Aggregation system for multi-account message processing

Abstract

The invention relates to the technical field of instant messaging, and provides a multi-account message processing aggregation system which can stably and efficiently push message data. AI processing equipment of the aggregation system calls AI service and processes part of message data in a message data set to obtain a primarily screened message data set; the server aggregates the primarily screened message data set to obtain a session set; the server determines a minimum message data set required by the user equipment for interface rendering in the session set based on perception of the current view of the client of the instant messaging application; the data sharing device receives the minimum message data sets uploaded by the servers, summarizes the minimum message data sets of the same user to obtain a multi-account minimum data set of the same user, and sends the multi-account minimum data set to a storage unit; and the server obtains the multi-account minimum data set of the storage unit and sends the multi-account minimum data set to the client, so that the user equipment performs interface rendering based on the multi-account minimum data set.

Description

Technical Field

[0001] The present application relates to the field of instant messaging technology, and in particular to an aggregation system for multi-account message processing. Background Art

[0002] In insurance marketing scenarios, service sales personnel can communicate with customers through instant messaging applications. In some scenarios, such as during peak periods of group insurance business, service sales personnel will use multiple accounts of instant messaging applications to serve hundreds or even thousands of customers.

[0003] It is difficult to provide services solely relying on the native capabilities of the instant messaging application client. With the help of an aggregation system, the message data of multiple accounts of service and sales personnel can be distributed and pushed, so that service and sales personnel can aggregate multiple accounts on the same interface to communicate with customers and provide services to customers.

[0004] In this mode, the amount of message data that the aggregation system needs to push is extremely large. How to enable the aggregation system to push message data stably and efficiently is a problem to be solved. Summary of the invention

[0005] Based on this, it is necessary to provide an aggregation system for multi-account message processing to address the above technical issues.

[0006] The present application provides an aggregation system for multi-account message processing, the aggregation system comprising an AI processing device, a server, a data sharing device and a storage unit;

[0007] The AI ​​processing device is used to receive, for an account of an instant messaging application hosted in the system, a corresponding message data set pushed by a server of the instant messaging application;

[0008] The AI ​​processing device is used to call the AI ​​service to process the message data that can be automatically processed by AI in the message data set to obtain a preliminary screening message data set;

[0009] The server is used to receive the preliminary screening message data set, aggregate the preliminary screening message data set, and obtain a session set;

[0010] The server is configured to determine, in the session set, a minimum message data set required for the user device to perform interface rendering based on perception of the current view of the client of the instant messaging application;

[0011] The data sharing device is used to receive the minimum message data set uploaded by each of the servers, aggregate the minimum message data set of the same user to obtain a multi-account minimum data set of the same user, and send the multi-account minimum data set to the storage unit;

[0012] The server is used to obtain the multi-account minimum data set of the storage unit and send it to the corresponding client, so that the user device performs interface rendering based on the multi-account minimum data set.

[0013] In one embodiment, when the AI ​​processing device calls the AI ​​service to process the message data that can be automatically processed by AI in the message data set to obtain the preliminary screening message data set, it specifically includes:

[0014] The AI ​​processing device is used to call the AI ​​service to perform semantic recognition on the message data in the message data set;

[0015] The AI ​​processing device is further used to determine whether the preset question-answer knowledge base includes matching reply content according to the semantic recognition result;

[0016] The AI ​​processing device is further configured to reply based on the answer content if the preset question and answer knowledge base includes matching answer content;

[0017] The AI ​​processing device is also used to add the message data to the initial screening message data set if the preset question and answer knowledge base does not include matching reply content.

[0018] In one embodiment, when the AI ​​processing device makes a reply based on the reply content, the step specifically includes:

[0019] The AI ​​processing device is further used to call the PRA device to simulate the client and reply to the reply content.

[0020] In one embodiment, when the server aggregates the pre-screened message data set to obtain a conversation set, the process specifically includes:

[0021] The server is used to aggregate the pre-screened message data set based on the sender and receiver of the message to obtain a conversation set.

[0022] In one embodiment, the server determines the minimum message data set required for the user device to perform interface rendering in the session set based on the perception of the current view of the client of the instant messaging application, specifically including:

[0023] The server is used to receive operation data sent by a user device for a client of the instant messaging application;

[0024] The server is further used to structure the operation data to obtain view information of the view currently located by the client;

[0025] The server is further configured to determine, according to the session identifier carried in the view information, a session in the session set that matches the session identifier, so as to obtain a minimum message data set required for the user equipment to perform interface rendering.

