Social machine account cluster task processing method based on collaborative filtering recommendation mechanism

Abstract

The invention provides a social machine account cluster task processing method based on a collaborative filtering recommendation mechanism, and belongs to the technical field of agent control, and the method comprises the steps: obtaining a target collaborative filtering recommendation task; determining a target agent from the plurality of agents based on the state data of each agent in the plurality of agents; a target algorithm corresponding to the target collaborative filtering recommendation task is determined, and the target algorithm is used for achieving at least one of the following events: a soft and hard news classification event, a text auditing event and an article classification event; and controlling the target agent to execute the target collaborative filtering recommendation task based on the target algorithm. According to the social machine account cluster task processing method based on the collaborative filtering recommendation mechanism provided by the invention, the technical problem that the social machine account cluster task processing method based on the collaborative filtering recommendation mechanism in related technologies is relatively low in task processing efficiency is solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent body control technology, and in particular to a social machine account cluster task processing method based on a collaborative filtering recommendation mechanism. Background Art

[0002] A Social Bot Account Cluster is a collection of multiple social bot accounts that work together to achieve specific goals, such as information dissemination, public opinion influence, brand promotion, etc. These accounts simulate the behavior of human users on social media platforms but are controlled by multiple agents.

[0003] Collaborative Filtering Recommendation Mechanism is a recommendation algorithm based on user behavior. It predicts items that users may be interested in by analyzing their historical behaviors (such as ratings, purchases, clicks, etc.) and recommends them to users.

[0004] In related technologies, when social machine account clusters process tasks related to collaborative filtering recommendation mechanisms, the completion rate of intelligent agents performing tasks is low, and the hit rate of accurately delivering target items to target groups is low, resulting in low task processing efficiency.

[0005] It can be seen that the social machine account cluster task processing method based on collaborative filtering recommendation mechanism in the related art has the technical problem of low task processing efficiency. Summary of the invention

[0006] The present invention provides a social machine account cluster task processing method based on a collaborative filtering recommendation mechanism, which is used to solve the technical problem of low task processing efficiency in the social machine account cluster task processing method based on a collaborative filtering recommendation mechanism in the related art.

[0007] The present invention provides a social machine account cluster task processing method based on a collaborative filtering recommendation mechanism, comprising the following steps: obtaining a target collaborative filtering recommendation task, wherein the target collaborative filtering recommendation task is a collaborative filtering recommendation task that reaches a preset deadline; determining a target intelligent agent from a plurality of intelligent agents based on status data of each intelligent agent in the plurality of intelligent agents, wherein the plurality of intelligent agents are used to execute pending tasks of a social machine account cluster, and the status data include performance data and load data; determining a target algorithm corresponding to the target collaborative filtering recommendation task, wherein the target algorithm is used to realize at least one of the following events: soft and hard news classification events, text review events, and article classification events; and controlling the target intelligent agent to execute the target collaborative filtering recommendation task based on the target algorithm.

[0008] According to a social machine account cluster task processing method based on a collaborative filtering recommendation mechanism provided by the present invention, the target intelligent agent is determined from the multiple intelligent agents based on the status data of each intelligent agent in the multiple intelligent agents, including: determining the intelligent agent that satisfies the first condition and the second condition at the same time among the multiple intelligent agents as the target intelligent agent, wherein the first condition is that the performance data of the intelligent agent is greater than a preset performance threshold, and the second condition is that the load data of the intelligent agent is less than a preset load threshold.

[0009] According to a social machine account cluster task processing method based on a collaborative filtering recommendation mechanism provided by the present invention, before determining the target agent from the multiple agents based on the status data of each agent in the multiple agents, the method also includes: performing an initialization operation on each of the multiple agents, wherein the initialization operation includes at least one of the following operations: basic parameter initialization, configuration file update.

[0010] According to a social machine account cluster task processing method based on a collaborative filtering recommendation mechanism provided by the present invention, after controlling the target intelligent agent to perform the target collaborative filtering recommendation task based on the target algorithm, the method also includes: obtaining task feedback information obtained by the target intelligent agent after performing the target collaborative filtering recommendation task, wherein the task feedback information is used to indicate the state of the target intelligent agent when performing the target collaborative filtering recommendation task and the task completion status of the target collaborative filtering recommendation task; and storing the task feedback information in a database.

