Matching processing methods, devices, equipment, storage media and program products

Abstract

This application provides a matching processing method, apparatus, electronic device, computer-readable storage medium, and computer program product for a cluster system. The cluster system includes multiple regional clusters. The method includes: performing speed testing on each regional cluster to obtain the test network latency of a first account corresponding to each regional cluster; determining the expansion order of the regional clusters corresponding to the first account and the matching waiting time of the first account in each regional cluster based on the test network latency of the first account corresponding to each regional cluster; and dynamically configuring the first account to at least one regional cluster for matching processing according to the expansion order of the regional clusters corresponding to the first account and the matching waiting time of the first account in each regional cluster. This application can improve matching processing efficiency while taking network latency into account.

Description

Technical Field

[0001] This application relates to Internet technology, and more particularly to a matching processing method, apparatus, electronic device, computer-readable storage medium, and computer program product for a cluster system. Background Technology

[0002] Before a user officially starts a game, the game client's server provides a matchmaking service, matching the user with other players for that particular game. However, because users are geographically distributed globally, it is difficult for the server to quickly provide game matchmaking services to users in different regions.

[0003] Related technologies involve partitioning servers and matching users through server clusters targeting multiple geographical regions. While partitioning servers can reduce network latency caused by geographical distance, the corresponding server clusters struggle to achieve fast matching, thus failing to balance network latency and matching efficiency. Summary of the Invention

[0004] This application provides a matching processing method, apparatus, electronic device, computer-readable storage medium, and computer program product for a cluster system, which can improve matching processing efficiency while taking into account network latency.

[0005] The technical solution of this application embodiment is implemented as follows:

[0006] This application provides a matching processing method for a cluster system, including:

[0007] Speed ​​testing is performed on each of the aforementioned regional clusters to obtain the test network latency for each of the aforementioned regional clusters corresponding to the first account;

[0008] Based on the test network latency of the first account for each of the regional clusters, the expansion order of the regional clusters corresponding to the first account and the matching waiting time of the first account in each of the regional clusters are determined.

[0009] According to the expansion order of the regional clusters corresponding to the first account and the matching waiting time of the first account in each regional cluster, the first account is dynamically configured to at least one of the regional clusters for matching processing.

[0010] This application provides a matching processing device for a cluster system, characterized in that the device includes:

[0011] The speed test module is used to perform speed test processing on each of the said regional clusters to obtain the test network latency of the first account for each of the said regional clusters;

[0012] The sequence module is used to determine the expansion order of the regional clusters corresponding to the first account based on the test network latency of each of the regional clusters corresponding to the first account.

[0013] The waiting module is used to determine the matching waiting time of the first account in each of the regional clusters based on the test network latency corresponding to the first account in each of the regional clusters;

[0014] The matching module is used to dynamically configure the first account to at least one of the regional clusters for matching processing according to the expansion order of the regional clusters corresponding to the first account and the matching waiting time of the first account in each of the regional clusters.

[0015] In the above scheme, the speed test module is further configured to: send the cluster address of the regional cluster to the client of the first account, so that the client performs speed test processing for each of the regional clusters based on the cluster address; and receive the speed test results reported by the client, wherein the speed test results include the test network latency of the first account accessing each of the regional clusters.

[0016] In the above scheme, the speed measurement module is further configured to: perform at least one of the following processes: in response to receiving an address acquisition request periodically sent by the client, periodically send the cluster address of each of the regional clusters to the client; in response to receiving a login request from the client, send the cluster address of each of the regional clusters to the client.

[0017] In the above scheme, the speed test module is further configured to: before sending the cluster address of the regional cluster to the client of the first account, in response to the expansion of the cluster system to add a new regional cluster, obtain the cluster address of the new regional cluster; and perform at least one of the following processes: in response to receiving an address acquisition request periodically sent by the client, periodically send the cluster address of the new regional cluster and the cluster address of each regional cluster to the client; in response to receiving a login request from the client, send the cluster address of the new regional cluster and the cluster address of each regional cluster to the client.

[0018] In the above scheme, the sequence module is further configured to: sort the multiple regional clusters in ascending order based on the test network latency of the first account accessing each of the regional clusters to obtain an ascending order sorting result; and use the ascending order sorting result as the regional cluster expansion order corresponding to the first account.

[0019] In the above solution, the waiting module is further configured to: obtain the following data for each of the regional clusters: the initial waiting time, the network delay parameter, and the conversion ratio parameter; perform the following processing for each of the regional clusters: based on the initial waiting time, the network delay parameter, and the conversion ratio parameter, determine a matching waiting time that is positively correlated with the test network delay of the regional cluster.

[0020] In the above solution, the waiting module is further configured to: determine the difference between the test network delay of the regional cluster and the network delay parameter of the regional cluster; determine the ratio of the difference to the conversion ratio parameter; determine the sum of the ratio and the initial waiting time as the matching waiting time.

[0021] In the above solution, the waiting module is further configured to: perform the following processing for each of the regional clusters: in response to a setting operation on the initial waiting time, the network delay parameter, and the conversion ratio parameter, obtain the initial waiting time of the regional cluster, the network delay parameter of the regional cluster, and the conversion ratio parameter of the regional cluster.

[0022] In the above solution, the waiting module is further configured to: call a neural network model to perform the following processing on the matching waiting time of each of the regional clusters: based on the test network delay of the first account corresponding to the regional cluster, extract the delay feature of the first account corresponding to the regional cluster; based on the historical matching records of the first account, extract the historical matching feature of the first account; perform a fusion process on the delay feature and the historical matching feature to obtain a fusion feature; perform a mapping process on the fusion feature to obtain the matching waiting time of the first account in the regional cluster.

[0023] In the above solution, the number of regional clusters in the cluster system is N, where N is an integer greater than or equal to 2, n is an integer variable starting from 1 and increasing, and 0 < n < N; the matching module is further configured to: when n is 1, perform the matching process for the first account in the nth regional cluster in the regional cluster expansion order, and time the matching process for the nth regional cluster; when the timing reaches the matching waiting time corresponding to the nth regional cluster and the matching has not been successful, continue to perform the matching process for the first account in the nth regional cluster and transfer to perform the matching process for the first account in the (n + 1)th regional cluster in the regional cluster expansion order.

[0024] In the above scheme, the matching module is further configured to: when the timer has not reached the matching waiting time for the corresponding nth regional cluster and the matching is successful, provide services to the first account based on the matching result, and stop performing matching processing for the first account in the subsequent regional clusters of the cluster system; wherein, the subsequent regional clusters are regional clusters that are ranked after the nth regional cluster in the cluster expansion order.

