Data processing methods, apparatus, equipment and storage media

Abstract

This invention discloses a data processing method, apparatus, device, and storage medium, relating to the field of artificial intelligence technology. The method involves receiving a model invocation request, wherein the request carries model-related data; converting the model-related data into a predetermined composite data structure, wherein the predetermined composite data structure is a composite data structure composed of a list and a set of key-value pairs; parsing the predetermined composite data structure; and obtaining a target machine learning model based on the parsing result. The data processing method provided by this invention converts model-related data in a model invocation request into a predetermined composite data structure for parsing, thereby processing target data, avoiding multiple development iterations for deploying machine learning model services, shortening the development cycle, and improving the convenience of data processing.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a data processing method, apparatus, device and storage medium. Background Technology

[0002] Most existing online service mechanisms for machine learning model computation require custom development of a corresponding service interface for each model deployed, resulting in long development cycles and a lack of flexibility and scalability. Current online services for machine learning model computation typically provide support for single-model, single-data-item computation, lacking support for batch computation requests for multiple data items or multiple models. Summary of the Invention

[0003] This invention provides a data processing method, apparatus, device, and storage medium that avoids multiple developments for deploying machine learning model services, shortens the development cycle, and improves the convenience of data processing.

[0004] In a first aspect, embodiments of the present invention provide a data processing method, including:

[0005] Receive a model invocation request; wherein the model invocation request carries model-related data;

[0006] The model-related data is transformed into a defined composite data structure; wherein the defined composite data structure is a composite data structure consisting of a list and a set of key-value pairs;

[0007] The defined composite data structure is parsed, and the parsing result is obtained.

[0008] The target machine learning model is obtained based on the analysis results.

[0009] Secondly, embodiments of the present invention also provide a data processing apparatus, comprising:

[0010] A model call request receiving module is used to receive model call requests; wherein, the model call request carries model-related data;

[0011] The data transformation module is used to transform the model-related data into a set composite data structure; wherein, the set composite data structure is a composite data structure composed of a list and a set of key-value pairs;

[0012] The data parsing module is used to parse the defined composite data structure and provide the parsing results.

[0013] The target machine learning model acquisition module is used to acquire the target machine learning model based on the parsing results.

[0014] Thirdly, embodiments of the present invention also provide a computer device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the data processing method as described in the embodiments of the present invention.

[0015] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processing device, implements the data processing method as described in the embodiments of the present invention.

[0016] This invention discloses a data processing method, apparatus, device, and storage medium. The method involves receiving a model invocation request, which carries model-related data; converting the model-related data into a defined composite data structure, wherein the defined composite data structure consists of a list and a set of key-value pairs; parsing the defined composite data structure; and obtaining the target machine learning model based on the parsing result. The data processing method provided by this invention converts model-related data in a model invocation request into a defined composite data structure for parsing, thereby processing the target data, avoiding multiple development iterations for deploying machine learning model services, shortening the development cycle, and improving the convenience of data processing. Attached Figure Description

[0017] Figure 1 This is a flowchart of a data processing method according to Embodiment 1 of the present invention;

[0018] Figure 2 This is a schematic diagram of the structure of a data processing device according to Embodiment 2 of the present invention;

[0019] Figure 3 This is a schematic diagram of the structure of a computer device according to Embodiment 3 of the present invention. Detailed Implementation

[0020] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0021] Example 1

[0022] Figure 1 This is a flowchart of a data processing method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where a machine learning model is called through a unified interface. This method can be executed by a data processing device, such as... Figure 1 As shown, the method specifically includes the following steps:

[0023] Step 110: Receive the model call request.

[0024] The model call request carries model-related data, which may include the model type, model file access identifier, model file packaging format, and model input parameters. The model type can be a machine learning model from XGboost, LightGBM, or the sklearn library; the model file access identifier identifies the model to be accessed; the model file packaging format characterizes the file's encapsulation and parsing format, such as binary storage, Python's pkl file format, or a specific text format; the model input parameters can be a string displayed as key-value pairs, recording the feature information of the input model.