[0011] According to a social machine account cluster task processing method based on a collaborative filtering recommendation mechanism provided by the present invention, the task feedback information includes browsing data and status data, the browsing data is used to indicate the type of the target collaborative filtering recommendation task and the task completion status, the status data is used to indicate the status of the target intelligent agent, the database includes a Bot table and a Response table; storing the task feedback information in the database includes: inputting the browsing data into the Response table; inputting the status data into the Bot table.

[0012] According to a social machine account cluster task processing method based on a collaborative filtering recommendation mechanism provided by the present invention, the database also includes a task database, and the task database is used to indicate the completion status of the task; after the browsing data is input into the Response table, it also includes: judging whether the target collaborative filtering recommendation task is completed based on the browsing data; if the judgment is yes, updating the number of pending executions of the target collaborative filtering recommendation task in the task database based on the type of the target collaborative filtering recommendation task; if the judgment is no, updating the number of retries of the target collaborative filtering recommendation task in the task database.

[0013] The present invention also provides a social machine account cluster task processing device based on a collaborative filtering recommendation mechanism, comprising the following modules: an acquisition module, used to acquire a target collaborative filtering recommendation task, wherein the target collaborative filtering recommendation task is a collaborative filtering recommendation task that reaches a preset deadline; a first determination module, used to determine a target intelligent agent from a plurality of intelligent agents based on status data of each intelligent agent in the plurality of intelligent agents, wherein the plurality of intelligent agents are used to execute tasks to be processed of a social machine account cluster, and the status data include performance data and load data; a second determination module, used to determine a target algorithm corresponding to the target collaborative filtering recommendation task, wherein the target algorithm is used to implement at least one of the following events: soft and hard news classification events, text review events, and article classification events; an execution module, used to control the target intelligent agent to execute the target collaborative filtering recommendation task based on the target algorithm.

[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for processing social machine account clustering tasks based on a collaborative filtering recommendation mechanism as described in any one of the above is implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described social machine account cluster task processing methods based on a collaborative filtering recommendation mechanism.

[0016] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned social machine account cluster task processing methods based on the collaborative filtering recommendation mechanism.

[0017] The social machine account cluster task processing method based on the collaborative filtering recommendation mechanism provided by the present invention obtains a target collaborative filtering recommendation task, determines a target intelligent agent from multiple intelligent agents based on the current state information of each intelligent agent in the multiple intelligent agents, determines a target algorithm corresponding to the target collaborative filtering recommendation task, and controls the target intelligent agent to perform the target collaborative filtering recommendation task based on the target algorithm; here, the target intelligent agent is an intelligent agent that can perform the target collaborative filtering recommendation task determined based on the current state information, and the target intelligent agent performs the target collaborative filtering recommendation task in combination with the target algorithm, which can further improve the task processing efficiency, thereby solving the technical problem of low task processing efficiency in the social machine account cluster task processing method based on the collaborative filtering recommendation mechanism in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced one by one below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is one of the flow charts of the social machine account cluster task processing method based on the collaborative filtering recommendation mechanism provided by the present invention.

[0020] Figure 2 This is the second flow chart of the social machine account cluster task processing method based on the collaborative filtering recommendation mechanism provided by the present invention.

[0021] Figure 3 This is the third flow chart of the social machine account cluster task processing method based on the collaborative filtering recommendation mechanism provided by the present invention.

[0022] Figure 4 It is a structural diagram of a social machine account cluster task processing device based on a collaborative filtering recommendation mechanism provided by the present invention.

[0023] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] It should be noted that in the description of the present invention, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. The orientation or position relationship indicated by the terms "upper", "lower" and the like is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0026] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" means at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0027] A social machine account cluster is a collection of multiple social machine accounts that work together to achieve specific goals, such as information dissemination, public opinion influence, brand promotion, etc. These accounts simulate the behavior of human users on social media platforms, but are controlled by multiple agents. The collaborative filtering recommendation mechanism is a recommendation algorithm based on user behavior. It predicts items that users may be interested in by analyzing their historical behaviors (such as ratings, purchases, clicks, etc.) and recommends them to users.

[0028] In the related art, when social machine account clusters process tasks related to the collaborative filtering recommendation mechanism, the completion rate of the intelligent agent in executing the task is low, and the hit rate of accurately delivering the target item to the target group is low, resulting in low task processing efficiency. Therefore, it can be seen that the task processing method of social machine account clusters based on the collaborative filtering recommendation mechanism in the related art has the technical problem of low task processing efficiency.