[0026] In one embodiment, when the data sharing device sends the multi-account minimum data set to the storage unit, it specifically includes:

[0027] The data sharing device is used to divide the multi-account minimum data sets of multiple users into different storage units, so that the multi-account minimum data sets of the same user are sent to the same storage unit and the data amounts received by different storage units are basically the same.

[0028] In one embodiment, the storage unit is further used to determine a server that meets the requirements among a plurality of servers belonging to the local end according to the idleness of the server;

[0029] The storage unit is also used to send the multi-account minimum data set stored in the device to a server that meets the requirements.

[0030] In one embodiment,

[0031] The server is also used to determine the storage unit to which the local terminal belongs after the local terminal goes online, and to register the service with the storage unit;

[0032] The storage unit is also used to determine several servers belonging to the local end according to the servers that register services with the local device.

[0033] In one embodiment, when the storage unit determines a server that meets the requirements among a plurality of servers belonging to the local end according to the idleness of the server, the storage unit specifically includes:

[0034] The storage unit is also used to obtain the idleness of several servers belonging to the local end;

[0035] The storage unit is further used to sort the servers in order of idleness from small to large, and take the servers in the front order as the servers that meet the requirements;

[0036] Alternatively, the storage unit is further used to sort the servers in descending order of idleness, and use the servers ranked later as servers that meet the requirements.

[0037] In one embodiment, the idleness of the server includes at least one of the processor idleness and memory idleness of the server.

[0038] The above-mentioned multi-account message processing aggregation system includes an AI processing device, a server, a data sharing device and a storage unit; the AI ​​processing device is used to receive the corresponding message data set pushed by the server of the instant messaging application for the account of the instant messaging application hosted in this system; the AI ​​processing device is used to call the AI ​​service, process the message data that can be automatically processed by AI in the message data set, and obtain the preliminary screening message data set; the server is used to receive the preliminary screening message data set, aggregate the preliminary screening message data set, and obtain a session set; the server is used to determine the minimum message data set required for the user device to render the interface in the session set based on the perception of the current view of the client of the instant messaging application; the data sharing device is used to receive the minimum message data set uploaded by each server, and summarize the minimum message data set of the same user to obtain the multi-account minimum data set of the same user, and send the multi-account minimum data set to the storage unit; the server is used to obtain the multi-account minimum data set of the storage unit and send it to the corresponding client, so that the user device performs interface rendering based on the multi-account minimum data set. The aggregation system provided in the present application uses AI-assisted filtering, view perception and message data structure optimization to form the minimum message data set required for user device interface rendering. Finally, through the data sharing device, the minimum message data set of the same user is aggregated for push, thereby reducing the amount of message data that needs to be pushed to the client of the instant messaging application, and achieving stable and efficient push. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 A schematic diagram of a process involved in a multi-account message processing aggregation system in one embodiment;

[0041] Figure 2 The current view of the client in one embodiment;

[0042] Figure 3 A schematic diagram of a process of AI-assisted filtering in one embodiment;

[0043] Figure 4 A schematic diagram of a process of view perception and message data structure optimization in one embodiment;

[0044] Figure 5 A schematic diagram of a process for aggregating and pushing multi-account data in one embodiment;

[0045] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] In the insurance marketing scenario, during peak business periods, sales personnel in various regions can use the aggregation system to view and reply to customer messages. A single sales personnel may be involved in dozens of accounts of instant messaging applications, and each account is associated with hundreds to thousands of customers. In this scenario, the message data push pressure of the aggregation system is extremely high. The aggregation system for multi-account message processing provided by this application can stably and efficiently push message data to sales personnel.

[0048] Specifically, refer to Figure 1 The aggregation system provided in this application uses AI (Artificial Intelligence) to assist in filtering, and then uses view perception and message data structure optimization to form the minimum message data set required for the user device to render the interface. Finally, through the data sharing device, the minimum message data set of the same user is aggregated for push, thereby reducing the amount of message data that needs to be pushed to the client of the instant messaging application, and achieving stable and efficient push.

[0049] in, Figure 1 The user shown may be a salesperson.

[0050] The aggregation system provided in this application includes an AI processing device, a server, a data sharing device and a storage unit.

