An AI-based prediction reconnection method and device, electronic equipment, and storage medium

Abstract

The embodiment of the application discloses a kind of based on AI prediction reconnection method, device, electronic equipment and storage medium, belong to data transmission technical field, can improve the efficiency of data transmission.The application includes: obtaining current network data and historical reconnection data;Based on current network data and historical reconnection data, the probability of disconnection and reconnection between cloud center module and terminal module is predicted, and the reconnection probability value is obtained;According to the predicted reconnection probability value, the corresponding data caching strategy is executed, to connect cloud center module and terminal module based on data caching strategy;Data caching strategy includes: informing terminal module to send reconnection request to cloud center module, and sending the current user data cached by terminal module to cloud center module in advance;After cloud center module and terminal module are connected, based on current user data, make cloud center module respond to the target service request of terminal module.

Description

Technical Field

[0001] This application relates to the field of data transmission technology, and in particular to an AI-based predictive reconnection method, apparatus, electronic device, and storage medium. Background Technology

[0002] Driven by the development of science and technology, the rapid iteration of services has led to a huge workload for the integration and adaptation of various set-top boxes. As a result, cloud-based set-top boxes have emerged, which virtualize the devices and cloudify the services, enabling the execution of services on the terminal to be processed in the cloud.

[0003] In related technologies, when encountering abnormal scenarios such as network interruptions, errors are prone to occur during data transmission. Users need to actively click multiple times to retry and initiate viewing again. Furthermore, there may be issues such as data instructions not being transmitted to the cloud, resulting in low data transmission efficiency. Summary of the Invention

[0004] The purpose of this application is to provide an AI-based predictive reconnection method, apparatus, electronic device, and storage medium to solve the problem of low data transmission efficiency.

[0005] To solve the above-mentioned technical problems, the embodiments of this application are implemented as follows:

[0006] In a first aspect, embodiments of this application provide an AI-based prediction-based reconnection method, comprising: acquiring current network data and historical reconnection data, wherein the current network data includes network status data of the communication connection between the AI ​​prediction module and the cloud center module, and the historical reconnection data includes communication status data of the terminal module's historical transmission of user data; predicting the probability of reconnection between the cloud center module and the terminal module based on the current network data and the historical reconnection data, and obtaining a reconnection probability value; executing a corresponding data caching strategy according to the predicted reconnection probability value, so as to enable the cloud center module and the terminal module to connect based on the data caching strategy; the data caching strategy includes: notifying the terminal module to send a reconnection request to the cloud center module, and pre-sending cached current user data sent by the terminal module to the cloud center module, wherein the current user data includes: relevant data sent by the terminal module for executing a target service request; after the cloud center module and the terminal module connect, enabling the cloud center module to respond to the target service request of the terminal module based on the current user data.

[0007] Secondly, embodiments of this application provide an AI-based predictive reconnection device, comprising: an acquisition module, configured to acquire current network data and historical reconnection data, wherein the current network data includes network status data of the communication connection between the AI ​​prediction module and the cloud center module, and the historical reconnection data includes communication status data of the terminal module's historical transmission of user data; a prediction module, configured to predict the probability of reconnection between the cloud center module and the terminal module based on the current network data and the historical reconnection data, and obtain a reconnection probability value; a connection module, configured to execute a corresponding data caching strategy according to the predicted reconnection probability value, so as to enable the cloud center module and the terminal module to connect based on the data caching strategy; the data caching strategy includes: notifying the terminal module to send a reconnection request to the cloud center module, and pre-sending cached current user data sent by the terminal module to the cloud center module, wherein the current user data includes relevant data sent by the terminal module for executing a target service request; and a response module, configured to, after the cloud center module and the terminal module are connected, enable the cloud center module to respond to the target service request of the terminal module based on the current user data.

[0008] Thirdly, embodiments of this application provide an electronic device, including a processor and a memory electrically connected to the processor, the memory storing a computer program, and the processor being used to call and execute the computer program from the memory to implement the aforementioned AI-based predictive reconnection method.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium for storing a computer program that can be executed by a processor to implement the aforementioned AI-based predictive reconnection method.

[0010] Fifthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the aforementioned AI-based predictive reconnection method.

[0011] Sixthly, embodiments of this application provide a computer program product, which includes a computer program that, when executed by a processor, implements the aforementioned AI-based predictive reconnection method.

[0012] The technical solution adopted in this application embodiment is applied to an AI prediction module to obtain current network data and historical reconnection data. The current network data includes network status data of the communication connection between the AI ​​prediction module and the cloud center module, and the historical reconnection data includes communication status data of the terminal module's historical transmission of user data. Based on the current network data and historical reconnection data, the probability of reconnection between the cloud center module and the terminal module is predicted to obtain a reconnection probability value. According to the predicted reconnection probability value, a corresponding data caching strategy is executed to enable the cloud center module and the terminal module to connect based on the data caching strategy. The data caching strategy includes: notifying the terminal module to send a reconnection request to the cloud center module, and pre-sending the cached current user data sent by the terminal module to the cloud center module, wherein the current user data includes: relevant data sent by the terminal module for executing the target service request. After the cloud center module and the terminal module connect, the cloud center module responds to the target service request of the terminal module based on the current user data. As can be seen, even before a network outage occurs, the AI ​​prediction module can predict the probability of a reconnection between the cloud center module and the terminal module and execute corresponding data caching strategies. When a network anomaly causes a network outage, the cloud center module and the terminal module can directly reconnect, reducing the need for active user operations. Since the current user data is pre-cached, the user does not need to actively re-upload the data, which improves the efficiency of reconnection and data transfer between the cloud center module and the terminal module, solving the problem of low data transmission efficiency. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in one or more embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in one or more embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a schematic diagram of the structure of an AI-based predictive reconnection system according to an embodiment of this application;

