Data processing method and device, equipment and storage medium

Abstract

The invention provides a data processing method and device, equipment and a storage medium, which are applied to a first base station, the first base station is used for receiving an artificial intelligence service request sent by a user side, and the method comprises the following steps: if the first base station meets a first preset condition for processing the artificial intelligence service request, processing the artificial intelligence service request; if it is detected that the first base station does not meet a second preset condition within a preset time period in the process of processing the artificial intelligence service request, determining a second base station which continues to process the artificial intelligence service request; and sending the processing information of the artificial intelligence service request and the user information to the second base station. According to the embodiment of the invention, the state of the base station is detected in the process of processing the artificial intelligence service request, so that the task processing information corresponding to the artificial intelligence service request is sent to other base stations when the state of the base station does not meet the corresponding condition, and the other base stations can continue to process the artificial intelligence service request. And the request can be normally processed.

Description

Technical Field

[0001] The present application belongs to the field of wireless communication technology, and specifically relates to a data processing method, device, equipment and storage medium. Background Art

[0002] At present, in order to reduce the limitations of traditional cloud computing structures in processing artificial intelligence services in terms of computing power, transmission speed, and network bandwidth, the Mobile Edge Computing (MEC) computing architecture is adopted to process artificial intelligence services. That is, MEC edge servers are deployed at network edge locations such as base stations, which can localize computing resources and data processing capabilities to achieve low-latency, high-bandwidth data processing and analysis.

[0003] However, when the base station receives the user's artificial intelligence service, it may be unable to process the current service normally because the current base station is in sleep mode, the computing resources of the current base station are occupied, or the current user triggers cell reselection or switching operations due to mobility. Summary of the invention

[0004] The present application proposes a data processing method, device, equipment and storage medium, which can solve the technical problem that the current base station cannot normally process the current business due to some reasons.

[0005] The first aspect of the present application provides a data processing method, which is applied to a first base station, where the first base station is used to receive an artificial intelligence service request sent by a user terminal, including:

[0006] If the first base station meets the first preset condition for processing the artificial intelligence service request, processing the artificial intelligence service request;

[0007] If, during the process of processing the artificial intelligence service request, it is detected that the first base station does not meet the second preset condition for processing the artificial intelligence service request within the preset time period, determining a second base station that continues to process the artificial intelligence service request;

[0008] The processing information and user information of the artificial intelligence service request are sent to the second base station, so that the second base station processes the artificial intelligence service request based on the processing information, and sends the processing result to the user end through the third base station corresponding to the user information.

[0009] The embodiment of the second aspect of the present application provides a data processing device, which is applied to a first base station, and the first base station is used to receive an artificial intelligence service request sent by a user terminal, including:

[0010] a processing module, configured to process the artificial intelligence service request if the first base station meets a first preset condition for processing the artificial intelligence service request;

[0011] a determination module, configured to determine a second base station that continues to process the artificial intelligence service request if it is detected that the first base station does not meet a second preset condition for processing the artificial intelligence service request within a preset time period during the process of processing the artificial intelligence service request;

[0012] A sending module is used to send processing information and user information of the artificial intelligence service request to the second base station, so that the second base station processes the artificial intelligence service request based on the processing information, and sends the processing result to the user end through a third base station corresponding to the user information.

[0013] An embodiment of the third aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in the first aspect above.

[0014] An embodiment of the fourth aspect of the present application provides a computer-readable storage medium on which a computer program is stored, and the program is executed by a processor to implement the method described in the first aspect above.

[0015] The technical solution provided in the embodiments of the present application has at least the following technical effects or advantages:

[0016] The present application proposes a data processing method, device and storage medium, which are applied to a first base station, and the first base station is used to receive an artificial intelligence service request sent by a user terminal, including: if the first base station meets the first preset condition for processing the artificial intelligence service request, then the artificial intelligence service request is processed; if in the process of processing the artificial intelligence service request, it is detected that the first base station does not meet the second preset condition within the preset time period, a second base station is determined to continue to process the artificial intelligence service request; and the processing information and user information of the artificial intelligence service request are sent to the second base station. The embodiment of the present application detects the status of the base station in the process of processing the artificial intelligence service request, so that when the status of the base station does not meet the corresponding condition, the task processing information corresponding to the artificial intelligence service request is sent to other base stations, so that other base stations can continue to process the artificial intelligence service request, ensuring that the request can be processed normally.

[0017] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] By reading the detailed description of the preferred embodiment below, various other advantages and benefits will become clear to those of ordinary skill in the art. The accompanying drawings are only used for the purpose of illustrating the preferred embodiment and are not considered to be limitations of the present application. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings.

