Data processing method and device, electronic equipment and readable storage medium

Abstract

The invention discloses a data processing method and device, electronic equipment and a readable storage medium, and the method comprises the steps: processing feedback information of a user input service based on a hybrid expert system, and determining first expert model information corresponding to the user input service, and a processing result of the hybrid expert system for the user input service; wherein the first expert model information at least comprises the number of first expert models; determining second expert model information of a target service type corresponding to the user input service based on the feedback information, the user input service, the first expert model information and the processing result; the second expert model information at least comprises the number of second expert models; the number of the second expert models is smaller than that of the first expert models; and storing the second expert model information of the target service type, so as to adjust a target expert model when the mixed expert system processes the service corresponding to the target service type based on the second expert model information of the target service type.

Description

Technical Field

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

[0002] As the capabilities of hybrid expert systems grow, the number of parameters in hybrid expert systems increases. Currently, when fine-tuning the parameters of hybrid expert systems, the hybrid expert systems need to be retrained, which requires huge resources and is inconvenient for real-time fine-tuning. Summary of the invention

[0003] In view of this, embodiments of the present application provide a data processing method, device, electronic device, and readable storage medium.

[0004] According to the first aspect of the present application, an embodiment of the present application provides a data processing method, including:

[0005] Based on the feedback information of the hybrid expert system processing the user input business, determine the first expert model information corresponding to the user input business and the processing result of the hybrid expert system on the user input business; wherein the first expert model information at least includes the number of first expert models;

[0006] Based on the feedback information, the user input service, the first expert model information and the processing result, determine the second expert model information of the target service type corresponding to the user input service; the second expert model information at least includes the number of second expert models; the number of the second expert models is less than the number of the first expert models;

[0007] The second expert model information of the target business type is saved, so as to adjust the target expert model when the hybrid expert system processes the business corresponding to the target business type based on the second expert model information of the target business type.

[0008] Optionally, determining second expert model information of a target service type corresponding to the user input service based on the feedback information, the user input service, the first expert model information and the processing result includes:

[0009] The parameter configuration model is used to process the feedback information, the user input service, the first expert model information and the processing result to obtain the second expert model information of the target service type corresponding to the user input service.

[0010] Optionally, the parameter configuration model is obtained by online reinforcement learning.

[0011] Optionally, based on the second expert model information of the target business type, adjusting the target expert model when the hybrid expert system processes the business corresponding to the target business type includes:

[0012] Obtain the business corresponding to the target business type;

[0013] The target business type corresponding business and the second expert model information of the target business type are input into the hybrid expert system, so that when the hybrid expert system processes the target business type corresponding business, the target expert model is adjusted based on the second expert model information.

[0014] Optionally, before inputting the service corresponding to the target service type and the second expert model information of the target service type into the hybrid expert system, the data processing method further includes:

[0015] Based on the target business type, second expert model information corresponding to the target business type is found from a comparison table of business types and expert model information.

[0016] Optionally, before determining the first expert model information corresponding to the user input service and the processing result of the user input service by the hybrid expert system based on the feedback information of the hybrid expert system processing the user input service, the data processing method further includes:

[0017] The satisfaction survey information on the processing result of the hybrid expert system in processing the user input business is displayed to the user.

[0018] Optionally, the data processing method further includes:

[0019] Based on the second expert model information of the target business type, the third expert model information corresponding to the target business type in the hybrid expert system is updated.

[0020] According to the second aspect of the present application, an embodiment of the present application provides a large model parameter adjustment device, including:

[0021] An acquisition module, configured to determine first expert model information corresponding to the user input service and a processing result of the user input service by the hybrid expert system based on feedback information of the user input service processed by the hybrid expert system; wherein the first expert model information at least includes the number of first expert models;

[0022] A determination module, configured to determine, based on the feedback information, the user input service, the first expert model information, and the processing result, second expert model information of the target service type corresponding to the user input service; the second expert model information at least includes the number of second expert models; the number of the second expert models is less than the number of the first expert models;

[0023] The saving module is used to save the second expert model information of the target business type, so as to adjust the target expert model when the hybrid expert system processes the business corresponding to the target business type based on the second expert model information of the target business type.

