Data processing method, apparatus, storage medium and electronic device

Abstract

The present application relates to the technical field of data processing. Disclosed are a data processing method, an apparatus, a storage medium and an electronic device. The method comprises: receiving a data processing request triggered by a target, and, by means of a proxy function, determining a data processing task corresponding to the data processing request; by means of the proxy function, determining from amongst a plurality of functions a first target function for processing the data processing task, wherein an artificial intelligence model is deployed in the first target function, and the artificial intelligence model is used for executing the data processing task; and using the artificial intelligence model deployed in the first target function to execute the data processing task, so as to obtain a data processing result. The present application solves the technical problem of low data processing efficiency caused by excessively long time for switching and loading of artificial intelligence models when different artificial intelligence models are required for data processing in the prior art.

Description

[0001] This application claims priority to Chinese patent application number 202410338010.X, filed with the China Patent Office on March 22, 2024, entitled "Data Processing Method and Apparatus, Storage Medium and Electronic Device," the entire contents of which are incorporated herein by reference. Technical Field This application relates to the field of data processing technology, and more specifically, to a data processing method and apparatus, a storage medium, and an electronic device. Background: Serverless computing, a computing model that allows developers to write and deploy code without worrying about the underlying infrastructure, has been widely used in recent years. Its pay-as-you-go billing and the lack of server management have attracted many developers and enterprises. The application of artificial intelligence models, particularly those requiring significant computing resources (such as machine learning models and deep learning), has rapidly developed and been adopted in various fields. These applications typically require significant computing resources and expertise to operate effectively. In serverless architectures, especially when it comes to the application of artificial intelligence models, model switching is a common problem. Because each request may require a different model, a different model needs to be loaded during the request processing process. This model switching is time-consuming, leading to poor performance and increased costs. In serverless systems that charge by time, prolonged model switching can waste resources and incur unnecessary costs. This problem is particularly acute when the model switching time significantly exceeds the actual computation time. Regarding the aforementioned related art problem of low data processing efficiency due to the lengthy switching and loading times required to process data using different artificial intelligence models, no effective solution has yet been proposed. SUMMARY OF THE INVENTION The present invention provides a data processing method and apparatus, a storage medium, and an electronic device to at least address the technical problem of low data processing efficiency due to the lengthy switching and loading times required to process data using different artificial intelligence models. According to one aspect of an embodiment of the present application, a data processing method is provided, including: receiving a data processing request triggered by a target object, and determining a data processing task corresponding to the data processing request through a proxy function; determining a first target function for processing the data processing task from multiple functions through the proxy function, wherein an artificial intelligence model is deployed in the first target function, and the artificial intelligence model is used to execute the data processing task; and executing the data processing task using the artificial intelligence model deployed in the first target function to obtain a data processing result.Furthermore, before receiving a data processing request triggered by a target object, the method further includes: determining multiple artificial intelligence models based on a data processing type; creating multiple functions based on the multiple artificial intelligence models, and deploying an artificial intelligence model from the multiple artificial intelligence models within a function of the multiple functions, wherein the artificial intelligence model and the function have a one-to-one correspondence. Furthermore, determining a first target function for processing the data processing task from the multiple functions using a proxy function includes: parsing the data processing task using the proxy function to obtain a target data processing type corresponding to the data processing task; performing function matching on the target data processing type among the multiple functions using the proxy function to determine the first target function corresponding to the target data processing type. Furthermore, after determining the first target function for processing the data processing task from the multiple functions using the proxy function, the method further includes: performing route matching on the first target function among multiple routes using the proxy function to obtain a matching result; if the matching result indicates the existence of a route matching the first target function, determining the route as the target route; and forwarding the data processing task to the first target function using the target route. Furthermore, using the artificial intelligence model deployed in the first objective function to execute the data processing task and obtain the data processing result includes: creating a target instance corresponding to the data processing task through the first objective function; and invoking the artificial intelligence model deployed in the function through the target instance to execute the data processing task and obtain the data processing result. Furthermore, receiving a data processing request triggered by a target object includes: responding to a target operation triggered by the target object through a first interface and generating a second interface based on the target operation; receiving identity information input by the target object through the second interface, wherein the identity information is used to perform security verification on the target object; and if the security verification indicates that the verification is successful, generating a third interface and receiving the data processing request triggered by the target object through the third interface. Furthermore, after executing the data processing task using the artificial intelligence model deployed in the first objective function and obtaining the data processing result, the method further includes: feeding back the data processing result to the proxy function through the first objective function; integrating and processing the data processing results through the proxy function to obtain a target data processing result; and pushing the target data processing result to the third interface through the proxy function.Furthermore, after using the artificial intelligence model deployed in the first objective function to execute the data processing task and obtaining a data processing result, the method further includes: obtaining performance data of the first objective function and data processing process data of the first objective function, wherein the data processing process data is data information generated by the first objective function during execution of the data processing task; evaluating the first objective function based on the performance data and the data processing process data to obtain an evaluation result; and optimizing the first objective function based on the evaluation result. According to another aspect of an embodiment of the present application, a data processing method is also provided, comprising: receiving an image segmentation processing request triggered by a target object, and determining, via a proxy function, an image segmentation task corresponding to the image segmentation processing request; determining, via the proxy function, a second objective function from multiple functions to process the image segmentation task, wherein the second objective function has an artificial intelligence model deployed therein, the artificial intelligence model being used to execute the image segmentation task; and executing the image segmentation task using the artificial intelligence model deployed in the second objective function to obtain a segmentation result of the image in the image segmentation processing request. According to another aspect of an embodiment of the present application, a data processing method is provided, comprising: receiving a summary generation request triggered by a target object, and determining a summary generation task corresponding to the summary generation request via a proxy function, wherein the summary generation request includes at least text information to be summarized; determining, via the proxy function, a third target function from multiple functions to process the summary generation task, wherein the third target function includes an artificial intelligence model for performing the summary generation task; and executing the summary generation task using the artificial intelligence model deployed in the third target function to obtain summary information of the text information. According to another aspect of an embodiment of the present application, a data processing device is provided, comprising: a receiving unit configured to receive a data processing request triggered by a target object, and determining, via the proxy function, a data processing task corresponding to the data processing request; a first determining unit configured to determine, via the proxy function, a first target function from multiple functions to process