by the server 105 to obtain a first sequencing result. And further processing the first sequencing result according to the attribute information different from that when the first sequencing result is determined or the attribute information needing to be highlighted, so as to obtain a second sequencing result. And determining the live broadcast resources to be recommended according to the second sequencing result. Or by a server or a cluster of servers capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105, processes the acquired multitude of live resources and finally determines the live resources to be recommended.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is 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 live resource recommendation method according to an embodiment of the present disclosure.

As shown in fig. 2, the method includes operations S210 to S240.

In operation S210, a first ordering result for a plurality of first direct broadcast resources is obtained. The first sorting result is obtained by sorting the plurality of first direct-broadcast resources according to the first attribute information.

In operation S220, a weight value of each first direct broadcast resource is determined according to the first attribute value of the second attribute information of each first direct broadcast resource.

In operation S230, a second ranking result for the plurality of first direct broadcast resources is determined according to the weight value and the first ranking result.

In operation S240, a live resource to be recommended is determined according to the second sorting result.

According to an embodiment of the present disclosure, the first live resource may include various types of live resources that have been historically played and are being played. The first attribute information may include at least one of user attribute information such as user territory, category information of live broadcast resources, style and grade information of the anchor, and the like. The first ranking result is obtained by performing score evaluation and ranking on each live broadcast resource through a trained ranking model, for example. The ranking model is trained to perform score evaluation on each live broadcast resource based on first attribute information of each live broadcast resource, and rank the related live broadcast resources according to the score evaluation result.

According to an embodiment of the present disclosure, the second attribute information may be some or some of the first attribute information, or may be other attribute information different from any of the first attribute information. Taking a live broadcast resource as an example, the first attribute information includes, for example, a category of the live broadcast resource, an anchor style, an anchor level, a number of users who pay attention to the live broadcast, a number of users who have viewed the live broadcast, and the like, and the second attribute information may be at least one of a number of real-time users, a number of real-time comments, a user viewing duration, and the like in the live broadcast room, and is not limited herein.

According to an embodiment of the present disclosure, the weighting values may be a predetermined series of values, such as 1 to 10. Each weight value may represent a plurality of first attribute values within the same preset range. Taking the second attribute information as the number of real-time users in the live broadcast room as an example, the first attribute value can represent the number of the real-time users. When determining the weight value of the live broadcast room, for example, it may be determined that the weight value of the live broadcast room in which the number of users is less than 500 is 1, the weight value of the live broadcast room in which the number of users is in the range of 10 to 30 ten thousand is 5, and the weight value of the live broadcast room in which the number of users is greater than 100 ten thousand is 10. The weight value may also be a numerical value calculated from the first attribute value according to a preset function. For example, the preset function may be that the weight value = first attribute value/10000, and the weight value corresponding to a live broadcast room with the number of users being 500 is 0.05, and the weight value corresponding to a live broadcast room with the number of users being 10 ten thousand is 10.

According to the embodiment of the disclosure, the second sorting result is, for example, a result of re-sorting the first attribute values of the corresponding live broadcast resources after the weights of the first attribute values are adjusted according to the weight values of each live broadcast resource.

Through the above embodiment of the disclosure, as the first sorting result of the target live broadcast resource is readjusted by combining the second attribute information, the interest points hidden by the user can be mined, richer live broadcast resources can be recalled, and the live broadcast resources to be recommended are determined according to the adjusted second sorting result, so that the technical problem of poor single sorting recommendation effect is at least partially solved, and the user experience is improved.

The method shown in fig. 2 is further described with reference to fig. 3-4 in conjunction with specific embodiments.

Fig. 3 schematically shows a flow chart of a live resource recommendation method according to another embodiment of the present disclosure.

As shown in fig. 3, the method includes operations S310 to S360.

In operation S310, a first ordering result for a plurality of first direct broadcast resources is obtained. The first sorting result is obtained by sorting the plurality of first direct-broadcast resources according to the first attribute information.

