CN114079825B

CN114079825B - Live broadcasting room user team forming method, equipment and medium

Info

Publication number: CN114079825B
Application number: CN202111328848.3A
Authority: CN
Inventors: 陈洋溢; 何楚
Original assignee: Guangzhou Cubesili Information Technology Co Ltd
Current assignee: Guangzhou Cubesili Information Technology Co Ltd
Priority date: 2021-11-10
Filing date: 2021-11-10
Publication date: 2024-02-09
Anticipated expiration: 2041-11-10
Also published as: CN114079825A

Abstract

The application relates to the field of network live broadcast and discloses a live broadcast room user team forming method and device, equipment, media and products thereof, wherein the method comprises the following steps: acquiring characteristic information of a live broadcasting room of a current user and playing data information related to a first direct broadcasting playing method service; a score prediction model is adopted, and the characteristic information of the live broadcasting room and the play data information are taken as inputs to predict the prediction score data of the current user; integrating the quantized data of the relationship between the current user and each other user of the second live broadcast playing method service and the corresponding prediction score data of the current user and each other user, and calculating the matching value of each other user corresponding to the current user; and configuring the user with relatively high matching value and the current user as a joint team in the second live playing service. According to the method and the device, the score of the new play service is predicted according to the play data of other play services, the fitting degree of the prediction result of the predicted new play service is guaranteed, and the team matching service of the new play service is optimized.

Description

Live broadcasting room user team forming method, equipment and medium

Technical Field

The present invention relates to the field of network live broadcast, and in particular, to a method for user team formation in a live broadcast room, and further, to a corresponding apparatus, device, non-volatile storage medium, and computer program product for the method.

Background

In the existing live broadcast platform, a live broadcast playing service, such as a continuous play service or a live broadcast playing service with other competitive properties, of a platform user in a live broadcast room is generally provided, so that audience users or anchor users in the live broadcast room participate in the live broadcast playing service, interaction among users in the live broadcast room is promoted, and a live broadcast atmosphere in the live broadcast room is promoted.

In the live broadcast playing service with the competitive property, team matching service is provided, and team matching is performed for users participating in the live broadcast playing service to form a team for performing the fight in the playing service, the existing team matching service usually performs the matching of the team friends by referring to the play data generated by the users in the live broadcast playing service currently participating in the playing service, but for the new live broadcast playing service, the online time is not long, the play data generated by the participating users in the new live broadcast playing service does not have the reference value, so that the matching effect of the team matching service provided in the new live broadcast playing service is poor, the team matching service cannot be matched to the team with high fitness for the participating users, and the playing experience of the users participating in the new playing service is poor.

In view of the above problems, the present applicant has made a corresponding search for consideration in solving the problems.

Disclosure of Invention

It is an object of the present application to meet the needs of, or overcome at least some of the deficiencies of, the prior art to provide a live room user queuing method and corresponding apparatus, electronic device, non-volatile storage medium and computer program product.

In order to achieve the purposes of the application, the following technical scheme is adopted:

the method for grouping the users in the live broadcasting room, which is provided for the purpose of the application, comprises the following steps:

acquiring characteristic information of a live broadcasting room of a current user and playing data information related to a first direct broadcasting playing method service;

a score prediction model which is pre-trained to a convergence state is adopted, and the characteristic information of the live broadcasting room and the playing data information of the first live broadcasting playing method service are taken as inputs to predict the prediction score data of the current user relative to the second live broadcasting playing method service;

integrating the quantized data of the relationship between the current user and each other user participating in the second live broadcast playing service and the respective corresponding prediction score data of the current user and all other users, and calculating the matching value of each other user corresponding to the current user;

and configuring other users with relatively high matching values and the current user as a joint team in the second live playing service.

In a further embodiment, a score prediction model pre-trained to a convergence state is adopted, and the step of predicting the predicted score data of the current user relative to the second live broadcast playing service by taking the live broadcast room feature information and the playing data information of the first live broadcast playing service as inputs includes the following steps executed by the score prediction model:

extracting feature vectors of the feature information of the live broadcasting room and the play data information of the first direct play service by adopting a first prediction model in the score prediction models, and predicting preliminary prediction score data of the current user in the first direct play service according to the feature vectors;

acquiring play data information generated by a current user in a second live play method service;

and predicting final prediction score data of the current user corresponding to the second live broadcast playing service according to the preliminary prediction score information and the playing data information of the second live broadcast playing service by adopting a second prediction model in the score prediction model.

and mapping the preliminary prediction score data into final prediction score data of the current user corresponding to the second live broadcast playing service by adopting a third prediction model in the score prediction models, wherein the third prediction model is trained in advance to obtain mapping relation information between the preliminary prediction score data and the final prediction score data.

In a further embodiment, the step of calculating the matching value of the current user corresponding to each other user respectively by integrating the quantized data of the relationship between the current user and each other user participating in the second live broadcast playing service and the respective prediction score data of the current user and all the other users includes the following steps:

sorting the users in descending order according to the prediction score data corresponding to each user in the second live broadcast playing service;

calculating a matching value between the user at the position of the front ranking and other users after each position of the middle ranking;

And determining one or more other users with relatively higher matching values with the users at the front positions, removing the other users and the users at the front positions from the ranking, and completing the calculation of the matching values between the corresponding users in the ranking according to the last step and the step.

acquiring the quantized data of the human relation between the current user and any other user participating in the second live playing service, wherein the quantized data of the human relation is determined according to the association relation between the current user and the other user participating in the first live playing service;

calculating a difference between the predicted score data of the current user and the other users;

and obtaining a calculation result of subtracting the difference value from the numerical value represented by the vein relation quantitative data, and taking the calculation result as a matching value between the current user and the other users.

In a further embodiment, the step of configuring the other users with relatively higher matching values and the current user as a joint team in the second live playing service includes the following steps:

according to the matching value between the current user and each other user participating in the second live playing service, ordering the other users in a descending order;

one or more other users and the current user who are ranked first are configured as a joint team in the second live play service.

