Data processing method and device and data interaction method, device and system

Abstract

The embodiment of the invention provides a data processing method and device and a data interaction method, device and system.The data processing method is applied to a code execution intelligent system and comprises the steps that to-be-processed data is determined, and an associated example corresponding to the to-be-processed data is determined according to a retrieval enhancement strategy; determining a target classification result of the associated examples; according to the to-be-processed data, the associated example and the target classification result, utilizing the data processing model to determine and run a program code corresponding to the to-be-processed data, and obtaining a target result corresponding to the to-be-processed data; the data processing model does not need to be trained, the limitation of the existing capability of the data processing model can be broken through, the long tail requirement of the user is met, the data processing efficiency is improved, the data processing model can automatically learn reflection, correction and improvement, and the reply accuracy of the code execution intelligent system is improved.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of computer technology, and in particular, to a data processing method, a data processing device, a data interaction method, a data interaction device, a data interaction system, a computing device, a computer storage medium, and a computer program product. Background Art

[0002] In the question-and-answer scenario, most of the existing code execution intelligent agent solutions currently adopt a direct solution of "generating code - running code - performing the next operation based on the running result", relying on the existing capabilities of the data processing model itself. For long-tail tasks and self-correction, special training of the data processing model is required to have relevant capabilities, but the training of the data processing model is time-consuming and resource-consuming.

[0003] Therefore, there is an urgent need for a data processing method to solve the technical problem that the data processing model is restricted by the existing capabilities and needs to be trained to obtain relevant capabilities in order to output accurate responses. Summary of the Invention

[0004] In view of this, the embodiments of this specification provide a data processing method. One or more embodiments of this specification also relate to a data interaction method, a data device, a data interaction device, a data interaction system, a computing device, a computer-readable storage medium, and a computer program product to solve the technical defects existing in the prior art.

[0005] According to the first aspect of the embodiments of this specification, a data processing method is provided, which is applied to a code execution intelligent system and includes:

[0006] Determine the data to be processed, and determine the associated example corresponding to the data to be processed according to the retrieval enhancement strategy, where the retrieval enhancement strategy is a strategy of retrieving from a retrieval knowledge base and applying the retrieval result to a data processing model;

[0007] Determine the target classification result of the associated example;

[0008] According to the data to be processed, the associated example, and the target classification result, use the data processing model to determine and run the program code corresponding to the data to be processed, and obtain the target result corresponding to the data to be processed.

[0009] According to the second aspect of the embodiments of this specification, a data interaction method is provided, which is applied to a client and includes:

[0010] Receive the data to be processed through an interaction interface and send the data to be processed to the server;

[0011] Receive the target result corresponding to the to-be-processed data obtained by applying the above data processing method returned by the server, display the target result through the interaction interface, and receive the result feedback information for the target result returned through the interaction interface.

[0012] According to the third aspect of the embodiments of the present specification, a data interaction method is provided, which is applied to a data interaction system. The system includes a client and a server, where

[0013] The client receives the to-be-processed data through the interaction interface and sends the to-be-processed data to the server;

[0014] The server receives the to-be-processed data, applies the above data processing method to obtain the target result corresponding to the to-be-processed data, and returns the target result to the client;

[0015] The client receives the target result, displays the target result through the interaction interface, and receives the result feedback information for the target result returned through the interaction interface.

[0016] According to the fourth aspect of the embodiments of the present specification, a data processing device is provided, which is applied to a code execution intelligent system, including:

[0017] A first determination module, configured to determine the to-be-processed data and determine the associated example corresponding to the to-be-processed data according to a retrieval enhancement strategy, where the retrieval enhancement strategy is a strategy of retrieving from a retrieval knowledge base and applying the retrieval result to a data processing model;

[0018] A second determination module, configured to determine the target classification result of the associated example;

[0019] A result obtaining module, configured to determine and run the program code corresponding to the to-be-processed data by using a processing data model according to the to-be-processed data, the associated example, and the target classification result, and obtain the target result corresponding to the to-be-processed data.

[0020] According to the fifth aspect of the embodiments of the present specification, a data interaction device is provided, which is applied to a client, including:

[0021] A receiving module, configured to receive the to-be-processed data through the interaction interface and send the to-be-processed data to the server;

[0022] A display module, configured to receive the target result corresponding to the data to be processed obtained by applying the above data processing method and returned by the server, display the target result through the interaction interface, and receive the result feedback information for the target result returned through the interaction interface.

[0023] According to a sixth aspect of the embodiments of the present specification, a data interaction system is provided, including a client and a server, wherein

[0024] The client is configured to receive the data to be processed through the interaction interface and send the data to be processed to the server;

[0025] The server is configured to receive the data to be processed, apply the above data processing method to obtain the target result corresponding to the data to be processed, and return the target result to the client;

[0026] The client is further configured to receive the target result, display the target result through the interaction interface, and receive the result feedback information for the target result returned through the interaction interface.

[0027] According to a seventh aspect of the embodiments of the present specification, a computing device is provided, including:

[0028] A memory and a processor;

[0029] The memory is configured to store computer programs / instructions, and the processor is configured to execute the computer programs / instructions. When the computer programs / instructions are executed by the processor, the steps of the above data processing method or data interaction method are implemented.

[0030] According to an eighth aspect of the embodiments of the present specification, a computer-readable storage medium is provided, which stores computer-executable instructions. When the instructions are executed by a processor, the steps of the above data processing method or data interaction method are implemented.

[0031] According to a ninth aspect of the embodiments of the present specification, a computer program product is provided, including computer programs / instructions. When the computer programs / instructions are executed by a processor, the steps of the above data method or data interaction method are implemented.

[0032] The data processing method provided in the embodiments of this specification is applied to a code execution intelligent system, and includes: determining data to be processed, and determining an associated example corresponding to the data to be processed according to a retrieval enhancement strategy, where the retrieval enhancement strategy is a strategy of retrieving from a retrieval knowledge base and applying the retrieval result to a data processing model; determining a target classification result of the associated example; and determining and running program code corresponding to the data to be processed by using the data processing model according to the data to be processed, the associated example, and the target classification result, so as to obtain a target result corresponding to the data to be processed.

[0033] Based on this, the data processing method determines an associated example corresponding to the data to be processed through a retrieval enhancement strategy, determines a target classification result of the associated example, inputs the data to be processed and the associated example into the data processing model according to the target classification result of the associated example, uses the context ability of the data processing model to determine program code corresponding to the data to be processed, and can call a code interpreter to execute the program code, so as to obtain a target result corresponding to the data to be processed. Without training the data processing model, the data processing model uses the target classification result of the associated example, and can refer to more associated examples of positive classification results and reflect on associated examples of negative classification results when processing the data to be processed, thereby breaking through the limitations of the existing capabilities of the data processing model, meeting the long-tail needs of users and improving the processing efficiency. It enables the data processing model to automatically learn to reflect, correct, and improve, and improves the accuracy of the response of the code execution intelligent system. Description of the Drawings

[0034] Figure 1 is a schematic diagram of a scenario of a data processing method provided in an embodiment of this specification;

[0035] Figure 2 is a flowchart of a data processing method provided in an embodiment of this specification;

[0036] Figure 3 is a flowchart of a processing process of a data processing method provided in an embodiment of this specification;

[0037] Figure 4 is a flowchart of a data interaction method applied to a client provided in an embodiment of this specification;

[0038] Figure 5 is an interaction flowchart of a data interaction method applied to a data interaction system provided in an embodiment of this specification;

[0039] Figure 6 is a schematic structural diagram of a data processing device provided in an embodiment of this specification;

[0040] Figure 7It is a schematic structural diagram of a data interaction device applied to a client provided by an embodiment of this specification;

[0041] Figure 8 It is a schematic structural diagram of a data interaction system provided by an embodiment of this specification;

[0042] Figure 9 It is a structural block diagram of a computing device provided by an embodiment of this specification. Detailed implementation manners

[0043] In the following description, many specific details are set forth in order to provide a thorough understanding of this specification. However, this specification can be implemented in many other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of this specification. Therefore, this specification is not limited by the specific implementations disclosed below.

[0044] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a", "the", and "said" used in one or more embodiments of this specification and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise. 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 of the associated listed items.

[0045] It should be understood that although the terms first, second, etc. may be used in one or more embodiments of this specification to describe various information, such 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 can be interpreted as "when" or "while" or "in response to determining".

[0046] 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 for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data that have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of the relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or refuse.

[0047] In one or more embodiments of this specification, a large model refers to a deep learning model with a large number of model parameters, usually including hundreds of millions, tens of billions, hundreds of billions, trillions or even more than one quadrillion model parameters. A large model can also be called a Foundation Model. Through pre-training of the large model with a large amount of unlabeled corpus, a pre-trained model with more than one hundred million parameters is produced. This model can adapt to a wide range of downstream tasks and has good generalization ability. For example, large language models (LLMs), multi-modal pre-training models, etc.

