CN116920422A

CN116920422A - Game account recommending method and device, electronic equipment and storage medium

Info

Publication number: CN116920422A
Application number: CN202210335967.XA
Authority: CN
Inventors: 陈博引
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2022-03-31
Filing date: 2022-03-31
Publication date: 2023-10-24

Abstract

The embodiment of the application discloses a game account recommending method, a game account recommending device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a first type candidate account which participates in game play together with an account to be recommended; scoring the first type candidate account according to scoring events corresponding to the first type candidate account to obtain a first scoring value, wherein the scoring events are determined by result data of game games and interaction data of the first type candidate account and the account to be recommended in the game games; and recommending the first candidate recommended account with the first scoring value larger than a preset threshold value to the account to be recommended as the friend recommended account. According to the method and the device for adding the friend recommendation account to the account to be recommended, probability that the friend recommendation account is added to the account to be recommended is improved, a certain number of friend recommendation accounts are generated for the account to be recommended based on the second type candidate account, the second type candidate account is a game account which does not participate in game play with the account to be recommended, and the degree of diversification of the method and the device can be improved.

Description

Game account recommending method and device, electronic equipment and storage medium

Technical Field

The application relates to the technical field of information prompt, in particular to a game account recommending method and device, electronic equipment and a storage medium.

Background

Currently, mobile communication devices are spread throughout the life of people, along with popularization of smart phones, various kinds of game and social APP are layered endlessly, and the mobile communication devices are not limited to one communication device in the life of people, and play a role in entertainment of people. But there is a common problem with various gaming APPs on today's networks: the player's true interactivity is not strong, and plays a guest role in the game, whether opponents or teammates. Moreover, because of the high degree of intelligence of mobile communication devices, many people are enthusiastic in network games in the virtual world, thereby ignoring the social interactions between people in real life. In the prior art, a friend recommending mode is adopted to recommend friends to a player, and the existing scheme is usually only to screen according to the distance or identity characteristics between game players, so that the requirement of adding friends to the game players is met to a certain extent. However, the searching effect of the scheme is generally poor, and the player is required to manually make a selection, and although a large number of game friends can be quickly added, the probability of adding requests is generally low, the time and the position of logging in the game are far away from each other, the communication interaction between players is affected, and the actual requirements of the players still cannot be met.

Disclosure of Invention

In order to solve the technical problems, the embodiment of the application provides a game account recommending method, a game account recommending device, electronic equipment and a computer readable storage medium, which can improve the probability that an account to be recommended adds a friend recommending account as a friend.

Other features and advantages of the application will be apparent from the following detailed description, or may be learned by the practice of the application.

According to one aspect of the embodiment of the application, there is provided a game account recommending method, including: acquiring a first type candidate account which participates in game play together with an account to be recommended; scoring the first type candidate account according to scoring events corresponding to the first type candidate account to obtain a first scoring value, wherein the scoring events are determined by result data of game games and interaction data of the first type candidate account and the account to be recommended in the game games; and if the first grading value is larger than a first preset threshold value, recommending the candidate recommended account as the friend recommended account to the account to be recommended.

According to an aspect of an embodiment of the present application, there is provided a game account recommending apparatus, including: the first acquisition module is used for acquiring a first type candidate account which participates in game play together with the account to be recommended; the scoring module is used for scoring the first type candidate account according to scoring events corresponding to the first type candidate account to obtain a first scoring value, wherein the scoring events are determined by the result data of the game and the interaction data of the first type candidate account and the account to be recommended in the game; and the first recommendation module is used for recommending the candidate recommendation account as the friend recommendation account to the account to be recommended if the first grading value is larger than a first preset threshold value.

In another exemplary embodiment, the scoring module includes a first obtaining unit and a first scoring unit, where the first obtaining unit is configured to obtain occurrence times and occurrence times corresponding to the scoring event; the first scoring unit is used for determining the weight corresponding to the scoring event based on the occurrence times and the occurrence time, and calculating the weighted sum of the scoring event and the weight to obtain a first scoring value.

In another exemplary embodiment, the first scoring unit includes an obtaining subunit, a first calculating subunit, and a second calculating subunit, where the obtaining subunit is configured to obtain an addition factor and an attenuation factor corresponding to the weight, the addition factor increasing as the number of times of occurrence of the scoring event increases, the attenuation factor increasing as a length of time between a time of occurrence of the scoring event and a current time increases; the first calculating subunit is used for calculating a first weight based on a preset initial weight and an addition factor, and calculating a second weight based on the initial weight and an attenuation factor; the second calculating subunit is configured to calculate a weighted sum of the first weight and the second weight, and use the weighted sum as the weight corresponding to the scoring event.

In another exemplary embodiment, the game account recommending device provided in this embodiment further includes an accumulating module, a second obtaining module, and a second recommending module, where the accumulating module is configured to add one to an accumulated amount of friend recommended accounts corresponding to the account to be recommended; the second obtaining module is used for obtaining a second type candidate account which does not participate in game play with the account to be recommended together if the obtained accumulated quantity is larger than a second preset threshold; the second recommendation module is used for recommending the second type candidate account meeting the preset recommendation condition to the object to be recommended.

In another exemplary embodiment, the second recommendation module includes a second scoring unit and a second recommendation unit, where the second scoring unit is configured to score the second class candidate account based on attribute information of the second class candidate account to obtain a second score value, where the attribute information includes at least one of login area information, online time information, segment information, and game role information; and the second recommending unit is used for recommending the second type candidate account to the account to be recommended if the second grading value is larger than a third preset threshold value.

In another exemplary embodiment, the game account recommending device provided in this embodiment further includes a matching module and an executing module, where the matching module is configured to match the first type candidate account with a blacklist and a friend list corresponding to the account to be recommended, respectively; and the execution module is used for executing the step of scoring the first type candidate account according to the scoring event corresponding to the first type candidate account if the matching is unsuccessful.

In another exemplary embodiment, the game account recommending device provided in this embodiment further includes a generating module and a sending module, where the generating module is configured to generate a recommendation reason based on the scoring event; the sending module is used for sending the recommendation reason to the account to be recommended.

According to an aspect of an embodiment of the present application, there is provided an electronic device including a processor and a memory, the memory storing computer readable instructions that when executed by the processor implement a game account recommendation method as above.

According to an aspect of an embodiment of the present application, there is provided a computer-readable storage medium having stored thereon computer-readable instructions which, when executed by a processor of a computer, cause the computer to perform a game account recommendation method as previously provided.

According to an aspect of embodiments of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the game account recommending method provided in the above-described various alternative embodiments.

In the technical scheme provided by the embodiment of the application, the first type candidate account which participates in the game in the opposite office together with the account to be recommended is scored, whether the first type candidate account is used as a friend recommendation account or not is determined according to the obtained first scoring value, compared with the completely strange game account, the account to be recommended obviously tends to be added with the game account which participates in the game in the opposite office together with the account to be recommended as a friend, and the interaction data of the account to be recommended and the first type candidate account in the game opposite office and the result data of the game opposite office further influence the probability that the account to be recommended adds the first type candidate account as a friend.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. It is evident that the drawings in the following description are only some embodiments of the present application and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art. In the drawings:

FIG. 1 is a schematic diagram illustrating an implementation environment in which the present application is directed, according to one illustrative embodiment;

FIG. 2 is a schematic diagram of a prior art approach to recommending game account numbers to a player using fuzzy search;

FIG. 3 is a flow chart of a game account recommendation method according to an exemplary embodiment of the present application;

FIG. 4 is a schematic diagram of a friend recommendation function setup page, shown in an exemplary embodiment of the application;

FIG. 5 is a flow chart of a game account recommendation method presented on the basis of the embodiment shown in FIG. 3;

FIG. 6 is a flow chart of step S102 in the embodiment shown in FIG. 3 in an exemplary embodiment;

FIG. 7 is a schematic diagram showing the influence of time factors and frequency factors on weights corresponding to standard scoring events according to an exemplary embodiment of the present application;

FIG. 8 is a flow chart of step S202 in the embodiment of FIG. 6 in an exemplary embodiment;

FIG. 9 is a flow chart of a game account recommendation method presented on the basis of the embodiment shown in FIG. 3;

FIG. 10 is a flow chart of step S402 in the embodiment of FIG. 9 in an exemplary embodiment;

fig. 11 is a schematic view of an attribute information setting page shown in an exemplary embodiment of the present application;

FIG. 12 is a graph showing scoring benchmarks for login area information, according to an exemplary embodiment of the present application;

FIG. 13 is a flow chart of a game account recommendation method presented on the basis of the embodiment shown in FIG. 3;

FIG. 14 is a flow chart of a game account recommendation method presented on the basis of the embodiment shown in FIG. 3;

FIG. 15 is a flowchart of an exemplary embodiment of step S701 in the embodiment shown in FIG. 14;

FIG. 16 is a diagram of a friend recommendation account page, according to an exemplary embodiment of the present application;

FIG. 17 is a block diagram of a game account recommending apparatus according to an exemplary embodiment of the present application;

FIG. 18 is a block diagram of a game account recommendation system, shown in accordance with an exemplary embodiment of the present application;

Fig. 19 shows a schematic diagram of a computer system suitable for use in implementing an embodiment of the application.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.

