Account matching method and device

Abstract

This disclosure relates to an account matching method and apparatus. The account matching method includes: when a target account enters a matching pool, identifying at least one first account in the matching pool, wherein the matching success rate between the first account and the target account is greater than a preset threshold; sorting the at least one first account based on information of each first account, wherein the information includes matching information and duration information, the matching information indicating the matching success rate between the first account and the target account, and the duration information indicating the duration of the first account in the matching pool; determining a matching account for the target account from the at least one first account based on the sorting result; and matching the matching account with the target account.

Description

Technical Field

[0001] This disclosure relates to the field of communications, and more particularly to an account matching method and apparatus. Background Technology

[0002] PVP (player versus player) refers to a game mode where players compete against each other. This PVP format has been widely adopted in live streaming, with a common application being several accounts competing against each other within a time limit based on resources and support. In live streaming PVP gameplay, account matching strategies have a significant impact on both platform rewards and user experience.

[0003] A matchmaking session can typically be a two-account matchmaking session or a multi-account matchmaking session, but the matching logic for multi-account matchmaking and two-account matchmaking differs significantly. Currently, in multi-account matchmaking sessions, the strategy of two-account matchmaking sessions is often reused, that is, selecting the accounts with the highest matching success rate from the recalled accounts. This approach often leads to poor matching between the selected accounts in a multi-account matchmaking session. Summary of the Invention

[0004] This disclosure provides an account matching method and apparatus to at least solve the problem of poor matching between multiple accounts in related technologies.

[0005] According to a first aspect of the present disclosure, an account matching method is provided, comprising: when a target account enters a matching pool, determining at least one first account in the matching pool, wherein the matching success rate between the first account and the target account is greater than a preset threshold; sorting the at least one first account based on information of each first account, wherein the information includes matching information and duration information, the matching information indicating the matching success rate between the first account and the target account, and the duration information indicating the duration of the first account in the matching pool; determining a matching account for the target account from the at least one first account based on the sorting result; and matching the matching account with the target account.

[0006] Optionally, before determining at least one first account in the matching pool, the method further includes: inputting the account information of each first account and the account information of the target account into the matching model to obtain the matching success rate of each first account and the target account, wherein the matching model is trained based on the account information of each pair of accounts and the historical matching success rate.

[0007] Optionally, the above information also includes agreeableness information, wherein the agreeableness information indicates the number of accounts in the matching pool whose matching success rate with the first account is greater than a preset threshold.

[0008] Optionally, before sorting at least one first account based on the information of each first account, the method further includes: for each first account, determining at least one second account in the matching pool, wherein the matching success rate between the second account and the first account is greater than a preset threshold; and obtaining the randomness information of the first account based on the number of at least one second account.

[0009] Optionally, based on the number of at least one second account, the willingness information of the first account is obtained, including: determining the proportion of at least one second account in the matching pool based on the number of at least one second account; and determining the proportion as the willingness information of the first account.

[0010] Optionally, based on the information of each first account, sorting at least one first account includes: periodically selecting a predetermined number of accounts from the matching pool; obtaining the average matching information and average duration information of a third account among the predetermined number of accounts, wherein the third account is an account among the predetermined number of accounts whose pairwise matching connection duration is greater than or equal to a preset duration; obtaining the average matching information and average duration information of a fourth account among the predetermined number of accounts, wherein the fourth account is an account among the predetermined number of accounts whose pairwise matching connection duration is less than a preset duration; determining the weight corresponding to the matching information based on the average matching information of the third account and the average matching information of the fourth account; determining the weight corresponding to the duration information based on the average duration information of the third account and the average duration information of the fourth account; using the weight corresponding to the matching information and the weight corresponding to the duration information within the period in which the current time is located as the respective weights of the matching information and duration information of each first account in the current time; and sorting at least one first account based on the respective weights of the matching information and duration information of each first account in the current time.

[0011] Optionally, based on the information of each first account, at least one first account is sorted, including: periodically selecting a predetermined number of accounts from the matching pool; obtaining the average matching information, average duration information, and average willingness information of a third account among the predetermined number of accounts, wherein the third account is an account among the predetermined number of accounts whose pairwise matching connection duration is greater than or equal to a preset duration; obtaining the average matching information, average duration information, and average willingness information of a fourth account among the predetermined number of accounts, wherein the fourth account is an account among the predetermined number of accounts whose pairwise matching connection duration is less than a preset duration; and sorting based on the average matching information of the third account and the average willingness information of the fourth account. All matching information is used to determine the weights corresponding to the matching information; the weights corresponding to the duration information are determined based on the average duration information of the third account and the average duration information of the fourth account; the weights corresponding to the agreeableness information are determined based on the average agreeableness information of the third account and the average agreeableness information of the fourth account; the weights corresponding to the matching information, duration information, and agreeableness information within the current time period are respectively used as the weights of the matching information, duration information, and agreeableness of each first account at the current time; based on the weights of the matching information, duration information, and agreeableness of each first account at the current time, at least one first account is sorted.