[0048] When a large model is actually applied, only a small number of samples are needed to fine-tune the pre-trained model for application to different tasks. Large models can be widely applied in the fields of natural language processing (NLP), computer vision, etc. Specifically, they can be applied to tasks in the field of computer vision such as visual question answering (VQA), image captioning (IC), image generation, etc., and tasks in the field of natural language processing such as text-based sentiment classification, text summary generation, machine translation, etc. The main application scenarios of large models include digital assistants, intelligent robots, search, online education, office software, e-commerce, intelligent design, etc.

[0049] First, the noun terms involved in one or more embodiments of this specification are explained.

[0050] Agent: An entity with intelligence; currently, it mostly refers to an entity that takes a large language model (LLM) as the core center to complete a series of complex tasks.

[0051] Retrieval augmentation: By connecting to an external knowledge base, the limited knowledge limitation of the model is broken through to improve the model performance.

[0052] In-context learning: Learning in context, which means that the model learns in a specific context environment; it takes into account the text context environment, as well as the relationships between data and the influence of context information. In this method, the learning algorithm will utilize context information to improve the accuracy and effectiveness of prediction and classification.

[0053] Long Tail: The protruding part in the middle of the normal curve is called the "head"; the relatively gentle parts on both sides are called the "tails". From the perspective of people's needs, most needs will be concentrated in the head, while the needs distributed in the tails are personalized, scattered, and small in quantity. And this part of the differentiated and small amount of needs will form a long "tail" on the demand curve.

[0054] An agent is a program that can simulate human intelligent behavior, aiming to enable a computer to perceive, reason, and make decisions like a human. With the development of large language models (LLMs), the application and development of AI (Artificial Intelligence) agents have also made remarkable progress; enabling large models to be used as AI agents to handle complex tasks and situations, making them better interact and cooperate with humans.

[0055] Among them, code execution is a relatively common complex task. The agent writes code according to human needs, calls the code interpreter tool to run the code, and thinks about the next operation based on the code execution result. However, it is relatively difficult for the code generated by the large model to run correctly and meet the requirements at one time. It often needs to learn self-reflection and correction after running errors. At the same time, there is a long-tail effect in users' needs. Therefore, there is an urgent need for a low-cost and lightweight data processing method to enable the large model to reflect and incrementally expand its capabilities when performing code execution, so as to meet users' long-tail needs, improve processing efficiency, and the accuracy of results.

[0056] In this specification, a data processing method and a data interaction method are provided. This specification also relates to a data processing device, a data interaction device, a data interaction system, a computing device, a computer-readable storage medium, and a computer program product, which will be described in detail one by one in the following embodiments.

[0057] See Figure 1 , Figure 1 which shows a schematic diagram of the scenario of a data processing method provided by an embodiment of this specification.

[0058] Specifically, this data processing method can be applied to various scenarios including question-and-answer scenarios, search scenarios, etc. Taking the application of the data processing method in a question-and-answer scenario as an example, this data processing method will be described in detail.

[0059] This data processing method is implemented using the client 102 and the code execution intelligent system 104. Among them, the client 102 is the front-end part for users to interact with the code execution intelligent system 104; it can be a web page, a mobile application, or other types of user interfaces; the client 102 is used to receive user input (such as text questions, voice commands, or pictures, etc.), send the user input to the code execution intelligent system 104, and display the results returned by the code execution intelligent system 104 to the user.

[0060] Specifically, the client 102 sends the data to be processed to the code execution intelligent system 104. In the Q&A scenario, the data to be processed can be understood as the question input by the user. For example, the question input by the user is "What is 2 + 2?". In practical applications, the user can input questions through text or voice in the interaction interface of the client 102. If the voice method is adopted, the client 102 will also include corresponding voice processing parts, such as voice parsing, voice-to-text conversion, voice synthesis, etc. modules, which are used to convert the questions input by the user through voice into text. This specification does not limit this.

[0061] The code execution intelligent system 104 includes a data processing model. In the Q&A scenario, this data processing model can be understood as a Q&A model. After receiving the question sent by the client 102, the code execution intelligent system 104 determines the associated examples related to the question according to the retrieval enhancement strategy. Among them, the associated examples include the associated questions related to the question input by the user, the associated answers corresponding to the associated questions, and the first answer probability of the associated answers. For example, the associated example 1 is "Question: What is 2 plus 2? Answer: 2 plus 2 equals 4. The first answer probability is 1". This first answer probability is used to represent the user's emotional polarity towards the associated answer. For example, when the first answer probability is 1, it means that the user's emotional polarity towards the associated answer is positive, that is, the user is satisfied with the associated answer.

[0062] In addition, the emotional classification model can be used to classify the associated example 1 to obtain the classification probability. The first answer probability and the classification probability are weighted and calculated to obtain the target answer probability of the above-mentioned associated example 1, so as to determine the target classification result of the associated example according to the target answer probability. For example, the target classification result of the associated example 1 is a positive case; correspondingly, the same processing can be performed on multiple associated examples to obtain the target classification results of each associated example.

[0063] The associated example and the question input by the user are spliced using a preset splicing template, and the spliced text is input into the data processing model. The data processing model generates the program code to solve the target problem, that is

[0064] "python

[0065] # Calculate 2 + 2

[0066] result = 2 + 2

[0067] # Output result

[0068] print(result)”

[0069] Call the code interpreter to run the program code, and obtain the running result "After running the above code, the output will be: 4". According to the running result, obtain the question reply template "2 + 2 equals 4"; output the program code, running result, and question reply template to obtain the target answer corresponding to the user's input question.

[0070] The code execution intelligent system 104 returns the obtained target answer to the client 102. When the client 102 receives the target answer, it displays the target answer to the user through the interaction interface and shows the "like, dislike" icons, so that the user can click on the corresponding icon to give feedback on the target answer and obtain the answer feedback information of the user for the target answer; of course, in the case where the user does not perform the "like, dislike" behavior, the answer feedback information of the user for the target answer can also be obtained through the user's next reply, such as "Okay, I got it" or "No, this is not the answer I want".

[0071] After the client 102 receives the answer feedback information of the user for the target answer, it can send the answer feedback information to the code execution intelligent system 104, so that the code execution intelligent system 104 can obtain the first answer probability of the target answer according to the answer feedback information. For example, when the user clicks the "like" icon, the answer probability of the target answer is 1. Of course, there may be a situation where the user clicks by mistake. Therefore, the classification probability of the sentiment classification model and the above answer probability can be combined to obtain the first answer probability of the target answer; store the input question, target answer, and the first answer probability of the target answer in the retrieval knowledge base for subsequent use.

[0072] The client 102 may include a browser, an APP (Application), a web application such as an H5 (Hyper Text Markup Language 5) application, a light application (also known as a mini-program, a lightweight application), or a cloud application, etc. The client 102 may be developed based on the software development kit (SDK) of the corresponding service provided by the server, such as developed based on the real-time communication (RTC) SDK. The client may be deployed in an electronic device and needs to rely on the device or certain APPs in the device to run, etc. The electronic device may have a display screen and support information browsing, etc., such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, etc. Various other types of applications can usually be configured in the electronic device, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0073] The code execution intelligent system 104 can be understood as a code execution intelligent agent, which is a backend service or a software application program. For example, it provides communication services for multiple clients, or provides services for processing data sent by clients, etc.

[0074] It should be noted that the data processing method provided in the embodiments of this specification can be executed by the code execution intelligent system 104. In other embodiments of this specification, the data processing model can be deployed in the client 102, so that the client 102 can also have similar functions to the code execution intelligent system 104, thereby executing the data processing method provided in the embodiments of this specification; in other embodiments, the data processing method provided in the embodiments of this specification can also be jointly executed by the client 102 and the code execution intelligent system 104.

[0075] The data processing method provided in the embodiments of this specification determines the associated example corresponding to the data to be processed from the retrieval knowledge base, determines the target classification result of the associated example, and according to the target classification result of the associated example, inputs the data to be processed and the associated example into the data processing model. Utilizing the context ability of the data processing model, the target result corresponding to the data to be processed is obtained. Without training the data processing model, it can break through the limitations of the existing capabilities of the data processing model, meet the long-tail needs of users and improve the processing efficiency. It can also enable the data processing model to automatically learn to reflect, correct, and improve, thereby improving the accuracy of the result.

[0076] See Figure 2 , Figure 2The flowchart of a data processing method provided by an embodiment of this specification is shown, which specifically includes the following steps.

[0077] Specifically, this data processing method is applied to a code execution intelligent system. Among them, the code execution intelligent system can be understood as a code execution intelligent agent, which is an artificial intelligence system that can understand and generate code to execute specific tasks or solve problems.

