Data processing method, problem processing method, computing device and storage medium

Through multi-stage data inference and data update methods, the problem of low inference efficiency of neural network models in complex data processing is solved, data processing efficiency is improved, and data processing needs are met in practical applications.

CN119005329APending Publication Date: 2024-11-22ALIBABA (CHINA) CO LTD

Patent Information

Application Number
CN202410897972.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-04
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

Neural network models are less inference efficient when processing complex and large data data, making it difficult for the existing technology to meet practical application needs.

Method used

Through the multi-stage data inference method, the initial data is decomposed using the data processing model, and data updates and inferences are gradually performed until an updated data with a smaller number of data is obtained, and whether inference continues to be continued at each stage is verified to avoid repeated calculations.

Benefits of technology

The overall inference efficiency of the data processing model is improved, the problem of inference efficiency of neural network models in complex data processing is avoided, and the demand for various types of data processing is met.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005329A_ABST
    Figure CN119005329A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a data processing method, a problem processing method, computing equipment and a storage medium, and the data processing method comprises the steps: determining initial data, and carrying out the data reasoning of the initial data through a data processing model, and obtaining an initial reasoning result; under the condition that it is determined that the initial data meets a data reasoning condition according to the initial reasoning result, data updating is conducted on the initial data through the data processing model according to the initial reasoning result, updated data are obtained, the data number of the updated data is smaller than that of the initial data, and the data processing model is used for processing the updated data. The data processing model is a machine learning model; performing data reasoning on the updated data by using the data processing model to obtain an updated reasoning result; and determining the update reasoning result as a target data processing result under the condition of determining that the update data does not meet the data reasoning condition according to the update reasoning result.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of this specification relate to the field of computer technology, and in particular, to a data processing method; one or more embodiments of this specification also relate to a problem handling method, a computing device, a computer-readable storage medium, and a computer program product. Background Art

[0002] With the continuous development of artificial intelligence technology, neural network models can be used to process various types of data to meet the needs of practical applications.

[0003] In the prior art, the data to be processed can be input into a neural network model, and the neural network model can be used to perform data reasoning to obtain corresponding data reasoning results; however, when the neural network model processes more complex and large data volumes, there will be a problem of low reasoning efficiency. Therefore, how to improve the data reasoning efficiency of the neural network model has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In view of this, an embodiment of this specification provides a data processing method. One or more embodiments of this specification also relate to a problem processing method, a data processing device, a problem processing device, a computing device, a computer-readable storage medium, and a computer program product to solve the technical defect of low data reasoning efficiency of neural network models in the prior art.

[0005] According to a first aspect of an embodiment of this specification, a data processing method is provided, including:

[0006] Determine initial data, and use a data processing model to perform data reasoning on the initial data to obtain initial reasoning results;

[0007] When it is determined that the initial data meets the data reasoning condition according to the initial reasoning result, the initial data is updated using the data processing model according to the initial reasoning result to obtain updated data, wherein the data quantity of the updated data is less than the data quantity of the initial data, and the data processing model is a machine learning model;

[0008] Performing data reasoning on the update data using the data processing model to obtain an update reasoning result;

[0009] When it is determined according to the update reasoning result that the update data does not satisfy the data reasoning condition, the update reasoning result is determined as the target data processing result.

[0010] According to a second aspect of an embodiment of this specification, there is provided a data processing device, including:

[0011] A first result determination module is configured to determine initial data, and perform data reasoning on the initial data using a data processing model to obtain an initial reasoning result;

[0012] a data updating module configured to, when it is determined that the initial data meets the data reasoning condition according to the initial reasoning result, update the initial data using the data processing model according to the initial reasoning result to obtain updated data, wherein the data quantity of the updated data is less than the data quantity of the initial data, and the data processing model is a machine learning model;

[0013] A second result determination module is configured to perform data reasoning on the update data using the data processing model to obtain an update reasoning result;

[0014] The third result determination module is configured to determine the updated reasoning result as the target data processing result when it is determined based on the updated reasoning result that the updated data does not satisfy the data reasoning condition.

[0015] According to a third aspect of the embodiments of this specification, a problem handling method is provided, including:

[0016] Determine an initial question text, and use a data processing model to perform question reasoning on the initial question text to obtain an initial question reasoning result;

[0017] When it is determined that the initial question text satisfies the question reasoning condition according to the initial question reasoning result, the initial question text is updated by using the data processing model according to the initial question reasoning result to obtain an updated question text, wherein the amount of data in the updated question text is less than the amount of data in the initial question text, and the data processing model is a machine learning model;

[0018] Performing question reasoning on the update question text using the data processing model to obtain an update question reasoning result;

[0019] When it is determined according to the update question reasoning result that the update question text does not satisfy the question reasoning condition, the update question reasoning result is determined as the target question processing result.

[0020] According to a fourth aspect of the embodiments of this specification, there is provided a problem handling device, including:

[0021] A first result determination module is configured to determine an initial question text, and perform question reasoning on the initial question text using a data processing model to obtain an initial question reasoning result;

[0022] A question updating module is configured to, when it is determined that the initial question text meets the question reasoning condition according to the initial question reasoning result, update the initial question text according to the initial question reasoning result using the data processing model to obtain an updated question text, wherein the data amount of the updated question text is less than the data amount of the initial question text, and the data processing model is a machine learning model;

[0023] A second result determination module is configured to perform question reasoning on the update question text using the data processing model to obtain an update question reasoning result;

[0024] The third result determination module is configured to determine the update question reasoning result as the target question processing result when it is determined that the update question text does not meet the question reasoning condition according to the update question reasoning result.

[0025] According to a fifth aspect of an embodiment of this specification, a computing device is provided, including:

[0026] Memory and processor;

[0027] The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer programs / instructions are executed by the processor, the steps of the above-mentioned data processing method or problem processing method are implemented.

[0028] According to the sixth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores a computer program / instruction, and when the computer program / instruction is executed by a processor, the steps of the above-mentioned data processing method or problem processing method are implemented.

[0029] According to a seventh aspect of the embodiments of this specification, a computer program product is provided, including a computer program / instruction, which implements the steps of the above-mentioned data processing method or problem processing method when executed by a processor.

[0030] The data processing method provided in one or more embodiments of the present specification, in the process of using the data processing model to perform data processing, first, the data processing model is used to perform the first stage of data reasoning on the initial data to obtain the initial reasoning result; and, when it is determined according to the initial reasoning result that the initial data meets the data reasoning condition, the initial data is updated according to the initial reasoning result, so as to obtain updated data with a smaller data amount; then, the data processing model is used to perform the second stage of data reasoning on the updated data with a smaller data amount, so as to quickly obtain the updated reasoning result. Since the data processing model can quickly reason on the updated data with a smaller data amount, although it is necessary to reason through multiple stages, the overall data reasoning efficiency will be higher than the data reasoning efficiency of the data processing model for data with a larger data amount, thereby improving the data reasoning efficiency of the data processing model and avoiding the problem of low reasoning efficiency of the neural network model in the process of processing more complex and large data; and, when it is determined according to the updated reasoning result that the updated data does not meet the data reasoning condition, it is determined to end the data reasoning and determine the updated reasoning result as the target data processing result, thereby meeting the need to use the neural network model to process various types of data in practical applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is an application schematic diagram of a data processing method provided by an embodiment of this specification;

[0032] Figure 2 is a flow chart of a data processing method provided by an embodiment of this specification;

[0033] Figure 3 is a processing flow chart of a data processing method provided by an embodiment of this specification;

[0034] Figure 4 is a flow chart of a problem handling method provided by an embodiment of this specification;

[0035] Figure 5 is a structural schematic diagram of a data processing device provided by an embodiment of this specification;

[0036] Figure 6 It is a structural schematic diagram of a problem handling device provided by an embodiment of this specification;

[0037] Figure 7 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0038] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0039] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0040] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, 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".

[0041] 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 this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0042] In one or more embodiments of this specification, 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 10 trillion model parameters. A large model can also be called a foundation model / foundation model (Foundation Model 1). The large model is pre-trained with 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 (Large Language Model 1, LLM), a multi-modal pre-training model (multi-modal pre-training model 1), etc.