The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.

Also to be described is: in the present application, the term "plurality" means two or more. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., a and/or B may represent: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship.

It can be appreciated that in the specific embodiment of the present application, the data related to the user, such as the result data of the game pair and the interaction data of the first candidate account and the account to be recommended in the game pair, is related to, when the above embodiment of the present application is applied to specific products or technologies, the user permission or consent needs to be obtained, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region.

FIG. 1 is a schematic diagram illustrating an implementation environment in which the present application may be practiced, according to one exemplary embodiment. The implementation environment related to the application can be applied to various scenes such as cloud technology, artificial intelligence, intelligent traffic, auxiliary driving and the like. As shown in fig. 1, the implementation environment of the present application includes at least a terminal 110 and a server 130 used by a user. Data interaction is realized between the terminal 110 and the server 130 through the internet.

The terminal 110 may be a smart phone, a tablet computer, a PC (Personal Computer ), an intelligent voice interaction device, an intelligent home appliance, a vehicle-borne terminal, or any other electronic device capable of running an application, without limitation. The server 130 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network ), and basic cloud computing services such as big data and artificial intelligence platform, which are not limited herein.

For example, the server 130 is configured to obtain a first type candidate account that participates in a game with the account to be recommended; scoring the first type candidate account according to scoring events corresponding to the first type candidate account to obtain a first scoring value, wherein the scoring events are determined by result data of game games and interaction data of the first type candidate account and the account to be recommended in the game games; and if the first grading value is larger than a first preset threshold value, recommending the candidate recommended account as the friend recommended account to the account to be recommended.

The inventor of the present application has found through long-term research that the prior art recommends friends for players in at least the following 2 ways: (1) Randomly selecting a batch of players with the same attribute to recommend, wherein the attributes of the game players include but are not limited to grades, segments, roles and the like, and the attributes are not particularly limited herein; (2) Allowing users to conduct fuzzy searches for close players according to some social/favorites attributes.

However, the 2 modes have the following disadvantages: the mode (1) is only based on static characteristics such as player segment positions, player preferences and the like, but does not combine historical game data of a player and other players to recommend, the granularity is too coarse, a result with very low matching degree is likely to be obtained, the meaning is not great, and the intention of the player to add friends is not high; the method (1) and the method (2) realize the structural query mainly depending on the database, and if the load of the database is exceeded when the request is concurrent under the scene of massive users, serious delay is caused, even the result cannot be returned, and intolerable experience is brought to the users.

Referring to fig. 2, fig. 2 is a schematic diagram of recommending game accounts to players by using a fuzzy search method in the prior art, and as shown in fig. 2, the account to be recommended may input a game account in a search box "input game account" and add the game account obtained by the search as a friend. The player can also obtain the game account matched with the corresponding option by setting specific values of options such as 'online time period', 'city', 'gender', 'section position', 'usual position', and the like, triggering 'search' of the route selection, and can select the game account obtained by matching to be added as friends, if no corresponding game account is found by matching, displaying 'no more game account is searched', and recommending game accounts which are possibly interested by the player, for example, the game account which is possibly interested by the player comprises a game account 1, the section position corresponding to the game account 1 is the section position 1, and the gender corresponding to the game account 1 is the gender 1; the game account number which the player may be interested in comprises a game account number 2, wherein the segment bit corresponding to the game account number 2 is segment bit 2, and the sex corresponding to the game account number 2 is sex 2; the game account number that the player may be interested in includes game account number 3, the segment corresponding to game account number 3 is segment number 3, the gender corresponding to game account number 3 is gender 3, etc., and the player may update the game account number that may be interested in by triggering the "change batch" option. The mode of recommending the game account number to the player through the fuzzy search requires the player to select each search condition by himself, and the player needs to understand each meaning and judge the relevance by himself, so that the operation is complex, the thinking dimension is large, and the user experience is poor.

In order to solve at least the above problems in the prior art, embodiments of the present application respectively provide a game account recommending method, a game account recommending device, an electronic device, and a computer readable storage medium, and these embodiments will be described in detail below.

Referring to fig. 3, fig. 3 is a flowchart of a game account recommending method according to an exemplary embodiment of the present application, and as shown in fig. 3, the game account recommending method provided in the present embodiment includes steps S101 to S103, and the detailed description is referred to as follows:

step S101: and obtaining a first type candidate account which participates in the game with the account to be recommended.

In this embodiment, the account to be recommended and the first type candidate account are both game accounts for uniquely identifying game players. The first type candidate account numbers which participate in the game counter together with the account numbers to be recommended represent game account numbers which are teammates or opponents with the account numbers to be recommended in at least one game counter within a preset time period.

The inventor discovers that the prior art recommends friends for the game account according to social attributes such as online time, geographic position and character preference of a game player, the granularity is too coarse, the recommended game account is quite unfamiliar to the account to be recommended, the result with very low matching degree is quite possibly obtained, the meaning of the account to be recommended is not great, the intention of adding friends to the account to be recommended is not high, and therefore, in order to improve the matching degree of the account to be recommended and the recommended game account, the application proposes to recommends based on the game account which participates in game play together with the account to be recommended, the account to be recommended and the game account participate in game play together with the game account, and the account to be recommended obviously has better intention to be added as friends compared with the game account which is quite unfamiliar.

For example, first, historical game data of an account to be recommended is obtained, and then a first type candidate account which participates in game games together with the account to be recommended is obtained from the historical game data.

By way of example, the game account recommending method provided by the embodiment allows the user to close the friend recommending function through setting, ensures privacy data of the user, has no supervision risk, and improves user experience, for example, setting in the setting to prevent other people from seeing themselves or not seeing other people.

Referring to fig. 4, fig. 4 is a schematic diagram of a friend recommendation function setting page according to an exemplary embodiment of the present application, as shown in fig. 4, after an account to be recommended closes a friend recommendation function, if the friend recommendation function is to be opened, the client device needs to be controlled to jump to the friend recommendation function setting page, and a "start friend recommendation function" option is triggered, and after the friend recommendation function is triggered, the friend recommendation function can be opened.

In an exemplary embodiment, after detecting that an account to be recommended logs in a game application program, a game pair ends settlement or a social label is modified, a game account recommending command is triggered, and then the background executes the game account recommending method provided by the embodiment to send a friend recommending account for the account to be recommended.

In an exemplary embodiment, the game account recommending method provided by the embodiment decouples the recommending process and the checking process, that is, after receiving the game account recommending command, the background automatically triggers the game account recommending process, stores the friend recommending account list, and returns to the friend recommending account list directly when the to-be-recommended account triggers to check the friend recommending account list, wherein the friend recommending account list comprises a plurality of friend recommending accounts.

Step S102: and scoring the first type candidate account according to the scoring event corresponding to the first type candidate account to obtain a first scoring value.

In this embodiment, the scoring event corresponding to the first type candidate account represents an event with a certain influence on the account to be recommended when the first type candidate account is added as a friend. The scoring event corresponding to the first type candidate account number can be one or more according to the actual game situation.

It should be noted that, the plurality of scoring events corresponding to the first type candidate account may occur in the same game play or different game plays. For example, the scoring event may be that the account to be recommended is a first type candidate account number endorsed, the first type candidate account number is opposite MVP to the account to be recommended, the account to be recommended and the first type candidate account number are winners and are a drop combination, the account to be recommended and the first type candidate account number are winners and are a wild plus combination, the account to be recommended and the first type candidate account number are winners and are other combinations, and the like, which are not limited herein.

The MVP is the game account with the highest KDA value, the KDA is the ratio of the sum of the number of the opponents to the death number, the winner MVP is the game player with the highest KDA of the current winner team, and the loser MVP is the game account with the highest KDA of the loser.

In this embodiment, the scoring event is determined by the result data of the game, and the interaction data of the first type candidate account and the account to be recommended in the game, where the result data of the game is, for example, the winner or loser of the account to be recommended in the game, the winner or loser of the first type candidate account, the MVP of the game in which the account to be recommended or the first type candidate account is, and so on, without specific limitation herein. The interaction data of the first type candidate account and the account to be recommended in the game, such as the fact that the first type candidate account is endorsed by the account to be recommended or the account to be recommended is endorsed by the first recommendation account, is not limited in detail herein.