In a preferred embodiment, after the step of configuring the other users with relatively higher matching values and the current user as a joint team in the second live playing service, the method includes the following steps:

sorting the combined warfare in descending order according to the warfare prediction score data corresponding to each of all the combined warfare in the second live playing service, wherein the warfare prediction score data is the sum of the prediction score data corresponding to each of all the users in the combined warfare;

configuring the combined warfare in the front position and the combined warfare in the middle position to a first fight track or a second fight track, wherein the first fight track and the second fight track respectively have the same number of combined warfare;

Starting a promotion war office among the combined warfare in each fight race track, wherein the promotion war office is provided with two combined warfare with relatively close warfare prediction score data;

and determining the combined warfare with higher match score data in each warfare in each match-up race track, starting a promotion warfare among the combined warfare, and the like until starting the champion warfare among the combined warfare of the final promotion of each first match-up race track and the second match-up race track.

A live room user team device, proposed for the purposes of the present application, comprising:

the play data acquisition module is used for acquiring the characteristic information of the live broadcasting room of the current user and the play data information of the live broadcasting room and the first direct broadcasting play method service;

the score data prediction module is used for predicting the predicted score data of the current user relative to the second live broadcast playing method service by taking the characteristic information of the live broadcast room and the playing data information of the first live broadcast playing method service as inputs by adopting a score prediction model pre-trained to a convergence state;

the matching value calculation module is used for integrating the quantized data of the human relation between the current user and each other user participating in the second live broadcast playing service and the corresponding prediction score data of the current user and each other user, and calculating the matching value of each other user corresponding to the current user;

And the joint combat team configuration module is used for configuring other users with relatively high matching values and the current user into a joint combat team in the second live playing service.

In a further embodiment, the score data prediction module includes:

the score data preliminary prediction sub-module is used for extracting feature vectors of live broadcasting room feature information and play data information of the first direct play service by adopting a first prediction model in the score prediction models, and predicting preliminary prediction score data of the current user in the first direct play service according to the feature vectors;

the play data information acquisition sub-module is used for acquiring play data information generated by the current user in the second live broadcast play service;

and the score data final prediction sub-module is used for predicting final prediction score data of the current user corresponding to the second live broadcast playing service according to the preliminary prediction score information and the playing data information of the second live broadcast playing service by adopting a second prediction model in the score prediction model.

In a preferred embodiment, the score data prediction module further includes:

And the score data mapping prediction sub-module is used for mapping the preliminary prediction score data into final prediction score data corresponding to the second live broadcast playing service of the current user by adopting a third prediction model in the score prediction models, and the third prediction model is trained in advance to acquire mapping relation information between the preliminary prediction score data and the final prediction score data.

In a further embodiment, the matching value calculation module includes:

the user descending order sorting sub-module is used for descending order sorting of the users according to the prediction score data corresponding to each user in the second live broadcast playing service;

the matching value calculation sub-module is used for calculating matching values between the users at the front-ranking positions and other users after each middle-ranking position;

and the user sorting and removing sub-module is used for determining one or more other users with relatively higher matching values with the users at the front positions, removing the other users and the users at the front positions from the sorting, and completing the calculation of the matching values between the corresponding users in the sorting according to the last step and the step.

In a preferred embodiment, the matching value calculation module further includes:

The system comprises a vein data acquisition sub-module, a first direct broadcast playing service module and a second direct broadcast playing service module, wherein the vein data acquisition sub-module is used for acquiring vein relation quantification data between a current user and any other user participating in the second direct broadcast playing service, and the vein relation quantification data is determined according to the association relation between the current user and the other user participating in the first direct broadcast playing service;

the score data difference value calculation sub-module is used for calculating the difference value between the prediction score data of the current user and the prediction score data of the other users;

and the matching value acquisition sub-module is used for acquiring a calculation result of subtracting the difference value from the numerical value represented by the vein relation quantitative data, and taking the calculation result as a matching value between the current user and the other users.

In a further embodiment, the joint team configuration module includes:

the user descending order sorting sub-module is used for descending order sorting of the other users according to the matching value between the current user and the other users participating in the second live broadcast playing service;

and the combined warfare configuration sub-module is used for configuring one or more other users and the current user which are ranked ahead as the combined warfare in the second live playing service.

An electronic device, as proposed for the purpose of the present application, comprises a central processor and a memory, said central processor being adapted to invoke the steps of running a computer program stored in said memory for performing said live room user queuing method.

A non-volatile storage medium adapted for the purposes of the present application stores a computer program implemented according to the live-room user queuing method, which when invoked by a computer, performs the steps comprised by its corresponding method.

In order to solve the above technical problem, an embodiment of the present application further provides a computer program product, which includes a computer program and computer instructions, where the computer program and the computer instructions, when executed by a processor, cause the processor to execute the steps of the live broadcast data layering prediction method or the live broadcast data layering acquisition method.

Compared with the prior art, the method has the following advantages:

according to the method, the score obtained by the user in the current live broadcast playing method service is predicted according to playing data transmitted by the user in the current live broadcast playing method service, calculation of matching values is performed by comprehensively predicting score data obtained by the users participating in the current live broadcast playing method and people vein relation quantitative data between the users, and further, a combined warfare participating in the current live broadcast playing method service is configured.

In addition, the score data prediction method adopts the play data of the user in other live playing methods to predict, so that the score data prediction method can be applied to playing method services with shorter online time and smaller data quantity, and the predicted prediction result is fitted with the actual result.

Secondly, the quantized data of the human relation are generated according to interaction activities when the two parties of the user participate in live broadcast playing, and compared with the traditional human relation data generated according to interaction of the two parties of the user in friend online service, the quantized data of the human relation have stronger reference value when being applied to scenes of the playing service, so that matching service of the playing service has an accurate matching effect.

Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.

Drawings

The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

FIG. 1 is a schematic diagram of a typical network deployment architecture relevant to implementing the technical solutions of the present application;

FIG. 2 is a flow chart of an exemplary embodiment of a live room user queuing method of the present application;

FIG. 3 is a flow chart illustrating an embodiment of predicted score data for predicting users who have undergone a second live play service in accordance with the present application;

FIG. 4 is a flow chart illustrating an embodiment of predicted score data for a user predicted to have not been subjected to a second live play service;

FIG. 5 is a schematic flow chart of an embodiment of two users selecting to perform matching value calculation;

FIG. 6 is a flow chart illustrating an embodiment of calculating a matching value between two parties of a user;

FIG. 7 is a flow chart illustrating an embodiment of determining other users with relatively high matching values to the current user;

FIG. 8 is a flow chart of an embodiment of a match course, a promotional war office, and a champion war office for a second live play service according to the present application;

FIG. 9 is a schematic diagram of a promotional and champion warfare arrangement of each of the fighting tracks in the second live play service;

FIG. 10 is a functional block diagram of an exemplary embodiment of a live room user team device of the present application;

FIG. 11 is a basic block diagram of a computer device according to one embodiment of the present application.