[0029] To at least solve some of the above problems, the following Figure 1-Figure 5 The present invention describes a social machine account cluster task processing method based on a collaborative filtering recommendation mechanism.

[0030] The social machine account cluster task processing method based on collaborative filtering recommendation mechanism provided by the present invention can be applied to the scenario where social machine account cluster processes collaborative filtering recommendation tasks; the social machine account cluster task processing method based on collaborative filtering recommendation mechanism provided by the present invention can be executed by a server, and the server is used to control the social machine account cluster to execute tasks.

[0031] Figure 1 is one of the flow charts of the social machine account cluster task processing method based on the collaborative filtering recommendation mechanism provided by the present invention, such as Figure 1 As shown, including but not limited to the following steps: Step 101 : obtaining a target collaborative filtering recommendation task, wherein the target collaborative filtering recommendation task is a collaborative filtering recommendation task that has reached a preset deadline.

[0032] In this embodiment, the collaborative filtering recommendation task refers to the task of predicting the user's preference for other unrated items based on the user's behavior and preference; the social machine account cluster is constructed and managed by multiple agents, and the multiple agents are controlled by a server.

[0033] Figure 2 This is the second flow chart of the social machine account cluster task processing method based on the collaborative filtering recommendation mechanism provided by the present invention. Figure 2 As shown, the step of obtaining the target collaborative filtering recommendation task can be performed by a distributor module. The distributor module is a module located in the server. The distributor is responsible for distributing the expired tasks in the database to the intelligent agents according to the corresponding attributes.

[0034] Specifically, after the allocator is started, it queries the task table in the task database to determine whether there is a collaborative filtering recommendation task that has reached a preset deadline. If the judgment is yes, the collaborative filtering recommendation task that has reached the preset deadline is published as the target collaborative filtering recommendation task to the task message queue; after a certain interval waiting time, the task table in the task database is queried again, and the above steps are repeated; it should be noted that the interval waiting time here does not exceed 30 seconds.

[0035] Step 102, determining a target agent from the multiple agents based on status data of each agent in the multiple agents, wherein the multiple agents are used to execute pending tasks of the social machine account cluster, and the status data includes performance data and load data.

[0036] In this embodiment, determining the target agent from multiple agents based on the status data of each agent in the multiple agents can be performed by the allocator module. Here, the target agent is an agent among the multiple agents whose performance data and load data meet the requirements. Specifically, the agent's performance data is better and its load data is smaller. In this case, the agent has the conditions to perform the target collaborative filtering recommendation task.

[0037] The allocator module is the core of the intelligent task scheduling system. It is responsible for intelligently allocating various tasks to the most suitable artificial intelligence agent or a group of agents according to execution time and related attributes. It uses advanced algorithms to optimize task allocation to ensure high efficiency and the best results of task execution. This module takes into account the capabilities of the agents, current loads, and task urgency to ensure efficient and fair resource utilization.

[0038] Optionally, determining a target agent from the multiple agents based on the state data of each agent in the multiple agents includes: An agent among multiple agents that satisfies both the first condition and the second condition is determined as the target agent, wherein the first condition is that the performance data of the agent is greater than a preset performance threshold, and the second condition is that the load data of the agent is less than a preset load threshold.

[0039] In this embodiment, an agent that satisfies both the first condition and the second condition is determined to be able to perform the target collaborative filtering recommendation task.

[0040] Step 103, determining a target algorithm corresponding to the target collaborative filtering recommendation task, wherein the target algorithm is used to implement at least one of the following events: soft and hard news classification events, text review events, and article classification events.

[0041] The target algorithm corresponding to the target collaborative filtering recommendation task can be determined by the server module. The server module is located in the server. The server module is the back-end support of the system and provides network services based on the RESTful specification (a network architecture style used to build network services in distributed systems. It emphasizes the representation of resources and the transfer of states to achieve scalable, easy-to-understand and maintain systems). The server module mainly provides the necessary data processing functions to the intelligent agent, such as text classification, content monitoring, etc., to support its automated decision-making and task execution. This module is a bridge for interacting with the intelligent agent to ensure that they can access the necessary service resources.

