Data processing method and device, storage medium and electronic equipment

Abstract

The invention discloses a data processing method and device, a storage medium and electronic equipment. The method relates to the technical field of data processing, and comprises the following steps: receiving a data processing request initiated by a target object through a server-free architecture; triggering a target function according to the data processing request, and loading a first artificial intelligence model and a first dependency library required by the first artificial intelligence application into the server-free architecture through the target function; and processing the to-be-processed data information based on the first artificial intelligence model and the first dependency library through the first artificial intelligence application to obtain a data processing result. According to the data processing method and device, the technical problem that when data processing is executed based on the AI application, due to the fact that the data size of the whole AI application code package is large, the loading time is too long, and then the data processing efficiency is low in the related technology is solved.

Description

Technical Field

[0001] The present application relates to the field of data information processing technology, and in particular to a data processing method and device, a storage medium, and an electronic device. Background Art

[0002] Serverless computing is a cloud computing execution model in which the cloud provider manages machine operations, while customers only provide the code to run. This architecture is favored by businesses and developers for its cost-efficiency and simplified operations management. The serverless model allows users to focus on code development without worrying about underlying hardware and operations. With the rapid development of artificial intelligence (AI) technology, AI (artificial intelligence) applications have become an integral part of various industries. These applications cover a wide range of fields, from natural language processing to image recognition. The development and deployment of AI applications has become a hot topic in current technological innovation. While the serverless architecture provides convenience for developers, when deploying large-scale AI applications with complex dependencies, the increased code package size caused by large dependencies and models increases the cold start time of AI applications, which seriously affects data processing efficiency.

[0003] Regarding the problem in the above-mentioned related technologies that when performing data processing based on AI applications, the loading time is too long due to the large amount of data in the entire AI application code package, which leads to relatively low data processing efficiency, no effective solution has been proposed yet. Summary of the Invention

[0004] The embodiments of the present application provide a data processing method and apparatus, a storage medium, and an electronic device to at least address the technical problem in the related art that, when performing data processing based on AI applications, the loading time is too long due to the large amount of data in the entire AI application code package, thereby resulting in relatively low data processing efficiency.

[0005] According to one aspect of an embodiment of the present application, a data processing method is provided, including: receiving a data processing request initiated by a target object through a serverless architecture, wherein the data processing request needs to be processed by a first artificial intelligence application, the data processing request includes at least data information to be processed, and a first image of the operating environment of the first artificial intelligence application is deployed in the serverless architecture; triggering a target function according to the data processing request, and loading a first artificial intelligence model and a first dependent library required by the first artificial intelligence application into the serverless architecture through the target function, wherein the target function is deployed in the serverless architecture; processing the data information to be processed based on the first artificial intelligence model and the first dependent library by the first artificial intelligence application to obtain a data processing result.

[0006] Furthermore, the data information to be processed is processed by the first artificial intelligence application based on the first artificial intelligence model and the first dependent library to obtain the data processing result, including: obtaining the first business logic code corresponding to the first artificial intelligence application; processing the data information to be processed by the first artificial intelligence model, the first dependent library and the first business logic code to obtain the data processing result.

[0007] Furthermore, loading the first artificial intelligence model and the first dependent library required by the first artificial intelligence application into the serverless architecture through the objective function includes: obtaining a first configuration file corresponding to the first artificial intelligence application, wherein the first configuration file includes at least the first storage address of the first artificial intelligence model and the identifier of the first public component storing the first dependent library, wherein the first public component is a basic component in the serverless architecture; determining the first storage address of the first artificial intelligence model and the identifier of the first public component based on the first configuration file; loading the first artificial intelligence model from the first storage address into the serverless architecture through the objective function; and loading the first dependent library from the first public component into the serverless architecture through the objective function based on the identifier of the first public component.

[0008] Furthermore, before receiving a data processing request initiated by a target object through a serverless architecture, the method also includes: obtaining the target object's demand information for a second artificial intelligence application; determining, based on the demand information, a second image, a second artificial intelligence model, and a second dependent library of the operating environment required for the second artificial intelligence application; constructing the business logic code of the second artificial intelligence application based on the demand information; and deploying the second artificial intelligence application in the serverless architecture based on the second image, the second artificial intelligence model, the second dependent library, and the business logic code.

[0009] Furthermore, based on the second image, the second artificial intelligence model, the second dependent library and the business logic code, deploying the second artificial intelligence application in the serverless architecture includes: storing the second artificial intelligence model in the target device to obtain a second storage address; creating a second public component in the serverless architecture based on the second dependent library, and storing the second dependent library in the second public component; obtaining a second configuration file of the second artificial intelligence application based on the second storage address and the identifier of the second public component; deploying the second image, the second configuration file and the business logic code in the serverless architecture to realize the deployment of the second artificial intelligence application in the serverless architecture.

[0010] Furthermore, loading the first artificial intelligence model into the serverless architecture from the first storage address through the target function includes: initiating an acquisition request for the first artificial intelligence model to the first device through the target function, wherein the first device is a device storing the first artificial intelligence model, and the acquisition request includes at least the identification information of the target function, and judging by the first device whether the identification information of the target function is in a preset list, and the preset list includes the identification information of the function allowed to load the first artificial intelligence model; if the identification information of the target function is in the preset list, then loading the first artificial intelligence model into the serverless architecture from the first storage address through the target function.

[0011] Furthermore, after the data information to be processed is processed by the first artificial intelligence model and the first dependent library to obtain the data processing result, the method also includes: obtaining the target data information generated by the first artificial intelligence model in the process of processing the data information to be processed; evaluating the first artificial intelligence model based on the target data information to obtain an evaluation result; and optimizing the first artificial intelligence model based on the evaluation result.

[0012] According to another aspect of an embodiment of the present application, a data processing device is also provided, including: a receiving unit, configured to receive a data processing request initiated by a target object through a serverless architecture, wherein the data processing request needs to be processed by a first artificial intelligence application, and the data processing request includes at least data information to be processed, and a first image of the operating environment of the first artificial intelligence application is deployed in the serverless architecture; a triggering unit, configured to trigger a target function according to the data processing request, and load a first artificial intelligence model and a first dependent library required by the first artificial intelligence application into the serverless architecture through the target function, wherein the target function is deployed in the serverless architecture; a processing unit, configured to process the data information to be processed based on the first artificial intelligence model and the first dependent library through the first artificial intelligence application to obtain a data processing result.

[0013] Furthermore, the processing unit includes: a first acquisition module, used to obtain a first business logic code corresponding to the first artificial intelligence application; a processing module, used to process the data information to be processed through a first artificial intelligence model, the first dependency library and the first business logic code to obtain the data processing result.

[0014] Furthermore, the triggering unit includes: a second acquisition module, used to obtain a first configuration file corresponding to the first artificial intelligence application, wherein the first configuration file includes at least the first storage address of the first artificial intelligence model and the identifier of the first common component storing the first dependency library, wherein the first common component is a basic component in the serverless architecture; a first determination module, used to determine the first storage address of the first artificial intelligence model and the identifier of the first common component based on the first configuration file; a first loading module, used to load the first artificial intelligence model into the serverless architecture from the first storage address through the target function; a second loading module, used to load the first dependency library into the serverless architecture from the first common component through the target function based on the identifier of the first common component.

