Task processing method, automatic question answering method, and task processing system

Abstract

A task processing method, an automatic question answering method, and a task processing system. The task processing method comprises: receiving a task processing request, wherein the task processing request carries data to be processed (502); screening, from among a plurality of candidate model parameters, a target model parameter corresponding to a target requester, wherein the candidate model parameters are obtained by training a pre-training processing model on the basis of sample sets specified by requesters, and the requesters corresponding to the candidate model parameters are different (504); on the basis of the target model parameter and a shared model parameter, constructing a task processing model, wherein the shared model parameter is a model parameter shared by the requesters in the pre-training processing model, and in the process of training the pre-training processing model, the shared model parameter is fixed (506); and inputting said data into the task processing model to obtain a task processing result (508). A task processing model does not need to be separately provided for each requester, thereby reducing the model deployment cost and the task processing resource consumption.

Description

Task processing method, automatic question answering method, and task processing system

[0001] Cross-reference

[0002] This disclosure claims priority to the Chinese patent application filed with the China Patent Office on September 19, 2023, with application number 202311213755.5 and invention name “Task processing method, automatic question-answering method and task processing system”, the entire contents of which are incorporated by reference into this disclosure. Technical Field

[0003] The present disclosure relates to the field of computer technology, and more particularly to a task processing method, an automatic question-answering method, and a task processing system. One or more embodiments of the present disclosure also relate to a task processing apparatus, an automatic question-answering apparatus, a computing device, a computer-readable storage medium, and a computer program. Background Art

[0004] With the development of computer technology, large models have begun to shine. Their remarkable capabilities in language understanding, generation, interaction, and reasoning have led to their widespread application in natural language processing, including dialogue, translation, and code generation. However, due to the enormous number of parameters in large models and the diverse needs of different enterprises, providing personalized model services to these vast numbers of enterprises has become a research priority.

[0005] Currently, enterprise-specific large models are typically trained through supervised fine-tuning: During the training process, all parameters of the large model are adjusted according to the enterprise's needs to achieve personalized training. However, due to the large number of large model parameters in this approach, and the deployment of a separate, dedicated large model for each enterprise, N enterprises will correspond to N large models, resulting in huge deployment and storage costs, resulting in a huge resource consumption. Therefore, a task processing solution with low resource consumption is urgently needed.

[0006] Summary of the Invention

[0007] In view of this, embodiments of the present disclosure provide a task processing method. One or more embodiments of the present disclosure also relate to an automatic question-answering method, a task processing system, a task processing apparatus, an automatic question-answering apparatus, a computing device, a computer-readable storage medium, and a computer program to address technical deficiencies in the prior art.

[0008] According to a first aspect of an embodiment of the present disclosure, there is provided a task processing method, comprising:

[0009] receiving a task processing request, wherein the task processing request carries data to be processed;

[0010] Filtering target model parameters corresponding to a target requester from a plurality of candidate model parameters, wherein the target requester is the object that sends the task processing request, and the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester;

[0011] Construct a task processing model based on the target model parameters and the shared model parameters, where the shared model parameters are model parameters shared by all requesting parties in the pre-trained processing model. During the training of the pre-trained processing model, the shared model parameters remain fixed.

[0012] Input the data to be processed into the task processing model to obtain the task processing results.

[0013] According to a second aspect of an embodiment of the present disclosure, there is provided an automatic question-answering method, comprising:

[0014] receiving a question handling request, wherein the question handling request carries data to be answered;

[0015] Filtering target model parameters corresponding to a target requester from a plurality of candidate model parameters, wherein the target requester is the object that sends the problem processing request, and the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester;

[0016] Construct a task processing model based on the target model parameters and the shared model parameters, where the shared model parameters are model parameters shared by all requesting parties in the pre-trained processing model. During the training of the pre-trained processing model, the shared model parameters remain fixed.

[0017] Input the data to be answered into the task processing model to obtain the answer to the question.

[0018] According to a third aspect of an embodiment of the present disclosure, there is provided a task processing system, comprising a service component and a candidate parameter storage component;

[0019] A candidate parameter storage component, used to store multiple candidate model parameters;

[0020] A service component is used to receive a task processing request, wherein the task processing request carries data to be processed; select target model parameters corresponding to a target requester from a plurality of candidate model parameters, wherein the target requester is the object sending the task processing request, and the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester; construct a task processing model based on the target model parameters and shared model parameters, wherein the shared model parameters are model parameters shared by each requester in the pre-trained processing model, and during the training of the pre-trained processing model, the shared model parameters remain fixed; input the data to be processed into the task processing model to obtain a task processing result.

[0021] According to a fourth aspect of an embodiment of the present disclosure, there is provided a task processing device, including:

[0022] A first receiving component is configured to receive a task processing request, wherein the task processing request carries data to be processed;

[0023] a first screening component configured to screen target model parameters corresponding to a target requester from a plurality of candidate model parameters, wherein the target requester is an object that sends a task processing request, the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester;

[0024] a first construction component configured to construct a task processing model based on target model parameters and shared model parameters, wherein the shared model parameters are model parameters shared by requesting parties in a pre-trained processing model, and the shared model parameters remain fixed during the training of the pre-trained processing model;

[0025] The first input component is configured to input the data to be processed into the task processing model to obtain the task processing result.

[0026] According to a fifth aspect of an embodiment of the present disclosure, there is provided an automatic question-answering device, comprising:

[0027] A second receiving component is configured to receive a question processing request, wherein the question processing request carries data to be answered;

[0028] a second screening component configured to screen target model parameters corresponding to a target requester from a plurality of candidate model parameters, wherein the target requester is an object that sends a problem processing request, the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester;

[0029] a second construction component configured to construct a task processing model based on the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by the requesting parties in the pre-trained processing model, and the shared model parameters remain fixed during the training of the pre-trained processing model;

[0030] The second input component is configured to input the data to be answered into the task processing model to obtain the question answering result.

[0031] According to a sixth aspect of an embodiment of the present disclosure, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of the method described in any one of the first to second aspects above.

[0032] According to a seventh aspect of an embodiment of the present disclosure, a computer program product is provided, comprising a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in any one of the first to second aspects above are implemented.

[0033] According to an eighth aspect of an embodiment of the present disclosure, a computer program is provided, which, when executed by a processor, implements the steps of the method described in any one of the first to second aspects above.

[0034] According to a ninth aspect of an embodiment of the present disclosure, there is provided a computing device, including:

[0035] memory and processor;

[0036] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method provided in the first aspect or the second aspect are implemented.

[0037] According to a tenth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, which stores computer-executable instructions. When the instructions are executed by a processor, the steps of the method provided in the first aspect or the second aspect are implemented.

[0038] An embodiment of the present disclosure provides a task processing method, which receives a task processing request, wherein the task processing request carries data to be processed; selects target model parameters corresponding to a target requester from multiple candidate model parameters, wherein the target requester is the object sending the task processing request, and the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester; constructs a task processing model based on the target model parameters and shared model parameters, wherein the shared model parameters are model parameters shared by each requester in the pre-trained processing model, and during the training of the pre-trained processing model, the shared model parameters remain fixed; inputs the data to be processed into the task processing model to obtain a task processing result. In the process of training the pre-trained processing model using sample sets specified by different requesters, the shared model parameters in the fixed pre-trained processing model remain unchanged, thereby efficiently obtaining the candidate model parameters corresponding to each requester, achieving the goal of using only one shared model parameter in combination with different candidate model parameters to serve different requesters, eliminating the need to provide a separate task processing model for each requester, and reducing model deployment costs and task processing resource consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] FIG1 is an architecture diagram of a task processing system provided by an embodiment of the present disclosure;

[0040] FIG2 is an architecture diagram of a first task processing system provided by an embodiment of the present disclosure;

[0041] FIG3 is an architecture diagram of a second task processing system provided by an embodiment of the present disclosure;

[0042] FIG4 is an architecture diagram of a third task processing system provided by an embodiment of the present disclosure;

[0043] FIG5 is a flowchart of a task processing method provided by an embodiment of the present disclosure;

[0044] FIG6 is a flow chart of an automatic question-answering method provided by an embodiment of the present disclosure;

[0045] FIG7 is a flowchart of a task processing method according to an embodiment of the present disclosure;

[0046] FIG8 is a schematic diagram of an automatic question-and-answer interface provided by an embodiment of the present disclosure;

[0047] FIG9 is a schematic structural diagram of a task processing device provided by an embodiment of the present disclosure;

[0048] FIG10 is a schematic structural diagram of an automatic question-answering device provided by an embodiment of the present disclosure;

[0049] FIG11 is a structural block diagram of a computing device provided by an embodiment of the present disclosure;

[0050] FIG12 is a schematic diagram showing the structure of a processor according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0051] The following description sets forth many specific details to facilitate a full understanding of the present disclosure. However, the present disclosure can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the scope of the present disclosure. Therefore, the present disclosure is not limited to the specific implementations disclosed below.