Detailed Description

Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for the purpose of illustrating the present application and are not to be construed as limiting the present application.

As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.

It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

As used herein, "client," "terminal device," and "terminal device" are understood by those skilled in the art to include both devices that include only wireless signal receivers without transmitting capabilities and devices that include receiving and transmitting hardware capable of two-way communication over a two-way communication link. Such a device may include: a cellular or other communication device such as a personal computer, tablet, or the like, having a single-line display or a multi-line display or a cellular or other communication device without a multi-line display; a PCS (Personal Communications Service, personal communication system) that may combine voice, data processing, facsimile and/or data communication capabilities; a PDA (Personal Digital Assistant ) that can include a radio frequency receiver, pager, internet/intranet access, web browser, notepad, calendar and/or GPS (Global Positioning System ) receiver; a conventional laptop and/or palmtop computer or other appliance that has and/or includes a radio frequency receiver. As used herein, "client," "terminal device" may be portable, transportable, installed in a vehicle (aeronautical, maritime, and/or land-based), or adapted and/or configured to operate locally and/or in a distributed fashion, at any other location(s) on earth and/or in space. As used herein, a "client," "terminal device," or "terminal device" may also be a communication terminal, an internet terminal, or a music/video playing terminal, for example, a PDA, a MID (Mobile Internet Device ), and/or a mobile phone with music/video playing function, or may also be a device such as a smart tv, a set top box, or the like.

The hardware referred to by the names "server", "client", "service node" and the like in the present application is essentially an electronic device having the performance of a personal computer, and is a hardware device having necessary components disclosed by von neumann's principle, such as a central processing unit (including an arithmetic unit and a controller), a memory, an input device, and an output device, and a computer program is stored in the memory, and the central processing unit calls the program stored in the external memory to run in the memory, executes instructions in the program, and interacts with the input/output device, thereby completing a specific function.

It should be noted that the concept of "server" as referred to in this application is equally applicable to the case of a server farm. The servers should be logically partitioned, physically separate from each other but interface-callable, or integrated into a physical computer or group of computers, according to network deployment principles understood by those skilled in the art. Those skilled in the art will appreciate this variation and should not be construed as limiting the implementation of the network deployment approach of the present application.

Referring to fig. 1, the hardware base required for implementing the related technical solution of the present application may be deployed according to the architecture shown in the figure. The server 80 is deployed at the cloud as a service server, and may be responsible for further connecting to related data servers and other servers providing related support, so as to form a logically related service cluster, to provide services for related terminal devices, such as a smart phone 81 and a personal computer 82 shown in the figure, or a third party server (not shown). The smart phone and the personal computer can access the internet through a well-known network access mode, and establish a data communication link with the cloud server 80 so as to run a terminal application program related to the service provided by the server.

For the server, the application program is generally constructed as a service process, and a corresponding program interface is opened for remote call of the application program running on various terminal devices.

The application program refers to an application program running on a server or terminal equipment, the application program adopts a programming mode to realize the related technical scheme of the application, the program codes of the application program can be stored in a nonvolatile storage medium which can be identified by a computer in the form of computer executable instructions, and the program codes are called by a central processing unit to run in a memory, and the related device of the application is constructed by the running of the application program on the computer.

The technical solution suitable for implementation in a terminal device in the present application may also be programmed to be built into an application providing live webcasting as part of which the functionality is extended. The network live broadcast refers to a live broadcast room network service realized based on the network deployment architecture.

The live broadcasting room refers to a video chat room realized by means of an Internet technology, and generally has an audio and video broadcasting control function, wherein the video chat room comprises a host user and a spectator user, and the spectator user can comprise registered users registered in a platform or unregistered guest users; the registered user who pays attention to the anchor user may be a registered user who pays attention to the anchor user or an unregistered user. The interaction between the anchor user and the audience user can be realized through the well-known online interaction modes such as voice, video, text and the like, generally, the anchor user performs programs for the audience user in the form of audio and video streams, and economic transaction behaviors can be generated in the interaction process. Of course, the application form of the live broadcast room is not limited to online entertainment, and can be popularized to other related scenes, such as educational training scenes, video conference scenes, product recommendation sales scenes and any other scenes needing similar interaction.

Those skilled in the art will appreciate that: although the various methods of the present application are described based on the same concepts so as to be common to each other, the methods may be performed independently, unless otherwise indicated. Similarly, for each of the embodiments disclosed herein, the concepts presented are based on the same inventive concept, and thus, the concepts presented for the same description, and concepts that are merely convenient and appropriately altered although they are different, should be equally understood.

The various embodiments to be disclosed herein, unless the plain text indicates a mutually exclusive relationship with each other, the technical features related to the various embodiments may be cross-combined to flexibly construct a new embodiment, so long as such combination does not depart from the inventive spirit of the present application and can satisfy the needs in the art or solve the deficiencies in the prior art. This variant will be known to the person skilled in the art.

Referring to fig. 2, in an exemplary embodiment, a method for user queuing in a live broadcast room of the present application includes the following steps:

step S11, obtaining the characteristic information of the live broadcasting room of the current user and the playing data information related to the first direct broadcasting playing service:

And the server acquires the characteristic information of the live broadcasting room of the current user currently participating in the second live broadcasting playing service and playing data information related to the second live broadcasting playing service.

The current user generally refers to a main broadcasting user of a live broadcasting platform, and the corresponding characteristic information of the live broadcasting room generally comprises ID of the live broadcasting room, vermicelli number data of the live broadcasting room, gift giving information of the live broadcasting room, ID of the main broadcasting user and the like which are used for describing the information of the live broadcasting room, recording interaction information of the live broadcasting room and the like, so that a server predicts prediction score data of the current user in a second live broadcasting playing method through the characteristic information and the play data information of the live broadcasting room; for the specific embodiment of predicting the prediction score data of the current user, please refer to the implementation of the following steps, which are not repeated.