[0015] Furthermore, the device also includes: a first acquisition unit, used to obtain the target object's demand information for the second artificial intelligence application before receiving a data processing request initiated by the target object through the serverless architecture; a determination unit, used to determine the second image, second artificial intelligence model and second dependent library of the operating environment required by the second artificial intelligence application based on the demand information; a construction unit, used to construct the business logic code of the second artificial intelligence application based on the demand information; and a deployment unit, used to deploy the second artificial intelligence application in the serverless architecture based on the second image, second artificial intelligence model, second dependent library and the business logic code.

[0016] Furthermore, the deployment unit includes: a storage module for storing the second artificial intelligence model in the target device to obtain a second storage address; a construction module for creating a second common component in the serverless architecture based on the second dependent library, and storing the second dependent library in the second common component; a second determination module for obtaining a second configuration file of the second artificial intelligence application based on the second storage address and the identifier of the second common component; a deployment module for deploying the second image, the second configuration file and the business logic code in the serverless architecture to realize the deployment of the second artificial intelligence application in the serverless architecture.

[0017] Furthermore, the first loading module includes: an acquisition submodule, used to initiate an acquisition request for the first artificial intelligence model to the first device through the target function, wherein the first device is a device storing the first artificial intelligence model, and the acquisition request includes at least the identification information of the target function, and the first device is used to determine whether the identification information of the target function is in a preset list, and the preset list includes the identification information of the function allowed to load the first artificial intelligence model; a recording submodule, used to load the first artificial intelligence model into the serverless architecture from the first storage address through the target function if the identification information of the target function is in the preset list.

[0018] Furthermore, the device also includes: a second acquisition unit, which is used to obtain target data information generated by the first artificial intelligence model in the process of processing the data information to be processed after processing the data information to be processed through the first artificial intelligence model and the first dependent library to obtain the data processing result; an evaluation unit, which is used to evaluate the first artificial intelligence model based on the target data information to obtain an evaluation result; and an optimization unit, which is used to optimize the first artificial intelligence model based on the evaluation result.

[0019] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, which stores a program. When the program is executed, the device where the storage medium is located is controlled to execute any one of the above-mentioned data processing methods.

[0020] According to another aspect of an embodiment of the present invention, an electronic device is provided, including a memory storing an executable program; and a processor for running the program, wherein the program executes any one of the above-mentioned data processing methods when running.

[0021] According to another aspect of an embodiment of the present invention, a computer program product is further provided. The computer program product includes a stored computer program. When the computer program is executed by a processor, the data processing method described in any one of the above items is implemented.

[0022] In an embodiment of the present application, the following steps are adopted: receiving a data processing request initiated by a target object through a serverless architecture, wherein the data processing request needs to be processed by a first artificial intelligence application, the data processing request includes at least data information to be processed, and a first image of the operating environment of the first artificial intelligence application is deployed in the serverless architecture; triggering a target function according to the data processing request, and loading the first artificial intelligence model and the first dependent library required by the first artificial intelligence application into the serverless architecture through the target function, wherein the target function is deployed in the serverless architecture; processing the data information to be processed based on the first artificial intelligence model and the first dependent library by the first artificial intelligence application to obtain a data processing result, thereby solving the technical problem in the related art that when performing data processing based on an AI application, the loading time is too long due to the large amount of data in the entire AI application code package, which leads to relatively low efficiency of data processing. In this solution, the first image of the operating environment of the first artificial intelligence application is directly deployed in the serverless architecture. Then, after the serverless architecture receives a data processing request initiated by the target object, the target function is triggered due to the data processing request. After the target function is triggered, the target function simultaneously loads the first artificial intelligence model and the first dependent library required by the first artificial intelligence application into the serverless architecture. Finally, the first artificial intelligence application uses the first artificial intelligence model and the first dependent library to implement the processing of the data information to be processed. By splitting the code package of the artificial intelligence application into the image of the operating environment, the required artificial intelligence model and the dependent library required at runtime, and then deploying the image of the operating environment in the serverless architecture, the artificial intelligence model and the dependent library are simultaneously loaded into the serverless architecture through the function when the data processing request is received, thereby avoiding the problem of loading time caused by loading the entire AI application code package in the existing technology, thereby achieving the effect of improving data processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0024] Figure 1 This is a hardware structure block diagram of a computer terminal provided according to the first embodiment of the present application;

[0025] Figure 2 This is the process of the data processing method provided in Example 1 of this application Figure 1 ;

[0026] Figure 3 This is the process of the data processing method provided in Example 1 of this application Figure 2 ;

[0027] Figure 4 is a schematic diagram of a data processing device provided according to Embodiment 2 of the present application;

[0028] Figure 5 is a schematic diagram of a data processing system provided according to Embodiment 3 of the present application;

[0029] Figure 6 This is a structural block diagram of a computer terminal provided according to Example 4 of the present application. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] First, some nouns or terms that appear in the description of the embodiments of the present application are subject to the following interpretations:

[0033] Serverless: It is a cloud computing model based on Platform as a Service (Paas). Serverless computing provides a micro-architecture. End customers do not need to deploy, configure or manage server services. The server services required for code execution are all provided by the cloud platform.

[0034] A dependency library is a file containing program code and data that can be used by other programs or components. The code in a dependency library can be shared between multiple programs, thus avoiding the problem of duplicate code writing.

[0035] 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, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0036] Example 1

[0037] 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 flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0038] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG1 shows a hardware structure block diagram of a computer terminal (or mobile device) for implementing a data processing method. Figure 1 As shown, the computer terminal (or mobile device) 10 may include a processor set 102 (the processor set 102 may include but is not limited to a processing device such as a microprocessor (Microcontroller Unit, referred to as MCU) or a programmable logic device (Field Programmer Gate Array, referred to as FPGA), and the processor set 102 may include a processor set, Figure 1 102a, 102b, ..., 102n are used to illustrate), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a Universal Serial Bus (USB) port (which can be included as one of the ports of the BUS), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0039] 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. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part 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 serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0040] The 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 embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the above-mentioned data processing method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0041] The transmission device 106 is used to receive or send data via a network. A specific example of the network may include a wireless network provided by the communications provider of the computer terminal 10. In one embodiment, the 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 another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0042] The display may be a touch screen liquid crystal display that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0043] Under the above operating environment, this application provides Figure 2 The data processing method shown. Figure 2 This is the process of the data processing method according to the first embodiment of the present application Figure 1 The data processing method includes:

[0044] Step S201: receiving a data processing request initiated by a target object through a serverless architecture, wherein the data processing request needs to be processed by a first artificial intelligence application, the data processing request includes at least data information to be processed, and a first image of the operating environment of the first artificial intelligence application is deployed in the serverless architecture.

[0045] Optionally, a first image of the operating environment of the first artificial intelligence application is deployed in the serverless architecture, and the first image is used to provide a stable operating environment for the first artificial intelligence application. A data processing request initiated by a user (i.e., the target object mentioned above) is received through the serverless architecture.