[0052] The terms used in one or more embodiments of the present disclosure are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of the present disclosure. The singular forms "a", "the", and "the" used in one or more embodiments of the present disclosure and the appended claims are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of the present disclosure refers to and includes any or all possible combinations of one or more associated listed items.

[0053] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of the present disclosure, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of one or more embodiments of the present disclosure, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0054] In addition, 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 one or more embodiments of the present disclosure 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 relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0055] In one or more embodiments of the present disclosure, a large model refers to a deep learning model with large-scale model parameters, which usually contains hundreds of millions, tens of billions, hundreds of billions, trillions, or even more than ten trillion model parameters. A large model can also be called a cornerstone model / foundation model (Foundation Model), which is pre-trained by using large-scale unlabeled corpus to produce a pre-trained model with more than 100 million parameters. This model can adapt to a wide range of downstream tasks, and the model has good generalization ability, such as a large-scale language model (LLM) and a multi-modal pre-training model.

[0056] When large models are used in practice, only a small number of samples are needed to fine-tune the pre-trained model and it can be applied to different tasks. Large models can be widely used in natural language processing (NLP), computer vision and other fields. Specifically, they can be applied to computer vision tasks such as visual question answering (VQA), image caption (IC), and image generation, as well as natural language processing tasks such as text-based sentiment classification, text summary generation, and machine translation. The main application scenarios of large models include digital assistants, intelligent robots, search, online education, office software, e-commerce, and intelligent design.

[0057] First, the terms involved in one or more embodiments of the present disclosure are explained.

[0058] Language model: The language model is an abstract mathematical model of language based on objective language facts and is an important direction in the field of natural language research.

[0059] With the development of computer technology, large models have begun to shine. Their remarkable capabilities in language understanding, generation, interaction, and reasoning have led to their widespread application in natural language processing, including dialogue, translation, and code generation. However, due to the enormous number of parameters in large models and the diverse needs of different enterprises, providing personalized model services to these vast numbers of enterprises has become a research priority.

[0060] At present, enterprise-specific large models are usually trained through supervised fine-tuning (SFT): during the large model training process, all parameters of the large model are adjusted according to the needs of the enterprise to achieve the purpose of personalized training model. However, in the above scheme, due to the large number of large model parameters, the training cost is very high. At the same time, in actual deployment, a separate exclusive large model is deployed for each enterprise, and N enterprises will correspond to the deployment and storage costs of N large models, resulting in huge resource consumption. Referring to Figure 1, Figure 1 is an architecture diagram of a task processing system provided by an embodiment of the present disclosure. As shown in Figure 1, the task processing system is a multi-enterprise multi-model task processing system. Enterprise A corresponds to task processing model A, enterprise B corresponds to task processing model B, enterprise C corresponds to task processing model C, and enterprise D corresponds to task processing model D.

[0061] In actual production, multiple large models need to be deployed for multiple enterprises, and the deployment cost is huge. The embodiment of the present disclosure proposes a training and deployment solution that calls the same large model base when deployed by enterprise users, supports the deployment of different enterprise models based on the unified large model base, and different enterprises only need to fine-tune the corresponding model parameters, thereby reducing the cost of model deployment. Referring to Figure 2, Figure 2 is an architectural diagram of the first task processing system provided by the embodiment of the present disclosure. As shown in Figure 2, the task processing system proposed by the embodiment of the present disclosure is a task processing system for multiple enterprises to uniformly share model parameters and multiple candidate model parameters. Enterprise A, Enterprise B, Enterprise C and Enterprise D share the shared model parameters of a pre-trained processing model. Each enterprise corresponds to different candidate model parameters. The candidate model parameters are obtained by training the pre-trained processing model based on the sample set specified by the enterprise. Specifically, Enterprise A corresponds to Candidate Model Parameter A, Enterprise B corresponds to Candidate Model Parameter B, Enterprise C corresponds to Candidate Model Parameter C, and Enterprise D corresponds to Candidate Model Parameter D.

[0062] Specifically, the disclosed embodiment proposes a task processing method, which includes receiving a task processing request, wherein the task processing request carries data to be processed; filtering out target model parameters corresponding to a target requester from a plurality of candidate model parameters, wherein the target requester is the object sending the task processing request, and the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester; constructing a task processing model based on the target model parameters and shared model parameters, wherein the shared model parameters are model parameters shared by each requester in the pre-trained processing model, and during the training of the pre-trained processing model, the shared model parameters remain fixed; inputting the data to be processed into the task processing model to obtain a task processing result. In the process of training the pre-trained processing model using sample sets specified by different requesters, the shared model parameters in the fixed pre-trained processing model remain unchanged, thereby efficiently obtaining the candidate model parameters corresponding to each requester, and realizing the use of only one shared model parameter in combination with different candidate model parameters to serve different requesters, without the need to provide a separate task processing model for each requester, thereby reducing the model deployment cost and the task processing resource consumption.

[0063] In the present disclosure, a task processing method is provided. The present disclosure also relates to an automatic question-answering method, a task processing system, a task processing device, an automatic question-answering device, a computing device, a computer-readable storage medium and a computer program, which are described in detail one by one in the following embodiments.

[0064] 3 , which is an architecture diagram of a second task processing system provided by an embodiment of the present disclosure, the task processing system may include a candidate parameter storage component 100 and a service component 200;

[0065] The candidate parameter storage component 100 is used to store multiple candidate model parameters;

[0066] The service component 200 is used to receive a task processing request, wherein the task processing request carries data to be processed; select target model parameters corresponding to a target requester from a plurality of candidate model parameters, wherein the target requester is the object sending the task processing request, and the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester; construct a task processing model based on the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by each requester in the pre-trained processing model, and during the training of the pre-trained processing model, the shared model parameters remain fixed; input the data to be processed into the task processing model to obtain a task processing result.

[0067] In the embodiment of the present disclosure, the task processing system further includes a shared parameter storage component 300 ; the shared parameter storage component 300 is used to store shared model parameters; and the service component 200 is further used to obtain shared model parameters from the shared parameter storage component 300 .

[0068] By applying the solution of the embodiments of the present disclosure, in the process of training the pre-training processing model using sample sets specified by different requesters, the shared model parameters in the fixed pre-training processing model remain unchanged, so that the candidate model parameters corresponding to each requester can be obtained efficiently, and only one shared model parameter is used in combination with different candidate model parameters to serve different requesters. There is no need to provide a separate task processing model for each requester, thereby reducing the model deployment cost and task processing resource consumption.

[0069] Referring to Figure 4, which is an architectural diagram of a third task processing system provided by an embodiment of the present disclosure, the task processing system may include multiple clients 400 and a service component 200. Multiple clients 400 may establish communication connections through the service component 200. In a task processing scenario, the service component 200 is used to provide task processing services between the multiple clients 400. The multiple clients 400 may act as senders or receivers, respectively, and communicate through the service component 200.

[0070] The target requester can interact with the service component 200 through the client 400 to receive data sent by other clients 400, or send data to other clients 400, etc. In the task processing scenario, the target requester can publish a data stream to the service component 200 through the client 400, and the service component 200 generates a task processing result based on the data stream and pushes the task processing result to other clients with which communication has been established.

[0071] The client 400 and the service component 200 are connected via a network. The network provides a medium for the communication link between the client 400 and the service component 200. The network can include various connection types, such as wired or wireless communication links or fiber optic cables. The data transmitted by the client 400 may need to be encoded, transcoded, compressed, etc. before being released to the service component 200.

[0072] The client 400 can be a browser, an application (APP), a web application such as a HyperText Markup Language 5 (H5) application, a light application (also known as a mini-program, a lightweight application), or a cloud application. The client 400 can be developed based on the software development kit (SDK) of the corresponding service provided by the service component 200, such as a real-time communication (RTC) SDK. The client 400 can be deployed in an electronic device and needs to rely on the device to run or certain apps in the device to run. For example, the electronic device can have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, etc. Various other types of applications can also be configured in the electronic device, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0073] The service component 200 may include servers that provide various services, such as servers that provide communication services to multiple clients, servers that support backend training for models used on clients, and servers that process data sent by clients. It should be noted that the service component 200 can be implemented as a distributed server cluster consisting of multiple servers or as a single server. The server can also be a server in a distributed system or a server integrated with a blockchain. The server can also be a cloud server for basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0074] It is worth noting that the task processing methods provided in the embodiments of the present disclosure are generally executed by the service component. However, in other embodiments of the present disclosure, the client may also have similar functions to the service component to execute the task processing methods provided in the embodiments of the present disclosure. In other embodiments, the task processing methods provided in the embodiments of the present disclosure may also be executed jointly by the client and the service component.