[0025] This application provides an electronic device, including:

[0026] Memory, used to store executable instructions;

[0027] The processor, when executing executable instructions stored in the memory, implements the matching processing method of the cluster system provided in the embodiments of this application.

[0028] This application provides a computer-readable storage medium storing executable instructions, which, when executed by a processor, implement the matching processing method of the cluster system provided in this application.

[0029] The embodiments of this application have the following beneficial effects:

[0030] Based on the test network latency of each regional cluster corresponding to the first account, the expansion order of the regional clusters corresponding to the first account and the matching waiting time of the first account in each regional cluster are determined. This allows us to predict the expansion direction and speed of the regional clusters used for matching. According to the expansion order of the regional clusters corresponding to the first account and the matching waiting time of the first account in each regional cluster, matching processing for the first account is performed in at least one regional cluster. By performing matching processing based on the expansion direction and speed, matching processing efficiency can be improved while taking into account network latency. Attached Figure Description

[0031] Figure 1A-1B This is a schematic diagram of server partitioning in related technologies;

[0032] Figure 2 This is a schematic diagram of the matching processing system architecture of the cluster system provided in the embodiments of this application;

[0033] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application;

[0034] Figures 4A-4C This is a flowchart illustrating the matching process of the cluster system provided in this application embodiment;

[0035] Figure 5 This is a schematic diagram of the architecture of the matching processing method for the cluster system provided in the embodiments of this application;

[0036] Figure 6 This is a dynamic speed measurement diagram of the matching processing method of the cluster system provided in the embodiments of this application;

[0037] Figure 7 This is a schematic diagram of the regional cluster expansion sequence of the matching processing method of the cluster system provided in the embodiments of this application;

[0038] Figure 8 This is a schematic diagram of cross-cluster matching of the matching processing method of the cluster system provided in the embodiments of this application;

[0039] Figure 9 This is a schematic diagram of cross-cluster matching of the matching processing method of the cluster system provided in the embodiments of this application. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0041] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0042] In the following description, the terms "first, second, third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0044] In the implementation of this application, the collection and processing of relevant data should strictly comply with the requirements of relevant laws and regulations, obtain the informed consent or separate consent of the personal information subject, and carry out subsequent data use and processing within the scope of laws and regulations and the authorization of the personal information subject.

[0045] Before providing a further detailed description of the embodiments of this application, the nouns and terms involved in the embodiments of this application will be explained, and the nouns and terms involved in the embodiments of this application shall be interpreted as follows.

[0046] 1) Game background speed test server (EchoSvr): The game background speed test server supports message echoing of the User Datagram Protocol (UDP). It can be used to test the access requests of clients and obtain the network latency of the access requests.

[0047] 2) Match Server (MatchSvr): The match server can manage match pools for different modes, thus enabling team matching.

[0048] 3) Game Lobby Server: The game lobby server is responsible for connecting players after they enter the game and sending announcements to them. Players will enter the lobby server after logging in and after the game ends.

[0049] 4) Dedicated Server (DS): A dedicated server is a server specifically designed for one or more functions. For example, a server that provides game battle services, with one dedicated server process for each battle.

[0050] 5) Battle Server (DSAgent): The Battle Server is used to manage the creation and recycling of dedicated servers.

[0051] 6) Subzone: A subzone is a cluster of combat servers that are deployed in a specific region.

[0052] See Figure 1A , Figure 1A This is a diagram illustrating server partitioning in related technologies. If players worldwide communicate with the same regional cluster (e.g., the North American cluster in the North American region) through their accounts to engage in game battles, then all global player accounts will enter that regional cluster for matchmaking. Since global user accounts can be concentrated in this regional cluster for matchmaking, the number of accounts participating in matchmaking is the largest, resulting in the shortest matchmaking wait time. However, since users' geographical locations are distributed around the world, uniformly accessing the same regional cluster will lead to higher latency for clients in distant regions during subsequent game battles. For example, the network latency for Asian users' accounts accessing the North American cluster through their clients is relatively long, up to 250 milliseconds.

[0053] See Figure 1B , Figure 1BThis is a diagram illustrating server partitioning in related technologies. If global players communicate with corresponding regional clusters (e.g., a North American cluster in North America, a European cluster in Europe, and an Asian cluster in Asia) through their accounts to engage in game battles, users in different regions can reduce network latency by accessing the nearest regional cluster through their accounts. For example, the network latency for an Asian user's account accessing the Asian cluster through the client is only 60 milliseconds. If global user accounts need to be placed in different regional clusters for matchmaking, it is equivalent to dividing the large group of global user accounts into many small groups, resulting in fewer accounts participating in matchmaking in a single regional cluster and longer matchmaking wait times.

[0054] In related technologies, global matching solutions typically employ the following implementation methods: First, regional division at the product level, such as North America and Europe, mitigates network latency for access from different regions and allows users to choose their region. However, this naturally divides users into several different regional clusters, resulting in different matching pools and thus longer matching times and response times. Second, manual configuration can be used, with an optimal list of regional clusters statically configured for each geographic region. During matching, users are placed into the designated regional clusters based on their geographic location.

[0055] Current solutions in related technologies focus on deploying multiple regional clusters to reduce network latency through proximity-based access. However, when the matching time between regional clusters before the game starts is long, such as when there are few users in a single regional cluster, the waiting time can be very long. Therefore, these technologies do not solve the problem of excessively long waiting times, and the operation and maintenance configuration of new regional clusters is complex and not automated enough. The first implementation naturally divides users into several different regional clusters, forming multiple corresponding matching pools. The smaller number of users in each matching pool increases the matching waiting time. Furthermore, the coarse-grained division into regions like Europe and North America results in large geographical spans, leading to higher network latency for users in remote areas within some regions. The second implementation's main problem is cumbersome configuration; each new regional cluster requires manual configuration adjustments, and manually configured regional clusters may not provide the optimal network experience.

[0056] This application provides a matching processing method, apparatus, electronic device, computer-readable storage medium, and computer program product for a cluster system, which can improve matching processing efficiency while taking into account network latency. The following describes exemplary applications of the electronic device provided in this application. The electronic device provided in this application can be implemented as various types of user terminals such as laptops, tablets, desktop computers, set-top boxes, and mobile devices (e.g., mobile phones, portable music players, personal digital assistants, dedicated messaging devices, portable gaming devices), or as a server. The following describes exemplary applications when the device is implemented as a server.

[0057] See Figure 2 , Figure 2 This is a schematic diagram of the architecture of the matching processing system of the cluster system provided in the embodiment of this application. The terminal 400 is connected to the server 200 through the network 300. The network 300 can be a wide area network or a local area network, or a combination of the two.