The first direct play playing service and the second direct play playing service have certain commonalities, for example, when the playing service provided by the first direct play service is a one-to-one continuous playing service of a host, the basic playing service provided by the second direct play service is a continuous playing service of a plurality of host players together, and rich basic playing services such as a rule of eliminating promotion are fused on the basis of the playing service, so that the prediction score data of the current user in the second direct play service can be predicted by referring to the playing data information related to the first direct play service due to certain commonalities of the playing service of the first direct play service and the playing service of the second direct play service; for the specific embodiment of predicting the prediction score data of the current user, please refer to the implementation of the following steps, which are not repeated.

The playing data information comprises data information generated by the current user for performing the first direct playing service, such as score data information, record information of the user playing together with the current user, playing time information, score data sequence information generated according to the playing time information and the score data information, and the like, and the information is used for recording the data information generated by the current user for performing the first direct playing service, so that the server can conveniently extract the characteristics of the current user in the first direct playing service through the playing data information of the current user associated with the first direct playing service, and forecast the forecast score data of the current user in the second direct playing service.

Step S12, a score prediction model pre-trained to a convergence state is adopted, and the feature information of the live broadcasting room and the play data information of the first live broadcasting play method service are taken as inputs to predict the prediction score data of the current user relative to the second live broadcasting play method service:

after the server obtains the live broadcasting room characteristic information and the play data information of the first live broadcasting playing service of the current user, the score prediction model which is pre-trained to a convergence state is adopted, so that the live broadcasting room characteristic information and the play data information are input into the score prediction model, and the predicted score data of the current user in the second live broadcasting playing service, which is predicted and output by the score prediction model, is obtained.

The score prediction model is a model pre-trained to a convergence state, and predicts the score data possibly acquired by the current user in the second live playing service as prediction score data according to the live broadcasting room characteristic information and the play data information of the current user, so that the server can match other users in the second live playing service to perform configuration of the united battle for the current user according to the prediction score data.

Specifically, the score prediction model comprises a first prediction model trained to a convergence state, and the first prediction model is used for predicting the prediction score data of the current user in the first direct play service, and the prediction score data of the current user in the first direct play service is predicted according to the feature training by extracting the feature information of the live broadcasting room of the current user and the play data information related to the first direct play service.

The score prediction model predicts the predicted score data of the current user in the first live broadcast playing service through the first prediction model, and obtains the playing data information of the current user associated with the second live broadcast playing service so as to adopt the second prediction model, and predicts the predicted score data of the current user in the second live broadcast playing service according to the predicted score data of the current user in the first live broadcast playing service and the playing data information of the current user associated with the second live broadcast playing service.

If the current user does not play the second live playing service, the current user does not have play data information related to the second live playing service, at this time, the score prediction model maps the score data predicted by the first prediction model into the score data predicted by the current user corresponding to the second live playing service by using a third prediction model, and the third prediction model obtains mapping relation information by training the score data generated by other users participating in the second live playing service and the score data predicted by the users in the first live playing service, and maps the score data predicted by the users not playing the second live playing service related to the first live playing service into the score data predicted by the users in the second live playing service according to the mapping relation information.

Step S13, integrating the quantized data of the relationship between the current user and each other user participating in the second live broadcast playing service, and the respective corresponding prediction score data of the current user and all the other users, and calculating the matching value of each other user corresponding to the current user respectively:

and after obtaining the predicted score data predicted and output by the score prediction model, the server obtains the vein relation quantification data between the current user and some other user participating in the second live broadcast playing service so as to synthesize the predicted score data and the vein relation quantification data of the current user and calculate the matching value between the current user and the other user.

The people pulse relation quantification data are determined according to the association relation between the current user and one other user participating in the second live broadcast playing service and participating in the first live broadcast playing service, for example, when the first live broadcast playing service is one-to-one continuous wheat service, and when the current user and the other user use the continuous wheat service provided by the first live broadcast playing service to connect wheat together, the people pulse relation quantification data between the two parties represent that the two parties have direct association relation in the first live broadcast playing service, and if the current user and the other user do not use the continuous wheat service provided by the first live broadcast playing service to connect wheat together, but have indirect association relation in the first live broadcast playing service between the current user and the other user in the people pulse relation quantification data.

In an embodiment, the vein relation quantization data is generated according to friend interaction data between a current user and some other user participating in the second live broadcast playing service, that is, the interaction data associated between the current user and the other user in the friend online service in the live broadcast platform, for example, the vein relation quantization data includes friend relation data which can characterize that both parties are friend relations in the friend online service in the live broadcast platform, communication data that both parties chat online through the friend online service, gift data that both parties perform virtual gift delivery through the friend online service, and the like, that is, the vein relation quantization data can be understood as data which characterizes intimacy between both parties.

When the server obtains the vein relation quantized data between the current user and the other users, a difference value between the prediction score data of the current user and the prediction score data of the other users are calculated, so that after the vein relation quantized data are obtained, a calculation result of the difference value is subtracted by a numerical value represented by the vein relation quantized data, and the calculation result is used as a matching value between the current user and the other users.

Regarding a method for determining users needing to perform matching value calculation with the current user in other users participating in the second live playing service, a server generally ranks the other users, the ranking ranks the other users in descending order according to prediction score data corresponding to each other user participating in the second live playing service, if the current user participates in a front position in the ranking, the matching value between the current user and the other users in a middle position of the ranking is calculated to prevent the users with higher prediction score data from being configured in the same joint battle, so that the actual force difference between the joint battle in the second live playing service is too large, and the play experience of the users with weaker actual force (i.e. the users with actually lower prediction scores) in the second live playing service is affected; and when one or more other users with higher matching values with the current user are determined in the sorting, removing the current user and the other users from the sorting, so that the calculation of the matching values among the other users is continued according to the logic until the calculation of the matching values among the corresponding users in the sorting, namely, participating in the second live game service, is completed.

Step S14, configuring the other users with relatively high matching values and the current user as a joint team in the second live playing service:

after the server calculates the matching values between the current user and a plurality of other users, configuring the user with the relatively higher matching value among the other users and the current user as the joint team participating in the second live playing service.

The combined warfare is a team configured by grouping a certain number of users participating in the second live playing service, and the matching value among the users in the combined warfare is relatively high so as to improve the playing experience of the users in the combined warfare; the number of users present in the co-warfare team is typically set in the range of 2 to 4.