[0043] When the big model is 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. The big model can be widely used in natural language processing (NLP), computer vision and other fields. Specifically, it can be applied to computer vision tasks such as visual question answering (VQA), image description (IC), 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 the big model include digital assistants, intelligent robots, search, online education, office software, e-commerce, intelligent design, etc.

[0044] First, the terms involved in one or more embodiments of this specification are explained.

[0045] RAG (Retrieval-augmented Generation): refers to retrieval-augmented generation, which is a retrieval-augmented generation model that combines retrieval and generation technologies; the retrieval-augmented generation model combines language models and information retrieval technology. Specifically, when the model needs to generate text or answer questions, it will first retrieve relevant information from a large document collection, and then use the retrieved information to guide text generation, thereby improving the quality and accuracy of predictions.

[0046] Markov Chain (MC): It is a stochastic process with Markov property in probability theory and mathematical statistics and exists in discrete index set and state space; its main idea is: a random process that changes from one state to another in state space. This process requires the property of "no memory": the probability distribution of the next state can only be determined by the current state, and the previous events in the time series are irrelevant to it.

[0047] CoT (Chain of Thought): refers to the chain of thought of large models. The chain of thought of large models is an advanced prompting project that aims to enhance the performance of large language models in various complex reasoning tasks. The performance of large models can be significantly improved by allowing large models to gradually participate in the process of decomposing a complex problem into sub-problems step by step and solving them in sequence. The intermediate steps of this series of reasoning are called the Chain of Thought.

[0048] too ls: refers to tools, which are various external tools that can be called by large models.

[0049] Reduction: refers to the process of converting a complex problem into one or more known, simpler problems. This conversion allows the original problem to be solved indirectly by solving these simpler problems.

[0050] Process: refers to a series of steps or strategies used when performing data reasoning. For example, a series of steps or strategies used when solving mathematical problems include selecting appropriate theorems, formulas, algorithms or methods to gradually approach the solution to the problem. For example, when solving a complex integral problem, a series of steps such as substitution and partial integration may be required. These can all be considered "processes".

[0051] Markov chain thinking: a model used to describe and infer system behavior, that is, to build LLM based on Markov chain and large model chain thinking.

[0052] Reasoning task: refers to the task of inferring unknown information through known information and reasoning rules.

[0053] ToT (Tree of Thoughts): A new language model reasoning framework. The tree provides a more structured prompt framework for LLM reasoning by breaking down complex problems into smaller problems that are easier to solve.

[0054] PoT: refers to thinking program reasoning, which converts the natural description language of the thinking chain into a thinking program based on CoT, and can perform better in reasoning.

[0055] With the continuous development of artificial intelligence technology, neural network models can be used to process various types of data to meet the needs of practical applications; for example, with the rapid development of artificial intelligence and natural language processing technology, large language models have become a hot research field in recent years; however, large models still perform poorly in logical reasoning, that is to say, large models have certain challenges and limitations in the field of reasoning (especially mathematical logic reasoning).

[0056] In practical applications, the reasoning methods of large models are divided into single-step reasoning and multi-step reasoning. Among them, single-step reasoning can solve simple problems and has relatively high reasoning efficiency; among them, multi-step reasoning has stronger reasoning logic and higher reasoning accuracy. However, multi-step reasoning has a big flaw: as the reasoning process deepens, it is easy to have hallucinations and low reasoning efficiency.

[0057] In response to the above problems, this specification provides a solution for logical reasoning using CoT, PoT, ToT, etc., but this solution has problems such as low decoding efficiency, accumulated decoding errors, and low utilization of training data.

[0058] Based on this, a data processing method is provided in this specification. One or more embodiments of this specification also involve a problem processing method, a data processing device, a problem processing device, a computing device, a computer-readable storage medium and a computer program product, which are described in detail one by one in the following embodiments.

[0059] See also Figure 1 , Figure 1 A schematic diagram of an application of a data processing method provided according to an embodiment of the present specification is shown. Figure 1 It can be seen that the user can send a question to the server 104 through the terminal 102, and the server 104 is the server used by the data processing method in one or more embodiments of this specification; after receiving the question, the server 104 inputs the question into the LLM large model, uses the large model to perform one-step reasoning on the current question, completes the one-step reasoning to obtain the reasoning result of the first stage, and then uses the question and the reasoning result to obtain a new question; uses the large model to perform one-step reasoning on the new question to obtain the reasoning result of the second stage, and again obtains a simpler question that is consistent with the answer to the new question based on the reasoning result and the new question; repeats this process until the answer can be obtained through question solving, and the answer corresponding to the user's question is obtained; and then the answer is sent to the terminal 102. In the above steps, by converting the long sequence reasoning process in the original complex problem into multiple short sequence reasoning processes, the reasoning cost of the large model is significantly reduced, and the reasoning efficiency of the large model is improved.

[0060] See also Figure 2 , Figure 2 A flow chart of a data processing method provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0061] Step 202: Determine initial data, and use a data processing model to perform data reasoning on the initial data to obtain initial reasoning results.

[0062] The initial data can be understood as data that needs to be processed using a data processing model, and the initial data can be any type of data, for example, the initial data can be text data, code data, language data, video data, image data, etc. In other words, the initial data can be initial question text, initial code data, initial voice data, initial image data, initial video data, etc., and no specific limitation is made here.

[0063] The data processing model can be understood as a neural network model that can perform data processing. The data processing model can be an LLM or a machine learning model. It should be noted that when the data processing method is applied to different scenarios, the data processing model is also different. For example, when the data processing method is applied to a problem reasoning scenario, the initial data can be an initial problem text; the initial reasoning result can be an initial problem reasoning result; the data processing model can be a problem processing model, which is used to perform problem reasoning and update the initial problem text; based on this, by inputting the initial problem text into the problem processing model, the problem reasoning result (such as the answer to the question) output by the problem processing model is obtained, thereby meeting the need to use a neural network model for problem reasoning in practical applications.

[0064] For another example, when the data processing method is applied to a code optimization scenario, the initial data may be initial code data; the initial reasoning result may be an initial code optimization result for the initial code data; the data processing model may be a code optimization model for performing code optimization and updating the initial code data; based on this, by inputting the initial code data into the code optimization model, the optimized code data (i.e., the target data processing result) output by the code optimization model is obtained, thereby meeting the need to use a neural network model for code optimization in actual applications.

[0065] The initial reasoning result can be understood as the processing result obtained after using the data processing model to perform the first stage of data reasoning on the initial data; the first stage of data reasoning can be understood as data reasoning on the initial sub-data in the initial data; for example, when the initial data is an initial question text, the initial sub-data can be a sub-problem constituting the initial question text; based on this, the initial reasoning result can be the problem reasoning result obtained by using the data processing model to perform problem reasoning on the sub-problems in the initial question text; for another example, when the initial data is initial code data, the initial sub-data can be one or more code statements in the initial code data; based on this, the initial reasoning result can be the code optimization result obtained by using the code optimization model to perform code optimization on one or more code statements in the initial code data.

[0066] In one or more embodiments provided in this specification, taking into account the problem of low reasoning efficiency when a neural network model processes relatively complex data with a large amount of data, the data processing method provided in this specification can use multi-stage data reasoning to process the initial data, and each stage can perform data reasoning on the initial sub-data in the initial data until the data reasoning for the initial data is completed; the specific implementation method is as follows.

[0067] The using the data processing model to perform data reasoning on the initial data to obtain an initial reasoning result includes:

[0068] Inputting the initial data into the data processing model, performing data extraction on the initial data using the data processing model, and determining a plurality of initial sub-data contained in the initial data;

[0069] The sub-data to be inferred are determined from the multiple initial sub-data, and semantic reasoning is performed on the sub-data to be inferred to obtain the initial reasoning result.