[0078] Step 202: Determine the data to be processed, and determine the associated example corresponding to the data to be processed according to the retrieval enhancement strategy, where the retrieval enhancement strategy is a strategy of retrieving from a retrieval knowledge base and applying the retrieval result to a data processing model.

[0079] Among them, the associated example includes associated data, the associated result corresponding to the associated data, and the first associated result probability of the associated result; the data to be processed can be understood as having different meanings according to different application scenarios. For example, in a question-and-answer scenario, the data to be processed can be understood as the question that the user inputs through the interaction interface of the client and wants to query. For example, the question input by the user is "There are chickens and rabbits in a cage. The total number of them is 30, and the total number of feet is 80. How many are there respectively?"; or in a search scenario, the data to be processed can be understood as the keyword input by the user through the interaction interface of the client.

[0080] The retrieval enhancement strategy can be understood as a strategy of retrieving from a retrieval knowledge base and applying the retrieval result to a data processing model to enhance the effect of the data processing model; the retrieval knowledge base can be understood as a database containing various data examples, and various data examples can be obtained from historical data or can be input manually, which is not limited here.

[0081] The associated example can be understood as a similar case corresponding to the data to be processed; the associated data can be understood as data similar to the data to be processed. For example, the associated data corresponding to the above user input question can be "There is a group of chickens and rabbits. The total number of legs is 60 more than twice the total number of heads. How many rabbits are there?" or "There are chickens and rabbits in a cage. The total number of heads is 123, and the total number of feet is 462. How many chickens and rabbits are there?" such associated questions.

[0082] The first associated result probability can be understood as the probability of the emotional polarity of the associated result stored in the retrieval knowledge base for the user. The first associated result probability includes a first positive probability and a first negative probability. The first positive probability can be understood as the probability that the emotional polarity of the associated result for the user is positive, and the first negative probability can be understood as the probability that the emotional polarity of the associated result for the user is negative. For example, the first associated result probability can be 1 or 0, where 1 represents the first positive probability and 0 represents the first negative probability. Through this first associated result probability, it can be understood what the emotional polarity of the user is towards the associated result corresponding to the associated data.

[0083] Specifically, taking the data processing method applied to the Q&A scenario as an example, at this time, the data to be processed can be understood as the target question input by the user; the associated example can be understood as the associated Q&A example; the first associated result probability can be understood as the first answer probability of the associated answer.

[0084] The server receives the target question input by the user through the interaction interface of the client, and determines the associated Q&A example corresponding to the target question from the Q&A examples in the retrieval knowledge base. The associated Q&A example not only includes the associated question, the associated answer corresponding to the associated question, but also includes the first answer probability of the associated answer. Thus, subsequently, it can be determined whether the associated Q&A example is a positive case or a negative case of the target question based on the first answer probability of the associated answer.

[0085] In one or more embodiments of this specification, to reduce the workload of the data processing model and accelerate the data processing efficiency, when retrieving the associated example corresponding to the data to be processed in the retrieval knowledge base, a preset number of associated examples can be selected, and based on the preset number of associated examples and the data to be processed, the target result corresponding to the data to be processed is obtained. The specific implementation method is as follows:

[0086] Determining the data to be processed and determining the associated example corresponding to the data to be processed according to the retrieval enhancement strategy includes:

[0087] Determining the data to be processed, and selecting a preset number of associated examples corresponding to the data to be processed from the retrieval knowledge base.

[0088] Among them, the preset number can be set according to actual needs, such as set to 10, 20, etc.

[0089] Taking the preset number as 10 for exemplary illustration, determine the data to be processed, and select 10 associated examples corresponding to the data to be processed from the retrieval knowledge base.

[0090] In the data processing method provided by the embodiments of this specification, when the preset quantity can be set according to actual requirements, the user can select a preset quantity of associated examples corresponding to the data to be processed from the retrieval knowledge base according to actual requirements. Subsequently, when inputting the data to be processed and the associated examples into the data processing model, the workload of the data processing model can be reduced and the data processing efficiency can be accelerated.

[0091] Step 204: Determine the target classification result of the associated example.

[0092] In one or more embodiments of this specification, determining the target classification result of the associated example includes:

[0093] Determine the target result probability of the associated example, where the target result probability is used to represent the probability of the user's emotional polarity towards the associated result in the associated example;

[0094] Determine the target classification result of the associated example according to the target result probability.

[0095] Among them, the target result probability of the associated example can be understood as the probability of the user's emotional polarity towards the associated result in the associated example; the target classification result can be understood as the classification result after classifying the associated example, including a positive classification result and a negative classification result; the positive classification result can be understood as that the associated example is a positive example of the data to be processed, and the negative classification result can be understood as that the associated example is a negative example of the data to be processed.

[0096] Specifically, by determining the probability of the user's emotional polarity towards the associated result in the associated example, the associated example is classified, so as to determine whether the associated example is a positive example of the data to be processed or a positive example of the data to be processed; for example, when the target result probability of the associated example is 0.8, it means that the user's emotional polarity towards the associated result in the associated example tends to be positive. Therefore, it can be determined that the associated example is a positive example of the data to be processed. Thus, when the data processing model processes the data to be processed, more reference is made to this associated example to obtain a more accurate target result.

[0097] In one or more embodiments of this specification, to ensure the accuracy of the target result probability of the obtained associated example, when the associated example retrieved from the knowledge base includes the first associated result probability, the second associated result probability of the associated result is also obtained by using the emotion classification model. The specific implementation method is as follows:

[0098] Determining the target result probability of the associated example includes:

[0099] Obtain the second association result probability of the said association result according to the sentiment classification model, where the second association result probability is used to represent the probability of the sentiment polarity of the user towards the association result obtained by the sentiment classification model;

[0100] Determine the target result probability of the association example according to the first association result probability of the association result and the second association result probability of the association result.

[0101] Among them, the sentiment classification model can be a single classification model, which is used to analyze the attitude expressed in the text, whether it is positive or negative; in practical applications, the sentiment classification model can also be implemented using a data processing model, that is, using the data processing model to obtain the second association result probability of the association result.

[0102] Among them, the second association result probability can be understood as the probability of the sentiment polarity of the user towards the association result calculated by the sentiment classification model. The second association result probability includes the second positive probability and the second negative probability. The second positive probability can be understood as the probability that the sentiment polarity of the user towards the association result is positive, and the second negative probability can be understood as the probability that the sentiment polarity of the user towards the association result is negative; the first association result probability can be expressed in percentage. For example, when the second positive probability is greater than or equal to 50%, it represents that the sentiment polarity of the user towards the association result is positive. Of course, it can also be that when the second positive probability is greater than or equal to 70%, it represents that the sentiment polarity of the user towards the association result is positive. Similarly, when the second negative probability is greater than or equal to 50%, it represents that the sentiment polarity of the user towards the association result is negative. Specifically, it can be set according to the actual situation and is not limited here.

[0103] In practical applications, when determining the target classification result of the association example according to the first association result probability in the retrieval knowledge base, there may be situations where the target classification result is inaccurate or accidental; therefore, to ensure the accuracy of the target classification result of the association example, it is also necessary to use the sentiment classification model to obtain the second association result probability of the association result.

[0104] For example, if the association result contains a statement like "Since the code interpreter returned an error, I couldn't determine the number of rabbits. It might be because the variable names or equations I entered were incorrect. Please check and provide the correct number of heads and legs, and I'll try to solve the problem again.", then the negative probability of this association result can be increased.

[0105] Specifically, based on the first associated result probability of the associated result stored in the retrieval knowledge base and the second associated result probability of the associated result obtained by using the sentiment classification model, the first associated result probability and the second associated result probability can be calculated by means such as taking the average or weighted calculation to obtain the target result probability. For example, when the first associated result probability is 0.8 and the second associated result probability is 0.6, the target result probability is calculated to be 0.7 by taking the average of the first associated result probability and the second associated result probability. Thus, according to the target result probability, the target classification result of the associated example is determined.

[0106] The data processing method provided by the embodiments of this specification, on the basis that the associated examples in the retrieval knowledge base include the first associated result probability, can also use the sentiment classification model to obtain the second associated result probability of the associated result, thereby determining the target result probability of the associated example according to the first associated result probability and the second associated result probability, improving the accuracy of the target result probability.

[0107] In one or more embodiments of this specification, there may be multiple associated examples, and according to a preset probability threshold, it can be determined whether the target classification result of each associated example is a positive classification result or a negative classification result. The specific implementation method is as follows:

[0108] There are multiple associated examples;

[0109] Determining the target result probability of the associated example according to the first associated result probability of the associated result and the second associated result probability of the associated result includes:

[0110] Determine the target result probability of each associated example according to the first associated result probability of each associated result and the second associated result probability of each associated result;

[0111] Determining the target classification result of the associated Q&A example according to the target result probability includes:

[0112] When the target result probability is greater than or equal to the preset probability threshold, determine the positive classification result of each associated Q&A example, or

[0113] When the target result probability is less than the preset probability threshold, determine the negative classification result of each associated Q&A example.