[0051] The AI ​​processing device is used to receive the corresponding message data set pushed by the server of the instant messaging application for the account of the instant messaging application hosted in the system;

[0052] The AI ​​processing device is used to call the AI ​​service, process the message data in the message data set that can be automatically processed by AI, and obtain the preliminary screening message data set.

[0053] User user_1 may be involved in N accounts of a certain instant messaging application, and user user_1 may host some or all of the accounts in the aggregation system. For example, if user user_1 hosts all N accounts in the aggregation system, the server of the instant messaging application may send the message data set containing the message data to the AI ​​processing device in the aggregation system after receiving the message data sent to the N accounts.

[0054] Among the message data sets received by the AI ​​processing device, some message data can be automatically processed by the AI ​​service without user intervention. Therefore, this part of the message data can be automatically processed by the AI ​​processing device calling the AI ​​service, thereby reducing the message data that needs to be pushed. Among the message data sets received by the AI ​​processing device, another part of the data is difficult to be automatically processed by the AI ​​service and requires user intervention. A preliminary screening message data set can be formed based on these message data; if the amount of message data that requires user intervention is large, the AI ​​processing device can form multiple preliminary screening message data sets based on the message data that requires user intervention, and send each preliminary screening message data set to different servers. The server can obtain the minimum message data set required for interface rendering based on view perception and message data structure optimization.

[0055] The server is used to receive the preliminary screening message data set, aggregate the preliminary screening message data set, and obtain a session set;

[0056] The server is used to determine the minimum message data set required for the user device to perform interface rendering in the session set based on the perception of the current view of the client of the instant messaging application.

[0057] Take server sever_1 as an example:

[0058] In the initial message data set received by server sever_1, each message data identifies the sender and the receiver. The message data of the same sender and the same receiver are aggregated together, and the aggregated message data can be recorded as a session. In this way, the structure of the message data can be optimized and subsequent data can be carried out in the form of a session.

[0059] The server sever_1 aggregates the initial message data set to obtain several sessions, which can be called a session set. Next, based on the perception of the current view of the client of the instant messaging application, the server sever_1 determines the minimum message data set required for the user device to render the interface in the session set.

[0060] Take user user_1 as an example. User user_1 has 10 accounts, all of which are hosted in the aggregation system. User user_1 accesses these 10 accounts at the same time through the client of the instant messaging application. At this time, the current view of the client includes the views of each of the 10 accounts. The view of an account may include the conversation window between the account and a certain customer, as well as the conversation list.

[0061] Take account userID_1 as an example. Figure 2As shown, the view of account userID_1 includes the conversation window between user user_1 and customer "Xiao Ming", and the conversation list shows the conversations between user user_1 and other customers, such as customers "Xiao Hong", "Xiao Bai", "Xiao Lan" and "Xiao Wang".

[0062] Based on the perception of the current view of the client, server sever_1 may perceive the views of some accounts. For example, server sever_1 perceives the view of userID_1.

[0063] If server sever_1 perceives the view of userID_1, server sever_1 can clearly understand that userID_1's view includes the conversation window between user user_1 and customer "Xiao Ming", and the conversation list included in userID_1's view includes conversations between user user_1 and "Xiao Hong", "Xiao Bai", "Xiao Lan" and "Xiao Wang" respectively.

[0064] Since the view of userID_1 includes the conversation window between user user_1 and client "Xiao Ming", in the conversation between user user_1 and client "Xiao Ming", all message data of the conversation are the message data required for the user device of user_1 to render the interface. Therefore, server sever_1 can retain all message data of the conversation and include it in the minimum message data set.

[0065] In the conversation between user user_1 and customer "Xiaohong", the latest message data is the message data required for interface rendering, so the latest message data can be retained and included in the minimum message data set. In the conversation between user user_1 and customer "Xiaobai", the latest message data is the message data required for interface rendering, so the latest message data can be retained and included in the minimum message data set. In the conversation between user user_1 and customer "Xiaolan", the latest message data is the message data required for interface rendering, so the latest message data can be retained and included in the minimum message data set. In the conversation between user user_1 and customer "Xiaowang", the latest message data is the message data required for interface rendering, so the latest message data can be retained and included in the minimum message data set.

[0066] After server sever_1 perceives the view, it can form a corresponding minimum message data set, which includes: the minimum message data required for interface rendering of the view of userID_1. The minimum message data required for interface rendering of views of other accounts of user user_1 may be generated by other servers.