Specifically, after the server calculates the matching values between the current user and the plurality of other users participating in the second live playing service, the other users are ordered in a descending order according to the matching values between the current user and the other users in the second live playing service, and then one or more other users with the top order and the current user are configured to participate in the joint team of the second live playing service.

It can be understood that the method predicts the score data of the current user in the current live broadcast playing service according to the play data of the current user associated with other live broadcast playing service, further calculates the matching value between the two parties according to the preset score data and the quantized data of the relationship between the current user and other users participating in the current live broadcast playing service, and further configures other users with relatively higher matching value and the current user as a joint warfare participating in the current live broadcast service; according to the method, the score data of the user in the new play service is predicted for the user based on the play data of the user in the new play service, so that the prediction result has stronger applicability, the situation that the prediction result is over-fitted or under-fitted due to the insufficient play data of the new play service line is avoided, the matching accuracy of the team matching service of the new play service is influenced, meanwhile, the team matching service is performed by integrating the vein relation quantification data among the users participating in the new play service, the default degree among the users in the matched team is guaranteed, the vein relation quantification data are generally data generated by referencing the participation of the two parties in the other play service, and compared with the traditional data determined by the friend service, the vein relation quantification data are close to the play service, so that the method has more reference value, the matching effect of the team matching service is effectively improved, and the interactivity among the users participating in the play service is guaranteed.

The above exemplary embodiments and variations thereof fully disclose embodiments of the live data hierarchical acquisition method of the present application, but various variations of the method can still be deduced by transforming and augmenting some technical means, as follows outline other embodiments:

in an embodiment, referring to fig. 3, the step of predicting the predicted score data of the current user with respect to the second live broadcast playing service by using the score prediction model pre-trained to a convergence state and taking the live broadcast room feature information and the playing data information of the first live broadcast playing service as inputs includes the following steps performed by the score prediction model:

step S121, extracting feature vectors of the feature information of the live broadcasting room and the play data information of the first direct play service by using a first prediction model in the score prediction models, and predicting preliminary prediction score data of the current user in the first direct play service according to the feature vectors:

after the server acquires the live broadcasting room characteristic information of the current user and the play data information related to the first direct broadcasting play service, extracting characteristic vectors of the live broadcasting room characteristic information and the play data information of the first direct broadcasting play service by adopting a first prediction model in the score prediction model, and predicting preliminary prediction score data of the current user in the first direct broadcasting play service according to the characteristic vectors, wherein the preliminary prediction score data is the prediction score data of the current user in the first direct broadcasting play service predicted by the first prediction model.

The first prediction model is generally a model constructed based on a Wide & Deep framework, and is trained to a convergence state by adopting live broadcasting room feature information of a plurality of users associated with the first live broadcasting playing method service and the live broadcasting room feature information of the users, wherein the Wide part is based on the thought of a linear model, one-hot sparse live broadcasting room feature information and playing data information are adopted, the live broadcasting room feature information and the playing data information are converted into feature vectors of binary representation so as to train and acquire corresponding weight information, so that the weight information is adopted to extract cross feature vectors of the live broadcasting room feature information and the playing data information of the current users, in addition, regarding the Deep part, the low-dimensional dense vectors of the live broadcasting room feature information and the playing data information of the current users are extracted based on a convolutional neural network, such as an FM (frequency modulation) or DNN (digital network) model, and finally, the first prediction model predicts and outputs preliminary prediction score data of the current users associated with the first live broadcasting playing method service through the cross feature and the low-dimensional dense vectors.

Step S122, playing data information generated by the current user in the second live playing service is acquired:

The server obtains the preliminary prediction score data of the current user associated with the first live playing service through a first prediction model of the prediction score model, and meanwhile obtains playing data information generated in the second live playing service of the current user.

The play data information is play data information generated by the current user in the second live broadcast playing method service, the play data information generally comprises historical average score data, win-win ratio information and other data generated by the second live broadcast playing method service, the historical average score data represents the latest global average score data of the current user in the second live broadcast playing method service and the latest average score data of 5 plays and other average score data, and the win-win ratio information is obtained by calculating the ratio of the win number of the current user in the second live broadcast playing method service to the total play number.

Step S123, predicting final prediction score data of the current user corresponding to the second live broadcast playing service according to the preliminary prediction score information and the playing data information of the second live broadcast playing service by using a second prediction model in the score prediction model:

After the server obtains the preliminary prediction score data predicted and output by the first prediction model and the play data information generated by the current user in the second live broadcast playing service, the second prediction model is adopted, and final prediction score data of the current user corresponding to the second live broadcast playing service is predicted according to the preliminary prediction score information and the play data information.

The second prediction model is generally a linear model, and is trained through the respective preliminary prediction score information of a plurality of users in a live broadcast platform and the play data information of a second live broadcast playing method service of the users, so as to obtain corresponding weight information, and further calculate the preliminary prediction score data and the play data information of the current user according to the weight information, so as to obtain the final prediction score data of the current user corresponding to the second live broadcast playing method service.

In this embodiment, the score prediction model obtains the prediction score data of the current user corresponding to the second live broadcast playing service in a "two-step" manner, where the score prediction model predicts the preliminary prediction score data of the current user in the first live broadcast playing service through the first prediction model, and then predicts the prediction score data of the current user corresponding to the second live broadcast playing service according to the preliminary prediction score data and the playing data information generated by the current user in the second live broadcast playing service by using the second prediction model, so as to synthesize the data generated by the current user in the first and second live broadcast playing services to predict the score data of the current user in the first live broadcast playing service, thereby ensuring the fitting of the predicted data.

In an embodiment, please refer to fig. 4, in the step of using the score prediction model pre-trained to the convergence state, if the current user has not participated in the second live playing service, the following steps are performed to perform the predicted score data of the current user corresponding to the second live playing service:

step S121', extracting feature vectors of the feature information of the live broadcasting room and the play data information of the first direct play service by using a first prediction model in the score prediction models, and predicting preliminary prediction score data of the current user in the first direct play service according to the feature vectors:

when the current user never participates in the second live playing service, the server predicts preliminary prediction score data of the current user in the first live playing service by adopting the first prediction model, and then maps the preliminary prediction score data into final prediction score data of the current user corresponding to the second live playing service by using a third prediction model in the score prediction models.

For the implementation of the first prediction model, please refer to the related example in the guarantee S121, and this step is not repeated.