[0015] Figure 2 This is a schematic flowchart of an AI-based predictive reconnection method according to an embodiment of this application;

[0016] Figure 3 This is a schematic diagram of the reconnection of the terminal module and the cloud center module according to an embodiment of this application;

[0017] Figure 4 This is a schematic diagram of the reconnection of the terminal module and the cloud center module according to another embodiment of this application;

[0018] Figure 5 This is a schematic diagram of a data caching strategy based on a reconnection probability value according to an embodiment of this application;

[0019] Figure 6 This is a schematic flowchart of an AI-based predictive reconnection method according to another embodiment of this application;

[0020] Figure 7 This is a schematic flowchart of an AI-based predictive reconnection method according to another embodiment of this application;

[0021] Figure 8 This is a schematic block diagram of an AI-based predictive reconnection device according to an embodiment of this application;

[0022] Figure 9 This is a schematic diagram of the hardware structure of an AI-based predictive reconnection device according to an embodiment of this application. Detailed Implementation

[0023] This application provides an AI-based predictive reconnection method, apparatus, electronic device, and storage medium to address the problem of low data transmission efficiency.

[0024] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0025] The AI-based predictive reconnection method provided in this application can be executed by an electronic device or by software installed in an electronic device. Specifically, the electronic device can be a terminal device or a server device. The terminal device can include smartphones, laptops, smart wearable devices, vehicle terminals, etc., and the server device can include an independent physical server, a server cluster consisting of multiple servers, or a cloud server capable of cloud computing.

[0026] The following description, in conjunction with the accompanying drawings, details an AI-based predictive reconnection method provided in this application through specific embodiments and application scenarios.

[0027] Figure 1 This is a schematic diagram of the structure of an AI-based predictive reconnection system according to an embodiment of this application. Figure 1As shown, the AI ​​prediction and reconnection system includes an AI prediction module, a cloud-based central module, and a terminal module. Specifically, the AI ​​prediction module, cloud-based central module, and terminal module are interconnected. The AI ​​prediction module caches the user's current user data and, based on current network data and historical reconnection data, predicts the reconnection probability values ​​for the cloud-based central module and the terminal module, and executes corresponding data caching strategies based on the reconnection probability values. The cloud-based central module receives reconnection requests sent by the terminal module, establishes communication connections with the terminal module, pushes target service request results, and handles and restores current user data in the event of network anomalies. The terminal module establishes multiple communication links with the cloud-based central module, sends target service requests to the cloud-based central module, and receives target service request results sent by the cloud-based central module.

[0028] Figure 2 The diagram illustrates an embodiment of the present invention providing an AI-based prediction-based reconnection method, which is applied to an AI prediction module and includes the following steps:

[0029] S202, obtain current network data and historical reconnection data.

[0030] The current network data includes network status data of the communication connection between the AI ​​prediction module and the cloud center module, while the historical reconnection data includes communication status data of the terminal module's historical transmission of user data.

[0031] Network status data includes: current network latency, packet loss rate, and throughput parameters; communication status data includes: historical reconnection time and reconnection latency data between the terminal module and the cloud center. The AI ​​prediction module can also acquire and store the mapping relationship between the terminal module and the cloud center module.

[0032] Specifically, based on the constructed AI prediction module, current network data and historical reconnection data are acquired in real time. By establishing a communication link between the AI ​​prediction module and the cloud center module, network status data of the communication connection between the two modules is acquired in real time; by establishing a communication link between the AI ​​prediction module and the terminal module, historical reconnection data of the corresponding client terminal module is acquired. Multiple communication links are established between the cloud center module and the terminal module.

[0033] S204. Based on current network data and historical reconnection data, predict the probability of reconnection between the cloud center module and the terminal module after a disconnection, and obtain the reconnection probability value.

[0034] Based on current network data and historical reconnection data, an AI prediction module is used to predict the probability of a current disconnection and reconnection event. This is achieved by calculating the probability of reconnection between the cloud center module and the terminal module. The acquired current network data and historical reconnection data are adjusted according to different scenario requirements. The AI ​​detection module can obtain relevant data used to obtain the predicted reconnection probability value, such as data representing the mapping relationship between the terminal module and the cloud center module. Other detailed related data for calculating the reconnection probability value are not specifically limited.

[0035] S206, based on the predicted reconnection probability value, execute the corresponding data caching strategy to enable the cloud center module and the terminal module to connect based on the data caching strategy.

[0036] The data caching strategy includes: notifying the terminal module to send a reconnection request to the cloud center module, and pre-sending the cached current user data sent by the terminal module to the cloud center module. The current user data includes: relevant data sent by the terminal module for executing the target business request.

[0037] Specifically, the obtained reconnection probability value is compared with a preset threshold to obtain the comparison result. Based on the comparison result, an corresponding data caching strategy is executed. The preset threshold is a range set based on historical data. When the reconnection probability value is within the preset threshold, the corresponding data caching strategy is executed. The AI ​​prediction module can pre-obtain and cache current user data from the terminal module. Based on the comparison result, it can notify the terminal module to send a reconnection request to the cloud center module and send the cached current user data to the cloud center module. Once the terminal module and the cloud center module are connected, the terminal module does not need to resend the current user data to the cloud center module again. Since the current business data includes relevant data for executing the target business request, the efficiency of data transmission can be improved.

[0038] S208: After the cloud center module and the terminal module are connected, the cloud center module responds to the target business request of the terminal module based on the current user data.