[0019] In the attached picture:

[0020] Figure 1 A schematic diagram of a scenario of a data processing method provided by an embodiment of the present application is shown;

[0021] Figure 2 A flow chart of a data processing method provided by an embodiment of the present application is shown;

[0022] Figure 3 A flow chart of a data processing method provided by an embodiment of the present application is shown;

[0023] Figure 4 A schematic diagram showing the structure of a data processing device provided by an embodiment of the present application is shown;

[0024] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application is shown;

[0025] Figure 6 A schematic diagram of a storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0026] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0027] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by technicians in the field to which this application belongs.

[0028] The data processing method of the present application can be executed by a computing device, and the computing device can be a server, such as a server, multiple servers, a server cluster, a cloud computing platform, etc. Optionally, the computing device can also be a terminal device, such as a mobile phone, a tablet computer, a game console, a portable computer, a desktop, an advertising machine, an all-in-one machine, etc. The present application does not limit the device type and the number of devices of the computing device. In line with the above background technology, the rapid popularization and application of 5G technology are promoting the widespread application of artificial intelligence (AI) technology in the network. With the continuous development of AI algorithms and the expansion of application scenarios, the demand for computing resources and data processing capabilities is also increasing. Although the traditional cloud computing architecture can provide powerful computing and storage capabilities, it is difficult to meet the AI ​​business with high requirements for real-time performance and response speed due to problems such as high data transmission delay and limited network bandwidth. In order to solve this problem, MEC has emerged as a new type of computing architecture. By deploying MEC edge servers at network edge locations such as base stations, computing resources and data processing capabilities can be proximalized to achieve low-latency, high-bandwidth data processing and analysis. Therefore, the MEC edge server based on 5G technology has become one of the important infrastructures to support rich AI business networks.

[0029] However, in the 5G network architecture, the base station (BS) provides users with close-range, low-latency computing services by integrating mobile edge computing servers, which is particularly advantageous when processing computing-intensive tasks such as AI training. However, the existing collaboration mechanism between users and base stations has exposed some key defects in practical applications, which may lead to unnecessary consumption of computing resources and service delays.

[0030] First, when users submit their AI training tasks to the currently serving base station, AI training tasks usually require the base station to complete the training and reasoning of the model in a longer time compared to traditional millisecond-level response communication services. During this period, if the base station enters a dormant state due to energy-saving strategies, or the user triggers a cell reselection or switching operation due to mobility, the current base station will not be able to complete the training and transmit the final training results back to the user. When the user successfully switches to a new base station, they have to upload the model data again and repeat the previous training process on the new base station. This process not only wastes computing resources, but may also increase the overall latency of the service due to repeated training, which has a negative impact on the user experience.

[0031] Secondly, limited by user mobility and network coverage, users can usually only establish connections with one or a few base stations. Therefore, in core areas with dense populations or frequent user activities, the MEC computing business load of these base stations will be very high, while the computing resources of surrounding base stations may be idle. This is because users cannot fully grasp the global information and cannot establish connections with all potential base stations to achieve effective sharing and utilization of computing resources. This problem of unbalanced distribution of computing demand not only limits the performance of 5G network MEC services, but may also lead to network congestion and reduced service quality.

[0032] It should be emphasized that, unlike traditional mec computing offloading, traditional mec business processing may actively split the current user's computing tasks and evenly distribute the tasks to each server, such as 70% offloading to base station A and 30% offloading to base station B. However, AI model training tasks are indivisible, that is, without the first 70% of training results / process volume, the last 30% of model training cannot be performed.

[0033] In order to solve the above problems, the embodiments of the present application provide a data processing method, device, equipment and storage medium, which are applied to a first base station, and the first base station is used to receive an artificial intelligence service request sent by a user terminal, including: if the first base station meets the first preset condition for processing the artificial intelligence service request, then the artificial intelligence service request is processed; if in the process of processing the artificial intelligence service request, it is detected that the first base station does not meet the second preset condition within the preset time period, a second base station is determined to continue to process the artificial intelligence service request; and the processing information and user information of the artificial intelligence service request are sent to the second base station. The embodiments of the present application detect the status of the base station in the process of processing the artificial intelligence service request, so that when the status of the base station does not meet the corresponding conditions, the task processing information corresponding to the artificial intelligence service request is sent to other base stations, so that other base stations can continue to process the artificial intelligence service request, ensuring that the request can be processed normally.

[0034] First, the application scenario of the area division method provided in the embodiment of the present application is described. Figure 1 As shown, the scenario includes multiple base stations and user terminals.

[0035] Among them, the user end can be implemented as an electronic device, which can be a mobile phone, tablet computer, laptop computer, desktop computer, television, projector, digital camera, audio equipment, game console, smart watch, smart wearable device e-reader, car entertainment system and household appliances (such as refrigerator, washing machine), etc.