In operation S320, feature information of each first direct broadcast resource is determined. The characteristic information comprises the live resource category of the first live resource and the live resource generation duration.

In operation S330, according to the live broadcast resource categories, a second attribute value of second attribute information of a second live broadcast resource is obtained for the feature information of each live broadcast resource category. And the second live broadcast resource is a live broadcast resource matched with the characteristic information.

In operation S340, in case that a preset condition is satisfied, a weight value of each first direct broadcast resource is determined according to a first attribute value and a second attribute value corresponding to the same feature information. The first attribute value is an attribute value of second attribute information of the first direct-broadcasting resource.

In operation S350, a second ranking result for the plurality of first direct broadcast resources is determined according to the weight value and the first ranking result.

In operation S360, a live resource to be recommended is determined according to the second sorting result.

According to the embodiment of the disclosure, the category of the live resources includes, for example, education, news, entertainment, games, goods, and the like, and the generation time of the live resources may be, for example, 30 minutes, 1 hour, 2 hours, and the like. Because the live broadcast resources of different categories have different heat degrees, and the heat degrees of the different live broadcast resources along with the change of the play duration may also be different, in order to eliminate the deviation caused by the category of the live broadcast resources and the play duration, for example, a dimension may be constructed according to the category of the live broadcast resources and the play duration, and the second live broadcast resource may be obtained based on the dimension.

According to the embodiment of the disclosure, a bucket can be constructed according to the feature information, and the second live broadcast resource and the second attribute value thereof acquired based on the feature information can be stored in the bucket. Taking the first live broadcast resource as the education live broadcast resource as an example, by analyzing the starting time of the education live broadcast resource, for example, determining that the characteristic information of the first live broadcast resource is the education live broadcast resource starting for 1 hour, a bucket for storing the education live broadcast resource starting for 1 hour and the second attribute value thereof can be constructed accordingly. In this case, the obtained second live broadcast resource is, for example, all educational live broadcast resources which are broadcast for 1 hour in history and are being broadcast. Taking the second attribute information as the number of real-time users in the live broadcast room as an example, the second attribute value can represent the number of current real-time users of the education live broadcast resources which are broadcast for 1 hour each time. The data stored in the bucket constructed with the educational type live resources that are played for 1 hour may include the current number of real-time users of the educational type live resources that are played for 1 hour each. The data in the bucket may be updated at the day level.

It should be noted that, a deviation threshold may be set for the live resource generation duration. For example, if the deviation threshold is set to 10 minutes, then 1 hour of playout could characterize the time period of 50 minutes of playout to 70 minutes of playout. By setting the deviation threshold, the fluctuation of the attribute value of the second attribute information, which may include the first attribute value and the second attribute value, can be further reduced. The deviation threshold value can be adaptively adjusted according to the actual scene.

According to the embodiment of the disclosure, the weight value of the first direct broadcast resource can be obtained by processing and calculating the first attribute value and the second attribute value through a predefined function.

Through the above embodiment of the present disclosure, a dimension can be established according to the live broadcast resource category and the live broadcast resource generation duration, and through analyzing the second attribute information of different live broadcast resources based on the dimension, the determined weight value of each live broadcast resource can eliminate the deviation caused by different factors such as the live broadcast resource category and the generation duration, and improve the validity of the live broadcast resource recommendation result.

According to an embodiment of the present disclosure, the characteristic information further includes time period information.

According to the embodiment of the disclosure, due to the fact that the popularity of different types of live broadcast resources in different time periods may be different, for example, the popularity of game type live broadcast resources is higher in the evening, and the popularity of news type live broadcast resources is higher in the morning. In order to eliminate the deviation caused by different time periods, for example, the time period information may be used as a reference dimension constituting the characteristic information. The time period information may be expressed as, for example, beijing time 7 to 9, 22.