In this embodiment, the first type candidate account may be scored, so that the scoring event that may occur in the first type candidate account may be preset, which may be called a possible scoring event, a corresponding scoring value is preset for each possible scoring event, and if the scoring event corresponding to the first type candidate account corresponds to one of the multiple possible scoring events, the scoring value corresponding to the possible scoring event is taken as the first scoring value.

Step S103: and if the first grading value is larger than a first preset threshold value, recommending the first type candidate account as the friend recommendation account to the account to be recommended.

In this embodiment, the first preset threshold may be flexibly determined according to an actual application scenario, for example, if the total number of friends in the buddy list corresponding to the account to be recommended is detected to be relatively small, the first preset threshold is controlled to be relatively small, for example, 70, 75, etc. so that more candidate accounts of the first type are larger than the first preset threshold, and further more friend-recommended accounts are recommended for the account to be recommended, otherwise, if the total number of friends in the buddy list corresponding to the account to be recommended is detected to be relatively large, the friend-making will of the account to be recommended is not very strong, so that the first preset threshold is controlled to be relatively large, for example, 90, 95, etc. so that fewer candidate accounts of the first type are larger than the first preset threshold, and further relatively fewer friend-recommended accounts are recommended for the account to be recommended.

The game account recommending method provided by the embodiment scores the first type candidate account which participates in the game with the account to be recommended, determines whether to send the first type candidate account to the account to be recommended as the friend recommending account according to the obtained first score value, and obviously, the account to be recommended is more prone to adding the game account which participates in the game with the account to be recommended as the friend relative to the complete strange game account, and the interaction data of the account to be recommended and the first type candidate account in the game and the result data of the game can further influence the probability that the account to be recommended adds the first type candidate account as the friend, therefore, the embodiment scores the game accounts which participate in the game play together with the account to be recommended based on the interaction data of the account to be recommended and the first type candidate account in the game play and the result data of the game play, and recommending the first type candidate account with the score value larger than the preset score value to the account to be recommended as the friend recommendation account, so that the matching degree between the first type candidate account and the account to be recommended can be improved, and the probability that the account to be recommended adds the friend recommendation account as a friend can be improved.

Referring to fig. 5, fig. 5 is a flowchart of a game account recommending method according to the embodiment shown in fig. 3, and before step S102, the game account recommending method according to the embodiment further includes steps S11 to S13, which are described in detail below:

step S11: and acquiring second interaction data and second result data of the account to be recommended and the corresponding friend account in the game.

In this embodiment, the second interactive data includes, but is not limited to, a friend account being a to-be-recommended account endorsed, a to-be-recommended account being a friend account endorsed, a friend account and a to-be-recommended account having dialogue data characterizing a good sense in game play, a friend account being a own MVP, a to-be-recommended account and a friend account being a drop combination, a to-be-recommended account and a friend account being a wild plus combination, a to-be-recommended account and a friend account being other combinations, and the like, which are not specifically limited herein; the second result data includes, but is not limited to, that the game is a friend account and an account to be recommended are winners, that the friend account and the account to be recommended are losers, that the friend account is a winner, that the account to be recommended is a loser, that the friend account is a loser, and that the account to be recommended is a winner.

Step S12: a plurality of standard scoring events are generated based on the second interaction data and the second result data.

The embodiment may generate the standard scoring event based on the second interaction data and the second result data, or may generate the standard scoring event in combination with the second interaction data and the second result data, which is not limited herein.

For example, if the second interaction data is that the friend account is endorsed by the account to be recommended, the generated standard scoring event is that the game account is endorsed by the account to be recommended; for example, if the second interaction data is that the account to be recommended is a friend account and a game account is praised by the friend account, the generated standard scoring event is that the account to be recommended is praised by the game account.

For example, the second interactive data is a combination of a to-be-recommended account and a friend account, the second result data is a combination of a wild and a middle road, the second result data is a combination of a friend account and a to-be-recommended account, the generated standard scoring event is a combination of a game and a middle road, the game and the middle road, for example, the second interactive data is a combination of the to-be-recommended account and the friend account, the second result data is a combination of a friend account and a non-friend account, the to-be-recommended account is a winner, the generated standard scoring event is a combination of a opponent account and a non-player.

Step S13: and if the target standard scoring event is matched with the first result data and the second interaction data, taking the target standard scoring event as the scoring event corresponding to the first type candidate account.

In this embodiment, each standard scoring event of the first result data and the second interaction data is matched, and if the matching is successful, the target standard scoring event matched with the first result data and the second interaction data is used as the scoring event corresponding to the first type candidate account.

The similarity between the first result data and the second interaction data and each standard scoring event is calculated, a standard scoring event corresponding to the maximum similarity is obtained, and the standard scoring event is used as a target standard scoring event; or judging whether at least one standard scoring event with the similarity larger than a preset threshold exists, and if so, taking the standard scoring event with the similarity larger than the preset threshold with the first result data and the second interaction data as a target standard scoring event.

In this embodiment, the second interaction data and the second result data in the game pair between the account to be recommended and the corresponding friend account are analyzed to determine an influence event of adding the friend account to the account to be recommended, and the influence event is used as a standard scoring event to analyze the first result data of the game pair and the first interaction data of the first candidate account and the account to be recommended in the game pair, so as to determine the scoring event of the first candidate account.

Illustratively, referring to fig. 6, fig. 6 is a flowchart of step S102 in an exemplary embodiment of the embodiment shown in fig. 3, and as shown in fig. 6, step S102 includes steps S201-S203, and the detailed description refers to the following:

step S201: and obtaining the occurrence times and the occurrence time corresponding to the scoring event corresponding to the account to be recommended.

The number of occurrences of the scoring event corresponds to the number of occurrences of the game event within a preset time period, and similarly, the occurrence time of the scoring event corresponds to the occurrence time point of the scoring event, and it can be understood that if the scoring event occurs multiple times within the preset time period, each occurrence time of the scoring event corresponds to one occurrence time.

For example, if the scoring event occurs multiple times within the preset time period, the occurrence time corresponding to the scoring event is an average time point corresponding to the time points when the multiple scoring events occur. For example, the scoring event occurs twice before and after the preset time period, the time point of the former corresponding occurrence is the whole number 8 of the 10 month No. 1 in 2020, the time point of the latter corresponding occurrence is the whole number 8 of the 10 month No. 7 in 2020, and the time of the corresponding occurrence of the scoring event is the whole number 8 of the 10 month No. 3 in 2020.

Step S202: and updating the initial weight corresponding to the scoring event based on the occurrence times and the occurrence time to obtain the weight corresponding to the scoring event.

In this embodiment, the initial weight is determined by the total number of friend accounts corresponding to the target criteria scoring event. And confirming whether each friend account of the accounts to be recommended corresponds to a target standard scoring event or not, and counting the total number of the friend accounts corresponding to the target standard scoring event. Illustratively, the ratio of the total number of friend accounts corresponding to the target standard scoring event to the total number of all friend accounts is taken as the initial weight of the scoring event.

In this embodiment, the weight corresponding to the scoring event indicates the probability that the account to be recommended adds the first type candidate account as a friend based on the scoring event, and the larger the weight is, the larger the probability that the account to be recommended adds the first type candidate account as a friend is, and otherwise, the smaller the weight is, the smaller the probability that the account to be recommended adds the first type candidate account as a friend is.

Since the magnitude of the weight corresponding to the scoring event is closely related to the occurrence time and the number of times of transmission corresponding to the scoring event, for example, the more the number of times of occurrence of the scoring event is, the shorter the time length of occurrence of the scoring event from the current time is, the greater the weight is, and conversely, the smaller the weight is. Therefore, in order to more accurately determine the influence of the scoring event, the embodiment determines the weight corresponding to the scoring event based on the occurrence times and the occurrence times, and when the number of the scoring events is a plurality of, calculates the weighted sum of the scoring event and the weight to obtain the first scoring value.

Referring to fig. 7, an exemplary embodiment of the present application is shown in fig. 7, where the weight corresponding to a standard scoring event is affected by a time factor and a frequency factor, and as shown in fig. 7, the standard scoring event includes "to-be-recommended account" to be a candidate account B of a first type, where the initial weight of the standard scoring event is 1, and if the scoring event corresponding to the candidate account of the first type includes the standard scoring event, the initial weight corresponding to the scoring event is 1; the standard scoring event comprises that a first type candidate account B is praise of an account A to be recommended, wherein the initial weight of the standard scoring event is 0.6;

as shown in fig. 7, the standard scoring event further includes a "winning game and a drop combination", where the "winning game and the drop combination" are result data of the game, and represent that the first type candidate account and the account to be recommended are players that win together, and the first type candidate account and the account to be recommended are a drop combination relationship in the game. Wherein the initial weight for the standard scoring event is 0.25.

