Network control method and system based on artificial intelligence and big data

Abstract

The invention provides a network control method and system based on artificial intelligence and big data, and relates to the technical field of network control, the method comprises the following steps: using a chat window determination model to determine a plurality of chat windows opened by a user in a preset time period; determining the lowest downloading speed of the downloading task based on the emergency degree of the downloading task, the file size of the downloading task, the correlation degree of the downloading task and the user and the target downloading time period of the user; determining a target downloading speed section of the social software chat function and a target downloading speed section of the downloading task based on the lowest downloading speed of the social software chat function and the lowest downloading speed of the downloading task; according to the method, network control is carried out on the chat function and the downloading task of the social software based on the target downloading speed section of the chat function of the social software and the target downloading speed section of the downloading task, the network control can be accurately carried out on the chat function of the social software and the downloading speed of the downloading task, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of network control technology, and in particular to a network control method and system based on artificial intelligence and big data. Background Art

[0002] With the development of the Internet and the widespread application of social software, users often need to perform download tasks when using social software, such as downloading files, pictures or videos from network hard disks or cloud storage spaces. However, during the download process, due to the limitation of network bandwidth, the competition of other network tasks and the characteristics of social software, the download task may be affected by network congestion or delay, resulting in a slow download speed. At the same time, the chat function in social software is also one of the functions frequently used by users. If the download speed of the download task is too fast, it may affect the chat function of the social software. Therefore, how to effectively allocate and control the network between the download task and the chat function to ensure that both can get a good user experience is an urgent problem to be solved. Traditional network control methods are usually based on technologies such as flow control, queue management and priority scheduling, but these methods often cannot perform refined network control when facing the characteristics of social software. These methods often cannot differentiate the needs of individual users and cannot balance the download speed between the chat function of social software and the download task.

[0003] Therefore, how to accurately control the chat function of social software and the download speed of download tasks to improve user experience is a problem that needs to be solved urgently. Summary of the invention

[0004] The main technical problem solved by the present invention is how to accurately control the chat function of social software and the download speed of download tasks through the network to improve user experience.

[0005] According to a first aspect, the present invention provides a network control method based on artificial intelligence and big data, including: determining whether social software is running a download task; if it is determined that the social software is running a download task, obtaining user information, download task information, a description text corresponding to the download task, a screen recording video of a preset time period before the download task starts, and multiple networking task information running in the system; using a chat window determination model to determine multiple chat windows opened by the user in the preset time period based on the screen recording video of the preset time period before the download task starts; obtaining chat records of the multiple chat windows opened by the user in the preset time period; using a chat record processing model to determine the minimum download speed of the chat function of the social software based on the chat records of the multiple chat windows opened by the user in the preset time period; and determining the minimum download speed of the chat function of the social software based on the chat records of the multiple chat windows opened by the user in the preset time period. The method comprises the steps of: determining the urgency of the download task, the relevance of the download task to the user, and the target download time period of the user based on the user information, the download task information, and the description text corresponding to the download task; determining the minimum download speed of the download task based on the urgency of the download task, the size of the download task file, the relevance of the download task to the user, and the target download time period of the user; determining the target download speed segment of the chat function of the social software and the target download speed segment of the download task based on the minimum download speed of the chat function of the social software, the minimum download speed of the download task, and the information of multiple networking tasks run by the system; and performing network control on the chat function of the social software and the download task based on the target download speed segment of the chat function of the social software and the target download speed segment of the download task.

[0006] Furthermore, the chat window determination model is a gated loop unit, the input of the chat window determination model is a screen recording video of a preset time period before the download task starts, and the output of the chat window determination model is a plurality of chat windows opened by the user in the preset time period.

[0007] Furthermore, the method also includes: if it is determined that the social software is not running the download task, limiting the chat function of the social software to a preset download speed.

[0008] Furthermore, the chat record processing model is an artificial neural network model, the input of the chat record processing model is the chat records of multiple chat windows opened by the user in a preset time period, and the output of the chat record processing model is the minimum download speed of the chat function of the social software.

[0009] Furthermore, the chat records of the multiple chat windows opened by the user in a preset time period include text content, picture content, chat content, and file content.