[0075] 5 , which is a flowchart of a task processing method provided by an embodiment of the present disclosure, specifically comprising the following steps:

[0076] Step 502: Receive a task processing request, wherein the task processing request carries data to be processed.

[0077] In one or more embodiments of the present disclosure, a task processing request may be received, and task processing may be performed based on the to-be-processed data carried in the task processing request to obtain a task processing result.

[0078] Specifically, the data to be processed is the object requested to be processed by the task processing request. The data to be processed can be data in different scenarios, such as data in conference scenarios, data in e-commerce scenarios, etc. The data to be processed can also be different types of data, such as text data, audio data, image data, etc.

[0079] In practical applications, there are multiple ways to receive task processing requests, and the specific method to be selected depends on the actual situation. The embodiments of the present disclosure do not impose any restrictions on this. In one possible implementation of the present disclosure, a task processing request sent by the target requester through the client can be received. In another possible implementation of the present disclosure, a task processing request sent by the client at a scheduled time can be received.

[0080] Step 504: Filter out target model parameters corresponding to the target requester from multiple candidate model parameters, wherein the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester.

[0081] In one or more embodiments of the present disclosure, after receiving a task processing request, a target model parameter corresponding to the target requester may be further screened from a plurality of candidate model parameters.

[0082] Specifically, the target requester refers to the object that sends the task processing request. The target requester can be an individual user or an enterprise user. The candidate model parameters are obtained by training the pre-training processing model based on the sample set specified by the requester, and the method for training the pre-training processing model can be parameter-efficient fine-tuning (PEFT). Parameter-efficient fine-tuning is a training technology that freezes most of the parameters in the pre-training processing model and only trains a small part of the parameters, while ensuring that the training effect is basically the same as the full training. That is, the candidate model parameters are obtained by training the pre-training processing model of the frozen shared model parameters based on the sample set specified by the requester. The method of efficient parameter fine-tuning includes but is not limited to LoRA, Adapter, P-tuning, prefix-tuning, etc. Preferably, in the embodiment of the present disclosure, the candidate model parameters can be obtained by training the pre-training processing model through the LoRA method, that is, by learning a low-rank matrix with small parameters to approximate the parameter update of the model weight matrix, and only optimize the low-rank matrix parameters during training.

[0083] Target model parameters are those obtained by training a pre-trained processing model based on a sample set specified by the target requester. A pre-trained processing model is a deep learning model. This can be obtained by training a large model with all its parameters based on the training set. Different candidate model parameters correspond to different requesters. For example, requester A corresponds to candidate model parameter A, requester B corresponds to candidate model parameter B, and requester C corresponds to candidate model parameter C.

[0084] It is worth noting that if the target model parameters corresponding to the target requester are not included in the multiple candidate model parameters, a sample set specified by the target requester can be obtained, and the pre-trained processing model can be trained using the sample set specified by the target requester to generate the target model parameters.

[0085] In actual applications, there are many ways to filter out the target model parameters corresponding to the target requester from multiple candidate model parameters. The specific selection is based on the actual situation, and the embodiments of the present disclosure do not impose any restrictions on this.

[0086] In one possible implementation of the present disclosure, a target model parameter corresponding to the target requester can be directly screened from multiple candidate model parameters based on the requester information of the target requester. For example, if the requester information of the target requester is number A, the requester information and the candidate model parameter number can be matched, and candidate model parameter A can be screened from candidate model parameter A, candidate model parameter B, and candidate model parameter C to be selected as the target model parameter.

[0087] In another possible implementation of the present disclosure, a parameter screening matrix may be generated based on the requester information of the target requester, and the parameter screening matrix may be further used to screen the target model parameters from the multiple candidate model parameters. That is, the above-mentioned screening of the target model parameters corresponding to the target requester from the multiple candidate model parameters may include the following steps:

[0088] Obtaining requester information of the target requester;

[0089] Construct a parameter screening matrix based on the requester information;

[0090] According to the parameter screening matrix, the target model parameters are screened out from multiple candidate model parameters.

[0091] Specifically, requester information refers to information that uniquely identifies the target requester, including but not limited to the requester's identification number, Internet Protocol address, and so on. In the parameter screening matrix, the value in the row corresponding to the target requester is 1, and the values ​​in the remaining rows are 0. The target model parameters are retained by selecting the rows with a value of 1 in the parameter screening matrix, while the candidate model parameters corresponding to the rows with a value of 0 are eliminated. The parameter screening matrix is ​​used to select the target model parameters from multiple candidate model parameters.

[0092] It should be noted that there are multiple ways to obtain the requester information of the target requester, and the specific method to be selected depends on the actual situation. The embodiments of this disclosure do not impose any restrictions on this. In one possible implementation of this disclosure, the requester information of the target requester can be obtained from a database. In another possible implementation of this disclosure, the requester information sent by the target requester through the client can be received.

[0093] Furthermore, after obtaining the requester information of the target requester, the original parameter screening matrix can be first obtained. Each row in the original parameter screening matrix corresponds to a requester. Then, based on the requester information, the target row corresponding to the target requester is determined from the original parameter screening matrix. The values ​​in the target row are set to 1, and the values ​​in the other rows are set to 0 to obtain the parameter screening matrix. Finally, the parameter screening matrix is ​​multiplied by the multiple candidate model parameters to filter out the target model parameters corresponding to the target requester from the multiple candidate model parameters.

[0094] Using the solution of the disclosed embodiments, the target requester's requester information is obtained; a parameter screening matrix is ​​constructed based on the requester information; and target model parameters are screened from multiple candidate model parameters based on the parameter screening matrix. By multiplying the parameter screening matrix by the multiple candidate model parameters, the target model parameters are accurately screened from the multiple candidate model parameters.

[0095] In an optional embodiment of the present disclosure, multiple candidate model parameters may be pre-generated, and target model parameters corresponding to the target requester may be further screened out from the pre-generated multiple candidate model parameters. That is, before screening out the target model parameters corresponding to the target requester from the multiple candidate model parameters, the following steps may be further included:

[0096] Obtain sample sets specified by multiple requesting parties;

[0097] For the first requester, training a pre-training processing model according to a sample set specified by the first requester to obtain pre-training model parameters corresponding to the first requester, wherein the first requester is any training data of the plurality of requesters;

[0098] The candidate model parameters corresponding to each requester are screened out from the pre-trained model parameters corresponding to each requester.

[0099] Specifically, the sample sets specified by multiple requesting parties can be the same or different. Pre-trained model parameters refer to the model parameters of the pre-trained processing model obtained by training the pre-trained processing model using the sample set specified by the first requesting party. The pre-trained model parameters include shared model parameters and candidate model parameters corresponding to the first requesting party. The shared model parameters remain fixed during the training of the pre-trained processing model.

[0100] In practical applications, there are various ways to obtain sample sets specified by multiple requesters, and the method of selecting one depends on the actual situation. This disclosure does not impose any restrictions on this method. In one possible implementation of this disclosure, the sample sets specified by each requester can be read from another database or data acquisition device. In another possible implementation of this disclosure, the sample sets sent by each requester through a client can be received.

[0101] It should be noted that after obtaining the pre-trained model parameters corresponding to the first requester, the shared model parameters and candidate model parameters can be separated from the pre-trained model parameters through tensor-related functions, and then stored separately, so that the corresponding candidate model parameters can be called subsequently according to the requester information.

[0102] Applying the solution of the embodiment of the present disclosure, a sample set specified by each of multiple requesting parties is obtained; for a first requesting party, a pre-trained processing model is trained based on the sample set specified by the first requesting party to obtain pre-trained model parameters corresponding to the first requesting party, wherein the first requesting party is any training data of the multiple requesting parties; and candidate model parameters corresponding to each requesting party are screened from the pre-trained model parameters corresponding to each requesting party. In the process of training the pre-trained processing model using sample sets specified by different requesting parties, the shared model parameters in the fixed pre-trained processing model remain unchanged, thereby efficiently obtaining the candidate model parameters corresponding to each requesting party, and realizing the use of only one shared model parameter in combination with different candidate model parameters to serve different requesting parties.

[0103] Furthermore, the above-mentioned training of the pre-trained processing model according to the sample set specified by the first requester to obtain the pre-trained model parameters corresponding to the first requester may include the following steps:

[0104] Extracting first sample data from a sample set specified by the first requesting party, wherein the first sample data is any sample data in the sample set, and the first sample data carries a first sample label;

[0105] Inputting the first sample data into the pre-training processing model for prediction to obtain a first sample prediction result;

[0106] According to the first sample prediction result and the first sample label, adjust the model parameters other than the shared model parameters in the pre-trained processing model, and return to the step of extracting the first sample data from the sample set specified by the first requester until the first preset stop condition is reached to obtain the pre-trained model parameters corresponding to the first requester.