As shown in fig. 7, the standard scoring event further includes "winning game, and threshing +up/middle road", where "winning game, threshing +up/middle road" is the result data of the game, and indicates that the first type candidate account and the account to be recommended are players that win together, and the first type candidate account and the account to be recommended are a combination relationship of threshing +up road or a combination relationship of threshing +middle road in the game. Wherein the initial weight corresponding to the standard scoring event is 0.22.

As shown in fig. 7, the standard scoring event also includes a "winning game, other combinations," where "winning game, other combinations" are the outcome data of the game's game, indicating that the first type candidate account number and the account number to be recommended are co-winning players, and the first type candidate account and the account to be recommended are other combinations except for the combination relationship of the wild + the upper road, the combination relationship of the wild + the middle road and the combination of the winning game and the lower road in the game pair. Wherein the initial weight corresponding to the standard scoring event is 0.2.

As shown in fig. 7, the standard scoring event further includes "the first type candidate account B is a own MVP", where "the first type candidate account B is a own MVP" is result data of the game play, and the initial weight corresponding to the standard scoring event is 0.6.

As shown in fig. 7, the standard scoring event further includes "the first type candidate account B is cross-paired with the account a to be recommended", and the initial weight corresponding to the standard scoring event is 0.1.

As shown in fig. 7, the standard scoring event further includes "the first type candidate account B is a loser's teammate", where "the first type candidate account B is a loser's teammate" indicates that the first type candidate account B and the account a to be recommended are both losers, and the initial weight corresponding to the standard scoring event is-0.1.

As shown in fig. 7, the standard scoring event further includes "the first class candidate account B and the account to be recommended have a common friend", where an initial weight corresponding to the standard scoring event is 0.8.

It can be understood that the initial weight corresponding to the standard scoring event reflects the influence of the corresponding scoring event on scoring the first class candidate account, and if the initial weight corresponding to the standard scoring event is larger, the influence is larger, otherwise, the influence is smaller. However, if the scoring event corresponding to the first type candidate account includes any one of the standard scoring events, the occurrence time and the occurrence frequency corresponding to each scoring event affect the weight corresponding to the scoring time.

As shown in fig. 7, the time decay function characterizes that the initial weight corresponding to each scoring event is affected by a time factor, that is, the time length of the current time distance corresponding scoring event is brought into the time decay function, so as to obtain a decayed weight, the weight corresponding to the scoring event decreases with the increase of the time length of the current time distance corresponding scoring event, in addition, the slope of the time decay function decreases with the increase of the time length of the current time distance corresponding scoring event, which means that the decreasing speed of the weight corresponding to the scoring event with the increase of the time length of the current time distance corresponding scoring event is slower, and it should be noted that, as long as the function meeting the characteristics can be used as the time decay function of the embodiment, the time decay function is not specifically limited, for example, the time decay function is y=1/x, and the like.

As shown in fig. 7, the number addition function characterizes that the initial weight corresponding to each scoring event is affected by the number factor, that is, the number of times the scoring event occurs is brought into the number addition function to obtain an added weight, as shown in fig. 7, the weight corresponding to the scoring event increases with the increase of the number of times the scoring event occurs, in addition, the slope of the number addition function slowly increases with the increase of the number of times the scoring event occurs at first and then slowly increases, which means that the speed of the increase of the weight corresponding to the scoring event with the increase of the number of times the scoring event occurs is firstly slowly and then slowly increases and finally slowly increases, and it should be noted that, as long as the function meeting the characteristics can be used as the number addition function of the embodiment, the method is not particularly limited herein.

Illustratively, referring to fig. 8, fig. 8 is a flowchart of step S202 in an exemplary embodiment of the embodiment shown in fig. 6, and as shown in fig. 8, step S202 includes steps S301-S303, and the detailed description refers to the following:

step S301: and acquiring an addition factor and a decay factor of the initial weight corresponding to the scoring event.

In this embodiment, the addition factor increases as the number of times of occurrence of the scoring event increases, wherein the addition factor is a positive number, the attenuation factor increases as the length of time between the time of occurrence of the scoring event and the current time increases, and the attenuation factor is a negative number.

The decay factor is a function of the time length between the time of occurrence of the scoring event and the current time, which may be called as a decay function, and the present embodiment may flexibly set the decay function according to the actual application scenario, which is not specifically limited herein, for example, the decay function is y= -x, y= -x ² The method comprises the steps of carrying out a first treatment on the surface of the The addition factor is a function of the number of times of occurrence of the scoring event, which may be called as an addition function, and similarly, the embodiment may flexibly set the addition function according to the actual application scenario, where the addition function is not specifically limited, for example, y=x ² 。

Step S302: the first weight is calculated based on a preset initial weight and an addition factor, and the second weight is calculated based on the initial weight and an attenuation factor.

In this embodiment, an initial weight is set in advance for the scoring event, and then the initial weight is updated based on the addition factor and the attenuation factor, and illustratively, the initial weight and the addition factor are added to obtain a first weight, and the initial weight and the attenuation factor are added to obtain a second weight.

Step S303: and calculating a weighted sum of the first weight and the second weight, and taking the weighted sum as the weight corresponding to the scoring event.

In consideration of the fact that the degree of influence of the event factor and the number factor on the weight may be different, after the first weight and the second weight are obtained, the present embodiment may set a first sub-weight for the first weight representing the number factor, set a second sub-weight for the second weight representing the time factor, and calculate a weighted sum of the first weight and the second weight based on the first sub-weight and the second sub-weight, and use the weighted sum as the weight corresponding to the scoring event.

Step S203: and calculating a weighted sum of the scoring event and the weight corresponding to the scoring event to obtain a first scoring value.

In this embodiment, on the one hand, the initial weight corresponding to the scoring event is determined by using the total number of friend accounts corresponding to the target standard scoring event, so that the initial weight corresponding to the scoring event is associated with the friend accounts of the accounts to be recommended, that is, if the total number of friend accounts corresponding to the target standard scoring event is larger, the initial weight corresponding to the scoring event is higher, which means that the probability that the account to be recommended adds the first type candidate account as a friend is higher, so that the accuracy of scoring the scoring event can be improved; on the other hand, the influence of the time factor and the frequency factor of the occurrence of the scoring event on the weight of the scoring event is fully considered, namely, the initial weight corresponding to the scoring event is updated based on the time factor and the frequency factor, so that the weight of the scoring event can be measured more accurately, the matching degree of the obtained scoring value and the account to be recommended is higher, and the probability that the account to be recommended adds the first type candidate account as a friend is improved.

Referring to fig. 9, fig. 9 is a flowchart of a game account recommending method according to the embodiment shown in fig. 3, and after step S103, the game account recommending method according to the embodiment further includes steps S401 to S402, which are described in detail below:

Step S401: and obtaining a second type candidate account which does not participate in the game with the account to be recommended.

In the embodiment shown in fig. 3, a part of game accounts from the first type candidate accounts which participate in the game with the account to be recommended are screened out and are recommended to the account to be recommended as friend recommendation accounts.

In an exemplary embodiment, a first type candidate account number which participates in a game with an account number to be recommended is obtained through historical game play data corresponding to the account number to be recommended, and a second type candidate account number which does not participate in the game with the account number to be recommended is screened out based on the first type candidate account number which participates in the game with the account number to be recommended.

Step S402: and recommending the second type candidate account meeting the preset recommendation condition to the object to be recommended.

In this embodiment, a part of game accounts which do not participate in a game with a recommended account are screened as friend recommendation accounts and recommended to the to-be-recommended account, where, for example, historical search data of the to-be-recommended account is obtained, the historical search data includes historical search conditions of a user, for example, the historical search data shows that the to-be-recommended account has been searched for the game accounts through the segment for multiple times, and the searched game accounts are added as friends, so that in this embodiment, a part of game accounts which do not participate in the game with the recommended account together can be screened, and the game accounts with the same segment as the to-be-recommended account can be screened from the game accounts which do not participate in the game with the recommended account and recommended to the to-be-recommended account.

According to the method, after friend recommendation accounts are generated for the to-be-recommended accounts based on the first type candidate accounts which participate in the game with the to-be-recommended accounts together and are recommended to the to-be-recommended accounts, friend recommendation accounts are generated for the to-be-recommended accounts in a supplementing mode based on the second type candidate accounts which do not participate in the game with the to-be-recommended accounts together and are recommended to the to-be-recommended accounts, and diversified recommendation is achieved.

Referring to fig. 10, fig. 10 is a flowchart of step S402 in the embodiment shown in fig. 9 in an exemplary embodiment, and as shown in fig. 10, step S402 includes steps S501-S502, and the detailed description refers to the following:

step S501: and scoring the second class candidate account based on the attribute information of the second class candidate account to obtain a second scoring value.