[0039] Based on the connection between the cloud center module and the terminal module as described above in S206, after the connection is established, the cloud center module can directly respond to the target business request of the corresponding terminal module because it receives the current user data sent by the AI ​​prediction module in advance, without waiting for the terminal module to send the current user data again.

[0040] The technical solution adopted in this application embodiment is applied to an AI prediction module to obtain current network data and historical reconnection data. The current network data includes network status data of the communication connection between the AI ​​prediction module and the cloud center module, and the historical reconnection data includes communication status data of the terminal module's historical transmission of user data. Based on the current network data and historical reconnection data, the probability of reconnection between the cloud center module and the terminal module is predicted to obtain a reconnection probability value. According to the predicted reconnection probability value, a corresponding data caching strategy is executed to enable the cloud center module and the terminal module to connect based on the data caching strategy. The data caching strategy includes: notifying the terminal module to send a reconnection request to the cloud center module, and pre-sending the cached current user data sent by the terminal module to the cloud center module, wherein the current user data includes: relevant data sent by the terminal module for executing the target service request. After the cloud center module and the terminal module connect, the cloud center module responds to the target service request of the terminal module based on the current user data. As can be seen, even before a network outage occurs, the AI ​​prediction module can predict the probability of a reconnection between the cloud center module and the terminal module and execute corresponding data caching strategies. When a network anomaly causes a network outage, the cloud center module and the terminal module can directly reconnect, reducing the need for active user operations. Since the current user data is pre-cached, the user does not need to actively re-upload the data, which improves the efficiency of reconnection and data transfer between the cloud center module and the terminal module, solving the problem of low data transmission efficiency.

[0041] In one embodiment, based on current network data and historical reconnection data, the probability of reconnection between the cloud center module and the terminal module is predicted to obtain a reconnection probability value (i.e., S204). The following steps A1-A3 can be executed:

[0042] Step A1: Obtain real-time data from the communication connection between the AI ​​prediction module and the cloud center module as the current network data.

[0043] Real-time data from the communication connection includes: latency, packet loss rate, and throughput parameters of the current network, obtained in real time based on the communication link between the cloud-based central module and the AI ​​prediction module. This real-time data is used as the current network data.

[0044] Step A2: Obtain the communication data of the terminal module's historical transmission of historical user data as historical reconnection data. The communication data includes: communication network data of disconnected reconnection and / or communication network data of unbroken reconnection.

[0045] The communication data for historical user data transmission includes: based on the communication link between the client terminal module and the AI ​​prediction module, the AI ​​prediction module obtains historical reconnection time, reconnection latency, and other data from the terminal module's historical records when transmitting corresponding historical user data. Specifically, this includes communication network data of reconnection after a break in the communication link between the terminal module and the cloud center module, and / or communication network data of reconnection without a break in the communication link. This communication data is used as historical reconnection data. The reasons for a break in the communication link can include defects such as weak network connection, network outage, or jitter. Historical user data includes current user data generated by the terminal module at a historical moment.

[0046] Meanwhile, since the terminal module is unique, the AI ​​prediction module stores the mapping relationship between the terminal module and the cloud center module, which facilitates the acquisition of relevant data such as the current network data and historical reconnection data of the cloud center module and the target terminal module.

[0047] It should be noted that the cloud center module can verify the terminal module. Only when the unique verification information of the terminal module corresponds to the cloud center module can a connection be established and data be transmitted.

[0048] Step A3: Input the current network data and historical reconnection data into the AI ​​big model in the AI ​​prediction module, calculate the similarity between the current network data and the historical reconnection data, and obtain the reconnection probability value. The AI ​​big model is used to predict the probability of reconnection between the cloud center module and the terminal module after a disconnection, and outputs the reconnection probability value.

[0049] Training a large AI model involves acquiring multiple samples of current network data, historical reconnection data, and reconnection probability values. The large AI model is then trained by adjusting its parameters until the output probability equals the reconnection probability value. The parameters in the large AI model include parameters used to calculate the similarity between the current network data and historical reconnection data, such as cosine values. The specific training process for the large AI model is not limited.

[0050] Based on the trained AI big model, the current network data and historical reconnection data are input into the AI ​​big model in the AI ​​prediction module, and the reconnection probability value is automatically calculated and output. This reconnection probability value is used to predict the probability of reconnection between the cloud center module and the terminal module after a disconnection.

[0051] In this embodiment, the AI ​​prediction module utilizes a large AI model, along with the cloud center module and terminal module, to perform probability analysis of connection reconnection after a break, obtaining a reconnection probability value. Compared to manual statistical analysis, the large AI model in the AI ​​prediction module is more intelligent, and it reduces the influence of human subjectivity in predicting the reconnection probability value for the current situation, making the predicted reconnection probability value more objective. Furthermore, the data analysis method combined with AI technology is far faster than manual analysis, effectively improving data analysis efficiency.

[0052] In one embodiment, based on the predicted reconnection probability value, a corresponding data caching strategy is executed to enable the cloud center module and the terminal module to connect based on the data caching strategy (i.e., S206). The following steps B1-B2 can be executed:

[0053] Step B1: When the predicted reconnection probability value is within the first preset threshold range, the AI ​​prediction module caches the current user data sent by the terminal module.

[0054] The first preset threshold range includes: based on historical statistical data, it is determined that within the first preset threshold range, the probability of reconnection between the terminal module and the cloud center module is the highest.

[0055] Step B2: The terminal module is notified to initiate a reconnection request to the cloud center module and send the current user data to the cloud center module so that the cloud center module and the terminal module can reconnect after a disconnection based on the mapping relationship between the terminal module and the cloud center module.