According to the embodiment of the disclosure, corresponding to an actual first live broadcast resource, the characteristic information of the first live broadcast resource is, for example, a news-like live broadcast resource which is broadcast for 30 minutes in a time period of 7. A bucket may be constructed from the news-class live broadcast resources broadcast for 30 minutes in the time period from 7. The second attribute value may include attribute values of various types of second attribute information that are listed or not listed in the foregoing embodiment, which is not described herein again.

Through the embodiment of the disclosure, a dimension can be established according to the time period information, the category of the live broadcast resources and the generation duration of the live broadcast resources, the second attribute information of different live broadcast resources is analyzed based on the dimension, the weight value of each determined live broadcast resource can eliminate the deviation caused by different factors such as the time period, the category of the live broadcast resources and the generation duration, and the validity of the recommendation result of the live broadcast resources is further improved.

According to an embodiment of the present disclosure, the determining the weight value of each first direct broadcast resource according to the first attribute value and the second attribute value corresponding to the same feature information includes: and determining target characteristic information corresponding to the target first direct broadcasting resource. And acquiring a target second attribute value of the target second live broadcast resource matched with the target characteristic information. And determining a target attribute value corresponding to the target characteristic information according to the target second attribute value. And determining a weight value of the target first direct broadcast resource according to the target attribute value and the first attribute value.

According to the embodiment of the disclosure, the target feature information may include feature information constructed by a live resource category and a live resource generation duration, and may also include feature information constructed by time slot information, a live resource category and a live resource generation duration. The target attribute value may be determined by normalizing the target second attribute value for the respective second live resource. For example, the second attribute values of all live resources matched with the target feature information are stored in the bucket constructed by the target feature information, and the target attribute values can be determined by performing normalization calculation on the second attribute values of all live resources in the bucket. Based on the result of the normalization calculation, for example, a key-value pair having the target feature information as a key and the target attribute value as a value can be obtained, and the value of the second attribute information adapted to the target feature information can be characterized. For example, a specific value of the number of real-time users of a live resource of a predetermined category that is played for a predetermined period of time within a predetermined time period may be determined based on a key-value pair. The key-value pair may be stored in a dictionary or database for later recall for use.

Through the embodiment of the disclosure, a manner of determining the weight value of a single live broadcast resource is provided, and the weight value of the live broadcast resource is determined through the dimension defined based on the target characteristic information, so that each weight value can effectively represent the heat of one live broadcast resource in the defined dimension, and reliable data support is provided for subsequent efficient recommendation of the live broadcast resource.

According to an embodiment of the present disclosure, the determining the target attribute value corresponding to the target feature information according to the target second attribute value includes: an average of the plurality of target second attribute values is calculated. The average value is taken as the target attribute value.

According to the embodiment of the present disclosure, the above normalization calculation process may be performed by averaging, for example, and the target attribute value may be determined according to the average value.

By the embodiment of the disclosure, an average value calculation mode is introduced, so that effective and reasonable target attribute values corresponding to target characteristic information can be determined, and reliable data support is provided for determination of subsequent weight values.

According to an embodiment of the present disclosure, the determining the target attribute value corresponding to the target feature information according to the target second attribute value includes: a median of the plurality of target second attribute values is determined. The median is taken as the target attribute value.

According to the embodiment of the present disclosure, the normalization calculation process may be completed by determining a median, and the target attribute value may be determined according to the median.

By the embodiment of the disclosure, a median determination mode is introduced, so that effective and reasonable target attribute values corresponding to target characteristic information can be determined, and reliable data support is provided for determination of subsequent weight values.

According to an embodiment of the present disclosure, the determining a weight value of the target first direct broadcast resource according to the target attribute value and the first attribute value includes: a weight calculation function is obtained. Wherein the weight calculation function includes: a parameter associated with the first attribute value, and a parameter associated with the target attribute value. And calculating the weight value by using a weight calculation function.