[0114] Among them, the preset probability threshold can be set according to the actual situation. For example, the preset probability threshold is 0.5. The positive classification result can be understood as the classification result in which the associated example is classified as a positive case corresponding to the data to be processed. The negative classification result can be understood as the classification result in which the associated example is classified as a negative case corresponding to the data to be processed.

[0115] In practical applications, the first associated result probability and the second associated result probability are the probabilities of the user's emotional polarity towards the associated answer. Here, taking the probability of the user's emotional polarity towards the associated answer as the probability that the user's emotional polarity towards the associated answer is positive as an example, a detailed description is given.

[0116] For example, in the case where the first associated result probability of the associated result in the associated example is 0.8, it means that the probability that the emotional polarity of the user towards the associated result stored in the retrieved knowledge base is positive is 0.8; in the case where the second associated result probability is 0.6, it means that the probability that the emotional polarity of the user towards the associated result obtained by using the emotion classification model is positive is 0.6; the target result probability is calculated to be 0.7 by using the method of taking the average. Since the target result probability is greater than the preset probability threshold of 0.5, it can be determined that the target classification result of the associated example is a positive classification result, that is, this associated Q&A example is a positive case of the data to be processed; correspondingly, if the target result probability of another associated Q&A example is less than the preset probability threshold of 0.5, it can be determined that the target classification result of this associated example is a negative classification result, that is, this associated example is a negative case of the data to be processed.

[0117] The data processing method provided by the embodiments of this specification can, through the determination method of the preset probability threshold, accurately determine whether the target classification result of each associated example is a positive classification result or a negative classification result according to the target result probabilities of each associated example in the case where there are multiple associated examples.

[0118] In one or more embodiments of this specification, different weight values can also be assigned to the first associated result probability and the second associated result probability, so as to determine the target result probability of the associated example according to the first associated result probability, the weight value corresponding to the first associated result probability, the second associated result probability, and the weight value corresponding to the second associated result probability. The specific implementation method is as follows:

[0119] Determining the target result probability of the associated example according to the first associated result probability of the associated result and the second associated result probability of the associated result includes:

[0120] Determining the first weight value of the first associated result probability and the second weight value of the second associated result probability;

[0121] Determining the target result probability of the associated example according to the first associated result probability, the first weight value, the second associated result probability, and the second weight value.

[0122] The target classification result of the association example is determined by the first association result probability and the second association result probability. Therefore, different weight values can be assigned to the first association result probability and the second association result probability. For example, the first weight value corresponding to the first association result probability is w1, and the second weight value corresponding to the second answer probability is w2.

[0123] Continuing with the above example, in the case where the first association result probability of the association result in the association example is 0.8 and the second association result probability is 0.6, the target result probability is obtained according to w1 * 0.8 + w2 * 0.6. For example, when w1 is 0.6 and w1 is 0.4, the target result probability is the calculation result of 0.6 * 0.8 + 0.4 * 0.6, that is, the target result probability is 0.72. Since the target answer probability is greater than 0.5, it can be determined that the target classification result of this association example is a positive classification result, that is, this association example is a positive case of the data to be processed.

[0124] The data processing method provided in the embodiments of this specification can reasonably assign weight values to the first association result probability and the second association result probability according to the actual situation when assigning weight values to the first association result probability and the second association result probability, so that the target result probability of the association example can be determined more accurately.

[0125] In one or more embodiments of this specification, the first association result probability may include a first positive probability or a first negative probability, that is, it may include the probability that the user's emotional polarity towards the association result is positive, or the probability that the user's emotional polarity towards the association result is negative; correspondingly, the second association result probability may also include a second positive probability or a second negative probability. The specific implementation method is as follows:

[0126] The first association result probability of the association result includes a first positive probability or a first negative probability, and the second association result probability of the association result includes a second positive probability or a second negative probability;

[0127] Then specifically, the target result probability of the association example can be determined according to the first positive probability or the first negative probability, the second positive probability or the second negative probability.

[0128] Among them, the first positive probability can be understood as the probability stored in the retrieval knowledge base that the user's emotional polarity towards the association result is positive; the first negative probability can be understood as the probability stored in the retrieval knowledge base that the user's emotional polarity towards the association result is negative.

[0129] The second positive probability can be understood as the probability that the emotional polarity of the user towards the associated result is positive obtained by using the sentiment classification model; the second negative probability can be understood as the probability that the emotional polarity of the user towards the associated result is negative obtained by using the sentiment classification model.

[0130] Specifically, retrieve the probability stored in the knowledge base that can be the probability that the emotional polarity of the user towards the associated result is positive or the probability that the emotional polarity of the user towards the associated result is negative; correspondingly, the probability obtained by using the sentiment classification model that can be the probability that the emotional polarity of the user towards the associated result is positive or the probability that the emotional polarity of the user towards the associated result is negative.

[0131] In practical applications, in the case where the first positive probability is a, the first negative probability is b, the second positive probability is c, and the second negative probability is d, following the above example, w1*a + w2*c can be used to obtain the positive classification result of the associated example, and w1*b + w2*d can be used to obtain the negative classification result of the associated example.

[0132] The data processing method provided by the embodiments of this specification can obtain the probability that the emotional polarity of the user towards the associated result is positive or the probability that the emotional polarity of the user towards the associated result is negative, so as to more flexibly determine the target classification result of the associated example according to the probability that the emotional polarity of the user towards the associated result is positive or the probability that the emotional polarity of the user towards the associated result is negative.

[0133] Step 206: According to the data to be processed, the associated example, and the target classification result, use the data processing model to determine and run the program code corresponding to the data to be processed, and obtain the target result corresponding to the data to be processed.

[0134] Specifically, according to the data to be processed, the associated example, and the target classification result of the associated example, utilize the context ability of the data processing model to autonomously learn positive associated examples and reflect on avoiding negative associated examples, determine the program code corresponding to the data to be processed, and run the program code by calling the code interpreter, so as to obtain the target result corresponding to the data to be processed.

[0135] In one or more embodiments of this specification, a preset target splicing template can be used to splice the data to be processed and the associated example, and input the spliced text into the data processing model to obtain the target result corresponding to the data to be processed output by the data processing model. The specific implementation method is as follows:

[0136] The step of using the data processing model to determine and run the program code corresponding to the data to be processed according to the data to be processed, the associated example, and the target classification result, and obtaining the target result corresponding to the data to be processed includes:

[0137] According to the target splicing template and the target classification result of the associated example, splice the data to be processed and the associated example and input them into the data processing model;

[0138] Use the data processing model to determine and run the program code corresponding to the data to be processed, and obtain the target result corresponding to the data to be processed output by the data processing model.

[0139] Among them, the target splicing template can be understood as a template for splicing the data to be processed and the associated Q&A examples; for example, the target splicing template is:

[0140] "The following are cases of correctly solving the task. Please learn from them:

[0141] {Positive cases}

[0142] The following are cases of wrong answers. Please reflect on them and avoid making similar mistakes again:

[0143] {Negative cases}

[0144] Data to be processed: {Data to be processed}

[0145] Target result: {Target result}"

[0146] According to the target splicing template and the target classification result of the associated example, splice the associated example with the target classification result of the positive classification result to the "{Positive cases}" place, and splice the associated example with the target classification result of the negative classification result to the "{Negative cases}" place, so as to splice the data to be processed and the associated example and input them into the data processing model. Use the data processing model to determine and run the program code corresponding to the data to be processed, and obtain the target result corresponding to the data to be processed output by the data processing model.

[0147] The data processing method provided in the embodiments of this specification, in the case of splicing the data to be processed and the associated example through the target splicing template and the target classification result of the associated example, unifies the input format of inputting the data to be processed and the associated example into the data processing model in the way of the target splicing template, improves the processing efficiency of the data processing model, and can quickly obtain the target result corresponding to the data to be processed.

[0148] In one or more embodiments of this specification, use the data processing model to obtain the program code corresponding to the data to be processed, and call the code interpreter to obtain the running result corresponding to the program code, obtain the question reply template, so as to obtain the target result corresponding to the data to be processed. The specific implementation method is as follows:

[0149] Determining and running the program code corresponding to the data to be processed by using the data processing model according to the data to be processed, the associated Q&A examples, and the target classification result to obtain the target result corresponding to the data to be processed includes:

[0150] Obtaining the program code corresponding to the data to be processed by using the data processing model according to the data to be processed, the associated examples, and the target classification result;

[0151] Invoking a code interpreter through the data processing model to run the program code, obtaining the running result corresponding to the program code, and obtaining a question reply template according to the running result;

[0152] Obtaining the target result corresponding to the data to be processed according to the program code, the running result, and the question reply template.