the data processing task, wherein the first target function includes an artificial intelligence model for performing the data processing task; and an executing unit configured to execute the data processing task using the artificial intelligence model deployed in the first target function to obtain a data processing result.Furthermore, the apparatus further includes: a second determination unit configured to, before receiving a data processing request triggered by a target object, determine multiple artificial intelligence models based on a data processing type; a deployment unit configured to create multiple functions based on the multiple artificial intelligence models and deploy an artificial intelligence model from the multiple artificial intelligence models within a function of the multiple functions, wherein the artificial intelligence models and the functions have a one-to-one correspondence. Furthermore, the first determination unit includes: a parsing module configured to parse the data processing task using the proxy function to obtain a target data processing type corresponding to the data processing task; and a matching module configured to perform function matching for the target data processing type among the multiple functions using the proxy function to determine the first target function corresponding to the target data processing type. Furthermore, the apparatus further includes: a matching unit configured to, after determining a first target function for processing the data processing task from multiple functions using a proxy function, perform route matching on the first target function among multiple routes using the proxy function to obtain a matching result; a third determination unit configured to, if the matching result indicates the existence of a route matching the first target function, determine the route as the target route; and a forwarding unit configured to forward the data processing task to the first target function via the target route. Furthermore, the execution unit includes: a creation module configured to create a target instance corresponding to the data processing task using the first target function; and an execution module configured to invoke the artificial intelligence model deployed in the function via the target instance to execute the data processing task and obtain the data processing result. Furthermore, the receiving unit includes: a response module, configured to respond to the target operation triggered by the target object through a first interface, and generate a second interface based on the target operation; a receiving module, configured to receive identity information input by the target object through the second interface, wherein the identity information is used to perform security verification on the target object; a generation unit, configured to generate a third interface when the security verification indicates that the verification is passed, and receive the data processing request triggered by the target object through the third interface.Furthermore, the apparatus further includes: a feedback unit configured to, after obtaining a data processing result by executing the data processing task using the artificial intelligence model deployed in the first objective function, feed the data processing result back to the proxy function via the first objective function; an integration unit configured to integrate the data processing results via the proxy function to obtain a target data processing result; and a push unit configured to push the target data processing result to the third interface via the proxy function. Furthermore, the apparatus further includes: an acquisition unit configured to, after obtaining a data processing result by executing the data processing task using the first objective function based on the artificial intelligence model deployed in the first objective function, acquire performance data of the first objective function and data processing process data of the first objective function, wherein the data processing process data is data information generated by the first objective function during the execution of the data processing task; an evaluation unit configured to evaluate the operating status of the first objective function based on the performance data and the data processing process data to obtain an evaluation result; and an optimization unit configured to optimize the first objective function based on the evaluation result. According to another aspect of an embodiment of the present application, a computer-readable storage medium is provided. The storage medium stores a program. When the program is executed, the device containing the storage medium is controlled to execute any of the aforementioned data processing methods. According to another aspect of an embodiment of the present application, an electronic device is provided. The electronic device includes a memory storing an executable program and a processor configured to execute the program. When the program is executed, the data processing method described above is executed. According to another aspect of an embodiment of the present application, a computer program product is provided. The computer program product includes a stored computer program. When the computer program is executed by the processor, the data processing method described above is implemented. In an embodiment of the present application, the following steps are adopted: receiving a data processing request triggered by a target object, and determining a data processing task corresponding to the data processing request through a proxy function; determining a first target function for processing the data processing task from multiple functions through the proxy function, wherein an artificial intelligence model is deployed in the first target function, and the artificial intelligence model is used to execute the data processing task; executing the data processing task using the artificial intelligence model deployed in the first target function to obtain a data processing result, thereby solving the technical problem in the related art of low data processing efficiency due to the long switching and loading time of the artificial intelligence models when data needs to be processed by different artificial intelligence models.In this application, upon receiving a data processing request initiated by a target object, a proxy function determines the data processing task corresponding to the request. The proxy function intelligently analyzes a first target function to process the data processing task. The first target function deploys an artificial intelligence model. Finally, the artificial intelligence model deployed in the first target function executes the data processing task to obtain a data processing result. By creating corresponding functions for artificial intelligence models, model preloading and caching are possible. This improves the response speed and processing efficiency of the artificial intelligence models in application scenarios that require frequent switching between different artificial intelligence models, thereby achieving improved data processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS The drawings described herein are provided to provide a further understanding of this application and constitute a part of this application. The illustrative embodiments of this application and their description are provided for the purpose of explaining this application and are not intended to unduly limit this application. In the accompanying drawings: Figure 1 is a hardware block diagram of a computer terminal provided according to the first embodiment of the present application; Figure 2 is a flow chart of a data processing method provided according to the first embodiment of the present application; Figure 3 is a schematic diagram of a first interface provided according to the first embodiment of the present application; Figure 4 is a schematic diagram of a second interface provided according to the first embodiment of the present application; Figure 5 is a schematic diagram of a third interface provided according to the first embodiment of the present application; Figure 6 is a schematic diagram of a data processing method provided according to the first embodiment of the present application; Figure 7 is a flow chart of a data processing method provided according to the second embodiment of the present application; Figure 8 is a flow chart of a data processing method provided according to the third embodiment of the present application; Figure 9 is a schematic diagram of a data processing device provided according to the fourth embodiment of the present application; and Figure 10 is a structural block diagram of a computer terminal provided according to the fifth embodiment of the present application. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS To help those skilled in the art better understand the present invention, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings. It should be understood that the described embodiments are only a portion of the embodiments of the present application, and not all of them. Based on the embodiments of the present application, all other embodiments derived by persons of ordinary skill in the art without inventive effort shall fall within the scope of protection of the present application. It should be noted that the terms "first," "second," and so on, in the specification and claims of this application and the aforementioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, such that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.Furthermore, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device comprising a series of steps or units need not be limited to the steps or units explicitly listed and may include other steps or units not explicitly listed or inherent to the process, method, product, or device. First, some nouns or terms appearing in the description of the embodiments of this application are subject to the following interpretations: Serverless computing is a cloud computing model based on Platform as a Service (PaaS). Serverless computing provides a micro-architecture where end customers do not need to deploy, configure, or manage server services; all server services required for code execution are provided by the cloud platform. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, storage, and display, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. The collection, use, and processing of the relevant data must comply with the relevant laws, regulations, and standards of the relevant region, and corresponding operation portals are provided for users to choose to authorize or reject. Embodiment 1 According to an embodiment of the present application, a data processing method is also provided. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system, such as a set of computer-executable instructions. Furthermore, although the flowcharts illustrate a logical order, in some cases, the steps shown or described may be executed in a different order than that shown. The method embodiment provided in Embodiment 1 of the present application can be executed in a mobile terminal, a computer terminal, or a similar computing device. FIG1 shows a hardware block diagram of a computer terminal (or mobile device) for implementing the data processing method. As shown in FIG1 , the computer terminal (or mobile device) 10 may include a processor assembly 102 (the processor assembly 102 may include, but is not limited to, a processing device such as a microprocessor (MCU) or a programmable logic device (FPGA), and the processor assembly 102 may include a processor assembly, as shown in FIG1 by 102a, 102b, ..., 102n), a memory 104 for storing data, and a transmission module 106 for communication functions.In addition, the device may also include: a display, an input / output interface (I / O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of a BUS), a network interface, a power supply, and / or a camera. Those skilled in the art will appreciate that the structure shown in FIG1 is merely illustrative and does not limit the structure of the electronic device. For example, the computer terminal 10 may include more or fewer components than shown in FIG1 , or have a configuration different from that shown in FIG1 . It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry." The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be fully or partially integrated into any of the other components of the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuitry functions as a processor control (e.g., selecting a variable resistor terminal path connected to an interface). Memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the data processing method in the embodiments of the present application. Processor 102 executes the software programs and modules stored in memory 104 to execute various functional applications and data processing, thereby implementing the aforementioned data processing method. Memory 104 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory remote from processor 102, which can be connected to computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof. Transmission device 106 is used to receive or transmit data via a network. Specific examples of such networks may include a wireless network provided by the telecommunications provider of computer terminal 10. In one example, transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.The display may be a touch-screen liquid crystal display, which enables a user to interact with the user interface of the computer terminal 10 (or mobile device). In the aforementioned operating environment, the present application provides a data processing method as shown in FIG2 . FIG2 is a flow chart of the data processing method according to Embodiment 1 of the present application. As shown in FIG2 , the data processing method includes: Step S201: receiving a data processing request triggered by a target object, and determining a data processing task corresponding to the data processing request through a proxy function. Optionally, a data processing request triggered by a user (i.e., the aforementioned target object) is received. It should be noted that the data processing request may include data information to be processed. The data processing task corresponding to the data processing request is determined through a proxy function. In an optional embodiment, if the number of currently received data processing requests exceeds a request number threshold, the proxy function is required to add the initial data processing task corresponding to the data processing request to a target queue. It should be noted that the proxy function may be a proxy function, which is responsible for adding the initial data processing tasks corresponding to all received data processing requests to the target queue. It should be noted that during peak traffic periods, the target queue can effectively control the flow of data processing tasks and rationally allocate resources to them. In an optional embodiment, pending data processing tasks can be determined from the initial data processing tasks in the target queue based on their priorities. This specifically includes the following steps: The data information to be processed and the corresponding timestamp information of the initial data processing tasks are obtained. The importance of the initial data processing tasks can be determined based on the data information to be processed, and the triggering order of the initial data processing tasks can be accurately determined based on the timestamp information. Therefore, the multiple initial data processing tasks are prioritized based on the data information to be processed and the timestamp information. Finally, pending data processing tasks are determined from the target queue based on the priorities of the data processing tasks. In an optional embodiment, pending data processing tasks can also be determined based on user (i.e., the aforementioned target object) attributes (e.g., whether the user is a paying user) and their priority. The above steps accurately determine pending data processing tasks, thereby more rationally allocating resources to them. In step S202, a proxy function is used to determine a first target function from multiple functions for processing the data processing task. The first target function includes an artificial intelligence model for executing the data processing task. Optionally, after the initial data processing task is added to the target queue, the current data processing task to be processed can be determined based on the trigger time of the initial data processing task.It should be noted that users can set a strategy for determining pending data processing tasks based on actual needs. For example, a strategy for determining pending data processing tasks can be developed based on the importance of the data processing task and the time it is triggered. It should be noted that an artificial intelligence model is deployed in the first objective function. Different artificial intelligence models are used to perform different data processing tasks, such as image processing or text recognition. The aforementioned first objective function is a Serverless function. Serverless functions are a new computing paradigm that allows developers to build and deploy functional code units, called functions. Serverless functions are typically event-driven, enabling flexible and reliable code execution and automatically scaling computing resources based on demand. These Serverless functions can be deployed and executed as separate functional modules. Deploying artificial intelligence models in Serverless functions can effectively improve AI model loading efficiency. In step S203, the artificial intelligence model deployed in the first objective function is used to execute the data processing task to obtain the data processing results. Optionally, after determining the first objective function, the proxy function sends the corresponding data processing task to the first objective function, which then uses the artificial intelligence model deployed in the first objective function to execute the data processing task and obtain the corresponding data processing result. In summary, upon receiving a data processing request initiated by a target object, the proxy function determines the data processing task corresponding to the request, intelligently analyzes the first objective function for processing the data processing task, which is deployed with the artificial intelligence model, and finally executes the data processing task using the artificial intelligence model deployed in the first objective function to obtain the data processing result. By creating corresponding functions for artificial intelligence models, model preloading and caching can be achieved. This improves the response speed and processing efficiency of artificial intelligence models in application scenarios that require frequent switching between different artificial intelligence models, thereby achieving improved data processing efficiency. In order to improve the efficiency of data processing, in the data processing method provided in the first embodiment of the present application, before receiving the data processing request triggered by the target object, the method also includes: determining multiple artificial intelligence models based on the data processing type; creating multiple functions based on the multiple artificial intelligence models, and deploying the artificial intelligence models among the multiple artificial intelligence models in functions of the multiple functions, wherein the artificial intelligence models and the functions have a one-to-one correspondence.Optionally, before receiving a data processing request, multiple corresponding AI models (e.g., image processing models, natural language models, etc.) are determined based on the data processing types that the current Serverless architecture can handle, such as image data processing or text data processing. A Serverless function is then created for each AI model. The AI ​​model from the multiple AI models is deployed within a function within the multiple functions, with a one-to-one correspondence between the AI ​​model and the function. By encapsulating the AI ​​model in a separate Serverless function, when the Serverless function is triggered, it can immediately begin processing the request without waiting for the AI ​​model to load. Furthermore, the execution of each Serverless function is independent, reducing interference and dependencies between different AI models and improving the stability and reliability of the overall Serverless system. To improve the accuracy of determining the first objective function, in the data processing method provided in Example 1 of the present application, determining the first objective function for processing a data processing task from multiple functions using a proxy function includes: parsing the data processing task using the proxy function to obtain a target data processing type corresponding to the data processing task; and performing function matching on the target data processing type among multiple functions using the proxy function to determine a first objective function corresponding to the target data processing type. Optionally, the following steps are used to determine the first objective function corresponding to the data processing task. After receiving the data processing task, the proxy function can accurately parse the data processing task, determine the target data processing type corresponding to the data processing task, and then determine an appropriate first objective function from multiple functions based on the target data processing type. The proxy function can accurately analyze the first objective function corresponding to the data processing task, thereby improving the execution efficiency of the data processing task. To further improve the execution efficiency of data processing tasks, in the data processing method provided in the first embodiment of the present application, after determining a first target function for processing the data processing task from multiple functions using a proxy function, the method further includes: performing route matching on the first target function in multiple routes using the proxy function to obtain a matching result; if the matching result indicates that a route matching the first target function exists, determining the route as a target route; and forwarding the data processing task to the first target function via the target route. Optionally, after the proxy function analyzes the first target function corresponding to the data processing task, the proxy function performs route matching on the first target function in multiple routes to obtain a matching result; if the matching result indicates that a route matching the first target function exists, forwarding the data processing task to the first target function via the target route.In an optional embodiment, if the matching result indicates that no matching route exists, a route can be determined from multiple routes based on availability to forward the data processing task, and a reminder message can be sent to the user to prompt the user to create a route corresponding to the first target function. Forwarding the corresponding data processing task via the route corresponding to the first target function can improve the forwarding efficiency of the data processing task, thereby improving the execution efficiency of the data processing task. To improve the execution efficiency of the first target function for the data processing task, in the data processing method provided in Example 1 of the present application, executing the data processing task using the artificial intelligence model deployed in the first target function to obtain the data processing result includes: creating a target instance corresponding to the data processing task via the first target function; and having the target instance call the artificial intelligence model deployed in the function to execute the data processing task and obtain the data processing result. Optionally, after receiving the data processing task, the first target function creates a target instance corresponding to the data processing task, and having the target instance call the artificial intelligence model deployed in the function to execute the data processing task and obtain the corresponding data processing result. In summary, the first objective function can create corresponding instances based on the data processing tasks to be processed. Multiple instances can be used to process the data processing tasks in parallel, thereby improving the execution efficiency of the first objective function for the data processing tasks. To improve user convenience and security in the Serverless architecture, the data processing method provided in the first embodiment of the present application includes: responding to a target operation triggered by the target object via a first interface, and generating a second interface based on the target operation; receiving identity information input by the target object via the second interface, where the identity information is used to perform security verification on the target object; and, if the security verification indicates that the verification is successful, generating a third interface, and receiving the data processing request triggered by the target object via the third interface. Optionally, the Serverless architecture includes at least a first interface, a second interface, and a third interface. For example, as shown in FIG3 , the first interface allows a user to trigger a data processing request by clicking a corresponding button on the first interface. After the first interface receives the user's target operation (e.g., a click operation), a second interface is generated to improve data security, such as the second interface shown in FIG4 . The user's identity information is received via the second interface, so that the user can be securely verified using the identity information. It should be noted that security and access control can be ensured through the API gateway. When the user's identity authentication is passed, a third interface is generated, as shown in FIG5 , and a data processing request triggered by the target object is received through the third interface.After receiving data to be processed by the user, i.e., a data processing request, on the third interface, the data processing request is sent to the proxy function so that the proxy function matches a function capable of processing the data processing request. These steps facilitate a user's intuitive understanding of the entire data processing process, improving user convenience and security within the Serverless architecture. To facilitate user access to responsive data processing results, the data processing method provided in the first embodiment of the present application, after executing the data processing task using the artificial intelligence model deployed in the first objective function and obtaining the data processing result, further comprises: feeding the data processing result back to the proxy function via the first objective function; integrating the data processing results via the proxy function to obtain the target data processing result; and pushing the target data processing result to the third interface via the proxy function. Optionally, after completing the data processing task, the first objective function feeds the data processing result back to the proxy function so that the proxy function can push the data processing result to the third interface, allowing the user to quickly access the data processing result. In an optional embodiment, the proxy function can integrate or further process multiple results from different serverless functions and then push the processed results to the third interface. To improve the stability of data processing for the first objective function, in the data processing method provided in Example 1 of the present application, after the first objective function executes a data processing task based on the artificial intelligence model deployed in the first objective function and obtains the data processing results, the method further includes: obtaining performance data and data processing process data of the first objective function, where the data processing process data is data information generated by the first objective function during the execution of the data processing task; evaluating the operating status of the first objective function based on the performance data and data processing process data to obtain an evaluation result; and optimizing the first objective function based on the evaluation result. Optionally, the process of the first objective function executing the data processing task can be tracked in real time to obtain performance data of the first objective function, such as response time, success rate, etc. The detailed processing flow of the data processing task can also be tracked to obtain data processing process data. The performance data and data processing process data of the first objective function are crucial for fault diagnosis, system optimization, and future improvements. The operating status of the first objective function is evaluated using performance data and data processing process data, and the first objective function is optimized based on the evaluation results. For example, if the evaluation results show that the response time of the first objective function is slow and the data processing success rate is low, the response time of the first objective function is optimized based on the evaluation results.The above steps provide real-time insights into function performance and overall system status, enhancing system maintainability and reliability and making problem diagnosis and resolution more efficient. In an optional embodiment, data processing can be implemented using the schematic diagram shown in Figure 6: 1. Receive Request: An external request enters the system through the API gateway and first reaches the Proxy function. At this point, the Proxy function performs preliminary analysis to identify the data request processing type and the required AI model. At this stage, necessary security checks and identity verification are also performed to ensure that only authorized external requests are processed.

