AI tool questioning method, computer equipment, and media
By obtaining the user's historical learning and examination information, predicting question keywords and using the question generation model, the inefficiency problem of users having to manually enter questions is solved, and efficient questioning is achieved.
Patent Information
- Application Number
- CN202511033445.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-25
- Publication Date
- 2025-09-30
- Estimated Expiration
- 2045-07-25
AI Technical Summary
When users ask questions to AI tools, they need to manually enter each character, resulting in inefficient questioning.
By obtaining the current user's historical learning information and historical examination information, predicting the keywords of the question, and using the question generation model to output multiple questions to be selected, the user selects the target question and directly inputs it into the AI tool.
It avoids users from manually entering questions and improves the efficiency of asking questions to AI tools.
Smart Images
Figure CN120524543B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of AI tool technology, and in particular to an AI tool questioning method, computer equipment, and medium. Background Art
[0002] In industries like architectural design, AI (artificial intelligence) tools are available for interior design. Users can ask questions to the AI tools and receive corresponding answers, eliminating the need to search for the answers in numerous interior design books.
[0003] However, when users ask questions to AI tools, they need to manually enter each character in the question to complete the question, which makes asking questions very inconvenient and greatly reduces the efficiency of asking questions to AI tools. Summary of the Invention
[0004] The embodiments of the present application provide a question-asking method, computer device, and medium for an AI tool, which aim to avoid the user manually entering each character in the question, thereby improving the efficiency of asking questions to the AI tool.
[0005] In a first aspect, an embodiment of the present application provides a questioning method of an AI tool, the questioning method of the AI tool comprising:
[0006] Get the current user's historical learning information and historical examination information;
[0007] Predicting keywords for the question currently required by the user based on the historical learning information and the historical examination information to obtain target keywords;
[0008] Inputting the target keyword into a preset question generation model to receive a plurality of candidate questions output by the question generation model;
[0009] Outputting a plurality of the candidate questions to determine a target question from the plurality of the candidate questions;
[0010] The target question is input into the AI tool of the architectural design industry to complete the questioning.
[0011] In some embodiments, the question generation model is generated by the following steps:
[0012] Obtaining a model training data set of a neural network model, wherein the model training data set includes a plurality of preset keywords and a plurality of preset questions corresponding to each of the preset keywords;
[0013] The neural network model is trained using the model training data set to obtain the problem generation model.
[0014] In some embodiments, the historical learning information includes the first knowledge point learned by the current user in the historical period;
[0015] The historical examination information includes a second knowledge point in an examination of the current user during a historical period, and a third knowledge point in the second knowledge point to which the current user gave an incorrect answer.
[0016] In some embodiments, the predicting of keywords for the question required by the current user based on the historical learning information and the historical examination information to obtain target keywords includes:
[0017] Determining a first keyword in a plurality of the first knowledge points, a second keyword in a plurality of the second knowledge points, and a third keyword in a plurality of the third knowledge points;
[0018] The target keyword is determined based on the first keyword, the second keyword, and the third keyword.
[0019] In some embodiments, determining the target keyword based on the first keyword, the second keyword, and the third keyword includes:
[0020] performing deduplication processing on the plurality of the first keywords, the plurality of the second keywords, and the plurality of the third keywords to obtain a plurality of fourth keywords;
[0021] For each of the fourth keywords, determining the number of occurrences of the fourth keyword in the first keywords, the second keywords, and the third keywords;
[0022] Based on the number of occurrences, the target keyword is determined from the plurality of fourth keywords.
[0023] In some embodiments, determining the target keyword from the plurality of fourth keywords based on the number of occurrences includes:
[0024] Determine a plurality of fifth keywords from the plurality of fourth keywords, wherein at least two of the occurrence counts of the fifth keywords in the plurality of first keywords, the plurality of second keywords, and the plurality of third keywords are non-zero;
[0025] Based on the number of occurrences, the target keyword is determined from the plurality of fifth keywords.