[0024] According to a third aspect of the present application, an embodiment of the present application provides an electronic device, including:

[0025] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the data processing method as in the first aspect or any embodiment of the first aspect.

[0026] According to the fourth aspect of the present application, an embodiment of the present application provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute a data processing method as in the first aspect or any embodiment of the first aspect.

[0027] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A flowchart of a data processing method in an embodiment of the present application;

[0029] Figure 2 This is a schematic diagram of the structure of a data processing device in an embodiment of the present application;

[0030] Figure 3 This is a schematic diagram of the hardware structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0032] The present application embodiment provides a data processing method, such as Figure 1 As shown, including:

[0033] S101, based on feedback information of the hybrid expert system processing the user input service, determine first expert model information corresponding to the user input service and the processing result of the hybrid expert system on the user input service; wherein the first expert model information at least includes the first expert model quantity.

[0034] In this embodiment, the Mixture of experts (MoE) is a neural network and also a mixed model. The hybrid expert system is different from the general neural network. It can train multiple models based on data separation. Each model is called an expert model. The hybrid expert system can integrate multiple expert models into a single user input service.

[0035] In this embodiment, each time feedback information is obtained when the hybrid expert system processes user input business, the expert model information of the hybrid expert system when processing the user input business corresponding to the target business type business can be triggered to be adjusted, so that when feedback information is obtained when the hybrid expert system processes the user input business, the first expert model information corresponding to the user input business and the processing result of the user input business by the hybrid expert system can be determined.

[0036] In this embodiment, the feedback information may include suggestion information, evaluation information, satisfaction information, scoring information, etc. input by the user regarding the processing result of the hybrid expert system.

[0037] In some embodiments, a comparison table of business types and expert model information in the hybrid expert system can be maintained, so that the business type can be determined based on the user input business, and then the first expert model information corresponding to the user input business can be found from the comparison table of business types and expert model information.

[0038] In some embodiments, the first expert model information may include a first expert model quantity and a first expert model corresponding to the first expert model quantity.

[0039] S102, based on the feedback information, the user input service, the first expert model information and the processing result, determine the second expert model information of the target service type corresponding to the user input service; the second expert model information at least includes the number of second expert models; the number of second expert models is less than the number of first expert models.

[0040] In this embodiment, the second expert model information may include the number of second expert models and the second expert models corresponding to the number of second expert models.

[0041] In this embodiment, the service input by the user is a specific task in the target service type. For example, the target service type is the English-Chinese translation service type, and the service input by the user is "translate table into Chinese".

[0042] In this embodiment, by analyzing the feedback information, the user input service, the first expert model information, and the processing results, it can be determined whether the number of first expert models and the first expert model specified in the first expert model information can meet the requirements of completing the user input service better and / or faster, thereby determining the second expert model information. For example, by analyzing the feedback information, the user input service, the first expert model information, and the processing results, it can be determined that the number of first expert models specified in the first expert model information cannot complete the user input service better and / or faster, thereby determining that the type and number of expert models should be adjusted, and the number of expert models can be reduced from m expert models to n expert models, where m is the number of first expert models, n is the number of second expert models, and n is less than m. For another example, by analyzing the feedback information, user input services, the first expert model information and the processing results, it can be determined that the number of first expert models specified in the first expert model information and the first expert model cannot complete the user input services better and / or faster, thereby determining that the type and number of expert models should be adjusted, the number of expert models can be reduced from m expert models to n expert models, and the type of expert model can be adjusted from the first expert model to the second expert model, where m is the number of first expert models, n is the number of second expert models, and n is less than m.