[0012] According to a second aspect of the present disclosure, an account matching apparatus is provided, comprising: a first account determining unit configured to determine at least one first account in a matching pool when a target account enters a matching pool, wherein the matching success rate between the first account and the target account is greater than a preset threshold; a sorting unit configured to sort the at least one first account based on information of each first account, wherein the information includes matching information and duration information, the matching information indicating the matching success rate between the first account and the target account, and the duration information indicating the duration of the first account in the matching pool; a matching account determining unit configured to determine a matching account for the target account from the at least one first account based on the sorting result; and a matching unit configured to match the matching account with the target account.

[0013] Optionally, the first account determination unit is further configured to input the account information of each first account and the account information of the target account into the matching model before determining at least one first account in the matching pool, so as to obtain the matching success rate of each first account and the target account, wherein the matching model is trained based on the account information of each pair of accounts and the historical matching success rate.

[0014] Optionally, the above information also includes agreeableness information, wherein the agreeableness information indicates the number of accounts in the matching pool whose matching success rate with the first account is greater than a preset threshold.

[0015] Optionally, the sorting unit is further configured to, before sorting at least one first account based on the information of each first account, determine at least one second account in the matching pool for each first account, wherein the matching success rate between the second account and the first account is greater than a preset threshold; and obtain the randomness information of the first account based on the number of at least one second account.

[0016] Optionally, the sorting unit is also configured to determine the proportion of at least one second account in the matching pool based on the number of at least one second account; and to determine the proportion as the randomness information of the first account.

[0017] Optionally, the sorting unit is further configured to periodically select a predetermined number of accounts from the matching pool; obtain the average matching information and average duration information of the third account among the predetermined number of accounts, wherein the third account is an account among the predetermined number of accounts whose pairwise matching connection duration is greater than or equal to a preset duration; obtain the average matching information and average duration information of the fourth account among the predetermined number of accounts, wherein the fourth account is an account among the predetermined number of accounts whose pairwise matching connection duration is less than a preset duration; determine the weight corresponding to the matching information based on the average matching information of the third account and the average matching information of the fourth account; determine the weight corresponding to the duration information based on the average duration information of the third account and the average duration information of the fourth account; use the weight corresponding to the matching information and the weight corresponding to the duration information within the period in which the current time is located as the respective weights of the matching information and duration information of each first account in the current time; and sort at least one first account based on the respective weights of the matching information and duration information of each first account in the current time.

[0018] Optionally, the sorting unit is further configured to periodically select a predetermined number of accounts from the matching pool; obtain the average matching information, average duration information, and average willingness information of the third account among the predetermined number of accounts, wherein the third account is an account among the predetermined number of accounts whose pairwise matching connection duration is greater than or equal to a preset duration; obtain the average matching information, average duration information, and average willingness information of the fourth account among the predetermined number of accounts, wherein the fourth account is an account among the predetermined number of accounts whose pairwise matching connection duration is less than a preset duration; and determine a match based on the average matching information of the third account and the average matching information of the fourth account. The weights corresponding to the information are determined; the weights corresponding to the duration information are determined based on the average duration information of the third account and the average duration information of the fourth account; the weights corresponding to the agreeableness information are determined based on the average agreeableness information of the third account and the average agreeableness information of the fourth account; the weights corresponding to the matching information, duration information, and agreeableness information within the current time period are respectively used as the weights of the matching information, duration information, and agreeableness of each first account at the current time; and at least one first account is sorted based on the weights of the matching information, duration information, and agreeableness of each first account at the current time.

[0019] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement an account matching method according to the present disclosure.

[0020] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided that, when instructions in the computer-readable storage medium are executed by at least one processor, causes at least one processor to perform the account matching method as described above according to the present disclosure.

[0021] According to a fifth aspect of the present disclosure, a computer program product is provided, including computer instructions that, when executed by a processor, implement the account matching method according to the present disclosure.

[0022] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects:

[0023] According to the account matching method and apparatus of this disclosure, when sorting at least one first account in the matching pool, the matching success rate and the duration of the account in the matching pool are comprehensively considered, making the order of the sorted at least one first account more consistent with the actual situation. Based on the sorted first accounts, multiple matching accounts that are more suitable for matching with the target account can be obtained, thereby improving the matching success rate between the target account and multiple accounts. Therefore, this disclosure solves the problem of poor matching between multiple accounts in related technologies.

[0024] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0025] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0026] Figure 1 This is a schematic diagram illustrating an implementation scenario of an account matching method according to an exemplary embodiment of the present disclosure;

[0027] Figure 2 This is a flowchart illustrating an account matching method according to an exemplary embodiment;

[0028] Figure 3 This is a block diagram illustrating an account matching device according to an exemplary embodiment;

[0029] Figure 4 This is a block diagram of an electronic device 400 according to an embodiment of the present disclosure. Detailed Implementation

[0030] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0031] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following examples do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0032] It should be noted that the phrase "at least one of several items" in this disclosure refers to three parallel cases: "any one of the several items", "a combination of any number of the several items", and "all of the several items". For example, "including at least one of A and B" includes the following three parallel cases: (1) including A; (2) including B; (3) including A and B. As another example, "performing at least one of step one and step two" indicates the following three parallel cases: (1) performing step one; (2) performing step two; (3) performing both step one and step two.