[0025] In this embodiment, the model invocation request also carries a request identifier (ID) to identify that the request is a model invocation request. Specifically, the model invoker sends the model invocation request to the service request interface, which parses the model invocation request to obtain the target machine learning model.

[0026] Step 120: Transform the model-related data into a defined composite data structure.

[0027] The composite data structure is defined as a combination of a list and a set of key-value pairs. A list can be understood as an array containing multiple elements, each element being a set of key-value pairs, and each set containing at least one key-value pair. A key-value pair is a data pair consisting of a key and a value, for example, represented as key:value. For example, a list can be represented as [L1, L2, L3, ..., Ln], where Li is the set of key-value pairs, which can be represented as {k1:v1; k1:v1, ..., km:vm}.

[0028] Specifically, the process of transforming model-related data into a defined composite data structure can be as follows: transforming the model type into a first key-value pair; transforming the data file access identifier into a second key-value pair; transforming the model file packaging format into a third key-value pair; transforming the model input parameters into a fourth key-value pair; and transforming the model-related data into a total key-value pair.

[0029] In this context, the fourth key-value pair contains a list consisting of at least one set of key-value pairs. Therefore, the fourth key-value pair corresponding to the model input parameters is a composite structure of "list + set of key-value pairs". The total key-value pairs contain a list consisting of the first, second, third, and fourth key-value pairs. Therefore, the total key-value pairs corresponding to the model-related data is a composite structure of "list + set of key-value pairs". For example, the first key-value pair converted from model type can be represented as model-type:XGBoost; the second key-value pair converted from data file access identifier can be represented as Model-mark:model-name; the third key-value pair converted from model file packaging format can be represented as Model-pack:pickle; and the fourth key-value pair converted from model input parameters can be represented as: Model-input-aparameters: {input1:value1, input2:values, ...}, {input1:value1, input2:values, ...}, ..., {input1:value1, input2:values, ...}.

[0030] Step 130: Parse the defined composite data structure to obtain the parsing result.

[0031] The defined composite data structure can be represented in text format. The parsing result can include information such as the model type that the computer can recognize, the model file access identifier, the model file packaging format, and the model input parameters. The parsing of the defined composite data structure can be performed by: converting the text-formatted defined composite data structure into a composite data structure in the target computer language; and then using the parsing logic of the target computer language to parse the composite data structure to obtain the parsing result.

[0032] The target computer language can be Python, Java, or Scala, etc. If the target language is Python, the composite data structure of "list + key-value pair set" needs to be transformed into a composite structure of "list + dictionary". If the target language is Java, the composite data structure of "list + key-value pair set" needs to be transformed into a composite structure of "array + map". For example, assuming the target language is Python, the process of parsing the composite data structure can be as follows: first, use the pandas library to convert it to DataFrame format, and then parse the DataFrame data.

[0033] Step 140: Obtain the target machine learning model based on the parsing results.

[0034] Specifically, after obtaining the parsing results, the target machine learning model is retrieved from the model database based on the model type, model file access identifier, and model file packaging format. The model database stores multiple pre-developed machine learning models.

[0035] Optionally, after obtaining the target machine learning model based on the parsing results, the following steps are also included: preloading the target machine learning model into a designated memory.

[0036] The target machine learning model comprises multiple model files, and all or some of these files can be loaded into a designated memory location. This designated memory can be the central processing unit (CPU) memory in a computer. The user can configure whether to preload all or some model files. In this embodiment, preloading the target machine learning model into the designated memory location can improve the model loading speed.

[0037] Optionally, after preloading the target machine learning model into a designated memory, the following steps are also included: processing the model input parameters into parameters of a first designated format; inputting the parameters of the designated format into the preloaded target machine learning model to obtain the calculation results.