[0070] Among them, the initial sub-data can be understood as the sub-data constituting the initial data. When the initial data is the initial question text, the initial sub-data can be the sub-question text in the initial question text. For example, the initial question text can be "What is 1+2×3 equal to?", and correspondingly, the multiple sub-question texts are "What is 1+2 equal to?", "What is 2×3 equal to?"; the initial question text can be "Who is the father of A's wife?", and correspondingly, the multiple sub-question texts are "Who is A's wife?", "Who is the father of the wife?"; when the initial data is the initial video data, the initial sub-data can be one or more video frames in the initial video data; when the initial data is the initial image data or the initial audio data, the initial sub-data can be a local image area in the initial image data or a small segment of audio data in the initial audio data, etc.; when the initial data is the initial code data, the initial sub-data can be one or more code statements in the initial code data. For example, the initial code data can be "int main(){

[0071]

[0072] Correspondingly, the initial sub-data may be one or more code statements in the initial code data. For example, the initial sub-data may be two code statements “int a=5;, int b=10;”.

[0073] Among them, the sub-data to be inferred can be understood as the sub-data among multiple initial sub-data that currently needs to use the data processing model for data reasoning; the sub-data to be inferred can be any initial sub-data among the multiple initial sub-data, or the initial sub-data determined according to data reasoning rules (such as mathematical operation rules, code running rules) that need to perform first-stage data reasoning; for example, the first sub-problem among multiple initial sub-problems, or the sub-problem determined according to mathematical operation rules that need to perform first-stage data reasoning, wherein, when the initial problem text is "What is 1+2×3 equal to", and the multiple sub-problem texts are "What is 1+2 equal to", "What is 2×3 equal to", the sub-problem determined according to the mathematical operation rules that needs to perform first-stage data reasoning can be understood as the sub-problem of "What is 2×3 equal to" determined by the data processing model according to the mathematical operation rules, which is the sub-problem for performing first-stage data reasoning.

[0074] The initial reasoning result can be understood as the result obtained by performing semantic reasoning on the sub-data to be reasoned using the data processing model. For example, when the sub-data to be reasoned is the sub-problem "What is 2×3 equal to", the initial problem reasoning result (i.e., the initial reasoning result) can be "2×3 equals 6"; when the sub-data to be reasoned is "int a=5;, int b=10;", two code statements that need to be optimized, the initial code optimization result (i.e., the initial reasoning result) can be "int a=5;, int b=10; which can be written as one code statement int a=5, b=10;".

[0075] The following is an example of the application of the data processing method provided in this specification in a problem reasoning scenario to illustrate the data processing method, wherein the initial data is the initial problem text, the data processing model is the problem processing model, the initial sub-data is the initial sub-problem, the sub-data to be reasoned is the sub-problem to be reasoned, and the initial reasoning result is the initial problem reasoning result; based on this, the data processing method provided in this specification can be applied to a data processing node, which, after determining the initial problem text, inputs the initial problem text into the trained problem processing model, and uses the problem processing model to perform problem extraction on the initial problem text, thereby identifying multiple initial sub-problems contained in the initial problem text; then, selects a sub-problem to be reasoned from the multiple initial sub-problems, and performs the first stage of problem reasoning on the sub-problem to be reasoned, thereby obtaining the initial problem reasoning result for the sub-problem to be reasoned.

[0076] It should be noted that the data processing node can be a service end, server, virtual machine, container, cloud server, client, mobile terminal and other devices, or the data processing node can be an application, software system and other software devices, which are not specifically limited here.

[0077] In the above embodiment, in the process of using the data processing model to perform data reasoning on the initial data to obtain the initial reasoning result, the sub-data to be inferred is determined from the multiple initial sub-data contained in the initial data by using the data processing model, and data reasoning is performed on the sub-data to be inferred to obtain the initial reasoning result; because the data processing model can quickly and accurately perform data reasoning on relatively simple sub-data with a smaller amount of data, therefore, when the data processing model is used to process the initial sub-data in a multi-stage data reasoning manner, data reasoning can be efficiently realized for the initial data, thereby avoiding the problem of low reasoning efficiency when the neural network model is used to process relatively complex data with a larger amount of data.

[0078] In one or more embodiments provided in this specification, the data processing node used by the data processing method can receive initial data sent by the user based on the client, and can subsequently perform data processing on the initial data. The specific implementation method is as follows.

[0079] The determining of initial data comprises:

[0080] Receiving the initial data sent by the client, wherein the initial data is generated by the client according to a data processing operation performed by the user on the data processing page;

[0081] The client may be a mobile terminal, a smart device or other server-side device, or the client may be an application, a software system or other software.

[0082] The data processing page may be understood as a user interaction interface displayed in the client for implementing user data processing; the data processing page may be a web page, an application program interface, and the like.

[0083] The data processing operation may be an operation performed by a user based on the data processing page, such as inputting data, clicking a button, etc. to trigger a data processing control in the data processing page.

[0084] Continuing with the above example, the client can display a data processing page to the user, and the user performs data processing operations based on the data processing controls (such as buttons, input boxes, etc.) in the data processing page, thereby triggering the client to generate initial data, and send the initial data to the data processing node, instructing the data processing node to use the data processing model to perform data processing operations on the initial data.

[0085] In the above embodiment, the user implements the data processing operation on the initial data by using the client and the data processing page, thereby satisfying the user's need to use the data processing model to process the initial data.

[0086] Step 204: When it is determined that the initial data meets the data reasoning conditions based on the initial reasoning result, the initial data is updated using the data processing model according to the initial reasoning result to obtain updated data, wherein the amount of data in the updated data is less than the amount of data in the initial data, and the data processing model is a machine learning model.

[0087] Among them, the data reasoning condition can be understood as the condition that the data processing model needs to be used again for data reasoning. The data reasoning condition can be set according to the actual application scenario. For example, satisfying the data reasoning condition can be understood as not completing the data reasoning operation for all the initial sub-data contained in the initial data, or the data can be updated based on the data reasoning result (such as the initial reasoning result, the updated reasoning result). For another example, not satisfying the data reasoning condition can be understood as completing the data reasoning operation for all the initial sub-data contained in the initial data, or the data cannot be updated based on the data reasoning result (such as the initial reasoning result, the updated reasoning result).

[0088] Updated data can be understood as data obtained after updating the initial data. For example, when the initial data is "1+2×3 equals to what" and the initial reasoning result is "2×3 equals to 6", the updated data can be "1+6 equals to what"; for another example, when the initial reasoning result is "int a=5;, int b=10; which can be written as a code statement int a=5, b=10;", the updated data can be "

[0089]

[0090] In one or more embodiments provided in this specification, during the process of multi-stage data reasoning, a check can be performed at each stage as to whether to continue reasoning, so that it can be determined in a timely manner whether the reasoning is completed. The specific implementation method is as follows.

[0091] The determining, based on the initial reasoning result, that the initial data satisfies a data reasoning condition includes:

[0092] Determining initial sub-data contained in the initial data using the data processing model;

[0093] Performing semantic analysis on the initial sub-data and the initial reasoning result, and determining that the initial data meets the data reasoning condition when it is determined that there are multiple initial sub-data and there is sub-data to be updated associated with the initial reasoning result among the multiple initial sub-data;

[0094] Among them, the sub-data to be updated can be understood as the sub-data that needs to be updated using the initial reasoning results. For example, when multiple sub-problem texts are "What is 1+2 equal to?", "What is 2×3 equal to?", and the initial reasoning result is "2×3 equals 6", the large model can be used to determine from multiple sub-problem texts that the sub-problem "What is 2×3 equal to" is the sub-data to be updated, and the sub-data to be updated can be subsequently updated based on the initial reasoning result.

[0095] Continuing with the above example, after using the data processing model to determine the initial problem reasoning result "2×3 equals 6", the initial problem reasoning result and the initial problem are input into the large model again for verification to determine whether to continue problem reasoning (i.e., problem reduction). When it is determined that the initial problem contains multiple sub-problems, and among the multiple sub-problems there is a sub-problem to be updated corresponding to "2×3 equals 6" "What is 2×3 equals", it is determined that problem reduction can continue.

[0096] In the above embodiment, during the multi-stage data reasoning process, by verifying whether to continue reasoning at each stage, it is possible to promptly determine whether the reasoning is completed, thereby avoiding wasting computing resources due to repeated reasoning.