[0033] Currently, compared to two-account matching, multi-account matching involves more complex issues. For example, when searching for three suitable matching accounts for account 1, it's necessary to consider not only whether account 1 has a high matching success rate with accounts 2, 3, and 4, but also whether accounts 2, 3, and 4 themselves have a high matching success rate with each other. For instance, if account 1 can be matched with multiple accounts (e.g., 50 accounts meeting the criteria), in a two-account matching scenario, only the account with the highest matching degree with account 1 needs to be found. However, in a multi-account matching scenario, the accounts with high matching degrees with account 1 may not actually match. Furthermore, assuming this multi-account matching scenario involves matching four accounts, finding the globally optimal solution for account 1 would require a search space of approximately 20,000 combinations (finding three accounts out of 50) of matching four accounts, and then finding the best combination (the one with the highest total connectivity of the six edges connecting the four accounts). Such a massive computational load is impossible in real-time scenarios. Meanwhile, the matching conditions for multi-account matching are more stringent than those for dual-account matching. In dual-account matching, finding a suitable account is enough for matching, but in multi-account matching, account 1 needs to wait for at least two accounts that meet the conditions, and the waiting time will definitely be longer than that for dual-account matching.

[0034] To address the aforementioned issues, this disclosure provides an account matching method that enables better matching between multiple accounts. The following explanation uses a live streaming scenario as an example.

[0035] Figure 1 This is a schematic diagram illustrating an implementation scenario of an account matching method according to an exemplary embodiment of the present disclosure, such as... Figure 1 The implementation scenario includes server 100, user terminal 110, and user terminal 120. The number of user terminals is not limited to two, and includes, but is not limited to, devices such as mobile phones and personal computers. The user terminals may have live streaming applications installed. The server may be a single server, a server cluster composed of several servers, or a cloud computing platform or virtualization center.

[0036] The application on user terminal 110 or 120 opens a live broadcast room through the target account. When multiple accounts need to be connected in the live broadcast room, the application instructs the user corresponding to the target account to click the connection menu. At this time, the target account enters the matching pool. When the target account enters the matching pool, user terminal 110 or 120 determines the recall account (i.e., the first account) in the matching pool at the current time. The success rate of matching between the recall account and the target account is greater than a preset threshold. Based on the matching information and duration information of each recall account, all recall accounts are sorted. The matching information indicates the success rate of matching between the first account and the target account, and the duration information indicates the duration of the first account in the matching pool. Based on the sorting results, the matching account of the target account is determined from all recall accounts. The matching account is then connected to the target account for matching.

[0037] It should be noted that user terminals 110 and 120 can perform this task independently, or they can receive data services from server 100; this disclosure does not limit this. When receiving data services from server 100, the application on user terminal 110 and / or user terminal 120 opens a live broadcast room through the target account. When multiple accounts need to be connected in the live broadcast room, the application instructs the user corresponding to the target account to click the connection menu. At this time, the target account enters the matching pool on server 100. When the target account enters the matching pool, server 100 determines the recalled account (i.e., the first account) in the matching pool at the current time, wherein the matching success rate between the recalled account and the target account is greater than a preset threshold. Based on the matching information and duration information of each recalled account, all recalled accounts are sorted, wherein the matching information indicates the matching success rate between the first account and the target account, and the duration information indicates the duration of the first account in the matching pool. Based on the sorting results, the matching account for the target account is determined from all recalled accounts. The matching account is then connected to the target account for matching.

[0038] The account matching method and apparatus according to exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings.

[0039] Figure 2 This is a flowchart illustrating an account matching method according to an exemplary embodiment, such as... Figure 2 As shown, the account matching method includes the following steps:

[0040] In step S201, when the target account enters the matching pool, at least one first account in the matching pool is determined, wherein the matching success rate between the first account and the target account is greater than a preset threshold.

[0041] As an example, a minimum matching success rate (i.e., the aforementioned preset threshold) can be set. This minimum matching success rate can be set independently according to business needs and actual conditions, or determined through experiments. This disclosure does not impose any limitations on this. Once the minimum matching success rate is determined, accounts in the matching pool with a matching success rate higher than this minimum matching success rate can be recalled. These are generally referred to as the recalled accounts of the target account, i.e., the aforementioned first account.

[0042] According to an exemplary embodiment of this disclosure, before determining at least one first account in the matching pool, the account information of each first account and the account information of the target account can be input into the matching model to obtain the matching success rate between each first account and the target account. The matching model is trained based on the account information of each pair of accounts and historical matching success rates. According to this embodiment, machine learning is introduced; that is, a more accurate matching success rate can be obtained through the trained matching model.