[0036] The user terminal can send an AI service request to a base station that establishes a communication connection with the user terminal.

[0037] A base station can be deployed with multiple MEC edge servers.

[0038] The MEC edge server can be one server, multiple servers, a server cluster, a cloud computing platform, etc.

[0039] The multiple base stations may include a first base station, a second base station and a third base station;

[0040] The first base station can receive an AI service request from a user terminal; detect whether the first base station meets a first preset condition for processing an artificial intelligence service request, and if the first base station meets the first preset condition for processing an artificial intelligence service request, process the artificial intelligence service request; if in the process of processing the artificial intelligence service request, it is detected that the first base station does not meet a second preset condition for processing the artificial intelligence service request within a preset time period, determine a second base station that continues to process the artificial intelligence service request; send processing information and user information of the artificial intelligence service request to the second base station, so that the second base station processes the artificial intelligence service request based on the processing information, and sends the processing result to the user terminal through a third base station corresponding to the user information.

[0041] A data processing method proposed according to an embodiment of the present application is described below in conjunction with the accompanying drawings. The method is applied to a first base station, and the first base station is used to receive an artificial intelligence service request sent by a user terminal.

[0042] See also Figure 2 , the method specifically comprises the following steps:

[0043] S201. If the first base station meets a first preset condition for processing an artificial intelligence service request, it processes the artificial intelligence service request.

[0044] Among them, the first base station is a base station that receives an AI service request from a user segment.

[0045] In some embodiments, the first base station may be provided with multiple MEC servers. After receiving the AI ​​service request, the first base station determines the current resource occupancy of each MEC server and the resource occupancy required to process the AI ​​service request, thereby determining the total resource occupancy when processing the AI ​​service request, and determines whether to process the AI ​​service request at the first base station based on the total resource occupancy. Correspondingly, the first preset condition may be that the total resource occupancy is less than the resource occupancy threshold of the first base station, wherein the resource occupancy threshold may be flexibly set based on actual conditions, such as 80%, 90%, etc.

[0046] In some embodiments, the first base station may be provided with a plurality of task processing channels. Therefore, the first preset condition may also be that the occupancy rate of the processing channel when the first base station processes the AI ​​task is less than a channel occupancy rate threshold, etc.

[0047] The first base station meets the first preset condition, which means that the first base station meets the condition for processing the AI ​​service request when receiving the AI ​​service request, and can start processing the AI ​​service request.

[0048] S202. If, during processing of an artificial intelligence service request, it is detected that the first base station does not meet a second preset condition for processing the artificial intelligence service request within a preset time period, a second base station is determined to continue processing the artificial intelligence service request.

[0049] It is understandable that in the process of processing the AI ​​service request, the base station state of the first base station may change or the communication state between the first base station and the user terminal may change. In order to ensure that the AI ​​service request can be processed normally, it is necessary to detect the base station state of the first base station. When it is determined that the first base station cannot process the AI ​​service request, a base station that can continue to process the AI ​​service request is determined to continue processing.

[0050] Among them, when the first base station is in different base station states, the available resources of the MEC server are different or the available channels are different. Therefore, the total resource occupancy when the first base station processes AI tasks or the channel occupancy when the first base station processes AI tasks will change.

[0051] When the total resource occupancy rate increases to a value greater than or equal to the total resource occupancy rate threshold when the first base station processes an AI task, or when the channel occupancy rate increases to a value greater than or equal to the channel occupancy rate threshold when the first base station processes an AI task, the first base station will not be able to process the AI ​​service request. Therefore, the second preset condition may be that the total resource occupancy rate is less than the resource occupancy rate threshold of the first base station, or that the occupancy rate of the processing channel when the first base station processes the AI ​​task is less than the channel occupancy rate threshold.

[0052] In addition, during the process of the first base station processing the AI ​​task, the user terminal may have a cell switch, that is, the communication connection between the first base station and the user terminal is interrupted. In some cases, when the communication between the base station and the user terminal is interrupted, the base station needs to send the request sent by the user terminal to the base station with which the user terminal establishes a connection. Therefore, the second preset condition may be that a cell switch occurs on the user terminal.

[0053] Among them, a period of time before the base station state of the first base station changes, the base station will receive the corresponding base station state switching instruction. Therefore, the first base station already knows when the base station state needs to be switched before determining the second base station; and before the switching operation of the cell switching on the user end is completed, the first user end can also obtain the information that the user end is going to switch the cell through the user end. Therefore, if the base station state of the first base station changes or the user end needs to switch the cell, there will be a corresponding buffer time. Therefore, the preset time period can be flexibly set based on the actual situation, but it is generally greater than the buffer time.

