Data processing method and system based on AI questions and answers

Abstract

The invention is suitable for the technical field of intelligent education, and provides a data processing method and system based on AI questions and answers, and the method comprises the steps: obtaining error option information, questioning information and historical answering information of a target user in response to a user questioning instruction, and then obtaining a preset knowledge database based on the preset knowledge database and the error option information; according to the method, correct answer information is quickly generated, then auxiliary knowledge information is generated according to question information and historical answer information, and finally reply result information is effectively generated according to the correct answer information and the auxiliary knowledge information. According to the method, intelligent and multi-dimensional deep analysis can be carried out on the learning condition of the user, the knowledge mastering degree and weak links of the user can be accurately positioned, a knowledge point case highly matched with the current learning condition of the user is dynamically generated, more highly-correlated and high-value learning contents are provided for the user, and the teaching effect is improved.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent education, and more specifically, to a data processing method and system based on AI question-answering. Background Art

[0002] Compared with traditional paper-based examination papers, educational software allows students to study anytime and anywhere without having to carry heavy books or go to tutoring classes, thus improving the efficiency of study time utilization. This has led to the wider application of educational software.

[0003] At present, when students encounter wrong questions, they usually just simply look up the specific wrong questions. Since the current educational software cannot conduct in-depth analysis based on the specific situation of the students, there is a problem of poor teaching effect, which needs further improvement. Summary of the Invention

[0004] Based on this, the embodiment of the present application provides a data processing method and system based on AI question and answer to solve the problem of poor teaching effect in the existing technology.

[0005] In a first aspect, an embodiment of the present application provides a data processing method based on AI question-answering, the method comprising: In response to a user's questioning instruction, obtaining the target user's wrong option information, question information, and historical answer information; Generating correct answer information based on a preset knowledge database and the incorrect option information; generating auxiliary knowledge information based on the question information and the historical answer information; Reply result information is generated based on the correct answer information and the auxiliary knowledge information.

[0006] Compared with the existing technology, the beneficial effect is: the data processing method based on AI question and answer provided by the embodiment of the present application, the terminal device can first respond to the user's question instruction, obtain the target user's wrong option information, question information and historical answer information, and then quickly generate correct answer information based on the preset knowledge database and wrong option information, and then generate auxiliary knowledge information based on the question information and historical answer information, and finally effectively generate response result information based on the correct answer information and auxiliary knowledge information, thereby realizing in-depth analysis based on the students' specific learning situation, providing students with more knowledge points that are strongly related to wrong questions, effectively improving teaching effects, and to a certain extent solving the current problem of poor teaching effects.

[0007] In a second aspect, an embodiment of the present application provides a data processing system based on AI question-answering, the system comprising: Question information acquisition module: used to respond to the user's question instruction and obtain the target user's wrong option information, question information and historical answer information; Correct answer information generation module: used to generate correct answer information based on a preset knowledge database and the wrong option information; Auxiliary knowledge information generation module: used to generate auxiliary knowledge information based on the question information and the historical answer information; Response result information generation module: used to generate response result information based on the correct answer information and the auxiliary knowledge information.

[0008] In a third aspect, an embodiment of the present application provides a terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method of the first aspect described above when executing the computer program.

[0009] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method of the first aspect described above are implemented.

[0010] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art.

[0012] Figure 1 This is a flow chart of a data processing method provided in one embodiment of the present application; Figure 2 1 is a flow chart of step S300 in the data processing method provided in one embodiment of the present application; Figure 3 This is a flow chart of the data processing method after step S300 according to an embodiment of the present application; Figure 4 A schematic diagram of the flow chart after step S307 in the data processing method provided in one embodiment of the present application; Figure 5 A schematic diagram of the flow chart after step S400 in the data processing method provided in one embodiment of the application; Figure 6 This is a module block diagram of a data processing system provided by an embodiment of the present application; Figure 7 This is a schematic diagram of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0013] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0014] In the description of this application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0015] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0016] In order to illustrate the technical solution described in this application, specific embodiments are provided below.

[0017] See also Figure 1 , Figure 1 : is a flow chart of a data processing method based on AI question-answering provided in an embodiment of the present application. In this embodiment, the execution subject of the data processing method is a terminal device. It is understood that the types of terminal devices include but are not limited to mobile phones, tablet computers, laptops, ultra-mobile personal computers (Ultra-Mobile Personal Computers, UMPCs), netbooks, personal digital assistants (Personal Digital Assistants, PDAs), etc., and the embodiments of the present application do not impose any restrictions on the specific types of terminal devices.