Step S122', mapping the preliminary prediction score data into final prediction score data corresponding to the second live broadcast playing service for the current user by using a third prediction model of the score prediction models, where the third prediction model is trained in advance to obtain mapping relationship information between the preliminary prediction score data and the final prediction score data:

When the current user does not have play data information generated by the second live playing service because the current user does not participate in the second live playing service, the server acquires the preliminary prediction score data of the current user through the first prediction model, and then maps the preliminary prediction score data into final prediction score data of the current user corresponding to the second live playing service through the third prediction model.

The third prediction model is trained through the preliminary prediction score data of a plurality of users in the live broadcast platform and score data generated by the users in the second live broadcast playing service, and mapping weights are obtained, so that the preliminary prediction score data of the current user is mapped into the final prediction score data corresponding to the second live broadcast playing service according to the mapping weights.

In this embodiment, for a user who does not participate in the second live broadcast playing service, the server predicts the preliminary prediction score data of the user corresponding to the first live broadcast playing service, and maps the preliminary prediction score data to the final prediction score data of the user corresponding to the second live broadcast playing service, so as to ensure the adaptability of the score prediction service in the system.

In an embodiment, please refer to fig. 5, in the step of calculating the matching value of the current user corresponding to each other user by integrating the quantized data of the vein relationship between the current user and each other user participating in the second live broadcast playing service, the current user and the respective prediction score data of all the other users, the method includes the following steps:

step S131, according to the prediction score data corresponding to each user in the second live broadcast playing service, the users are ordered in descending order:

after the server obtains the prediction score data of each user participating in the second live playing service, which corresponds to the second live playing service, the users are sorted in descending order according to the prediction score data of each user.

Step S132, calculating a matching value between the user in the top ranking position and the other users each after the middle ranking position:

after the server finishes the descending order sequencing of the users, the matching value between the user positioned at the front position of the sequencing and other users positioned at the middle position of the sequencing is calculated, so that the user performing the matching value calculation is controlled.

Step S133, determining one or more other users having relatively higher matching values with the user at the front position, removing the other users and the user at the front position from the ranking, and completing the calculation of the matching values between the corresponding users in the ranking according to the previous step and the present step:

and after the server finishes calculating the matching value between the user positioned at the front position and other users positioned at the middle position of the sequence and determining one or more other users with relatively higher matching values with the user positioned at the front position, removing the current user and the other users from the descending sequence, controlling the user for calculating the matching value according to the previous step, removing the user with relatively higher matching values from the descending sequence, and the like, so as to finish the calculation of the matching value between the corresponding users in the descending sequence.

In this embodiment, according to the predicted score data of each user participating in the second live broadcast playing service, the user performing matching value calculation is controlled, so that users in the combined team subsequently matching and participating in the second live broadcast playing service are ensured not to configure the user with higher predicted score data in the current second live broadcast playing service to be the uncombined team due to consideration of the matching value, unbalance of a team matching system is caused, and playing experience of other users in the playing service is affected.

In an embodiment, please refer to fig. 6, in the step of calculating the matching value of the current user corresponding to each other user by integrating the quantized data of the vein relationship between the current user and each other user participating in the second live broadcast playing service, the current user and the respective prediction score data of all the other users, the method includes the following steps:

step S131', obtaining the quantized data of the relationship between the current user and any other user participating in the second live playing service, wherein the quantized data of the relationship is determined according to the association relationship between the current user and the other user participating in the first live playing service:

the server obtains the people's vein relation quantification data between the current user and any other user participating in the second live broadcast playing service, the people's vein relation quantification data is determined according to the association relation between the current user and any other user participating in the second live broadcast playing service, for example, when the first live broadcast playing service is one-to-one wheat linking service, the current user and the other user use the wheat linking service provided by the first live broadcast playing service to link together, the people's vein relation quantification data between the two parties will represent that the two parties have a direct association relation in the first live broadcast playing service, and if the current user and the other user do not use the wheat linking service provided by the first live broadcast playing service to link together, but have the indirect association relation in the first live broadcast playing service between the current user and the other user.

Step S132', calculating the difference between the prediction score data of the current user and the other user:

the server obtains the prediction score data of each of the current user and other users corresponding to the vein relation quantification data so as to calculate the difference value between the prediction score data of each of the current user and the other users.

Step S133', a calculation result of subtracting the difference value from the numerical value represented by the vein relation quantification data is obtained, and the calculation result is used as a matching value between the current user and the other users:

after obtaining the difference value between the prediction score data between the current user and the other users and the vein relation quantization data between the two parties, the server subtracts the calculation result of the difference value from the numerical value represented by the obtained vein relation quantization data, and takes the calculation result as the matching value between the current user and the other users, wherein the specific calculation formula is as follows:

the P direct relationship is a value corresponding to a direct association relationship between the two parties indicated in the quantized data of the relationship in the first direct play service, the value is generally 1 or more than a value corresponding to an indirect relationship in P indirect relationship, the P indirect relationship is a value corresponding to an indirect association relationship between the two parties indicated in the quantized data of the relationship in the first direct play service, the value is generally 0.5 or less than a value corresponding to the P direct relationship, and it can be understood that the value indicated by the quantized data of the relationship between the current user and other users can only be one of the P direct relationship or the P indirect relationship.

In this embodiment, matching values of the two parties are calculated through quantized data of the relationship between the current user and the other user in the first direct play service, and compared with the traditional method of calculating matching values according to interactive data such as online chatting of the two parties of the user in the friend online service, the quantized data of the relationship between the two parties in the play service has a more reference value and is more fit with the play service.

In one embodiment, referring to fig. 7, the step of configuring the other users with relatively high matching values and the current user as a joint team in the second live playing service includes the following steps:

step S141, according to the matching values between the current user and the other users participating in the second live playing service, ordering the other users in a descending order:

after calculating the matching values between the current user and other users corresponding to the second live playing service, the server ranks the other users in descending order according to the matching values between the other users and the current user.

Step S142, configuring the top ranked one or more other users and the current user as a joint team in the second live playing service:

The server configures one or more other and current users in the descending order as the joint team in the second live house play service, and specifically, the number of other users determined by the server from the descending order is generally set in the range of 1 to 3, so as to ensure that the number of users in the joint team is sufficient to participate in the second live house play service.

In this embodiment, the other users are sorted in a descending order according to the matching values between the current user and the plurality of other users, so that it is quickly determined that the other users with relatively high matching values with the current user are configured as a joint team in the second live playing method.