[0056] Specifically, as an example, such as Figure 3 The diagram illustrates a reconnection process between a terminal module and a cloud-based central module according to an embodiment of this application. The first preset threshold ranges from [90, 100]. When the reconnection probability value is within the first preset threshold range, it indicates a high probability of connection failure due to issues such as lag, blurry images, or screen tearing. Therefore, the AI ​​prediction module synchronously pre-caches and stores current user data and proactively sends a notification to the terminal module initiating a reconnection request to the cloud-based central module. Simultaneously, the AI ​​prediction module uploads the cached current user data to the cloud-based central module. The cloud-based central module receives the reconnection request from the terminal module. Due to the uniqueness of the terminal module and the mapping relationship between the cloud-based central module and the terminal module, the cloud-based central module allows the terminal module to reconnect after verifying its identity information. After the cloud-based central module and the terminal module establish a connection, the cloud-based central module has already received the current user data sent by the AI ​​prediction module. Therefore, it can promptly restore the current user data of the current user in the current virtual machine or container, achieving seamless reconnection and restoration of the target service. The cloud-based central module then sends the result of executing the target service request to the terminal module.

[0057] The current user data includes user identification (ID), playback speed, playback application, remote control input, etc.

[0058] In this embodiment, when the predicted reconnection probability value is within the first preset threshold range, it indicates that there is a problem of disconnection and reconnection between the terminal module and the cloud center module. The AI ​​prediction module can notify the terminal module in advance to initiate a reconnection request to the cloud center module and reconnect according to the mapping relationship between the two. This enables seamless link reconnection and improves the efficiency of processing target services.

[0059] In one embodiment, based on the predicted reconnection probability value, a corresponding data caching strategy is executed to enable the cloud center module and the terminal module to connect based on the data caching strategy (i.e., S206). The following steps C1-C2 can be executed:

[0060] Step C1: When the predicted reconnection probability value is within the range of the second preset threshold, the AI ​​prediction module caches the current user data sent by the terminal; wherein, the range of the second preset threshold is smaller than the range of the first preset threshold.

[0061] The second preset threshold range includes: based on historical statistical data, it is determined that within the second preset threshold range, the probability of disconnection and reconnection between the terminal module and the cloud center module is generally within the range. The second preset threshold range is smaller than the first preset threshold range, indicating that the larger the preset threshold range, the greater the probability of disconnection and reconnection between the terminal module and the cloud center module.

[0062] Step C2: Monitor the reconnection request initiated by the terminal module to the cloud center module, and send the current user data to the cloud center module. When the terminal module successfully initiates the reconnection request, based on the mapping relationship between the terminal module and the cloud center module, enable the cloud center module and the terminal module to reconnect after the connection is lost.

[0063] Specifically, as an example, such as Figure 4The diagram illustrates the reconnection process between the terminal module and the cloud center module according to another embodiment of this application. The second preset threshold ranges from [60, 90). When the reconnection probability is within the second preset threshold range, it indicates that the network condition is slightly worse but acceptable. Therefore, the AI ​​prediction module synchronously pre-caches and stores the current user data and detects reconnection requests initiated by the terminal module to the cloud center module. While waiting for the terminal module to initiate a reconnection request, the AI ​​prediction module uploads the cached current user data to the cloud center module, which then receives the reconnection request. When the terminal module initiates a reconnection request, due to the uniqueness of the terminal module and the mapping relationship with the cloud center module, the cloud center module allows the terminal module to reconnect after verifying its identity information. After the cloud center module and the terminal module establish a connection, the cloud center module has already received the current user data sent by the AI ​​prediction module. Therefore, it can promptly restore the current user data of the current user in the current virtual machine or container, achieving seamless reconnection and restoration of the target service. The cloud center module then sends the result of the target service execution request to the terminal module.

[0064] In summary, in scenarios with network anomalies, the AI ​​prediction module can cache current user data and send it to the cloud center module. By acquiring current network data and historical reconnection data, it can predict the probability of reconnection between the terminal module and the cloud center module, obtain a reconnection probability value, and execute the corresponding caching strategy based on the reconnection probability value. When the terminal module and the cloud center module reconnect, the cloud center module restores the current user data based on the current user data sent by the AI ​​prediction module, achieving seamless link reconnection.

[0065] In this embodiment, when the predicted reconnection probability value is within the second preset threshold range, it indicates that there may be a problem of disconnection and reconnection between the terminal module and the cloud center module, but the problem is not significant. The AI ​​prediction module monitors the reconnection request initiated by the terminal module to the cloud center module. There is no need to notify the terminal module to initiate a reconnection request. When the terminal module initiates a reconnection request to the cloud center module, the connection is reconnected according to the mapping relationship between the two, which can perform link reconnection without being noticed, thereby improving the efficiency of processing target services.

[0066] In one embodiment, based on the predicted reconnection probability value, a corresponding data caching strategy is executed to enable the cloud center module and the terminal module to connect based on the data caching strategy (i.e., S206). The following step D can be executed:

[0067] Step D: When the predicted reconnection probability value is within the range of the third preset threshold, the AI ​​prediction module caches the current user data sent by the terminal module and clears the expired historical user data in the AI ​​prediction module; wherein, the range of the third preset threshold is smaller than the range of the second preset threshold.

[0068] The third preset threshold range includes: based on historical statistical data, it is determined that within this range, the probability of connection loss and reconnection between the terminal module and the cloud center module is very small. The third preset threshold range is smaller than the second preset threshold range, indicating that the larger the preset threshold range, the greater the probability of connection loss and reconnection between the terminal module and the cloud center module. The smallest third preset threshold range indicates a good network, with almost no connection loss and reconnection.