[0026] In some embodiments, determining the target keyword from the plurality of fifth keywords based on the number of occurrences includes:
[0027] For each of the fifth keywords, performing a weighted summation of the number of times the fifth keyword appears in the first keywords, the second keywords, and the third keywords to obtain a comprehensive number of occurrences;
[0028] Based on the comprehensive number of occurrences, the target keyword is determined from the plurality of fifth keywords.
[0029] In some embodiments, the weight of the fifth keyword when performing a weighted sum of the number of times the fifth keyword appears in the plurality of first keywords, the plurality of second keywords, and the plurality of third keywords is determined by:
[0030] Determining a first historical moment of a first knowledge point most recently learned in the historical learning information;
[0031] Determine a second historical moment of a second knowledge point of a most recent exam in the historical exam information;
[0032] Determining a third historical moment of a third knowledge point in the historical test information where a third knowledge point was most recently answered incorrectly;
[0033] Based on the time sequence between the first historical moment, the second historical moment, and the third historical moment, different weights are set for the number of times the fifth keyword appears in multiple first keywords, multiple second keywords, and multiple third keywords respectively.
[0034] In a second aspect, an embodiment of the present application provides a questioning device for an AI tool, wherein the questioning device for the AI tool includes:
[0035] The acquisition module is used to obtain the current user's historical learning information and historical examination information;
[0036] A prediction module, configured to predict keywords for the question currently required by the user based on the historical learning information and the historical examination information, and obtain target keywords;
[0037] A question generation module, configured to input the target keyword into a preset question generation model to receive a plurality of candidate questions output by the question generation model;
[0038] A question determination module is used to output a plurality of the candidate questions to determine a target question from the plurality of the candidate questions;
[0039] The questioning module is used to input the target question into the AI tool of the architectural design industry to complete the questioning.
[0040] In a third aspect, an embodiment of the present application provides a computer device comprising a processor and a memory, wherein a computer program is stored in the memory, and the computer program is configured to be executed by the processor to implement the questioning method of the AI tool as described in any one of the above items.
[0041] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, wherein the computer program is configured to be executed by a processor to implement the question-asking method of the AI tool as described in any one of the above items.
[0042] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program or instructions, which are executed by a processor to implement the questioning method of the AI tool as described in any of the above items.
[0043] Beneficial effects of the embodiments of the present application:
[0044] In an embodiment of the present application, the keywords of the questions required by the current user are predicted through the current user's historical learning information and historical examination information, so that the questions required by the current user are completed for asking questions to the AI tool, avoiding the user manually entering each character in the question and improving the efficiency of asking questions to the AI tool. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] 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 description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0046] Figure 1 This is a flowchart of an embodiment of the questioning method of the AI tool provided in the embodiments of the present application;
[0047] Figure 2 This is a flowchart of another embodiment of the questioning method of the AI tool provided in the embodiments of the present application;
[0048] Figure 3 This is a flowchart of another embodiment of the questioning method of the AI tool provided in the embodiments of the present application;
[0049] Figure 4 This is a flowchart of another embodiment of the questioning method of the AI tool provided in the embodiments of the present application;
[0050] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0051] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.
[0052] In the description of this application, "plurality" means two or more, unless otherwise specifically defined. Furthermore, in the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features being described. Thus, features defined as "first" or "second" may explicitly or implicitly include one or more of the described features.
[0053] In the first aspect, the embodiments of the present application provide a method for asking questions using an AI tool. Figure 1 , Figure 1 The following is a flow chart of an embodiment of a questioning method of an AI tool. Figure 1 The AI tool's questioning methods may include:
[0054] 101. Get the current user's historical learning information and historical examination information.
[0055] In an embodiment of the present application, the current user refers to the user of the platform where the AI tool is located, and the platform is connected to the platform for learning, practicing, and assessing content such as interior design, so as to obtain the current user's historical learning information and historical examination information from the platform for learning, practicing, and assessing content such as interior design.
[0056] In the embodiment of the present application, the historical learning information of the current user refers to the historical learning record of the current user on the content of interior design, etc. The historical examination information of the current user refers to the historical examination record of the current user on the content of interior design, etc.