According to an embodiment of the present disclosure, the weight calculation function is, for example: factor =1+ β (real _ user _ num/poseroir _ user _ num). Wherein, the factor is a weighted value, β is an adjustment parameter, the real _ user _ num can represent a parameter related to the first attribute value, such as the current real-time number of people in the live broadcast room, and the postero _ user _ num can represent a parameter related to the target attribute value, such as the posterior live broadcast room number of people in the live broadcast resource matched with the feature information of the live broadcast room. The posterior live room population may be, for example, an average or median of the live room population, and may be determined, for example, by a median of the real-time population of live resources stored in buckets created by the feature information of the live room.

Through the embodiment of the disclosure, the weight calculation function is introduced, a standardized calculation mode is provided for determining the weight value, and the weight value calculation process is simplified.

According to the embodiment of the disclosure, the preset condition includes that the live broadcast resource generation duration of the first live broadcast resource is greater than or equal to a preset duration, or the number of the second live broadcast resources matched with the feature information is greater than or equal to a preset number.

According to the embodiments of the present disclosure, it is necessary to determine the weight value of each first live broadcast resource according to the first attribute value and the second attribute value corresponding to the same feature information, for example, based on a certain prerequisite. In the case where this prerequisite is not satisfied, for example, the calculation process of the weight value cannot be performed, or even if the calculation process can be performed, there is a significant inaccuracy in the calculation result. The preset condition can be used, for example, to characterize the prerequisite.

According to the embodiment of the disclosure, taking the live broadcast resource as an example, for example, when the start time of the live broadcast resource is less than 15min, or the number of live broadcast resources of the live broadcast resource in the bucket constructed by the feature information of the live broadcast resource is too small (for example, less than 6), the weighting operation is not executed, that is, the weight value does not need to be calculated in this case. One embodiment of the preset condition may be that the start time of the live broadcast resource is greater than or equal to 15min, the number of live broadcast resources of the live broadcast resource in the bucket constructed by the feature information of the live broadcast resource is greater than or equal to 6, and the numerical value may be adaptively adjusted, which is not specifically limited herein.

Through the above embodiments of the present disclosure, a prerequisite condition is defined for the calculation of the weight value, so that the reliability of the calculation result of the weight value is further enhanced.

According to an embodiment of the present disclosure, the determining the second ranking result for the plurality of first direct broadcast resources according to the weight value and the first ranking result includes: acquiring an evaluation value of each first direct broadcast resource in the first sequencing result; and calculating a product value of a target weight value and a target evaluation value, wherein the target weight value and the target evaluation value correspond to the same first direct broadcast resource. A second ordering result is determined based on the product value.

According to an embodiment of the present disclosure, the weighting formula for implementing the transformation of the first sorted result to the second sorted result may be, for example: q _ ratio = factor. Where q _ ratio may be used to represent an evaluation value of the first on-air resource in the first ranking result, e.g., a target evaluation value representing a target first on-air resource, and the factor may be used to represent a weight value of the corresponding first on-air resource, e.g., a target weight value representing the target first on-air resource. For example, a weighting result obtained by weighting the evaluation value of each first broadcast resource can be obtained by calculating q _ ratio factor. The second sorting result may be determined according to the size of the weighting result.

Through the embodiments of the present disclosure, a standardized conversion manner is provided, the conversion from the first sorting result to the second sorting result is realized, and the conversion process is simplified.

According to an embodiment of the present disclosure, the live resource recommendation method further includes: and acquiring target attribute information influencing the real-time heat of the first direct-broadcast resource. And acquiring the attribute value of the target attribute information as the first attribute value of the second attribute information.

Through the embodiment of the disclosure, all attribute information capable of influencing the real-time popularity of the live broadcast resources can be used as the second attribute information, and the initial sequencing result of the live broadcast resources is adjusted by combining the attribute values of the second attribute information, so that the accuracy of recommending the live broadcast resources can be improved.