[0038] The first specified format is a data format recognizable by the target machine learning model. This first specified format can be a vector or matrix of a specified size. In this embodiment, after the parameters of the specified format are input into the preloaded target machine learning model, the target machine learning model processes the input specified format and outputs the calculation results. Whether the model input parameters are processed into parameters of the first specified format can be determined based on the user's configuration information.

[0039] Optionally, after obtaining the calculation results, the following steps are also included: processing the calculation results into data in a second set format; and returning the data in the second set format to the model caller.

[0040] The second setting format is a format that can be recognized by the model caller.

[0041] Optionally, it may also include: configuration model preloading information, input parameter processing information, and calculation result processing information.

[0042] The model preloading information may include whether to preload the model and which model files to preload; the input parameter processing information may include whether to process the model input parameters into a first set format and the specific form of the first set format; the calculation result processing information may include whether to process the calculation results into a second set format and the specific form of the second set format.

[0043] The key protection points of this implementation are as follows: A general online service interface is designed for data processing, which supports flexible configuration of model calls, avoids redundant development for machine learning model service deployment, shortens the development cycle, and enhances the flexibility of the online service. It supports batch request computation for multiple datasets and multiple models, enhancing the scalability of the online service. The processing of model input parameters and model computation results provides specific processing capabilities for different model deployments, allowing the online service mechanism to possess both the universality of multi-model deployment and the diversity of customized development for multi-model deployment, enhancing the adaptability and flexibility of the online service.

[0044] The technical solution of this embodiment involves receiving a model call request, wherein the model call request carries model-related data; converting the model-related data into a predetermined composite data structure; wherein the predetermined composite data structure is a composite data structure composed of a list and a set of key-value pairs; parsing the predetermined composite data structure; and obtaining the target machine learning model based on the parsing result. The data processing method provided by this embodiment converts the model-related data in the model call request into a predetermined composite data structure for parsing, thereby realizing the processing of target data, avoiding multiple developments for deploying machine learning model services, shortening the development cycle, and improving the convenience of data processing.

[0045] Example 2

[0046] Figure 2 This is a schematic diagram of the structure of a data processing device provided in Embodiment 2 of the present invention, as shown below. Figure 2 As shown, the device includes:

[0047] The model call request receiving module 210 is used to receive model call requests; wherein, the model call request carries model-related data;

[0048] The data transformation module 220 is used to transform model-related data into a defined composite data structure; wherein the defined composite data structure is a composite data structure consisting of a list and a set of key-value pairs.

[0049] Data parsing module 230 is used to parse a given composite data structure and output the parsing results.

[0050] The target machine learning model acquisition module 240 is used to acquire the target machine learning model based on the parsing results.

[0051] Optionally, model-related data includes model type, model file access identifier, model file packaging format, and model input parameters.

[0052] Optionally, the data conversion module 220 is also used for:

[0053] Convert the model type into a first key-value pair;

[0054] Transform the data file access model into a second key-value pair;

[0055] Convert the model file's packaging format into third-party key-value pairs;

[0056] The input parameters of the model are transformed into fourth key-value pairs; where the values ​​in the fourth key-value pairs are lists consisting of at least one set of key-value pairs.

[0057] The model-related data is transformed into a total key-value pair; where the value in the total key-value pair is a list consisting of the first key-value pair, the second key-value pair, the third key-value pair, and the fourth key-value pair.

[0058] Optionally, the data parsing module 230 is also used for:

[0059] Transform the text formatting of the complex data structure into a complex data structure in the target computer language;

[0060] The parsing logic of the target computer language is used to parse the composite data structure and obtain the parsing result.

[0061] Optionally, the target machine learning model acquisition module 240 is also used for:

[0062] The target machine learning model is retrieved from the model database based on the model type, model file access identifier, and model file packaging format.

[0063] Optionally, it also includes: a model preloading module, used for:

[0064] Preload the target machine learning model into the designated memory.

[0065] Optionally, it also includes: a model input parameter processing module, used for:

[0066] The input parameters of the model are processed into parameters of a first set format; wherein, the first set format is a data format that the target machine learning model can recognize;

[0067] Input the parameters in the specified format into the preloaded target machine learning model to obtain the calculation results.