[0057] 102. Based on historical learning information and historical examination information, predict the keywords of the questions required by the current user to obtain target keywords.
[0058] In the embodiment of the present application, since it is necessary to predict the questions that the current user needs, the keywords of the questions that the current user needs can be predicted first to obtain the target keywords. The historical learning information and historical examination information represent the current user's historical needs for content such as interior design. Therefore, the keywords of the questions that the current user needs can be predicted based on the historical learning information and historical examination information, making the prediction of the questions that the current user needs more accurate.
[0059] It is understandable that users may have doubts or misunderstandings during the process of history learning and history examinations, and therefore there will be a need to further understand and consolidate relevant content. Therefore, based on historical learning information and historical examination information, the keywords of the questions currently needed by users are predicted, so that the predicted target keywords can match user needs.
[0060] 103. Input the target keyword into a preset question generation model to receive multiple candidate questions output by the question generation model.
[0061] In the embodiment of the present application, a question generation module is pre-set, and the question generation model can output multiple corresponding questions based on the input keywords. Therefore, the target keyword can be input into the question generation model to receive multiple candidate questions output by the question generation model.
[0062] 104. Output multiple candidate questions to determine the target question from the multiple candidate questions.
[0063] In an embodiment of the present application, multiple questions to be selected are output to the terminal where the current user is located, so that the current user selects one question from the multiple questions to be selected based on actual needs and uses it as the target question.
[0064] 105. Input the target question into the AI tool of the architectural design industry to complete the question.
[0065] In an embodiment of the present application, an AI tool for the architectural design industry can be, for example, an AI tool for interior design, which integrates a large amount of knowledge points related to interior design. By inputting a target question into the AI tool for the architectural design industry, the AI tool can provide a corresponding answer based on the input target question. Therefore, the user only needs to select the target question from multiple options to complete the question of the AI tool, without having to manually enter each character of the question.
[0066] It can be seen that in the above embodiments of the present application, the keywords of the questions required by the current user are predicted through the current user's historical learning information and historical examination information, so that the questions required by the current user are completed for asking questions to the AI tool, avoiding the user manually entering each character in the question and improving the efficiency of asking questions to the AI tool.
[0067] In some embodiments of the present application, Figure 2 As shown, in Figure 1 Based on the embodiment shown, the question generation model can be generated by the following steps:
[0068] 201. Obtain a model training data set of a neural network model, where the model training data set includes multiple preset keywords and multiple preset questions corresponding to each preset keyword.
[0069] In an embodiment of the present application, the model training dataset of the neural network model can be set based on content such as interior design. That is, the preset keywords and preset questions in the model training dataset can be generated based on content such as interior design. The preset keywords serve as samples for model training, and the multiple preset questions corresponding to the preset keywords serve as labels for the samples.
[0070] 202. Use the model training data set to train the neural network model to obtain a problem generation model.
[0071] In the embodiments of the present application, a neural network model is trained using a model training dataset to generate a question generation model that outputs multiple questions based on the input keywords. This question generation model can be integrated into the platform where the AI tool resides, allowing users to use it when they need to ask questions of the AI tool.
[0072] In some embodiments of the present application, a detailed description of the current user's historical learning information and historical examination information is provided, specifically including at least one of the following:
[0073] The historical learning information includes the first knowledge point learned by the current user in the historical period;
[0074] The historical examination information includes the second knowledge point in the examination of the current user in the historical period and the third knowledge point in the second knowledge point to which the current user answered incorrectly.
[0075] It can be understood that the first knowledge point, the second knowledge point, and the third knowledge point can all be knowledge points in the interior design content, such as wall stone dry hanging construction technology, wall wood veneer construction technology, door and window decoration engineering construction, etc.
[0076] In some embodiments of the present application, Figure 3 As shown, in Figures 1 to 2 Based on any of the embodiments shown, the keywords of the questions currently required by the user are predicted based on historical learning information and historical examination information to obtain target keywords, which may include:
[0077] 301. Determine a first keyword in a plurality of first knowledge points, a second keyword in a plurality of second knowledge points, and a third keyword in a plurality of third knowledge points.