[0002] 2. Request Analysis and Forwarding: Based on the initial analysis, the Proxy function determines which model-specific ServerIss function to forward the request to. The Proxy function uses its built-in routing logic to direct the request to the appropriate function. This process involves determining which functions are available and which have preloaded the required model.

[0003] 3. Model Processing: Because the Serverless function has already preloaded and cached the corresponding AI model, it can immediately begin processing the request. The function uses its AI model to process the input data, performing the required calculations and analysis. Once processing is complete, the results are packaged and ready for return.

[0004] 4. Result Return: The processed results are sent back to the Proxy function. If necessary, the Proxy function can consolidate or further process multiple results from different Serverless functions. Ultimately, the processed results are returned to the user or the client or interface that initiated the request through the API gateway.

[0005] 5. Logging and Monitoring: The system tracks key performance indicators (KPIs) during processing, such as response time and success rate, in real time. The detailed processing flow and results of each request are recorded in the log. Logs and performance data are crucial for troubleshooting, system optimization, and future improvements.

[0006] 6. Queue Management: When request volumes are high, proxy functions utilize queues to control request flow, ensuring the system doesn't crash due to overload. Based on predefined rules or real-time analysis, the system can adjust request priorities within the queue. This application encapsulates AI models within independent Serverless functions and utilizes proxy functions for intelligent routing and load management, providing an efficient and flexible solution. Compared to traditional Serverless deployments, this application reduces model switching time, minimizes computing resource waste, and thus reduces operating costs. This makes the deployment and operation of AI applications more cost-effective. Through intelligent routing and queue management, this application provides excellent system scalability. It can flexibly handle loads of varying sizes and types while maintaining system stability and reliability. The integrated logging and monitoring system facilitates maintenance and monitoring of the entire Serverless architecture. By collecting detailed performance data and log information, system administrators can effectively understand system status and quickly identify and resolve issues. In the data processing method provided in Example 1 of the present application, a data processing request triggered by a target object is received, and a proxy function is used to determine the data processing task corresponding to the data processing request. The proxy function then determines a first target function from multiple functions to process the data processing task, wherein the first target function includes an artificial intelligence model for executing the data processing task. The artificial intelligence model deployed in the first target function is then used to execute the data processing task to obtain a data processing result. This method solves the technical problem in related arts of low data processing efficiency due to the lengthy switching and loading time of artificial intelligence models when processing data using different artificial intelligence models. In the present application, upon receiving a data processing request initiated by a target object, the proxy function determines the data processing task corresponding to the request, intelligently analyzes the first target function to process the data processing task, wherein the first target function includes an artificial intelligence model. Finally, the artificial intelligence model deployed in the first target function executes the data processing task to obtain a data processing result. By creating corresponding functions for artificial intelligence models, model preloading and caching can be achieved. This improves the response speed and processing efficiency of artificial intelligence models in application scenarios that require frequent switching between different artificial intelligence models, thereby achieving the effect of improving data processing efficiency.It should be noted that, for simplicity of description, the aforementioned method embodiments are described as a series of combined actions. However, those skilled in the art should be aware that this application is not limited by the order of the actions described, as certain steps may be performed in a different order or simultaneously. Furthermore, those skilled in the art should also be aware that the embodiments described in this specification are preferred embodiments, and the actions and modules involved are not necessarily required for this application. Through the above description of the embodiments, those skilled in the art will clearly understand that the methods according to the aforementioned embodiments can be implemented using software plus a required general-purpose hardware platform. Hardware can also be used, but in many cases the former is the preferred implementation. Based on this understanding, the technical solution of this application, or the portion 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 (e.g., ROM / RAM, a magnetic disk, or an optical disk) and includes instructions for enabling a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of the various embodiments of this application. Example 2 According to an embodiment of the present application, a data processing method is also provided. As shown in FIG7 , the data processing method includes: Step S701: receiving an image segmentation processing request triggered by a target object, and determining, through a proxy function, an image segmentation task corresponding to the image segmentation processing request; Step S702: determining, through the proxy function, a second objective function for processing the image segmentation task from multiple functions, wherein the second objective function includes an artificial intelligence model for performing the image segmentation task; Step S703: executing the image segmentation task using the artificial intelligence model deployed in the second objective function to obtain a segmentation result for the image in the image segmentation processing request. It should be noted that the specific method for processing the image segmentation processing request is the same as that in Example 1 and will not be further described here. It should be noted that, for simplicity of description, the aforementioned method embodiments are described as a series of actions. However, those skilled in the art should understand that the present application is not limited to the order of the actions described, as certain steps may be performed in a different order or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are preferred embodiments, and the actions and modules involved are not necessarily required for this application. Through the above description of the embodiments, those skilled in the art will clearly understand that the methods according to the above embodiments can be implemented using software plus a required general-purpose hardware platform. Of course, hardware can also be used, but in many cases the former is a more preferred implementation method.Based on this understanding, the technical solution of this application, or the portion that contributes to the prior art, can essentially be embodied in the form of a software product. This computer software product is stored in a storage medium (e.g., ROM / RAM, a magnetic disk, or an optical disk) and includes instructions for enabling a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of various embodiments of this application. Example 3 According to an embodiment of this application, a data processing method is also provided. As shown in FIG8 , this data processing method includes: Step S801: receiving