[0153] Among them, the question reply template can be understood as a supplementary reply obtained according to the running result. If the program code can run correctly, the supplementary reply obtained according to the running result can be "The number of chickens is A, and the number of rabbits is B"; if the program code runs incorrectly, the supplementary reply obtained according to the running result can be "Since the code interpreter returned an error, I cannot determine the number of rabbits. It may be because the variable names or equations I entered are incorrect. Please check and provide the correct number of heads and legs, and I will try to solve this problem again."

[0154] For example, using the data processing model to obtain the program code corresponding to the data to be processed: Let the number of chickens be x and the number of rabbits be y. According to the problem, the following two equations can be listed: x + y = 30 (the number of heads) 2x + 4y = 80 (the number of feet).

[0155] {Program code in any programming language}

[0156] The data processing model invokes the code interpreter to run the above-generated program code to obtain the running result corresponding to the program code:

[0157] (20, 10)

[0158] The data processing model obtains the question reply template "There are 20 chickens and 10 rabbits." according to this running result, combines the program code, the running result, and the question reply template, and outputs the target answer to the data to be processed:

[0159] Let the number of chickens be x and the number of rabbits be y. According to the problem, the following two equations can be listed: x + y = 30 (the number of heads) 2x + 4y = 80 (the number of feet).

[0160] {Program code in any programming language}

[0161] (20,10)

[0162] There are 20 chickens and 10 rabbits.

[0163] In actual applications, the code execution agent obtains feedback from the code running results. When errors occur in the code running, the code execution agent can correct the generated code to improve accuracy. In other words, the code execution agent can let the model automatically learn to reflect, correct, and improve based on the feedback of the running results returned by the code interpreter.

[0164] The data processing method provided in the embodiments of this specification utilizes a data processing model and an autonomous intelligent agent solution for code execution, writes code according to human needs, calls a code interpreter tool to run the code, and thinks about the next step based on the code running results. From the code running feedback, the data processing model can automatically learn to reflect, correct, and improve, thereby improving the accuracy of the results.

[0165] In one or more embodiments of the present specification, in order to accurately obtain the first target result probability of the target result, after the target result corresponding to the data to be processed is displayed to the user, result feedback information returned by the user for the target result is received, and the first target result probability of the target result is obtained according to the result feedback information. The specific implementation method is as follows:

[0166] After obtaining the target result corresponding to the data to be processed, the method further includes:

[0167] Displaying the target result through an interactive interface of a client, and receiving result feedback information returned by the client for the target result;

[0168] Obtaining a first target result probability of the target result according to the result feedback information, wherein the first target result probability is used to represent the probability of the user's emotional polarity toward the target result;

[0169] The data to be processed, the target result corresponding to the data to be processed, and the first target result probability of the target result are stored in a retrieval knowledge base.

[0170] Among them, the interactive interface can be understood as the interface for users to interact with the client; the result feedback information can be understood as the result feedback information of the user regarding the target result, such as the result feedback information can include the user's like / dislike behavior regarding the target result, the user's reply information regarding the target result, etc.

[0171] Specifically, when the target result is displayed to the user through the interaction interface of the client, buttons for "liking / disliking" the target result can be displayed on the interaction interface. Based on the user's click behavior of liking / disliking the target result, the first target result probability of the target result is obtained; or when the user does not perform a click behavior of liking / disliking, based on the response information of the user for the target result, the first target result probability of the target result is obtained; and when the first target result probability is obtained, the data to be processed, the target result corresponding to the data to be processed, and the first target result probability of the target result are stored in the retrieval knowledge base for subsequent use.

[0172] The data processing method provided by the embodiments of this specification can obtain the first target result probability of the target result more accurately by receiving the result feedback information returned by the user for the target result. When storing the data to be processed, the target result corresponding to the data to be processed, and the first target result probability of the target result in the retrieval knowledge base, the number of associated examples and the data richness in the retrieval knowledge base are increased, improving the accuracy of the target result output by the subsequent model.

[0173] In one or more embodiments of this specification, to obtain the first target result probability of the target result more comprehensively and accurately, the first target result probability of the target result can be obtained using multiple implementation methods flexibly according to the information included in the result feedback information. The specific implementation methods are as follows:

[0174] Obtaining the first target result probability of the target result according to the result feedback information includes:

[0175] If the result feedback information includes the user's satisfaction click behavior for the target result, then according to the satisfaction click behavior, the first target result probability of the target result is obtained, or

[0176] According to the satisfaction click behavior and the sentiment classification model, the first target result probability of the target result is obtained;

[0177] If the result feedback information does not include the user's satisfaction click behavior for the target result, then when the result feedback information includes the result feedback text for the target result, according to the result feedback text, the first target result probability of the target result is obtained, or

[0178] According to the result feedback text and the sentiment classification model, the first target result probability of the target result is obtained.

[0179] Among them, the satisfaction click behavior can be understood as the click behavior of the user's like / dislike of the target result in the above embodiments, and the result feedback text can be understood as the reply information of the user to the target result in the above embodiments.

[0180] Specifically, when the target result is displayed to the user through the interaction interface of the client, buttons for "like / dislike" of the target result can be displayed on the interaction interface. When the user clicks on the "like / dislike" button, the result feedback information includes the user's satisfaction click behavior for the target result. For example, if the user clicks the "like" button, the first target result probability of the target result is 1. Or in the case where the user may accidentally click, to ensure the accuracy of the first target result probability, the target result is analyzed using an emotion classification model, and thus, based on the user's satisfaction click behavior and the emotion classification model, the first target result probability of the target result is obtained.

[0181] When the user does not click on the "like / dislike" button but the user replies to the target result, the result feedback information includes the result feedback text for the target result. For example, after the user obtains the target result and replies "Okay, I got it", the first target result probability of the target result can be obtained based on this reply text; or similarly, to ensure the accuracy of the first target result probability, the target result is analyzed using an emotion classification model, and thus, based on the result feedback text and the emotion classification model, the first target result probability of the target result is obtained.

[0182] Of course, in actual applications, there may also be a situation where the user neither performs a satisfaction click behavior nor replies with an answer feedback text. In this case, the target result can be directly analyzed using an emotion classification model to obtain the first target result probability of the target result.

[0183] The data processing method provided in the embodiments of this specification can flexibly obtain the first target result probability of the target result according to different result feedback information based on the different information included in the result feedback information; and to ensure the accuracy of the first target result probability, the first target result probability of the target result can be obtained based on the result feedback information and the emotion classification model.

[0184] In one or more embodiments of this specification, when obtaining the first target result probability of the target result based on the satisfaction click behavior and the emotion classification model, the behavior result probability and the emotion result probability of the target result are respectively obtained, and thus, based on the behavior result probability and the emotion result probability, the first target result probability of the target result is obtained. The specific implementation method is as follows:

[0185] Obtaining a first target result probability of the target result according to the satisfaction click behavior and the sentiment classification model includes:

[0186] Obtaining a behavior result probability of the target result according to the satisfaction click behavior, where the behavior result probability is used to represent the probability of the sentiment polarity of the user towards the target result obtained through the satisfaction click behavior of the user;

[0187] Using the sentiment classification model to obtain a sentiment result probability of the target result, where the sentiment result probability is used to represent the probability of the sentiment polarity of the user towards the target result obtained through the sentiment classification model;

[0188] Obtaining a first target result probability of the target result according to the behavior result probability and the sentiment result probability.

[0189] Specifically, in the case of obtaining the behavior result probability and the sentiment result probability, the first target result probability of the target result can be calculated by using weighted calculation or directly taking the average value; for example, when the user clicks the "like" button, the behavior result probability of the target result obtained is 1, and the probability of the sentiment polarity of the user towards the target result obtained by using the sentiment classification model is 0.7; then in the case where the weight of like / dislike is w1 (such as 0.6) and the weight of the sentiment classification model is w2 (such as 0.4), the first target result probability is obtained by 0.6 * 1 + 0.4 * 0.7 to be 0.88; or the first target result probability is obtained by taking the average value as (1 + 0.7) / 2, that is, the probability value is 0.85.

[0190] The data processing method provided by the embodiments of this specification can effectively avoid the problem of inaccurate first target result probability caused by incorrect clicks in the satisfaction click behavior of the user when obtaining the first target result probability according to the satisfaction click behavior and the sentiment classification model.

[0191] In one or more embodiments of this specification, in the case of obtaining a first result probability of the target result according to the result feedback text and the sentiment classification model, the feedback result probability and the sentiment result probability of the target result are obtained respectively, so as to obtain the first result probability of the target result according to the feedback result probability and the sentiment result probability. The specific implementation method is as follows:

[0192] Obtaining a first target result probability of the target result according to the result feedback text and the sentiment classification model includes:

[0193] According to the result feedback text, obtain the feedback result probability of the target result, where the feedback result probability is used to represent the probability of the emotional polarity of the user towards the target result obtained through the user's result feedback text;

[0194] Use the sentiment classification model to obtain the sentiment result probability of the target result;

[0195] According to the feedback result probability and the sentiment result probability, obtain the first target result probability of the target result.