[0069] Historical user data includes historical current user data stored in the AI ​​detection module, expired historical user data, and historical user data that no longer needs to be used to predict reconnection probability values, as there is already enough data for the AI ​​detection module to use.

[0070] Specifically, as an example, when the third preset threshold range is between [0, 60), when the reconnection probability value is within the third preset threshold range, it indicates that the network condition is good and there is no need to disconnect and reconnect. At this time, the AI ​​prediction module stores the current user data and also cleans up expired historical user data to reduce the storage of invalid data.

[0071] In this embodiment, when the predicted reconnection probability value is within the range of the third preset threshold, the AI ​​prediction module caches the current user data sent by the terminal module, and can use the latest current user data as the subsequent historical user data to calculate the reconnection probability value, thereby improving the accuracy of calculating the reconnection probability value. Furthermore, by cleaning up expired historical user data, the pressure on stored data is alleviated.

[0072] In one embodiment, to connect the cloud center module and the terminal module based on a data caching strategy (S208), the following step E can be performed:

[0073] Step E: When there is a reconnection between the cloud center module and the terminal module, receive the latency parameters of the reconnection process synchronized by the terminal module, and update the historical reconnection data stored in the AI ​​prediction module.

[0074] The latency parameters include the time required for the terminal module to transmit the current user data to the cloud center module, and the latency parameters in the historical reconnection data recorded in the AI ​​prediction module are updated.

[0075] Specifically, after a reconnection operation occurs in the terminal module, the terminal module will synchronize the latency parameters involved in the reconnection process to the AI ​​prediction module, thereby updating the historical user data in the AI ​​prediction module for subsequent data analysis.

[0076] In this embodiment, after the cloud center module and the terminal module reconnect, the cloud center module receives the latency parameters synchronized by the terminal module during the reconnection process and updates the historical reconnection data stored in the AI ​​prediction module for subsequent data analysis to improve the accuracy of the predicted reconnection probability value.

[0077] In one embodiment, such as Figure 5 The diagram illustrates a data caching strategy based on reconnection probability values. The AI ​​prediction module predicts the probability of reconnection after a connection failure by acquiring current network data and historical reconnection data. It also receives current user data, reads the predicted reconnection probability value, and determines whether the probability value is between [90, 100]. If the probability value is between [90, 100], the module stores the current user data and sends it to the cloud center module. Simultaneously, it actively notifies the terminal module to initiate a reconnection request to the cloud center module. Based on the reconnection request, the terminal module and the cloud center module re-establish communication. Alternatively, the module can determine whether the reconnection probability value is between [60, 90). If the probability value is between [60, 90), the module stores the current user data and sends it to the cloud center module. It also waits for the terminal module to initiate a reconnection request to the cloud center module. Based on the reconnection request, the terminal module and the cloud center module re-establish communication. The system checks if the reconnection probability value is between [0, 60). If it is, it stores the current user data and cleans up expired historical user data. Since the AI ​​prediction module pre-caches the current user data and can send it to the cloud center module in advance, the cloud center module can promptly respond to the terminal module's target business requests after the terminal module and cloud center module reconnect, without requiring the terminal module to send the current user data to the cloud center module again.

[0078] In this embodiment, the AI ​​prediction module executes different data caching strategies based on the predicted reconnection probability values ​​within different ranges. Furthermore, it caches current user data in the event of a link failure and sends this data to the cloud center module in advance, eliminating the need for the terminal module to resend data to the cloud center module and overcoming the impact of communication link failures on the user experience. For scenarios where link failures may occur, the data caching strategy for business data is executed in advance. By caching current user data in advance, it effectively avoids business application interruptions when communication links fail. Simultaneously, the cached current user data is updated periodically, such as periodically cleaning up expired historical user data, thereby effectively ensuring data real-time performance and reducing errors caused by differences in historical user data. When a communication link failure occurs, the system can automatically reconnect based on the predicted reconnection probability value, improving the user experience of the cloud-based video system.

[0079] Figure 6This diagram illustrates an AI-based predictive reconnection method according to another embodiment of the present invention. The method is applied to a cloud-based central module and includes the following steps:

[0080] S601 receives current user data sent by the AI ​​prediction module.

[0081] S602, receive a reconnection request sent by the terminal module.

[0082] S603 verifies the terminal module based on the mapping relationship between the terminal module and the cloud center module.

[0083] The current user data may include the mapping relationship between the terminal module and the cloud center module.

[0084] S604, after successful verification, the cloud center module and the terminal module establish a communication connection.

[0085] S605 restores the current user data in the current virtual machine or container and transmits data with the terminal module to respond to the target business request in the terminal module.

[0086] Figure 7 This is a schematic flowchart of an AI-based predictive reconnection method according to another embodiment of this application, such as... Figure 7 As shown, the method includes the following steps:

[0087] S701, builds an AI prediction module and establishes a data communication link.

[0088] The data communication links include the communication links between the AI ​​prediction module and the terminal module, the communication links between the AI ​​prediction module and the cloud center module, and multiple communication links between the terminal module and the cloud center module.

[0089] S702, the AI ​​prediction module obtains current network data and historical reconnection data.

[0090] S703, based on current network data and historical reconnection data, predicts the probability of reconnection between the cloud center module and the terminal module after a disconnection, and obtains the reconnection probability value.

[0091] S704 compares the reconnection probability value with a preset threshold range to obtain the comparison result, and executes the corresponding data caching strategy based on the comparison result.

[0092] The preset threshold ranges include a first preset threshold range, a second preset threshold range, and a third preset threshold range, wherein the first preset threshold range is greater than the second preset threshold range, and the second preset threshold range is greater than the third preset threshold range.