a summary generation request triggered by a target object, and determining a summary generation task corresponding to the summary generation request through a proxy function, wherein the summary generation request includes at least text information to be summarized; Step S802: determining, through the proxy function, a third target function from multiple functions to process the summary generation task, wherein the third target function includes an artificial intelligence model for executing the summary generation task; Step S803: executing the summary generation task using the artificial intelligence model deployed in the third target function to obtain summary information of the text information. It should be noted that the specific method for processing a summary generation request is the same as that in Example 1 and will not be elaborated upon here. It should be noted that, for simplicity of description, the aforementioned method embodiments are presented as a series of actions. However, those skilled in the art should be aware that this application is not limited by the order of the actions described, as certain steps may be performed in a different order or simultaneously. Furthermore, those skilled in the art should also be aware that the embodiments described in this specification are preferred embodiments, and the actions and modules involved are not necessarily required for this application. Through the above description of the embodiments, those skilled in the art will clearly understand that the methods according to the aforementioned embodiments can be implemented using software plus a required general-purpose hardware platform. Hardware can also be used, but in many cases the former is the preferred implementation. Based on this understanding, the technical solution of this application, or the portion 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 (e.g., ROM / RAM, a magnetic disk, or an optical disk) and includes instructions for enabling a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of the various embodiments of this application. Example 4 According to an embodiment of the present application, a data processing device for implementing the above data processing method is further provided. As shown in FIG9 , the device includes: a receiving unit 901, a first determining unit 902, and an executing unit 903.A receiving unit 901 is configured to receive a data processing request triggered by a target object, and determine a data processing task corresponding to the data processing request through a proxy function; a first determining unit 902 is configured to determine a first target function for processing the data processing task from multiple functions through a proxy function, wherein an artificial intelligence model is deployed in the first target function, and the artificial intelligence model is used to execute the data processing task; an executing unit 903 is configured to use the artificial intelligence model deployed in the first target function to execute the data processing task and obtain a data processing result. In the data processing device provided in Example 2 of the present application, a receiving unit 901 receives a data processing request triggered by a target object and determines the data processing task corresponding to the data processing request through a proxy function. A first determining unit 902 uses the proxy function to determine a first target function from multiple functions to process the data processing task. The first target function includes an artificial intelligence model for executing the data processing task. An executing unit 903 uses the artificial intelligence model deployed in the first target function to execute the data processing task and obtain a data processing result. This solves the technical problem in related arts of low data processing efficiency due to the lengthy switching and loading time of artificial intelligence models when processing data using different artificial intelligence models. In the present application, upon receiving a data processing request initiated by a target object, the proxy function determines the data processing task corresponding to the data processing request, intelligently analyzes the first target function for processing the data processing task, which includes an artificial intelligence model. Finally, the artificial intelligence model deployed in the first target function executes the data processing task and obtains a data processing result. By creating corresponding functions for AI models, model preloading and caching can be achieved. This improves the response speed and processing efficiency of AI models in application scenarios that require frequent switching between different AI models, thereby increasing data processing efficiency. Optionally, the data processing device provided in Example 2 of the present application further includes: a second determination unit configured to determine, before receiving a data processing request triggered by a target object, multiple AI models based on the data processing type; and a deployment unit configured to create multiple functions based on the multiple AI models and deploy the AI ​​models from the multiple AI models within a function of the multiple functions, wherein there is a one-to-one correspondence between the AI ​​models and the functions.Optionally, in the data processing device provided in the second embodiment of the present application, the first determination unit 902 includes: a parsing module configured to parse the data processing task using a proxy function to obtain a target data processing type corresponding to the data processing task; a matching module configured to perform function matching on the target data processing type among multiple functions using the proxy function to determine a first target function corresponding to the target data processing type. Optionally, in the data processing device provided in the second embodiment of the present application, the device further includes: a matching unit configured to, after determining a first target function for processing the data processing task from the multiple functions using the proxy function, perform route matching on the first target function among multiple routes using the proxy function to obtain a matching result; a third determination unit configured to determine the route as the target route if the matching result indicates that a route matching the first target function exists; and a forwarding unit configured to forward the data processing task to the first target function via the target route. Optionally, in the data processing device provided in the second embodiment of the present application, the execution unit 903 includes: a creation module configured to create a target instance corresponding to the data processing task using a first target function; an execution module configured to invoke the artificial intelligence model deployed in the function via the target instance to execute the data processing task and obtain a data processing result. Optionally, in the data processing device provided in the second embodiment of the present application, the receiving unit includes: a response module configured to respond to a target operation triggered by a target object via a first interface and generate a second interface based on the target operation; a receiving module configured to receive identity information input by the target object via the second interface, wherein the identity information is used to perform security verification on the target object; and a generation unit configured to generate a third interface if the security verification indicates that the verification is successful, and receive a data processing request triggered by the target object via the third interface. Optionally, in the data processing device provided in Example 2 of the present application, the device further includes: a feedback unit, configured to perform a data processing task using the artificial intelligence model deployed in the first objective function, and after obtaining the