[0046] Step S202: triggering a target function based on a data processing request, and loading a first artificial intelligence model and a first dependency library required for a first artificial intelligence application into a serverless architecture through the target function, wherein the target function is deployed in the serverless architecture.

[0047] Optionally, after receiving a data processing request, a target function for processing the data processing request can be triggered by a trigger. After the target function is triggered, the target function will load the first artificial intelligence model required by the first artificial intelligence application and the first dependent library relied on in executing the data processing request into the serverless architecture.

[0048] Step S203: Process the data information to be processed by the first artificial intelligence application based on the first artificial intelligence model and the first dependency library to obtain a data processing result.

[0049] Optionally, the data information to be processed is processed in the first image of the running environment of the first artificial intelligence application through the first artificial intelligence model and the first dependent library to obtain a final data processing result.

[0050] To sum up, the first image of the operating environment of the first artificial intelligence application is directly deployed in the serverless architecture. Then, after the serverless architecture receives a data processing request initiated by the target object, the target function is triggered due to the data processing request. After the target function is triggered, the target function simultaneously loads the first artificial intelligence model and the first dependent library required by the first artificial intelligence application into the serverless architecture. Finally, the first artificial intelligence application uses the first artificial intelligence model and the first dependent library to implement the processing of the data information to be processed. By splitting the code package of the artificial intelligence application into the image of the operating environment, the required artificial intelligence model and the dependent library required at runtime, and then deploying the image of the operating environment in the serverless architecture, the artificial intelligence model and the dependent library are loaded into the serverless architecture through the function at the same time when the data processing request is received, thereby avoiding the problem of loading time caused by loading the entire AI application code package in the existing technology, thereby achieving the effect of improving data processing efficiency.

[0051] In order to improve the efficiency of data processing, in the data processing method provided in Example 1 of the present application, the data information to be processed is processed by a first artificial intelligence application based on a first artificial intelligence model and a first dependent library, and the data processing result is obtained, including: obtaining a first business logic code corresponding to the first artificial intelligence application; processing the data information to be processed by the first artificial intelligence model, the first dependent library and the first business logic code to obtain a data processing result.

[0052] Optionally, the first AI model and the first dependent library process the data information to be processed, including the following steps: after the first AI model and the first dependent library are loaded into the serverless architecture, obtaining first business logic code for the first AI application. It should be noted that business logic code refers to the code portion that implements specific business requirements. It is responsible for tasks such as processing data, performing calculations, validating inputs, and making decisions to ensure that the application operates as expected.

[0053] It should be noted that when deploying the first artificial intelligence application, the corresponding business logic code is deployed to the Serverless platform.

[0054] After obtaining the above-mentioned business logic code, the target function will execute the business logic code. The business logic code processes the data information to be processed by calling the above-mentioned first artificial intelligence model and the first dependent library to obtain the corresponding processing results.

[0055] It should be noted that the interface for loading and using the artificial intelligence model will be defined in the business logic code so that the artificial intelligence model can be seamlessly called and executed after it is mounted.

[0056] The data information to be processed is processed through business logic code, which improves the effect of data processing.

[0057] In order to improve the loading efficiency of the objective function, in the data processing method provided in Example 1 of the present application, loading the first artificial intelligence model and the first dependent library required by the first artificial intelligence application into the serverless architecture through the objective function includes: obtaining a first configuration file corresponding to the first artificial intelligence application, wherein the first configuration file includes at least the first storage address of the first artificial intelligence model and the identifier of the first public component storing the first dependent library, wherein the first public component is a basic component in the serverless architecture; determining the first storage address of the first artificial intelligence model and the identifier of the first public component based on the first configuration file; loading the first artificial intelligence model from the first storage address into the serverless architecture through the objective function; and loading the first dependent library from the first public component into the serverless architecture through the objective function based on the identifier of the first public component.

[0058] Optionally, when the target function loads the first artificial intelligence model and the first dependency library, the following steps are included: obtaining a first configuration file corresponding to the first artificial intelligence application from the serverless architecture. It should be noted that the first configuration file includes at least the first storage address of the first artificial intelligence model and the identifier of the first common component storing the first dependency library. The first configuration file may also include specific parameters for running the artificial intelligence application, such as API keys, database connections, etc.

[0059] After obtaining the first configuration file, the target function loads the first artificial intelligence model into the serverless architecture from the first storage address, and loads the first dependent library into the serverless architecture from the first public component.

[0060] It should be noted that the common component is the Layer component, the basic component in the serverless architecture, which is used to quickly and conveniently create, configure and manage layer resources of artificial intelligence applications.

[0061] It should be noted that AI models are deployed in a mounted manner. For example, dynamic loading: when the function is executed, the AI ​​model is dynamically loaded from the cloud storage service according to the first storage address. Mount point configuration: In the configuration file, it refers to the storage location (such as URL or path) and mount point of the AI ​​model, and then the AI ​​model is loaded from the local computer.

[0062] Layer technology significantly improves the deployment efficiency and operational performance of AI applications in serverless architectures. It not only reduces repetitive dependency management tasks but also accelerates application startup and execution, effectively improving data processing efficiency.

[0063] In order to improve the efficiency of data processing, in the data processing method provided in Example 1 of the present application, before receiving a data processing request initiated by a target object through a serverless architecture, the method also includes: obtaining the target object's demand information for a second artificial intelligence application; determining, based on the demand information, a second image, a second artificial intelligence model, and a second dependent library of the operating environment required for the second artificial intelligence application; constructing the business logic code of the second artificial intelligence application based on the demand information; and deploying the second artificial intelligence application in the serverless architecture based on the second image, the second artificial intelligence model, the second dependent library, and the business logic code.

[0064] Optionally, the resources required by AI applications can be divided into different types to optimize deployment and operation efficiency. The resources required by AI applications mainly include the following:

[0065] Dependent libraries (Libraries): Includes all third-party libraries and frameworks required for the operation of AI applications, such as TensorFlow. Runtime Environment (Runtime Environment): Includes the basic operating system, programming language interpreters (such as Python, Node.js) and necessary system libraries. One or several sets of general basic images can be set up according to the commonly used runtime environment, allowing users to select and load appropriate resources according to their needs. AI Models (AIModels): Includes machine learning or deep learning models, which are usually large in size and take a long time to load. Business Logic Code: Code for specific applications, including data processing, request processing, etc. Configuration Files: Application configuration files, environment variables and necessary small data files.

[0066] Based on the aforementioned resource partitioning, deploying the second AI model involves the following steps: obtaining the user's (i.e., the aforementioned target object) defined requirements for the second AI application; then, based on this requirements, selecting the second image, second AI model, and second dependency library required for the second AI application's runtime environment. Business logic code for the second AI application, including data processing and request handling, is written based on the requirements. Finally, the second AI application is deployed based on the second image, second AI model, second dependency library, and business logic code.

[0067] Detailed resource type segmentation enables more efficient management of the various components of AI applications, optimizing resource loading and execution efficiency. This segmentation approach can significantly mitigate cold start issues in serverless environments, particularly for applications requiring large dependency libraries and AI models, while maintaining application flexibility and scalability.