[0093] S705, when the comparison result is that the reconnection probability value is within the first preset threshold range, the AI ​​prediction module caches the current user data and sends it to the cloud center module; at the same time, the terminal is notified to initiate a reconnection request to the cloud center module.

[0094] S706, the cloud center module verifies the terminal and establishes a communication connection with the terminal, and responds to the current user data corresponding to the terminal that is pre-sent by the AI ​​prediction module.

[0095] S707, when the comparison result is that the reconnection probability value is within the second preset threshold range, the AI ​​prediction module caches the current user data and sends it to the cloud center module; at the same time, it waits for the terminal to initiate a reconnection request to the cloud center module.

[0096] S708, after the terminal module initiates a reconnection request to the cloud center module, the cloud center module verifies the terminal module and establishes a communication connection with the terminal module, and responds with the current user data corresponding to the terminal module that was pre-sent by the AI ​​prediction module.

[0097] S709, when the comparison result shows that the reconnection probability value is within the range of the third preset threshold, the AI ​​prediction module caches the current user data and clears the expired historical user data in the AI ​​prediction module.

[0098] S710, when there is a reconnection between the cloud center module and the terminal module, receives the latency parameters of the reconnection process synchronized by the terminal module, and updates the historical reconnection data stored in the AI ​​prediction module.

[0099] The specific processes from S701 to S710 have been described in detail in the above embodiments and will not be repeated here.

[0100] The technical solution adopted in this application embodiment is applied to an AI prediction module to obtain current network data and historical reconnection data. The current network data includes network status data of the communication connection between the AI ​​prediction module and the cloud center module, and the historical reconnection data includes communication status data of the terminal module's historical transmission of user data. Based on the current network data and historical reconnection data, the probability of reconnection between the cloud center module and the terminal module is predicted to obtain a reconnection probability value. According to the predicted reconnection probability value, a corresponding data caching strategy is executed to enable the cloud center module and the terminal module to connect based on the data caching strategy. The data caching strategy includes: notifying the terminal module to send a reconnection request to the cloud center module, and pre-sending the cached current user data sent by the terminal module to the cloud center module, wherein the current user data includes: relevant data sent by the terminal module for executing the target service request. After the cloud center module and the terminal module connect, the cloud center module responds to the target service request of the terminal module based on the current user data. As can be seen, even before a network outage occurs, the AI ​​prediction module can predict the probability of a reconnection between the cloud center module and the terminal module and execute corresponding data caching strategies. When a network anomaly causes a network outage, the cloud center module and the terminal module can directly reconnect, reducing the need for active user operations. Since the current user data is pre-cached, the user does not need to actively re-upload the data, which improves the efficiency of reconnection and data transfer between the cloud center module and the terminal module, solving the problem of low data transmission efficiency.

[0101] In summary, specific embodiments of this subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing can be advantageous.

[0102] The above is an AI-based predictive reconnection method provided by the embodiments of this application. Based on the same idea, the embodiments of this application also provide an AI-based predictive reconnection device.

[0103] Figure 8 This is a schematic diagram of an AI-based predictive reconnection device according to an embodiment of the present invention. Figure 8 As shown, the AI-based predictive reconnection device includes: an acquisition module 81, a prediction module 82, a connection module 83, and a response module 84.

[0104] The acquisition module 81 is used to acquire current network data and historical reconnection data. The current network data includes network status data of the communication connection between the AI ​​prediction module and the cloud center module. The historical reconnection data includes communication status data of the terminal module's historical transmission of user data.

[0105] The prediction module 82 is used to predict the probability of reconnection between the cloud center module and the terminal module based on the current network data and historical reconnection data, and obtain the reconnection probability value.

[0106] The connection module 83 is used to execute a corresponding data caching strategy based on the predicted reconnection probability value, so as to enable the cloud center module and the terminal module to connect based on the data caching strategy; the data caching strategy includes: notifying the terminal module to send a reconnection request to the cloud center module, and pre-sending the cached current user data sent by the terminal module to the cloud center module, wherein the current user data includes: relevant data sent by the terminal module for executing the target business request;

[0107] The response module 84 is used to enable the cloud center module to respond to the target business request of the terminal module based on the current user data after the cloud center module and the terminal module are connected.

[0108] In one embodiment, the prediction module 82 is specifically used to acquire real-time data of the communication connection between the AI ​​prediction module and the cloud center module as current network data; acquire communication data of historical user data transmitted by the terminal module as historical reconnection data, the communication data including: communication network data of disconnected reconnection and / or communication network data of undisconnected reconnection; input the current network data and historical reconnection data into the AI ​​big model in the AI ​​prediction module, calculate the similarity between the current network data and the historical reconnection data, and obtain the reconnection probability value, wherein the AI ​​big model is used to predict the probability of disconnected reconnection between the cloud center module and the terminal module, and output the reconnection probability value.

[0109] In one embodiment, the connection module 83 is specifically used to cache the current user data sent by the terminal module when the predicted reconnection probability value is within the first preset threshold range; notify the terminal module to initiate a reconnection request to the cloud center module, and send the current user data to the cloud center module, so as to enable the cloud center module and the terminal module to reconnect after a disconnection based on the mapping relationship between the terminal module and the cloud center module.

[0110] In one embodiment, the connection module 83 is further configured to: when the predicted reconnection probability value is within a second preset threshold range, cache the current user data sent by the terminal; wherein the second preset threshold range is less than the first preset threshold range; monitor the reconnection request initiated by the terminal module to the cloud center module, and send the current user data to the cloud center module; when the terminal module successfully initiates the reconnection request, based on the mapping relationship between the terminal module and the cloud center module, enable the cloud center module and the terminal module to reconnect after the connection is lost.