[0068] Optionally, it also includes: a calculation result processing module, used for:

[0069] The calculation results are processed into data in a second predefined format; wherein the second predefined format is a format that can be recognized by the model caller;

[0070] Return the data in the second specified format to the model caller.

[0071] Optionally, it also includes a configuration module for configuring the model's preloading information, input parameter processing information, and calculation result processing information.

[0072] The above-described apparatus can execute the methods provided in all the foregoing embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the above methods. Technical details not described in detail in this embodiment can be found in the methods provided in all the foregoing embodiments of the present invention.

[0073] Example 3

[0074] Figure 3 This is a schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention. Figure 3 A block diagram of a computer device 312 suitable for implementing embodiments of the present invention is shown. Figure 3 The computer device 312 shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention. Device 312 is a typical computing device with data processing capabilities.

[0075] like Figure 3 As shown, the computer device 312 is presented in the form of a general-purpose computing device. The components of the computer device 312 may include, but are not limited to: one or more processors 316, a storage device 328, and a bus 318 connecting different system components (including the storage device 328 and the processor 316).

[0076] Bus 318 represents one or more of several bus architectures, including memory buses or memory controllers, peripheral buses, graphics acceleration ports, processors, or local buses using any of the various bus architectures. Examples of these architectures include, but are not limited to, Industry Standard Architecture (ISA) buses, Micro Channel Architecture (MCA) buses, Enhanced ISA buses, Video Electronics Standards Association (VESA) local buses, and Peripheral Component Interconnect (PCI) buses.

[0077] Computer device 312 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 312, including volatile and non-volatile media, removable and non-removable media.

[0078] Storage device 328 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 330 and / or cache memory 332. Computer device 312 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 334 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 3 Not shown; usually referred to as a "hard drive"). Although Figure 3 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disc drive for reading and writing to a removable non-volatile optical disc (e.g., a Compact Disc-Read Only Memory (CD-ROM), a Digital Video Disc-Read Only Memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 318 via one or more data media interfaces. Storage device 328 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0079] A program 336 having a set (at least one) of program modules 326 may be stored in, for example, a storage device 328. Such program modules 326 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 326 typically perform the functions and / or methods described in the embodiments of the present invention.

[0080] Computer device 312 can also communicate with one or more external devices 314 (e.g., keyboard, pointing device, camera, display 324, etc.), and with one or more devices that enable a user to interact with the computer device 312, and / or with any device that enables the computer device 312 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 322. Furthermore, computer device 312 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN)) and / or public networks, such as the Internet) via network adapter 320. As shown, network adapter 320 communicates with other modules of computer device 312 via bus 318. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with computer device 312, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, Redundant Arrays of Independent Disks (RAID) systems, tape drives, and data backup storage systems.

[0081] The processor 316 executes various functional applications and data processing by running programs stored in the storage device 328, such as implementing the data processing method provided in the above embodiments of the present invention.

[0082] Example 4

[0083] This invention provides a computer-readable storage medium storing a computer program that, when executed by a processing device, implements the data processing method described in this invention. The computer-readable medium described above can be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. For example, a computer-readable storage medium can be—but is not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0084] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0085] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0086] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: receive a model invocation request; wherein the model invocation request carries model-related data; convert the model-related data into a predetermined composite data structure; wherein the predetermined composite data structure is a composite data structure composed of a list and a set of key-value pairs; parse the predetermined composite data structure, and obtain the parsing result; and obtain a target machine learning model based on the parsing result.