[0018] See also Figure 1 The data processing method provided in the embodiment of the present application includes but is not limited to the following steps: In S100 , in response to a user's questioning instruction, the target user's wrong option information, questioning information, and historical answer information are obtained.

[0019] Specifically, the terminal device can first respond to a user question instruction and obtain the target user's incorrect option information, question information, and historical answer information. The user question instruction is used to indicate that the target user has initiated a question request. For example, after the target user incorrectly answers a question on the educational software, the target user can send a user question instruction to the terminal device via the user terminal; the target user can be a student. The incorrect option information describes the incorrect option selected by the target user in the current question; the question information describes the question entered by the target user in response to the current question; and the historical answer information describes the questions the target user has answered in the past.

[0020] In S200, correct answer information is generated based on a preset knowledge database and incorrect option information.

[0021] Specifically, after the terminal device obtains the question information and historical answer information, the terminal device can search the questions corresponding to the incorrect option information based on the preset knowledge database, determine the correct answer in the current question, and quickly generate the correct answer information, wherein the knowledge database pre-stores multiple questions, all pre-options corresponding to each question, and the correct options corresponding to each question; the correct answer information is used to describe the correct option for the current question.

[0022] In S300 , auxiliary knowledge information is generated based on question information and historical answer information.

[0023] Specifically, after the terminal device generates the correct answer information, the terminal device can accurately generate auxiliary knowledge information based on the question information and historical answer information, wherein the auxiliary knowledge information is used to assist the target user to efficiently learn knowledge points related to the current question.

[0024] Without loss of generality, the historical answer information includes multiple incorrect question information and the chapter information corresponding to each incorrect question information, wherein the incorrect question information is used to describe the questions that the target user answered incorrectly in the past; the chapter information is used to describe the chapter corresponding to the incorrectly answered question in the course.

[0025] In some possible implementations, in order to generate effective auxiliary knowledge information, please refer to Figure 2 Step S300 includes but is not limited to the following steps: In S310 , target chapter information is determined based on a preset keyword extraction algorithm and question information.

[0026] Specifically, the terminal device can use a preset keyword extraction algorithm to perform keyword extraction processing on the question information, and quickly determine the target chapter information based on the keywords of the question information and the current topic corresponding to the question information. The keyword extraction algorithm can be a RAKE (Rapid Automatic Keyword Extraction) algorithm; the target chapter information is used to describe the chapter corresponding to the current topic in the course to which it belongs.

[0027] In S320, for each incorrect question information in the historical answer information: determine whether the chapter information corresponding to the incorrect question information is the same as the target chapter information.

[0028] Specifically, after the terminal device determines the target chapter information, the terminal device can perform this processing for each incorrect question information in the historical answer information: determine whether the chapter information corresponding to the incorrect question information is the same as the target chapter information.

[0029] In S330 , if the chapter information corresponding to the erroneous title information is the same as the target chapter information, then the associated knowledge information of the erroneous title information is obtained.

[0030] Specifically, if the chapter information corresponding to the incorrect question information is the same as the target chapter information, it indicates that the current question is related to the questions that the target user has answered incorrectly in the past, so the terminal device can obtain the associated knowledge information of the incorrect question information, where the associated knowledge information is used to describe the knowledge points associated with the incorrect question information.

[0031] In S340 , the associated knowledge information is determined to be auxiliary knowledge information.

[0032] Specifically, after the terminal device obtains the associated knowledge information, the terminal device can quickly determine the associated knowledge information as auxiliary knowledge information, thereby helping the target user to learn more knowledge points related to the current question and improving teaching effects.

[0033] In some possible implementations, in order to further improve the teaching effect, please refer to Figure 3 After step S300, the method further includes but is not limited to the following steps: In S301 , in response to a deep analysis instruction, multiple thought keyword information of a target user is obtained.

[0034] Without loss of generality, the historical answer information also includes correct option information corresponding to each incorrect question information, wherein the correct option information is used to describe the correct option corresponding to the incorrect question information.

[0035] Specifically, the terminal device can respond to the in-depth analysis instruction and obtain multiple keyword information of the target user. The in-depth analysis instruction is used to indicate that the user has initiated an in-depth analysis request. The keyword information is used to describe the keywords that the target user is thinking about while solving the current problem. The keyword information can be manually entered by the target user.