[0054] Among them, if the total resource occupancy rate of the first base station when processing the AI ​​task is less than the resource occupancy rate threshold of the first base station, or the occupancy rate of the processing channel when the first base station processes the AI ​​task is less than the channel occupancy rate threshold, the second base station can be the base station with the smallest total resource occupancy rate or the smallest processing channel occupancy rate among the base stations communicating with the first base station.

[0055] If a cell handover occurs at the user terminal, the second base station is the base station that establishes a communication connection with the user terminal.

[0056] S203: Send processing information and user information of the artificial intelligence service request to the second base station, so that the second base station processes the artificial intelligence service request based on the processing information, and sends the processing result to the user end through the third base station corresponding to the user information.

[0057] Because it is different from traditional mec computing offloading, traditional mec business processing may actively split the current user's computing tasks and evenly distribute the tasks to each server, such as base station A unloading 70% and base station B unloading 30%. However, the AI ​​model training task is indivisible, that is, without the first 70% of the training results / process volume, the last 30% of model training cannot be performed. Therefore, when the second base station is determined, the processing information and user information of the AI ​​service request need to be sent to the second base station.

[0058] After receiving the processing information and user information, the second base station will also determine whether the second base station meets the third preset condition corresponding to the second base station based on the processing information. If it does, it will continue to process the AI ​​service request based on the processing information, that is, continue to train the model or continue to reason, obtain the processing result and broadcast the user information, determine the third base station that is currently connected to the user terminal corresponding to the user information, and send the processing result to the user terminal through the third base station.

[0059] The third base station is a base station that processes the connection status with the user terminal when the processing result is obtained.

[0060] Further, the user terminal confirms the processing result and provides further feedback and requirements. The third base station records the feedback information and performs continuous optimization and improvement.

[0061] The embodiment of the present application provides a data processing method, which is applied to a first base station, and the first base station is used to receive an artificial intelligence service request sent by a user terminal. In the embodiment of the present application, if the first base station meets the first preset condition for processing the artificial intelligence service request, the artificial intelligence service request is processed; if in the process of processing the artificial intelligence service request, it is detected that the first base station does not meet the second preset condition within the preset time period, a second base station is determined to continue to process the artificial intelligence service request; and the processing information and user information of the artificial intelligence service request are sent to the second base station. The embodiment of the present application detects the status of the base station in the process of processing the artificial intelligence service request, and thus sends the task processing information corresponding to the artificial intelligence service request to other base stations when the status of the base station does not meet the corresponding conditions, so that other base stations can continue to process the artificial intelligence service request, ensuring that the request can be processed normally.

[0062] In some embodiments, the method further comprises:

[0063] If the first base station does not meet the first preset condition, the service information and user information of the artificial intelligence service request are sent to the fourth base station, so that the fourth base station processes the artificial intelligence service request based on the service information and sends it to the user end through the fifth base station corresponding to the user information.

[0064] If the first base station does not meet the first preset condition, that is, the total resource occupancy rate of the first base station when processing the AI ​​task is less than the resource occupancy rate threshold of the first base station, or the occupancy rate of the processing channel when the first base station processes the AI ​​task is less than the channel occupancy rate threshold, the service information and user information of the artificial intelligence service request are sent to the fourth base station. Therefore, the fourth base station can be the base station with the smallest total resource occupancy rate or the smallest processing channel occupancy rate among the base stations communicating with the first base station. The fifth base station is the base station that processes the connection state with the user terminal when the processing result is obtained.

[0065] In some embodiments, the method further comprises:

[0066] If the second preset condition is always met during the process of the first base station processing the artificial intelligence service request, the corresponding processing result is obtained; and the processing result is sent to the user end.

[0067] Among them, in the process of the first base station processing the AI ​​service request, the first base station can detect the base station status and the communication link between the user end in real time. If the second preset condition is always met in the process of the first base station processing the artificial intelligence service request, that is, the total resource occupancy rate of the first base station when processing the AI ​​task is less than the resource occupancy rate threshold of the first base station, or the occupancy rate of the processing channel when the first base station processes the AI ​​task is less than the channel occupancy rate threshold, and the user end does not have a cell switching, after obtaining the corresponding processing result, the processing result can be sent to the user end.

[0068] In some embodiments, if during the process of processing the artificial intelligence service request, it is detected that the first base station does not meet the second preset condition within the preset time period, determining the second base station that continues to process the artificial intelligence service request includes:

[0069] In the process of processing the artificial intelligence service request, if it is detected that the total occupancy rate of the second resource of the first base station within the preset time period is greater than or equal to the second resource occupancy rate threshold, it is determined that the first base station does not meet the second preset condition within the preset time period, and the second base station that continues to process the artificial intelligence service request is determined;

[0070] Alternatively, in the process of processing an artificial intelligence service request, if it is detected that the user terminal performs cell switching within a preset time period, it is determined that the first base station does not meet the second preset condition within the preset time period, and a second base station is determined to continue processing the artificial intelligence service request.