According to an embodiment of the present disclosure, the live resource recommendation method further includes, for example: and responding to the user request, and acquiring a plurality of target live broadcast resources matched with the target live broadcast resource categories included in the user request. And determining a plurality of first live broadcast resources according to the target live broadcast resources.

According to an embodiment of the present disclosure, the user request is, for example, for requesting a live resource that the user wants to acquire. After the user request is sent out, the category of the live broadcast resources which the user wants to request can be determined according to the request content of the user request, and the time period which the user request can correspond to in one day can be determined according to the sending time of the request. All live resources that are in accordance with the live resource class may be retrieved first in response to a user request, for example, and the first live resource may be determined from the plurality of live resources, for example. The determination method includes, for example, determining according to the request time of the user request, or determining according to the popularity of all requested live resources, and the like.

According to an embodiment of the present disclosure, the first live broadcast resource may also be, for example, a part of live broadcast resources with a higher popularity that are automatically screened out by the system, and is not limited herein.

Through the embodiment of the disclosure, a live broadcast resource request mode is provided, and a data basis is provided for further determining the live broadcast resource to be recommended subsequently.

Fig. 4 schematically shows an implementation flowchart of a live resource recommendation method according to an embodiment of the present disclosure.

As shown in fig. 4, for example, 5000 live broadcast resources exist in the live broadcast resource candidate set, and when a live broadcast resource recommendation is required, the recommendation flow includes operations S410 to S440, for example.

In operation S410, recall. The recall phase may recall from 5000 live resources a live resource associated with a user action in response to the user action. The user operation behavior includes, for example, a click operation of the user on a certain type of live resources, a request instruction of the user for a certain type of live resources, and the like. Taking the example that the user requests the game type live resources, the result of the recall is, for example, 500 game type live resources.

In operation S420, sorting is performed. The sorting stage may, for example, combine with a sorting model to screen and sort recalled live resources. For example, after 500 game-type live broadcast resources are input into the sorting model, 200 live broadcast resources can be obtained by screening according to attribute information of interest of a user, anchor level and the like, each live broadcast resource is scored, and sorting is performed according to the scoring result to obtain a result such as G1: q _ ratio1, G2: q _ ratio2, G3: q _ ratio3, G4: q _ ratio4, G5: q _ ratio5, G6: q _ ratio6, G7: q _ ratio7 …, G200: q _ ratio 200.

In operation S430, the weights are adjusted. And the right adjusting stage can adjust the right of the first sequencing result according to attribute information which cannot be considered in the sequencing model, such as the real-time consumption behavior of a user, the number of comments in the live broadcast room, the number of real-time users in the live broadcast room and the like. The weighting process may use the weighting formula q _ ratio = factor described above. For example, q _ ratio4 _adjust The result is obtained after weighting the evaluation value q _ ratio4 of G4 in the first ranking result. In the right-adjusting stage, for example, 200 live resources are reordered according to the right-adjusting result, and a result is shown as G4: q _ ratio4 _adjust 、…、G1：q_ratio1 _adjust 、G6：q_ratio6 _adjust 、G2：q_ratio2 _adjust 、G3：q_ratio3 _adjust 、…、G5：q_ratio5 _adjust 、G7：q_ratio7 _adjust 、…、G200：q_ratio200 _adjust ….

In operation S440, topN is taken. At this stage, the TopN (for example, top 5) pieces of the 200 live resources sorted by the second sorting result may be selected as the live resources to be recommended. At this stage, for example, topN (such as Top 50) pieces of the 200 live broadcast resources sorted according to the second sorting result may be selected for the second sorting and tuning, and then TopN (such as Top 5) pieces of the second sorting result after the second sorting and tuning are taken as the live broadcast resources to be recommended. It should be noted that the process of sorting and adjusting the right may be repeated multiple times to determine more accurate to recommend the live resources.

Through the embodiment of the disclosure, as the right-adjusting operation is further executed on the sequencing result, the interest points hidden by the user can be excavated, richer live broadcast resources can be recalled, and the user experience is improved.