data processing result, feed back the data processing result to the proxy function through the first objective function; an integration unit, configured to integrate the data processing result through the proxy function to obtain a target data processing result; and a push unit, configured to push the target data processing result to the third interface through the proxy function.Optionally, in the data processing device provided in Example 2 of the present application, the device further includes: an acquisition unit configured to, after obtaining a data processing result by executing a data processing task using a first objective function based on an artificial intelligence model deployed in the first objective function, acquire performance data of the first objective function and data processing process data of the first objective function, wherein the data processing process data is data information generated by the first objective function during the execution of the data processing task; an evaluation unit configured to evaluate the operating status of the first objective function based on the performance data and the data processing process data to obtain an evaluation result; and an optimization unit configured to optimize the first objective function based on the evaluation result. It should be noted that the receiving unit 901, first determination unit 902, and execution unit 903 described above correspond to steps S201 to S203 in Example 1. The examples and application scenarios implemented by these three units and the corresponding steps are the same, but are not limited to the contents disclosed in Example 1. It should be noted that the above modules, as part of the device, can be executed in the computer terminal 10 provided in Example 1. It should be noted that the preferred implementation schemes involved in the above embodiments of this application are the same as the solution, application scenarios, and implementation processes provided in Example 1, but are not limited to the solution provided in Example 1. Example 5 The embodiments of this application may provide a computer terminal, which may be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal may be replaced with a terminal device such as a mobile terminal. Optionally, in this embodiment, the computer terminal may be located in at least one of multiple network devices in a computer network. In this embodiment, the computer terminal may execute the aforementioned data processing method. Optionally, Figure 10 is a block diagram of the structure of a computer terminal according to an embodiment of this application. As shown in Figure 10 , the computer terminal 10 may include one or more (only one is shown in Figure 10 ) processors 102 and a memory 104. oThe computer terminal 10 may further include a storage controller for controlling and managing the memory 104. The computer terminal 10 may also include a peripheral interface for connecting to a radio frequency module, an audio module, and a display screen. The memory may be used to store software programs and modules, such as the program instructions / modules corresponding to the data processing methods and apparatuses described in the embodiments of the present application. The processor executes the software programs and modules stored in the memory to perform various functional applications and data processing, thereby implementing the aforementioned data processing methods. The memory may include high-speed random access memory (RAM) and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some embodiments, the memory may further include memory remote from the processor, which may be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof. The processor may access information and applications stored in the memory via a transmission device to execute the aforementioned data processing methods. Those skilled in the art will appreciate that the structure shown in FIG10 is merely illustrative, and the computer terminal may also be a smartphone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile internet device (MID), a PAD, or other terminal device. FIG10 does not limit the structure of the aforementioned electronic devices. For example, the computer terminal 10 may include more or fewer components (such as a network interface, a display device, etc.) than those shown in FIG10 , or may have a configuration different from that shown in FIG10 . Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by a program instructing the hardware associated with the terminal device. The program may be stored in a computer-readable storage medium, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk. Example 6 The embodiments of the present application also provide a computer-readable storage medium. Optionally, in this embodiment, the storage medium may be used to store the program code executed by the data processing method provided in Example 1 above. Optionally, in this embodiment, the storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.Optionally, in this embodiment, the storage medium is configured to store program code for executing the aforementioned data processing method. The serial numbers of the embodiments of this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. In the embodiments of this application, the descriptions of each embodiment have their own specific focus. For portions not described in detail in a particular embodiment, reference should be made to the relevant descriptions of other embodiments. In the several embodiments provided herein, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is merely a logical functional division. In actual implementation, other divisions may be employed. For example, multiple units or components may be combined or integrated into another system, or some features may be omitted or not implemented. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through interfaces, or indirect coupling or communication connection between units or modules, which may be electrical or otherwise. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in a single location or distributed across multiple network units. Some or all of these units may be selected based on actual needs to achieve the objectives of the present embodiment. Furthermore, the functional units in the various embodiments of the present application may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. These integrated units may be implemented in hardware or as software functional units. If these integrated units are implemented as software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the portion that contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk or optical disk and other media that can store program code.The above is merely a preferred embodiment of the present application. It should be noted that those skilled in the art could make several improvements and modifications without departing from the principles of the present application, and such improvements and modifications should also be considered within the scope of protection of the present application. Industrial Applicability: The data processing method provided in the embodiments of this application provides an efficient and flexible solution by encapsulating AI models in independent Serverless functions and utilizing proxy functions for intelligent routing and load management. Compared to traditional Serverless deployments, this application reduces model switching time, reduces computing resource waste, and thus reduces operating costs. This makes the deployment and operation of AI applications more economical and efficient. Through intelligent routing and queue management, this application provides excellent system scalability. It can flexibly handle loads of varying sizes and types while maintaining system stability and reliability. The integrated logging and monitoring system facilitates maintenance and monitoring of the entire Serverless architecture. By collecting detailed performance data and log information, system administrators can effectively understand system status and quickly locate and resolve problems.