[0067] Therefore, after each server generates a minimum message data set, it can upload the minimum message data set to the data sharing device. The server can associate the minimum message data set with the user identifier to which the minimum message data set belongs and upload it to the data sharing device.

[0068] The data sharing device is used to receive the minimum message data set uploaded by each server, and aggregate the minimum message data set of the same user to obtain the multi-account minimum data set of the same user, and send the multi-account minimum data set to the storage unit.

[0069] After the data sharing device receives the minimum message data sets uploaded by each server, since each minimum data set is associated with a user identifier, the data sharing device can determine which minimum message data sets belong to the same user, and aggregate the minimum message data sets of the same user to obtain the multi-account minimum data sets of the same user. The data sharing device can send the multi-account minimum data sets of multiple users to the storage unit.

[0070] The server is used to obtain the multi-account minimum data set of the storage unit and send it to the corresponding client, so that the user device performs interface rendering based on the multi-account minimum data set.

[0071] The aggregation system provided in the present application uses AI-assisted filtering, view perception and message data structure optimization to form the minimum message data set required for user device interface rendering. Finally, through the data sharing device, the minimum message data set of the same user is aggregated for push, thereby reducing the amount of message data that needs to be pushed to the client of the instant messaging application, and achieving stable and efficient push.

[0072] In one embodiment, when the AI ​​processing device calls the AI ​​service to process the message data that can be automatically processed by AI in the message data set to obtain the preliminary screening message data set, it specifically includes:

[0073] AI processing device, used to call AI services and perform semantic recognition on message data in the message data set;

[0074] The AI ​​processing device is further used to determine whether a preset question-and-answer knowledge base includes matching answer content based on the semantic recognition result;

[0075] The AI ​​processing device is further configured to respond based on the response content if the preset question-answer knowledge base includes matching response content;

[0076] The AI ​​processing device is also used to add the message data to the initial screening message data set if the preset question and answer knowledge base does not include matching reply content.

[0077] In this embodiment, with the help of AI services and a question-and-answer knowledge base, automatic replies are made to message data that can be automatically processed by AI without user intervention, thereby achieving preliminary filtering of the message data set and forming a preliminary screening message data set with a reduced amount of message data.

[0078] When some instant messaging applications do not open message reply-related interface calls, the PRA device can be called to simulate the client to reply. Based on this, the present application provides an embodiment, when the AI ​​processing device replies based on the reply content, specifically includes: the AI ​​processing device is also used to call the PRA device to simulate the client and reply to the reply content.

[0079] Among them, the full English name of PRA is Process Robot Automation, and its Chinese name is Robotic Process Automation. It is a technology that realizes business process automation by simulating human operations through software robots.

[0080] The aggregation system provided by this application uses AI-assisted filtering to initially screen the message data set. Figure 3 A timing diagram of AI-assisted filtering is shown. Figure 3 After the AI ​​processing device receives the message data set sent by the server of the instant messaging application, it can call the AI ​​service to perform semantic recognition on the message data in the message data set; then, the AI ​​processing device can determine whether the preset question and answer knowledge base includes matching reply content based on the semantic recognition result; if the preset question and answer knowledge base includes matching reply content, the AI ​​processing device can call the PRA device to simulate the client and reply to the reply content; if the preset question and answer knowledge base does not include matching reply content, the AI ​​processing device can add the message data to the initial screening message data set.

[0081] In one embodiment, when the server aggregates the pre-screened message data set to obtain a conversation set, the following steps are specifically performed:

[0082] The server is used to aggregate the initial screening message data set based on the sender and receiver of the message to obtain a session set.

[0083] Specifically, the sender and receiver of the message both have corresponding accounts in the instant messaging application. Therefore, the initial screening message data set can be aggregated according to the dimension of "message sender's account - message receiver's account", and the message data corresponding to the same "message sender's account - message receiver's account" are aggregated together. The aggregated message data is called a session. A session can be the smallest unit for the program to perform allocation, circulation and other processing.

[0084] In one embodiment, when the server determines the minimum message data set required for the user device to render the interface in the session set based on the perception of the current view of the client of the instant messaging application, the server specifically includes:

[0085] The server is used to receive operation data sent by the user equipment for the client of the instant messaging application;

[0086] The server is also used to structure the operation data to obtain the view information of the view currently located by the client;

[0087] The server is further configured to determine, according to the session identifier carried in the view information, a session in the session set that matches the session identifier, so as to obtain a minimum message data set required for the user device to perform interface rendering.