[0058] In some embodiments, a speed test processing request is received from the terminal 400 corresponding to the first account and sent to the server 200. The server 200 performs speed test processing on each regional cluster to obtain the test network latency of the first account for each regional cluster. Based on the test network latency of the first account for each regional cluster, the server 200 determines the regional cluster expansion order of the first account in multiple regional clusters and the matching waiting time of the first account in each regional cluster. The server 200 performs the matching processing of the first account for the cluster system according to the regional cluster expansion order of the first account in multiple regional clusters and the matching waiting time of the first account in each regional cluster.

[0059] In some embodiments, server 200 may be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. Terminal 400 may be a smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smartwatch, etc., but is not limited thereto. Terminals and servers can be directly or indirectly connected via wired or wireless communication, which is not limited in this embodiment.

[0060] In some embodiments, the terminal or server can implement the matching processing method of the cluster system provided in this application by running a computer program. For example, the computer program can be a native program or software module in the operating system; it can be a native application (APP), that is, a program that needs to be installed in the operating system to run, such as a live streaming APP or an instant messaging APP; it can also be a mini-program, that is, a program that only needs to be downloaded into the browser environment to run; or it can be a mini-program that can be embedded in any APP. In short, the above-mentioned computer program can be any form of application, module or plugin.

[0061] Next, the structure of the electronic device for implementing the matching processing method of a cluster system provided in the embodiments of this application will be described. As before, the electronic device provided in the embodiments of this application may be... Figure 2 Server 200 or Terminal 400. See also Figure 3 , Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiment of this application. The electronic device is described using server 200 as an example. Figure 3 The server 200 shown includes at least one processor 210, memory 250, and at least one network interface 220. The various components of server 200 are coupled together via a bus system 240. It is understood that the bus system 240 is used to implement communication between these components. In addition to a data bus, the bus system 240 also includes a power bus, a control bus, and a status signal bus. However, for clarity, ... Figure 3 The general labeled all buses as Bus System 240.

[0062] Processor 210 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0063] The memory 250 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state storage, hard disk drives, optical disk drives, etc. The memory 250 may optionally include one or more storage devices physically located away from the processor 210.

[0064] The memory 250 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), and the volatile memory may be random access memory (RAM). The memory 250 described in this application embodiment is intended to include any suitable type of memory.

[0065] In some embodiments, memory 250 is capable of storing data to support various operations, examples of which include programs, modules, and data structures or subsets or supersets thereof, as illustrated below.

[0066] Operating system 251 includes system programs for handling various basic system services and performing hardware-related tasks, such as the framework layer, core library layer, driver layer, etc., for implementing various basic business functions and handling hardware-specific tasks.

[0067] The network communication module 252 is used to reach other computing devices via one or more (wired or wireless) network interfaces 220, such as Bluetooth, WiFi, and Universal Serial Bus (USB).

[0068] In some embodiments, the matching processing device of the cluster system provided in this application can be implemented in software. Figure 3 A matching processing device 255 for a cluster system, stored in memory 250, is shown. This device can be software in the form of programs and plug-ins, and includes the following software modules: a speed measurement module 2551, a sequence module 2552, a waiting module 2553, and a matching module 2554. These modules are logically connected and can therefore be arbitrarily combined or further separated according to their implemented functions. The functions of each module will be described below.

[0069] The matching processing method of the cluster system provided in this application embodiment will be described in conjunction with the exemplary application and implementation of the server provided in the embodiments of this application.

[0070] See Figure 4A , Figure 4A This is a flowchart illustrating the matching process of a cluster system provided in this application embodiment. The cluster system includes multiple regional clusters and will combine... Figure 4A Steps 101 to 104 are described below.

[0071] In step 101, dynamic speed testing is performed on each regional cluster to obtain the test network latency for each regional cluster corresponding to the first account.

[0072] As an example, dynamic speed testing is a test of the communication speed between the client of the first account and the regional cluster. Since the services subsequently provided to the first account are provided through the regional cluster, the network latency between the client and the regional cluster is crucial.

[0073] In some embodiments, see Figure 4B , Figure 4B This is a flowchart illustrating the matching process of the cluster system provided in this application embodiment. In step 101, dynamic speed testing is performed on each regional cluster to obtain the test network latency of the first account for each regional cluster. Figure 4B Steps 1011 to 1012 shown are implemented.

[0074] In step 1011, the cluster address of the regional cluster is sent to the client of the first account so that the client can perform dynamic speed test processing for each regional cluster based on the cluster address.

[0075] In step 1012, the test network latency reported by the client is received, wherein the test network latency includes the network latency of the first account accessing each regional cluster.

[0076] As an example, the client sends a User Datagram Protocol (UDP) speed test request to the game's backend speed test server and calculates the network latency from the client to different regional clusters. The client then aggregates the network latency data from different regional clusters and reports it to the game's backend lobby server. An example of the aggregated data is as follows: delay_data = {{Regional Cluster 1, 150 milliseconds}, {Regional Cluster 2, 50 milliseconds}, {Regional Cluster 3, 250 milliseconds}}.

[0077] In some embodiments, sending the cluster address of the regional cluster to the client of the first account in step 1011 can be achieved by performing at least one of the following processes: periodically sending the cluster address of each regional cluster to the client in response to receiving a periodically sent address acquisition request from the client; or sending the cluster address of each regional cluster to the client in response to receiving a login request from the client. These two implementations can ensure the real-time performance and accuracy of the speed measurement results.

[0078] As an example, after the first account logs into the game's backend lobby server, it can obtain the address (cluster address) of the game's backend speed test server in each regional cluster, or the first account can periodically obtain the address (cluster address) of the game's backend speed test server in each regional cluster through the game's backend lobby server.

[0079] In some embodiments, before sending the cluster address of the regional cluster to the client of the first account, in response to the expansion of the cluster system to add a new regional cluster, the cluster address of the new regional cluster is obtained; the step 1011 of sending the cluster address of the regional cluster to the client of the first account can be implemented by performing at least one of the following processes: in response to receiving a periodically sent address acquisition request from the client, periodically sending the cluster address of the new regional cluster and the cluster address of each regional cluster to the client; in response to receiving a login request from the client, sending the cluster address of the new regional cluster and the cluster address of each regional cluster to the client. Through the embodiments of this application, even if the cluster system automatically expands, real-time and accurate speed measurement can still be achieved, thereby improving the reliability of subsequent matching schemes.