[0043] In some embodiments, by analyzing user feedback information, user satisfaction information on the processing results can be obtained, such as whether the user input service is completed better and / or faster. By analyzing the user input service and the processing results, the accuracy information of the processing results can be determined. By analyzing the user satisfaction information on the processing results and the accuracy information of the processing results, the user's habit information can be determined; by analyzing the user's habit information and the first expert model information, the range of the first expert model quantity to be adjusted can be determined, and whether the first expert model needs to be adjusted to the second expert model, thereby determining the second expert model information.

[0044] S103, saving the second expert model information of the target business type, so as to adjust the target expert model when the hybrid expert system processes the business corresponding to the target business type based on the second expert model information of the target business type.

[0045] In this embodiment, after determining the second expert model information of the target business type, the second expert model information of the target business type can be saved. Therefore, when the user initiates a specific business of the target business type again, the saved second expert model information of the target business type can be input into the hybrid expert system together, so that when the hybrid expert system processes the business corresponding to the target business type, the target expert model is adjusted based on the second expert model information; or the saved second expert model information of the target business type is used to adjust the target parameters in the hybrid expert system, and the target parameters include the number of target expert models and / or target expert models when processing the business corresponding to the target business type, so as to adjust the target expert model when the hybrid expert system processes the business corresponding to the target business type.

[0046] In specific implementation, if a comparison table of business types and expert model information in the hybrid expert system is maintained, the second expert model information can replace the first expert model information in the comparison table to achieve the purpose of saving the second expert model information and keep the comparison table updated in real time.

[0047] The data processing method provided in the embodiment of the present application determines the first expert model information corresponding to the user input business and the processing result of the user input business by the hybrid expert system based on the feedback information of the user input business; wherein the first expert model information at least includes the number of first expert models; based on the feedback information, the user input business, the first expert model information and the processing result, determines the second expert model information of the target business type corresponding to the user input business; the second expert model information at least includes the number of second expert models; the number of second expert models is less than the number of first expert models; the second expert model information of the target business type is saved, so as to adjust the target expert model when the hybrid expert system processes the business corresponding to the target business type based on the second expert model information of the target business type; in this way, the expert model information of the hybrid expert system for processing the task can be adjusted in real time according to the user's feedback to achieve the optimal number of expert models that meet the task, and there is no need to retrain the hybrid expert system, which can greatly reduce the computing resources and time for fine-tuning the parameters of the hybrid expert system.

[0048] In an optional embodiment, step S102, based on the feedback information, the user input service, the first expert model information and the processing result, determines the second expert model information of the target service type corresponding to the user input service, including:

[0049] The parameter configuration model is used to process the feedback information, the user input service, the first expert model information and the processing result to obtain the second expert model information of the target service type corresponding to the user input service.

[0050] In this embodiment, the parameter configuration model is a model with a parameter amount far smaller than that of the hybrid expert system.

[0051] In this embodiment, the neural network can be trained through historical data to obtain a parameter configuration model. The historical data may include historical feedback information, historical user input services, historical first expert model information, and historical processing results.

[0052] In this embodiment, the parameter configuration model may also be trained by online reinforcement learning.

[0053] In this embodiment, the second expert model information of the target service type corresponding to the user input service is determined by configuring the model with parameters, so that the second expert model information of the target service type corresponding to the user input service can be obtained quickly and accurately.

[0054] In an optional embodiment, the parameter configuration model is obtained by online reinforcement learning. In this way, since the parameter configuration model needs to be trained based on user feedback information, and the user feedback information is updated in real time, the parameter configuration model can be trained by online reinforcement learning, so that the parameter configuration model can be updated in real time, thereby obtaining more accurate second expert model information.

[0055] In an optional embodiment, in step S103, based on the second expert model information of the target business type, adjusting the target expert model when the hybrid expert system processes the business corresponding to the target business type includes:

[0056] Obtain the business corresponding to the target business type; input the business corresponding to the target business type and the second expert model information of the target business type into the hybrid expert system, so that when the hybrid expert system processes the business corresponding to the target business type, the target expert model is adjusted based on the second expert model information.