[0107] It should be noted that the training method for the pre-training processing model is supervised training. The first sample data carrying the first sample label is the real label of the pre-training processing model training process, which can also be understood as a training target, used to guide the training process of the pre-training processing model. The sample set includes multiple sample data, and the sample data can be data from different scenarios, such as data in conference scenarios and data in e-commerce scenarios. The sample data can also be different types of data, such as audio data and text data. It should be noted that if the sample data is a type of data other than text data, the sample data can be converted to obtain sample data in text form.

[0108] In actual applications, the first sample data is input into the pre-training processing model for prediction. After obtaining the first sample prediction result, the first loss value can be calculated based on the first sample prediction result and the first sample label, and the model parameters other than the shared model parameters in the pre-training processing model are adjusted according to the first loss value. The step of extracting the first sample data from the sample set specified by the first requester is returned to execute until the first preset stop condition is reached to obtain the pre-training model parameters corresponding to the first requester.

[0109] In one possible implementation of the present disclosure, the first preset stopping condition includes the first loss value being less than or equal to a first preset threshold value. After calculating the first loss value based on the first sample prediction result and the first sample label, the first loss value is compared with the first preset threshold value.

[0110] Specifically, if the first loss value is greater than the first preset threshold, it means that the difference between the first sample prediction result and the first sample label is large, and the pre-training processing model has poor prediction ability for the first sample prediction result. At this time, the model parameters other than the shared model parameters in the pre-training processing model can be adjusted, and the step of extracting the first sample data from the sample set specified by the first requester is returned to execute, and the pre-training processing model is continued to be trained until the first loss value is less than or equal to the first preset threshold, indicating that the difference between the first sample prediction result and the first sample label is small, and the first preset stop condition is reached, and the pre-training model parameters corresponding to the first requester are obtained.

[0111] In another possible implementation of the present disclosure, in addition to comparing the first loss value and the first preset threshold, it is also possible to determine whether the pre-trained model parameters corresponding to the first requester are obtained in combination with the preset number of iterations.

[0112] Specifically, if the first loss value is greater than the first preset threshold, the model parameters other than the shared model parameters in the pre-training processing model are adjusted, and the step of extracting the first sample data from the sample set specified by the first requesting party is returned to execute, and the pre-training processing model is continued to be trained until the first preset number of iterations is reached, and the iteration is stopped to obtain the pre-training model parameters corresponding to the first requesting party, wherein the first preset threshold and the first preset number of iterations are selected according to the actual situation, and the embodiments of the present disclosure do not impose any restrictions on this.

[0113] In practical applications, there are many functions for calculating the first loss value, such as cross entropy loss function, L1 norm loss function, maximum loss function, mean square error loss function, logarithmic loss function, etc. The specific selection is based on the actual situation, and the embodiments of this disclosure do not impose any restrictions on this.

[0114] Applying the solution of the disclosed embodiment, a first loss value is calculated based on the first sample prediction result and the first sample label, and the first loss value is compared with a first preset stopping condition. If the first preset stopping condition is not met, the pre-training processing model is continuously trained until the first preset stopping condition is met, completing the training and obtaining the pre-training model parameters corresponding to the first requester. By continuously adjusting model parameters other than the shared model parameters in the pre-training processing model, the resulting pre-training model parameters can be made more accurate.

[0115] It is worth noting that by fixing the shared model parameters in the pre-trained processing model, only about 1% of the parameters need to be trained to achieve good training results. At the same time, due to the reduction in parameter adjustments during the training process, the graphics card and storage space required for training are also significantly reduced. Taking the training of a 13B model as an example, if the pre-trained processing model is fully trained with all parameters, at least two 80G graphics cards are required. At the same time, if 10 checkpoints are stored during the training process, at least 10*20G=200G of storage space will be required, which is a huge consumption. However, by efficiently fine-tuning the parameters of the fixed shared model parameters, only one 80G graphics card is needed to train the pre-trained processing model. At the same time, if 10 checkpoints are stored during the training process, only 10*20G*1%=2G of storage space will be occupied, which significantly reduces the storage space.

[0116] In an optional embodiment of the present disclosure, after obtaining the pre-trained model parameters corresponding to the first requester, the pre-trained model parameters can be sent to the first requester. The first requester can locally build a model based on the pre-trained model parameters and determine whether the current pre-trained model parameters meet the requirements. If they do not meet the requirements, the first requester can send sample adjustment data to continue training the pre-trained model. That is, the above-mentioned training of the pre-trained processing model based on the sample set specified by the first requester, after obtaining the pre-trained model parameters corresponding to the first requester, can also include the following steps:

[0117] Sending the pre-trained model parameters to the first requester;

[0118] Receive sample adjustment data sent by the first requester based on the pre-training model parameters, and adjust the parameters of the pre-training processing model according to the sample adjustment data.

[0119] Specifically, the sample adjustment data may be sample data outside the sample set, or the number of model training iterations during parameter adjustment. The sample adjustment data is used to adjust model parameters other than the shared model parameters in the pre-training processing model. If the sample adjustment data is sample data outside the sample set, the sample adjustment data may be data from different scenarios, such as data in a conference scenario or data in an e-commerce scenario. The sample adjustment data may also be different types of data, such as audio data or text data. It should be noted that if the sample adjustment data is data of a type other than text data, the sample adjustment data may be converted to obtain sample adjustment data in text form.

[0120] In actual applications, when the pre-trained model parameters are sent to the first requesting party, the pre-trained model parameters can be sent to the first requesting party through the client. Furthermore, sample adjustment data sent by the first requesting party through the client can be received, wherein the sample adjustment data is obtained based on the pre-trained model parameters.

[0121] It should be noted that the method of adjusting the parameters of the pre-training processing model according to the sample adjustment data is the same as the implementation method of the above-mentioned "training the pre-training processing model according to the sample set specified by the first requesting party", and will not be repeated in this embodiment of the disclosure.

[0122] By applying the solution of the embodiment of the present disclosure, the pre-trained model parameters are sent to the first requesting party; the sample adjustment data sent by the first requesting party based on the pre-trained model parameters is received, and the parameters of the pre-trained processing model are adjusted according to the sample adjustment data, so that the candidate model parameters corresponding to the first requesting party are more accurate, further ensuring the accuracy of the task processing model.

[0123] In an optional embodiment of the present disclosure, the pre-trained model parameters include shared model parameters; after screening the candidate model parameters corresponding to each requesting party from the pre-trained model parameters corresponding to each requesting party, the following steps may also be included:

[0124] Storing the candidate model parameters corresponding to each requester in the candidate parameter storage component respectively;

[0125] Stores shared model parameters to the shared parameter storage component.

[0126] Specifically, the candidate parameter storage component and the shared parameter storage component may be different databases, or different storage subcomponents in the same database.

[0127] It should be noted that when the candidate model parameters corresponding to each requester are stored in the candidate parameter storage component respectively, the candidate model parameters can be stored in a columnar storage manner according to the requester information of each requester.

[0128] Using the solution of the embodiments of the present disclosure, after selecting candidate model parameters corresponding to each requester from the pre-trained model parameters corresponding to each requester, the candidate model parameters corresponding to each requester are stored in a candidate parameter storage component; and the shared model parameters are stored in a shared parameter storage component. This allows the target model parameters corresponding to the target requester to be directly extracted from the candidate parameter storage component, and the shared model parameters to be extracted from the shared parameter storage component to construct the task processing model.

[0129] In practical applications, the shared model parameters can be directly stored in the shared parameter storage component. Furthermore, since the shared model parameters are model parameters shared by all requesting parties and are fixed, if the shared model parameters have already been stored in the shared parameter storage component, there is no need to repeatedly store the shared model parameters in the shared parameter storage component. That is, before storing the shared model parameters in the shared parameter storage component, the following steps may be further included:

[0130] Determining whether the shared parameter storage component includes shared model parameters;

[0131] Storing shared model parameters in the shared parameter storage component can include the following steps:

[0132] In a case where the shared model parameters are not included in the shared parameter storage component, the shared model parameters are stored in the shared parameter storage component.

[0133] It should be noted that there are multiple ways to determine whether the shared parameter storage component includes shared model parameters, and the method is selected according to actual circumstances. The embodiments of the present disclosure do not impose any limitation on this.

[0134] In one possible implementation of the present disclosure, it is possible to identify whether the shared parameter storage component is empty. If the shared parameter storage component is empty, it means that the shared parameter storage component does not include shared model parameters, and the shared model parameters can be stored in the shared parameter storage component; if the shared parameter storage component is not empty, it means that the shared parameter storage component includes shared model parameters, and there is no need to store the shared model parameters in the shared parameter storage component.