[0043] Specifically, data from the dual-account matching mode can be used to model the matching success rate between accounts. The prediction target of the established matching model can be the probability that two accounts will remain connected within N seconds after matching, i.e., the matching success rate. The aforementioned account information may include the account's profile (basic characteristics such as name, gender, and height) and historical PVP matching behavior, which are not limited in this disclosure.

[0044] It should be noted that the account information (including but not limited to device information, personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are all information and data authorized by the user to whom the account belongs or fully authorized by all parties.

[0045] For example, multiple accounts in the dual-account matching mode are obtained, and the account information of the paired accounts is input into the initial matching model to obtain the estimated matching success rate of the paired accounts. Based on the estimated matching success rate and the actual matching success rate of the paired accounts, the parameters of the initial matching model are adjusted to complete the training of the initial matching model and obtain the trained matching model.

[0046] return Figure 2 In step S202, at least one first account is sorted based on the information of each first account. The information includes matching information and duration information. The matching information indicates the success rate of matching between the first account and the target account, and the duration information indicates the duration of the first account in the matching pool.

[0047] For example, the matching information and duration information of each first account and the target account can be weighted and summed to obtain the ranking information of each first account; alternatively, the matching information and duration information of each first account can be integrated through a self-attention mechanism to obtain the ranking information of each first account. This disclosure does not limit the scope of the method.

[0048] According to an exemplary embodiment of this disclosure, the aforementioned information further includes agreeableness information, wherein the agreeableness information indicates the number of accounts in the matching pool whose matching success rate with the first account is greater than a preset threshold. According to this embodiment, when determining suitable matching accounts to match the target account, the agreeableness information of each predetermined account in the matching pool is also taken into consideration, thereby further improving the matching success rate between the target account and multiple accounts.

[0049] The aforementioned sorting of at least one first account based on the information of each first account may include: sorting at least one first account based on the matching information, duration information, and agreeableness information of each first account, and this disclosure does not limit this. For example, the agreeableness information of each first account in the matching pool can be obtained in advance, and then the ranking information of each first account can be obtained by weighting the matching information, duration information, and agreeableness information of each first account, and then the first accounts can be sorted based on the ranking information.

[0050] It's important to note that the waiting time for each top account is generally inversely proportional to its agreeableness level. This is because accounts with low agreeableness levels are likely to rank lower in any account's sorting list, resulting in significantly longer waiting times for them and negatively impacting their user experience. Therefore, when sorting top accounts, it's advisable to prioritize accounts with longer waiting times.

[0051] According to an exemplary embodiment of this disclosure, before sorting at least one first account based on the information of each first account, at least one second account in the matching pool can be determined for each first account, wherein the matching success rate between the second account and the first account is greater than a preset threshold; and the agreeableness information of the first account is obtained based on the number of at least one second account. According to this embodiment, by measuring the number of second accounts, the number of accounts in the matching pool that can be matched with the first account can be determined intuitively and conveniently, thereby revealing the agreeableness information of the predetermined account.

[0052] Specifically, the biggest difference between multi-account matching scenarios and dual-account matching scenarios lies in this: Assuming Account 1 and Account X have a high match success rate, but Account X itself might be very picky, meaning its match success rate with most accounts is low, then when Account 1 finds a second account Y to enter the matching pool, Account X might be disconnected due to Account Y's appearance. Therefore, it's advisable to prioritize easy-going users to avoid this situation. Since Account X is already in the matching pool when Account 1 enters, and Account X typically undergoes a recall process after entering the pool, but for some reason didn't start matching before Account 1 entered, Account X's easy-going information can definitely be obtained.

[0053] For example, to determine the agreeableness information of account X in the matching pool, accounts in the matching pool with a matching success rate greater than a preset threshold can be obtained. These are generally referred to as the recalled accounts of account X (corresponding to the second account in the above embodiment). The number of recalled accounts is then obtained, and this number basically determines the agreeableness information of account X. It should be noted that the agreeableness of an account is directly proportional to the number of recalled accounts; the larger the number of recalled accounts, the greater the agreeableness of the account, and the smaller the number of recalled accounts, the smaller the agreeableness of the account.

[0054] According to an exemplary embodiment of this disclosure, obtaining the agreeableness information of a first account based on the number of at least one second account may include: determining the proportion of at least one second account in the matching pool based on the number of at least one second account; and determining the proportion as the agreeableness information of the first account. According to this embodiment, a relatively accurate agreeableness information can be determined by the proportion of the number of second accounts in the matching pool.

[0055] For example, taking the determination of the agreeableness information of account X in the matching pool as an example, after obtaining the number of recalled accounts of account X, the proportion of recalled accounts can be obtained by the number of recalled accounts and the total number of accounts in the matching pool, and this proportion can be used as the agreeableness information of account X. Of course, this disclosure does not limit the determination of agreeableness.

[0056] According to an exemplary embodiment of this disclosure, sorting at least one first account based on information of each first account may include: determining the weights of matching information and duration information for each first account; sorting at least one first account based on the weights of matching information and duration information for each first account at the current time, for example, by performing a weighted summation of matching information and duration information using determined weights to obtain sorting information for at least one first account; and sorting at least one first account based on the sorting information. According to this embodiment, by determining corresponding weights for the two factors, matching information and duration information, and combining them based on these weights, the influence of each factor on the sorting information can be flexibly adjusted, making the sorted predetermined accounts more closely reflect the actual situation.