[0097] In one or more embodiments provided in this specification, the initial data is an initial question text, the initial reasoning result is an initial question reasoning result, and the data processing model is a question processing model;

[0098] When it is determined according to the initial reasoning result that the initial data meets the data reasoning condition, updating the initial data using the data processing model according to the initial reasoning result to obtain updated data includes:

[0099] When it is determined that the initial question text meets the question reasoning condition according to the initial question reasoning result, the initial question text is updated by using the question processing model according to the initial question reasoning result to obtain an updated question text.

[0100] The problem reasoning condition may be problem reduction.

[0101] For the explanation of this embodiment, reference may be made to the corresponding or corresponding explanations in one or more other embodiments.

[0102] In one or more embodiments provided in this specification, taking into account the problem of low reasoning efficiency when a neural network model processes relatively complex data with a large amount of data, the data processing method provided in this specification can process the initial data through multi-stage data reasoning, and in the processing process of each stage, the data reasoning result is used to update the data to be reasoned (such as initial data) in the current stage to obtain data with a smaller amount of data. The specific implementation method is as follows.

[0103] The method of updating the initial data using the data processing model according to the initial reasoning result to obtain updated data includes steps 1 and 2:

[0104] Step 1: using the data processing model, determine a plurality of initial sub-data contained in the initial data, and determine the sub-data to be updated associated with the initial reasoning result from the plurality of initial sub-data.

[0105] Specifically, the using the data processing model to determine a plurality of initial sub-data contained in the initial data, and determining the sub-data to be updated associated with the initial reasoning result from the plurality of initial sub-data, includes:

[0106] Inputting the initial reasoning result and the initial data into the data processing model, performing data extraction on the initial data using the data processing model, and determining the multiple initial sub-data contained in the initial data;

[0107] Semantic analysis is performed on each initial sub-data and the initial reasoning result to obtain the sub-data to be updated associated with the initial reasoning result.

[0108] Continuing with the above example, after using the data processing model to determine the inference result of the initial problem "2×3 equals 6", the initial problem inference result and the initial problem are input into the large model again for semantic analysis. From the multiple sub-problems contained in the initial problem, the updated sub-problem "2×3 equals what" corresponding to "2×3 equals 6" is determined to facilitate subsequent problem reduction.

[0109] In the above embodiment, in the process of using the data processing model to determine multiple initial sub-data contained in the initial data, and determining the sub-data to be updated associated with the initial reasoning result from the multiple initial sub-data, the data processing model can be used to perform semantic analysis on the multiple initial sub-data contained in the initial data, so as to determine the sub-data to be updated associated with the initial reasoning result, so as to facilitate the subsequent use of the initial reasoning result to accurately update the sub-data to be updated, avoid the semantic deviation of the initial data due to update errors, and ensure the accuracy of the target data processing results.

[0110] Step 2: Using the data processing model, based on the initial reasoning result, update the sub-data to be updated in the initial data to obtain the updated data.

[0111] Specifically, the using the data processing model to update the sub-data to be updated in the initial data based on the initial reasoning result to obtain the updated data includes:

[0112] Using the data processing model, based on the initial reasoning result, the sub-data to be updated in the initial data is replaced to obtain the updated data; or

[0113] The data processing model is used to semantically rewrite the sub-data to be updated in the initial data based on the initial reasoning result to obtain the updated data.

[0114] Continuing with the above example, the initial problem reasoning result can be "2×3 equals 6" or "6"; based on this, when the data processing model is used to determine the updated sub-problem "2×3 equals what" corresponding to the initial problem reasoning result "6", the updated sub-problem "2×3 equals what" in the initial problem text "1+2×3 equals what" can be directly replaced based on the initial problem reasoning result to obtain the replaced problem text "1+6 equals what", thereby achieving problem reduction.

[0115] When the initial question reasoning result is “2×3 equals 6”, the data processing model can be used to semantically rewrite the sub-data “2×3 equals how much” to be updated in the initial question text “1+2×3 equals how much” based on the initial question reasoning result “2×3 equals 6” to obtain the semantically rewritten question text “1+6 equals how much”, thereby achieving problem reduction.

[0116] In the above embodiment, the data to be inferred (eg, initial data) at the current stage is updated by using the data inference result to obtain data with a smaller amount of data, thereby improving the data processing efficiency of the subsequent data processing model.

[0117] Step 206: Use the data processing model to perform data reasoning on the update data to obtain an update reasoning result.

[0118] Among them, using the data processing model to perform data reasoning on the updated data to obtain updated reasoning results can refer to the above-mentioned steps of using the data processing model to perform data reasoning on the initial data to obtain initial reasoning results, which will not be elaborated here.

[0119] Continuing with the above example, the updated question text can be "What is 1+6 equal to?", which is input into the large model for semantic reasoning to obtain the corresponding reasoning result "1+6 equals 7".

[0120] Step 208: When it is determined according to the update reasoning result that the update data does not satisfy the data reasoning condition, the update reasoning result is determined as the target data processing result.

[0121] Among them, the target data processing result is understood to be the processing result for the initial data. For example, when the initial data is the initial question text, the target data processing result can be the answer to the question corresponding to the question text; when the initial data is the initial code data, the target data processing result can be the code data obtained after optimizing the initial code data; it should be noted that the initial reasoning result can be the reasoning result for a certain initial sub-data in the initial data, and the updated reasoning result can be the reasoning result for a certain updated sub-data in the updated data; the target data processing can be the overall processing result for the initial data; and, when the updated reasoning result determines that the updated data does not meet the data reasoning conditions, the updated reasoning result can be determined as the target data processing result.

[0122] Continuing with the above example, when it is determined that the update question reasoning result corresponding to the update question text (i.e., the update reasoning result) is "1+6 equals 7", the update question reasoning result and the update question are input into the large model again for semantic analysis. When it is determined that the update question contains only one sub-question "what is 1+6 equal to", and the sub-question is associated with the update question reasoning result, it is determined that the multi-stage data reasoning is completed, so that the update question reasoning result "the answer equals 7" is used as the final answer (i.e., the target data processing result). Alternatively, when the update question reasoning result is "1+6 equals 7", "1+6 equals 7" is converted into the question answer "1+2×3 equals 7" (i.e., the target data processing result).

[0123] In one or more embodiments provided in this specification, during the process of multi-stage data reasoning, it is necessary to verify whether to continue reasoning at each stage so as to promptly determine whether the reasoning is completed. The specific implementation method is as follows.

[0124] The determining, according to the update reasoning result, that the update data does not satisfy the data reasoning condition includes:

[0125] Determining the update sub-data included in the update data by using the data processing model;

[0126] Semantic analysis is performed on the update sub-data and the update reasoning result, and when it is determined that the update sub-data is one and the update sub-data is associated with the update reasoning result, it is determined that the update data does not satisfy the data reasoning condition.

[0127] The update sub-data may be understood as the sub-data included in the update data. For example, when the update data is an update question text, the update sub-data may be understood as the sub-question text included in the update question text.

[0128] Continuing with the above example, when it is determined that the update problem reasoning result corresponding to the update problem text (i.e., the update reasoning result) is "1+6 equals 7", the update problem reasoning result and the update problem are input into the large model again for semantic analysis. When it is determined that the update problem contains only one sub-problem "1+6 equals multiple", and this sub-problem is associated with the update problem reasoning result, it is determined that the multi-stage data reasoning is completed.

[0129] In the above embodiment, during the multi-stage data reasoning process, by verifying whether to continue reasoning at each stage, it is possible to promptly determine whether the reasoning is completed, thereby avoiding wasting computing resources due to repeated reasoning.

[0130] In one or more embodiments provided in this specification, the data processing node used by the data processing method can display the target data processing results to the client after receiving the initial data sent by the user based on the client and performing data processing on the initial data. The specific implementation method is as follows.

[0131] After determining, based on the update reasoning result, that the update data does not satisfy the data reasoning condition, the update reasoning result is determined as the target data processing result, the method further includes:

[0132] The target data processing result is sent to the client, so that the client displays the target data processing result based on the data processing page.

[0133] Among them, displaying the target data processing result based on the data processing page can be understood as displaying the target data processing result to the user based on the data processing page, or displaying the target data processing result to other objects based on the data processing page. The other object may be an object that needs to obtain the target data processing result, for example, the user may be a teacher, and the other object may be a student.