[0068] Optionally, deploying a second artificial intelligence application in a serverless architecture based on the second image, the second artificial intelligence model, the second dependency library and the business logic code includes: storing the second artificial intelligence model in the target device to obtain a second storage address; creating a second public component in the serverless architecture based on the second dependency library, and storing the second dependency library in the second public component; obtaining a second configuration file of the second artificial intelligence application based on the second storage address and the identifier of the second public component; deploying the second image, the second configuration file and the business logic code in the serverless architecture to realize the deployment of the second artificial intelligence application in the serverless architecture.

[0069] Optionally, the deployment of the second artificial intelligence application based on the second image, the second artificial intelligence model, the second dependency library and the business logic code includes the following steps: First, the second artificial intelligence model is stored in the target device. It should be noted that the target device can be a cloud storage service or a local storage device. After the second artificial intelligence model is stored, the second artificial intelligence application is mounted, for example, dynamically mounted: when the function is executed, the AI ​​model is loaded from the cloud storage service. Mounting by mounting a mount point: specify the storage location (such as a URL or path) and the mount point of the model in the configuration of the Serverless function, and record the AI ​​model from the mount point.

[0070] It should be noted that in order to improve performance, commonly used models can be cached in a serverless environment to reduce subsequent loading time.

[0071] Then, based on the second dependency library, a second common component is created in the serverless architecture, known as a layer component. In the serverless architecture, a layer is a reusable package of code and / or data that stores common components of functions, such as libraries, custom runtimes, and other dependencies. Layers make sharing and managing common resources more efficient. By using layers, different serverless functions can share the same dependencies without having to include them repeatedly in each deployment package.

[0072] You can create a layer containing a specific dependency library and upload it to the Serverless platform. Layer supports version control, and you can ensure consistency and compatibility by specifying a specific version of the layer. For AI applications, you can create a dedicated layer to store large machine learning libraries and commonly used AI tool sets. AI applications can dynamically reference different layers based on demand, such as switching when different machine learning frameworks or different versions of libraries are required, and the layer is isolated from the function code at runtime, ensuring security and stability. You can also control access rights to the layer to ensure that only authorized functions can use a specific layer. By placing common dependencies in the layer, you can reduce the size of the function's deployment package and speed up the deployment process. By sharing the layer, you reduce resource duplication and optimize the use of memory and storage space.

[0073] After storing the above-mentioned second dependent library, the second configuration file of the second artificial intelligence application is configured according to the second storage address and the identifier of the second common component. Finally, the second image, the second configuration file and the business logic code are deployed in the serverless architecture to realize the deployment of the second artificial intelligence application in the serverless architecture.

[0074] The above deployment process significantly reduces the cold start time, and improves resource utilization efficiency through Layer technology and dynamic model mounting, thereby achieving the effect of improving data processing efficiency.

[0075] In order to improve data security, in the data processing method provided in Example 1 of the present application, loading the first artificial intelligence model into the serverless architecture from the first storage address through the target function includes: initiating an acquisition request for the first artificial intelligence model to the first device through the target function, wherein the first device is a device storing the first artificial intelligence model, and the acquisition request includes at least the identification information of the target function, and the first device determines whether the identification information of the target function is in a preset list, and the preset list includes the identification information of the function allowed to load the first artificial intelligence model; if the identification information of the target function is in the preset list, the first artificial intelligence model is loaded into the serverless architecture from the first storage address through the target function.

[0076] Optionally, the target function loading the first artificial intelligence model from the first storage address into the serverless architecture includes the following steps: the target function initiates a request to the first device to obtain the first artificial intelligence model, the target function's request including at least identification information of the target function and the target function's identification information. After receiving the request, the first device determines whether the identification information of the target function is within a preset list. If the identification information of the target function is within the preset list, the first device returns the first artificial intelligence model to the serverless architecture.

[0077] Optionally, in order to further improve data security, the artificial intelligence model is encrypted during transmission and storage to further ensure data security.

[0078] In order to improve the accuracy of data processing by the artificial intelligence model, in the data processing method provided in Example 1 of the present application, after the data information to be processed is processed by the first artificial intelligence model and the first dependent library to obtain the data processing result, the method also includes: obtaining the target data information generated by the first artificial intelligence model in the process of processing the data information to be processed; evaluating the first artificial intelligence model based on the target data information to obtain an evaluation result; and optimizing the first artificial intelligence model based on the evaluation result.

[0079] Optionally, after the data to be processed is processed, target data generated by the first artificial intelligence model during the processing of the data to be processed, such as execution efficiency and memory usage data, is collected. The first artificial intelligence model is then evaluated based on the target data to determine whether optimization of the first artificial intelligence model is necessary, i.e., optimizing the first artificial intelligence model based on the evaluation results.

[0080] Alternatively, in AI applications based on a serverless architecture, continuous optimization and adjustment are key to ensuring application performance and cost efficiency. The following is a detailed description of the optimization and adjustment process:

[0081] Performance testing: Testing includes key performance indicators such as startup time, execution time, memory usage, and error rate. Runtime data is collected using the testing tools provided by the Serverless platform.

[0082] Resource configuration optimization: Memory and CPU allocation: Adjust the memory and CPU resources allocated to serverless functions based on application performance requirements and actual usage. Concurrent execution management: Adjust concurrent execution settings, such as increasing or decreasing the number of concurrent function instances, to balance performance and cost.

[0083] Code and dependency optimization: Code refactoring: Regularly refactor the code to improve efficiency and reduce unnecessary resource consumption. Dependency update: Update the dependency library in Layer to the latest version to ensure good performance.

[0084] AI model optimization: Model efficiency: Analyze and adjust AI models to improve their operational efficiency, such as reducing model size through techniques such as model pruning and quantization. Loading strategy adjustment: Adjust model loading strategies, such as caching frequently used models to reduce loading time.

[0085] Cost Efficiency Analysis: Cost monitoring: Detect and analyze the running costs of Serverless functions, including computing resource usage and storage fees. Cost optimization strategies: Adjust resource usage based on cost analysis results, such as optimizing function execution frequency and duration, to reduce costs. Automated optimization tools: Use automated tools and scripts to perform performance and cost analysis and automatically adjust resource allocation.

[0086] User feedback and adjustments: Regularly collect user feedback to understand performance and functionality issues. Adjust the app based on user feedback to improve the user experience.

[0087] Through these optimization and adjustment steps, AI applications in serverless architectures can continuously improve their performance while maintaining cost efficiency. This continuous optimization process is crucial for responding to ever-changing technical environments and business needs.

[0088] Alternatively, you can Figure 3 The flowchart shown implements the process of data processing:

[0089] Code preparation: Business logic code, specifically for the AI ​​application, is written. This includes functions such as data processing and responding to user requests. Environment configuration involves setting environment variables and configuration files. These configurations specify specific parameters for application operation, such as API keys and database connections.

[0090] Code packaging and uploading: Packaging refers to packaging the business logic code and necessary configuration files. Typically, this packaging process requires excluding large dependencies and AI models, which are handled by the Layer and model mounting services, respectively. The packaged code is uploaded to the Serverless platform.