[0057] In this embodiment, since the second expert model information of the target business type is saved, when the user initiates a specific business of the target business type again, the second expert model information of the target business type can be used to obtain the second expert model information of the hybrid expert system when processing the specific business. The specific business and the corresponding second expert model information are then input into the hybrid expert system, so that the hybrid expert system selects the corresponding expert model to process the specific business based on the second expert model information, so that the hybrid expert system adjusts the target expert model when processing the business corresponding to the target business type.

[0058] In an embodiment of the present application, the business corresponding to the target business type and the second expert model information corresponding to the target business type are input into the hybrid expert system together, so that when the hybrid expert system processes the business corresponding to the target business type, the target expert model is adjusted based on the second expert model information. In this way, there is no need to adjust the original parameters in the hybrid expert system in real time. When the hybrid expert system processes the business corresponding to the target business type, the expert model can still be selected according to the second expert model information corresponding to the target business type.

[0059] In an optional embodiment, before inputting the service corresponding to the target service type and the second expert model information of the target service type into the hybrid expert system, the data processing method further includes:

[0060] Based on the target business type, second expert model information corresponding to the target business type is found from a comparison table of business types and expert model information.

[0061] In this embodiment, outside the hybrid expert system, a comparison table of business types and expert model information is maintained, so that after obtaining the business corresponding to the target business type, the second expert model information corresponding to the target business type can be found from the comparison table of business types and expert model information based on the target business type.

[0062] In this embodiment, a comparison table between business types and expert model information is maintained, thereby facilitating searching for the second expert model information corresponding to the target business type.

[0063] In an optional embodiment, before determining the first expert model information corresponding to the user input service and the processing result of the user input service by the hybrid expert system based on the feedback information of the user input service processed by the hybrid expert system in step S101, the data processing method further includes:

[0064] The satisfaction survey information on the processing result of the hybrid expert system in processing the user input business is displayed to the user.

[0065] In this embodiment, when the hybrid expert system processes the user input service and obtains the processing result, the processing result can be fed back to the user, and at the same time or after the processing result is fed back to the user, the satisfaction survey information on the processing result of the hybrid expert system processing the user input service can be displayed to the user. The satisfaction survey information indicates whether the user is satisfied with the processing result, as well as improvement information, suggestion information, etc.

[0066] In this embodiment, by displaying satisfaction survey information on the processing results of the hybrid expert system processing user input services to the user, it is possible to adjust the expert model information when the hybrid expert system processes services in real time based on user feedback.

[0067] In an optional embodiment, after saving the second expert model information of the target business type in step S103, the data processing method further includes:

[0068] Based on the second expert model information of the target business type, the third expert model information corresponding to the target business type in the hybrid expert system is updated.

[0069] In this embodiment, after determining the second expert model information of the target business type, the second expert model information of the target business type can directly replace the third expert model information corresponding to the target business type in the hybrid expert system, thereby achieving real-time adjustment of parameters in the hybrid expert system.

[0070] The present application also provides a large model parameter adjustment device, such as Figure 2 As shown, including:

[0071] The acquisition module 21 is used to determine the first expert model information corresponding to the user input business and the processing result of the user input business by the hybrid expert system based on the feedback information of the hybrid expert system processing the user input business; wherein the first expert model information at least includes the first expert model quantity.

[0072] The determination module 22 is used to determine the second expert model information of the target business type corresponding to the user input business based on the feedback information, the user input business, the first expert model information and the processing result; the second expert model information at least includes the number of second expert models; the number of second expert models is less than the number of first expert models.

[0073] The saving module 23 is used to save the second expert model information of the target business type, so as to adjust the target expert model when the hybrid expert system processes the business corresponding to the target business type based on the second expert model information of the target business type.