[0135] In another possible implementation of the present disclosure, since the stored data may not be shared model parameters when the shared parameter storage component is not empty, the stored data in the shared parameter storage component can be obtained, and the stored data and the shared model parameters can be compared. If the stored data and the shared model parameters are different, it means that the shared parameter storage component does not include the shared model parameters, and the shared model parameters can be stored in the shared parameter storage component; if the stored data and the shared model parameters are the same, it means that the shared parameter storage component includes the shared model parameters, and there is no need to store the shared model parameters in the shared parameter storage component.

[0136] By applying the solution of the embodiment of the present disclosure, it is determined whether the shared parameter storage component includes the shared model parameters; if the shared model parameters are not included in the shared parameter storage component, the shared model parameters are stored in the shared parameter storage component. This avoids redundant storage of the shared model parameters and reduces the occupancy rate of the shared parameter storage component.

[0137] Step 506: Construct a task processing model based on the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by each requesting party in the pre-trained processing model. During the training of the pre-trained processing model, the shared model parameters remain fixed.

[0138] In one or more embodiments of the present disclosure, after receiving a task processing request and screening out target model parameters corresponding to the target requester from multiple candidate model parameters, a task processing model can be further constructed based on the target model parameters and the shared model parameters.

[0139] Specifically, shared model parameters refer to parameters that remain unchanged during the training of the pre-trained processing model based on the sample set specified by the requester. They can also be understood as frozen parameters. Since the target model parameters are obtained by training the pre-trained processing model based on the sample set specified by the target requester, the task processing model can be understood as a processing model that is exclusive to the target requester.

[0140] It should be noted that when constructing a task processing model based on the target model parameters and the shared model parameters, the target model parameters and the shared model parameters can be concatenated to obtain the model parameters of the task processing model.

[0141] Step 508: Input the data to be processed into the task processing model to obtain the task processing result.

[0142] In one or more embodiments of the present disclosure, a task processing request is received, target model parameters corresponding to the target requester are screened out from a plurality of candidate model parameters, and a task processing model is constructed based on the target model parameters and the shared model parameters. Further, the data to be processed can be input into the task processing model to obtain the task processing result.

[0143] By applying the solution of the embodiments of the present disclosure, in the process of training the pre-training processing model using sample sets specified by different requesters, the shared model parameters in the fixed pre-training processing model remain unchanged, so that the candidate model parameters corresponding to each requester can be obtained efficiently, and only one shared model parameter is used in combination with different candidate model parameters to serve different requesters. There is no need to provide a separate task processing model for each requester, thereby reducing the model deployment cost and task processing resource consumption.

[0144] In an optional embodiment of the present disclosure, after inputting the data to be processed into the task processing model and obtaining the task processing result, the following steps may be further included:

[0145] Sending the task processing result to the client, wherein the task processing result is displayed by the client to the target requester;

[0146] Receive adjustment information sent by the target requester through the client, and adjust the target model parameters according to the adjustment information, wherein the adjustment information is obtained based on the task processing result.

[0147] It should be noted that after inputting the data to be processed into the task processing model and obtaining the task processing result, the task processing result can be sent to the client, and the model parameters of the task processing model can also be sent to the client.

[0148] In actual applications, there are multiple ways for the client to display the task processing results to the target requester, and the specific method to be selected depends on the actual situation. The embodiments of the present disclosure do not impose any restrictions on this. In one possible implementation of the present disclosure, the client can only display the task processing results to the target requester. In another possible implementation of the present disclosure, the client can simultaneously display the task processing results and the model parameters of the task processing model to the target requester.

[0149] It is worth noting that after obtaining the task processing result, the task processing result can be quality checked. If the quality check passes, the task processing result is sent to the client. If the quality check fails, the task processing is performed again.

[0150] Furthermore, after the client displays the task processing results to the target requester, the target requester can perform data processing on its own based on the task processing results, or it can adjust the task processing results displayed by the client to generate adjustment information, and send the adjustment information to the task processing system through the client, so that the task processing system adjusts the target model parameters according to the adjustment information, wherein the adjustment information may include the data to be processed and the adjusted task processing results.

[0151] By applying the solution of the embodiment of the present disclosure, the task processing result is sent to the client, wherein the task processing result is displayed by the client to the target requester; the adjustment information sent by the target requester through the client is received, and the target model parameters are adjusted according to the adjustment information, so that the target requester can accurately obtain the task processing result, thereby increasing the interaction with the target requester and improving the satisfaction of the target requester.

[0152] In an optional embodiment of the present disclosure, before selecting the target model parameter corresponding to the target requester from the plurality of candidate model parameters, the following steps may be included:

[0153] Obtaining a training set, wherein the training set includes a plurality of training data, and the training data carries a training label;

[0154] Extracting first training data from the training set, wherein the first training data is any requesting party in the training set;

[0155] Inputting the first training data into the original processing model to obtain a first training prediction result;

[0156] The original processing model is trained according to the first training prediction result and the first training label carried by the first training data to obtain a trained pre-trained processing model.

[0157] It should be noted that the original processing model can be a deep learning model for natural language processing. The original processing model is trained using supervised training. The training labels carried by the training data are the true labels of the original processing model training process. The training labels can also be understood as training targets, which are used to guide the training process of the original processing model. The training set includes multiple training data. The training data can be data from different scenarios, such as data in conference scenarios or data in e-commerce scenarios. The training data can also be different types of data, such as audio data or text data. It should be noted that if the training data is data of a type other than text data, it can be converted to obtain training data in text form.

[0158] There are multiple ways to obtain a training set, and the specific method to be used depends on the actual situation. The embodiments of this disclosure do not impose any restrictions on this. In one possible implementation of this disclosure, multiple training data can be read from other data acquisition devices or databases, and the training set can be constructed based on the multiple training data. In another possible implementation of this disclosure, a large amount of training data can be manually input, and the training set can be constructed based on the manually input training data.

[0159] In actual applications, the first training data is input into the original processing model. After obtaining the first training prediction result, the second loss value can be calculated based on the first training prediction result and the first training label. The model parameters of the original processing model are adjusted according to the second loss value, and the step of extracting the first training data from the training set is returned to execute until the second preset stop condition is reached to obtain a pre-trained processing model that has completed training.

[0160] In one possible implementation of the present disclosure, the second preset stopping condition includes the second loss value being less than or equal to a second preset threshold value. After calculating the second loss value based on the first training prediction result and the first training label, the second loss value is compared with the second preset threshold value.

[0161] Specifically, if the second loss value is greater than the second preset threshold, it means that the difference between the first training prediction result and the first training label is large, and the original processing model has poor prediction ability for the first training prediction result. At this time, the model parameters of the original processing model can be adjusted, and the step of extracting the first training data from the training set can be returned to continue training the original processing model until the second loss value is less than or equal to the second preset threshold, indicating that the difference between the first training prediction result and the first training label is small, and the second preset stop condition is met, and a pre-trained processing model that has completed training is obtained.

[0162] In another possible implementation of the present disclosure, in addition to comparing the magnitude relationship between the second loss value and the second preset threshold, it is also possible to determine whether the pre-training processing model is trained in combination with a preset number of iterations.

[0163] Specifically, if the second loss value is greater than the second preset threshold, the model parameters of the original processing model are adjusted, and the step of extracting the first training data from the training set is returned to execute, and the original processing model is continued to be trained until the second preset number of iterations is reached, and the iteration is stopped to obtain a pre-trained processing model that has been trained. The second preset threshold and the second preset number of iterations are selected according to actual conditions, and the embodiments of the present disclosure do not impose any restrictions on this.

[0164] In practical applications, there are many functions for calculating the second loss value, such as cross entropy loss function, L1 norm loss function, maximum loss function, mean square error loss function, logarithmic loss function, etc. The specific selection is based on the actual situation, and the embodiments of this disclosure do not impose any restrictions on this.

[0165] Using the solution of the disclosed embodiment, a second loss value is calculated based on the first training prediction result and the first training label, and the second loss value is compared with a second preset stopping condition. If the second preset stopping condition is not met, the original processing model is trained continuously until the second preset stopping condition is met, thereby obtaining a pre-trained processing model. By continuously adjusting the model parameters of the original processing model, the pre-trained processing model can be made more accurate.

[0166] In the embodiments of the present disclosure, the above-mentioned task processing method has a variety of application scenarios, such as data recommendation scenarios, intelligent question-answering scenarios, etc. The following is combined with Figure 6, taking the application of the task processing method provided by the present disclosure in the intelligent question-answering scenario as an example to further illustrate the task processing method. Referring to Figure 6, Figure 6 is a flow chart of an automatic question-answering method provided by the embodiment of the present disclosure, which specifically includes the following steps:

[0167] Step 602: Receive a question handling request, wherein the question handling request carries data to be answered.

[0168] Step 604: Filter out target model parameters corresponding to the target requester from multiple candidate model parameters, wherein the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester.

[0169] Step 606: Construct a task processing model based on the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by each requesting party in the pre-trained processing model. During the training of the pre-trained processing model, the shared model parameters remain fixed.