[0042] In this embodiment, the server module is responsible for providing the necessary artificial intelligence algorithm services to the data analysis function of the intelligent agent or the front end through the RESTful interface, mainly including: classification, recognition and judgment of text, pictures and videos.

[0043] The server module provides a variety of algorithmic services in the form of a protocol and standard (Application Programming Interface, Web API) that allows different software applications to interact and communicate with each other, or in the form of a Hypertext Transfer Protocol POST (HTTP POST) request, each service has a fixed interface. The server module only serves the agents registered in the database, which can be judged by the Internet communication protocol (Internet Protocol, IP) and agent identification (Identification, ID).

[0044] The target algorithm is used to implement at least one of the following events: soft and hard news classification events, text review events, and article classification events.

[0045] Exemplarily, the target algorithm can be used to implement the following functions: 1. English hard and soft news classification function, the target algorithm can be a hard and soft news (HSN) classification algorithm for English news.

[0046] 2. Simplified Chinese soft and hard news classification function, the target algorithm can be a soft and hard classification algorithm for simplified Chinese news.

[0047] 3. Text review function. The target algorithm can be a recognition algorithm based on natural language understanding, deep learning and other technologies, which can effectively identify illegal text content and have the ability to recognize variants such as pinyin, homophony, character decomposition, similar characters, and allusion.

[0048] 4. Article classification function. The target algorithm can be a classification algorithm that automatically classifies articles according to content types, and can support multiple mainstream content types such as entertainment, society, music, humanities, science, history, military, sports, technology, and education.

[0049] 5. Sentiment tendency function: the target algorithm can be a sentiment analysis algorithm, which is used to judge the sentiment tendency of texts containing subjective information, and provide assistance for applications such as word-of-mouth analysis, topic monitoring, and public opinion analysis.

[0050] Step 104: Control the target agent to perform the target collaborative filtering recommendation task based on the target algorithm.

[0051] In this embodiment, after determining the target agent, the target algorithm, and the target collaborative filtering recommendation task based on the above steps, the server controls the target agent to perform the target collaborative filtering recommendation task based on the target algorithm.

[0052] Through the embodiments provided by the present application, a target collaborative filtering recommendation task is obtained, wherein the target collaborative filtering recommendation task is a collaborative filtering recommendation task that reaches a preset deadline; a target agent is determined from multiple agents based on the status data of each agent in the multiple agents, wherein the multiple agents are used to execute pending tasks of a social machine account cluster, and the status data includes performance data and load data; a target algorithm corresponding to the target collaborative filtering recommendation task is determined, wherein the target algorithm is used to implement at least one of the following events: soft and hard news classification events, text review events, and article classification events; the target agent is controlled to execute the target collaborative filtering recommendation task based on the target algorithm, thereby solving the technical problem of low task processing efficiency in the social machine account cluster task processing method based on the collaborative filtering recommendation mechanism in the related art and improving the task processing efficiency.

[0053] As an optional solution, before determining the target agent from the multiple agents based on the state data of each of the multiple agents, the method further includes: S11, performing an initialization operation on each of the multiple agents, wherein the initialization operation includes at least one of the following operations: basic parameter initialization, configuration file update.

[0054] The initialization operation for each of the multiple agents can be performed by the agent management module, which is arranged in the server; the initialization operation includes at least one of the following operations: basic parameter initialization, configuration file update; wherein, basic parameter initialization refers to initializing the basic parameters of the agent; configuration file update may include updating the learning strategy, interface, and enabling or disabling certain functional modules of the agent.

[0055] In this embodiment, the agent management module is the basic component of the system and is responsible for the life cycle management of the agent, including initialization settings, startup sequence, stop commands, and real-time update and management of configuration files. This module allows administrators to operate through the user interface or application programming interface (API) to ensure that the agent can be appropriately adjusted according to the latest system requirements and configuration files. Through this module, the behavior of the agent can be finely controlled to respond to environmental changes or new operating instructions.

[0056] Optionally, the intelligent agent management module is a subsystem of the recommendation algorithm security risk monitoring system, which mainly runs on the developer's personal computer. Its main purpose is to provide visual operation functions for the intelligent agent: including initialization, start and stop of the intelligent agent, configuration file update, etc. This module runs directly through the software resource package, which is easy for developers to deploy and use.