[0080] As an example, each regional cluster deploys a game background speed test server. When a new regional cluster is dynamically expanded, the user's client can also dynamically obtain the address of the new game background speed test server and perform network speed tests and data reporting. After the first account logs into the game background lobby server, it can obtain the address of the game background speed test server (cluster address) of the new regional cluster, or the first account can periodically obtain the address of the game background speed test server (cluster address) of the new regional cluster through the game background lobby server.

[0081] In step 102, the expansion order of the regional clusters corresponding to the first account is determined based on the test network latency of each regional cluster corresponding to the first account.

[0082] In some embodiments, determining the expansion order of regional clusters for the first account based on the test network latency of each regional cluster in step 102 can be achieved through the following technical solution: Based on the test network latency of the first account accessing each regional cluster, sort the multiple regional clusters in ascending order to obtain an ascending sort result; use the ascending sort result as the expansion order of the first account among the multiple regional clusters. By determining the expansion order of the regional clusters according to the test network latency of each regional cluster, the minimum network latency can be provided to the user during game battles after matchmaking ends.

[0083] As an example, see Figure 7 , Figure 7This is a schematic diagram of the regional cluster expansion order of the matching processing method of the cluster system provided in this application embodiment. According to the different network latency of users to different regional clusters, the regional clusters are sorted to distinguish priorities. For example, taking the latency of account A to regional cluster 1, regional cluster 2, and regional cluster 3 as 150 milliseconds, 50 milliseconds, and 250 milliseconds respectively, then the latency effect of user access to regional clusters is that regional cluster 2 is better than regional cluster 1, and regional cluster 1 is better than regional cluster 3. The ascending order is regional cluster 2, regional cluster 1, and regional cluster 3. Therefore, the regional cluster expansion order is regional cluster 2, regional cluster 1, and regional cluster 3. Thus, account A is given priority to enter regional cluster 2 for matching. Then, the matching processing of account A in regional cluster 2 is maintained, while account A is also allowed to enter regional cluster 1 for matching. Finally, the matching processing of account A in regional cluster 2 and regional cluster 1 is maintained, while account A is also allowed to enter regional cluster 3 for matching.

[0084] In step 103, the matching waiting time of the first account in each regional cluster is determined based on the test network latency of the first account corresponding to each regional cluster.

[0085] In some embodiments, see Figure 4C , Figure 4C This is a flowchart illustrating the matching process of the cluster system provided in this application embodiment. In step 103, based on the test network latency of the first account corresponding to each regional cluster, the matching waiting time of the first account in each regional cluster is determined. Figure 4C Steps 1031 to 1032 shown are implemented.

[0086] In step 1031, the following data are obtained for each regional cluster: initial waiting time, network latency parameters, and conversion ratio parameters.

[0087] In step 1032, the following processing is performed for each regional cluster: based on the initial waiting time, network latency parameters, and conversion ratio parameters, a matching waiting time that is positively correlated with the test network latency of the regional cluster is determined.

[0088] As an example, all regional clusters in a cluster system can have the same initial wait time, network latency parameters, and conversion ratio parameters, or each regional cluster can have its own specific initial wait time, network latency parameters, and conversion ratio parameters.

[0089] In some embodiments, the determination of the matching waiting time positively correlated with the test network latency of the regional cluster in step 1032 based on the initial waiting time, network latency parameters, and conversion ratio parameters can be achieved through the following technical solution: determining the difference between the test network latency of the regional cluster and the network latency parameters of the regional cluster; determining the ratio of the difference to the conversion ratio parameters; and determining the matching waiting time by summing the ratio with the initial waiting time.

[0090] As an example, in order to determine the matching speed and direction of cross-region cluster matching, this application embodiment provides the introduction of the expansion speed to dynamically calculate the waiting time of cross-region cluster matching. Considering that the longer the matching waiting time, the more tolerable the relatively high network latency, otherwise it will lead to unlimited waiting or matching timeout, it is set that an additional 2 milliseconds of access latency can be tolerated for every additional 1 second of waiting, that is, the ratio between 2 milliseconds and 1 second is 2 (conversion ratio parameter, no need to consider unit difference here), and then the waiting time can be calculated by referring to the following formula (1):

[0091] Waiting time = initial waiting time + (new_region cluster_delay – 60 milliseconds) / 2 (1);

[0092] The initial waiting time is a set threshold (matching time) for the optimal regional cluster, for example, 30 seconds. new_regional cluster_delay represents the network latency when crossing the regional cluster. The network latency parameter is 60 milliseconds. Since an additional 2 milliseconds of access latency can be tolerated for every additional second of waiting, the conversion ratio parameter is 2.

[0093] As an example, see Figure 9 , Figure 9 This is a schematic diagram of cross-cluster matching in the cluster system matching processing method provided in this application embodiment. Account A needs to wait 30 seconds + (150 milliseconds – 60 milliseconds) / 2 milliseconds = 75 seconds to move from region cluster 2 to region cluster 1. Account B needs to wait 30 seconds + (200 milliseconds – 60 milliseconds) / 2 milliseconds = 100 seconds to move from region cluster 1 to region cluster 2. Therefore, by introducing the concept of expansion speed, the waiting time for cross-region clusters is dynamically calculated. The higher the network latency of a region cluster, the longer the matching waiting time. Ultimately, account A prioritizes moving to region cluster 1 for matching, thus achieving the goal of directional cross-region cluster matching.

[0094] In some embodiments, obtaining the initial waiting time, network latency parameter, and conversion ratio parameter for each regional cluster in step 1031 can be achieved through the following technical solution: performing the following processing for each regional cluster: in response to the setting operation for the initial waiting time, network latency parameter, and conversion ratio parameter, obtaining the initial waiting time, network latency parameter, and conversion ratio parameter of the regional cluster.

[0095] As an example, network latency parameters, conversion ratio parameters, and initial waiting time can be configured based on user selection. The server can include a user interface to receive setting operations and obtain the initial waiting time, network latency parameters, and conversion ratio parameters of the regional cluster based on the setting operations.

[0096] In some embodiments, determining the matching wait time of the first account in each regional cluster based on the test network latency of the first account in each regional cluster in step 103 can be achieved through the following technical solution: A neural network model is invoked to perform the following processing on the matching wait time of each regional cluster: Based on the test network latency of the regional cluster corresponding to the first account, the latency features of the regional cluster corresponding to the first account are extracted; based on the historical matching records of the first account, the historical matching features of the first account are extracted; the latency features and historical matching features are fused to obtain fused features; the fused features are mapped to obtain the matching wait time of the first account in the regional cluster. The matching wait time can be automatically determined through the neural network model, thereby improving the accuracy of the matching wait time.