[0010] According to a second aspect, the present invention provides a network control system based on artificial intelligence and big data, including: a detection module for determining whether a social software is running a download task; A judgment module, for obtaining user information, download task information, description text corresponding to the download task, screen recording video of a preset time period before the start of the download task, and information of multiple network tasks run by the system if it is judged that the social software is running a download task; A window determination module, used to determine a plurality of chat windows opened by a user in a preset time period using a chat window determination model based on a screen recording video in a preset time period before the download task starts; An acquisition module, used to acquire chat records of multiple chat windows opened by a user during a preset time period; A chat record processing module, configured to determine the minimum download speed of the chat function of the social software using a chat record processing model based on the chat records of multiple chat windows opened by the user in a preset time period; A download task processing module, used to determine the urgency of the download task, the relevance of the download task to the user, and the user's target download time period based on the user information, the download task information, and the description text corresponding to the download task; A download speed determination module, used to determine the minimum download speed of the download task based on the urgency of the download task, the size of the download task file, the relevance of the download task to the user, and the user's target download time period; A chat function processing module, configured to determine a target download speed segment of the social software chat function and a target download speed segment of the download task based on the minimum download speed of the social software chat function, the minimum download speed of the download task, and information of multiple networking tasks run by the system; The control module is used to perform network control on the chat function and download task of the social software based on the target download speed segment of the chat function of the social software and the target download speed segment of the download task.

[0011] Furthermore, the chat window determination model is a gated loop unit, the input of the chat window determination model is a screen recording video of a preset time period before the download task starts, and the output of the chat window determination model is a plurality of chat windows opened by the user in the preset time period.

[0012] Furthermore, the system is also used to: if it is determined that the social software is not running the download task, limit the chat function of the social software to a preset download speed.

[0013] Furthermore, the chat record processing model is an artificial neural network model, the input of the chat record processing model is the chat records of multiple chat windows opened by the user in a preset time period, and the output of the chat record processing model is the minimum download speed of the chat function of the social software.

[0014] Furthermore, the chat records of the multiple chat windows opened by the user in a preset time period include text content, picture content, chat content, and file content.

[0015] The present invention provides a network control method and system based on artificial intelligence and big data, the method comprising: determining whether social software is running a download task; if it is determined that the social software is running a download task, obtaining user information, download task information, description text corresponding to the download task, screen recording video of a preset time period before the download task starts, and multiple network task information running in the system; using a chat window determination model to determine multiple chat windows opened by the user in the preset time period based on the screen recording video of the preset time period before the download task starts; obtaining chat records of multiple chat windows opened by the user in the preset time period; using a chat record processing model to determine the minimum download speed of the chat function of the social software based on the chat records of multiple chat windows opened by the user in the preset time period; and determining the minimum download speed of the chat function of the social software based on the chat records of the multiple chat windows opened by the user in the preset time period. The descriptive text corresponding to the download task determines the urgency of the download task, the relevance of the download task to the user, and the user's target download time period; the minimum download speed of the download task is determined based on the urgency of the download task, the file size of the download task, the relevance of the download task to the user, and the user's target download time period; the target download speed segment of the social software chat function and the target download speed segment of the download task are determined based on the minimum download speed of the social software chat function, the minimum download speed of the download task and multiple networking task information running in the system; the chat function of the social software and the download task are controlled on the network based on the target download speed segment of the social software chat function and the target download speed segment of the download task. This method can accurately control the chat function of the social software and the download speed of the download task on the network, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of a network control method based on artificial intelligence and big data provided by an embodiment of the present invention; Figure 2 A schematic diagram of a network control system based on artificial intelligence and big data provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In an embodiment of the present invention, there is provided Figure 1A network control method based on artificial intelligence and big data is shown, and the network control method based on artificial intelligence and big data includes steps S1 to S9: Step S1, determining whether the social software is running a download task.

[0018] Social software refers to applications used by people to communicate socially, such as WeChat, QQ, DingTalk, etc.

[0019] Download tasks refer to operations initiated by users in social software that require downloading files and other resources from a network hard drive or cloud storage space.

[0020] In some embodiments, it can be determined whether a task related to downloading is running by monitoring the background process or thread of the social software.

[0021] In some embodiments, the download task status of the social software can be obtained by calling the corresponding API interface to determine whether there is an ongoing download task. For example, the interface provided by the WeChat open platform can be called to obtain the download task information of WeChat.

[0022] Step S2, if it is determined that the social software is running a download task, user information, download task information, description text corresponding to the download task, screen recording video of a preset time period before the start of the download task, and multiple network task information running by the system are obtained.

[0023] User information refers to information related to users who use social software. User information includes user position, interests and hobbies, personal habits, user ID, nickname, avatar, location, social network, friend relationships, work and rest schedule, etc.