[0036] In S302, based on a preset question database, multiple keyword-related information of correct option information is obtained.

[0037] Specifically, after the terminal device obtains the thinking keyword information, the terminal device can obtain multiple keyword-related information of the correct option information based on a preset question database, wherein the keyword-related information is used to describe the keywords corresponding to the correct option information.

[0038] In S303 , based on a preset synonym database, first synonym information corresponding to each piece of thinking keyword information is obtained, and second synonym information corresponding to each piece of related keyword information is obtained.

[0039] Specifically, after the terminal device obtains multiple keyword-related information, the terminal device can obtain the first synonym information corresponding to each thinking keyword information based on a preset synonym database, and obtain the second synonym information corresponding to each keyword-related information, wherein the synonym database is used to store multiple words and their synonyms; the first synonym information is used to describe the synonyms of the thinking keyword information, that is, words that are close or similar in meaning to the thinking keyword information, and the second synonym information is used to describe the synonyms of the keyword-related information, that is, words that are close or similar in meaning to the keyword-related information.

[0040] In S304, first coincidence information is generated based on the thought keyword information and the related keyword information.

[0041] Specifically, after the terminal device obtains the first synonym information and the second synonym information, the terminal device can determine the overlapping words and the number of overlapping words among multiple thinking keyword information and multiple related keyword information, and effectively determine the generation of first overlap information, wherein the overlapping words are used to describe the thinking keyword information that is the same as the related keyword information.

[0042] Exemplarily, the terminal device can first determine a first number of overlapping words between multiple thinking keyword information and multiple related keyword information, and then determine the total word quantity based on the sum of the number of multiple thinking keyword information and multiple related keyword information, recorded as the second number, and then use the quotient of the first number divided by the second number to determine the first overlap information.

[0043] In S305 , second coincidence degree information is generated based on the first synonym information and the second synonym information.

[0044] Specifically, after the terminal device generates the first overlap information, the terminal device can generate the second overlap information based on the first synonym information and the second synonym information. The specific calculation process can refer to the relevant content in the above step S304, so it is not repeated here.

[0045] In S306 , it is determined whether the first overlap information is less than a preset overlap threshold information, and whether the second overlap information is less than the overlap threshold information.

[0046] Specifically, after the terminal device generates the second coincidence information, the terminal device can determine whether the first coincidence information is less than the preset coincidence threshold information, and at the same time determine whether the second coincidence information is less than the coincidence threshold information. In S307 , if the first overlap information is less than the overlap threshold information and the second overlap information is less than the overlap threshold information, a serious thinking direction error message is generated; otherwise, a normal thinking direction error message is generated.

[0047] Specifically, if the first overlap information is less than the overlap threshold information, and at the same time the second overlap information is less than the overlap threshold information, it indicates that the target user's thinking direction seriously deviates from the thinking direction of selecting the correct answer, so the terminal device can generate a serious error in thinking direction information, wherein the serious error in thinking direction information is used to describe that the target user's thinking direction seriously deviates from the thinking direction of the correct answer. Otherwise, the terminal device can generate a regular error in thinking direction information, wherein the regular error in thinking direction information is used to describe that the target user's thinking direction generally deviates from the thinking direction of the correct answer.

[0048] In some possible implementations, in order to facilitate the target users to know their own learning status, please refer to Figure 4 If the terminal device generates a serious thinking direction error message, after step S300, the method further includes but is not limited to the following steps: In S308, each piece of thought keyword information and each piece of related keyword information are compared in sequence to determine the difference keyword set information.

[0049] Specifically, the terminal device can compare each thinking keyword information and each related keyword information in turn, and quickly determine the difference keyword set information among multiple thinking keyword information and multiple related keyword information, wherein the difference keyword set information includes multiple difference keywords, and the difference keywords are used to describe the related keyword information that is different from the thinking keyword information.

[0050] In S309 , based on the synonym database, a plurality of first-order synonym information corresponding to each difference keyword is obtained, and a plurality of second-order synonym information corresponding to each first-order synonym information is obtained.

[0051] Specifically, after the terminal device determines the difference keyword set information, the terminal device can obtain multiple first-order synonym information corresponding to each difference keyword based on the synonym database, and at the same time obtain multiple second-order synonym information corresponding to each first-order synonym information, wherein the first-order synonym information is used to describe the synonyms of the difference keyword, and the second-order synonym information is used to describe the synonyms of the first-order synonym information.