[0097] As an example, historical matching record samples of the sample account are obtained, historical matching feature samples are extracted from the historical matching record samples, speed test samples of the sample account are obtained, delay feature samples are extracted from the speed test samples, the delay feature samples and historical matching feature samples are fused to obtain fused feature samples, the predicted matching waiting time is obtained based on the fused feature samples, the error between the predicted matching waiting time and the actual waiting time of the sample account is determined, and the parameters of the neural network model are updated based on the error to obtain the trained neural network model.

[0098] In step 104, the first account is dynamically configured to at least one regional cluster for matching processing according to the expansion order of the corresponding regional cluster and the matching waiting time of the first account in each regional cluster.

[0099] In some embodiments, the number of regional clusters in the cluster system is N, where N is an integer greater than or equal to 2, n is an integer variable starting from 1 and increasing incrementally, and 0 < n < N; in step 104, the first account is dynamically configured into at least one regional cluster for matching processing according to the regional cluster expansion order corresponding to the first account and the matching waiting time of the first account in each regional cluster, which can be achieved through the following technical solution: perform matching processing for the first account in the nth regional cluster in the regional cluster expansion order, and time the matching processing of the nth regional cluster; when the timing reaches the matching waiting time corresponding to the nth regional cluster and the matching has not been successful yet, continue to perform matching processing for the first account in the nth regional cluster and transfer to perform matching processing for the first account in the (n + 1)th regional cluster in the regional cluster expansion order.

[0100] In some embodiments, when the timing has not reached the matching waiting time corresponding to the nth regional cluster and the matching is successful, provide services to the first account based on the matching result and stop performing matching processing for the first account in the subsequent regional clusters of the cluster system; where the subsequent regional clusters are the regional clusters ranked after the nth regional cluster in the cluster expansion order.

[0101] Performing matching processing based on the expansion direction and expansion speed can improve the matching processing efficiency while taking network latency into account.

[0102] As an example, the regional cluster expansion order of the first account includes regional cluster A, regional cluster B, and regional cluster C, that is, regional cluster A is the 1st regional cluster in the regional cluster expansion order, regional cluster B is the 2nd regional cluster in the regional cluster expansion order, and regional cluster C is the 3rd regional cluster in the regional cluster expansion order.

[0103] As an example, matchmaking for the first account is performed in the first regional cluster, and a timer is set for this matchmaking process. When the timer reaches the matchmaking waiting time for the corresponding first regional cluster and a match has not yet been successfully made, the matchmaking for the first account continues to be performed in the first regional cluster, and the process then switches to the second regional cluster in the regional cluster expansion order. When the timer does not reach the matchmaking waiting time for the corresponding first regional cluster and a match is successfully made, services are provided to the first account based on the matchmaking result, and matchmaking for the first account stops in subsequent regional clusters of the cluster system. These subsequent regional clusters are those that follow the first regional cluster in the cluster expansion order. In regional cluster 1, in addition to the first account, other accounts participate in matchmaking. Matchmaking can involve the first account being matched with an account of similar level to form a two-player game, or the first account being matched with a set number of accounts to form a team game.

[0104] As an example, the matching process for the first account continues in the already matched regional clusters, that is, the matching process for the first account continues in the first regional cluster, and the matching process for the first account is also executed in the second regional cluster in the regional cluster expansion order. The matching process executed in the second regional cluster is timed. When the timer reaches the matching waiting time of the corresponding second regional cluster and no match has been successfully matched, the matching process for the first account continues to be executed in the first and second regional clusters, and the process is switched to the third regional cluster in the regional cluster expansion order to execute the matching process for the first account.

[0105] The following will describe an exemplary application of the embodiments of this application in a game matchmaking scenario.

[0106] In some embodiments, see Figure 5 , Figure 5 This is a schematic diagram of the architecture of the matching processing method of the cluster system provided in this application embodiment. The server of the lobby receives the speed test processing request sent by the terminal corresponding to the first account. The server performs dynamic speed test processing on the North American regional cluster, the European regional cluster, and the Asian regional cluster to obtain the test network latency of the first account for each regional cluster. Based on the test network latency of the first account for each regional cluster, the server determines the regional cluster expansion order of the first account and the matching waiting time of the first account in each regional cluster. In response to the server receiving the matching request sent by the terminal corresponding to the first account, the server performs matching processing for the first account in at least one regional cluster according to the regional cluster expansion order of the first account in multiple regional clusters and the matching waiting time of the first account in each regional cluster. When the matching is successful, the first account can play the game.

[0107] Matchmaking is a necessity in gaming scenarios, such as ranked matchmaking. The specific matchmaking scheme is a purely backend solution. In a game's matchmaking system, it's necessary to comprehensively consider both network access latency and matchmaking wait time. These two durations often conflict, requiring a delicate balance. This is a pain point and challenge for every matchmaking project targeting global users. During the implementation of this application's embodiments, the applicant found that the more players simultaneously matched, the easier it was to meet the player requirement for a single match, and the shorter the player matchmaking wait time. However, considering network latency, matchmaking would need to be divided into multiple regional clusters for proximity-based access, further fragmenting the user base and increasing wait times. The matchmaking processing method provided in this application's embodiments achieves a dynamic balance between network access latency and matchmaking wait time, resulting in an optimal user experience.

[0108] In some embodiments, see Figure 6 Each regional cluster deploys a game background speed test server. When a new regional cluster is dynamically added, the user's client can also dynamically obtain the address of the new game background speed test server and perform network speed testing and data reporting. The detailed process is as follows: 1. The game background speed test server in each regional cluster reports its external address (network address: port number) to the game background lobby server via heartbeat. Therefore, for newly added regional clusters, the address of the game background speed test server of the newly added regional cluster will also be dynamically reported to the game background lobby server; 2. After logging into the game background lobby server, the user's account can obtain the address of the game background speed test server of each regional cluster, or the user's account can periodically obtain the address of the game background speed test server of each regional cluster through the game background lobby server; 3. The client sends a user datagram protocol speed test request to the game background speed test server and calculates the network latency from the client to different regional clusters; 4. The client summarizes the network latency data to different regional clusters and reports it to the game background lobby server. An example of the summarized data is as follows: delay_data ={{Regional cluster 1, 150 milliseconds}, {Regional cluster 2, 50 milliseconds}, {Regional cluster 3, 250 milliseconds}}.