[0111] In one embodiment, the connection module 83 is further configured to cache the current user data sent by the terminal module and clear expired historical user data in the AI ​​prediction module when the predicted reconnection probability value is within the range of a third preset threshold; wherein the range of the third preset threshold is smaller than the range of the second preset threshold.

[0112] In one embodiment, the device further includes an update module, which is used to receive latency parameters from the reconnection process synchronized by the terminal module and update the historical reconnection data stored in the AI ​​prediction module when there is a reconnection between the cloud center module and the terminal module.

[0113] The technical solution adopted in this application embodiment is applied to an AI prediction module to obtain current network data and historical reconnection data. The current network data includes network status data of the communication connection between the AI ​​prediction module and the cloud center module, and the historical reconnection data includes communication status data of the terminal module's historical transmission of user data. Based on the current network data and historical reconnection data, the probability of reconnection between the cloud center module and the terminal module is predicted to obtain a reconnection probability value. According to the predicted reconnection probability value, a corresponding data caching strategy is executed to enable the cloud center module and the terminal module to connect based on the data caching strategy. The data caching strategy includes: notifying the terminal module to send a reconnection request to the cloud center module, and pre-sending the cached current user data sent by the terminal module to the cloud center module, wherein the current user data includes: relevant data sent by the terminal module for executing the target service request. After the cloud center module and the terminal module connect, the cloud center module responds to the target service request of the terminal module based on the current user data. As can be seen, even before a network outage occurs, the AI ​​prediction module can predict the probability of a reconnection between the cloud center module and the terminal module and execute corresponding data caching strategies. When a network anomaly causes a network outage, the cloud center module and the terminal module can directly reconnect, reducing the need for active user operations. Since the current user data is pre-cached, the user does not need to actively re-upload the data, which improves the efficiency of reconnection and data transfer between the cloud center module and the terminal module, solving the problem of low data transmission efficiency.

[0114] Those skilled in the art will understand that Figure 8 The AI-based predictive reconnection device described above can be used to implement the AI-based predictive reconnection method. The details of the method description should be similar to those in the previous section. To avoid being too complicated, they will not be repeated here.

[0115] Based on the same technical concept, embodiments of this application also provide an electronic device for executing the above-described AI-based predictive reconnection method. Figure 9 This is a schematic diagram of the structure of an electronic device to implement various embodiments of this application. The electronic device can vary significantly due to differences in configuration or performance, and may include a processor 910, a communication interface 920, a memory 930, and a communication bus 940. The processor 910, communication interface 920, and memory 930 communicate with each other via the communication bus 940. The processor 910 can call a computer program stored in the memory 930 and executable on the processor 910 to perform the following steps:

[0116] Acquire current network data and historical reconnection data. Current network data includes network status data of communication connection between the AI ​​prediction module and the cloud center module. Historical reconnection data includes communication status data of the terminal module's historical transmission of user data.

[0117] Based on current network data and historical reconnection data, the probability of reconnection between the cloud center module and the terminal module is predicted, and the reconnection probability value is obtained.

[0118] Based on the predicted reconnection probability value, the corresponding data caching strategy is executed to enable the cloud center module and the terminal module to connect. The data caching strategy includes: notifying the terminal module to send a reconnection request to the cloud center module, and pre-sending the cached current user data sent by the terminal module to the cloud center module. The current user data includes: relevant data sent by the terminal module for executing the target business request.

[0119] After the cloud center module and the terminal module are connected, the cloud center module responds to the target business requests of the terminal module based on the current user data.

[0120] The technical solution adopted in this application embodiment is applied to an AI prediction module to obtain current network data and historical reconnection data. The current network data includes network status data of the communication connection between the AI ​​prediction module and the cloud center module, and the historical reconnection data includes communication status data of the terminal module's historical transmission of user data. Based on the current network data and historical reconnection data, the probability of reconnection between the cloud center module and the terminal module is predicted to obtain a reconnection probability value. According to the predicted reconnection probability value, a corresponding data caching strategy is executed to enable the cloud center module and the terminal module to connect based on the data caching strategy. The data caching strategy includes: notifying the terminal module to send a reconnection request to the cloud center module, and pre-sending the cached current user data sent by the terminal module to the cloud center module, wherein the current user data includes: relevant data sent by the terminal module for executing the target service request. After the cloud center module and the terminal module connect, the cloud center module responds to the target service request of the terminal module based on the current user data. As can be seen, even before a network outage occurs, the AI ​​prediction module can predict the probability of a reconnection between the cloud center module and the terminal module and execute corresponding data caching strategies. When a network anomaly causes a network outage, the cloud center module and the terminal module can directly reconnect, reducing the need for active user operations. Since the current user data is pre-cached, the user does not need to actively re-upload the data, which improves the efficiency of reconnection and data transfer between the cloud center module and the terminal module, solving the problem of low data transmission efficiency.

[0121] The specific execution steps can be found in the various steps of the above-described AI-based predictive reconnection method embodiment, and can achieve the same technical effect. To avoid repetition, they will not be repeated here.

[0122] It should be noted that the electronic devices in the embodiments of this application include: servers, terminals, or other devices besides terminals.

[0123] The above electronic device structure does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or arrange them differently. For example, an input unit may include a Graphics Processing Unit (GPU) and a microphone, and a display unit may use a liquid crystal display (LCD), organic light-emitting diode (OLED), or other similar display panels. User input units include at least one of a touch panel and other input devices. A touch panel is also called a touchscreen. Other input devices may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be elaborated further here.