[0052] In S3091 , core keyword information is determined based on a plurality of first-order synonym information and a plurality of second-order synonym information.

[0053] Specifically, after the terminal device obtains the first-order synonym information and the second-order synonym information, the terminal device can first determine the first-order synonym information that is not the same as any thinking keyword information, and then process these first-order synonym information to determine that the first-order synonym information whose corresponding all second-order synonym information is not the same as any thinking keyword information is the core keyword information, and effectively determine the core keyword information, so as to determine the most missing keywords in the thinking direction of the target user. After knowing the core keyword information, the target user is helped to match his or her thinking direction with the thinking direction of answering the question correctly, wherein the multiple first-order synonym information corresponding to the core keyword information are not the same as any thinking keyword information, and the multiple second-order synonym information corresponding to the core keyword information are not the same as any thinking keyword information, that is, the respective second-order synonym information corresponding to the multiple first-order synonym information of the core keyword information are not the same as any thinking keyword information.

[0054] In S3092 , the difference keyword set information and the core keyword information are sent to the user terminal of the target user.

[0055] Specifically, after the terminal device determines the core keyword information, the terminal device can send the difference keyword set information and the core keyword information to the user terminal of the target user, so that the target user can directly understand the differences between the thinking direction of the correct answer and the most missing keywords in the thinking direction.

[0056] In S400, response result information is generated based on the correct answer information and the auxiliary knowledge information.

[0057] Specifically, the terminal device can generate reply result information based on the correct answer information and the auxiliary knowledge information, wherein the reply result information is used to describe the analysis results obtained by performing an in-depth analysis on the learning situation of the target user.

[0058] In some possible implementations, in order to facilitate the tracing of the target user's learning status, please refer to Figure 5 After step S400, the method further includes but is not limited to the following steps: In S401 , learning profile information is generated based on question information and answer result information.

[0059] Specifically, the terminal device may generate learning profile information based on the question information and the answer result information, wherein the learning profile information is used to describe a personal profile related to the target user's learning situation.

[0060] In S402, the learning profile information is sent to the cloud server.

[0061] Specifically, after the terminal device generates the learning profile information, the terminal device can send the learning profile information to the cloud server.

[0062] In one possible implementation, after step S400, the terminal device may also evaluate and review the reply result information from multiple dimensions, for example, assigning a weight of 0.4 to the accuracy of the reply result information, a weight of 0.2 to the completeness of the reply result information, a weight of 0.2 to the relevance of the reply result information, a weight of 0.1 to the logic of the reply result information, and a weight of 0.1 to the timeliness of the reply result information, and then multiplying the evaluation scores of each dimension by the corresponding weights and adding them together to obtain the overall evaluation score.

[0063] In one possible implementation, after step S400, the terminal device may also collect the user's evaluation of the reply result information, quantify the user feedback data, for example, record satisfaction as 1 and dissatisfaction as 0, and then incorporate the user feedback score into the calculation of the overall evaluation score, for example, appropriately reduce other weights, and then give the user feedback score a weight of 0.2, and then calculate the final evaluation result in combination with the scores of other dimensions.

[0064] The implementation principle of the data processing method based on AI question and answer in the embodiment of the present application is: the terminal device can first respond to the user's question instruction, obtain the target user's wrong option information, question information and historical answer information, and then quickly generate correct answer information based on the preset knowledge database and wrong option information, and then generate auxiliary knowledge information based on the question information and historical answer information. Finally, based on the correct answer information and the auxiliary knowledge information, effectively generate reply result information, thereby achieving in-depth analysis based on the students' specific learning situation, providing students with more strongly relevant knowledge points, and effectively improving teaching effectiveness.

[0065] It should be noted that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0066] The embodiment of the present application also provides a data processing system based on AI question answering. For ease of explanation, only the parts related to the present application are shown, such as Figure 6 As shown, the system 60 includes: The question information acquisition module 61 obtains the target user's wrong option information, question information and historical answer information in response to the user's question instruction; The correct answer information generating module 62 generates correct answer information based on a preset knowledge database and incorrect option information; The auxiliary knowledge information generating module 63 generates auxiliary knowledge information based on the question information and the historical answer information; The answer result information generating module 64 generates answer result information according to the correct answer information and the auxiliary knowledge information.