[0078] In the embodiments of the present application, the first, second, and third knowledge points all include corresponding keywords. For example, the keywords may include at least one of interior design styles and interior design elements. Interior design styles may include, for example, modern, cream, Nordic, and log styles. Interior design elements may include, for example, ceilings, doors and windows, tables and chairs, wall decorations, and floor decorations.
[0079] 302. Determine a target keyword based on the first keyword, the second keyword, and the third keyword.
[0080] In an embodiment of the present application, since at least one of the first keyword, the second keyword, and the third keyword matches the user demand, at least one target keyword can be screened out from the first keyword, the second keyword, and the third keyword.
[0081] In some embodiments of the present application, the screening of target keywords can be determined based on the number of times the keywords appear. Specifically, based on the first keyword, the second keyword, and the third keyword, determining the target keyword can include: deduplicating multiple first keywords, multiple second keywords, and multiple third keywords to obtain multiple fourth keywords; for each fourth keyword, determining the number of times the fourth keyword appears in the multiple first keywords, multiple second keywords, and multiple third keywords respectively; based on the number of appearances, determining the target keyword from the multiple fourth keywords. It can be seen that based on the number of appearances, the target keyword that better matches the user's needs can be determined, thereby predicting the accuracy of the target question.
[0082] In some embodiments of the present application, since the current user may directly input information into the question input field of the AI tool, the fourth keyword may be filtered based on the information input into the question input field of the AI tool. Specifically, after obtaining multiple fourth keywords, it may also include: obtaining the semantic similarity and / or text similarity between each fourth keyword and the information input into the question input field of the AI tool; retaining the fourth keywords whose semantic similarity and / or text similarity is greater than the preset similarity threshold, and deleting the fourth keywords whose semantic similarity and / or text similarity is less than or equal to the similarity threshold, to obtain the updated multiple fourth keywords, and then based on the updated multiple fourth keywords, executing for each fourth keyword, determining the number of occurrences of the fourth keyword in the multiple first keywords, the multiple second keywords, and the multiple third keywords, and subsequent steps.
[0083] The semantic similarity and / or text similarity may be calculated based on a deep learning model of NPL (Natural Language Processing), which is not limited here.
[0084] In some embodiments of the present application, determining a target keyword from multiple fourth keywords based on the number of occurrences may include: determining multiple fifth keywords from multiple fourth keywords, wherein the number of occurrences of the fifth keyword in multiple first keywords, multiple second keywords, and multiple third keywords, respectively, has a non-zero value for at least two of the numbers of occurrences; and determining a target keyword from multiple fifth keywords based on the number of occurrences.
[0085] The non-zero values for at least two of the occurrence counts refer to the number of occurrences of the fifth keyword in multiple first keywords, the number of occurrences of the fifth keyword in multiple second keywords, and the number of occurrences of the fifth keyword in multiple third keywords. If the values for at least two of the occurrence counts are zero, it indicates that the user has a low demand for the corresponding fourth keyword, and therefore it can be omitted as the fifth keyword, thereby filtering the fourth keyword.
[0086] In some embodiments of the present application, determining a target keyword from multiple fifth keywords based on the number of occurrences may include: for each fifth keyword, performing a weighted summation of the number of occurrences of the fifth keyword in multiple first keywords, multiple second keywords, and multiple third keywords to obtain a comprehensive number of occurrences; and determining the target keyword from the multiple fifth keywords based on the comprehensive number of occurrences. It can be seen that the weighted summation can obtain a more accurate comprehensive number of occurrences, thereby making the determined target keyword more in line with user needs.
[0087] In some embodiments of the present application, Figure 4 As shown, in Figures 1 to 3 Based on any of the embodiments shown, the weight of the fifth keyword when performing weighted summation of the number of times the fifth keyword appears in the multiple first keywords, the multiple second keywords, and the multiple third keywords can be determined by the following method:
[0088] 401. Determine the first historical moment of the first knowledge point most recently learned in the historical learning information.