[0071] As mentioned above, the second preset condition may be that the total resource occupancy rate is less than the resource occupancy rate threshold of the first base station, or the occupancy rate of the processing channel when the first base station processes the AI ​​task is less than the channel occupancy rate threshold, or a cell switching occurs at the user end.

[0072] Among them, cell switching is a key technology in mobile communication systems to ensure seamless connection and communication continuity during user mobility. Its process includes neighbor search and measurement, where the mobile user device searches for neighbor cells near the currently connected cell, obtains information about surrounding cells, and measures parameters such as signal strength; switching decision, where it decides whether to initiate a switching request based on the neighbor measurement results and preset strategies; switching trigger, where if the decision is that switching is necessary, a switching request is sent to the current base station; resource allocation and preparation, where the target cell allocates resources to mobile users based on load conditions and resource availability and prepares for switching; switching execution, where the target cell notifies the mobile user that the switching is complete, ensuring wireless connection continuity and communication quality; switching completion and optimization, where the system optimizes the switching process through monitoring and optimization algorithms to improve user experience and network performance. Throughout the entire process, all links work closely together to ensure the continuity and stability of communication services for users during mobility.

[0073] When a cell handover occurs, the current communication protocol does not have clear requirements for the base station that processes the user's AI service request.

[0074] In some embodiments, when a cell switch occurs, the base station after the switch is required to process the AI ​​service request. Therefore, when a cell switch is detected at the user end, a second base station is determined to continue processing the AI ​​service request.

[0075] In some embodiments, when a cell switch occurs, there is no provision for the base station that processes the AI ​​service request. Therefore, when a cell switch is detected at the user end, the first base station can continue to process the AI ​​service request. After obtaining the processing result, the second base station that currently establishes a communication connection with the user end is determined, and the processing result is returned to the user end through the second base station.

[0076] In some embodiments, before detecting that the total occupancy rate of the second resource of the first base station within a preset time period is greater than or equal to a second resource occupancy rate threshold, it also includes: in the process of processing an artificial intelligence service request, detecting the base station state of the first base station within a preset time period; determining the total occupancy rate of the second resource corresponding to the first base station when processing the artificial intelligence service request in the base station state; detecting whether the total occupancy rate of the second resource of the first base station within the preset time period is greater than or equal to the second resource occupancy rate threshold.

[0077] When the first base station starts to process the AI ​​service request, the first base station is in a normal state, and as the processing proceeds, the base station state of the first base station may change. The base station state includes: a shutdown state and a dormant state.

[0078] The shutdown states include: symbol shutdown, carrier shutdown and channel shutdown.

[0079] Symbol shutdown: When the load is low, the symbol shutdown technology can be used to shut down the sending or receiving functions of some symbols of the base station. By controlling the power allocation and adjustment at the symbol level, the power consumption can be reduced while ensuring the communication quality. Carrier shutdown: When the load is low, the carrier shutdown technology can be used to shut down some carrier channels of the base station. The base station monitors the network load level and dynamically chooses to shut down some carriers to reduce energy consumption. These carriers will be reopened when the capacity needs to be increased. Channel shutdown: The base station can shut down some physical channels when the load is low according to the needs of the communication system. By shutting down unnecessary channels, power consumption and resource consumption are reduced while maintaining the necessary communication capabilities. Cell dormancy: In areas with low user density or low demand periods, some cells can be put into dormant state. The cells in dormant state stop broadcasting and paging, and only retain necessary monitoring and maintenance functions to reduce energy consumption.

[0080] Among them, when the first base station is in different base station states, the available resources of the MEC server are different or the number of available channels is different. Generally, when it is in the off state or the dormant state, the available resource rate of the MEC server decreases, or the number of available channels decreases. Therefore, as the first base station changes from the normal state to the off state, the available resource rate of the MEC server decreases, or the number of available channels decreases. Therefore, when the first base station processes AI tasks, the total resource occupancy rate increases or the channel occupancy rate increases when the first base station processes AI tasks. When the total resource occupancy rate increases to a value greater than or equal to the total resource occupancy rate threshold when the first base station processes AI tasks or the channel occupancy rate increases to a value greater than or equal to the channel occupancy rate threshold when the first base station processes AI tasks, the first base station will not be able to process AI service requests.

[0081] In some embodiments, determining the second base station to continue processing the artificial intelligence service request includes:

[0082] If, in the process of processing an artificial intelligence service request, it is detected that the total occupancy rate of the second resource of the first base station within a preset time period is greater than or equal to a second resource occupancy rate threshold, the base station with the lowest resource occupancy rate among the multiple base stations corresponding to the first base station is determined as the second base station.