[0088] Specifically, when the user operates the client of the instant messaging application on the user device, the user device can actively collect operation data, which may include the button currently clicked by the user, the page stayed, the open session window, etc. The user device sends the collected operation data to at least one server.

[0089] After receiving the operation data, the server can structure the operation data and perform multi-level grouping to obtain the view information of the view currently in the client. After the server obtains the view information, it can upload the view information to the data sharing device for cache storage. After the view information received by the data sharing device is integrated together, it can be split into multiple copies and sent to each server for subsequent processing.

[0090] In the insurance marketing scenario, the specific structure of view information is, for example:

[0091] key:userViewMap

[0092] Field:userNo / / User No.

[0093] value:{

[0094] orgCode:123123 / / User organization code

[0095] groupID:123 / / User group

[0096] view:assign / / The current view of the client

[0097] userID:123213 / / account ID of instant messaging application

[0098] sessionID:123321 / / session id, uniquely identifies a session}

[0099] Among them, the user ID can be used as a user ID to uniquely identify the user of the user organization. The user organization code can uniquely identify the user organization. The user group is used to determine the group to which the user belongs in the user organization.

[0100] Some message data is sent to all users in the user organization, so the view information includes the user organization code. Some message data is sent to all users in a group, so the view information includes the user group.

[0101] The server can obtain view information, which reflects the stay status of the client of the instant messaging application on the user device. Therefore, the server can determine the session matching the session identifier in the session set based on the session identifier carried by the view information; if the session is the session window currently opened by the client, all message data of the session can be included in the minimum message data set required for interface rendering; if the session is the session displayed in the session list, the latest message data in the session can be included in the minimum message data set required for interface rendering.

[0102] The aggregation system provided in the present application further screens and aggregates the initial message data set through view perception and message data structure optimization, further optimizes the data structure, and obtains the minimum message data set required for interface rendering on the user device while ensuring that the message data is timely and complete, thereby further reducing the magnitude and frequency of message data to be pushed. Figure 4 The view awareness and message data structure optimization process is shown.

[0103] Reference Figure 4 When a user operates an instant messaging application client on a user device, the user device can actively collect operation data, and the operation data may include the button currently clicked by the user, the page stayed on, the session window opened, etc. The user device sends the collected operation data to one of the servers.

[0104] After receiving the operation data, the server can structure the operation data, perform multi-level grouping, and assemble the view information of the view currently in the client. After the server obtains the view information, it can upload the view information to the data sharing device for cache storage. After the view information received by the data sharing device is integrated together, it can be split into multiple copies and sent to each server for subsequent processing.

[0105] The server aggregates the initial screening message data set obtained by AI-assisted filtering to obtain a conversation set.

[0106] The server obtains the view information, which reflects the stay status of the client of the instant messaging application on the user device. Therefore, the server can determine the session matching the session identifier in the session set based on the session identifier carried in the view information; if the session is the session window currently opened by the client, all message data of the session can be included in the minimum message data set required for interface rendering; if the session is the session displayed in the session list, the latest message data in the session can be included in the minimum message data set required for interface rendering.

[0107] In one embodiment, when the data sharing device sends the multi-account minimum data set to the storage unit, it specifically includes:

[0108] The data sharing device is used to divide the multi-account minimum data sets of multiple users into different storage units, so that the multi-account minimum data sets of the same user are sent to the same storage unit and the data amounts received by different storage units are basically the same.

[0109] The minimum message data set uploaded by multiple servers can be uploaded to the cache stream of the data sharing device, which is shared by all servers. The cache stream structure can be used to aggregate the minimum message data set of the same user in a lightweight manner, thereby achieving the effect of simultaneously pushing message data from multiple accounts, and facilitating subsequent unified scheduling.

[0110] After the data sharing device obtains the cache stream containing the multi-account minimum data set of each user, it can structurally divide the cache stream to obtain multiple storage units, each of which contains the multi-account minimum data set. The principle of structural division is that the multi-account minimum data set of the same user is divided into the same storage unit, supplemented by the fact that the amount of data received by different storage units is basically the same.

[0111] The multi-account minimum data sets in different storage units can be processed separately, thereby increasing the parallelism of processing and thus improving the ability to push message data.