[0087] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0088] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0089] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0090] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0091] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0092] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A data processing method, characterized by, The method comprises the following steps: receiving a model calling request; wherein the model calling request carries model related data, the model related data comprising a model type, a model file access identifier, a model file packaging format and model input parameters; the model type is used to identify a machine learning model, the model file access identifier is used to identify a model to be accessed, the model file packaging format is used to represent the packaging and parsing format of a file, and the model input parameters record the feature information of an input model; converting the model related data into a set composite data structure; wherein the set composite data structure is a composite data structure composed of a list and a key-value pair set; analyzing the set composite data structure to obtain an analysis result; wherein the analysis result comprises the model type, the model file access identifier and the model file packaging format; based on the analysis result, obtaining a target machine learning model from a model database; wherein the model database stores a plurality of developed machine learning models.

2. The method of claim 1, wherein, The step of converting the model related data into a set composite data structure comprises: converting the model type into a first key-value pair; converting the data file access identifier into a second key-value pair; converting the model file packaging format into a third key-value pair; converting the model input parameters into a fourth key-value pair; wherein the value in the fourth key-value pair is a list composed of at least one key-value pair set; converting the model related data into a total key-value pair; wherein the value in the total key-value pair is a list composed of the first key-value pair, the second key-value pair, the third key-value pair and the fourth key-value pair.

3. The method of claim 1, wherein, The step of analyzing the set composite data structure comprises: converting the set composite data structure in text format into a composite data structure in a target computer language; using the analysis logic of the target computer language to analyze the composite data structure to obtain an analysis result.

4. The method of claim 1, wherein, The step of obtaining a target machine learning model based on the analysis result comprises: obtaining a target machine learning model from a model database according to the model type, the model file access identifier and the model file packaging format.

5. The method of claim 4, wherein, After obtaining the target machine learning model based on the analysis result, the method further comprises: preloading the target machine learning model into a set memory.

6. The method of claim 5, wherein, After preloading the target machine learning model into the set memory, the method further comprises: processing the model input parameters into parameters in a first set format; wherein the first set format is a data format recognizable by the target machine learning model; inputting the parameters in the set format into the preloaded target machine learning model to obtain a calculation result.

7. The method of claim 6, wherein, After obtaining the calculation result, the method further comprises: processing the calculation result into data in a second set format; wherein the second set format is a format recognizable by a model calling party; returning the data in the second set format to the model calling party.

8. The method of claim 7, wherein, The method further comprises: configuring preloading information of the model, input parameter processing information and calculation result processing information.

9. A data processing apparatus, characterized by, The method comprises the following steps: The model calling request receiving module is configured to receive a model calling request, wherein the model calling request carries model related data, and the model related data includes a model type, a model file access identifier, a model file packaging format, and model input parameters; the model type is used to identify a machine learning model, the model file access identifier is used to identify a model to be accessed, the model file packaging format is used to represent a file packaging and parsing format, and the model input parameters record feature information of an input model; The data conversion module is configured to convert the model related data into a set composite data structure; wherein the set composite data structure is a composite data structure composed of a list and a key-value pair set; The data analysis module is configured to analyze the set composite data structure to obtain an analysis result; wherein the analysis result includes the model type, the model file access identifier, and the model file packaging format; The target machine learning model obtaining module is configured to obtain a target machine learning model from a model database based on the analysis result; wherein the model database stores a plurality of developed machine learning models.

10. The apparatus of claim 9, wherein, The data conversion module is further configured to: convert the model type into a first key-value pair; convert the data file access model into a second key-value pair; convert the model file packaging format into a third key-value pair; convert the model input parameters into a fourth key-value pair; wherein the value in the fourth key-value pair is a list composed of at least one key-value pair set; convert the model related data into a total key-value pair; wherein the value in the total key-value pair is a list composed of the first key-value pair, the second key-value pair, the third key-value pair, and the fourth key-value pair.

11. The apparatus of claim 9, wherein, The data analysis module is further configured to: convert the set composite data structure in a text format into a composite data structure in a target computer language; analyze the composite data structure using an analysis logic in the target computer language to obtain an analysis result.

12. A computer device, comprising: The device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the data processing method of any one of claims 1-8 when executing the program.

13. A computer readable storage medium having stored thereon a computer program, characterized in that The program is executed by the processing device to implement the data processing method of any one of claims 1-8.

Images