[0067] Optionally, the historical answer information includes multiple incorrect question information and chapter information corresponding to each incorrect question information; the auxiliary knowledge information generation module 63 includes: Target chapter information determination submodule: used to determine the target chapter information based on the preset keyword extraction algorithm and question information; The chapter information judgment submodule is used to judge whether the chapter information corresponding to the wrong question information is the same as the target chapter information for each wrong question information in the historical answer information; Related knowledge information acquisition submodule: used to obtain related knowledge information of the wrong title information if the chapter information corresponding to the wrong title information is the same as the target chapter information; Auxiliary knowledge information determination submodule: used to determine the associated knowledge information as auxiliary knowledge information.

[0068] Optionally, the historical answer information also includes correct option information corresponding to each incorrect question information; the system 60 also includes: Thinking keyword information acquisition module: used to obtain multiple thinking keyword information of the target user in response to the deep analysis instruction; Keyword information acquisition module: used to obtain multiple keyword information related to correct option information based on a preset question database; Synonym information acquisition module: used to acquire first synonym information corresponding to each thinking keyword information and second synonym information corresponding to each related keyword information based on a preset synonym database; A first coincidence information generating module is configured to generate first coincidence information based on the thought keyword information and the related keyword information; A second coincidence information generating module: configured to generate second coincidence information based on the first synonym information and the second synonym information; Coincidence information judgment module: used to judge whether the first coincidence information is less than the preset coincidence threshold information, and whether the second coincidence information is less than the coincidence threshold information; Thinking direction serious error information generating module: used to generate thinking direction serious error information if the first overlap information is less than the overlap threshold information and the second overlap information is less than the overlap threshold information, otherwise generate thinking direction normal error information.

[0069] Optionally, the system 60 further includes: A difference keyword set information determination module is used to sequentially compare each piece of thinking keyword information with each piece of related keyword information to determine difference keyword set information, wherein the difference keyword set information includes a plurality of difference keywords, and the difference keywords are used to describe related keyword information that is different from the thinking keyword information; First-order synonym information acquisition module: used to acquire multiple first-order synonym information corresponding to each difference keyword based on the synonym database, and acquire multiple second-order synonym information corresponding to each first-order synonym information; A core keyword information determination module is configured to determine core keyword information based on a plurality of first-order synonym information and a plurality of second-order synonym information, wherein the plurality of first-order synonym information corresponding to the core keyword information is not identical to any of the thinking keyword information, and the plurality of second-order synonym information corresponding to the core keyword information is not identical to any of the thinking keyword information; The difference keyword set information sending module is used to send the difference keyword set information and the core keyword information to the user terminal of the target user.

[0070] Optionally, the system 60 further includes: Learning profile information generation module: used to generate learning profile information based on question information and answer result information; Learning file information sending module: used to send learning file information to the cloud server.

[0071] It should be noted that the information interaction, execution process and other contents between the above modules are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0072] The present application also provides a terminal device, such as Figure 7As shown, the terminal device 70 of this embodiment includes: a processor 71, a memory 72, and a computer program 73 stored in the memory 72 and executable on the processor 71. When the processor 71 executes the computer program 73, the steps in the above-mentioned data processing method embodiment are implemented, for example Figure 1 Steps S100 to S400 shown; or, when the processor 71 executes the computer program 73, the functions of each module in the above device are realized, for example Figure 6 The functions of modules 61 to 64 are shown.

[0073] The terminal device 70 can be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server, and the terminal device 70 includes but is not limited to a processor 71 and a memory 72. Those skilled in the art will understand that Figure 7 It is merely an example of the terminal device 70 and does not constitute a limitation of the terminal device 70. The terminal device 70 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device 70 may also include input and output devices, network access devices, buses, etc.

[0074] Among them, the processor 71 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.; the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0075] The memory 72 can be an internal storage unit of the terminal device 70, such as a hard disk or memory of the terminal device 70, or the memory 72 can be an external storage device of the terminal device 70, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal device 70; further, the memory 72 can also include both the internal storage unit of the terminal device 70 and the external storage device, the memory 72 can also store the computer program 73 and other programs and data required by the terminal device 70, and the memory 72 can also be used to temporarily store data that has been output or is to be output.

[0076] One embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form; the computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium.

[0077] The above are all preferred embodiments of the present application, and are not intended to limit the scope of protection of the present application. Therefore, any equivalent changes made based on the methods, principles, and structures of the present application should be included in the scope of protection of the present application.