[0112] The cache stream mentioned above can be a stream stream, which is a data structure mainly used in real-time data processing scenarios. When the cache stream is a stream stream, the stream stream is logically split into segments, and the resulting storage units are called segments.

[0113] In one embodiment, the storage unit is further used to determine a server that meets the requirements among several servers belonging to the local end according to the idleness of the server; the storage unit is also used to send the multi-account minimum data set stored in the device to the server that meets the requirements.

[0114] The idleness of the server includes at least one of the idleness of the processor and the idleness of the memory of the server. The processor may be a CPU (central processing unit).

[0115] There are several servers under each storage unit. The storage unit can determine a server with relatively idle processor and memory among several servers belonging to the local end according to the idle processor and memory idleness of the server, and use the server as a server that meets the requirements. The storage unit can trigger the server that meets the requirements to read the stored multi-account minimum data set.

[0116] After the server obtains the multi-account minimum data set, it can establish a webSocket long connection with the client of the multi-account minimum data set and send the multi-account minimum data set to the client. As a result, the user device where the client is located can render the interface based on the multi-account minimum data set. WebSocket is a protocol for full-duplex communication over a single TCP connection.

[0117] In one embodiment, the server is also used to determine the storage unit to which the local end belongs and register services with the storage unit after the local end goes online; the storage unit is also used to determine several servers belonging to the local end based on the servers that register services with the local device.

[0118] After any server is online, it can determine the storage unit to which it belongs through a hash algorithm and register the service with the storage unit. Thus, the storage unit can determine which servers belong to the local end according to the servers registered with the service.

[0119] In one embodiment, when the storage unit determines a server that meets the requirements among a plurality of servers belonging to the local end according to the idleness of the server, the method specifically includes:

[0120] The storage unit is also used to obtain the idleness of several servers belonging to the local end;

[0121] The storage unit is further used to sort the servers in order of idleness from small to large, and take the server in the front as the server that meets the requirements;

[0122] Alternatively, the storage unit is further used to sort the servers in descending order of idleness, and use the servers ranked later as servers that meet the requirements.

[0123] For example, after sorting the servers in ascending order of their idleness, the first N servers can be used as servers that meet the requirements, where N is a positive integer greater than or equal to 1.

[0124] In another exemplary embodiment, after sorting the servers in descending order of their idleness, the last M servers can be used as servers that meet the requirements, where M is a positive integer greater than or equal to 1.

[0125] The aggregation system provided by this application aggregates the minimum message data set of the same user through a data sharing device to complete the aggregation of multiple account data of the same user. When pushing, unified load scheduling and batch push are performed to achieve stable and efficient push. Figure 5 The process of data sharing and distribution push is shown.

[0126] Reference Figure 5 ,The aggregation system can deploy multiple servers, e.g. Figure 5 Server 1, Server 2 and Server 3 are shown. After any server generates a minimum message data set, it can upload the minimum message data set to the stream of the data sharing device, and the stream is shared by all servers. The stream structure can be used to aggregate the minimum message data set of the same user in a lightweight manner, thereby achieving the effect of simultaneously pushing message data of multiple accounts, and facilitating subsequent unified scheduling.

[0127] The data sharing device can divide the stream into multiple segments, such as Figure 5 Segment 1 and segment 2 are shown. The division principle is that the minimum data set of multiple accounts of the same user is divided into the same segment, and the amount of data received by different segments is basically the same.

[0128] The multi-account minimum data sets of different segments can be processed separately to increase the parallelism of processing and thus improve the ability to push message data.

[0129] After any server goes online, it can use the hash algorithm to determine the segment it belongs to and register the service with the segment. In this way, the segment can determine which servers belong to the local end based on the servers registered with the service.

[0130] Segment can determine the server with relatively idle CPU and memory among several servers belonging to the local end, and use this server as the server that meets the requirements. Segment can trigger the server that meets the requirements to read the stored multi-account minimum data set.

[0131] After the server obtains the multi-account minimum data set from the segment, it can establish a webSocket long connection with the client of the multi-account minimum data set for data communication. Each time data communication occurs, the multi-account minimum data set of the processing batch can be aggregated and sent to the client in batches, effectively reducing the push frequency under massive data. At the same time, with the data temporary storage capability of the stream structure, the data that failed to be pushed can be resent to ensure the stability of data push.

[0132] The user device where the client is located can render the interface based on the multi-account minimum data set.