[0057] The management interface of the intelligent agent management module may include: a function bar, a search bar and an information bar; wherein the function bar includes the following operations: intelligent agent initialization, intelligent agent configuration update, intelligent agent account login, intelligent agent start, intelligent agent stop, log viewing, uploading files, downloading files, uploading intelligent agent configuration, updating intelligent agent information, batch creation of intelligent agents; the search bar, specifies the screening of artificial intelligence agents according to the platform name, portrait name, and city location; the information bar displays the basic information of the intelligent agent, including the intelligent agent name, the IP address of the cloud server, the city, the platform name, and the portrait name.

[0058] Through this embodiment, the initialization operation is performed on each of the multiple agents, which can improve the stability and reliability of the subsequent task execution of the agent.

[0059] As an optional solution, after controlling the target agent to perform the target collaborative filtering recommendation task based on the target algorithm, the method further includes: S21, obtaining task feedback information obtained by the target intelligent agent after performing the target collaborative filtering recommendation task, wherein the task feedback information is used to indicate the state of the target intelligent agent when performing the target collaborative filtering recommendation task and the task completion status of the target collaborative filtering recommendation task; S22, storing the task feedback information in a database.

[0060] Obtaining the task feedback information obtained by the target agent after performing the target collaborative filtering recommendation task can be performed by a collector module, which is located in the server and is used to collect task feedback from the agent.

[0061] In this embodiment, the main responsibility of the collector module is to monitor and collect feedback information and data during the agent's task execution. It can automatically process and correct errors that occur during task execution to ensure the integrity and accuracy of the data. In addition, it can also provide real-time feedback to system administrators to facilitate real-time monitoring of task progress and performance.

[0062] Through this embodiment, the reliability of the target collaborative filtering recommendation task execution process can be improved.

[0063] As an optional solution, the task feedback information includes browsing data and status data. The browsing data is used to indicate the type of the target collaborative filtering recommendation task and the task completion status. The status data is used to indicate the status of the target agent. The database includes a Bot table and a Response table. Store task feedback information in the database, including: S31, input browsing data into Response table; S32, inputting the status data into the Bot table.

[0064] Figure 3 This is a flowchart of the third method for processing social machine account cluster tasks based on collaborative filtering recommendation mechanism provided by the present invention. Figure 3 As shown, after receiving the task feedback information, the collector module classifies the task feedback information; identifies the status data used to represent the state of the agent, and determines whether there is information about the agent corresponding to the status data in the Bot table. Here, the Bot table is used to record the basic information, configuration parameters, operating status, and statistical information related to the operation of the agent; when it is determined that there is information about the agent corresponding to the status data in the Bot table, the status and reporting time of the agent in the Bot table are updated based on the status data. Here, the reporting time refers to the time when the status data is obtained.

[0065] The task feedback information is classified, and the browsing data used to indicate the type of target collaborative filtering recommendation task and the task completion status is entered into the Response table. Here, the Response table is used to store the response data of the agent or system to a specific request or event. The Response table records how the system responds to external input, which can be user interaction, the output of automated tasks, or feedback from internal system events. After entering the browsing data into the Response table, the agent status and reporting time in the Response table are updated.

[0066] Through this embodiment, task feedback information is obtained and stored, which can improve the accuracy and efficiency of task feedback information processing.

[0067] As an optional solution, the database further includes a task database, and the task database is used to indicate the completion status of the task; After the browse data is entered into the Response table, also include: S41, judging whether the target collaborative filtering recommendation task is completed based on the browsing data; S42, if the judgment is yes, updating the number of pending executions of the target collaborative filtering recommendation task in the task database based on the type of the target collaborative filtering recommendation task; S43: If the judgment is negative, the number of retries of the target collaborative filtering recommendation task in the task database is updated.

[0068] like Figure 3 As shown, after the browsing data is input into the Response table, it is also necessary to determine whether the target collaborative filtering recommendation task is completed based on the browsing data; if it is determined to be yes, the number of pending executions of the target collaborative filtering recommendation task in the task database is updated based on the type of the target collaborative filtering recommendation task; if it is determined to be no, the number of retries of the target collaborative filtering recommendation task in the task database is updated.