Claims

1. A data processing method based on AI question and answer, characterized in that: The method comprises: In response to a user's questioning instruction, obtaining the target user's wrong option information, questioning information, and historical answer information; Generate correct answer information based on a preset knowledge database and the wrong option information; Generate auxiliary knowledge information according to the question information and the historical answer information; Reply result information is generated based on the correct answer information and the auxiliary knowledge information.

2. The method according to claim 1, characterized in that: The historical answer information includes a plurality of wrong question information and the chapter information corresponding to each of the wrong question information; The generating of auxiliary knowledge information according to the question information and the historical answer information includes: Determine target chapter information according to a preset keyword extraction algorithm and the question information; For each of the wrong question information in the historical answer information: determining whether the chapter information corresponding to the wrong question information is the same as the target chapter information; If the chapter information corresponding to the erroneous title information is the same as the target chapter information, then obtaining the associated knowledge information of the erroneous title information; The associated knowledge information is determined to be the auxiliary knowledge information.

3. The method according to claim 2, characterized in that The historical answer information also includes correct option information corresponding to each of the incorrect question information; after generating auxiliary knowledge information according to the question information and the historical answer information, the method further includes: In response to the deep analysis instruction, obtaining multiple thinking keyword information of the target user; Based on the preset question database, multiple keyword information related to the correct option information is obtained; Based on a preset synonym database, first synonym information corresponding to each of the thinking keyword information is obtained, and second synonym information corresponding to each of the related keyword information is obtained; Generate first coincidence information according to the thought keyword information and the related keyword information; generating second coincidence degree information according to the first synonym information and the second synonym information; Determine whether the first coincidence information is less than a preset coincidence threshold information, and whether the second coincidence information is less than the coincidence threshold information; If the first overlap information is less than the overlap threshold information, and the second overlap information is less than the overlap threshold information, a serious thinking direction error message is generated, otherwise a normal thinking direction error message is generated.

4. The method according to claim 3, characterized in that If the serious error in thinking direction information is generated, after generating the auxiliary knowledge information according to the question information and the historical answer information, the method further includes: Compare each of the thinking keyword information and each of the related keyword information in sequence to determine difference keyword set information, wherein the difference keyword set information includes a plurality of difference keywords, and the difference keywords are used to describe the related keyword information that is different from the thinking keyword information; Based on the synonym database, obtaining a plurality of first-order synonym information corresponding to each of the difference keywords, and obtaining a plurality of second-order synonym information corresponding to each of the first-order synonym information; Determine core keyword information based on the plurality of first-order synonym information and the plurality of second-order synonym information, wherein the plurality of first-order synonym information corresponding to the core keyword information is not the same as any of the thinking keyword information, and the plurality of second-order synonym information corresponding to the core keyword information is not the same as any of the thinking keyword information; The difference keyword set information and the core keyword information are sent to a user terminal of the target user.

5. The method according to claim 1, characterized in that After generating the reply result information according to the correct answer information and the auxiliary knowledge information, the method further includes: Generate learning profile information based on the question information and the answer result information; Send the learning profile information to the cloud server.

6. A data processing system based on AI question and answer, characterized in that: The system comprises: Question information acquisition module: used to respond to the user's question instruction and obtain the target user's wrong option information, question information and historical answer information; Correct answer information generating module: used for generating correct answer information based on a preset knowledge database and the wrong option information; Auxiliary knowledge information generation module: used to generate auxiliary knowledge information according to the question information and the historical answer information; Reply result information generation module: used to generate reply result information based on the correct answer information and the auxiliary knowledge information.

7. The system according to claim 6, characterized in that The historical answer information includes a plurality of wrong question information and the corresponding chapter information of each wrong question information; the auxiliary knowledge information generation module includes: Target chapter information determination submodule: used to determine the target chapter information according to a preset keyword extraction algorithm and the question information; The chapter information determination submodule is used to determine, for each of the wrong question information in the historical answer information, whether the chapter information corresponding to the wrong question information is the same as the target chapter information; The associated knowledge information acquisition submodule is used to acquire the associated knowledge information of the erroneous title information if the chapter information corresponding to the erroneous title information is the same as the target chapter information; Auxiliary knowledge information determination submodule: used to determine that the associated knowledge information is the auxiliary knowledge information.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images