In the present embodiment, the attribute information includes at least one of login area information, online time information, segment information, and game character information. In this embodiment, a page for setting attribute information may be provided for an account to be recommended, referring to fig. 11, fig. 11 is a schematic diagram of an attribute information setting page shown in an exemplary embodiment of the present application, where, as shown in fig. 11, the attribute information setting page includes a game role setting option, a login area setting option, an online time setting option, and a segment setting option, the account to be recommended may set the options and further set corresponding attribute information in a user-defined manner, and finally, the user may set the account by clicking a confirmation option.

The login area information comprises login areas corresponding to the second type of candidate accounts, if the login areas corresponding to the second type of candidate accounts comprise at least two login areas, each login area corresponds to one login frequency, the login area with the largest login frequency in a preset time period is matched with the login area information of the account to be recommended, and similarly, if the login area corresponding to the account to be recommended comprises a plurality of login areas, the login area with the largest login frequency is matched with the login area corresponding to the second type of candidate accounts.

In consideration of the fact that the account to be recommended is more prone to adding login area information, online time information, segment information and game role information which are the same as or similar to the account to be recommended as friends relative to strangers, the probability of adding the second type candidate account to the account to be recommended as friends can be improved.

In an exemplary embodiment, the second type candidate account may be scored by respectively matching the login area information, the online time information, the segment information, the game role information corresponding to the account to be recommended with the login area information, the online time information, the segment information and the game role information corresponding to the second type candidate account, and scoring the second type candidate account according to the matching result to obtain a second scoring value.

For example, if the login area information corresponding to the account to be recommended is matched with the login area information corresponding to the second type candidate account, the second score value corresponding to the second type candidate account is A1; if the login area information corresponding to the account to be recommended is matched with the login area information corresponding to the second type candidate account, the online time information corresponding to the account to be recommended is matched with the online time information corresponding to the second type candidate account, and the second grading value corresponding to the second type candidate account is A2; if the login area information corresponding to the account to be recommended is matched with the login area information corresponding to the second type candidate account, the online time information corresponding to the account to be recommended is matched with the online time information corresponding to the second type candidate account, and the segment information corresponding to the account to be recommended is matched with the segment information corresponding to the second type candidate account, the second grading value corresponding to the second type candidate account is A3; if the login area information corresponding to the account to be recommended is matched with the login area information corresponding to the second type candidate account, the online time information corresponding to the account to be recommended is matched with the online time information corresponding to the second type candidate account, the segment information corresponding to the account to be recommended is matched with the segment information corresponding to the second type candidate account, the game role information corresponding to the account to be recommended is matched with the game role information corresponding to the second type candidate account, and the second scoring value corresponding to the second type candidate account is A4, wherein A4 is greater than A3 and A2 is greater than A1.

For example, if it is detected that the online time information corresponding to the account to be recommended overlaps with the online time information corresponding to the second type candidate account, it indicates that the online time information corresponding to the account to be recommended matches with the online time information corresponding to the second type candidate account, for example, the online time information corresponding to the account to be recommended is 10 to 12 am every day, the online time information corresponding to the second type candidate account is 11 to 14 pm every day, and the online time information corresponding to the account to be recommended matches with the online time information corresponding to the second type candidate account.

The login area information may include a login area corresponding to the account to be recommended or the second type candidate account, where the login area may be a country, for example, the login area is a country a, a country B, or the like, or may be a cultural area formed by a plurality of countries, the login area is a cultural area formed by a country a and a country B, or may be a preferred connection server as a distinction degree, where the preferred connection server is a server that is most likely to be connected to the client device when the client device logs in the game application program in the game account, for example, the preferred connection server is a server closest to the current geographic position of the client device, so if the preferred connection server is used as a distinction degree, if the account to be recommended is the same as the preferred connection server of the second type candidate account, it is determined that the login area information corresponding to the account to be recommended is matched with the login area information corresponding to the second type candidate account.

The login area information includes at least one of login country, login cultural area and preferred connection server corresponding to the account to be recommended or the second type candidate account. For example, if the login area information includes one of a login country, a login culture area and a preferred connection server, when the account to be recommended is the same as the login country or the login culture area or the preferred connection server corresponding to the second type candidate account, it is determined that the login area information corresponding to the account to be recommended is matched with the login area information corresponding to the second type candidate account.

If the login area information includes a login country, a login culture area and a preferred connection server, and the login culture area corresponding to the account to be recommended and the second type candidate account is the same as the preferred connection server, it is determined that the login area information corresponding to the account to be recommended is matched with the login area information corresponding to the second type candidate account.

For example, scoring is performed on the login area information corresponding to the second type candidate account, and if the obtained scoring value is greater than the preset threshold, it is determined that the login area information corresponding to the account to be recommended matches the login area information corresponding to the second type candidate account, and referring to fig. 12, for example, fig. 12 is a schematic diagram of scoring criteria of the login area information shown in an exemplary embodiment of the present application, as shown in fig. 12, scoring is performed on the login area information corresponding to the second type candidate account based on the login country, the cultural area, and the preferred connection server corresponding to the second type candidate account, where the server scoring the login area information corresponding to the second type candidate account may be different according to the server connected to the game account recommendation device, for example, zoneSvr a, zoneSvr B, … …, zoneSvr N, and the like, which are not particularly limited herein.

If the server ZoneSvr a scores the login area information corresponding to the second type candidate account, if the login country corresponding to the second type candidate account is the same as the login country corresponding to the account to be recommended, the score value is A1, if the login cultural area corresponding to the second type candidate account is the same as the login cultural area corresponding to the account to be recommended, the score value is B1, and if the preferred connection server corresponding to the second type candidate account is the same as the preferred connection server corresponding to the account to be recommended, the score value is C1, it can be understood that when the login area information corresponding to the second type candidate account is scored, if the login area information corresponding to the second type candidate account meets at least two of the three conditions, the score values of the corresponding conditions are directly added to obtain the score value of the login area information corresponding to the second type candidate account. For example, if the login country and the login culture area corresponding to the second type candidate account are the same as the account to be recommended, the score value of the login area information corresponding to the second type candidate account is a1+b1.

And if the login area information corresponding to the second type candidate account is the same as the login country corresponding to the account to be recommended, the score value is A2, if the login cultural area corresponding to the second type candidate account is the same as the login cultural area corresponding to the account to be recommended, the score value is B2, and if the preferred connection server corresponding to the second type candidate account is the same as the preferred connection server corresponding to the account to be recommended, the score value is C2.

And if the login area information corresponding to the second type candidate account is the same as the login country corresponding to the account to be recommended, the score value is An, if the login area information corresponding to the second type candidate account is the same as the login cultural area corresponding to the account to be recommended, the score value is Bn, and if the preferred connection server corresponding to the second type candidate account is the same as the preferred connection server corresponding to the account to be recommended, the score value is Cn.

Step S502: and if the second grading value is larger than a second preset threshold value, recommending the second class candidate account to the account to be recommended.

In the embodiment, after the number of friend recommendation accounts obtained by the method in the embodiment shown in fig. 3 reaches a certain value, the game accounts are recommended for the accounts to be recommended based on social attributes such as online time information, login area information, segment information, game role information and the like, diversified selection is provided for the accounts to be recommended, and user experience is improved.

Referring to fig. 13, fig. 13 is a flowchart of a game account recommending method according to the embodiment shown in fig. 3, and as shown in fig. 13, after step S101, the game account recommending method according to the embodiment further includes steps S601 to S602, which are described in detail below:

Step S601: and matching the first type candidate account with a blacklist and a friend list corresponding to the account to be recommended respectively.

In this embodiment, a blacklist and a friend list corresponding to the account to be recommended are stored in advance, the blacklist is used for storing all game accounts which participate in the game with the account to be recommended and are blacked by the account to be recommended, and the friend list is used for storing all game accounts which participate in the game with the account to be recommended and are added as friends by the account to be recommended.

For example, whether the first type candidate account is included in the blacklist and the friend list is determined, if the first type candidate account is included in the blacklist, it indicates that the first type candidate account has been blacked out by the account to be recommended, in which case the probability that the account to be recommended adds the first type candidate account as a friend is usually zero or very low, so that in this case, no subsequent recommendation step is performed to save computer processing resources. Similarly, if the first type candidate account is included in the friend list, the first type candidate account is indicated to be a friend of the account to be recommended, and in this case, it is obviously unnecessary to recommend the first type candidate account to the account to be recommended.

Step S602: and if the matching is unsuccessful, scoring the first type candidate account according to a scoring event corresponding to the first type candidate account to obtain a first scoring value.

In this embodiment, if the first type candidate account is not matched with the blacklist and the friendly list corresponding to the account to be recommended, it is indicated that the first type candidate account is not included in the blacklist and the friendly list, and the first type candidate account can be recommended to the account to be recommended as the candidate account.