In one embodiment, referring to fig. 8 and 9, after the step of configuring the other users with relatively high matching values and the current user as a joint team in the second live playing service, the method includes the following steps:

step S15, sorting the combined warfare in descending order according to the warfare prediction score data corresponding to each of all the combined warfare in the second live playing service, wherein the warfare prediction score data is the sum of the prediction score data corresponding to each of all the users in the combined warfare:

after the server completes configuration of all the combined teams participating in the second live playing method service, the teams prediction score data corresponding to the combined teams are calculated, wherein the teams prediction score data is the sum of the prediction score data corresponding to all the users in the combined teams.

After the server obtains the predicted score data of the teams corresponding to the combined teams, the teams are sorted in descending order according to the predicted score data of the teams.

Step S16, configuring the combined team at the front position and the combined team at the middle position to a first match track or a second match track, wherein the first match track and the second match track respectively have the same number of combined teams:

after the server finishes the descending order of the combined warfare, the combined warfare in the front position of the descending order and the combined warfare in the middle position of the order are allocated to the first fight track or the second fight track, the combined warfare is removed from the descending order, and if the combined warfare is allocated to the first fight track, the two combined warfare determined in the descending order are allocated to the second fight track, and the like, each combined warfare in the descending order is evenly allocated to the first fight track and the second fight track, so that the first fight track and the second fight track have the same number of combined warfare.

Step S17, starting a promotion war office among the combined war teams in each fight race track, wherein the promotion war office is provided with two combined war teams with relatively close war team prediction score data:

the server starts a promotion combat office between each combined combat team in the first combat race and the second combat race, the combat team prediction score data of each of the two combined combat teams performing the combat in the promotion combat office is relatively close, for example, the combined combat team with the highest combat team prediction score data in the combat race generally performs the combat of the promotion combat office with the combined combat team with the combat team prediction score data close to the median of all the combined combat teams in the combat race.

In the promotion combat office of the match-up course, the joint combat team with the highest match-up score data in the promotion combat office is taken as the winning joint combat team, and the joint combat team and the winning joint combat team in another promotion combat office in the match-up course are configured to be matched with the same promotion combat office, and so on until the winning joint combat team appears in the final promotion combat office in the match-up course.

The generation mode of the fight score data of each combined fight team is defined according to the playing rules of the second live playing method service, for example, when the second live playing method service is a continuous operation, the fight score data of each combined fight team is determined according to virtual gifts given by audience users in the living broadcast room received by each user in each combined fight team.

The number of the fight times of the promotion combat office is generally based on the number of the users in the engaged combined combat team, for example, when the number of the users in the combined combat team of both parties in the promotion combat office is 3, and the fight of the promotion combat office is one-to-one continuous combat activity, the number of the fight times of the promotion combat office is 3.

Step S18, determining the combined warfare with higher match score data in each warfare in each match-up race track, starting the advanced warfare among the combined warfare, and the like until the champion warfare among the combined warfare of the final promotion of the first match-up race track and the second match-up race track is started:

after determining a combined team with higher score data of a promotion battle in each level of the first and second match tracks, namely, the combined team with the highest score data in the final battle, the server configures each combined team in the first and second match tracks as the champion battle, and specifically, please refer to fig. 9, fig. 9 is a schematic diagram of the configuration of the promotion battle and the configuration of the champion battle of each match track in the second live broadcast playing service.

In this embodiment, by allocating the combined warfare for promoting the warfare in each competition track according to the sum of the predicted score data of each user in each combined warfare, the combined warfare for promoting the competition in each competition track and the first round of warfare are reasonably allocated according to the predicted result, so as to further improve the playing experience of the warfare in each warfare and enhance the ornamental value of the playing service.

Further, by performing the functionalization of each step in the method disclosed in the foregoing embodiments, a live broadcast room user team device of the present application may be constructed, and according to this concept, please refer to fig. 10, where in one exemplary embodiment, the device includes: a play data obtaining module 11, configured to obtain feature information of a live broadcasting room of a current user and play data information related to a first direct broadcasting play service thereof; the score data predicting module 12 is configured to predict, using a score predicting model pre-trained to a convergence state, prediction score data of the current user with respect to the second live broadcast playing service, with the live broadcast room feature information and the playing data information of the first live broadcast playing service as input; the matching value calculation module 13 is configured to integrate quantized data of a vein relationship between the current user and each other user participating in the second live broadcast playing service, and respective prediction score data of the current user and each of the other users, and calculate a matching value of the current user corresponding to each of the other users; and the joint warfare configuration module 14 is used for configuring other users with relatively high matching values and the current user as the joint warfare in the second live playing service.

In one embodiment, the score data prediction module 12 includes: the score data preliminary prediction sub-module is used for extracting feature vectors of live broadcasting room feature information and play data information of the first direct play service by adopting a first prediction model in the score prediction models, and predicting preliminary prediction score data of the current user in the first direct play service according to the feature vectors; the play data information acquisition sub-module is used for acquiring play data information generated by the current user in the second live broadcast play service; and the score data final prediction sub-module is used for predicting final prediction score data of the current user corresponding to the second live broadcast playing service according to the preliminary prediction score information and the playing data information of the second live broadcast playing service by adopting a second prediction model in the score prediction model.

In another embodiment, the score data prediction module 12 further includes: the score data preliminary prediction sub-module is used for extracting feature vectors of live broadcasting room feature information and play data information of the first direct play service by adopting a first prediction model in the score prediction models, and predicting preliminary prediction score data of the current user in the first direct play service according to the feature vectors; and the score data mapping prediction sub-module is used for mapping the preliminary prediction score data into final prediction score data corresponding to the second live broadcast playing service of the current user by adopting a third prediction model in the score prediction models, and the third prediction model is trained in advance to acquire mapping relation information between the preliminary prediction score data and the final prediction score data.

In one embodiment, the matching value calculation module 13 includes: the user descending order sorting sub-module is used for descending order sorting of the users according to the prediction score data corresponding to each user in the second live broadcast playing service; the matching value calculation sub-module is used for calculating matching values between the users at the front-ranking positions and other users after each middle-ranking position; and the user sorting and removing sub-module is used for determining one or more other users with relatively higher matching values with the users at the front positions, removing the other users and the users at the front positions from the sorting, and completing the calculation of the matching values between the corresponding users in the sorting according to the last step and the step.