[0170] Step 608: Input the data to be answered into the task processing model to obtain the question answering result.

[0171] It should be noted that the data to be answered is also the data to be processed, and the result of answering the question is also the result of task processing. The implementation of steps 602 to 608 is the same as the implementation of steps 502 to 508 above, and will not be repeated in this embodiment.

[0172] By applying the solution of the embodiments of the present disclosure, in the process of training the pre-training processing model using sample sets specified by different requesters, the shared model parameters in the fixed pre-training processing model remain unchanged, so that the candidate model parameters corresponding to each requester can be efficiently obtained, and only one shared model parameter is used in combination with different candidate model parameters to serve different requesters. There is no need to provide a separate task processing model for each requester, thereby reducing the model deployment cost and the consumption of automatic question and answer resources.

[0173] 7 , which is a flowchart of a task processing method provided by an embodiment of the present disclosure, specifically comprising the following steps:

[0174] Step 702: Acquire sample sets respectively specified by multiple requesting parties.

[0175] Step 704: For the first requester, train a pre-training processing model according to the sample set specified by the first requester to obtain pre-training model parameters corresponding to the first requester, wherein the first requester is any requester among the multiple requesters.

[0176] Step 706: Filter out candidate model parameters corresponding to each requester from the pre-trained model parameters corresponding to each requester.

[0177] Step 708: Store the candidate model parameters corresponding to each requester into the candidate parameter storage component respectively.

[0178] Step 710: Store the shared model parameters in the pre-trained model parameters into the shared parameter storage component.

[0179] Step 712: Receive a task processing request, wherein the task processing request carries data to be processed.

[0180] Step 714: Filter out target model parameters corresponding to the target requester from multiple candidate model parameters stored in the candidate parameter storage component, wherein the candidate model parameters are obtained by training the pre-trained processing model based on the sample set specified by the requester, and each candidate model parameter corresponds to a different requester.

[0181] Step 716: Construct a task processing model based on the target model parameters and the shared model parameters in the shared parameter storage component, wherein the shared model parameters are model parameters shared by each requester in the pre-trained processing model. During the training of the pre-trained processing model, the shared model parameters remain fixed.

[0182] Step 718: Input the data to be processed into the task processing model to obtain the task processing result.

[0183] It should be noted that the implementation of steps 702 to 718 is the same as the implementation of steps 502 to 508 described above, and will not be described in detail in this embodiment of the present disclosure.

[0184] By applying the solution of the embodiments of the present disclosure, in the process of training the pre-training processing model using sample sets specified by different requesters, the shared model parameters in the fixed pre-training processing model remain unchanged, so that the candidate model parameters corresponding to each requester can be obtained efficiently, and only one shared model parameter is used in combination with different candidate model parameters to serve different requesters. There is no need to provide a separate task processing model for each requester, thereby reducing the model deployment cost and task processing resource consumption.

[0185] The task processing method proposed in the embodiments of the present disclosure utilizes efficient parameter fine-tuning to train specific enterprise-specific parameters. During the deployment phase, the same pre-trained processing model is used as the foundation to dynamically switch the specific parameters corresponding to different enterprises to achieve the purpose of serving different enterprises. This achieves the goal of using only one large model with multiple specific parameters to simultaneously serve multiple enterprises, achieving the goal of significantly reducing deployment and storage costs. The task processing method mainly includes three parts: efficient training, parameter splitting, storage and assembly, and efficient deployment architecture. Among them, efficient training includes full parameter training and efficient parameter fine-tuning.

[0186] Full parameter training: Obtain a training set, extract first training data from the training set, input the first training data into the original processing model, obtain a first training prediction result, train the original processing model based on the first training prediction result and the first training label carried by the first training data, and obtain a pre-trained processing model.

[0187] It should be noted that during the original processing model training phase, after the training data is prepared, the original processing model can be fine-tuned in a supervised manner on all parameters. The advantage of this method is that by fully adjusting the original processing model parameters, it can better fit the training data and achieve better training results. However, due to the large number of parameters in the original processing model, full parameter training requires a large amount of graphics card resources, and storing the trained checkpoint files also consumes a large amount of storage space. Therefore, this disclosure proposes a training method for efficient parameter fine-tuning after the original processing model training is completed.

[0188] Efficient parameter fine-tuning: Obtain sample sets specified by multiple requesters respectively, train a pre-trained processing model for the first requester based on the sample set specified by the first requester, obtain the pre-trained model parameters corresponding to the first requester, and filter out candidate model parameters corresponding to each requester from the pre-trained model parameters corresponding to each requester.

[0189] Parameter Splitting, Storage, and Assembly: In actual production, to address the challenges of efficient training and deployment across multiple enterprises, in addition to developing algorithms for efficient parameter fine-tuning, the disclosed embodiments also implement separate storage of candidate model parameters and parameter assembly during model deployment. Specifically, candidate model parameters corresponding to each requester are stored in the candidate parameter storage component, while shared model parameters are stored in the shared parameter storage component.

[0190] It should be noted that parameter splitting, storage, and assembly can be achieved through PyTorch's underlying Tensor operations. During the parameter assembly process, the shared model parameters and target model parameters can be loaded separately, and then multiplied by the input matrix, and then added to complete the task processing.

[0191] Efficient Deployment Architecture: For training tasks targeting N companies, a single pre-trained processing model can be used as the base, with N small candidate model parameters and the base model's shared model parameters loaded into graphics memory together. Compared to deploying N different task processing models, this approach can effectively reduce GPU consumption by a factor of N. When used online, the corresponding small candidate model parameters can be automatically switched based on the requests of different companies. Together with the shared model parameters, a temporary task processing model can be formed to process the requests and generate answers.

[0192] By applying the solution of the embodiment of the present disclosure, the resource consumption problem when multiple enterprises train and deploy large models is effectively solved by using an efficient parameter adjustment method. By combining and deploying the shared model parameters in the base pre-training processing model and the candidate model parameters of multiple enterprises at the same time, it is possible to deploy the model with only 1.x times the base model resources, greatly reducing the resource consumption problem when multiple enterprises collaborate to deploy.

[0193] See Figure 8, which is a schematic diagram of an automated question-and-answer interface provided by an embodiment of the present disclosure. The automated question-and-answer interface is divided into a question-handling request input interface and a response result display interface. The question-handling request input interface includes a question-handling request input box, an "OK" control, and a "Cancel" control. The response result display interface includes a response result display box.

[0194] The target requester enters a question processing request through the question processing request input box displayed on the client. The question processing request carries the data to be answered. After clicking the "OK" control, the service component receives the question processing request sent by the client and selects the target model parameters corresponding to the target requester from multiple candidate model parameters. The candidate model parameters are trained using a pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester. A task processing model is constructed based on the target model parameters and shared model parameters. The shared model parameters are model parameters shared by all requesters in the pre-trained processing model and remain fixed during the training of the pre-trained processing model. The data to be answered is input into the task processing model, and a question answer result is obtained. The question answer result is then sent to the client. The client displays the question answer result in the answer result display box.

[0195] In actual applications, the target requester operates the control by any of the following methods: clicking, double-clicking, touching, hovering the mouse, sliding, long pressing, voice control, or shaking. The specific selection is based on the actual situation, and the embodiments of this disclosure do not impose any restrictions on this.

[0196] Corresponding to the above-mentioned task processing method embodiment, the present disclosure also provides a task processing device embodiment. FIG9 is a structural diagram of a task processing device provided by an embodiment of the present disclosure. As shown in FIG9 , the device includes:

[0197] A first receiving component 902 is configured to receive a task processing request, wherein the task processing request carries data to be processed;

[0198] A first screening component 904 is configured to screen target model parameters corresponding to a target requester from a plurality of candidate model parameters, wherein the target requester is the object that sends the task processing request, and the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester;

[0199] A first construction component 906 is configured to construct a task processing model based on the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by the requesting parties in the pre-trained processing model, and the shared model parameters remain fixed during the training of the pre-trained processing model;

[0200] The first input component 908 is configured to input the data to be processed into the task processing model to obtain the task processing result.

[0201] Optionally, the device also includes: a first training component, configured to obtain sample sets specified by multiple requesters respectively; for the first requester, training a pre-training processing model according to the sample set specified by the first requester to obtain pre-training model parameters corresponding to the first requester, wherein the first requester is any one of the multiple requesters; and screening out candidate model parameters corresponding to each requester from the pre-training model parameters corresponding to each requester.

[0202] Optionally, the first training component is further configured to extract first sample data from a sample set specified by the first requester, wherein the first sample data is any sample data in the sample set and the first sample data carries a first sample label; input the first sample data into a pre-training processing model for prediction to obtain a first sample prediction result; adjust the model parameters other than the shared model parameters in the pre-training processing model according to the first sample prediction result and the first sample label, and return to execute the step of extracting the first sample data from the sample set specified by the first requester until the first preset stop condition is reached to obtain the pre-training model parameters corresponding to the first requester.