[0133] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0134] In an exemplary embodiment, the aggregation system provided by the present application may be implemented by a computer device. The internal structure diagram of the computer device may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the data involved in the above-mentioned embodiments. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements the steps involved in an aggregation system.

[0135] Those skilled in the art will understand that Figure 6The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0136] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0137] Those skilled in the art can understand that all or part of the processes in the above embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above embodiments. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0138] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0139] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A multi-account message processing aggregation system, characterized in that: The aggregation system includes an AI processing device, a server, a data sharing device, and a storage unit; The AI ​​processing device is used to receive, for an account of an instant messaging application hosted in the system, a corresponding message data set pushed by a server of the instant messaging application; The AI ​​processing device is used to call the AI ​​service to process the message data that can be automatically processed by AI in the message data set to obtain a preliminary screening message data set; The server is used to receive the preliminary screening message data set, aggregate the preliminary screening message data set, and obtain a session set; The server is configured to determine, in the session set, a minimum message data set required for the user device to perform interface rendering based on perception of the current view of the client of the instant messaging application; The data sharing device is used to receive the minimum message data set uploaded by each of the servers, aggregate the minimum message data set of the same user to obtain a multi-account minimum data set of the same user, and send the multi-account minimum data set to the storage unit; The server is used to obtain the multi-account minimum data set of the storage unit and send it to the corresponding client, so that the user device performs interface rendering based on the multi-account minimum data set.

2. The system according to claim 1, characterized in that When the AI ​​processing device calls the AI ​​service to process the message data in the message data set that can be automatically processed by AI to obtain the preliminary screening message data set, it specifically includes: The AI ​​processing device is used to call the AI ​​service to perform semantic recognition on the message data in the message data set; The AI ​​processing device is further used to determine whether the preset question-answer knowledge base includes matching reply content according to the semantic recognition result; The AI ​​processing device is further configured to reply based on the answer content if the preset question and answer knowledge base includes matching answer content; The AI ​​processing device is also used to add the message data to the initial screening message data set if the preset question and answer knowledge base does not include matching reply content.

3. The system according to claim 2, characterized in that When the AI ​​processing device makes a reply based on the reply content, the step specifically includes: The AI ​​processing device is further used to call the PRA device to simulate the client and reply to the reply content.

4. The system according to claim 1, characterized in that When the server aggregates the pre-screened message data set to obtain a conversation set, the process specifically includes: The server is used to aggregate the pre-screened message data set based on the sender and receiver of the message to obtain a conversation set.

5. The system according to claim 1, characterized in that The server determines, based on the perception of the current view of the client of the instant messaging application, the minimum message data set required for the user device to perform interface rendering in the session set, specifically including: The server is used to receive operation data sent by a user device for a client of the instant messaging application; The server is further used to structure the operation data to obtain view information of the view currently located by the client; The server is further configured to determine, according to the session identifier carried in the view information, a session in the session set that matches the session identifier, so as to obtain a minimum message data set required for the user equipment to perform interface rendering.

6. The system according to claim 1, characterized in that When the data sharing device sends the multi-account minimum data set to the storage unit, it specifically includes: The data sharing device is used to divide the multi-account minimum data sets of multiple users into different storage units, so that the multi-account minimum data sets of the same user are sent to the same storage unit and the data amounts received by different storage units are basically the same.

7. The system according to claim 1, characterized in that The storage unit is further used to determine a server that meets the requirements among a plurality of servers belonging to the local end according to the idleness of the server; The storage unit is also used to send the multi-account minimum data set stored in the device to a server that meets the requirements.

8. The system according to claim 7, characterized in that The server is also used to determine the storage unit to which the local terminal belongs after the local terminal goes online, and register the service with the storage unit; The storage unit is also used to determine several servers belonging to the local end according to the servers that register services with the local device.

9. The system according to claim 7, characterized in that When the storage unit determines a server that meets the requirement among a plurality of servers belonging to the local end according to the idleness of the server, the storage unit specifically includes: The storage unit is also used to obtain the idleness of several servers belonging to the local end; The storage unit is further used to sort the servers in order of idleness from small to large, and take the servers in the front order as the servers that meet the requirements; Alternatively, the storage unit is further used to sort the servers in descending order of idleness, and use the servers ranked later as servers that meet the requirements.

10. The system according to claim 7, characterized in that The idleness of the server includes at least one of the processor idleness and the memory idleness of the server.

Images