In another embodiment, the matching value calculating module 13 further includes: the system comprises a vein data acquisition sub-module, a first direct broadcast playing service module and a second direct broadcast playing service module, wherein the vein data acquisition sub-module is used for acquiring vein relation quantification data between a current user and any other user participating in the second direct broadcast playing service, and the vein relation quantification data is determined according to the association relation between the current user and the other user participating in the first direct broadcast playing service; the score data difference value calculation sub-module is used for calculating the difference value between the prediction score data of the current user and the prediction score data of the other users; and the matching value acquisition sub-module is used for acquiring a calculation result of subtracting the difference value from the numerical value represented by the vein relation quantitative data, and taking the calculation result as a matching value between the current user and the other users.

In one embodiment, the federated team configuration module 14 includes: the user descending order sorting sub-module is used for descending order sorting of the other users according to the matching value between the current user and the other users participating in the second live broadcast playing service; and the combined warfare configuration sub-module is used for configuring one or more other users and the current user which are ranked ahead as the combined warfare in the second live playing service.

To solve the above technical problem, the embodiments of the present application further provide a computer device, configured to run a computer program implemented according to the live broadcast room user team formation method. Referring specifically to fig. 11, fig. 11 is a basic structural block diagram of a computer device according to the present embodiment.

As shown in fig. 11, the internal structure of the computer device is schematically shown. The computer device includes a processor, a non-volatile storage medium, a memory, and a network interface connected by a system bus. The nonvolatile storage medium of the computer device stores an operating system, a database and computer readable instructions, the database can store a control information sequence, and the computer readable instructions can enable a processor to realize a live broadcasting room user team forming method when the computer readable instructions are executed by the processor. The processor of the computer device is used to provide computing and control capabilities, supporting the operation of the entire computer device. The memory of the computer device may have stored therein computer readable instructions that, when executed by the processor, cause the processor to perform a live room user queuing method. The network interface of the computer device is for communicating with a terminal connection. It will be appreciated by those skilled in the art that the structure shown in fig. 11 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

The processor in this embodiment is configured to perform specific functions of each module/sub-module in the live broadcast room user team device of the present invention, and the memory stores program codes and various types of data required for executing the modules. The network interface is used for data transmission between the user terminal or the server. The memory in this embodiment stores program codes and data required for executing all modules/sub-modules in the live broadcast room user team device, and the server can call the program codes and data of the server to execute the functions of all sub-modules.

The present application also provides a non-volatile storage medium, in which the live-room user queuing method is written as a computer program, and the computer program is stored in the storage medium in the form of computer readable instructions, where the computer readable instructions when executed by one or more processors mean that the program runs in a computer, thereby causing the one or more processors to perform the steps of the live-room user queuing method in any of the embodiments described above.

Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored in a computer-readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).

In summary, the score of the new play service is predicted according to the play data of other play services, so that the fitting degree of the prediction result of the predicted new play service is ensured, and the matching effect of the team matching service in the new play service is optimized.

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

Those of skill in the art will appreciate that the various operations, methods, steps in the flow, actions, schemes, and alternatives discussed in the present application may be alternated, altered, combined, or eliminated. Further, other steps, means, or steps in a process having various operations, methods, or procedures discussed in this application may be alternated, altered, rearranged, split, combined, or eliminated. Further, steps, measures, schemes in the prior art with various operations, methods, flows disclosed in the present application may also be alternated, altered, rearranged, decomposed, combined, or deleted.

The foregoing is only a partial embodiment of the present application, and it should be noted that, for a person skilled in the art, several improvements and modifications can be made without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

Claims

1. A method for user queuing in a live broadcast room, comprising the steps of:

a score prediction model which is pre-trained to a convergence state is adopted, and the characteristic information of the live broadcasting room and the playing data information of the first live broadcasting playing method service are taken as inputs to predict the prediction score data of the current user relative to the second live broadcasting playing method service; the score prediction model comprises two prediction models, wherein one prediction model predicts preliminary prediction score data according to the characteristic information of the living broadcast room and game data of a first direct broadcast playing method service, the other prediction model predicts and determines the prediction score data according to the initial prediction score data and game data information generated by a second direct broadcast playing method service of a current user, or determines the prediction score data corresponding to the initial prediction score data according to mapping relation information, and the mapping relation information is obtained by training score data generated by other users participating in the second direct broadcast playing method service and prediction score data obtained by predicting the first direct broadcast playing method service of the users;

Integrating the quantized data of the relationship between the current user and each other user participating in the second live broadcast playing service and the respective corresponding prediction score data of the current user and all other users, and calculating the matching value of each other user corresponding to the current user; wherein, include: acquiring the quantized data of the human relation between the current user and any other user participating in the second live playing service, wherein the quantized data of the human relation is determined according to the association relation between the current user and the other user participating in the first live playing service; sorting the users in descending order according to the prediction score data corresponding to each user in the second live broadcast playing service; calculating a matching value between the user at the position of the front ranking and other users after each position of the middle ranking; determining one or more other users with relatively higher matching values with the users at the front positions, removing the other users and the users at the front positions from the ranking, and completing calculation of the matching values between the corresponding users in the ranking according to the last step and the step;

2. The method of claim 1, wherein the step of employing the score prediction model pre-trained to a convergence state comprises the steps of:

3. The method of claim 1, wherein the step of employing the score prediction model pre-trained to a convergence state comprises the steps of:

4. The method according to claim 1, wherein the step of integrating the quantized data of the relationship between the current user and each other user participating in the second live playing service, the respective prediction score data of the current user and each of the other users, and calculating the matching value of the current user for each of the other users respectively includes the steps of:

5. The method of claim 1, wherein the step of configuring the other users having the relatively high matching value and the current user as a joint team in the second live play service comprises the steps of:

6. The method according to any one of claims 1 to 5, characterized in that after the step of configuring the other users with the relatively high matching value with the current user as a joint team in a second live playing service, the steps of:

7. An electronic device comprising a central processor and a memory, characterized in that the central processor is adapted to invoke a computer program stored in the memory for performing the steps of the method according to any of claims 1 to 6.

8. A non-volatile storage medium, characterized in that it stores in form of computer readable instructions a computer program implemented according to the method of any one of claims 1 to 6, which when invoked by a computer, performs the steps comprised by the method.