If the first type candidate account is not matched with the blacklist and the friendly list corresponding to the account to be recommended, judging whether the first type candidate account is an artificial intelligent machine account or a nonsensical candidate account of negative behaviors, and if so, executing the step of scoring the first type candidate account according to a scoring event corresponding to the first type candidate account. Where the nonsensical candidate account number of negative behavior indicates that the game account number is present in the game play, such as, for example, stationary for a long period of time, exiting the game play midway, or deliberately inputting to an opponent.

According to the game account recommending method, when the fact that the first type candidate account is not in the blacklist or the friend list is confirmed, the step of scoring the first type candidate account according to scoring events corresponding to the first type candidate account is carried out, namely when the fact that the first type candidate account is blacked by the account to be recommended or is a friend of the account to be recommended is confirmed, the first type candidate account is not recommended to the account to be recommended as the friend recommending account, and therefore invalid recommendation is avoided, computer processing resources are wasted, and processing time is prolonged.

Referring to fig. 14, fig. 14 is a flowchart of a game account recommending method according to the embodiment shown in fig. 3, and as shown in fig. 14, after step S103, the game account recommending method according to the embodiment further includes steps S701 to S702, which are described in detail below:

step S701: recommendation reasons are generated based on the scoring event.

In this embodiment, after the candidate recommendation account is recommended to the account to be recommended as the friend recommendation account, a recommendation reason corresponding to the first type candidate account is generated and sent for the account to be recommended, so that the account to be recommended refers to the recommendation reason to add friends, and user experience is improved.

In the present embodiment, the recommendation reason is generated based on the scoring event.

Illustratively, referring to fig. 15, fig. 15 is a flowchart of an exemplary embodiment of step S701 in the embodiment shown in fig. 14, and as shown in fig. 15, step S701 includes steps S21-S23, which are described in detail below:

step S21: and matching the scoring event with the recommendation reason template list to obtain a recommendation reason template corresponding to the scoring event.

In this embodiment, a plurality of preset recommendation reason templates are configured and a recommendation reason template list is formed based on the recommendation reason templates, and each recommendation reason template includes a plurality of template parameters to be determined. In this embodiment, the scoring event is matched with each recommendation reason template list, so as to obtain a recommendation reason template corresponding to the scoring event.

The template parameters included in the recommendation reason template are different according to different recommendation reason templates, for example, the recommendation reason template is "you give a candidate account of the first type" to get praise, "the candidate account of the first type" is the template parameter, and in the actual application scene, the template parameter [ candidate account of the first type ] is changed into a specific game account; illustratively, the recommendation reason template is "you praise the [ first type candidate account at [ time point ]," and includes two template parameters, namely [ time point ] and [ first type candidate account ]; for example, the recommendation reason template is "you praise the [ first type candidate account at [ time point 1] and [ time point 2], and includes three template parameters, namely [ time point 1], [ time point 2] and [ first type candidate account ], where it is to be noted that if the scoring event corresponding to the first type candidate account includes two or more scoring events, a corresponding recommendation reason may be generated for each scoring event, which is not limited herein.

For example, if the scoring event corresponding to the first type candidate account includes two or more scoring events, a recommendation reason corresponding to the first type candidate account is generated according to each scoring event and the weight corresponding to each scoring event. Illustratively, the recommendation reason template is "[ first class candidate account number ] to praise you, and the corresponding weight is [ weight 1]; the candidate account number of the first type is the counterpart MVP, the corresponding weight is weight 2', and the recommendation reason template comprises three template parameters which are respectively weight 1, weight 2 and first type candidate account number.

Illustratively, the similarity between the scoring event and each recommendation reason template is calculated, and the recommendation reason template with the largest similarity is used as the recommendation reason template corresponding to the scoring event.

Step S22: and determining the value of the template parameter of the recommendation reason template corresponding to the grading event based on the first result data and the first interaction data.

In this embodiment, since the scoring event corresponding to the first type candidate account does not include information about the first type candidate account, time information of game play in which the first type candidate account and the account to be recommended participate together, and the like, and the first result data and the first interaction data necessarily include the above information, the present embodiment determines the value of the template parameter of the recommendation reason template corresponding to the scoring event based on the first result data and the first interaction data.

For example, the scoring event corresponding to the first type candidate account is a combination of winners and a wild adding road, and if the scoring event corresponding to the scoring event is a combination of a to-be-recommended account and a first type game account, wherein the first type game account is a template parameter, and at this time, a recommendation reason can be obtained by determining a value of the first type game account based on the first interaction data and the first result data.

Step S23: and carrying the template parameter value into a recommendation reason template corresponding to the scoring event to obtain recommendation reasons.

For example, the recommendation reason template corresponding to the scoring event is [ first class game account number ] and is praise [ number ] times of the account number to be recommended, and the recommendation reason template includes two template parameters, namely [ first class game account number ] and [ number ] times, for example, based on the first result data and the first interaction data, it can be determined that [ first class game account number ] is 00001 and [ number ] is 2, and the generated recommendation reason is 00001 and praise 2 times of the account number to be recommended.

Step S702: and sending the recommendation reason to the account to be recommended.

The method includes the steps of associating a recommendation reason with a first type of candidate account, and then sending the associated recommendation reason to the account to be recommended so that the account to be recommended can determine the recommendation reason corresponding to each friend recommendation account. For example, UI design (User Interface design) is performed on a plurality of friend recommendation accounts and recommendation reasons corresponding to each friend recommendation account in advance, so that each friend physical examination account and corresponding recommendation reasons are associated, and further the to-be-recommended account can determine the recommendation reason corresponding to each friend recommendation account on the display Interface. By way of example, through UI design, display positions are designed for each friend recommendation account and corresponding recommendation reasons, and the display positions of the recommendation reasons corresponding to each friend recommendation account are designed to be at preset distances from the display positions of the corresponding friend recommendation accounts.

The UI design refers to the overall design of man-machine interaction, operation logic and attractive interface of software. UI designs are classified into physical UIs and virtual UIs.

Referring to fig. 16, an exemplary embodiment of the present application is shown in fig. 16, where, after an account to be recommended triggers a "recommendation" option, the friend recommendation account page displays a friend recommendation account generated for the account to be recommended and a recommendation reason corresponding to each friend recommendation account, as shown in fig. 16, where, the friend recommendation account corresponding to the account to be recommended includes a game account 1, the recommendation reason is "you have praised the game account 1", and the account to be recommended may add the game account 1 as a friend by triggering a "+" option; the friend recommendation account corresponding to the account to be recommended comprises a game account 2, wherein the recommendation reason is that the game account 2 is praise for you, and the account to be recommended can add the game account 2 as a friend by triggering a "+" option; the friend recommendation account corresponding to the account to be recommended comprises a game account 3, the recommendation reason is that the technical levels are similar, and the account to be recommended can add the game account 3 as a friend by triggering a "+" option; the friend recommendation account corresponding to the account to be recommended comprises a game account 4, the recommendation reason is that the technical levels are similar, the account to be recommended can be used for adding the game account 4 into friends by triggering a "+" option, wherein the "technical levels are similar" can be represented by segment information of the account to be recommended and the candidate account, and the method is not particularly limited.

In this embodiment, the account to be recommended may jump the sum page to the attribute information setting page by triggering the my tag option to set the attribute information of the account to be recommended; the account to be recommended can be switched to other friend recommendation accounts by triggering a rearranging option.

According to the game account recommending method, the first recommending reason corresponding to the first type candidate account is sent to the account to be recommended, so that friends are added to the account to be recommended according to the recommending reason, and user experience is improved.

Fig. 17 is a block diagram of a game account recommending apparatus according to an exemplary embodiment of the present application, and as shown in fig. 17, a game account recommending apparatus 800 includes a first obtaining module 801, a scoring module 802, and a first recommending module 803.

The first obtaining module 801 is configured to obtain a first type candidate account that participates in a game with an account to be recommended; the scoring module 802 is configured to score the first type candidate account according to a scoring event corresponding to the first type candidate account, so as to obtain a first scoring value, where the scoring event is determined by result data of the game and interaction data of the first type candidate account and the account to be recommended in the game; the first recommendation module 803 is configured to recommend the candidate recommendation account as a friend recommendation account to the account to be recommended if the first score value is greater than a first preset threshold.

The game account recommending device provided by the embodiment utilizes the scoring module 802 to score the first type candidate accounts which participate in the game pair with the account to be recommended, and utilizes the first recommending module 803 to determine whether to send the first type candidate accounts to the account to be recommended as friend recommending accounts according to the obtained first scoring value, wherein the interaction data of the account to be recommended and the first type candidate accounts in the game pair and the result data of the game pair are used as scoring factors to score the first type candidate accounts, so that the matching degree between the first type candidate accounts and the account to be recommended can be improved, and the probability that the account to be recommended adds the first type candidate accounts as friends can be improved.