[0057] Specifically, the weights of the above factors can be set manually based on experience and actual needs. For example, the weight of each factor can be set manually; multiple weights can be set for each factor, and then the weights for each factor can be selected based on experiments; or the weight of each factor can be determined directly through experiments. This disclosure does not limit the scope of the disclosure.

[0058] For example, assuming W1 and W2 represent the weights of an account's matching information and duration information, respectively, the account's ranking information can be W1 × matching information + W2 × duration information; the larger the ranking information, the higher the account ranks in the corresponding target account ranking list. It should be noted that the form of the duration information can also be varied, such as using the ratio of duration to the longest duration in the matching pool, or other forms; this disclosure does not limit this.

[0059] The method of selecting the weight of each factor based on experiments will be discussed in detail below.

[0060] According to an exemplary embodiment of this disclosure, determining the weights of matching information and duration information for each first account may include: periodically selecting a predetermined number of accounts from the matching pool; obtaining the average matching information and average duration information of a third account among the predetermined number of accounts, wherein the third account is an account among the predetermined number of accounts whose pairwise matching connection duration is greater than or equal to a preset duration; obtaining the average matching information and average duration information of a fourth account among the predetermined number of accounts, wherein the fourth account is an account among the predetermined number of accounts whose pairwise matching connection duration is less than a preset duration; determining the weights corresponding to the matching information based on the average matching information of the third account and the average matching information of the fourth account; determining the weights corresponding to the duration information based on the average duration information of the third account and the average duration information of the fourth account; and using the weights corresponding to the matching information and the duration information within the current time period as the respective weights of the matching information and duration information of each first account at the current time. According to this embodiment, the weights of each factor can be automatically determined without relying on manual labor, saving manpower.

[0061] Specifically, the aforementioned period can be set as needed, such as 5 seconds or 10 seconds, and this disclosure does not limit this. The aforementioned predetermined number can also be set as needed, such as 20% or 30% of the accounts in the matching pool, and this disclosure does not limit this. The aforementioned preset duration can also be set as needed, such as 30 seconds or 20 seconds, and this disclosure does not limit this.

[0062] For example, taking a 5-second cycle, a predetermined number of accounts (20%) in the matching pool, and a preset duration of 30 seconds as an example, firstly, every 5 seconds, 20% of the accounts in the matching pool are randomly selected and randomly matched; secondly, the following two indicators are calculated for each of the matches that did not disconnect within 30 seconds and the matches that disconnected within 30 seconds in these random matching sessions: Indicator 1 - the average of the account duration information, and Indicator 2 - the average of the matching information between accounts. For Indicator 2, assuming that 4 accounts are matched in a session, the average of C(4,2) = 6 matching information needs to be calculated; then, the average values ​​of the two indicators are calculated for all sessions that did not disconnect, i.e., the average matching information and average duration information of the third account in the above embodiment. The average values ​​of the two indicators are also calculated for all sessions that disconnected, i.e., the average matching information and average duration information of the fourth account in the above embodiment; finally, the weights of the two indicators can be determined according to the ratio of the two indicators in the disconnected and undisconnected sessions, such as:

[0063] W1 = Average matching information of matches without disconnection / Average matching information of matches with disconnection

[0064] W2 = Average duration of matches that did not disconnect / Average duration of matches that disconnected.

[0065] It should be noted that the weight is not necessarily determined by the ratio of the two indicators in the number of matches with and without disconnection; it can also be determined by the difference, etc. This disclosure does not limit this.

[0066] According to an exemplary embodiment of this disclosure, sorting at least one first account based on information of each first account may include: determining the weights of matching information, duration information, and agreeableness information for each first account; sorting at least one first account based on the weights of matching information, duration information, and agreeableness information for each first account at the current time, for example, by performing a weighted summation of matching information, duration information, and agreeableness information using determined weights to obtain sorting information for at least one first account; and sorting at least one first account based on the sorting information. According to this embodiment, by determining corresponding weights for agreeableness information and combining the three factors based on these weights, the influence of each factor on the sorting information can be flexibly adjusted, making the sorted predetermined accounts more closely reflect the actual situation.

[0067] Specifically, the aforementioned weights can be set manually based on experience and actual needs. For example, the weights of the agreeableness information can be set manually; multiple weights can be set for the agreeableness information, and then the respective weights can be selected for the agreeableness information based on experiments; or the weights of the agreeableness information can be determined directly through experiments. This disclosure does not limit the scope of the discussion.

[0068] For example, assuming W1, W2, and W3 represent the weights of an account's matching information, duration information, and agreeableness information, respectively, then the account's ranking information can be W1 × matching information + W2 × duration information + W2 × agreeableness information; the larger the ranking information, the higher the account ranks in the corresponding target account ranking list. It should be noted that the form of the aforementioned duration information can also be varied. For example, the duration information can be the ratio of the first account's duration to the longest duration in the matching pool, or it can be in other forms; this disclosure does not limit this.