[0024] Download task information refers to the relevant information of the download task in progress in the social software. For example, the download task information includes the task ID, file name, size, download speed, remaining time, file deadline, importance, etc.

[0025] The description text corresponding to the download task refers to the specific description text of the download task, such as file name, task type, download link, brief description, tags, etc.

[0026] The screen recording video of the preset time period before the download task starts refers to the screen content video of the user device within a period of time before the download task starts recorded by the screen recording tool. In some embodiments, the screen can be recorded in advance by the screen recording tool.

[0027] The information of multiple network tasks running in the system refers to the relevant information of multiple applications or tasks that require network connection and are running simultaneously on the user's device, such as process ID, used network traffic, download speed, CPU usage, etc.

[0028] In some embodiments, if it is determined that the social software is not running the download task, the chat function of the social software is limited to a preset download speed.

[0029] In some embodiments, the preset download speed may be manually input in advance.

[0030] In some embodiments, the preset download speed may be determined by the following formula: in is the default download speed. The total file size of the chat records received in the previous 24 hours. Indicates the duration of the past 24 hours in seconds.

[0031] Step S3, based on the screen recording video of the preset time period before the download task starts, use the chat window determination model to determine multiple chat windows opened by the user in the preset time period.

[0032] The chat window determination model is a gated loop unit, the input of the chat window determination model is a screen recording video of a preset time period before the download task starts, and the output of the chat window determination model is a plurality of chat windows opened by the user in the preset time period.

[0033] The gated recurrent unit is an implementation of artificial intelligence. The gated recurrent unit includes a gated recurrent unit (GRU). The gated recurrent unit includes three components: a memory unit, an update gate, and a reset gate. The memory unit stores the information of the previous time step and passes it to the input and hidden state of the current time step to retain historical information. The update gate determines whether to update the information of the memory unit. The reset gate determines how to use the memory unit of the previous time step. The gated recurrent unit adjusts the update gate and the reset gate so that the model can better handle the dependency relationship of long sequence data. By processing the screen recording video of the preset time period before the start of the download task in the continuous time period through the gated recurrent unit, the relationship in the time series of the screen recording video of the preset time period before the start of the download task can be better captured, and the features that comprehensively consider the correlation between the screen recording videos at each time point can be output, so that the output features are more accurate and comprehensive.

[0034] Specifically, the gated recurrent unit can receive a screen recording video sequence as input and represent the model's understanding and memory of the user's behavior by calculating the hidden state. At each time step, the model can calculate the hidden state of the next time step based on the current input and the hidden state of the previous time step, thereby gradually capturing the patterns and characteristics of the user opening the chat window. Finally, by analyzing the hidden state sequence, it is possible to determine the multiple chat windows that the user has opened within a preset time period.

[0035] The screen recording video of the preset time period before the download task starts records the user's operations in the preset time period, including opening and closing chat windows, scrolling pages, etc. The screen recording video provides visual information of the user in the preset time period, including the position, size, content, etc. of the chat window. By analyzing the visual information in the video, it can be determined whether the user has opened a chat window and which chat windows have been opened.

[0036] In some embodiments, the chat window determination model includes a video matching layer, a chat window position detection layer, a chat text extraction layer, and a chat window screening layer. The video matching layer, the chat window position detection layer, the chat text extraction layer, and the chat window screening layer all include a gated loop unit. The input of the video matching layer is a screen recording video of a preset time period before the download task starts. The output of the video matching layer is a plurality of video frames containing a chat window within a preset time period. The input of the chat window detection layer is a plurality of video frames containing a chat window within a preset time period. The output of the chat window detection layer is the chat window position within a preset time period. The input of the text extraction layer is the chat window position within a preset time period. The output of the text extraction layer is the text content in the chat window within a preset time period. The input of the chat window screening layer is the text content in the chat window within a preset time period. The output of the chat window screening layer is a plurality of chat windows opened by the user within a preset time period.

[0037] The video matching layer is used to extract multiple video frames containing chat windows within a preset time period, the chat window detection layer is used to detect the chat window position, the text extraction layer is used to extract the text content in the chat window, and the chat window screening layer is used to screen according to the text content, and finally output multiple chat windows that the user has opened within the preset time period. Since a user may frequently open a chat window, the text content in the chat window may be repeated, so it is necessary to screen the chat windows through the chat window screening layer, so as to filter the repeated chat windows, and finally obtain multiple chat windows that the user has opened within the preset time period.

[0038] Step S4, obtaining chat records of multiple chat windows opened by the user during a preset time period.