[0091] Layer and model integration: Specify which layers to use in the Serverless platform configuration. These layers contain the dependency libraries required for code execution. Model mounting configuration specifies the storage location and mounting method of the AI ​​model to ensure dynamic loading at runtime.

[0092] Function trigger settings: Define triggers. Based on application requirements, set function triggers, which can be HTTP requests, database events, scheduled tasks, etc. Trigger configuration: Configure specific trigger parameters, such as the HTTP endpoint path and the execution frequency of scheduled tasks.

[0093] Code Execution Process: When a trigger is triggered, the Serverless platform launches the function instance. Dynamic Resource Loading: The function instance dynamically loads the required layers and AI models based on the configuration. Business Logic Execution: After loading the necessary resources, the business logic code begins executing, processing input data, invoking the AI ​​model for calculations, and generating a response.

[0094] Performance optimization and testing: Use tools provided by the Serverless platform to test function execution, including startup time, execution time, memory usage, etc. Tuning: Adjust resource configuration (such as memory size and execution time limit) and code logic based on the test data to optimize performance.

[0095] Security and Compliance: Code Audits: Regularly audit code and dependencies to ensure security. Compliance: Ensure that code and data processing adhere to relevant data protection and privacy regulations.

[0096] Through the above steps, the code deployment and execution process is optimized in the server-less architecture, ensuring the efficient operation of AI applications.

[0097] In the data processing method provided in Example 1 of the present application, a data processing request initiated by a target object is received through a serverless architecture, wherein the data processing request needs to be processed by a first artificial intelligence application, and the data processing request includes at least data information to be processed, and a first image of the operating environment of the first artificial intelligence application is deployed in the serverless architecture; the target function is triggered according to the data processing request, and the first artificial intelligence model and the first dependent library required by the first artificial intelligence application are loaded into the serverless architecture through the target function, wherein the target function is deployed in the serverless architecture; the data information to be processed is processed by the first artificial intelligence application based on the first artificial intelligence model and the first dependent library to obtain a data processing result, which solves the technical problem in the related art that when performing data processing based on an AI application, the loading time is too long due to the large amount of data in the entire AI application code package, which leads to relatively low data processing efficiency. In this solution, the first image of the operating environment of the first artificial intelligence application is directly deployed in the serverless architecture. Then, after the serverless architecture receives a data processing request initiated by the target object, the target function is triggered due to the data processing request. After the target function is triggered, the target function simultaneously loads the first artificial intelligence model and the first dependent library required by the first artificial intelligence application into the serverless architecture. Finally, the first artificial intelligence application uses the first artificial intelligence model and the first dependent library to implement the processing of the data information to be processed. By splitting the code package of the artificial intelligence application into the image of the operating environment, the required artificial intelligence model and the dependent library required at runtime, and then deploying the image of the operating environment in the serverless architecture, when the data processing request is received, the artificial intelligence model and the dependent library are simultaneously loaded into the serverless architecture through the function, thereby avoiding the problem of loading time caused by loading the entire AI application code package in the existing technology, thereby achieving the effect of improving data processing efficiency.

[0098] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0099] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0100] Example 2

[0101] According to an embodiment of the present application, a data processing device for implementing the above data processing method is also provided. Figure 4 As shown, the device includes: a receiving unit 401, a triggering unit 402 and a processing unit 403.

[0102] A receiving unit 401 is configured to receive, via a serverless architecture, a data processing request initiated by a target object, wherein the data processing request is to be processed by a first artificial intelligence application, the data processing request includes at least data information to be processed, and a first image of an operating environment of the first artificial intelligence application is deployed in the serverless architecture;

[0103] a triggering unit 402 configured to trigger a target function based on a data processing request, and load a first artificial intelligence model and a first dependency library required by the first artificial intelligence application into the serverless architecture through the target function, wherein the target function is deployed in the serverless architecture;

[0104] The processing unit 403 is used to process the data information to be processed based on the first artificial intelligence model and the first dependency library through the first artificial intelligence application to obtain a data processing result.

[0105] In the data processing device provided in Example 2 of the present application, a data processing request initiated by a target object is received through a receiving unit 401 through a serverless architecture, wherein the data processing request needs to be processed by a first artificial intelligence application, and the data processing request includes at least data information to be processed, and a first image of the operating environment of the first artificial intelligence application is deployed in the serverless architecture; the triggering unit 402 triggers the target function according to the data processing request, and loads the first artificial intelligence model and the first dependent library required by the first artificial intelligence application into the serverless architecture through the target function, wherein the target function is deployed in the serverless architecture; the processing unit 403 processes the data information to be processed based on the first artificial intelligence model and the first dependent library through the first artificial intelligence application to obtain a data processing result, thereby solving the technical problem in the related art that when data processing is performed based on an AI application, the loading time is too long due to the large amount of data in the entire AI application code package, which leads to relatively low efficiency of data processing. In this solution, the first image of the operating environment of the first artificial intelligence application is directly deployed in the serverless architecture. Then, after the serverless architecture receives a data processing request initiated by the target object, the target function is triggered due to the data processing request. After the target function is triggered, the target function simultaneously loads the first artificial intelligence model and the first dependent library required by the first artificial intelligence application into the serverless architecture. Finally, the first artificial intelligence application uses the first artificial intelligence model and the first dependent library to implement the processing of the data information to be processed. By splitting the code package of the artificial intelligence application into the image of the operating environment, the required artificial intelligence model and the dependent library required at runtime, and then deploying the image of the operating environment in the serverless architecture, when the data processing request is received, the artificial intelligence model and the dependent library are simultaneously loaded into the serverless architecture through the function, thereby avoiding the problem of loading time caused by loading the entire AI application code package in the existing technology, thereby achieving the effect of improving data processing efficiency.

[0106] Optionally, in the data processing device provided in the second embodiment of the application, the processing unit 403 includes: a first acquisition module, used to obtain the first business logic code corresponding to the first artificial intelligence application; a processing module, used to process the data information to be processed through the first artificial intelligence model, the first dependency library and the first business logic code to obtain a data processing result.

[0107] Optionally, in the data processing device provided in the second embodiment of the application, the trigger unit 402 includes: a second acquisition module, used to obtain a first configuration file corresponding to the first artificial intelligence application, wherein the first configuration file includes at least a first storage address of the first artificial intelligence model and an identifier of a first common component storing a first dependency library, wherein the first common component is a basic component in the serverless architecture; a first determination module, used to determine the first storage address of the first artificial intelligence model and the identifier of the first common component based on the first configuration file; a first loading module, used to load the first artificial intelligence model into the serverless architecture from the first storage address through a target function; a second loading module, used to load the first dependency library into the serverless architecture from the first common component through a target function based on the identifier of the first common component.