[0069] According to an exemplary embodiment of this disclosure, determining the respective weights of the matching information, duration information, and agreeableness information of each first account may include: periodically selecting a predetermined number of accounts from the matching pool; obtaining the average matching information, average duration information, and average agreeableness information of a third account among the predetermined number of accounts, wherein the third account is an account among the predetermined number of accounts whose pairwise matching connection duration is greater than or equal to a preset duration; obtaining the average matching information, average duration information, and average agreeableness information of a fourth account among the predetermined number of accounts, wherein the fourth account is an account among the predetermined number of accounts whose pairwise matching connection duration is less than a preset duration; determining the weight corresponding to the matching information based on the average matching information of the third account and the average matching information of the fourth account; determining the weight corresponding to the duration information based on the average duration information of the third account and the average duration information of the fourth account; determining the weight corresponding to the agreeableness information based on the average agreeableness information of the third account and the average agreeableness information of the fourth account; and using the weights corresponding to the matching information, duration information, and agreeableness information within the period in which the current time is located as the respective weights of the matching information, duration information, and agreeableness of each first account at the current time. According to this embodiment, the weight of the affability information can be automatically determined without relying on human intervention, thus saving manpower.

[0070] For example, taking a 5-second cycle, a predetermined number of accounts (20%) in the matching pool, and a preset duration of 30 seconds as an example, firstly, every 5 seconds, 20% of the accounts in the matching pool are randomly selected and randomly matched; secondly, the following three indicators are calculated for each of the matches that did not disconnect within 30 seconds and the matches that disconnected within 30 seconds: Indicator 1 - the average of account duration information, Indicator 2 - the average of matching information between accounts, and Indicator 3 - the average of account randomness information. For Indicator 2, assuming a match has 4... To match accounts, we need to calculate the average of C(4,2) = 6 matching data points. Then, we calculate the average of the three indicators for all matches that were not disconnected, i.e., the average matching information, average duration information, and average compliance information of the third account in the above embodiment. We also need to calculate the average of the three indicators for all matches that were disconnected, i.e., the average matching information, average duration information, and average compliance information of the fourth account in the above embodiment. Finally, we can determine the weights of the three indicators based on the ratios of the three indicators in matches that were disconnected and matches that were not disconnected, such as:

[0071] W1 = Average matching information of matches without disconnection / Average matching information of matches with disconnection

[0072] W2 = Average duration of matches without disconnection / Average duration of matches with disconnection

[0073] W3 = Average randomness information of matches without disconnection / Average randomness information of matches with disconnection.

[0074] It should also be noted that the weight is not necessarily determined by the ratio of the indicator in the number of matches with and without disconnection, but can also be determined by the difference, etc. This disclosure does not limit this.

[0075] return Figure 2 In step S203, based on the sorting results, a matching account for the target account is determined from at least one first account. The matching account in this step can be multiple or just one; regardless of the number of matching accounts, the account ranked first in the sorted list is selected.

[0076] For example, if four matching accounts are needed, you can select the first four accounts from the sorted first account as the matching accounts for the target account.

[0077] return Figure 2 In step S204, the matching account is matched with the target account. This matching can be a live stream connection or a video call in a conference, and this disclosure does not limit the scope of the matching.

[0078] It should be noted that the account information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0079] In summary, after the target account enters the matching pool, the accounts in the matching pool at the current time point become the candidate set of matching accounts for the target account. At this point, a preliminary recall of accounts within the candidate set is required, i.e., selecting accounts with a matching success rate greater than a certain threshold. Then, the recalled accounts are sorted. This sorting may consider the matching success rate between the target account and accounts in the candidate set, the randomness of accounts in the candidate set, and the duration of accounts in the candidate set in the matching pool. Other factors may also be considered, and this disclosure does not limit this. This disclosure comprehensively considers the matching degree between accounts, the randomness of accounts, and the duration of accounts during matching, and assigns corresponding weights to each factor determining whether a match is made. This disclosure allows for finding suitable matching accounts with relatively low computational cost.

[0080] Figure 3 This is a block diagram illustrating an account matching device according to an exemplary embodiment. (Refer to...) Figure 3 The device includes a first account determination unit 30, a sorting unit 32, a matching account determination unit 34, and a matching unit 36.

[0081] The first account determination unit 30 is configured to determine at least one first account in the matching pool when the target account enters the matching pool, wherein the matching success rate between the first account and the target account is greater than a preset threshold; the sorting unit 32 is configured to sort at least one first account based on the information of each first account, wherein the information includes matching information and duration information, the matching information indicating the matching success rate between the first account and the target account, and the duration information indicating the duration of the first account in the matching pool; the matching account determination unit 34 is configured to determine the matching account of the target account from at least one first account based on the sorting result; and the matching unit 36 ​​is configured to match the matching account with the target account.