[0203] Optionally, the first training component is further configured to send the pre-trained model parameters to the first requester; receive sample adjustment data sent by the first requester based on the pre-trained model parameters, and adjust the parameters of the pre-trained processing model according to the sample adjustment data.

[0204] Optionally, the pre-trained model parameters include shared model parameters; the first training component is further configured to store the candidate model parameters corresponding to each requesting party in the candidate parameter storage component respectively; and store the shared model parameters in the shared parameter storage component.

[0205] Optionally, the first training component is further configured to determine whether the shared parameter storage component includes shared model parameters; if the shared parameter storage component does not include shared model parameters, store the shared model parameters in the shared parameter storage component.

[0206] Optionally, the first screening component 904 is further configured to obtain requester information of the target requester; construct a parameter screening matrix according to the requester information; and screen the target model parameters from multiple candidate model parameters according to the parameter screening matrix.

[0207] Optionally, the device also includes: a second training component, configured to obtain a training set, wherein the training set includes multiple training data, and the training data carries a training label; extract first training data from the training set, wherein the first training data is any training data in the training set; input the first training data into the original processing model to obtain a first training prediction result; train the original processing model according to the first training prediction result and the first training label carried by the first training data to obtain a pre-trained processing model that has completed training.

[0208] Optionally, the device also includes: a sending component configured to send the task processing result to the client, wherein the task processing result is displayed by the client to the target requester; receiving adjustment information sent by the target requester through the client, and adjusting the target model parameters according to the adjustment information, wherein the adjustment information is obtained based on the task processing result.

[0209] By applying the solution of the embodiments of the present disclosure, in the process of training the pre-training processing model using sample sets specified by different requesters, the shared model parameters in the fixed pre-training processing model remain unchanged, so that the candidate model parameters corresponding to each requester can be obtained efficiently, and only one shared model parameter is used in combination with different candidate model parameters to serve different requesters. There is no need to provide a separate task processing model for each requester, thereby reducing the model deployment cost and task processing resource consumption.

[0210] The above is a schematic scheme of a task processing device of this embodiment. It should be noted that the technical scheme of the task processing device and the technical scheme of the task processing method described above are of the same concept. For details not described in detail in the technical scheme of the task processing device, please refer to the description of the technical scheme of the task processing method described above.

[0211] Corresponding to the above-mentioned automatic question-answering method embodiment, the present disclosure also provides an automatic question-answering device embodiment. FIG10 is a schematic diagram of the structure of an automatic question-answering device provided by an embodiment of the present disclosure. As shown in FIG10 , the device includes:

[0212] The second receiving component 1002 is configured to receive a question processing request, wherein the question processing request carries data to be answered;

[0213] A second screening component 1004 is configured to screen target model parameters corresponding to a target requester from a plurality of candidate model parameters, wherein the target requester is the party that sends the problem processing request, and the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester;

[0214] A second construction component 1006 is configured to construct a task processing model based on the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by the requesting parties in the pre-trained processing model, and the shared model parameters remain fixed during the training of the pre-trained processing model;

[0215] The second input component 1008 is configured to input the data to be answered into the task processing model to obtain the question answering result.

[0216] Optionally, the device also includes: a first training component, configured to obtain sample sets specified by multiple requesters respectively; for the first requester, training a pre-training processing model according to the sample set specified by the first requester to obtain pre-training model parameters corresponding to the first requester, wherein the first requester is any one of the multiple requesters; and screening out candidate model parameters corresponding to each requester from the pre-training model parameters corresponding to each requester.

[0217] By applying the solution of the embodiments of the present disclosure, in the process of training the pre-training processing model using sample sets specified by different requesters, the shared model parameters in the fixed pre-training processing model remain unchanged, so that the candidate model parameters corresponding to each requester can be efficiently obtained, and only one shared model parameter is used in combination with different candidate model parameters to serve different requesters. There is no need to provide a separate task processing model for each requester, thereby reducing the model deployment cost and the consumption of automatic question and answer resources.

[0218] The above is a schematic diagram of an automatic question-answering device according to this embodiment. It should be noted that the technical solution of this automatic question-answering device and the technical solution of the automatic question-answering method described above are based on the same concept. For details not described in detail in the technical solution of the automatic question-answering device, please refer to the description of the technical solution of the automatic question-answering method described above.

[0219] Figure 11 is a block diagram of a computing device provided by an embodiment of the present disclosure. Components of the computing device 1100 include, but are not limited to, a memory 1110 and a processor 1120. The processor 1120 is connected to the memory 1110 via a bus 1130, and a database 1150 is used to store data.

[0220] The computing device 1100 also includes an access device 1140 that enables the computing device 1100 to communicate via one or more networks 1160. Examples of such networks include a Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 1140 may include one or more of any type of network interface (e.g., a Network Interface Card (NIC)) whether wired or wireless, such as an IEEE 802.11 Wireless Local Area Networks (WLAN) wireless interface, a World Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, and the like.

[0221] In one embodiment of the present disclosure, the aforementioned components of the computing device 1100 and other components not shown in FIG11 may also be connected to each other, for example, via a bus. It should be understood that the computing device structure block diagram shown in FIG11 is for illustrative purposes only and does not limit the scope of the present disclosure. Those skilled in the art may add or replace other components as needed.

[0222] Computing device 1100 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, personal digital assistant, laptop computer, notebook computer, netbook computer, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or personal computer (PC). Computing device 1100 may also be a mobile or stationary server.

[0223] The processor 1120 is configured to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the above-mentioned task processing method or automatic question-answering method.

[0224] The above is a schematic diagram of a computing device according to this embodiment. It should be noted that the technical solution of this computing device is based on the same concept as the technical solutions of the task processing method and the automatic question-answering method described above. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solutions of the task processing method or the automatic question-answering method described above.

[0225] The present disclosure also provides a processor. FIG12 is a schematic diagram showing the structure of a processor according to an embodiment of the present disclosure. As shown in FIG12 , the processor 1200 is configured to run a program, wherein the program, when run by the processor, executes the method in the above embodiment.

[0226] In the embodiment of the present disclosure, the processor 1200 may execute the operating program of the method in the embodiment.

[0227] Optionally, the processor 1200 can be configured to perform the following steps: receiving a task processing request, wherein the task processing request carries data to be processed; screening out target model parameters corresponding to the target requester from multiple candidate model parameters, wherein the target requester is the object that sends the task processing request, and the candidate model parameters are obtained by training the pre-trained processing model based on the sample set specified by the requester, and each candidate model parameter corresponds to a different requester; constructing a task processing model based on the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by each requester in the pre-trained processing model, and during the process of training the pre-trained processing model, the shared model parameters remain fixed; inputting the data to be processed into the task processing model to obtain the task processing result.

[0228] Optionally, the processor 1200 can be configured to perform the following steps: receiving a question processing request, wherein the question processing request carries data to be answered; screening out target model parameters corresponding to the target requester from multiple candidate model parameters, wherein the target requester is the object sending the question processing request, and the candidate model parameters are obtained by training the pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester; constructing a task processing model based on the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by each requester in the pre-trained processing model, and during the process of training the pre-trained processing model, the shared model parameters remain fixed; inputting the data to be answered into the task processing model to obtain a question answer result.

[0229] The embodiment of the present disclosure also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned task processing method or automatic question-answering method.

[0230] The above is a schematic diagram of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium is based on the same concept as the technical solutions of the task processing method and the automatic question-answering method described above. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solutions of the task processing method or the automatic question-answering method described above.

[0231] The embodiments of the present disclosure further provide a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method provided in the embodiments of the present disclosure is implemented.

[0232] An embodiment of the present disclosure further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned task processing method or automatic question-answering method.

[0233] Optionally, the above-mentioned computer program implements the program code of the following steps when executed by the processor: receiving a task processing request, wherein the task processing request carries data to be processed; screening out target model parameters corresponding to the target requester from multiple candidate model parameters, wherein the target requester is the object sending the task processing request, and the candidate model parameters are obtained by training the pre-trained processing model based on the sample set specified by the requester, and each candidate model parameter corresponds to a different requester; constructing a task processing model based on the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by each requester in the pre-trained processing model, and during the training of the pre-trained processing model, the shared model parameters remain fixed; inputting the data to be processed into the task processing model to obtain the task processing result.

[0234] Optionally, the above-mentioned computer program implements the program code of the following steps when executed by the processor: receiving a question processing request, wherein the question processing request carries data to be answered; screening out target model parameters corresponding to the target requester from multiple candidate model parameters, wherein the target requester is the object sending the question processing request, and the candidate model parameters are obtained by training the pre-trained processing model based on the sample set specified by the requester, and each candidate model parameter corresponds to a different requester; constructing a task processing model based on the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by each requester in the pre-trained processing model, and during the process of training the pre-trained processing model, the shared model parameters remain fixed; inputting the data to be answered into the task processing model to obtain the question answer result.