[0108] Optionally, in the data processing device provided in the second embodiment of the application, the device also includes: a first acquisition unit, used to obtain the target object's demand information for the second artificial intelligence application before receiving the data processing request initiated by the target object through the serverless architecture; a determination unit, used to determine the second image, second artificial intelligence model and second dependency library of the operating environment required for the second artificial intelligence application based on the demand information; a construction unit, used to construct the business logic code of the second artificial intelligence application based on the demand information; and a deployment unit, used to deploy the second artificial intelligence application in the serverless architecture based on the second image, second artificial intelligence model, second dependency library and business logic code.

[0109] Optionally, in the data processing device provided in the second embodiment of the application, the deployment unit includes: a storage module, used to store the second artificial intelligence model in the target device and obtain a second storage address; a construction module, used to create a second common component in the serverless architecture based on the second dependency library, and store the second dependency library in the second common component; a second determination module, used to obtain a second configuration file of the second artificial intelligence application based on the second storage address and the identifier of the second common component; a deployment module, used to deploy the second image, the second configuration file and the business logic code in the serverless architecture to realize the deployment of the second artificial intelligence application in the serverless architecture.

[0110] Optionally, in the data processing device provided in the second embodiment of the application, the first loading module includes: an acquisition sub-module, which is used to initiate an acquisition request for the first artificial intelligence model to the first device through the target function, wherein the first device is a device storing the first artificial intelligence model, and the acquisition request includes at least the identification information of the target function, and the first device is used to determine whether the identification information of the target function is in a preset list, and the preset list includes the identification information of the function allowed to load the first artificial intelligence model; a recording sub-module, which is used to load the first artificial intelligence model into the serverless architecture from the first storage address through the target function if the identification information of the target function is in the preset list.

[0111] Optionally, in the data processing device provided in the second embodiment of the application, the device also includes: a second acquisition unit, which is used to obtain the target data information generated by the first artificial intelligence model in the process of processing the data information to be processed after processing the data information to be processed through the first artificial intelligence model and the first dependent library to obtain the data processing result; an evaluation unit, which is used to evaluate the first artificial intelligence model based on the target data information to obtain an evaluation result; and an optimization unit, which is used to optimize the first artificial intelligence model based on the evaluation result.

[0112] It should be noted that the receiving unit 401, triggering unit 402, and processing unit 403 described above correspond to steps S201 to S203 in Example 1. The examples and application scenarios implemented by the 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 run in the computer terminal 10 provided in Example 1.

[0113] It should be noted that the preferred implementation scheme involved in the above embodiments of this application is the same as the scheme provided in Example 1, as well as the application scenario and implementation process, but is not limited to the scheme provided in Example 1.

[0114] Example 3

[0115] According to an embodiment of the present application, a data processing system for implementing the above data processing method is also provided. Figure 5 As shown, the data processing system includes: a user layer 50, a configuration layer 51, a deployment layer 52 and an execution layer 53.

[0116] The user layer 50 defines AI application requirements and selects appropriate base images and layers. The configuration layer 51 configures resources, including dependencies, runtime environments, and models. The deployment layer 52 deploys applications to the serverless platform, including layer configuration and model loading. The execution layer 53 runs the AI ​​application on the serverless platform, dynamically loading required resources.

[0117] The data processing system performs the following steps to process data: Select an appropriate base image based on the AI ​​application requirements. Configure the required dependency layers. Configure the model mounting service and specify the model location. Deploy the business logic code to the Serverless platform. The Serverless platform dynamically loads the layers and model at runtime and runs the AI ​​application. Adjust resource allocation based on the running situation to optimize performance.

[0118] By separating dependencies from models and leveraging Layer technology and disk mounting services, we significantly reduce the cold start time of AI applications in serverless architectures, while improving resource utilization and application performance. This solution provides an efficient and flexible solution for deploying and executing large-scale AI applications in serverless environments.

[0119] It should be noted that the preferred implementation scheme involved in the above embodiments of this application is the same as the scheme provided in Example 1, as well as the application scenario and implementation process, but is not limited to the scheme provided in Example 1.

[0120] Example 4

[0121] The embodiment of the present application can provide a computer terminal, which can be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal can also be replaced by a terminal device such as a mobile terminal.

[0122] Optionally, in this embodiment, the computer terminal may be located in at least one network device among a plurality of network devices of a computer network.

[0123] In this embodiment, the above-mentioned computer terminal can execute the program code of the following steps in the data processing method: receiving a data processing request initiated by the target object through the serverless architecture, wherein the data processing request needs to be processed by the first artificial intelligence application, the data processing request includes at least the data information to be processed, and the first image of the operating environment of the first artificial intelligence application is deployed in the serverless architecture; triggering the target function according to the data processing request, and loading the first artificial intelligence model and the first dependent library required by the first artificial intelligence application into the serverless architecture through the target function, wherein the target function is deployed in the serverless architecture; processing the data information to be processed based on the first artificial intelligence model and the first dependent library by the first artificial intelligence application to obtain the data processing result.

[0124] The above-mentioned computer terminal can execute the program code of the following steps in the data processing method: processing the data information to be processed based on the first artificial intelligence model and the first dependent library through the first artificial intelligence application, and obtaining the data processing result includes: obtaining the first business logic code corresponding to the first artificial intelligence application; processing the data information to be processed through the first artificial intelligence model, the first dependent library and the first business logic code to obtain the data processing result.

[0125] The above-mentioned computer terminal can execute the program code of the following steps in the data processing method: loading the first artificial intelligence model and the first dependent library required by the first artificial intelligence application into the serverless architecture through the objective function includes: obtaining a first configuration file corresponding to the first artificial intelligence application, wherein the first configuration file at least includes the first storage address of the first artificial intelligence model and the identifier of the first public component storing the first dependent library, wherein the first public component is the basic component in the serverless architecture; determining the first storage address of the first artificial intelligence model and the identifier of the first public component based on the first configuration file; loading the first artificial intelligence model from the first storage address into the serverless architecture through the objective function; and loading the first dependent library from the first public component into the serverless architecture through the objective function based on the identifier of the first public component.

[0126] The above-mentioned computer terminal can execute the program code of the following steps in the data processing method: before receiving the data processing request initiated by the target object through the serverless architecture, the method also includes: obtaining the target object's demand information for the second artificial intelligence application; determining the second image, second artificial intelligence model and second dependent library of the operating environment required by the second artificial intelligence application based on the demand information; constructing the business logic code of the second artificial intelligence application based on the demand information; and deploying the second artificial intelligence application in the serverless architecture based on the second image, second artificial intelligence model, second dependent library and business logic code.

[0127] The above-mentioned computer terminal can execute the program code of the following steps in the data processing method: based on the second image, the second artificial intelligence model, the second dependency library and the business logic code, deploying the second artificial intelligence application in the serverless architecture includes: storing the second artificial intelligence model in the target device to obtain a second storage address; creating a second public component in the serverless architecture based on the second dependency library, and storing the second dependency library in the second public component; obtaining a second configuration file of the second artificial intelligence application based on the second storage address and the identifier of the second public component; deploying the second image, the second configuration file and the business logic code in the serverless architecture to realize the deployment of the second artificial intelligence application in the serverless architecture.