[0109] In some embodiments, see Figure 7Based on the varying network latency to different regional clusters, the regional clusters are prioritized. For example, if account A's latency to regional clusters 1, 2, and 3 is 150 milliseconds, 50 milliseconds, and 250 milliseconds respectively, then the latency advantage for user access to regional clusters is: regional cluster 2 is better than regional cluster 3, and regional cluster 1 is better than regional cluster 3. Therefore, account A is prioritized to access regional cluster 2 for matching. If there are many users, matching can be completed quickly, thus account A obtains the optimal network access latency and a shorter matching wait time when accessing regional cluster 2. If the number of users is small, and account A's matching wait time in regional cluster 2 exceeds a set threshold (e.g., 30 seconds), account A will simultaneously be placed in regional cluster 1 for matching. Each regional cluster has a corresponding matching pool, meaning account A is simultaneously placed in the matching pools of both regional cluster 1 and regional cluster 2. Therefore, if the number of users is small, as the matching wait time increases, account A will eventually enter the matching pools of regional cluster 2, regional cluster 1, and regional cluster 3 sequentially. When account A enters the matching pool of regional cluster 1, it remains in the matching pool of regional cluster 2, and when it enters the matching pool of regional cluster 3, it remains in the matching pools of both regional cluster 2 and regional cluster 1. Overall, when the number of users is large, matching is prioritized in the optimal regional cluster (the one with the lowest network latency). When the number of users is small, the matching wait time becomes increasingly longer, so the pool can be gradually expanded to include account A in more regional clusters, effectively increasing account A's matching pool and thus reducing the matching wait time.

[0110] In some embodiments, see Figure 8 , Figure 8This is a schematic diagram of cross-cluster matching in the matching processing method of the cluster system provided in this application embodiment. The network latency for account A to access regional cluster 1 and regional cluster 2 is 150 milliseconds and 50 milliseconds, respectively, and the network latency for account B to access regional cluster 1 and regional cluster 2 is 60 milliseconds and 200 milliseconds, respectively. In the default optimal situation, account A enters the matching pool of regional cluster 2 for matching, and account B enters the matching pool of regional cluster 1 for matching. When the number of users is small and the matching waiting time exceeds the set threshold of 30 seconds, cross-regional cluster matching will be triggered. Account A enters regional cluster 2, and account B enters regional cluster 1. The number of users in the matching pools of regional cluster 1 and regional cluster 2 increases simultaneously, so both may be able to match successfully. However, considering the overall network latency analysis, since account A's latency to access regional cluster 1 is 150 milliseconds and account B's latency to access regional cluster 2 is 200 milliseconds, account A's latency to access regional cluster 1 is lower. Therefore, it is more desirable to successfully match in the matching pool of regional cluster 1. Ultimately, both account A and account B enter regional cluster 1 to fight. In summary, even cross-regional cluster matching is not completely equal; speed and direction are also required. In the above example, it is more desirable for account A to enter regional cluster 1 faster.

[0111] In some embodiments, in order to determine the matching speed and direction of cross-region cluster matching, this application embodiment provides the introduction of expansion speed to dynamically calculate the waiting time of cross-region cluster matching. Considering that the longer the matching waiting time, the more tolerable the relatively high network latency, otherwise it will lead to unlimited waiting or matching timeout, it is set that an additional 2 milliseconds of access latency can be tolerated for every additional 1 second of waiting. Therefore, the waiting time can be calculated by referring to the following formula (2):

[0112] Waiting time = initial waiting time + (new_region cluster_delay – 60 milliseconds) / 2 (2);

[0113] The initial waiting time is a set threshold (matching time) for the optimal regional cluster, for example, 30 seconds. new_regional cluster_delay represents the network latency when crossing regional clusters.

[0114] In some embodiments, see Figure 9 , Figure 9This is a schematic diagram of cross-cluster matching in the cluster system matching processing method provided in this application embodiment. Account A needs to wait 30 seconds + (150 milliseconds – 60 milliseconds) / 2 milliseconds = 75 seconds to move from region cluster 2 to region cluster 1. Account B needs to wait 30 seconds + (200 milliseconds – 60 milliseconds) / 2 milliseconds = 100 seconds to move from region cluster 1 to region cluster 2. Therefore, by introducing the concept of expansion speed, the waiting time for cross-region clusters is dynamically calculated. The higher the network latency of a region cluster, the longer the matching waiting time. Ultimately, account A prioritizes moving to region cluster 1 for matching, thus achieving the goal of directional cross-region cluster matching.

[0115] By employing dynamic speed testing, tiered matching, and the introduction of expanded access speeds, users can achieve nearest-neighbor access while avoiding excessively long waiting times when the number of users is small. Ultimately, this allows more users to achieve nearest-neighbor access within an acceptable matching wait time. Specifically, multi-region cluster matching, dynamic speed testing, and nearest-neighbor access ensure a better network experience. Tiered matching and dynamically expanding regional clusters optimize waiting times. Finally, dynamically expanding regional clusters according to specific directions and speeds further optimizes access latency.

[0116] The matching processing method for the cluster system provided in this application can be applied to global matching projects. It features full automation and adaptability, achieving a balance between network latency and waiting time. Through dynamic speed measurement, the network latency of users to different regional clusters can be obtained. Based on network latency, different regional clusters are prioritized, and finally, the expansion direction is determined according to priority, gradually expanding the matching range of regional clusters at a specific speed. Ultimately, the entire matching process and the expansion of regional clusters require no manual decision-making or configuration, and can adapt to the current infrastructure. Each addition of a regional cluster inevitably reduces the network latency for some users, and the matching waiting time remains within a controllable range, exhibiting a continuous optimization and cumulative effect.

[0117] It is understood that in the embodiments of this application, data such as user information are involved. When the embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0118] The following description continues to illustrate the exemplary structure of the matching processing device 255 of the cluster system provided in this application embodiment as a software module. In some embodiments, such as Figure 3As shown, the software modules in the matching processing device 255 of the cluster system stored in the memory 250 may include: a speed measurement module 2551, used to perform dynamic speed measurement processing on each regional cluster to obtain the test network latency of the first account for each regional cluster; a sequence module 2552, used to determine the regional cluster expansion order of the first account in multiple regional clusters based on the test network latency of the first account for each regional cluster; a waiting module 2553, used to determine the matching waiting time of the first account in each regional cluster based on the test network latency of the first account for each regional cluster; and a matching module 2554, used to dynamically configure the first account to at least one regional cluster for matching processing according to the regional cluster expansion order of the first account in multiple regional clusters and the matching waiting time of the first account in each regional cluster.

[0119] In some embodiments, the speed test module 2551 is further configured to: send the cluster address of the regional cluster to the client of the first account, so that the client performs dynamic speed test processing for each regional cluster based on the cluster address; and receive the test network latency reported by the client, wherein the test network latency includes the network latency of the first account accessing each regional cluster.