In another exemplary embodiment, the game account recommending device 800 provided in this embodiment further includes a second obtaining module, a generating module, and a first matching module, where the second obtaining module is configured to obtain second interaction data and second result data between the account to be recommended and the corresponding friend account in the game; the generation module is used for generating a plurality of standard scoring events based on the second interaction data and the second result data; and the first matching module is used for taking the target standard scoring event as the scoring event corresponding to the first type candidate account if the target standard scoring event is matched with the first result data and the second interaction data.

In another exemplary embodiment, the scoring module 802 includes a first obtaining unit, a first scoring unit, and a calculating unit, where the first obtaining unit is configured to obtain the occurrence times and the occurrence times corresponding to the scoring event; the first scoring unit is used for updating initial weights corresponding to scoring events based on the occurrence times and the occurrence time to obtain weights corresponding to the scoring events, wherein the initial weights are determined by the total number of friend accounts corresponding to target standard scoring events; the calculating unit is used for calculating the weighted sum of the scoring event and the weight corresponding to the scoring event to obtain a first scoring value.

In another exemplary embodiment, the first scoring unit includes an obtaining subunit, a first calculating subunit, and a second calculating subunit, where the obtaining subunit is configured to obtain an addition factor and an attenuation factor corresponding to the initial weight, the addition factor increasing as the number of times of occurrence of the scoring event increases, the attenuation factor increasing as a length of time between a time of occurrence of the scoring event and a current time increases; the first calculating subunit is used for calculating a first weight based on a preset initial weight and an addition factor, and calculating a second weight based on the initial weight and an attenuation factor; the second calculating subunit is configured to calculate a weighted sum of the first weight and the second weight, and use the weighted sum as the weight corresponding to the scoring event.

The game account recommending device 800 provided in this embodiment fully considers the time factor and the frequency factor of occurrence of the scoring event, and can measure the weight of the scoring event more accurately, so that the matching degree between the obtained scoring value and the account to be recommended is higher, and the probability that the account to be recommended adds the first type candidate account as a friend is improved.

In another exemplary embodiment, the game account recommending apparatus 800 provided in this embodiment further includes a third obtaining module and a second recommending module, where the third obtaining module is configured to obtain a second type of candidate account that does not participate in a game with the account to be recommended; the second recommendation module is used for recommending the second type candidate account meeting the preset recommendation condition to the object to be recommended.

In this embodiment, after the number of friend recommendation accounts obtained by the game account recommendation device 800 in the embodiment shown in fig. 17 reaches a certain value, game accounts are recommended for the accounts to be recommended based on social attributes such as online time, login area, segment information, game character preference, and the like, diversified selections are provided for the accounts to be recommended, and user experience is improved.

In another exemplary embodiment, the game account recommending apparatus 800 provided in this embodiment further includes a second matching module and an executing module, where the second matching module is configured to match the first type of candidate account with a blacklist and a friend list corresponding to the account to be recommended, respectively; and the execution module is used for executing the step of scoring the first type candidate account according to the scoring event corresponding to the first type candidate account if the matching is unsuccessful.

The game account recommending device 800 provided in this embodiment performs the step of scoring the first type candidate account according to the scoring event corresponding to the first type candidate account when confirming that the first type candidate account is not in the blacklist or the friend list, that is, when confirming that the first type candidate account has been blacked by the account to be recommended or has been a friend of the account to be recommended, does not recommend the first type candidate account as the friend recommending account to the account to be recommended, thereby avoiding invalid recommendation, wasting computer processing resources and prolonging processing time.

In another exemplary embodiment, the game account recommending apparatus 800 provided in this embodiment further includes a generating module and a sending module, where the generating module is configured to generate a recommendation reason based on the scoring event; the sending module is used for sending the recommendation reason to the account to be recommended.

In another exemplary embodiment, the generating module includes a matching unit, a determining unit and a substituting unit, where the matching unit is configured to match the scoring event with a recommendation reason template list to obtain a recommendation reason template corresponding to the scoring event, the recommendation reason template list includes a plurality of preset recommendation reason templates, and each recommendation reason template includes a plurality of template parameters; the determining unit is used for determining the value of the template parameter of the recommendation reason template corresponding to the scoring event based on the first result data and the first interaction data; the substituting unit is used for substituting the template parameter value into the recommendation reason template corresponding to the scoring event to obtain the recommendation reason.

The game account recommending device 800 provided in this embodiment sends the first recommendation reason corresponding to the first type candidate account to the account to be recommended, so that the account to be recommended refers to the recommendation reason to add friends, and user experience is improved.

It should be noted that, the apparatus provided in the foregoing embodiments and the method provided in the foregoing embodiments belong to the same concept, and the specific manner in which each module and unit perform the operation has been described in detail in the method embodiments, which is not repeated herein.

Participation in fig. 18, fig. 18 is a block diagram of a game account recommendation system according to an exemplary embodiment of the present application, and as shown in fig. 18, a game account recommendation system 900 includes a client device 901 and a server device 902.

The client device 901 includes a login module, a matching module, a log-in module, a settlement module, a social label setting module, and a friend recommendation module.

The login module is used for responding to the account to be recommended to log in the game application program; the matching module is used for matching the account to be recommended with the game account which participates in the game after requesting the game for the account to be recommended; the game checking module is used for responding to the account to be recommended and performing game checking operation with the matched game account; the settlement module is used for generating a settlement event corresponding to each game account in the game play process after the game play is finished.

The settlement event includes an event reflecting the game score of the corresponding game account, for example, the settlement event includes the total number of defeating opponents in the game pair of the corresponding game account, the total number of being assisted in the game pair of the corresponding game account, the corresponding game account being a KDA, wherein the KDA is a ratio of the total sum of the number of assisted and defeated opponents to the death number, the corresponding game account being an MVP, wherein the MVP is the game account with the highest KDA value, the winner MVP is the game player with the highest KDA of the current winner, and the loser MVP is the game account with the highest KDA of the loser. When the KDA is highest in parallel in the game pair, the highest total number of defeating opponents is MVP, and if the total number of defeating opponents is the same, the cash amount is compared.

The social label setting module is configured to respond to an instruction for changing or updating a social label triggered by the account to be recommended, and update social label information of the account to be recommended based on the instruction, where the social label information includes, but is not limited to, role information of a game, segment information of the game, login area information of the game, online information of the game, a preferred connection server, and the like, and is not limited in detail herein.

The friend recommendation module is configured to obtain a friend recommendation list from the server device 902, and display the friend recommendation list to the account to be recommended, so that the account to be recommended selects a game account from the friend recommendation list to perform friend adding operation.

The server device 902 includes a game information pulling module, a friend recommendation algorithm module, a supplementary recommendation player module, an attribute condition setting module, and a cache module.

The cache module is used for acquiring and storing game play information from the play module, and the data storage pressure of the server device 902 is reduced by setting the cache module, so that the game account recommending system 900 can use the game play information, social label information corresponding to the account to be recommended, friend recommending list and other data, and the other modules query the cache module when using the data by setting the cache module, thereby greatly reducing the pressure of the server device 902 database storage system and reducing the operation and maintenance cost.

The game information pulling module is used for pulling game information and the like from the cache module; the friend recommendation algorithm module is used for generating a corresponding friend recommendation account for the account to be recommended based on the opposite office information sent by the opposite office information receiving and pulling module, and the friend recommendation accounts form a friend recommendation list.

The friend recommendation algorithm module is used for acquiring candidate accounts which participate in game play together with the account to be recommended; scoring the candidate account according to scoring events corresponding to the candidate account to obtain scoring values, wherein the scoring events are determined by result data of game games and interaction data of the candidate account and the account to be recommended in the game games; and if the grading value is larger than a preset threshold, recommending the candidate account as a friend recommendation account to the account to be recommended. The game information comprises game result data and interaction number data of the candidate account number and the account number to be recommended in the game.

The attribute information condition setting module is used for acquiring the attribute information of the account to be recommended or the candidate account from the social label setting module, setting preset conditions which are required to be met by the attribute information corresponding to the candidate account, and storing the attribute information corresponding to the candidate account as a friend recommending account and a friend recommending list when the attribute information corresponding to the candidate account meets the preset conditions.

The supplementary recommendation player module is used for acquiring social label information of an account to be recommended or a candidate account from the attribute information condition setting module, generating the account to be recommended to generate a corresponding friend recommendation account based on the social label information of the account to be recommended or the candidate account and the candidate account which does not participate in a game with the account to be recommended together, and adding the friend recommendation account obtained by supplementation to a friend recommendation list.