[0124] Memory can be used to store software programs and various data. Memory can primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area can store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, memory can include volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0125] The processor may include one or more processing units; optionally, the processor integrates an application processor and a modem processor, wherein the application processor mainly handles operations related to the operating system, user interface, and applications, while the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor.

[0126] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described AI-based predictive reconnection method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0127] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0128] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described AI-based prediction reconnection method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0129] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0130] This application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the processor is used to run the program or instructions to implement the various processes of the above-mentioned product recommended method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0131] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0132] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0133] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. An AI-based prediction-based reconnection method, applied to an AI prediction module, characterized in that, The method includes: Acquire current network data and historical reconnection data. The current network data includes network status data of the communication connection between the AI ​​prediction module and the cloud center module. The historical reconnection data includes communication status data of the terminal module's historical transmission of user data. Based on the current network data and the historical reconnection data, the probability of reconnection between the cloud center module and the terminal module is predicted, and a reconnection probability value is obtained. Based on the predicted reconnection probability value, a corresponding data caching strategy is executed to enable the cloud center module and the terminal module to connect based on the data caching strategy. The data caching strategy includes: notifying the terminal module to send a reconnection request to the cloud center module, and pre-sending the cached current user data sent by the terminal module to the cloud center module, wherein the current user data includes: relevant data sent by the terminal module for executing the target service request. After the cloud center module and the terminal module are connected, the cloud center module responds to the target service request of the terminal module based on the current user data.

2. The method according to claim 1, characterized in that, The step of predicting the probability of reconnection between the cloud center module and the terminal module based on the current network data and the historical reconnection data, and obtaining the reconnection probability value, includes: The real-time data from the communication connection between the AI ​​prediction module and the cloud center module is obtained as the current network data. The communication data of the terminal module that transmits historical user data is obtained as the historical reconnection data. The communication data includes: communication network data of disconnected reconnection and / or communication network data of non-disconnected reconnection. The current network data and the historical reconnection data are input into the AI ​​big model in the AI ​​prediction module to calculate the similarity between the current network data and the historical reconnection data, and obtain the reconnection probability value. The AI ​​big model is used to predict the probability of reconnection between the cloud center module and the terminal module after a disconnection, and outputs the reconnection probability value.

3. The method according to claim 1, characterized in that, The step of executing a corresponding data caching strategy based on the predicted reconnection probability value, so as to enable the cloud center module and the terminal module to connect based on the data caching strategy, includes: When the predicted reconnection probability value is within the first preset threshold range, the AI ​​prediction module caches the current user data sent by the terminal module; The terminal module is notified to initiate a reconnection request to the cloud center module and send the current user data to the cloud center module, so that the cloud center module and the terminal module can reconnect after a disconnection based on the mapping relationship between the terminal module and the cloud center module.

4. The method according to claim 3, characterized in that, The step of executing a corresponding data caching strategy based on the predicted reconnection probability value, so as to enable the cloud center module and the terminal module to connect based on the data caching strategy, further includes: When the predicted reconnection probability value is within the second preset threshold range, the AI ​​prediction module caches the current user data sent by the terminal; wherein the second preset threshold range is smaller than the first preset threshold range; The system monitors the reconnection request initiated by the terminal module to the cloud center module and sends the current user data to the cloud center module. When the terminal module successfully initiates the reconnection request, the system enables the cloud center module and the terminal module to reconnect after the connection is lost, based on the mapping relationship between the terminal module and the cloud center module.

5. The method according to claim 4, characterized in that, The step of executing a corresponding data caching strategy based on the predicted reconnection probability value, so as to enable the cloud center module and the terminal module to connect based on the data caching strategy, further includes: When the predicted reconnection probability value is within the range of the third preset threshold, the AI ​​prediction module caches the current user data sent by the terminal module and clears the expired historical user data in the AI ​​prediction module; wherein, the range of the third preset threshold is smaller than the range of the second preset threshold.

6. The method according to claim 1, characterized in that, After the cloud center module and the terminal module are connected based on the data caching strategy, the following steps are included: When the cloud center module and the terminal module reconnect, the latency parameters of the reconnection process synchronized by the terminal module are received, and the historical reconnection data stored in the AI ​​prediction module is updated.

7. An AI-based predictive reconnection device, characterized in that, The device includes: The acquisition module is used to acquire current network data and historical reconnection data. The current network data includes network status data of the communication connection between the AI ​​prediction module and the cloud center module. The historical reconnection data includes communication status data of the terminal module's historical transmission of user data. The prediction module is used to predict the probability of reconnection between the cloud center module and the terminal module based on the current network data and the historical reconnection data, and obtain the reconnection probability value. The connection module is used to execute a corresponding data caching strategy based on the predicted reconnection probability value, so as to enable the cloud center module and the terminal module to connect based on the data caching strategy; the data caching strategy includes: notifying the terminal module to send a reconnection request to the cloud center module, and pre-sending the cached current user data sent by the terminal module to the cloud center module, wherein the current user data includes: relevant data sent by the terminal module for executing the target service request; The response module is used to, after the cloud center module and the terminal module are connected, enable the cloud center module to respond to the target service request of the terminal module based on the current user data.

8. An electronic device, characterized in that, The device includes a processor and a memory electrically connected to the processor, the memory storing a computer program, and the processor being configured to call and execute the computer program from the memory to implement an AI-based predictive reconnection method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The storage medium is used to store a computer program that can be executed by a processor to implement an AI-based predictive reconnection method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program, which, when executed by a processor, implements an AI-based predictive reconnection method as described in any one of claims 1 to 6.

Images