Fig. 5 schematically shows a block diagram of a live resource recommendation apparatus according to an embodiment of the present disclosure.

As shown in fig. 5, the live resource recommendation apparatus 500 includes a first obtaining module 510, a first determining module 520, a second determining module 530, and a third determining module 540.

A first obtaining module 510, configured to obtain a first ordering result for a plurality of first direct broadcast resources. The first ordering result is obtained by ordering the plurality of first direct-broadcasting resources according to the first attribute information.

The first determining module 520 is configured to determine a weight value of each first direct broadcast resource according to the first attribute value of the second attribute information of each first direct broadcast resource.

A second determining module 530, configured to determine a second sorting result for the plurality of first direct broadcast resources according to the weight value and the first sorting result.

And a third determining module 540, configured to determine, according to the second sorting result, a live broadcast resource to be recommended.

According to the embodiment of the disclosure, the live broadcast resource recommendation device further comprises a fourth determining module, a second obtaining module and a fifth determining module.

And the fourth determining module is used for determining the characteristic information of each first direct broadcasting resource. The characteristic information comprises a live broadcast resource category of the first live broadcast resource and a live broadcast resource generation duration.

And the second acquisition module is used for acquiring a second attribute value of second attribute information of a second live broadcast resource aiming at the characteristic information of each live broadcast resource category according to the live broadcast resource category. And the second live broadcast resource is a live broadcast resource matched with the characteristic information.

And the fifth determining module is used for determining the weight value of each first direct broadcast resource according to the first attribute value and the second attribute value corresponding to the same characteristic information under the condition that the preset condition is met.

According to an embodiment of the present disclosure, the fifth determining module includes a first determining unit, a first obtaining unit, a second determining unit, and a third determining unit.

And the first determining unit is used for determining the target characteristic information corresponding to the target first direct broadcast resource.

And the first acquisition unit is used for acquiring a target second attribute value of the target second live broadcast resource matched with the target characteristic information.

And the second determining unit is used for determining a target attribute value corresponding to the target characteristic information according to the target second attribute value.

And the third determining unit is used for determining the weight value of the target first direct broadcast resource according to the target attribute value and the first attribute value.

According to an embodiment of the present disclosure, the target second attribute value has a plurality, and the second determination unit includes a first calculation subunit and a first definition subunit.

And the first calculating subunit is used for calculating the average value of the plurality of target second attribute values.

And the first definition subunit is used for taking the average value as the target attribute value.

According to an embodiment of the present disclosure, the target second attribute value has a plurality, and the second determination unit includes a determination subunit and a second definition subunit.

A determining subunit, configured to determine median of the plurality of target second attribute values.

And the second definition subunit is used for taking the median as a target attribute value.

According to an embodiment of the present disclosure, the third determination unit includes an acquisition subunit and a second calculation subunit.

And the obtaining subunit is used for obtaining the weight calculation function. Wherein the weight calculation function includes: a parameter associated with the first attribute value, and a parameter associated with the target attribute value.

And the second calculating subunit is used for calculating the weight value by using the weight calculating function.

According to the embodiment of the disclosure, the preset condition includes that the live broadcast resource generation duration of the first live broadcast resource is greater than or equal to the preset duration, or the number of the second live broadcast resources matched with the feature information is greater than or equal to the preset number.

According to an embodiment of the present disclosure, the second determination module includes a second acquisition unit, a calculation unit, and a fourth determination unit.

A second obtaining unit, configured to obtain an evaluation value of each first direct broadcast resource in the first sequencing result.

A calculation unit for calculating a product value of the target weight value and the target evaluation value. Wherein the target weight value and the target evaluation value correspond to the same first direct broadcast resource.

A fourth determination unit for determining a second ordering result based on the product value.

According to the embodiment of the disclosure, the live broadcast resource recommendation device further comprises a third acquisition module and a definition module.