[0128] The above-mentioned computer terminal can execute the program code of the following steps in the data processing method: loading the first artificial intelligence model from the first storage address into the serverless architecture through the target function includes: initiating an acquisition request for the first artificial intelligence model to the first device through the target function, wherein the first device is a device storing the first artificial intelligence model, and the acquisition request includes at least the identification information of the target function, and the first device determines whether the identification information of the target function is in a preset list, and the preset list includes the identification information of the function allowed to load the first artificial intelligence model; if the identification information of the target function is in the preset list, then the first artificial intelligence model is loaded into the serverless architecture from the first storage address through the target function.

[0129] The above-mentioned computer terminal can execute the program code of the following steps in the data processing method: after processing the data information to be processed by the first artificial intelligence model and the first dependent library to obtain the data processing result, the method also includes: obtaining the target data information generated by the first artificial intelligence model in the process of processing the data information to be processed; evaluating the first artificial intelligence model based on the target data information to obtain an evaluation result; and optimizing the first artificial intelligence model based on the evaluation result.

[0130] Optionally, Figure 6 This is a structural block diagram of a computer terminal according to an embodiment of the present application. Figure 6 As shown, the computer terminal 10 may include: one or more ( Figure 6 (only one is shown) processor 102, memory 104. The computing terminal 10 may also include a storage controller to control and manage the memory 104; the computing terminal 10 may also include a peripheral interface to connect to a radio frequency module, an audio module, and a display screen, etc.

[0131] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the data processing method and device in the embodiments of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned data processing method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0132] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: receiving a data processing request initiated by the target object through the serverless architecture, wherein the data processing request needs to be processed by the first artificial intelligence application, the data processing request includes at least the data information to be processed, and the first image of the operating environment of the first artificial intelligence application is deployed in the serverless architecture; triggering the target function according to the data processing request, and loading the first artificial intelligence model and the first dependent library required by the first artificial intelligence application into the serverless architecture through the target function, wherein the target function is deployed in the serverless architecture; processing the data information to be processed based on the first artificial intelligence model and the first dependent library by the first artificial intelligence application to obtain the data processing result.

[0133] Optionally, the processor may also execute the program code of the following steps: processing the data information to be processed based on the first artificial intelligence model and the first dependency library through the first artificial intelligence application, and obtaining the data processing result includes: obtaining the first business logic code corresponding to the first artificial intelligence application; processing the data information to be processed through the first artificial intelligence model, the first dependency library and the first business logic code to obtain the data processing result.

[0134] Optionally, the processor may also execute the following program code: loading the first artificial intelligence model and the first dependency library required for the first artificial intelligence application into the serverless architecture through the objective function includes: obtaining a first configuration file corresponding to the first artificial intelligence application, wherein the first configuration file includes at least the first storage address of the first artificial intelligence model and the identifier of the first public component storing the first dependency library, wherein the first public component is a basic component in the serverless architecture; determining the first storage address of the first artificial intelligence model and the identifier of the first public component based on the first configuration file; loading the first artificial intelligence model from the first storage address into the serverless architecture through the objective function; and loading the first dependency library from the first public component into the serverless architecture through the objective function based on the identifier of the first public component.

[0135] Optionally, the processor may also execute program code for the following steps: before receiving a data processing request initiated by a target object through a serverless architecture, the method may further include: obtaining the target object's demand information for a second artificial intelligence application; determining, based on the demand information, a second image, a second artificial intelligence model, and a second dependency library of the operating environment required for the second artificial intelligence application; constructing, based on the demand information, the business logic code of the second artificial intelligence application; and deploying the second artificial intelligence application in the serverless architecture based on the second image, the second artificial intelligence model, the second dependency library, and the business logic code.

[0136] Optionally, the processor may also execute the program code of the following steps: deploying the second artificial intelligence application in the serverless architecture based on the second image, the second artificial intelligence model, the second dependency library and the business logic code, including: storing the second artificial intelligence model in the target device to obtain a second storage address; creating a second public component in the serverless architecture based on the second dependency library, and storing the second dependency library in the second public component; obtaining a second configuration file of the second artificial intelligence application based on the second storage address and the identifier of the second public component; deploying the second image, the second configuration file and the business logic code in the serverless architecture to realize the deployment of the second artificial intelligence application in the serverless architecture.

[0137] Optionally, the processor may also execute the program code of the following steps: loading the first artificial intelligence model into the serverless architecture from the first storage address through the target function includes: initiating an acquisition request for the first artificial intelligence model to the first device through the target function, wherein the first device is a device storing the first artificial intelligence model, and the acquisition request includes at least the identification information of the target function, and determining through the first device whether the identification information of the target function is in a preset list, and the preset list includes the identification information of the function allowed to load the first artificial intelligence model; if the identification information of the target function is in the preset list, then loading the first artificial intelligence model into the serverless architecture from the first storage address through the target function.

[0138] Optionally, the processor may also execute the program code of the following steps: after processing the data information to be processed by the first artificial intelligence model and the first dependent library to obtain the data processing result, the method further includes: obtaining the target data information generated by the first artificial intelligence model in the process of processing the data information to be processed; evaluating the first artificial intelligence model based on the target data information to obtain an evaluation result; and optimizing the first artificial intelligence model based on the evaluation result.

[0139] It can be understood by those skilled in the art that Figure 6 The structure shown is for illustration only, and the computer terminal may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 6 It does not limit the structure of the above electronic device. For example, the computer terminal 10 may also include Figure 6 More or fewer components (such as network interfaces, display devices, etc.) shown in, or with Figure 6 Different configurations shown.

[0140] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0141] Example 5

[0142] The embodiment of the present application further provides a computer-readable storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the data processing method provided in the first embodiment.

[0143] 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.

[0144] Optionally, in this embodiment, the above-mentioned storage medium is configured to store program code for executing the following steps: receiving a data processing request initiated by a target object through a serverless architecture, wherein the data processing request needs to be processed by a first artificial intelligence application, the data processing request includes at least data information to be processed, and a first image of the operating environment of the first artificial intelligence application is deployed in the serverless architecture; triggering a target function based on the data processing request, and loading the first artificial intelligence model and the first dependent library required by the first artificial intelligence application into the serverless architecture through the target function, wherein the target function is deployed in the serverless architecture; processing the data information to be processed based on the first artificial intelligence model and the first dependent library by the first artificial intelligence application to obtain a data processing result.

[0145] The above-mentioned storage medium is configured to store program codes for executing the following steps: processing the data information to be processed based on the first artificial intelligence model and the first dependent library through the first artificial intelligence application, and obtaining the data processing results including: obtaining the first business logic code corresponding to the first artificial intelligence application; processing the data information to be processed through the first artificial intelligence model, the first dependent library and the first business logic code to obtain the data processing results.

[0146] The above-mentioned storage medium is configured to store program code for executing the following steps: loading the first artificial intelligence model and the first dependent library required by the first artificial intelligence application into the serverless architecture through the objective function includes: obtaining a first configuration file corresponding to the first artificial intelligence application, wherein the first configuration file includes at least the first storage address of the first artificial intelligence model and the identifier of the first public component storing the first dependent library, wherein the first public component is a basic component in the serverless architecture; determining the first storage address of the first artificial intelligence model and the identifier of the first public component based on the first configuration file; loading the first artificial intelligence model from the first storage address into the serverless architecture through the objective function; and loading the first dependent library from the first public component into the serverless architecture through the objective function based on the identifier of the first public component.