[0134] In the above embodiment, the target data processing result is displayed by using the client and the data processing page, thereby satisfying the user's need to use the data processing model to process the initial data.

[0135] In one or more embodiments provided in this specification, during the process of multi-stage data reasoning, it is necessary to verify whether to continue reasoning at each stage so as to promptly determine whether the reasoning is completed. The specific implementation method is as follows.

[0136] After performing data reasoning on the update data using the data processing model to obtain an update reasoning result, the method further includes:

[0137] When it is determined that the updated data satisfies the data reasoning condition according to the update reasoning result, the updated data is updated using the data processing model according to the update reasoning result to obtain second updated data, wherein the data quantity of the second updated data is less than the data quantity of the updated data;

[0138] The second update data is determined as the update data, and the step of performing data reasoning on the update data using the data processing model to obtain an update reasoning result is continued until it is determined, based on the update reasoning result, that the update data does not satisfy the data reasoning condition.

[0139] Continuing with the above example, the initial problem may be “what is 1+1+2×3 equal to”, the update problem may be “what is 1+1+6 equal to”, and the update problem reasoning result for the subproblem “what is 1+1 equal to” in the update problem may be “1+1 equals 2”. Based on this, after the update problem reasoning result “1+1 equals 2” is determined using the data processing model, the update problem reasoning result and the update problem are input into the large model again for verification to determine whether to continue problem reasoning (i.e., problem reduction). When it is determined that the update problem contains multiple subproblems “what is 1+1 equal to” and “what is 1+6 equal to”, and there is a subproblem “what is 1+1 equal to” to be updated corresponding to “1+1 equals 2” among the multiple subproblems, it is determined that problem reduction can continue.

[0140] The data processing method provided in one or more embodiments of the present specification, in the process of using the data processing model to perform data processing, first, the data processing model is used to perform the first stage of data reasoning on the initial data to obtain the initial reasoning result; and, when it is determined according to the initial reasoning result that the initial data meets the data reasoning condition, the initial data is updated according to the initial reasoning result, so as to obtain updated data with a smaller data amount; then, the data processing model is used to perform the second stage of data reasoning on the updated data with a smaller data amount, so as to quickly obtain the updated reasoning result. Since the data processing model can quickly reason on the updated data with a smaller data amount, although it is necessary to reason through multiple stages, the overall data reasoning efficiency will be higher than the data reasoning efficiency of the data processing model for data with a larger data amount, thereby improving the data reasoning efficiency of the data processing model and avoiding the problem of low reasoning efficiency of the neural network model in the process of processing more complex and large data; and, when it is determined according to the updated reasoning result that the updated data does not meet the data reasoning condition, it is determined to end the data reasoning and determine the updated reasoning result as the target data processing result, thereby meeting the need to use the neural network model to process various types of data in practical applications.

[0141] The following combination Figure 3 , taking the application of the data processing method provided in this specification in a data reasoning scenario as an example, the data processing method is further described. Figure 3 A flowchart of a data processing method provided by an embodiment of the present specification is shown. Figure 3 It can be seen that the data processing method provided in this specification can combine the Markov chain with CoT, PoT, or ToT. The core idea is to convert the problem into multiple independent problem reasoning and sub-problem generation; that is, the multi-step reasoning problem is converted into a process of multiple independent problem reasoning and sub-problem generation, and the reasoning process of the problem is completed through multiple rounds of iterations; specifically, the following steps are included.

[0142] Step 302: Input the question 1 provided by the user into the LLM for reasoning.

[0143] Specifically, question 1 can be understood as a question that requires the use of LLM to perform problem reasoning to obtain an answer. Question 1 can be the original question input by the user. For example, question 1 can be "given that s in a = 1 / 2, and a is the first quadrant angle, solve tan a?".

[0144] Step 304: Determine the inference result 1 obtained by the LLM for problem reasoning on problem 1, and perform problem reduction on problem 1 based on the inference result 1 to obtain problem 2.

[0145] Specifically, the data processing method provided in this specification can complete the reasoning process of the problem through a multi-stage iteration. During this process, the original large model LLM will use the information of the previous reasoning to perform the reasoning of the current step (i.e., the current stage); thereby converting the problem reasoning steps for the original problem into a more streamlined process in which a large model only needs to complete one step of reasoning through the current problem to complete the entire task reasoning.

[0146] Among them, the one-step reasoning refers to simplifying / transforming and solving one or more sub-problems (i.e. known conditions) in the original problem in the form of large model + too ls or large model CoT.

[0147] Based on this, the execution method of step 304 is: the LLM large model can be used to perform one-step reasoning on the sub-problem in the current problem (i.e., problem 1); after the one-step reasoning is completed, the reasoning result 1 corresponding to the sub-problem (i.e., step-wise solution) is obtained;

[0148] Then, a new question (ie, question 2) is obtained using the original question and the inference result 1, and the new question has the same answer as the original question.

[0149] Among them, the new problem is obtained by reducing problem 1 using reasoning result 1.

[0150] Problem reduction: refers to using the text generation capability of the large model to replace and rewrite the known conditions in the original problem based on the original problem and the simplified conditions in the one-step reasoning process (i.e., the reasoning result), thereby obtaining a new problem that is simpler than the original problem;

[0151] For example, let's take the above problem 1 as an example to explain the problem reduction; the original problem is "Given that s in a = 1 / 2, and a is a first quadrant angle, find tan a?"; The reasoning result obtained by performing one-step reasoning on it is: "Because s in a = 1 / 2, and a is a first quadrant angle, we can get a = 30 degrees"; that is to say, this one-step reasoning is to perform problem reasoning on the sub-problem of "Given that s in a = 1 / 2, and a is a first quadrant angle" in the original problem, so as to obtain the corresponding reasoning result.

[0152] Then, based on the reasoning result, the sub-problem "Given that s in a = 1 / 2, and a is a first quadrant angle" in the original problem "Given that s in a = 1 / 2, and a is a first quadrant angle, find tan a?" can be replaced and rewritten, thereby converting the original problem into a new problem "Given that a = 30 degrees, find tan a?".

[0153] In addition, it should be noted that in the process of multi-stage problem reasoning, the large model needs to verify whether to continue the problem reasoning at each stage, so as to determine whether the reasoning is completed in a timely manner to avoid wasting computing resources due to repeated reasoning; the way the large model verifies whether to continue the problem reasoning can be seen in the following example:

[0154] For example, the original question may be “What is 1+2×3?”, and the corresponding sub-questions may be “What is 1+2?” and “What is 2×3?”. After the first stage of one-step reasoning on the original question, the reasoning result is determined to be “2×3 is equal to 6.”

[0155] After using the large model to determine that the reasoning result of one step of reasoning is "2×3 equals 6", the original question and the current reasoning result are input into the large model to verify whether to continue the question reasoning.

[0156] In the process of verifying whether to continue problem reasoning, the large model can determine whether the original problem contains multiple sub-problems, and whether there are sub-problems among the multiple sub-problems that can be reduced based on the reasoning results; if the original problem contains multiple sub-problems and there are sub-problems that can be reduced, it is determined that the problem reasoning needs to continue.

[0157] For example, when the large model determines that the current original problem contains two sub-problems, "What is 1+2 equal to" and "What is 2×3 equal to", and that the sub-problem exists in the sub-problem "What is 2×3 equal to" which can be reduced using the reasoning result "2×3 equals 6", it determines that it is necessary to continue problem reasoning.

[0158] When it is determined that the problem reasoning needs to be continued, the original problem is reduced based on the reasoning result to obtain a new problem, and the reasoning operation is continued based on the new problem until the data reasoning is completed.

[0159] Step 306: Input question 2 into the LLM to continue the reasoning step.

[0160] Step 308: Determine the inference result 2 obtained by the LLM in reasoning about problem 2, and perform problem reduction on problem 2 based on the inference result 2.

[0161] Specifically, the large model is used to perform one-step reasoning on the new problem. After obtaining reasoning result 2 (step-wise solution), reasoning result 2 is used again to reduce the new problem to obtain a problem that is consistent with the answer to the new problem but is simpler.

[0162] Repeat the above step of reasoning and problem reduction until the most concise problem N is obtained.