[0074] The data processing device provided in the embodiment of the present application determines the first expert model information corresponding to the user input business and the processing result of the user input business by the hybrid expert system based on the feedback information of the user input business processed by the hybrid expert system; wherein the first expert model information at least includes the number of first expert models; based on the feedback information, the user input business, the first expert model information and the processing result, determines the second expert model information of the target business type corresponding to the user input business; the second expert model information at least includes the number of second expert models; the number of second expert models is less than the number of first expert models; the second expert model information of the target business type is saved, so as to adjust the target expert model when the hybrid expert system processes the business corresponding to the target business type based on the second expert model information of the target business type; in this way, the expert model information of the hybrid expert system for processing the task can be adjusted in real time according to the user's feedback to achieve the optimal number of expert models that meet the task, and there is no need to retrain the hybrid expert system, which can greatly reduce the computing resources and time for fine-tuning the parameters of the hybrid expert system.

[0075] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0076] Figure 3 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0077] like Figure 3 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0078] Multiple components in the electronic device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0079] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as data processing methods. For example, in some embodiments, the data processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the data processing method in any other appropriate manner (e.g., by means of firmware).

[0080] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0081] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0082] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0083] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0084] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0085] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0086] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0087] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0088] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A data processing method, comprising: Based on feedback information of the hybrid expert system processing the user input service, determine first expert model information corresponding to the user input service and a processing result of the hybrid expert system on the user input service; wherein the first expert model information at least includes the number of first expert models; Determine, based on the feedback information, the user input service, the first expert model information and the processing result, second expert model information of a target service type corresponding to the user input service; the second expert model information at least includes a second expert model quantity; the second expert model quantity is less than the first expert model quantity; The second expert model information of the target business type is saved, so as to adjust the target expert model when the hybrid expert system processes the business corresponding to the target business type based on the second expert model information of the target business type.

2. The data processing method according to claim 1, determining second expert model information of a target business type corresponding to the user input business based on the feedback information, the user input business, the first expert model information and the processing result, comprising: The feedback information, the user input service, the first expert model information and the processing result are processed using a parameter configuration model to obtain second expert model information of a target service type corresponding to the user input service.

3. According to the data processing method of claim 2, the parameter configuration model is obtained by online reinforcement learning.

4. The data processing method according to claim 1, based on the second expert model information of the target business type, adjusting the target expert model when the hybrid expert system processes the business corresponding to the target business type, comprising: Obtain the business corresponding to the target business type; The target business type corresponding business and the second expert model information of the target business type are input into the hybrid expert system, so that when the hybrid expert system processes the target business type corresponding business, the target expert model is adjusted based on the second expert model information.

5. The data processing method according to claim 4, before inputting the target business type corresponding business and the second expert model information of the target business type into the hybrid expert system, further comprising: Based on the target service type, second expert model information corresponding to the target service type is found from a comparison table of service types and expert model information.

6. The data processing method according to claim 1, before determining the first expert model information corresponding to the user input service and the processing result of the user input service by the hybrid expert system based on the feedback information of the hybrid expert system, further comprising: The satisfaction survey information on the processing result of the hybrid expert system in processing the user input business is displayed to the user.

7. The data processing method according to claim 1, further comprising: Based on the second expert model information of the target business type, the third expert model information corresponding to the target business type in the hybrid expert system is updated.

8. A large model parameter adjustment device, comprising: An acquisition module, configured to determine, based on feedback information of the hybrid expert system processing the user input service, first expert model information corresponding to the user input service and a processing result of the hybrid expert system on the user input service; wherein the first expert model information at least includes the number of first expert models; a determination module, configured to determine, based on the feedback information, the user input service, the first expert model information, and the processing result, second expert model information of a target service type corresponding to the user input service; the second expert model information at least includes a second expert model quantity; the second expert model quantity is less than the first expert model quantity; The saving module is used to save the second expert model information of the target business type, so as to adjust the target expert model when the hybrid expert system processes the business corresponding to the target business type based on the second expert model information of the target business type.

9. An electronic device, comprising: at least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the data processing method as described in any one of claims 1-7.

10. A computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the data processing method according to any one of claims 1 to 7.

Images