[0083] It can be understood that if it is detected that the total occupancy rate of the second resource of the first base station within a preset time period is greater than or equal to the second resource occupancy rate threshold, it means that the first base station cannot process the AI ​​service request at this time. Therefore, the second base station is required to process the AI ​​service request. In order to ensure that the second base station can continue to process the AI ​​service request, the base station with the lowest resource occupancy rate can be determined as the second base station among the multiple base stations corresponding to the first base station.

[0084] Furthermore, the second base station receives and verifies the received processing information, and when the AI ​​service request is processed, sends the corresponding processing result to the base station that currently establishes a communication connection with the user terminal.

[0085] In some embodiments, determining the second base station to continue processing the artificial intelligence service request includes:

[0086] If, in the process of processing an artificial intelligence service request, it is detected that a cell switching occurs at the user end of the first base station within a preset time period, the sixth base station to which the user end switches is determined; if the total resource occupancy rate of the sixth base station when processing the artificial intelligence service request based on the processing information is less than the third resource occupancy rate threshold of the sixth base station, the sixth base station is determined as the second base station; if the total resource occupancy rate of the sixth base station when processing the artificial intelligence service request based on the processing information is greater than or equal to the third resource occupancy threshold, the base station with the lowest resource occupancy rate among the multiple base stations corresponding to the first base station is determined as the second base station.

[0087] When a cell switching occurs, if the switched base station needs to process the AI ​​service request, the sixth base station to which the user terminal switches is determined, and a judgment is made as to whether the total resource occupancy rate of the sixth base station when processing the artificial intelligence service request based on the processing information is less than the third resource occupancy rate threshold of the sixth base station. If the total resource occupancy rate of the sixth base station when processing the artificial intelligence service request based on the processing information is less than the third resource occupancy rate threshold of the sixth base station, the sixth base station is determined as the second base station; if the total resource occupancy rate of the sixth base station when processing the artificial intelligence service request based on the processing information is greater than or equal to the third resource occupancy threshold, the base station with the lowest resource occupancy rate among the multiple base stations corresponding to the first base station is determined as the second base station.

[0088] In order to illustrate the data processing method of the embodiment of the present application, the embodiment of the present application also provides a flow chart of the data processing method, such as Figure 3 As shown, it includes a first base station, a second base station and a third base station.

[0089] The method comprises the following steps:

[0090] S301. A user terminal sends an AI service request to a first base station.

[0091] Among them, AI business requests can be AI business requests such as model training and reasoning.

[0092] S302: If the first base station meets a first preset condition for processing an artificial intelligence service request, it processes the artificial intelligence service request.

[0093] Among them, the first preset condition may be that the total resource occupancy rate of the first base station when processing the AI ​​task is less than the resource occupancy rate threshold of the first base station, or the occupancy rate of the processing channel when the first base station processes the AI ​​task is less than the channel occupancy rate threshold.

[0094] S303. If, during processing of an artificial intelligence service request, the first base station detects that the first base station does not meet a second preset condition for processing the artificial intelligence service request within a preset time period, processing is stopped and a second base station that continues to process the artificial intelligence service request is determined.

[0095] The first preset condition may be that the total resource occupancy rate of the first base station when processing the AI ​​task is less than the resource occupancy rate threshold of the first base station, or the occupancy rate of the processing channel when the first base station processes the AI ​​task is less than the channel occupancy rate threshold, or a cell switching occurs at the user end.

[0096] S304. The first base station sends processing information and user information of the artificial intelligence service request to the second base station.

[0097] S305. The second base station processes the artificial intelligence service request based on the processing information, and sends the processing result to the user end through the third base station corresponding to the user information.

[0098] The present application also provides a data processing device, which is used to execute the data processing method provided in any of the above embodiments. Figure 4 As shown, the device includes: a processing module 401, a determining module 402 and a sending module 403.

[0099] The processing module 401 is configured to process the artificial intelligence service request if the first base station meets a first preset condition for processing the artificial intelligence service request;

[0100] The determination module 402 is configured to determine a second base station that continues to process the artificial intelligence service request if it is detected that the first base station does not meet a second preset condition for processing the artificial intelligence service request within a preset time period during the process of processing the artificial intelligence service request;

[0101] The sending module 403 is used to send the processing information and user information of the artificial intelligence service request to the second base station, so that the second base station processes the artificial intelligence service request based on the processing information, and sends the processing result to the user end through the third base station corresponding to the user information.