[0120] In some embodiments, the speed measurement module 2551 is further configured to: perform at least one of the following processes: in response to receiving an address acquisition request periodically sent by the client, periodically send the cluster address of each regional cluster to the client; in response to receiving a login request from the client, send the cluster address of each regional cluster to the client.

[0121] In some embodiments, the speed measurement module 2551 is further configured to: before sending the cluster address of the regional cluster to the client of the first account, in response to the expansion of the cluster system to add a new regional cluster, obtain the cluster address of the new regional cluster; and perform at least one of the following processes: in response to receiving an address acquisition request periodically sent by the client, periodically send the cluster address of the new regional cluster and the cluster address of each regional cluster to the client; in response to receiving a login request from the client, send the cluster address of the new regional cluster and the cluster address of each regional cluster to the client.

[0122] In some embodiments, the sequence module 2552 is further configured to: sort multiple regional clusters in ascending order based on the test network latency of the first account accessing each regional cluster, and obtain an ascending order sorting result; and use the ascending order sorting result as the regional cluster expansion order of the first account in multiple regional clusters.

[0123] In some embodiments, the waiting module 2553 is further configured to: obtain the following data for each regional cluster: initial waiting time, network delay parameter, and conversion ratio parameter; perform the following processing for each regional cluster: based on the initial waiting time, network delay parameter, and conversion ratio parameter, determine a matching waiting time that is positively correlated with the test network delay of the regional cluster.

[0124] In some embodiments, the waiting module 2553 is further configured to: determine the difference between the test network delay of the regional cluster and the network delay parameter of the regional cluster; determine the ratio of the difference to the conversion ratio parameter; determine the sum of the ratio and the initial waiting time as the matching waiting time.

[0125] In some embodiments, the waiting module 2553 is further configured to: perform the following processing for each regional cluster: in response to a setting operation on the initial waiting time, network delay parameter, and conversion ratio parameter, obtain the initial waiting time of the regional cluster, the network delay parameter of the regional cluster, and the conversion ratio parameter of the regional cluster.

[0126] In some embodiments, the waiting module 2553 is further configured to: call a neural network model to perform the following processing on the matching waiting time of each regional cluster: based on the test network delay of the regional cluster corresponding to the first account, extract the delay feature of the regional cluster corresponding to the first account; based on the historical matching record of the first account, extract the historical matching feature of the first account; perform a fusion processing on the delay feature and the historical matching feature to obtain a fusion feature; perform a mapping processing on the fusion feature to obtain the matching waiting time of the first account in the regional cluster.

[0127] In some embodiments, the number of regional clusters in the cluster system is N, N is an integer greater than or equal to 2, n is an integer variable starting from 1 and increasing incrementally, and 0 < n < N; the matching module 2554 is further configured to: perform a matching process for the first account in the nth regional cluster in the regional cluster expansion order, and time the matching process; when the timing reaches the matching waiting time corresponding to the nth regional cluster and the matching is not successful yet, continue to perform the matching process for the first account in the nth regional cluster and transfer to perform the matching process for the first account in the (n + 1)th regional cluster in the regional cluster expansion order.

[0128] In some embodiments, the matching module 2554 is further configured to: when the timing does not reach the matching waiting time corresponding to the nth regional cluster and the matching is successful, provide services to the first account based on the matching result and stop performing the matching process for the first account in the subsequent regional clusters in the cluster system; wherein, the subsequent regional clusters are the regional clusters ranked after the nth regional cluster in the regional cluster expansion order.

[0129] This application provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the matching processing method of the cluster system described in this application.

[0130] This application provides a computer-readable storage medium storing executable instructions. When these executable instructions are executed by a processor, they cause the processor to execute the matching processing method of the cluster system provided in this application. For example, ... Figures 4A-4C The matching processing method of the cluster system is shown.

[0131] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a variety of devices including one or any combination of the above-mentioned memories.

[0132] In some embodiments, executable instructions may take the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0133] As an example, executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple collaborating files (e.g., a file that stores one or more modules, subroutines, or code sections).

[0134] As an example, executable instructions can be deployed to execute on a single computing device, or on multiple computing devices located in one location, or on multiple computing devices distributed across multiple locations and interconnected via a communication network.

[0135] In summary, by using the test network latency of each regional cluster corresponding to the first account in this application embodiment, the expansion order of the regional clusters corresponding to the first account and the matching waiting time of the first account in each regional cluster can be determined. This allows for the prediction of the expansion direction and speed of the regional clusters used for matching. According to the expansion order of the regional clusters corresponding to the first account and the matching waiting time of the first account in each regional cluster, matching processing for the first account is performed in at least one regional cluster. By performing matching processing based on the expansion direction and speed, matching processing efficiency can be improved while taking into account network latency.

[0136] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and scope of this application are included within the scope of protection of this application.

Claims

1. A matching processing method of a cluster system, characterized by, The cluster system includes multiple regional clusters, and the method includes: Speed ​​testing is performed on each of the aforementioned regional clusters to obtain the test network latency for each of the aforementioned regional clusters corresponding to the first account; Based on the test network latency of each of the regional clusters corresponding to the first account, the expansion order of the regional clusters corresponding to the first account is determined; Obtain the following data for each of the said regional clusters: initial waiting time, network latency parameters, and conversion ratio parameters; For each of the said regional clusters, the following processing is performed: determining the difference between the test network latency of the regional cluster and the network latency parameter of the regional cluster; determining the ratio of the difference to the conversion ratio parameter; and summing the ratio with the initial waiting time to determine the matching waiting time; wherein, the conversion ratio parameter is the ratio of the additional access latency tolerated for each additional preset waiting time to the preset waiting time. According to the expansion order of the regional clusters corresponding to the first account and the matching waiting time, the first account is dynamically configured to at least one of the regional clusters for matching processing.

2. The method according to claim 1, characterized in that, The step of performing speed testing on each of the regional clusters to obtain the test network latency for each regional cluster corresponding to the first account includes: Send the cluster address of the regional cluster to the client of the first account, so that the client performs speed test processing for each regional cluster based on the cluster address; The system receives speed test results reported by the client, wherein the speed test results include the test network latency of the first account accessing each of the regional clusters.

3. The method according to claim 2, characterized in that, Sending the cluster address of the regional cluster to the client of the first account includes: Perform at least one of the following processes: The cluster address of each regional cluster is periodically sent to the client; In response to receiving a login request from the client, the cluster address of each of the regional clusters is sent to the client.