[0082] According to an exemplary embodiment of this disclosure, the first account determination unit 30 is further configured to input the account information of each first account and the account information of the target account into a matching model before determining at least one first account in the matching pool, so as to obtain the matching success rate of each first account and the target account, wherein the matching model is trained based on the account information of each pair of accounts and the historical matching success rate.

[0083] According to an exemplary embodiment of this disclosure, the above information further includes agreeableness information, wherein the agreeableness information indicates the number of accounts in the matching pool whose matching success rate with the first account is greater than a preset threshold.

[0084] According to an exemplary embodiment of the present disclosure, the sorting unit 32 is further configured to, before sorting at least one first account based on the information of each first account, determine at least one second account in the matching pool for each first account, wherein the matching success rate between the second account and the first account is greater than a preset threshold; and obtain the randomness information of the first account based on the number of at least one second account.

[0085] According to an exemplary embodiment of this disclosure, the sorting unit is further configured to determine the proportion of at least one second account in the matching pool based on the number of at least one second account; and to determine the proportion as the agreeableness information of the first account.

[0086] According to an exemplary embodiment of this disclosure, the sorting unit 32 is further configured to determine the respective weights of the matching information and duration information of each first account; perform weighted summation processing on the matching information and duration information using the determined weights to obtain sorting information of at least one first account; and sort the at least one first account based on the sorting information.

[0087] According to an exemplary embodiment of this disclosure, the sorting unit 32 is further configured to periodically select a predetermined number of accounts from the matching pool; obtain the average matching information and average duration information of a third account among the predetermined number of accounts, wherein the third account is an account among the predetermined number of accounts whose pairwise matching connection duration is greater than or equal to a preset duration; obtain the average matching information and average duration information of a fourth account among the predetermined number of accounts, wherein the fourth account is an account among the predetermined number of accounts whose pairwise matching connection duration is less than a preset duration; determine the weight corresponding to the matching information based on the average matching information of the third account and the average matching information of the fourth account; determine the weight corresponding to the duration information based on the average duration information of the third account and the average duration information of the fourth account; and use the weight corresponding to the matching information and the weight corresponding to the duration information within the period in which the current time is located as the respective weights of the matching information and duration information of each first account in the current time.

[0088] According to an exemplary embodiment of this disclosure, the sorting unit 32 is further configured to determine the respective weights of the matching information, duration information, and agreeableness information of each first account; perform weighted summation processing on the matching information, duration information, and agreeableness information using the determined weights to obtain sorting information of at least one first account; and sort the at least one first account based on the sorting information.

[0089] According to an exemplary embodiment of this disclosure, the sorting unit 32 is further configured to periodically select a predetermined number of accounts from the matching pool; obtain the average matching information, average duration information, and average agreeableness information of a third account among the predetermined number of accounts, wherein the third account is an account among the predetermined number of accounts whose pairwise matching connection duration is greater than or equal to a preset duration; obtain the average matching information, average duration information, and average agreeableness information of a fourth account among the predetermined number of accounts, wherein the fourth account is an account among the predetermined number of accounts whose pairwise matching connection duration is less than a preset duration; determine the weight corresponding to the matching information based on the average matching information of the third account and the average matching information of the fourth account; determine the weight corresponding to the duration information based on the average duration information of the third account and the average duration information of the fourth account; determine the weight corresponding to the agreeableness information based on the average agreeableness information of the third account and the average agreeableness information of the fourth account; and use the weight corresponding to the matching information, the weight corresponding to the duration information, and the weight corresponding to the agreeableness information within the period in which the current time is located as the respective weights of the matching information, duration information, and agreeableness of each first account in the current time.

[0090] According to embodiments of this disclosure, an electronic device may be provided. Figure 4This is a block diagram of an electronic device 400 according to an embodiment of the present disclosure. The electronic device includes at least one memory 401 and at least one processor 402. The at least one memory stores a set of computer-executable instructions. When the set of computer-executable instructions is executed by the at least one processor, an account matching method according to an embodiment of the present disclosure is performed.

[0091] As an example, electronic device 400 may be a PC, tablet, personal digital assistant, smartphone, or other device capable of executing the aforementioned set of instructions. Here, electronic device 1000 is not necessarily a single electronic device, but may be a collection of any devices or circuits capable of executing the aforementioned instructions (or instruction sets) individually or in combination. Electronic device 400 may also be part of an integrated control system or system manager, or may be configured to interconnect with a portable electronic device locally or remotely (e.g., via wireless transmission) through an interface.

[0092] In electronic device 400, processor 402 may include a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller, or a microprocessor. By way of example and not limitation, processor 402 may also include analog processors, digital processors, microprocessors, multi-core processors, processor arrays, network processors, etc.

[0093] The processor 402 can execute instructions or code stored in memory, wherein memory 401 can also store data. Instructions and data can also be sent and received over a network via a network interface device, wherein the network interface device can employ any known transmission protocol.

[0094] The memory 401 may be integrated with the processor 402, for example, by placing RAM or flash memory within an integrated circuit microprocessor. Alternatively, the memory 401 may include a separate device, such as an external disk drive, a storage array, or other storage device that can be used by any database system. The memory 401 and the processor 402 may be operatively coupled, or may communicate with each other, for example, via I / O ports, network connections, etc., enabling the processor 402 to read files stored in the memory 401.