[0039] The chat records of multiple chat windows opened by the user in a preset time period refer to the records of the content generated in the chat windows, and the chat records of multiple chat windows opened by the user in the preset time period include text content, picture content, chat content, and file content.

[0040] In some embodiments, for each chat window, the chat history can be obtained from the corresponding social software through API or crawler technology.

[0041] Step S5, determining the minimum download speed of the chat function of the social software using a chat record processing model based on the chat records of multiple chat windows opened by the user in a preset time period.

[0042] The chat record processing model is an artificial neural network model, the input of the chat record processing model is the chat records of multiple chat windows opened by the user in a preset time period, and the output of the chat record processing model is the minimum download speed of the social software chat function. The basic structure of the artificial neural network model includes an input layer, a hidden layer and an output layer. The input layer receives external input data, the hidden layer is responsible for processing and processing the input data, and finally passes the result to the output layer, and the output layer generates the final prediction or classification result. The chat records of multiple chat windows opened by the user in a preset time period are transmitted to the user device through the network. Therefore, to achieve a smooth chat experience, the user device needs to have sufficient download speed to receive and load these chat records. If the download speed of the user device is too slow, the chat records may be loaded slowly or delayed, thereby affecting the user's chat experience. As an example, the larger the storage capacity of the chat records of the multiple chat windows opened by the user in the preset time period, the higher the minimum download speed of the social software chat function, so as to ensure that the user chat function can normally receive and load the chat records, thereby achieving a smooth chat experience. The chat record processing model can determine the minimum download speed of the social software chat function based on the chat records of the multiple chat windows opened by the user in the preset time period.

[0043] By analyzing the file content size of these chat records, we can determine the network speed requirements of users during the chat period. Compared with obtaining all chat records, it is more effective to obtain only the records of multiple chat windows, because the content of all chat records is large and users are unlikely to click to view all records. However, obtaining only the records of multiple chat windows can more accurately reflect the user's actual chat network speed requirements.

[0044] Step S6, determining the urgency of the download task, the relevance of the download task to the user, and the user's target download time period based on the user information, the download task information, and the description text corresponding to the download task.

[0045] The urgency of a download task refers to how quickly the task needs to be completed or processed.

[0046] The relevance of a download task to a user refers to the degree to which the task matches the user's interests, preferences, or needs.

[0047] The user's target download time period refers to the time range in which the user plans to complete the download task. For example, if the user's target download time period is three hours, it means that the user hopes to complete the download task within three hours.

[0048] In some embodiments, the urgency of the download task, the relevance of the download task to the user, and the target download time period of the user can be determined by a download task determination model. The download task determination model is an artificial neural network model, the input of the download task determination model is the user information, the download task information, and the description text corresponding to the download task, and the output of the download task determination model is the urgency of the download task, the relevance of the download task to the user, and the target download time period of the user.

[0049] The user information, the download task information, and the description text corresponding to the download task will affect the urgency of the download task, the relevance of the download task to the user, and the user's target download time period. As an example, the description text corresponding to the download task can provide attribute information such as the type, source, and size of the download task, which are related to the urgency of the download task. For example, some download tasks may be updates or patches that users need to obtain in a timely manner, or new movies or news reports that users expect to see as soon as possible. Hobbies, social networks, friend relationships, etc. in user information can reflect the user's preferences and interests. By matching the description text corresponding to the download task with the hobbies and interests in the user information, the relevance of the download task to the user can be determined. Attributes such as the type and source in the download task information can indicate the characteristics of the download task. If the type of the download task is consistent with the music, video, document, etc. that the user likes, or the source of the download task is the same as the website or local folder that the user frequently visits, it may indicate that the download task is highly relevant to the user. The description text corresponding to the download task can provide detailed information and content description of the download task, and by comparing it with the user information, the relevance of the download task to the user can be determined. For example, if the description text mentions the subject, person, or place that the user is interested in, it means that the download task is highly relevant to the user. The user's active time periods and behavior patterns in the user information can reveal the user's daily habits and preferences. For example, if the user usually turns off the computer after 5 pm, the user tends to complete the download task before 5 pm. The deadline and importance in the download task information can affect the time range in which the user plans to complete the task. If the task deadline is urgent, the user may prioritize completing the task in an earlier time period.

[0050] Step S7, determining the minimum download speed of the download task based on the urgency of the download task, the size of the download task file, the relevance of the download task to the user, and the user's target download time period.

[0051] The minimum download speed of a download task refers to the minimum download speed when the download task is downloading.