The supplementary recommendation player module is used for adding one to the accumulated quantity of friend recommendation accounts corresponding to the accounts to be recommended; if the obtained accumulated quantity is larger than a preset threshold value, obtaining candidate accounts which do not participate in game play together with the account to be recommended; and recommending the candidate account numbers meeting the preset recommendation conditions to the object to be recommended. Recommending the candidate account meeting the preset recommendation condition to the object to be recommended comprises scoring the candidate account based on attribute information of the candidate account to obtain a scoring value, wherein the attribute information comprises at least one of login area information, online time information, segment information and game role information; and if the grading value is larger than a preset threshold value, recommending the candidate account to the account to be recommended.

After the login module logs in the game application program in response to the account to be recommended, the settlement module initiates a settlement operation after the game is played, or after the social label setting module responds to an instruction for changing or updating the social label triggered by the account to be recommended, and further updates social label information of the account to be recommended based on the instruction, a friend recommendation instruction is sent to the server device 902, specifically, a friend recommendation instruction is sent to the game play information pulling module, so that the game play information pulling module obtains game play information from the cache module.

The game account recommendation system 900 provided in this embodiment scores candidate accounts that participate in a game pair with an account to be recommended, determines whether to send the candidate accounts to the account to be recommended as friend recommendation accounts according to the obtained score value, and scores a first class candidate account by taking interaction data of the account to be recommended and the candidate accounts in the game pair and result data of the game pair as score factors, so that the matching degree between the candidate accounts and the account to be recommended can be improved, and further the probability that the candidate accounts to be recommended are added as friends to the account to be recommended can be improved. In addition, the embodiment recommends the game account for the account to be recommendable based on social attributes such as login time, login area, character preference and the like, provides diversified selection for the account to be recommendable, and improves user experience.

In another exemplary embodiment, the application provides an electronic device comprising a processor and a memory, wherein the memory has stored thereon computer readable instructions that when executed by the processor implement a game account recommendation method as before. In this embodiment, the electronic device includes, but is not limited to, a mobile phone, a computer, an intelligent voice interaction device, an intelligent home appliance, a vehicle-mounted terminal, and the like.

It should be noted that, the computer system 1000 of the electronic device shown in fig. 19 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.

As shown in fig. 19, the computer system 1000 includes a central processing unit (Central Processing Unit, CPU) 1001 that can perform various appropriate actions and processes, such as performing the information recommendation method in the above-described embodiment, according to a program stored in a Read-Only Memory (ROM) 1002 or a program loaded from a storage section 1008 into a random access Memory (Random Access Memory, RAM) 1003. In the RAM 1003, various programs and data required for system operation are also stored. The CPU 1001, ROM 1002, and RAM 1003 are connected to each other by a bus 1004. An Input/Output (I/O) interface 1005 is also connected to bus 1004.

The following components are connected to the I/O interface 1005: an input section 1006 including a keyboard, a mouse, and the like; an output portion 1007 including a Cathode Ray Tube (CRT), a liquid crystal display (Liquid Crystal Display, LCD), and a speaker; a storage portion 1008 including a hard disk or the like; and a communication section 1009 including a network interface card such as a LAN (Local Area Network ) card, a modem, or the like. The communication section 1009 performs communication processing via a network such as the internet. The drive 1010 is also connected to the I/O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like, is installed as needed in the drive 1010, so that a computer program read out therefrom is installed as needed in the storage section 1008.

In particular, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 1009, and/or installed from the removable medium 1011. When executed by a Central Processing Unit (CPU) 1001, the computer program performs various functions defined in the system of the present application.

It should be noted that, the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having 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 (Erasable Programmable Read Only Memory, EPROM), flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with a computer-readable computer program embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

It will be appreciated that in the embodiments of the present application, related data such as user information is referred to, and when the above embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data is required to comply with related laws and regulations and standards of related countries and regions.

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

The units involved in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.

Another aspect of the application also provides a computer readable storage medium having stored thereon computer readable instructions which, when executed by a processor, implement the game account recommendation method of any of the previous embodiments.

Another aspect of the application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the game account recommending method provided in the above embodiments.

It should be noted that, the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having 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 (Erasable Programmable Read Only Memory, EPROM), flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with a computer-readable computer program embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The foregoing is merely illustrative of the preferred embodiments of the present application and is not intended to limit the embodiments of the present application, and those skilled in the art can easily make corresponding variations or modifications according to the main concept and spirit of the present application, so that the protection scope of the present application shall be defined by the claims.

Claims

1. A game account recommendation method, comprising:

acquiring a first type candidate account which participates in game play together with an account to be recommended;

scoring the first type candidate account according to a scoring event corresponding to the first type candidate account to obtain a first scoring value, wherein the scoring event is determined by first result data of the game play and first interaction data of the first type candidate account and the account to be recommended in the game play;

and if the first grading value is larger than a first preset threshold value, recommending the first type candidate account as a friend recommendation account to the account to be recommended.

2. The method of claim 1, wherein before scoring the first type of candidate account according to the scoring event corresponding to the first type of candidate account, the method further comprises:

acquiring second interaction data and second result data of the account to be recommended and the corresponding friend account in a game;

generating a plurality of standard scoring events based on the second interaction data and second result data;

and if the target standard scoring event is matched with the first result data and the second interaction data, the target standard scoring event is used as the scoring event corresponding to the first type candidate account.

3. The method of claim 2, wherein scoring the first type of candidate account according to the scoring event corresponding to the first type of candidate account includes:

acquiring the occurrence times and the occurrence time corresponding to the scoring event;

updating initial weights corresponding to the scoring events based on the occurrence times and the occurrence time to obtain weights corresponding to the scoring events, wherein the initial weights are determined by the total number of friend accounts corresponding to the target standard scoring events;

And calculating a weighted sum of the scoring event and the weight corresponding to the scoring event to obtain the first scoring value.

4. The method of claim 3, wherein updating the initial weights for the scoring events based on the number of occurrences and the time of occurrence, the obtaining weights for the scoring events comprises:

acquiring an addition factor and a decay factor corresponding to the initial weight, the addition factor increasing as the number of occurrences of the scoring event increases, the decay factor increasing as the length of time between the time of occurrence of the scoring event and the current time increases;

calculating a first weight based on the initial weight and the addition factor, and calculating a second weight based on the initial weight and the decay factor;

and calculating a weighted sum of the first weight and the second weight, and taking the weighted sum as the weight corresponding to the scoring event.

5. The method of claim 1, wherein after recommending the candidate recommended account number as a friend recommended account number to the account number to be recommended if the first score value is greater than a first preset threshold value, the method further comprises:

Obtaining a second type candidate account which does not participate in game play together with the account to be recommended;

and recommending the second class candidate account meeting the preset recommendation condition to the object to be recommended.

6. The method of claim 5, wherein recommending the second type of candidate account satisfying a preset recommendation condition to the object to be recommended comprises:

scoring the second class candidate account based on attribute information of the second class candidate account to obtain a second scoring value, wherein the attribute information comprises at least one of login area information, online time information, segment information and game role information;

and if the second grading value is larger than a second preset threshold value, recommending the second class candidate account to the account to be recommended.

7. The method of claim 1, wherein after the obtaining a first type of candidate account numbers that are co-engaged with the account number to be recommended for the game, the method further comprises:

matching the first type candidate account with a blacklist and a friend list corresponding to the account to be recommended respectively;

and if the matching is unsuccessful, executing the step of scoring the first type candidate account according to the scoring event corresponding to the first type candidate account.

8. The method of claim 1, wherein after recommending the candidate recommended account number as a friend recommended account number to the account number to be recommended if the first score value is greater than a preset threshold value, the method further comprises:

generating a recommendation reason based on the scoring event;

and sending the recommendation reason to the account to be recommended.

9. The method of claim 8, wherein the generating a recommendation reason based on the scoring event comprises:

matching the scoring event with a recommendation reason template list to obtain a recommendation reason template corresponding to the scoring event, wherein the recommendation reason template list comprises a plurality of preset recommendation reason templates, and each recommendation reason template comprises a plurality of template parameters;

determining a value of a template parameter of a recommendation reason template corresponding to the scoring event based on the first result data and the first interaction data;

and the template parameter value is put into a recommendation reason template corresponding to the scoring event, and the recommendation reason is obtained.

10. A game account recommending apparatus, comprising:

the first acquisition module is used for acquiring a first type candidate account which participates in game play together with the account to be recommended;

The scoring module is used for scoring the first type candidate account according to scoring events corresponding to the first type candidate account to obtain a first scoring value, wherein the scoring events are determined by the result data of the game play and the interaction data of the first type candidate account and the account to be recommended in the game play;

and the first recommendation module is used for recommending the candidate recommendation account as a friend recommendation account to the account to be recommended if the first grading value is larger than a first preset threshold value.

11. An electronic device, comprising:

a memory storing computer readable instructions;

a processor reading computer readable instructions stored in a memory to perform the method of any one of claims 1-9.

12. A computer readable storage medium having stored thereon computer readable instructions which, when executed by a processor of a computer, cause the computer to perform the method of any of claims 1-9.