[0102] The embodiment of the present application provides a data processing device, which is applied to a first base station, and the first base station is used to receive an artificial intelligence service request sent by a user terminal, including: if the first base station meets the first preset condition for processing the artificial intelligence service request, then the artificial intelligence service request is processed; if in the process of processing the artificial intelligence service request, it is detected that the first base station does not meet the second preset condition within the preset time period, a second base station is determined to continue to process the artificial intelligence service request; and the processing information and user information of the artificial intelligence service request are sent to the second base station. The embodiment of the present application detects the status of the base station in the process of processing the artificial intelligence service request, so that when the status of the base station does not meet the corresponding condition, the task processing information corresponding to the artificial intelligence service request is sent to other base stations, so that other base stations can continue to process the artificial intelligence service request, ensuring that the request can be processed normally.

[0103] In some embodiments, the sending module 403 is further configured to:

[0104] If the first base station does not meet the first preset condition, the service information and user information of the artificial intelligence service request are sent to the fourth base station, so that the fourth base station processes the artificial intelligence service request based on the service information and sends it to the user end through the fifth base station corresponding to the user information.

[0105] In some embodiments, the above device further includes: an acquisition module, configured to:

[0106] If the second preset condition is always met during the process of the first base station processing the artificial intelligence service request, a corresponding processing result is obtained;

[0107] The sending module 403 is further configured to send the processing result to the user terminal if the first base station maintains a communication connection with the user terminal when the processing result is obtained.

[0108] In some embodiments, the determination module 402 is specifically configured to:

[0109] In the process of processing the artificial intelligence service request, if it is detected that the total occupancy rate of the second resource of the first base station within the preset time period is greater than or equal to the second resource occupancy rate threshold, it is determined that the first base station does not meet the second preset condition within the preset time period, and the second base station that continues to process the artificial intelligence service request is determined;

[0110] Alternatively, in the process of processing the artificial intelligence service request, if it is detected that the user terminal performs cell switching within the preset time period, it is determined that the first base station does not meet the second preset condition within the preset time period, and a second base station is determined to continue processing the artificial intelligence service request.

[0111] In some embodiments, the determination module 402 is further specifically configured to:

[0112] In the process of processing the artificial intelligence service request, detecting the base station status of the first base station within the preset time period;

[0113] Determine a total occupancy rate of a second resource corresponding to the first base station when processing the artificial intelligence service request in the base station state;

[0114] Detecting whether the total occupancy rate of the second resource by the first base station in the preset time period is greater than or equal to a second resource occupancy threshold

[0115] In some embodiments, the determination module is further specifically configured to:

[0116] If, in the process of processing the artificial intelligence service request, it is detected that the total occupancy rate of the second resource of the first base station within a preset time period is greater than or equal to the second resource occupancy rate threshold, the base station with the lowest resource occupancy rate among the multiple base stations corresponding to the first base station is determined as the second base station.

[0117] In some embodiments, the determination module 402 is further specifically configured to:

[0118] If, during the process of processing the artificial intelligence service request, it is detected that the first base station causes a cell handover of the user terminal within the preset time period, determining a sixth base station to which the user terminal is switched;

[0119] If the total resource occupancy rate when the sixth base station processes the artificial intelligence service request based on the processing information is less than the third resource occupancy rate threshold of the sixth base station, determining the sixth base station as the second base station;

[0120] If the total resource occupancy rate when the sixth base station processes the artificial intelligence service request based on the processing information is greater than or equal to the third resource occupancy rate threshold, then the base station with the lowest resource occupancy rate among the multiple base stations corresponding to the first base station is determined as the second base station.

[0121] The present application also provides an electronic device to execute the above data processing method. Figure 5 It shows a schematic diagram of an electronic device provided by some embodiments of the present application. Figure 5 As shown, the electronic device 7 includes: a processor 700, a memory 701, a bus 702 and a communication interface 703. The processor 700, the communication interface 703 and the memory 701 are connected via the bus 702; the memory 701 stores a computer program that can be run on the processor 700, and when the processor 700 runs the computer program, it executes the data processing method provided in any of the aforementioned embodiments of the present application.

[0122] The memory 701 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the device network element and at least one other network element is realized through at least one communication interface 703 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0123] The bus 702 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 701 is used to store programs, and the processor 700 executes the program after receiving an execution instruction. The data processing method disclosed in any implementation of the aforementioned embodiment of the present application may be applied to the processor 700, or implemented by the processor 700.

[0124] The processor 700 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 700. The above processor 700 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 701, and the processor 700 reads the information in the memory 701 and completes the steps of the above method in combination with its hardware.

[0125] The electronic device provided in the embodiment of the present application and the data processing method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented therein.

[0126] The present application also provides a computer-readable storage medium corresponding to the data processing method provided in the above embodiment. Figure 6 The computer-readable storage medium shown is a CD 30 on which a computer program (ie, a program product) is stored. When the computer program is run by a processor, it executes the data processing method provided by any of the aforementioned embodiments.