[0235] The above is a schematic diagram of a computer program according to this embodiment. It should be noted that the technical solution of this computer program is based on the same concept as the technical solutions of the task processing method and the automatic question-answering method described above. For details not described in detail in the technical solution of the computer program, please refer to the description of the technical solutions of the task processing method or the automatic question-answering method described above.

[0236] The foregoing description describes specific embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0237] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium.

[0238] It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this disclosure are not limited by the order of the actions described, because according to the embodiments of this disclosure, 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 this disclosure in the specification are all preferred embodiments, and the actions and components involved are not necessarily required by the embodiments of this disclosure.

[0239] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0240] The preferred embodiments of the present disclosure disclosed above are only used to help illustrate the disclosure of this specification. The optional embodiments do not describe all details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made based on the content of the embodiments of this disclosure. This disclosure selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this disclosure, so that those skilled in the art can better understand and use this disclosure. This disclosure is limited only by the claims and their full scope and equivalents. Industrial Applicability

[0241] The solution provided by the embodiment of the present disclosure can be applied to the task processing process, receiving a task processing request, wherein the task processing request carries data to be processed; screening out target model parameters corresponding to the target requester from multiple candidate model parameters, wherein the target requester is the object sending the task processing request, and the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester; constructing a task processing model based on the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by each requester in the pre-trained processing model, and during the training of the pre-trained processing model, the shared model parameters remain fixed; inputting the data to be processed into the task processing model to obtain a task processing result, thereby solving the technical problem of high resource consumption for task processing of the data to be processed.

Claims

1. A task processing method, comprising: receiving a task processing request, wherein the task processing request carries data to be processed; Filtering out target model parameters corresponding to a target requester from a plurality of candidate model parameters, wherein the target requester is the object that sends the task processing request, the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and the requesters corresponding to the candidate model parameters are different; Constructing a task processing model according to the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by the requesting parties in the pre-trained processing model, and the shared model parameters remain fixed during the training of the pre-trained processing model; The data to be processed is input into the task processing model to obtain a task processing result.

2. The method according to claim 1, before selecting the target model parameter corresponding to the target requester from the plurality of candidate model parameters, the method further comprises: Acquire the sample sets respectively specified by the multiple requesting parties; For a first requester, training the pre-training processing model according to the sample set specified by the first requester to obtain a pre-training model parameter corresponding to the first requester, wherein the first requester is any one of the multiple requesters; The candidate model parameters corresponding to each of the requesting parties are screened out from the pre-trained model parameters corresponding to each of the requesting parties.

3. The method according to claim 2, training the pre-training processing model according to the sample set specified by the first requester to obtain the pre-training model parameters corresponding to the first requester, comprising: Extracting first sample data from the sample set specified by the first requester, wherein the first sample data is any sample data in the sample set, and the first sample data carries a first sample label; Inputting the first sample data into the pre-training processing model for prediction to obtain a first sample prediction result; According to the first sample prediction result and the first sample label, the model parameters other than the shared model parameters in the pre-trained processing model are adjusted, and the step of extracting the first sample data from the sample set specified by the first requester is returned to execute until a first preset stop condition is reached to obtain the pre-trained model parameters corresponding to the first requester.

4. The method according to claim 2, after training the pre-training processing model according to the sample set specified by the first requester and obtaining the pre-training model parameters corresponding to the first requester, the method further comprises: Sending the pre-trained model parameters to the first requester; Receive sample adjustment data sent by the first requester based on the pre-trained model parameters, and adjust the parameters of the pre-trained processing model according to the sample adjustment data.

5. The method according to claim 2, wherein the pre-trained model parameters include the shared model parameters; storing the candidate model parameters corresponding to each of the requesting parties in a candidate parameter storage component respectively; The shared model parameters are stored in a shared parameter storage component.

6. The method according to claim 5, before storing the shared model parameters in the shared parameter storage component, further comprises: In a case where the shared model parameters are not included in the shared parameter storage component, the shared model parameters are stored in the shared parameter storage component.

7. The method according to claim 1, screening out a target model parameter corresponding to the target requester from a plurality of candidate model parameters, comprises: Acquire requester information of the target requester; Constructing a parameter screening matrix according to the requester information; The target model parameters are screened out from the multiple candidate model parameters according to the parameter screening matrix.

8. The method according to claim 1, before selecting the target model parameter corresponding to the target requester from the plurality of candidate model parameters, the method further comprises: Acquire a training set, wherein the training set includes a plurality of training data, and the training data carries a training label; Extracting first training data from the training set, wherein the first training data is any training data in the training set; Inputting the first training data into the original processing model to obtain a first training prediction result; The original processing model is trained according to the first training prediction result and the first training label carried by the first training data to obtain the trained pre-trained processing model.

9. The method according to claim 1, after inputting the data to be processed into the task processing model and obtaining the task processing result, the method further comprises: Sending the task processing result to the client, wherein the task processing result is displayed by the client to the target requester; Receive adjustment information sent by the target requester through the client, and adjust the target model parameters according to the adjustment information, wherein the adjustment information is obtained based on the task processing result.

10. An automatic question-answering method, comprising: receiving a question handling request, wherein the question handling request carries data to be answered; Filtering out a target model parameter corresponding to a target requester from a plurality of candidate model parameters, wherein the target requester is the object that sends the problem processing request, the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and the requesters corresponding to the candidate model parameters are different; Constructing a task processing model according to the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by the requesting parties in the pre-trained processing model, and the shared model parameters remain fixed during the training of the pre-trained processing model; The data to be answered is input into the task processing model to obtain the question answering result.

11. The method according to claim 10, before selecting the target model parameter corresponding to the target requester from the plurality of candidate model parameters, the method further comprises: Acquire the sample sets respectively specified by the multiple requesting parties; For a first requester, training the pre-training processing model according to the sample set specified by the first requester to obtain a pre-training model parameter corresponding to the first requester, wherein the first requester is any one of the multiple requesters; The candidate model parameters corresponding to each of the requesting parties are screened out from the pre-trained model parameters corresponding to each of the requesting parties.

12. A task processing system, comprising a service component and a candidate parameter storage component; The candidate parameter storage component is used to store multiple candidate model parameters; The service component is used to receive a task processing request, wherein: The task processing request carries data to be processed; Filter out target model parameters corresponding to the target requester from the multiple candidate model parameters, wherein the target requester is the object that sends the task processing request, and the candidate model parameters are obtained by training the pre-trained processing model based on the sample set specified by the requester, and each candidate model parameter corresponds to a different requester; construct a task processing model according to the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by each requester in the pre-trained processing model, and the shared model parameters remain fixed during the training of the pre-trained processing model; input the data to be processed into the task processing model to obtain a task processing result.

13. The system of claim 12, further comprising a shared parameter storage component; The shared parameter storage component is used to store the shared model parameters; The service component is further used to obtain the shared model parameters from the shared parameter storage component.

14. A task processing device, comprising: A first receiving component is configured to receive a task processing request, wherein the task processing request carries data to be processed; A first screening component is configured to screen out a target model parameter corresponding to a target requester from a plurality of candidate model parameters, wherein the target requester is an object that sends the task processing request, the candidate model parameters are obtained by training a pre-trained processing model based on a sample set specified by the requester, and each candidate model parameter corresponds to a different requester; A first construction component is configured to construct a task processing model according to the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by the requesting parties in the pre-trained processing model, and the shared model parameters are fixed in the process of training the pre-trained processing model; The first input component is configured to input the data to be processed into the task processing model to obtain a task processing result.

15. An automatic question-answering device, comprising: A second receiving component is configured to receive a question processing request, wherein the question processing request carries data to be answered; The second screening component is configured to screen out a target model corresponding to the target requester from a plurality of candidate model parameters. Model parameters, wherein the target requester is the object that sends the problem processing request, the candidate model parameters are obtained by training the pre-trained processing model based on the sample set specified by the requester, and the requesters corresponding to the candidate model parameters are different; A second construction component is configured to construct a task processing model according to the target model parameters and the shared model parameters, wherein the shared model parameters are model parameters shared by the requesting parties in the pre-trained processing model, and the shared model parameters are fixed during the training of the pre-trained processing model; The second input component is configured to input the data to be answered into the task processing model to obtain a question answering result.

16. A computer program product, wherein: The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 11.

17. A computer program product, wherein: The invention comprises a non-volatile computer-readable storage medium storing a computer program, wherein the computer program implements the method according to any one of claims 1 to 11 when executed by a processor.

18. A computer program, wherein When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

19. A computing device comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method described in any one of claims 1 to 11 are implemented.

20. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the steps of the method according to any one of claims 1 to 11.

Images