[0196] Among them, the feedback result probability can be understood as the probability of the emotional polarity of the user towards the target result obtained according to the user's result feedback text; for example, when the user's result feedback text is "Okay, I understand, thank you", the probability that the user's emotional polarity towards the target result is positive is relatively large; when the user's result feedback text is "No, this is not the result I want", the probability that the user's emotional polarity towards the target result is negative is relatively large.

[0197] When the feedback result probability and the sentiment result probability are obtained, the first target result probability of the target result can be calculated by means of weighted calculation or directly taking the mean; the specific implementation is similar to the above embodiment and will not be elaborated here.

[0198] The data processing method provided in the embodiments of this specification, when obtaining the first target result probability according to the result feedback text and the sentiment classification model, can reasonably and accurately obtain the first target result probability of the target result according to the feedback result probability and the sentiment result probability.

[0199] The data processing method provided in the embodiments of this specification determines the associated example corresponding to the data to be processed through a retrieval enhancement strategy, determines the target classification result of the associated example, and according to the target classification result of the associated example, inputs the data to be processed and the associated example into the data processing model. Using the context ability of the data processing model, the target result corresponding to the data to be processed is obtained. Without training the data processing model, it can break through the limitations of the existing capabilities of the data processing model, meet the long-tail needs of users and improve the question-and-answer efficiency. It can also enable the data processing model to automatically learn to reflect, correct, and improve, improving the accuracy of the target result.

[0200] See Figure 3 , Figure 3 shows the processing procedure flowchart of a data processing method provided in an embodiment of this specification, which specifically includes the following steps.

[0201] Taking the application of the data processing method in a question-and-answer scenario as an example, this data processing method will be described in detail.

[0202] Step 302: User input.

[0203] The user inputs the target question to be queried (i.e., the data to be processed in the above embodiment), such as "There are chickens and rabbits in a cage. The total number of them is 30, and the total number of feet is 80. How many chickens and rabbits are there respectively?".

[0204] Step 304: Retrieve and feedback enhancement.

[0205] Specifically, according to the target question, cases similar to the current target question are retrieved from the knowledge base (i.e., the associated examples in the above embodiment); in practical applications, the number of associated examples can also be adjusted according to the actual situation.

[0206] Among them, according to the user's "like" and "dislike", the sentiment polarity of the associated examples is distinguished. "Like" indicates a positive sentiment polarity, and "dislike" indicates a negative sentiment polarity; and the associated examples are classified using a sentiment classification model, and the user's "like / dislike" and the classification results of the sentiment classification model are weighted and calculated to obtain more reliable user feedback.

[0207] Moreover, the retrieved associated examples and user feedback (sentiment polarity) can be concatenated before the user input in the following way, enabling the data processing model to autonomously learn positive cases through the context and reflect on and avoid negative cases.

[0208] "The following are cases of correctly solving the task. Please learn from them:

[0209] {Positive cases}

[0210] The following are cases of incorrect responses. Please reflect on them and avoid making similar mistakes again:

[0211] {Negative cases}

[0212] Question: {User input}

[0213] Reply: "

[0214] Step 306: Generate program code.

[0215] Specifically, in the case of inputting the concatenated target question and associated examples into the data processing model, the data processing model generates a reply and generates program code to solve the user's target question.

[0216] Step 308: Invoke the code interpreter.

[0217] After the program code is generated, the data processing model interrupts the generation, invokes the code interpreter to run the program code, and obtains the running result corresponding to the program code.

[0218] Step 310: Model reply.

[0219] Splice the operation result into the generated reply of the data processing model. The data processing model completes the reply according to the operation result and outputs the target answer to the target question (i.e., the target result in the above embodiment).

[0220] The data processing method provided in the embodiments of this specification does not require incremental training of the model. By retrieving the knowledge base and context learning, this low-cost and lightweight method enables the data processing model to incrementally expand its capabilities. Moreover, the data processing model does not need to be trained, and it can automatically learn to reflect, correct, and improve from the user's emotional feedback and code operation feedback, thereby improving the accuracy of the reply.

[0221] See Figure 4 , Figure 4 which shows the flowchart of a data interaction method applied to a client provided in an embodiment of this specification, specifically including the following steps.

[0222] Step 402: Receive the data to be processed through the interaction interface and send the data to be processed to the server.

[0223] Step 404: Receive the target result corresponding to the data to be processed obtained by applying the above data processing method returned by the server, display the target result through the interaction interface, and receive the result feedback information for the target result returned through the interaction interface.

[0224] For the specific implementation, refer to the above embodiments and will not be elaborated here.

[0225] The data interaction method provided in the embodiments of this specification can receive the data to be processed input by the user through the interaction interface and display the target result to the user through the interaction interface, which facilitates the user to operate using the interaction interface, improves the interaction efficiency, and provides a good user experience.

[0226] The above is a schematic solution of a data interaction method applied to a client in this embodiment. It should be noted that the technical solution of the data interaction method applied to the client and the technical solution of the above data processing method belong to the same concept. For the details not described in the technical solution of the data interaction method applied to the client, reference can be made to the description of the technical solution of the above data processing method.

[0227] See Figure 5 , Figure 5 which shows the interaction flowchart of a data interaction method applied to a data interaction system provided in an embodiment of this specification, specifically including the following steps.

[0228] Specifically, the data interaction system includes a client and a server.

[0229] Step 502: The client receives the data to be processed through the interaction interface and sends the data to be processed to the server.

[0230] Step 504: The server receives the data to be processed, applies the above data processing method to obtain the target result corresponding to the data to be processed, and returns the target result to the client.

[0231] Step 506: The client receives the target result, displays the target result through the interaction interface, and receives the result feedback information for the target result returned through the interaction interface.

[0232] After receiving the result feedback information for the target result returned through the interaction interface, it further includes:

[0233] The client sends the feedback information to the server;

[0234] The server receives the result feedback information, obtains the first target result probability of the target result according to the result feedback information, and stores the data to be processed, the target result, and the first target result probability of the target result in the retrieval knowledge base.

[0235] The data interaction method provided in the embodiments of this specification can improve the efficiency of users obtaining the target result by receiving the data to be processed input by the user through the client, displaying the target result to the user, and obtaining the target result corresponding to the data to be processed through the server, and using the interaction between the client and the server.

[0236] The above is a schematic solution of a data interaction method applied to a data interaction system in this embodiment. It should be noted that the technical solution of the data interaction method applied to the data interaction system and the technical solution of the above data processing method belong to the same concept. For the details not described in the technical solution of the data interaction method applied to the data interaction system, reference can be made to the description of the technical solution of the above data processing method.

[0237] Corresponding to the above method embodiments, this specification also provides embodiments of a question-and-answer device, Figure 6 showing a schematic structural diagram of a data processing device provided in an embodiment of this specification. As Figure 6 shown, the device, applied to a code execution intelligent system, includes:

[0238] A first determination module 602, configured to determine the data to be processed and determine the associated example corresponding to the data to be processed according to the retrieval enhancement strategy, where the retrieval enhancement strategy is a strategy of retrieving from a retrieval knowledge base and applying the retrieval result to a data processing model;

[0239] A second determination module 604, configured to determine a target classification result of the associated example;

[0240] A result obtaining module 606, configured to determine and run program code corresponding to the data to be processed by using the data processing model according to the data to be processed, the associated example, and the target classification result, and obtain a target result corresponding to the data to be processed.

[0241] Optionally, the result obtaining module 606 is further configured to:

[0242] Obtain program code corresponding to the data to be processed by using the data processing model according to the data to be processed, the associated example, and the target classification result;

[0243] Call a code interpreter through the data processing model to run the program code, obtain a running result corresponding to the program code, and obtain a question reply template according to the running result;

[0244] Obtain a target result corresponding to the data to be processed according to the program code, the running result, and the question reply template.

[0245] Optionally, the second determination module 604 is further configured to:

[0246] Determine a target result probability of the associated example, where the target result probability is used to represent a probability of an emotional polarity of a user for an associated result in the associated example;

[0247] Determine a target classification result of the associated example according to the target result probability.

[0248] The apparatus further includes:

[0249] A storage module, configured to display the target result through an interaction interface of a client, and receive result feedback information returned by the client for the target result; obtain a first target result probability of the target result according to the result feedback information, where the first target result probability is used to represent a probability of an emotional polarity of a user for the target result; store the data to be processed, the target result corresponding to the data to be processed, and the first target result probability of the target result in a retrieval knowledge base.