[0127] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0128] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the data processing method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0129] It should be noted that:

[0130] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known structures and technologies are not shown in detail so as not to obscure the understanding of this description.

[0131] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0132] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A data processing method, It is characterized in that Applied to a first base station, the first base station is used to receive an artificial intelligence service request sent by a user terminal, including: If the first base station meets the first preset condition for processing the artificial intelligence service request, processing the artificial intelligence service request; If, during the process of processing the artificial intelligence service request, it is detected that the first base station does not meet the second preset condition for processing the artificial intelligence service request within the preset time period, determining a second base station that continues to process the artificial intelligence service request; The processing information and user information of the artificial intelligence service request are sent to the second base station, so that the second base station processes the artificial intelligence service request based on the processing information, and sends the processing result to the user end through the third base station corresponding to the user information.

2. The method according to claim 1, It is characterized in that The method further comprises: If the first base station does not meet the first preset condition, the service information and user information of the artificial intelligence service request are sent to the fourth base station, so that the fourth base station processes the artificial intelligence service request based on the service information and sends it to the user end through the fifth base station corresponding to the user information.

3. The method according to claim 1, It is characterized in that The method further comprises: If the second preset condition is always met during the process of the first base station processing the artificial intelligence service request, a corresponding processing result is obtained; If the first base station maintains a communication connection with the user terminal when the processing result is obtained, the processing result is sent to the user terminal.

4. The method according to claim 1, It is characterized in that If, during the process of processing the artificial intelligence service request, it is detected that the first base station does not meet the second preset condition within the preset time period, determining the second base station that continues to process the artificial intelligence service request includes: In the process of processing the artificial intelligence service request, if it is detected that the total occupancy rate of the second resource of the first base station within the preset time period is greater than or equal to the second resource occupancy rate threshold, it is determined that the first base station does not meet the second preset condition within the preset time period, and the second base station that continues to process the artificial intelligence service request is determined; Alternatively, in the process of processing the artificial intelligence service request, if it is detected that the user terminal performs cell switching within the preset time period, it is determined that the first base station does not meet the second preset condition within the preset time period, and a second base station is determined to continue processing the artificial intelligence service request.

5. The method according to claim 4, It is characterized in that Before detecting that the total occupancy rate of the second resource of the first base station within a preset time period is greater than or equal to a second resource occupancy rate threshold, the method further includes: In the process of processing the artificial intelligence service request, detecting the base station status of the first base station within the preset time period; Determine a total occupancy rate of a second resource corresponding to the first base station when processing the artificial intelligence service request in the base station state; It is detected whether the total occupancy rate of the second resource by the first base station in the preset time period is greater than or equal to a second resource occupancy rate threshold.

6. The method according to any one of claims 1 to 5, It is characterized in that The determining of the second base station that continues to process the artificial intelligence service request includes: If, in the process of processing the artificial intelligence service request, it is detected that the total occupancy rate of the second resource of the first base station within a preset time period is greater than or equal to a second resource occupancy rate threshold, the base station with the lowest resource occupancy rate among the multiple base stations corresponding to the first base station is determined as the second base station.

7. The method according to any one of claims 1 to 5, It is characterized in that The determining of the second base station that continues to process the artificial intelligence service request includes: If, during the process of processing the artificial intelligence service request, it is detected that the first base station causes a cell handover of the user terminal within the preset time period, determining a sixth base station to which the user terminal is switched; If the total resource occupancy rate when the sixth base station processes the artificial intelligence service request based on the processing information is less than the third resource occupancy rate threshold of the sixth base station, determining the sixth base station as the second base station; If the total resource occupancy rate when the sixth base station processes the artificial intelligence service request based on the processing information is greater than or equal to the third resource occupancy rate threshold, then the base station with the lowest resource occupancy rate among the multiple base stations corresponding to the first base station is determined as the second base station.

8. A data processing device, It is characterized in that Applied to a first base station, the first base station is used to receive an artificial intelligence service request sent by a user terminal, including: a processing module, configured to process the artificial intelligence service request if the first base station meets a first preset condition for processing the artificial intelligence service request; a determination module, configured to determine a second base station that continues to process the artificial intelligence service request if it is detected that the first base station does not meet a second preset condition for processing the artificial intelligence service request within a preset time period during the process of processing the artificial intelligence service request; A sending module is used to send processing information and user information of the artificial intelligence service request to the second base station, so that the second base station processes the artificial intelligence service request based on the processing information, and sends the processing result to the user end through a third base station corresponding to the user information.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that The processor runs the computer program to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that The program is executed by a processor to implement the method according to any one of claims 1 to 7.

Images