4. The method according to claim 2, characterized in that, Before sending the cluster address of the regional cluster to the client of the first account, the method further includes: In response to the expansion of the cluster system to create a new regional cluster, the cluster address of the new regional cluster is obtained; Sending the cluster address of the regional cluster to the client of the first account includes: Perform at least one of the following processes: The client is periodically sent with the cluster address of the newly added regional cluster and the cluster address of each regional cluster. In response to receiving a login request from the client, the system sends the cluster address of the newly added regional cluster and the cluster address of each of the regional clusters to the client.

5. The method according to claim 1, characterized in that, The step of determining the expansion order of the regional clusters corresponding to the first account based on the test network latency of each regional cluster corresponding to the first account includes: Based on the test network latency of the first account accessing each of the regional clusters, the multiple regional clusters are sorted in ascending order to obtain the ascending order sorting result. The ascending sort result is used as the regional cluster expansion order corresponding to the first account.

6. The method according to claim 1, characterized in that, The acquisition of the following data for each of the regional clusters includes: initial waiting time, network latency parameters, and conversion ratio parameters, including: Perform the following processing for each of the aforementioned regional clusters: Obtain the initial waiting time, network latency parameter, and conversion ratio parameter selected and configured by the user; In response to setting operations for the initial waiting time, the network latency parameter, and the conversion ratio parameter, the initial waiting time of the regional cluster, the network latency parameter of the regional cluster, and the conversion ratio parameter of the regional cluster are obtained.

7. The method according to claim 1, characterized in that, The method further includes: The neural network model is invoked to perform the following processing on the matching wait time for each of the aforementioned regional clusters: Based on the test network latency of the regional cluster corresponding to the first account, the latency features of the regional cluster corresponding to the first account are extracted. Based on the historical matching records of the first account, extract the historical matching features of the first account; The delay features and the historical matching features are fused together to obtain fused features; The fusion features are mapped to obtain the matching waiting time of the first account in the regional cluster.

8. The method according to claim 1, characterized in that, The number of regional clusters in the cluster system is N, where N is an integer greater than or equal to 2, and n is an integer variable that increments from 1, and 0 < n < n. <n<N; The step of dynamically configuring the first account to at least one of the regional clusters for matching processing according to the expansion order of the corresponding regional clusters and the matching waiting time includes: In the nth regional cluster of the regional cluster expansion sequence, the matching process for the first account is performed, and the matching process of the nth regional cluster is timed. When the timer reaches the matching waiting time for the corresponding nth regional cluster and a match has not yet been successfully made, the matching process for the first account continues to be performed in the nth regional cluster, and then the process is switched to the (n+1)th regional cluster in the regional cluster expansion order to perform the matching process for the first account.

9. The method according to claim 8, characterized in that, The method further includes: When the timeout has not reached the matching waiting time of the corresponding nth regional cluster and the matching is successful, the service is provided to the first account based on the matching result, and the matching process for the first account is stopped in the subsequent regional clusters of the cluster system. The subsequent regional cluster is the regional cluster that follows the nth regional cluster in the regional cluster expansion order.

10. A matching processing device for a cluster system, characterized in that, The cluster system includes multiple regional clusters, and the device includes: The speed test module is used to perform speed test processing on each of the said regional clusters to obtain the test network latency of the first account for each of the said regional clusters; The sequence module is used to determine the expansion order of the regional clusters corresponding to the first account based on the test network latency of each of the regional clusters corresponding to the first account. The waiting module is used to obtain the following data for each of the said regional clusters: initial waiting time, network latency parameters, and conversion ratio parameters; For each of the said regional clusters, the following processing is performed: determining the difference between the test network latency of the regional cluster and the network latency parameter of the regional cluster; determining the ratio of the difference to the conversion ratio parameter; and summing the ratio with the initial waiting time to determine the matching waiting time; wherein, the conversion ratio parameter is the ratio of the additional access latency tolerated for each additional preset waiting time to the preset waiting time. The matching module is used to dynamically configure the first account to at least one of the regional clusters for matching processing according to the expansion order of the regional clusters corresponding to the first account and the matching waiting time.

11. The apparatus according to claim 10, characterized in that, The speed test module is also used to send the cluster address of the regional cluster to the client of the first account, so that the client performs speed test processing for each regional cluster based on the cluster address; The system receives speed test results reported by the client, wherein the speed test results include the test network latency of the first account accessing each of the regional clusters.

12. The apparatus according to claim 11, characterized in that, The speed measuring module is also used to perform at least one of the following processes: The cluster address of each regional cluster is periodically sent to the client; In response to receiving a login request from the client, the cluster address of each of the regional clusters is sent to the client.

13. The apparatus according to claim 11, characterized in that, The speed measurement module is also used to obtain the cluster address of the newly added regional cluster in response to the expansion of the cluster system. The speed measuring module is also used to perform at least one of the following processes: The client is periodically sent with the cluster address of the newly added regional cluster and the cluster address of each regional cluster. In response to receiving a login request from the client, the system sends the cluster address of the newly added regional cluster and the cluster address of each of the regional clusters to the client.

14. The apparatus according to claim 10, characterized in that, The sequence module is further configured to perform ascending sorting on the multiple regional clusters based on the test network latency of the first account accessing each of the regional clusters, and obtain the ascending sorting result. The ascending sort result is used as the regional cluster expansion order corresponding to the first account.

15. The apparatus according to claim 10, characterized in that, The waiting module is also configured to perform the following processing for each of the regional clusters: Obtain the initial waiting time, network latency parameter, and conversion ratio parameter selected and configured by the user; In response to setting operations for the initial waiting time, the network latency parameter, and the conversion ratio parameter, the initial waiting time of the regional cluster, the network latency parameter of the regional cluster, and the conversion ratio parameter of the regional cluster are obtained.

16. The apparatus according to claim 10, characterized in that, The waiting module is further configured to invoke a neural network model to perform the following processing on the matching waiting time for each of the regional clusters: Based on the test network latency of the regional cluster corresponding to the first account, the latency features of the regional cluster corresponding to the first account are extracted. Based on the historical matching records of the first account, extract the historical matching features of the first account; The delay features and the historical matching features are fused together to obtain fused features; The fusion features are mapped to obtain the matching waiting time of the first account in the regional cluster.

17. An electronic device, characterized in that, The electronic device includes: Memory, used to store executable instructions; A processor, when executing executable instructions stored in the memory, implements the matching processing method of the cluster system according to any one of claims 1 to 9.

18. A computer-readable storage medium storing executable instructions, characterized in that, When the executable instructions are executed by the processor, they implement the matching processing method of the cluster system according to any one of claims 1 to 9.

19. A computer program product comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by the processor, they implement the matching processing method of the cluster system according to any one of claims 1 to 9.

Images