And the third acquisition module is used for acquiring the target attribute information influencing the real-time heat of the first direct broadcast resource.

And the definition module is used for acquiring the attribute value of the target attribute information as the first attribute value of the second attribute information.

According to the embodiment of the disclosure, the live broadcast resource recommendation device further comprises a fourth obtaining module and a sixth determining module.

And the fourth acquisition module is used for responding to the user request and acquiring a plurality of target live broadcast resources matched with the target live broadcast resource types included in the user request.

And the sixth determining module is used for determining a plurality of first direct broadcast resources according to the plurality of target direct broadcast resources.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the live resource recommendation method as described above.

According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium having stored thereon computer instructions for causing a computer to execute a live resource recommendation method as described above.

According to an embodiment of the present disclosure, a computer program product comprising a computer program which, when executed by a processor, implements a live resource recommendation method as described above.

FIG. 6 illustrates a schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 6, the apparatus 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The calculation unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

A number of components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, a mouse, and the like; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The computing unit 601 performs the various methods and processes described above, such as the live resource recommendation method. For example, in some embodiments, the live resource recommendation method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of a computer program may be loaded onto and/or installed onto device 600 via ROM 602 and/or communications unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the live resource recommendation method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the live resource recommendation method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, 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), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A live broadcast resource recommendation method comprises the following steps:

obtaining a first sequencing result aiming at a plurality of first direct-playing resources, wherein the first sequencing result is obtained by sequencing the plurality of first direct-playing resources according to first attribute information;

determining a weight value of each first direct broadcast resource according to a first attribute value of second attribute information of each first direct broadcast resource;

determining a second ranking result for the plurality of first direct broadcast resources according to the weight values and the first ranking result; and

determining the live broadcast resources to be recommended according to the second sequencing result;

wherein the determining, according to the first attribute value of the second attribute information of each of the first live broadcast resources, the weight value of each of the first live broadcast resources includes:

determining characteristic information of each first direct broadcast resource;

constructing a bucket according to the characteristic information, wherein the bucket comprises a second live broadcast resource obtained according to the characteristic information and a second attribute value of second attribute information of the second live broadcast resource;

and determining a weight value of the first direct broadcast resource corresponding to the characteristic information according to the first attribute value corresponding to the characteristic information and the second attribute value in the bucket corresponding to the characteristic information.

2. The method of claim 1, wherein the characteristic information includes a live resource category and a live resource generation duration of the first live resource, the method further comprising:

according to the live broadcast resource categories, aiming at the characteristic information of each live broadcast resource category, acquiring a second attribute value of second attribute information of the second live broadcast resource; and

and under the condition that a preset condition is met, determining the weight value of each first direct broadcast resource according to the first attribute value and the second attribute value corresponding to the same characteristic information.

3. The method of claim 2, wherein determining a weight value for each of the first live resources as a function of a first attribute value and a second attribute value corresponding to the same feature information comprises:

determining target characteristic information corresponding to a target first direct-broadcast resource;

acquiring a target second attribute value of a target second live broadcast resource matched with the target characteristic information;

determining a target attribute value corresponding to the target characteristic information according to the target second attribute value; and

and determining a weight value of the target first direct broadcast resource according to the target attribute value and the first attribute value.

4. The method of claim 3, wherein the target second attribute value has a plurality, and determining the target attribute value corresponding to the target feature information from the target second attribute value comprises:

calculating an average value of a plurality of the target second attribute values; and

and taking the average value as the target attribute value.

5. The method of claim 3, wherein the target second attribute value has a plurality, and determining the target attribute value corresponding to the target feature information from the target second attribute value comprises:

determining a median of a plurality of the target second attribute values; and

and taking the median as the target attribute value.

6. The method of any of claims 3 to 5, wherein determining a weight value for the target first live resource as a function of the target attribute value and the first attribute value comprises:

obtaining a weight calculation function, wherein the weight calculation function comprises: a parameter associated with the first attribute value, and a parameter associated with the target attribute value; and

calculating the weight value using the weight calculation function.