[0250] Optionally, the storage module is further configured to:

[0251] If the result feedback information includes a satisfaction click behavior of the user for the target result, obtain the first target result probability of the target result according to the satisfaction click behavior, or

[0252] Obtain a first target result probability of the target result according to the satisfaction click behavior and the sentiment classification model;

[0253] If the result feedback information does not include the satisfaction click behavior of the user for the target result, then when the result feedback information includes the result feedback text for the target result, obtain the first target result probability of the target result according to the result feedback text, or

[0254] Obtain a first target result probability of the target result according to the result feedback text and the sentiment classification model.

[0255] Optionally, the storage module is further configured to:

[0256] Obtain a behavioral result probability of the target result according to the satisfaction click behavior, where the behavioral result probability is used to represent the probability of the emotional polarity of the user for the target result obtained through the satisfaction click behavior of the user;

[0257] Obtain an emotional result probability of the target result by using the sentiment classification model, where the emotional result probability is used to represent the probability of the emotional polarity of the user for the target result obtained through the sentiment classification model;

[0258] Obtain a first target result probability of the target result according to the behavioral result probability and the emotional result probability.

[0259] Optionally, the storage module is further configured to:

[0260] Obtain a feedback result probability of the target result according to the result feedback text, where the feedback result probability is used to represent the probability of the emotional polarity of the user for the target result obtained through the result feedback text of the user;

[0261] Obtain an emotional result probability of the target result by using the sentiment classification model;

[0262] Obtain a first target result probability of the target result according to the feedback result probability and the emotional result probability.

[0263] Optionally, the second determination module 604 is further configured to:

[0264] Obtain a second association result probability of the association result according to the sentiment classification model, where the second association result probability is used to represent the probability of the emotional polarity of the user for the association result obtained through the sentiment classification model;

[0265] Determine the target result probability of the associated example according to the first association result probability of the association result and the second association result probability of the association result.

[0266] Optionally, the second determination module 604 is further configured to:

[0267] Determine a first weight value of the first association result probability and a second weight value of the second association result probability;

[0268] Determine the target result probability of the associated example according to the first association result probability, the first weight value, the second association result probability, and the second weight value.

[0269] Optionally, the second determination module 604 is further configured to:

[0270] Determine the target result probability of each associated example according to the first association result probability of each association result and the second association result probability of each association result;

[0271] In the case where the target result probability is greater than or equal to a preset probability threshold, determine the positive classification result of each associated example, or

[0272] In the case where the target result probability is less than the preset probability threshold, determine the negative classification result of each associated example.

[0273] Optionally, the result obtaining module 606 is further configured to:

[0274] According to the target splicing template and the target classification result of the associated example, splice the data to be processed and the associated example and input them into the data processing model;

[0275] Use the data processing model to determine and run the program code corresponding to the data to be processed, and obtain the target result corresponding to the data to be processed output by the data processing model.

[0276] Optionally, the first determination module 602 is further configured to:

[0277] Determine the data to be processed, and select a preset number of associated examples corresponding to the data to be processed from the retrieval knowledge base.

[0278] The data processing device provided in the embodiments of this specification determines associated examples corresponding to the data to be processed by retrieving enhancement policies, determines the target classification results of the associated examples, and based on the target classification results of the associated examples, inputs the data to be processed and the associated examples into a data processing model. Using the context capabilities of the data processing model, the target result corresponding to the data to be processed is obtained. Without training the data processing model, it can break through the limitations of the existing capabilities of the data processing model, meet the long-tail needs of users and improve processing efficiency. It can also enable the data processing model to automatically learn to reflect, correct, and improve, thereby improving the accuracy of the results.

[0279] The above is a schematic solution of a data processing device in this embodiment. It should be noted that the technical solution of this data processing device and the technical solution of the above data processing method belong to the same concept. For the details not described in detail in the technical solution of the data processing device, reference can be made to the description of the technical solution of the above data processing method.

[0280] Corresponding to the above method embodiments, this specification also provides embodiments of a data interaction device applied to a client. Figure 7 The structure diagram of a data interaction device applied to a client provided in an embodiment of this specification is shown. As Figure 7 shown, the device includes:

[0281] A receiving module 702, configured to receive data to be processed through an interaction interface and send the data to be processed to a server;

[0282] A display module 704, configured to receive the target result corresponding to the data to be processed obtained by applying the above data processing method and returned by the server, display the target result through the interaction interface, and receive result feedback information for the target result returned through the interaction interface.

[0283] The data interaction device provided in the embodiments of this specification can receive data to be processed input by a user through an interaction interface and display the target result to the user through the interaction interface, facilitating the user to operate using the interaction interface, improving the interaction efficiency, and providing a good user experience.

[0284] The above is a schematic solution of a data interaction device applied to a client in this embodiment. It should be noted that the technical solution of this data interaction device applied to a client and the technical solution of the above data interaction method applied to a client belong to the same concept. For the details not described in detail in the technical solution of the data interaction device applied to a client, reference can be made to the description of the technical solution of the above data interaction method applied to a client.

[0285] Corresponding to the above method embodiments, this specification also provides data interaction system embodiments. Figure 8 The schematic structural diagram of a data interaction system 800 provided by an embodiment of this specification is shown. As Figure 8 shown, the system includes a client 802 and a server 804, where

[0286] the client 802 is configured to receive data to be processed through an interaction interface and send the data to be processed to the server;

[0287] the server 804 is configured to receive the data to be processed, apply the above data processing method, obtain a target result corresponding to the data to be processed, and return the target result to the client 802;

[0288] the client 802 is further configured to receive the target result, display the target result through the interaction interface, and receive result feedback information for the target result returned through the interaction interface.

[0289] Optionally, the client 802 is further configured to:

[0290] send the feedback information to the server 804;

[0291] Optionally, the client 804 is further configured to:

[0292] receive the result feedback information, obtain a first target result probability of the target result according to the result feedback information, and store the data to be processed, the target result, and the first target result probability of the target result in a retrieval knowledge base.

[0293] The data interaction system provided by the embodiments of this specification can improve the efficiency of users obtaining the target result by receiving the data to be processed input by the user through the client, displaying the target result to the user, obtaining the target result corresponding to the data to be processed through the server, and utilizing the interaction between the client and the server.

[0294] The above is a schematic solution of a data interaction system in this embodiment. It should be noted that the technical solution of this data interaction system and the technical solution of the above data interaction method belong to the same concept. For the details not described in the technical solution of the data interaction system, reference can be made to the description of the technical solution of the above data interaction method.

[0295] Figure 9FIG. 0 shows a block diagram of a computing device 900 provided according to an embodiment of the present specification. The components of the computing device 900 include, but are not limited to, a memory 910 and a processor 920. The processor 920 is connected to the memory 910 via a bus 930, and a database 950 is used to store data.

[0296] The computing device 900 further includes an access device 940, which enables the computing device 900 to communicate via one or more networks 960. Examples of these networks include the Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 940 may include one or more of any type of wired or wireless network interface (e.g., a network interface card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, or a Near Field Communication (NFC) interface.

[0297] In an embodiment of the present specification, the above components of the computing device 900 and Figure 9 other components not shown therein may also be connected to each other, for example, via a bus. It should be understood that Figure 9 the block diagram of the computing device shown is merely for illustrative purposes and is not a limitation on the scope of the present specification. Those skilled in the art may add or replace other components as needed.

[0298] The computing device 900 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smart phones), wearable computing devices (e.g., smart watches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or personal computers (PCs). The computing device 900 can also be a mobile or stationary server.

[0299] Wherein, the processor 920 is configured to execute the following computer-executable instructions, and when the computer-executable instructions are executed by the processor, the steps of the above-mentioned data processing method or data interaction method are implemented.

[0300] The above is a schematic solution of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solutions of the above data processing method or data interaction method belong to the same concept. For the details not described in detail in the technical solution of the computing device, reference can be made to the descriptions of the technical solutions of the above data processing method or data interaction method.

[0301] An embodiment of this specification also provides a computer-readable storage medium, which stores computer programs / instructions, and when the computer programs / instructions are executed by a processor, the steps of the above-mentioned data processing method or data interaction method are implemented.

[0302] The above is a schematic solution of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium and the technical solutions of the above data processing method or data interaction method belong to the same concept. For the details not described in detail in the technical solution of the storage medium, reference can be made to the descriptions of the technical solutions of the above data processing method or data interaction method.

[0303] An embodiment of this specification also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned data processing method or data interaction method are implemented.

[0304] The above is a schematic solution of a computer program product according to this embodiment. It should be noted that the technical solution of this computer program product and the technical solutions of the above data processing method or data interaction method belong to the same concept. For the details not described in detail in the technical solution of the computer program product, reference can be made to the descriptions of the technical solutions of the above data processing method or data interaction method.