[0163] For example, when the original problem is “Given that s in a=1 / 2, and a is a first quadrant angle, find tan a?”, the most simplified problem N may be “Given that a=30 degrees, find tan a?”.

[0164] For another example, when the original question may be “What is 1+2×3 equal to?”, the most simplified question N may be “What is 1+6 equal to?”.

[0165] Step 310: Input question N into LLM to continue question reasoning.

[0166] Step 312: Obtain the final inference result N.

[0167] Specifically, the above-mentioned one-step reasoning and problem reduction process is repeated until the answer (ie, reasoning result N) is obtained through problem solving, and it is determined that the problem reasoning is completed.

[0168] It should be noted that the judgment conditions of the problem reasoning results can be:

[0169] During the multi-stage problem reasoning process, the large model needs to verify whether to continue the problem reasoning at each stage. During the verification process of whether to continue the problem reasoning, if it is determined that the original problem contains only one sub-problem and the sub-problem cannot be reduced, then it can be determined that the problem reasoning is over.

[0170] For example, when the large model determines that the current original problem contains a sub-problem of "what is 1+6 equal to", and that the sub-problem cannot be further reduced, it determines that the problem reasoning is finished.

[0171] Based on the above content, it can be seen that the data processing method in one or more embodiments of the present specification provides an efficient reasoning method based on Markov thought chain. The above illustrates the application of the Markov thought chain reasoning (MCTR) method in mathematical reasoning tasks; based on the above content, it can be seen that the present method regards the problem as a state, the solution as an action, abstracts the solution process as the process from the current state to the current action, and abstracts the reduction process as the state transition process from the current state to the next state, thereby realizing logical reasoning through multiple rounds of Markov state transitions.

[0172] It should be noted that the data processing method in one or more embodiments of this specification takes into account the defects of solutions using CoT, PoT, ToT and other methods for logical reasoning, and proposes corresponding solutions.

[0173] Among them, regarding the low utilization rate of training data: the large model training data in the above solution requires a complete reasoning link for each problem. The difficulty of constructing such data is relatively high, and the current reasoning link can only meet the reasoning of this problem, so the reasoning link is unique.

[0174] However, the data processing method in one or more embodiments of the present specification, after converting the model into the form of MCoT, will convert a complex problem into a series of one-step reasoning problems from difficult to simple sub-problems, called atomic steps, so that the uniqueness of the original reasoning link can be broken, ensuring that when solving new and more difficult problems, suitable steps can be found from the previous atomic steps and combined to achieve the solution.

[0175] Among them, regarding the low decoding efficiency: the data processing method in one or more embodiments of the present specification guides the reasoning efficiency / time of the large model to decrease significantly in the form of o(n^2) / exponential as the reasoning length increases. When converted into the form of MCoT, the reasoning process of each sub-problem will be very short, which will significantly reduce the attention window of the large model, significantly reduce the demand for video memory for large model decoding, and improve decoding efficiency.

[0176] Based on this, it can be seen that the data processing method in one or more embodiments of this specification, by adopting the Markov chain of thought (MCoT) reasoning method, divides mathematical logic reasoning into two processes: one-step reasoning and problem reduction, and uses the independence of each sub-problem reasoning to achieve problem reduction on the data set and effectively improve the decoding efficiency of the large model. The technical effect achieved by this method is:

[0177] First, through the two processes of one-step reasoning and problem reduction, the original complex problem is simplified into a simpler and more intuitive problem. At the same time, multiple complex problems can be converted into the same simple and intuitive problem (problem reduction process), thus reducing the difficulty of learning the original complex problem in the large model reasoning path learning (the large model transforms from learning to solve this complex problem into a combination of simplifying the complex problem and solving simple problems, and simple problems / one-step reasoning problems are more data in the large model training corpus and are easier to learn), achieving more efficient use of pre-trained models and task training data, and improving data utilization efficiency;

[0178] Secondly, by converting the long sequence reasoning process in the original complex problem into multiple short sequence reasoning processes, the reasoning cost of the large model is significantly reduced and the reasoning efficiency of the large model is improved (because in the reasoning process of the large model, each step of reasoning must interact with all the previous steps, which makes the decoding calculation amount and video memory occupancy very high. If the partitioned area reasoning is performed, these two points can be significantly optimized). The current solution can make the training of large models do not require longcontext (i.e. long context), which is an alternative to longcontext in reasoning generation; combined with rag, it can even solve all current longcontext needs.

[0179] Finally, the MCTR method has the following advantages: the process is more consistent with human reasoning logic, the reasoning process is efficient and accurate, and the data set does not need to be manually constructed.

[0180] See also Figure 4 , Figure 4 A flowchart of a problem handling method provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0181] Step 402: determine the initial question text, and use the data processing model to perform question reasoning on the initial question text to obtain the initial question reasoning result.

[0182] Step 404: When it is determined that the initial question text satisfies the question reasoning conditions based on the initial question reasoning result, the initial question text is updated using the data processing model based on the initial question reasoning result to obtain an updated question text, wherein the amount of data in the updated question text is less than the amount of data in the initial question text, and the data processing model is a machine learning model.

[0183] Step 406: Use the data processing model to perform question reasoning on the update question text to obtain an update question reasoning result.

[0184] Step 408: When it is determined that the updated question text does not satisfy the question reasoning condition according to the updated question reasoning result, the updated question reasoning result is determined as the target question processing result.

[0185] In one or more embodiments provided in this specification, determining the initial question text includes:

[0186] Receiving the initial question text sent by the client, wherein the initial question text is generated by the client according to the problem handling operation performed by the user on the problem handling page;

[0187] After determining, based on the update question reasoning result, that the update question text does not satisfy the question reasoning condition, the update question reasoning result is determined as the target question processing result, the method further includes:

[0188] The target problem processing result is sent to the client, so that the client displays the target problem processing result to the user based on the problem processing page.

[0189] In one or more embodiments of the present specification, the problem handling method provided, in the process of using the problem handling model to handle the problem, first, the problem handling model is used to perform the first stage of problem reasoning on the initial problem text to obtain the initial problem reasoning result; and, when it is determined according to the initial problem reasoning result that the initial problem text meets the problem reasoning condition, the initial problem text is updated according to the initial problem reasoning result, so as to obtain an updated problem text with a smaller amount of data; then, the problem handling model is used to perform the second stage of problem reasoning on the updated problem text with a smaller amount of data, so as to quickly obtain the updated problem reasoning result. Since the problem handling model can quickly reason on the updated problem text with a smaller amount of data, although it is necessary to reason through multiple stages, the overall reasoning efficiency will be higher than the problem reasoning efficiency of the problem handling model for the problem text with a larger amount of data, thereby improving the problem reasoning efficiency of the problem handling model and avoiding the problem of low reasoning efficiency in the process of the neural network model processing more complex and large data; and, when it is determined according to the updated problem reasoning result that the updated problem text does not meet the problem reasoning condition, it is determined to end the problem reasoning and determine the updated problem reasoning result as the target problem handling result, thereby meeting the need to use the neural network model to handle various types of problems in practical applications.

[0190] The above is an illustrative solution of a problem solving method of this embodiment. It should be noted that the technical solution of the problem solving method and the technical solution of the above data processing method belong to the same concept, and the details not described in detail in the technical solution of the problem solving method can be referred to the description of the technical solution of the above data processing method.

[0191] Corresponding to the above method embodiment, this specification also provides a data processing device embodiment, Figure 5 FIG. 1 is a schematic diagram showing the structure of a data processing device provided by an embodiment of the present specification. Figure 5 As shown, the device comprises:

[0192] The first result determination module 502 is configured to determine initial data and perform data reasoning on the initial data using a data processing model to obtain an initial reasoning result;

[0193] The data updating module 504 is configured to, when it is determined that the initial data meets the data reasoning condition according to the initial reasoning result, update the initial data using the data processing model according to the initial reasoning result to obtain updated data, wherein the data quantity of the updated data is less than the data quantity of the initial data, and the data processing model is a machine learning model;

[0194] A second result determination module 506 is configured to perform data reasoning on the update data using the data processing model to obtain an update reasoning result;

[0195] The third result determination module 508 is configured to determine the updated reasoning result as the target data processing result when it is determined that the updated data does not satisfy the data reasoning condition according to the updated reasoning result.