[0069] Specifically, updating the number of target collaborative filtering recommendation tasks to be executed in the task database based on the type of the target collaborative filtering recommendation task includes: determining whether the target collaborative filtering recommendation task is a Browse task, where the Browse task refers to a series of operations performed by an intelligent agent (such as a robot, an automated script, or a software agent) to simulate the browsing behavior of human users on the Internet; when the target collaborative filtering recommendation task is a Browse task, writing the browsing data into the Browse database, and determining whether the loop is greater than 0, where the loop refers to the number of times the target collaborative filtering recommendation task needs to be executed in a loop; if the judgment is yes, updating the task database, reducing the number of loops of the target collaborative filtering recommendation task in the task database by 1; if the judgment is no, updating the task database, and considering that the target collaborative filtering recommendation task has been completed; when the target collaborative filtering recommendation task is not a Browse task, skipping the step of writing the browsing data into the Browse database, and executing subsequent steps.

[0070] Specifically, updating the number of retries of the target collaborative filtering recommendation task in the task database includes determining whether Retry is greater than 0. Here, Retry refers to the maximum number of times the agent attempts to re-execute the same task after encountering a failure. When Retry is greater than 0, the task database is updated and the number of Retry times corresponding to the target collaborative filtering recommendation task is reduced by 1; when Retry is not greater than 0, the task database is updated and the target collaborative filtering recommendation task is marked as a task error.

[0071] It should be noted that, in this embodiment, the collector module takes no more than 10 seconds to perform the step of feeding back the task feedback information of a single task.

[0072] Through this embodiment, the task database is updated based on the completion results of the target collaborative filtering recommendation tasks, which can improve the accuracy and efficiency of task feedback information processing.

[0073] As an optional solution, the server is equipped with an artificial intelligence operation management system, which can be composed of an intelligent agent management module, an artificial intelligence agent module, a distributor module, a collector module, a server module, a task management module, and a data display module.

[0074] The artificial intelligence agent module consists of a set of distributed programs that are deployed on cloud hosts or mobile devices and can autonomously perform tasks assigned to them. These tasks usually involve automated social interactions on designated social media platforms, such as browsing content, reading posts, following users, posting comments, and liking. The agents in this module can simulate the behavior of real users and efficiently consume information and engage in social behaviors through algorithm-driven.

[0075] The task management module allows administrators to create, distribute, monitor and manage tasks on the system interface. Through this module, administrators can specify task parameters, send them to specific agents, and track the execution status of tasks to ensure that tasks proceed as planned.

[0076] The data display module provides an intuitive visual interface for the system, through which it can monitor and display the data fed back by the intelligent agents. It can process and present data according to the user's filtering conditions, and provides powerful reporting and export functions so that users can conduct in-depth analysis and record retention. This module makes data analysis more intuitive and easy to understand, providing support for user decision-making.

[0077] (I) In order to realize the ability to quickly build social machine account clusters, several key modules in the artificial intelligence operation and management system are as follows: Agent management module: This module is responsible for the initialization of the agent and the updating of the configuration file, which is crucial for the social machine account to quickly adjust its behavior according to platform changes. It ensures that the agent can be quickly started and stopped with the required configuration, thus supporting the survival rate of the social machine account on the social platform.

[0078] Artificial Intelligence Agent Module: The distributed agents in this module can perform tasks such as browsing and commenting on various cloud hosts or mobile phones, allowing them to simulate the social behavior of real users and meet the requirement of being highly consistent with real user behavior.

[0079] Allocator Module: To test and optimize the social machine account algorithm, the allocator module is able to efficiently assign tasks to agents with the best simulated behaviors, which helps maintain the similarity verification metrics of the agents under various test scenarios.

[0080] Data display module: By providing visualization of the agent’s feedback data, this module helps analyze the similarity between the agent’s behavior and the real user’s behavior, so that the conditional entropy and relative entropy can be maintained at a given level.

[0081] (II) In order to realize the information dissemination capability that supports the collaborative filtering recommendation mechanism, several key modules in the artificial intelligence operation and management system are as follows: Task management module: Tasks related to the collaborative filtering recommendation mechanism are issued through the task management module. This module supports the testing and verification of the algorithm on the MIND dataset, as well as the accurate delivery of recommended content.

[0082] Server module: The server module using RESTful specification provides necessary algorithm services for the recommendation mechanism, such as text classification and content monitoring, thereby enhancing the accuracy and effectiveness of information dissemination.

[0083] Collector module: Used to collect feedback and performance data of the recommendation system, monitor target hit rate and overflow rate, and adjust and optimize the recommendation strategy.