[0305] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0306] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, removable hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0307] It should be noted that for the foregoing method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of this specification are not limited by the described order of actions, because according to the embodiments of this specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential for the embodiments of this specification.

[0308] In the above embodiments, the descriptions of the various embodiments have their own focuses. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0309] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The alternative embodiments do not elaborate on all the details and do not limit the invention to only the specific embodiments described. Obviously, many modifications and variations can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can understand and utilize this specification well. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A data processing method, applied to an intelligent code execution system, includes: Determine the data to be processed, and determine the associated example corresponding to the data to be processed according to a retrieval enhancement strategy, where the retrieval enhancement strategy is a strategy of retrieving from a retrieval knowledge base and applying the retrieval result to a data processing model; Determine the target classification result of the associated example; According to the data to be processed, the associated example, and the target classification result, use the data processing model to determine and run the program code corresponding to the data to be processed, and obtain the target result corresponding to the data to be processed.

2. The data processing method according to claim 1, where the step of using the data processing model to determine and run the program code corresponding to the data to be processed according to the data to be processed, the associated example, and the target classification result, and obtaining the target result corresponding to the data to be processed includes: According to the data to be processed, the associated example, and the target classification result, use the data processing model to obtain the program code corresponding to the data to be processed; Call a code interpreter through the data processing model to run the program code, obtain the running result corresponding to the program code, and obtain a question reply template according to the running result; According to the program code, the running result, and the question reply template, obtain the target result corresponding to the data to be processed.

3. The data processing method according to claim 1, where the step of determining the target classification result of the associated example includes: Determine the target result probability of the associated example, where the target result probability is used to represent the probability of the user's emotional polarity towards the associated result in the associated example; Determine the target classification result of the associated example according to the target result probability.

4. The data processing method according to claim 1, after obtaining the target result corresponding to the data to be processed, further includes: Display the target result through an interaction interface of the client, and receive the result feedback information returned by the client for the target result; According to the result feedback information, obtain the first target result probability of the target result, where the first target result probability is used to represent the probability of the user's emotional polarity towards the target result; Store the data to be processed, the target result corresponding to the data to be processed, and the first target result probability of the target result in the retrieval knowledge base.

5. The data processing method according to claim 4, where the step of obtaining the first target result probability of the target result according to the result feedback information includes: If the result feedback information contains the user's satisfaction click behavior for the target result, then obtain the first target result probability of the target result according to the satisfaction click behavior, or Obtain the first target result probability of the target result according to the satisfaction click behavior and an emotion classification model; If the result feedback information does not include the user's satisfaction click behavior for the target result, then when the result feedback information includes the result feedback text for the target result, according to the result feedback text, obtain the first target result probability of the target result, or According to the result feedback text and the sentiment classification model, obtain the first target result probability of the target result.

6. The data processing method according to claim 5, wherein the obtaining the first target result probability of the target result according to the satisfaction click behavior and the sentiment classification model includes: According to the satisfaction click behavior, obtain the behavioral result probability of the target result, where the behavioral result probability is used to represent the probability of the user's sentiment polarity towards the target result obtained through the user's satisfaction click behavior; Use the sentiment classification model to obtain the sentiment result probability of the target result, where the sentiment result probability is used to represent the probability of the user's sentiment polarity towards the target result obtained through the sentiment classification model; According to the behavioral result probability and the sentiment result probability, obtain the first target result probability of the target result.

7. The data processing method according to claim 5, wherein the obtaining the first target result probability of the target result according to the result feedback text and the sentiment classification model includes: According to the result feedback text, obtain the feedback result probability of the target result, where the feedback result probability is used to represent the probability of the user's sentiment polarity towards the target result obtained through the user's result feedback text; Use the sentiment classification model to obtain the sentiment result probability of the target result; According to the feedback result probability and the sentiment result probability, obtain the first target result probability of the target result.

8. The data processing method according to claim 3, wherein the associated example includes associated data corresponding to the data to be processed, an associated result corresponding to the associated data, and a first associated result probability of the associated result; The determining the target result probability of the associated example includes: According to the sentiment classification model, obtain a second associated result probability of the associated result, where the second associated result probability is used to represent the probability of the user's sentiment polarity towards the associated result obtained through the sentiment classification model; According to the first associated result probability of the associated result and the second associated result probability of the associated result, determine the target result probability of the associated example.

9. The data processing method according to claim 8, wherein the determining the target result probability of the associated example according to the first associated result probability of the associated result and the second associated result probability of the associated result includes: Determine a first weight value of the first associated result probability and a second weight value of the second associated result probability; According to the first associated result probability, the first weight value, the second associated result probability, and the second weight value, determine the target result probability of the associated example.

10. The data processing method according to claim 8, wherein there are multiple associated examples; Determining the target result probability of the associated example according to the first associated result probability of the associated result and the second associated result probability of the associated result includes: Determining the target result probability of each associated example according to the first associated result probability of each associated result and the second associated result probability of each associated result; Determining the target classification result of the associated example according to the target result probability includes: When the target result probability is greater than or equal to a preset probability threshold, determining the positive classification result of each associated example, or When the target result probability is less than the preset probability threshold, determining the negative classification result of each associated example.

11. The data processing method according to claim 1, wherein determining and running the program code corresponding to the data to be processed by using the data processing model according to the data to be processed, the associated example, and the target classification result to obtain the target result corresponding to the data to be processed includes: According to the target splicing template and the target classification result of the associated example, splicing the data to be processed and the associated example and inputting them into the data processing model; Using the data processing model to determine and run the program code corresponding to the data to be processed, and obtaining the target result corresponding to the data to be processed output by the data processing model.

12. The data processing method according to claim 8, wherein the first associated result probability of the associated result includes a first positive probability or a first negative probability, and the second associated result probability of the associated result includes a second positive probability or a second negative probability.

13. The data processing method according to claim 1, wherein determining the data to be processed and determining the associated example corresponding to the data to be processed according to the retrieval enhancement strategy includes: Determining the data to be processed and selecting a preset number of associated examples corresponding to the data to be processed from the retrieval knowledge base.

14. A data interaction method applied to a client, including: Receiving the data to be processed through an interaction interface and sending the data to be processed to the server; Receiving the target result corresponding to the data to be processed obtained by applying the data processing method according to any one of claims 1-13 by the server, displaying the target result through the interaction interface, and receiving the result feedback information for the target result returned through the interaction interface.

15. A data interaction method applied to a data interaction system, the system including a client and a server, wherein The client receives the data to be processed through an interaction interface and sends the data to be processed to the server; The server receives the data to be processed, applies the data processing method according to any one of claims 1-13 to obtain the target result corresponding to the data to be processed, and returns the target result to the client; The client receives the target result, displays the target result through the interaction interface, and receives result feedback information for the target result returned through the interaction interface.

16. The data interaction method according to claim 15, after receiving the result feedback information for the target result returned through the interaction interface, further includes: The client sends the result feedback information to the server; The server receives the result feedback information, obtains a first target result probability of the target result according to the result feedback information, and stores the data to be processed, the target result, and the first target result probability of the target result in the retrieval knowledge base.

17. A data processing device, applied to a code execution intelligent system, includes: A first determination module configured to determine data to be processed and determine an associated example corresponding to the data to be processed according to a retrieval enhancement strategy, where the retrieval enhancement strategy is a strategy of retrieving from a retrieval knowledge base and applying the retrieval result to a data processing model; A second determination module configured to determine a target classification result of the associated example; A result obtaining module configured to determine and run a program code corresponding to the data to be processed by using the data processing model according to the data to be processed, the associated example, and the target classification result, and obtain a target result corresponding to the data to be processed.

18. A data interaction device, applied to a client, includes: A receiving module configured to receive data to be processed through an interaction interface and send the data to be processed to a server; A display module configured to receive a target result corresponding to the data to be processed obtained by applying the data processing method according to any one of claims 1-13 returned by the server, display the target result through the interaction interface, and receive result feedback information for the target result returned through the interaction interface.

19. A data interaction system includes a client and a server, where The client is configured to receive data to be processed through an interaction interface and send the data to be processed to the server; The server is configured to receive the data to be processed, apply the data processing method according to any one of claims 1-13, obtain a target result corresponding to the data to be processed, and return the target result to the client; The client is further configured to receive the target result, display the target result through the interaction interface, and receive result feedback information for the target result returned through the interaction interface.

20. A computing device, comprising: A memory and a processor; 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 data processing method according to any one of claims 1 to 13 or the data interaction method according to any one of claims 14 to 16 are implemented.

21. A computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the steps of the data processing method described in any one of claims 1 to 13 or the steps of the data interaction method described in any one of claims 14 to 16 are implemented.

22. A computer program product stores a computer program / instructions, and when the computer program / instructions are executed by a processor, the steps of the data processing method described in any one of claims 1 to 13 or the steps of the data interaction method described in any one of claims 14 to 16 are implemented.

Images