[0147] The above-mentioned storage medium is configured to store program code for executing the following steps: before receiving a data processing request initiated by a target object through a serverless architecture, the method also includes: obtaining the target object's demand information for a second artificial intelligence application; determining, based on the demand information, a second image, a second artificial intelligence model, and a second dependent library of the operating environment required for the second artificial intelligence application; based on the demand information, constructing the business logic code of the second artificial intelligence application; and deploying the second artificial intelligence application in the serverless architecture based on the second image, the second artificial intelligence model, the second dependent library, and the business logic code.

[0148] The above-mentioned storage medium is configured to store program code for executing the following steps: deploying the second artificial intelligence application in the serverless architecture based on the second image, the second artificial intelligence model, the second dependency library and the business logic code, including: storing the second artificial intelligence model in the target device to obtain a second storage address; creating a second public component in the serverless architecture based on the second dependency library, and storing the second dependency library in the second public component; obtaining a second configuration file of the second artificial intelligence application based on the second storage address and the identifier of the second public component; deploying the second image, the second configuration file and the business logic code in the serverless architecture to realize the deployment of the second artificial intelligence application in the serverless architecture.

[0149] The above-mentioned storage medium is configured to store program code for executing the following steps: loading the first artificial intelligence model into the serverless architecture from the first storage address through the target function includes: initiating an acquisition request for the first artificial intelligence model to the first device through the target function, wherein the first device is a device storing the first artificial intelligence model, and the acquisition request includes at least the identification information of the target function, and the first device determines whether the identification information of the target function is in a preset list, and the preset list includes the identification information of the function allowed to load the first artificial intelligence model; if the identification information of the target function is in the preset list, then the first artificial intelligence model is loaded into the serverless architecture from the first storage address through the target function.

[0150] The above-mentioned storage medium is configured to store program code for executing the following steps: after processing the data information to be processed by the first artificial intelligence model and the first dependent library to obtain the data processing result, the method also includes: obtaining the target data information generated by the first artificial intelligence model in the process of processing the data information to be processed; evaluating the first artificial intelligence model based on the target data information to obtain an evaluation result; and optimizing the first artificial intelligence model based on the evaluation result.

[0151] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0152] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0153] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0154] 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 one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0155] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0156] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0157] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A data processing method, characterized in that: include: Receiving, through a serverless architecture, a data processing request initiated by a target object, wherein the data processing request needs to be processed by a first artificial intelligence application, the data processing request includes at least data information to be processed, and a first image of an operating environment of the first artificial intelligence application is deployed in the serverless architecture; triggering a target function according to the data processing request, and loading a first artificial intelligence model and a first dependency library required by the first artificial intelligence application into the serverless architecture through the target function, wherein the target function is deployed in the serverless architecture; The data information to be processed is processed by a first artificial intelligence application based on the first artificial intelligence model and the first dependent library to obtain a data processing result.

2. The method according to claim 1, characterized in that Processing the data information to be processed by the first artificial intelligence application based on the first artificial intelligence model and the first dependency library, obtaining a data processing result includes: Obtaining a first business logic code corresponding to the first artificial intelligence application; The data information to be processed is processed through the first artificial intelligence model, the first dependency library and the first business logic code to obtain the data processing result.

3. The method according to claim 1, characterized in that Loading the first artificial intelligence model and the first dependent library required by the first artificial intelligence application into the serverless architecture through the objective function includes: Obtaining a first configuration file corresponding to the first artificial intelligence application, wherein the first configuration file includes at least a first storage address of the first artificial intelligence model and an identifier of a first public component storing a first dependency library, wherein the first public component is a basic component in the serverless architecture; Determining, according to the first configuration file, a first storage address of the first artificial intelligence model and an identifier of the first common component; loading the first artificial intelligence model from the first storage address into the serverless architecture through the objective function; According to the identifier of the first common component, the first dependent library is loaded from the first common component into the serverless architecture through the target function.

4. The method according to claim 1, wherein Before receiving a data processing request initiated by a target object through the serverless architecture, the method further includes: Obtaining information about the target object's demand for a second artificial intelligence application; Determining, based on the requirement information, a second image, a second artificial intelligence model, and a second dependent library of the operating environment required by the second artificial intelligence application; Constructing the business logic code of the second artificial intelligence application based on the demand information; Deploy the second artificial intelligence application in the serverless architecture based on the second image, the second artificial intelligence model, the second dependent library and the business logic code.

5. The method according to claim 4, characterized in that Deploying the second artificial intelligence application in the serverless architecture based on the second image, the second artificial intelligence model, the second dependency library, and the business logic code includes: Storing the second artificial intelligence model in a target device to obtain a second storage address; Creating a second public component in the serverless architecture according to the second dependent library, and storing the second dependent library in the second public component; Obtaining a second configuration file of the second artificial intelligence application according to the second storage address and the identifier of the second common component; Deploy the second image, the second configuration file, and the business logic code in the serverless architecture to deploy the second artificial intelligence application in the serverless architecture.

6. The method according to claim 3, characterized in that Loading the first artificial intelligence model from the first storage address into the serverless architecture through the objective function includes: Initiating an acquisition request for the first artificial intelligence model to a first device through the target function, wherein the first device is a device storing the first artificial intelligence model, the acquisition request includes at least identification information of the target function, and the first device determines whether the identification information of the target function is in a preset list, wherein the preset list includes identification information of functions allowed to load the first artificial intelligence model; If the identification information of the objective function is in the preset list, the first artificial intelligence model is loaded into the serverless architecture from the first storage address through the objective function.

7. The method according to claim 1, characterized in that After the data information to be processed is processed by the first artificial intelligence model and the first dependent library to obtain a data processing result, the method further includes: Acquire target data information generated by the first artificial intelligence model in the process of processing the data information to be processed; Evaluating the first artificial intelligence model based on the target data information to obtain an evaluation result; The first artificial intelligence model is optimized according to the evaluation result.

8. A data processing device, characterized in that: include: a receiving unit, configured to receive, via a serverless architecture, a data processing request initiated by a target object, wherein the data processing request needs to be processed by a first artificial intelligence application, the data processing request includes at least data information to be processed, and a first image of an operating environment of the first artificial intelligence application is deployed in the serverless architecture; a triggering unit, configured to trigger a target function according to the data processing request, and load a first artificial intelligence model and a first dependency library required by the first artificial intelligence application into the serverless architecture through the target function, wherein the target function is deployed in the serverless architecture; A processing unit is used to process the data information to be processed based on the first artificial intelligence model and the first dependency library through a first artificial intelligence application to obtain a data processing result.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the data processing method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: a memory storing an executable program; A processor, configured to run the program, wherein the program, when running, executes the data processing method according to any one of claims 1 to 7.

11. A computer program product, characterized in that The computer program product comprises a stored computer program, and when the computer program is executed by a processor, the data processing method according to any one of claims 1 to 7 is implemented.

Images