[0084] The functions of the above functional modules are detailed in the following table.

[0085]

[0086] Figure 4 is a structural diagram of a social machine account cluster task processing device based on a collaborative filtering recommendation mechanism provided by the present invention, such as Figure 4 As shown, including but not limited to the following modules: An acquisition module 401 is used to acquire a target collaborative filtering recommendation task, wherein the target collaborative filtering recommendation task is a collaborative filtering recommendation task that has reached a preset deadline; A first determination module 402 is used to determine a target agent from the multiple agents based on state data of each agent in the multiple agents, wherein the multiple agents are used to perform the to-be-processed tasks of the social machine account cluster, and the state data includes performance data and load data; The second determination module 403 is used to determine a target algorithm corresponding to the target collaborative filtering recommendation task, wherein the target algorithm is used to implement at least one of the following events: a soft and hard news classification event, a text review event, and an article classification event; The execution module 404 is used to control the target agent to execute the target collaborative filtering recommendation task based on the target algorithm.

[0087] Through the embodiments of the present application, a target collaborative filtering recommendation task is obtained, wherein the target collaborative filtering recommendation task is a collaborative filtering recommendation task that reaches a preset deadline; a target agent is determined from multiple agents based on the status data of each agent in the multiple agents, wherein the multiple agents are used to execute pending tasks of a social machine account cluster, and the status data includes performance data and load data; a target algorithm corresponding to the target collaborative filtering recommendation task is determined, wherein the target algorithm is used to implement at least one of the following events: soft and hard news classification events, text review events, and article classification events; the target agent is controlled to execute the target collaborative filtering recommendation task based on the target algorithm, which solves the technical problem of low task processing efficiency in the social machine account cluster task processing method based on the collaborative filtering recommendation mechanism in the related art, thereby improving the task processing efficiency.

[0088] It should be noted that the social machine account cluster task processing device based on collaborative filtering recommendation mechanism provided by the present invention can execute the social machine account cluster task processing method based on collaborative filtering recommendation mechanism of any of the above embodiments during specific operation, which will not be elaborated in this embodiment.

[0089] Figure 5 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 5 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute a social machine account cluster task processing method based on a collaborative filtering recommendation mechanism, the method comprising: obtaining a target collaborative filtering recommendation task, wherein the target collaborative filtering recommendation task is a collaborative filtering recommendation task that reaches a preset deadline; determining a target intelligent agent from a plurality of intelligent agents based on the status data of each intelligent agent in a plurality of intelligent agents, wherein the plurality of intelligent agents are used to execute the to-be-processed tasks of the social machine account cluster, and the status data include performance data and load data; determining a target algorithm corresponding to the target collaborative filtering recommendation task, wherein the target algorithm is used to implement at least one of the following events: soft and hard news classification events, text review events, and article classification events; and controlling the target intelligent agent to execute the target collaborative filtering recommendation task based on the target algorithm.

[0090] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0091] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the social machine account cluster task processing method based on the collaborative filtering recommendation mechanism provided in the above-mentioned embodiments, and the method includes: obtaining a target collaborative filtering recommendation task, wherein the target collaborative filtering recommendation task is a collaborative filtering recommendation task that reaches a preset deadline; determining a target intelligent agent from multiple intelligent agents based on the status data of each intelligent agent in the multiple intelligent agents, wherein the multiple intelligent agents are used to execute the pending tasks of the social machine account cluster, and the status data includes performance data and load data; determining a target algorithm corresponding to the target collaborative filtering recommendation task, wherein the target algorithm is used to realize at least one of the following events: soft and hard news classification events, text review events, and article classification events; controlling the target intelligent agent to perform the target collaborative filtering recommendation task based on the target algorithm.

[0092] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the social machine account cluster task processing method based on the collaborative filtering recommendation mechanism provided in the above-mentioned embodiments, the method comprising: obtaining a target collaborative filtering recommendation task, wherein the target collaborative filtering recommendation task is a collaborative filtering recommendation task that reaches a preset deadline; determining a target intelligent agent from multiple intelligent agents based on the status data of each intelligent agent in the multiple intelligent agents, wherein the multiple intelligent agents are used to execute the pending tasks of the social machine account cluster, and the status data includes performance data and load data; determining a target algorithm corresponding to the target collaborative filtering recommendation task, wherein the target algorithm is used to implement at least one of the following events: soft and hard news classification events, text review events, and article classification events; controlling the target intelligent agent to execute the target collaborative filtering recommendation task based on the target algorithm.