[0052] In some embodiments, the urgency of the download task, the size of the download task file, the relevance of the download task to the user, and the target download time period of the user can be constructed as a vector to be matched, and by calculating the distance between the vector to be matched and each reference vector in the database, the minimum download speed of the download task corresponding to the reference vector whose distance is less than the threshold is determined as the minimum download speed of the current download task. The database is pre-constructed, and includes reference vectors and the minimum download speed of the download task corresponding to the reference vector. The reference vector is constructed based on the urgency of the download task, the size of the download task file, the relevance of the download task to the user, and the target download time period of the user in the historical data, and the minimum download speed of the download task corresponding to the reference vector is the minimum download speed of the download task determined in the historical data.

[0053] Step S8, determining the target download speed segment of the social software chat function and the target download speed segment of the download task based on the minimum download speed of the social software chat function, the minimum download speed of the download task and information of multiple networking tasks run by the system.

[0054] The target download speed segment of the social software chat function is the range of download speeds required for the social software chat function.

[0055] The target download speed segment of the download task is the range of download speeds required by the social software download task.

[0056] The information of multiple network tasks running in the system can provide the current download speed and resource situation of the system. For example, the system may be carrying out multiple download tasks of other software at the same time.

[0057] In some embodiments, the target download speed segment of the social software chat function and the target download speed segment of the download task can be determined by the download speed determination model. The download speed determination model is an artificial neural network model. The input of the download speed determination model is the minimum download speed of the social software chat function, the minimum download speed of the download task, and the multiple networking task information run by the system, and the output of the download speed determination model is the target download speed segment of the social software chat function and the target download speed segment of the download task. For the social software chat function and the download task, factors such as the minimum download speed and the networking task information will affect the target download speed segment of the social software chat function and the target download speed segment of the download task. The artificial neural network model can capture the complex relationship between input and output through a nonlinear mapping function. The artificial neural network model can model this nonlinear relationship through multiple hidden layers and activation functions. The download speed determination model can comprehensively consider the minimum download speed of the social software chat function, the minimum download speed of the download task, and the multiple networking task information run by the system, and finally determine the target download speed segment of the social software chat function and the target download speed segment of the download task.

[0058] Step S9: network control is performed on the chat function and the download task of the social software based on the target download speed segment of the chat function of the social software and the target download speed segment of the download task.

[0059] In some embodiments, corresponding rules or policies can be set in the network control device or software to control the download speed of the chat function and download tasks of the social software. For example, by limiting the bandwidth usage of other applications or services, bandwidth can be allocated to the chat function of the social software first to ensure that chat messages can be loaded instantly; at the same time, bandwidth resources can be reasonably allocated according to the priority of the download task and the target download speed range to ensure that the download task can be completed on time.

[0060] In some embodiments, it is possible to monitor whether the chat delay of the chat function of the social software is greater than a threshold, and if the chat delay of the chat function of the social software is greater than the delay threshold, steps S1 to S9 are re-executed. The delay threshold can be manually input in advance.

[0061] Based on the same inventive concept, Figure 2 A schematic diagram of a network control system based on artificial intelligence and big data provided by an embodiment of the present invention, the network control system based on artificial intelligence and big data includes: Detection module 21, used to determine whether the social software is running a download task; The judgment module 22 is used to obtain user information, download task information, description text corresponding to the download task, screen recording video of a preset time period before the download task starts, and multiple network task information of the system operation if it is judged that the social software is running a download task; A window determination module 23, configured to determine a plurality of chat windows opened by a user in a preset time period using a chat window determination model based on the screen recording video in a preset time period before the download task starts; An acquisition module 24 is used to acquire chat records of multiple chat windows opened by the user in a preset time period; A chat record processing module 25, configured to determine the minimum download speed of the chat function of the social software using a chat record processing model based on the chat records of multiple chat windows opened by the user in a preset time period; The download task processing module 26 is used to determine the urgency of the download task, the relevance of the download task to the user, and the user's target download time period based on the user information, the download task information, and the description text corresponding to the download task; A download speed determination module 27, configured to determine a minimum download speed of a download task based on the urgency of the download task, the size of the download task file, the relevance of the download task to the user, and the user's target download time period; A chat function processing module 28, configured to determine a target download speed segment of the social software chat function and a target download speed segment of the download task based on the minimum download speed of the social software chat function, the minimum download speed of the download task, and information of multiple networking tasks run by the system; The control module 29 is used to perform network control on the chat function and the download task of the social software based on the target download speed segment of the chat function of the social software and the target download speed segment of the download task.