7. The method of claim 2, wherein the preset condition includes that a live resource generation duration of the first live resource is greater than or equal to a preset duration, or that the number of second live resources matching the feature information is greater than or equal to a preset number.

8. The method of claim 1 or 2, wherein determining a second ranking result for the plurality of first direct cast resources as a function of the weight values and the first ranking results comprises:

obtaining an evaluation value of each first direct broadcast resource in the first sequencing result;

calculating a product value of a target weight value and a target evaluation value, wherein the target weight value and the target evaluation value correspond to the same first direct broadcast resource; and

and determining the second sequencing result according to the product value.

9. The method of claim 1 or 2, further comprising:

acquiring target attribute information influencing the real-time heat of the first direct-broadcast resource; and

and acquiring the attribute value of the target attribute information as the first attribute value of the second attribute information.

10. The method of claim 1 or 2, further comprising:

responding to a user request, and acquiring a plurality of target live broadcast resources matched with the target live broadcast resource types included in the user request; and

and determining the plurality of first live broadcast resources according to the plurality of target live broadcast resources.

11. The method of claim 2, wherein the characteristic information further comprises time period information.

12. The method of claim 1, wherein the first attribute information includes at least one of user attribute information, live resource category information, and anchor attribute information, and the second attribute information includes at least one of a number of live users, a number of live comments, and a user viewing duration of the live room.

13. A live resource recommendation apparatus, comprising:

a first obtaining module, configured to obtain a first ordering result for a plurality of first direct-broadcast resources, where the first ordering result is obtained by ordering the plurality of first direct-broadcast resources according to first attribute information;

the first determining module is used for determining a weight value of each first direct broadcast resource according to a first attribute value of the second attribute information of each first direct broadcast resource;

a second determining module, configured to determine a second ranking result for the plurality of first direct broadcast resources according to the weight value and the first ranking result; and

a third determining module, configured to determine, according to the second sorting result, a live broadcast resource to be recommended;

wherein the first determining module is further configured to:

determining characteristic information of each first direct broadcast resource;

14. The apparatus of claim 13, wherein the characteristic information comprises a live resource category and a live resource generation duration of the first live resource, the apparatus further comprising:

a second obtaining module, configured to obtain, according to the live broadcast resource categories, second attribute values of second attribute information of the second live broadcast resource for the feature information of each live broadcast resource category; and

and the fifth determining module is used for determining the weight value of each first direct broadcast resource according to the first attribute value and the second attribute value corresponding to the same feature information under the condition that a preset condition is met.

15. The apparatus of claim 14, wherein the fifth determining means comprises:

the first determining unit is used for determining target characteristic information corresponding to the target first direct broadcast resource;

the first acquisition unit is used for acquiring a target second attribute value of a target second live broadcast resource matched with the target characteristic information;

a second determining unit, configured to determine a target attribute value corresponding to the target feature information according to the target second attribute value; and

a third determining unit, configured to determine a weight value of the target first direct broadcast resource according to the target attribute value and the first attribute value.

16. The apparatus according to claim 15, wherein the target second attribute value has a plurality, the second determining unit includes:

a first calculating subunit configured to calculate an average value of a plurality of the target second attribute values; and

17. The apparatus according to claim 15, wherein the target second attribute value has a plurality, the second determining unit includes:

a determining subunit, configured to determine a median of the plurality of target second attribute values; and

and the second definition subunit is used for taking the median as the target attribute value.

18. The apparatus of any of claims 15 to 17, wherein the third determining unit comprises:

an obtaining subunit, configured to obtain a weight calculation function, where the weight calculation function includes: a parameter associated with the first attribute value, and a parameter associated with the target attribute value; and

a second calculating subunit, configured to calculate the weight value by using the weight calculating function.

19. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-12.

20. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-12.