[0093] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0094] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A social machine account cluster task processing method based on collaborative filtering recommendation mechanism, characterized in that: include: Acquire a target collaborative filtering recommendation task, wherein the target collaborative filtering recommendation task is a collaborative filtering recommendation task that has reached a preset deadline; Determining a target agent from a plurality of agents based on state data of each agent in the plurality of agents, wherein the plurality of agents are used to perform tasks to be processed of a social machine account cluster, the state data including performance data and load data; Determine a target algorithm corresponding to the target collaborative filtering recommendation task, wherein the target algorithm is used to implement at least one of the following events: a soft and hard news classification event, a text review event, and an article classification event; Control the target agent to perform the target collaborative filtering recommendation task based on the target algorithm.

2. The social machine account cluster task processing method based on collaborative filtering recommendation mechanism according to claim 1 is characterized in that: The step of determining a target intelligent agent from the plurality of intelligent agents based on the status data of each intelligent agent in the plurality of intelligent agents comprises: An agent among the multiple agents that satisfies both the first condition and the second condition is determined as the target agent, wherein the first condition is that the performance data of the agent is greater than a preset performance threshold, and the second condition is that the load data of the agent is less than a preset load threshold.

3. The social machine account cluster task processing method based on collaborative filtering recommendation mechanism according to claim 1 is characterized in that: Before determining the target agent from the plurality of agents based on the status data of each of the plurality of agents, the method further comprises: Performing an initialization operation on each of the plurality of agents; The initialization operation includes at least one of the following operations: basic parameter initialization and configuration file update.

4. The social machine account cluster task processing method based on collaborative filtering recommendation mechanism according to any one of claims 1 to 3, characterized in that: After controlling the target agent to perform the target collaborative filtering recommendation task based on the target algorithm, the method further includes: Acquire task feedback information obtained by the target agent after executing the target collaborative filtering recommendation task, wherein the task feedback information is used to indicate the state of the target agent when executing the target collaborative filtering recommendation task and the task completion status of the target collaborative filtering recommendation task; The task feedback information is stored in a database.

5. The social machine account cluster task processing method based on collaborative filtering recommendation mechanism according to claim 4 is characterized in that: The task feedback information includes browsing data and status data, wherein the browsing data is used to indicate the type of the target collaborative filtering recommendation task and the task completion status, and the status data is used to indicate the status of the target agent, and the database includes a Bot table and a Response table; The step of storing the task feedback information in a database comprises: Input the browsing data into the Response table; The status data is entered into the Bot table.

6. The social machine account cluster task processing method based on collaborative filtering recommendation mechanism according to claim 5 is characterized in that: The database further includes a task database, and the task database is used to indicate the completion status of the task; After the browsing data is input into the Response table, the method further includes: Determining whether the target collaborative filtering recommendation task is completed based on the browsing data; If the answer is yes, updating the number of to-be-executed times of the target collaborative filtering recommendation task in the task database based on the type of the target collaborative filtering recommendation task; If the judgment is no, the number of retries of the target collaborative filtering recommendation task in the task database is updated.

7. A social machine account cluster task processing device based on collaborative filtering recommendation mechanism, characterized in that: include: An acquisition module, used to acquire a target collaborative filtering recommendation task, wherein the target collaborative filtering recommendation task is a collaborative filtering recommendation task that has reached a preset deadline; A first determination module is configured to determine a target agent from a plurality of agents based on state data of each agent in the plurality of agents, wherein the plurality of agents are configured to execute a task to be processed of a social machine account cluster, the state data comprising performance data and load data; A second determination module is used to determine a target algorithm corresponding to the target collaborative filtering recommendation task, wherein the target algorithm is used to implement at least one of the following events: a soft and hard news classification event, a text review event, and an article classification event; An execution module is used to control the target agent to execute the target collaborative filtering recommendation task based on the target algorithm.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the social machine account clustering task processing method based on the collaborative filtering recommendation mechanism as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for processing social machine account cluster tasks based on a collaborative filtering recommendation mechanism as claimed in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for processing social machine account cluster tasks based on a collaborative filtering recommendation mechanism as claimed in any one of claims 1 to 6 is implemented.

Images