Claims

1. A network control method based on artificial intelligence and big data, characterized in that: include: Determine whether the social software is running a download task; If it is determined that the social software is running a download task, then user information, download task information, a description text corresponding to the download task, a screen recording video of a preset time period before the download task starts, and information about multiple network tasks running in the system are obtained; Determine multiple chat windows opened by the user in the preset time period using a chat window determination model based on the screen recording video in the preset time period before the download task starts; Obtain chat records of multiple chat windows opened by the user during a preset time period; Determine the minimum download speed of the chat function of the social software using a chat record processing model based on the chat records of multiple chat windows opened by the user in a preset time period; Determine the urgency of the download task, the relevance of the download task to the user, and the user's target download time period based on the user information, the download task information, and the description text corresponding to the download task; Determine the minimum download speed of the download task based on the urgency of the download task, the size of the download task file, the relevance of the download task to the user, and the user's target download time period; Determine a target download speed range of the social software chat function and a target download speed range of the download task based on the minimum download speed of the social software chat function, the minimum download speed of the download task, and information of multiple networking tasks run by the system; The chat function and the download task of the social software are controlled through the network based on the target download speed segment of the chat function of the social software and the target download speed segment of the download task.

2. The network control method based on artificial intelligence and big data according to claim 1, characterized in that: The chat window determination model is a gated loop unit, the input of the chat window determination model is a screen recording video of a preset time period before the download task starts, and the output of the chat window determination model is a plurality of chat windows opened by the user in the preset time period.

3. The network control method based on artificial intelligence and big data according to claim 1, characterized in that: The method further comprises: If it is determined that the social software is not running the download task, the chat function of the social software is limited to a preset download speed.

4. The network control method based on artificial intelligence and big data according to claim 1, characterized in that: The chat record processing model is an artificial neural network model, the input of the chat record processing model is the chat records of multiple chat windows opened by the user in a preset time period, and the output of the chat record processing model is the minimum download speed of the chat function of the social software.

5. The network control method based on artificial intelligence and big data according to claim 1, characterized in that: The chat records of multiple chat windows opened by the user in a preset time period include text content, picture content, chat content, and file content.

6. A network control system based on artificial intelligence and big data, characterized in that: include: A detection module is used to determine whether the social software is running a download task; A judgment module, for obtaining user information, download task information, description text corresponding to the download task, screen recording video of a preset time period before the start of the download task, and information of multiple network tasks run by the system if it is judged that the social software is running a download task; A window determination module, used to determine a plurality of chat windows opened by a user in a preset time period using a chat window determination model based on a screen recording video in a preset time period before the download task starts; An acquisition module, used to acquire chat records of multiple chat windows opened by a user during a preset time period; A chat record processing module, configured to determine the minimum download speed of the chat function of the social software using a chat record processing model based on the chat records of multiple chat windows opened by the user in a preset time period; A download task processing module, used to determine the urgency of the download task, the relevance of the download task to the user, and the user's target download time period based on the user information, the download task information, and the description text corresponding to the download task; A download speed determination module, used to determine the minimum download speed of the download task based on the urgency of the download task, the size of the download task file, the relevance of the download task to the user, and the user's target download time period; A chat function processing module, configured to determine a target download speed segment of the social software chat function and a target download speed segment of the download task based on the minimum download speed of the social software chat function, the minimum download speed of the download task, and information of multiple networking tasks run by the system; The control module is used to perform network control on the chat function and download task of the social software based on the target download speed segment of the chat function of the social software and the target download speed segment of the download task.

7. The network control system based on artificial intelligence and big data as claimed in claim 6, characterized in that: The chat window determination model is a gated loop unit, the input of the chat window determination model is a screen recording video of a preset time period before the download task starts, and the output of the chat window determination model is a plurality of chat windows opened by the user in the preset time period.

8. The network control system based on artificial intelligence and big data as claimed in claim 6, characterized in that: The system is also used to: If it is determined that the social software is not running the download task, the chat function of the social software is limited to a preset download speed.

9. The network control system based on artificial intelligence and big data as claimed in claim 6, characterized in that: The chat record processing model is an artificial neural network model, the input of the chat record processing model is the chat records of multiple chat windows opened by the user in a preset time period, and the output of the chat record processing model is the minimum download speed of the chat function of the social software.

10. The network control system based on artificial intelligence and big data as claimed in claim 6, characterized in that: The chat records of multiple chat windows opened by the user in a preset time period include text content, picture content, chat content, and file content.

Images