[0196] Optionally, the data updating module 504 is further configured to:

[0197] Using the data processing model, determining a plurality of initial sub-data contained in the initial data, and determining, from the plurality of initial sub-data, sub-data to be updated associated with the initial reasoning result;

[0198] The data processing model is used to update the sub-data to be updated in the initial data based on the initial reasoning result to obtain the updated data.

[0199] Optionally, the data updating module 504 is further configured to:

[0200] Using the data processing model, based on the initial reasoning result, the sub-data to be updated in the initial data is replaced to obtain the updated data; or

[0201] The data processing model is used to semantically rewrite the sub-data to be updated in the initial data based on the initial reasoning result to obtain the updated data.

[0202] Optionally, the data updating module 504 is further configured to:

[0203] Inputting the initial reasoning result and the initial data into the data processing model, performing data extraction on the initial data using the data processing model, and determining the multiple initial sub-data contained in the initial data;

[0204] Semantic analysis is performed on each initial sub-data and the initial reasoning result to obtain the sub-data to be updated associated with the initial reasoning result.

[0205] Optionally, the first result determination module 502 is further configured to:

[0206] Inputting the initial data into the data processing model, performing data extraction on the initial data using the data processing model, and determining a plurality of initial sub-data contained in the initial data;

[0207] The sub-data to be inferred are determined from the multiple initial sub-data, and semantic reasoning is performed on the sub-data to be inferred to obtain the initial reasoning result.

[0208] Optionally, the data processing device further includes a data reasoning module configured to:

[0209] When it is determined that the updated data satisfies the data reasoning condition according to the update reasoning result, the updated data is updated using the data processing model according to the update reasoning result to obtain second updated data, wherein the data quantity of the second updated data is less than the data quantity of the updated data;

[0210] The second update data is determined as the update data, and the step of performing data reasoning on the update data using the data processing model to obtain an update reasoning result is continued until it is determined, based on the update reasoning result, that the update data does not satisfy the data reasoning condition.

[0211] Optionally, the first result determination module 502 is further configured to:

[0212] Receiving the initial data sent by the client, wherein the initial data is generated by the client according to a data processing operation performed by the user on the data processing page;

[0213] The data processing device further includes a result sending module, which is configured to:

[0214] The target data processing result is sent to the client, so that the client displays the target data processing result based on the data processing page.

[0215] Optionally, the initial data is an initial question text, the initial reasoning result is an initial question reasoning result, and the data processing model is a question processing model;

[0216] The data updating module 504 is further configured to:

[0217] When it is determined that the initial question text meets the question reasoning condition according to the initial question reasoning result, the initial question text is updated by using the question processing model according to the initial question reasoning result to obtain an updated question text.

[0218] Optionally, the data updating module 504 is further configured to:

[0219] Determining initial sub-data contained in the initial data using the data processing model;

[0220] Performing semantic analysis on the initial sub-data and the initial reasoning result, and determining that the initial data meets the data reasoning condition when it is determined that there are multiple initial sub-data and there is sub-data to be updated associated with the initial reasoning result among the multiple initial sub-data;

[0221] The third result determination module 508 is configured to:

[0222] Determining the update sub-data included in the update data by using the data processing model;

[0223] Semantic analysis is performed on the update sub-data and the update reasoning result, and when it is determined that the update sub-data is one and the update sub-data is associated with the update reasoning result, it is determined that the update data does not satisfy the data reasoning condition.

[0224] The data processing device provided in one or more embodiments of the present specification, in the process of using the data processing model to perform data processing, first, uses the data processing model to perform the first stage of data reasoning on the initial data to obtain the initial reasoning result; and, when it is determined according to the initial reasoning result that the initial data meets the data reasoning condition, the initial data is updated according to the initial reasoning result, thereby obtaining updated data with a smaller data amount; then, the data processing model is used to perform the second stage of data reasoning on the updated data with a smaller data amount, thereby quickly obtaining the updated reasoning result. Since the data processing model can quickly reason on the updated data with a smaller data amount, although it is necessary to reason through multiple stages, the overall data reasoning efficiency will be higher than the data reasoning efficiency of the data processing model for data with a larger data amount, thereby improving the data reasoning efficiency of the data processing model and avoiding the problem of low reasoning efficiency in the process of the neural network model processing more complex and large data; and, when it is determined according to the updated reasoning result that the updated data does not meet the data reasoning condition, it is determined to end the data reasoning and determine the updated reasoning result as the target data processing result, thereby meeting the need to use the neural network model to process various types of data in practical applications.

[0225] The above is a schematic scheme of a data processing device of this embodiment. It should be noted that the technical scheme of the data processing device and the technical scheme of the above data processing method belong to the same concept, and the details of the technical scheme of the data processing device that are not described in detail can be referred to the description of the technical scheme of the above data processing method.

[0226] Corresponding to the above method embodiment, this specification also provides a problem handling device embodiment, Figure 6 FIG. 1 is a schematic diagram showing a structure of a problem handling device provided by an embodiment of the present specification. Figure 6 As shown, the device comprises:

[0227] The first result determination module 602 is configured to determine an initial question text, and perform question reasoning on the initial question text using a data processing model to obtain an initial question reasoning result;

[0228] The question updating module 604 is configured to, when it is determined that the initial question text meets the question reasoning condition according to the initial question reasoning result, update the initial question text according to the initial question reasoning result using the data processing model to obtain an updated question text, wherein the data amount of the updated question text is less than the data amount of the initial question text, and the data processing model is a machine learning model;

[0229] The second result determination module 606 is configured to use the data processing model to perform question reasoning on the update question text to obtain an update question reasoning result;

[0230] The third result determination module 608 is configured to determine the update question reasoning result as the target question processing result when it is determined that the update question text does not meet the question reasoning condition according to the update question reasoning result.

[0231] Optionally, the first result determination module 602 is further configured to:

[0232] Receiving the initial question text sent by the client, wherein the initial question text is generated by the client according to the problem handling operation performed by the user on the problem handling page;

[0233] The problem handling device further includes a result sending module, which is configured to:

[0234] The target problem processing result is sent to the client, so that the client displays the target problem processing result to the user based on the problem processing page.

[0235] In one or more embodiments of the present specification, the problem processing device provides, in the process of using the problem processing model to process the problem, first, using the problem processing model to perform the first stage of problem reasoning on the initial problem text to obtain the initial problem reasoning result; and, when it is determined according to the initial problem reasoning result that the initial problem text meets the problem reasoning condition, the initial problem text is updated according to the initial problem reasoning result, so as to obtain an updated problem text with a smaller amount of data than the initial problem text; then, the problem processing model is used to perform the second stage of problem reasoning on the updated problem text with a smaller amount of data, so as to quickly obtain the updated problem reasoning result. Since the problem processing model can quickly reason on the updated problem text with a smaller amount of data, although it is necessary to reason through multiple stages, the overall reasoning efficiency will be higher than the problem reasoning efficiency of the problem processing model for the problem text with a larger amount of data, thereby improving the problem reasoning efficiency of the problem processing model and avoiding the problem of low reasoning efficiency in the process of the neural network model processing more complex and large data; and, when it is determined according to the updated problem reasoning result that the updated problem text does not meet the problem reasoning condition, it is determined to end the problem reasoning and determine the updated problem reasoning result as the target problem processing result, thereby meeting the need to use the neural network model to process various types of problems in practical applications.

[0236] The above is a schematic scheme of a problem solving device of this embodiment. It should be noted that the technical scheme of the problem solving device and the technical scheme of the problem solving method described above are of the same concept, and the details not described in detail in the technical scheme of the problem solving device can be found in the description of the technical scheme of the problem solving method described above.

[0237] Figure 7 The block diagram of a computing device 700 according to an embodiment of the present specification is shown. The components of the computing device 700 include but are not limited to a memory 710 and a processor 720. The processor 720 is connected to the memory 710 via a bus 730, and the database 750 is used to store data.

[0238] The computing device 700 also includes an access device 740 that enables the computing device 700 to communicate via one or more networks 760. Examples of these 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 740 may include one or more of any type of network interface, wired or wireless (e.g., a network interface card (NIC)), such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, and a Near Field Communication (NFC).