Claims

Claims 1. A data processing method, comprising: Receive a data processing request triggered by a target object, and determine a data processing task corresponding to the data processing request through a proxy function; A first objective function for processing the data processing task is determined from multiple functions through a proxy function, wherein an artificial intelligence model is deployed in the first objective function, and the artificial intelligence model is used to perform the data processing task; the data processing task is performed using the artificial intelligence model deployed in the first objective function to obtain a data processing result.

2. The method according to claim 1, wherein: Before receiving a data processing request triggered by a target object, the method further includes: determining multiple artificial intelligence models based on a data processing type; creating multiple functions based on the multiple artificial intelligence models, and deploying an artificial intelligence model from the multiple artificial intelligence models in a function of the multiple functions, wherein the artificial intelligence model and the function have a one-to-one correspondence.

3. The method according to claim 1, wherein: Determining the first target function for processing the data processing task from multiple functions through a proxy function includes: parsing the data processing task through the proxy function to obtain a target data processing type corresponding to the data processing task; performing function matching on the target data processing type among the multiple functions through the proxy function to determine the first target function corresponding to the target data processing type.

4. The method according to claim 3, wherein: After determining, by the proxy function, a first target function for processing the data processing task from a plurality of functions, the method further includes: performing route matching on the first target function among a plurality of routes by the proxy function to obtain a matching result; if the matching result indicates that a route matching the first target function exists, determining the route as a target route; The data processing task is forwarded to the first target function through the target routing.

5. The method according to claim 1, wherein: Using the artificial intelligence model deployed in the first objective function to perform the data processing task and obtain the data processing result includes: creating a target instance corresponding to the data processing task through the first objective function; and calling the artificial intelligence model deployed in the function through the target instance to perform the data processing task and obtain the data processing result.

6. The method according to claim 1, wherein: Receiving a data processing request triggered by a target object includes: responding to a target operation triggered by the target object through a first interface, and generating a second interface based on the target operation; receiving identity information input by the target object through the second interface, wherein the identity information is used to perform security verification on the target object; generating a third interface when the security verification indicates that the verification is passed, and receiving the data processing request triggered by the target object through the third interface.

7. The method according to claim 6, wherein: After the data processing task is performed using the artificial intelligence model deployed in the first objective function to obtain a data processing result, the method further includes: feeding back the data processing result to the proxy function through the first objective function; integrating the data processing result through the proxy function to obtain a target data processing result; and pushing the target data processing result to the third interface through the proxy function.

8. The method according to claim 1, wherein: After the artificial intelligence model deployed in the first objective function is used to execute the data processing task and obtain the data processing result, the method further includes: obtaining performance data of the first objective function and data processing process data of the first objective function, wherein the data processing process data is data information generated by the first objective function in the process of executing the data processing task; evaluating the operating status of the first objective function based on the performance data and the data processing process data to obtain an evaluation result; and optimizing the first objective function based on the evaluation result.

9. A data processing method, comprising: Receive an image segmentation processing request triggered by a target object, and determine an image segmentation task corresponding to the image segmentation processing request through a proxy function; Determining, by a proxy function, a second objective function for processing the image segmentation task from a plurality of functions, wherein an artificial intelligence model is deployed in the second objective function, and the artificial intelligence model is used to perform the image segmentation task; The artificial intelligence model deployed in the second objective function is used to perform the image segmentation task to obtain a segmentation result of the image in the image segmentation processing request.

10. A data processing method, comprising: A summary generation request triggered by a target object is received, and a summary generation task corresponding to the summary generation request is determined through a proxy function, wherein the summary generation request includes at least text information for which summary information is to be generated; a third target function is determined through the proxy function from a plurality of functions to process the summary generation task, wherein an artificial intelligence model is deployed in the third target function, and the artificial intelligence model is used to execute the summary generation task; and the summary generation task is executed using the artificial intelligence model deployed in the third target function to obtain summary information of the text information.

11. A data processing device, comprising: a receiving unit configured to receive a data processing request triggered by a target object, and determine a data processing task corresponding to the data processing request through a proxy function; A first determination unit is configured to determine a first objective function for processing the data processing task from multiple functions through a proxy function, wherein an artificial intelligence model is deployed in the first objective function, and the artificial intelligence model is used to execute the data processing task; and an execution unit is configured to use the artificial intelligence model deployed in the first objective function to execute the data processing task and obtain a data processing result.

12. A computer-readable storage medium comprising a stored program, wherein: When the program is running, the device where the storage medium is located is controlled to execute the data processing method according to any one of claims 1 to 10.

13. An electronic device, comprising: A memory storing an executable program; A processor is configured to run the program, wherein the program executes the data processing method according to any one of claims 1 to 10 when running.

14. A computer program product, comprising a stored computer program, wherein when the computer program is executed by a processor, the computer program implements the data processing method according to any one of claims 1 to 10. 22

Images