[0095] In addition, the electronic device 400 may also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, mouse, touch input device, etc.). All components of the electronic device can be interconnected via a bus and / or network.

[0096] According to embodiments of this disclosure, a computer-readable storage medium may also be provided, wherein when instructions in the computer-readable storage medium are executed by at least one processor, the at least one processor causes to perform the account matching method of embodiments of this disclosure. Examples of computer-readable storage media include: read-only memory (ROM), random access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or optical disc storage, hard disk drive (HDD), solid-state drive (SSD), card storage (such as multimedia cards, secure digital (SD) cards, or ultra-fast digital (XD) cards), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state drive, and any other device configured to store a computer program and any associated data, data files, and data structures in a non-transitory manner and to provide the computer program and any associated data, data files, and data structures to a processor or computer so that the processor or computer can execute the computer program. The computer program in the aforementioned computer-readable storage medium can run in an environment deployed in computer devices such as clients, hosts, agent devices, servers, etc. Furthermore, in one example, the computer program and any associated data, data files, and data structures are distributed across a networked computer system, such that the computer program and any associated data, data files, and data structures are stored, accessed, and executed in a distributed manner through one or more processors or computers.

[0097] According to an embodiment of this disclosure, a computer program product is provided, including computer instructions that, when executed by a processor, implement the account matching method of this disclosure.

[0098] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0099] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. An account matching method, characterized in that, include: When a target account enters the matching pool, at least one first account in the matching pool is identified, wherein the matching success rate between the first account and the target account is greater than a preset threshold. Based on the information of each first account, the at least one first account is sorted, wherein the information includes matching information, duration information and agreeableness information, the matching information indicates the matching success rate between the first account and the target account, the duration information indicates the duration of the first account in the matching pool, and the agreeableness information indicates the number of accounts in the matching pool whose matching success rate with the first account is greater than the preset threshold. Based on the sorting results, a matching account for the target account is determined from the at least one first account; The matching account is matched with the target account.

2. The account matching method as described in claim 1, characterized in that, Before determining at least one first account in the matching pool, the process also includes: The account information of each first account and the account information of the target account are input into the matching model to obtain the matching success rate of each first account and the target account. The matching model is trained based on the account information of each pair of accounts and the historical matching success rate.

3. The account matching method as described in claim 1, characterized in that, Before sorting the at least one first account based on the information of each first account, the method further includes: For each first account, at least one second account is identified in the matching pool, wherein the matching success rate between the second account and the first account is greater than the preset threshold; Based on the number of the at least one second account, obtain the agreeableness information of the first account.

4. The account matching method as described in claim 3, characterized in that, The step of obtaining the agreeableness information of the first account based on the number of the at least one second account includes: Based on the number of the at least one second account, determine the proportion of the at least one second account in the matching pool; The percentage is determined as the agreeableness information of the first account.

5. The account matching method as described in claim 1, characterized in that, The sorting of the at least one first account based on the information of each first account includes: A predetermined number of accounts are periodically selected from the matching pool; Obtain the average matching information, average duration information, and average agreeableness information of the third account among the predetermined number of accounts, wherein the third account is an account among the predetermined number of accounts whose pairwise matching connection duration is greater than or equal to a preset duration; Obtain the average matching information, average duration information, and average agreeableness information of the fourth account among the predetermined number of accounts, wherein the fourth account is an account among the predetermined number of accounts whose pairwise matching connection duration is less than the preset duration; Based on the average matching information of the third account and the average matching information of the fourth account, the weights corresponding to the matching information are determined. Based on the average duration information of the third account and the average duration information of the fourth account, the weight corresponding to the duration information is determined; Based on the average agreeableness information of the third account and the average agreeableness information of the fourth account, the weight corresponding to the agreeableness information is determined; The weights corresponding to the matching information, the duration information, and the agreeableness information within the current time period are respectively used as the weights of the matching information, the duration information, and the agreeableness of each first account at the current time. The at least one first account is sorted based on the matching information, duration information, and weights of the agreeableness of each first account at the current time.

6. An account matching device, characterized in that, include: The first account determination unit is configured to determine at least one first account in the matching pool when the target account enters the matching pool, wherein the matching success rate between the first account and the target account is greater than a preset threshold. The sorting unit is configured to sort the at least one first account based on information of each first account, wherein the information includes matching information, duration information and agreeableness information, the matching information indicates the matching success rate of the first account with the target account, the duration information indicates the duration of the first account in the matching pool, and the agreeableness information indicates the number of accounts in the matching pool whose matching success rate with the first account is greater than the preset threshold. The matching account determination unit is configured to determine the matching account of the target account from the at least one first account based on the sorting result; The matching unit is configured to match the matching account with the target account.

7. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the account matching method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by at least one processor, the at least one processor causes the at least one processor to perform the account matching method as described in any one of claims 1 to 5.

Images