[0239] In one embodiment of the present specification, the above components of the computing device 700 and Figure 7 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 7 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0240] The computing device 700 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 700 may also be a mobile or stationary server.

[0241] The processor 720 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned data processing method or problem processing method.

[0242] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the computing device embodiment, since it is basically similar to the data processing method or problem processing method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the data processing method or problem processing method embodiment.

[0243] An embodiment of the present specification further provides a computer-readable storage medium storing a computer program / instruction, which implements the steps of the above-mentioned data processing method or problem processing method when executed by a processor.

[0244] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the computer-readable storage medium embodiment, since it is basically similar to the data processing method or problem processing method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the data processing method or problem processing method embodiment.

[0245] An embodiment of the present specification also provides a computer program product, including a computer program / instruction, which implements the steps of the above-mentioned data processing method or problem processing method when executed by a processor.

[0246] The above is a schematic scheme of a computer program product of this embodiment. It should be noted that the technical scheme of the computer program product and the technical scheme of the above-mentioned data processing method or problem processing method belong to the same concept, and the details not described in detail in the technical scheme of the computer program product can be referred to the description of the technical scheme of the above-mentioned data processing method or problem processing method.

[0247] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0248] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0249] It should be noted that, for the above-mentioned 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 specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0250] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0251] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can understand and use this specification well. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A data processing method, include: Determine initial data, and use a data processing model to perform data reasoning on the initial data to obtain initial reasoning results; When it is determined that the initial data meets the data reasoning condition according to the initial reasoning result, the initial data is updated using the data processing model according to the initial reasoning result to obtain updated data, wherein the data quantity of the updated data is less than the data quantity of the initial data, and the data processing model is a machine learning model; Performing data reasoning on the update data using the data processing model to obtain an update reasoning result; When it is determined according to the update reasoning result that the update data does not satisfy the data reasoning condition, the update reasoning result is determined as the target data processing result.

2. The data processing method according to claim 1, wherein the initial data is updated using the data processing model according to the initial inference result to obtain updated data. include: Using the data processing model, determining a plurality of initial sub-data contained in the initial data, and determining, from the plurality of initial sub-data, sub-data to be updated associated with the initial reasoning result; The data processing model is used to update the sub-data to be updated in the initial data based on the initial reasoning result to obtain the updated data.

3. The data processing method according to claim 2, wherein the data processing model is used to update the sub-data to be updated in the initial data based on the initial reasoning result to obtain the updated data, include: Using the data processing model, based on the initial reasoning result, the sub-data to be updated in the initial data is replaced to obtain the updated data; or The data processing model is used to semantically rewrite the sub-data to be updated in the initial data based on the initial reasoning result to obtain the updated data.

4. The data processing method according to claim 2, wherein the data processing model is used to determine a plurality of initial sub-data contained in the initial data, and the sub-data to be updated associated with the initial reasoning result is determined from the plurality of initial sub-data, include: Inputting the initial reasoning result and the initial data into the data processing model, performing data extraction on the initial data using the data processing model, and determining the multiple initial sub-data contained in the initial data; Semantic analysis is performed on each initial sub-data and the initial reasoning result to obtain the sub-data to be updated associated with the initial reasoning result.

5. The data processing method according to claim 1, wherein the data processing model is used to perform data inference on the initial data to obtain an initial inference result. include: Inputting the initial data into the data processing model, performing data extraction on the initial data using the data processing model, and determining a plurality of initial sub-data contained in the initial data; The sub-data to be inferred are determined from the multiple initial sub-data, and semantic reasoning is performed on the sub-data to be inferred to obtain the initial reasoning result.

6. The data processing method according to claim 1, wherein the data processing model is used to perform data reasoning on the update data, and after obtaining the update reasoning result, include: When it is determined that the updated data satisfies the data reasoning condition according to the update reasoning result, the updated data is updated using the data processing model according to the update reasoning result to obtain second updated data, wherein the data quantity of the second updated data is less than the data quantity of the updated data; The second update data is determined as the update data, and the step of performing data reasoning on the update data using the data processing model to obtain an update reasoning result is continued until it is determined, based on the update reasoning result, that the update data does not satisfy the data reasoning condition.

7. The data processing method according to claim 1, wherein the determining of the initial data comprises: include: Receiving the initial data sent by the client, wherein the initial data is generated by the client according to a data processing operation performed by the user on the data processing page; After determining, based on the update reasoning result, that the update data does not satisfy the data reasoning condition, the update reasoning result is determined as the target data processing result, the method further includes: The target data processing result is sent to the client, so that the client displays the target data processing result based on the data processing page.

8. The data processing method according to any one of claims 1 to 7, wherein the initial data is an initial question text, the initial reasoning result is an initial question reasoning result, and the data processing model is a question processing model; When it is determined that the initial data meets the data reasoning condition according to the initial reasoning result, the initial data is updated using the data processing model according to the initial reasoning result to obtain updated data, include: When it is determined that the initial question text meets the question reasoning condition according to the initial question reasoning result, the initial question text is updated by using the question processing model according to the initial question reasoning result to obtain an updated question text.

9. The data processing method according to any one of claims 1 to 7, wherein the initial data is determined to satisfy a data reasoning condition based on the initial reasoning result, include: Determining initial sub-data contained in the initial data using the data processing model; Performing semantic analysis on the initial sub-data and the initial reasoning result, and determining that the initial data meets the data reasoning condition when it is determined that there are multiple initial sub-data and there is sub-data to be updated associated with the initial reasoning result among the multiple initial sub-data; The determining, according to the update reasoning result, that the update data does not satisfy the data reasoning condition includes: Determining the update sub-data included in the update data by using the data processing model; Semantic analysis is performed on the update sub-data and the update reasoning result, and when it is determined that the update sub-data is one and the update sub-data is associated with the update reasoning result, it is determined that the update data does not satisfy the data reasoning condition.

10. A method of problem solving, include: Determine an initial question text, and use a data processing model to perform question reasoning on the initial question text to obtain an initial question reasoning result; When it is determined that the initial question text satisfies the question reasoning condition according to the initial question reasoning result, the initial question text is updated by using the data processing model according to the initial question reasoning result to obtain an updated question text, wherein the amount of data in the updated question text is less than the amount of data in the initial question text, and the data processing model is a machine learning model; Performing question reasoning on the update question text using the data processing model to obtain an update question reasoning result; When it is determined according to the update question reasoning result that the update question text does not satisfy the question reasoning condition, the update question reasoning result is determined as the target question processing result.

11. The problem handling method according to claim 10, wherein the determining of the initial problem text comprises: include: Receiving the initial question text sent by the client, wherein the initial question text is generated by the client according to the problem handling operation performed by the user on the problem handling page; After determining, based on the update question reasoning result, that the update question text does not satisfy the question reasoning condition, the update question reasoning result is determined as the target question processing result, the method further includes: The target problem processing result is sent to the client, so that the client displays the target problem processing result to the user based on the problem processing page.

12. A computing device, include: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer program / instructions are executed by the processor, the steps of the data processing method described in any one of claims 1 to 9 or the problem processing method described in any one of claims 10 to 11 are implemented.

13. A computer-readable storage medium storing a computer program / instruction, which, when executed by a processor, implements the steps of the data processing method described in any one of claims 1 to 9 or the problem processing method described in any one of claims 10 to 11.

14. A computer program product, comprising a computer program / instruction, which, when executed by a processor, implements the steps of the data processing method according to any one of claims 1 to 9 or the problem processing method according to any one of claims 10 to 11.

Citation Information

Patent Citations

  • A question-answering method and device based on medical knowledge graph to construct question-answer pairs

    CN114936275A

  • Method and device for obtaining result, electronic equipment and storage medium

    CN115203366A

  • Intelligent solving method, system and equipment for mathematical application questions and storage medium

    CN116680502A

  • Big language model-based reasoning calculation method, apparatus and device, and storage medium

    CN117973530A

  • Systems and methods of question answering against system of record utilizing natural language interpretation

    US20210382923A1

Cited By

  • Data processing method, problem processing method, computing device, and storage medium

    WO2026007668A1