[0089] In an embodiment of the present application, since each first knowledge point in the historical learning information corresponds to a corresponding user learning moment, the user learning moment closest to the current time point can be determined among multiple user learning moments and used as the first historical moment of the first knowledge point most recently learned in the historical learning information.
[0090] 402. Determine a second historical moment of a second knowledge point of a most recent exam in the historical exam information.
[0091] In an embodiment of the present application, since each second knowledge point in the historical examination information corresponds to a corresponding user examination time, the user examination time closest to the current time point can be determined among the user examination times of multiple second knowledge points, and used as the second historical moment of the second knowledge point of the most recent examination in the historical examination information.
[0092] 403. Determine the third historical moment of the third knowledge point that was most recently answered incorrectly in the historical examination information.
[0093] In an embodiment of the present application, since each third knowledge point in the historical examination information corresponds to a corresponding user examination time, the user examination time closest to the current time point can be determined among the user examination times of multiple third knowledge points, and used as the third historical moment of the third knowledge point that was most recently answered incorrectly in the historical examination information.
[0094] 404. Based on the time sequence among the first historical moment, the second historical moment, and the third historical moment, different weights are set for the number of times the fifth keyword appears in the multiple first keywords, the multiple second keywords, and the multiple third keywords, respectively.
[0095] In an embodiment of the present application, in chronological order, the closer the fifth keyword is to the current time point, the greater the weight of its number of occurrences in multiple corresponding keywords. Taking the chronological order of the first historical moment, the second historical moment, and the third historical moment as an example, the weight of the number of occurrences of the fifth keyword in multiple first keywords, the weight of the number of occurrences of the fifth keyword in multiple second keywords, and the weight of the number of occurrences of the fifth keyword in multiple third keywords decrease in sequence. In this way, through weighted summation, a more accurate comprehensive number of occurrences can be obtained, thereby making the determined target keywords more in line with user needs.
[0096] In a second aspect, based on the questioning method of the AI tool in the above embodiment, embodiments of the present application provide an AI tool questioning device, which is configured to execute the steps in any of the embodiments of the above AI tool questioning method. Specifically, the AI tool questioning device may include:
[0097] The acquisition module is used to obtain the current user's historical learning information and historical examination information;
[0098] The prediction module is used to predict the keywords of the questions currently required by the user based on historical learning information and historical examination information to obtain the target keywords;
[0099] A question generation module is used to input the target keyword into a preset question generation model to receive multiple candidate questions output by the question generation model;
[0100] A problem determination module is used to output a plurality of candidate problems to determine a target problem from the plurality of candidate problems;
[0101] The questioning module is used to input target questions into the AI tool in the architectural design industry to complete the questioning.
[0102] In a third aspect, embodiments of the present application provide a computer device that integrates the questioning apparatus of any of the AI tools provided in the embodiments of the present application. The computer device includes a processor and a memory, wherein the memory stores a computer program configured to be executed by the processor to implement the questioning method of the AI tool described in any of the above embodiments, for example:
[0103] Obtain the current user's historical learning information and historical examination information; predict the keywords of the questions required by the current user based on the historical learning information and historical examination information to obtain target keywords; input the target keywords into a preset question generation model to receive multiple candidate questions output by the question generation model; output multiple candidate questions to determine the target question from the multiple candidate questions; input the target question into the AI tool of the architectural design industry to complete the questioning.
[0104] In a fourth aspect, an embodiment of the present application provides a computer device that integrates a questioning device of any AI tool provided in an embodiment of the present application. Figure 5 , which shows a schematic diagram of the structure of the computer device involved in the embodiment of the present application, specifically:
[0105] The computer device may include one or more processing core processors 501, one or more computer readable storage medium storage units 502, a power supply 503 and an input unit 504. Those skilled in the art will understand that Figure 5 The computer device structure shown in the figure does not constitute a limitation on the computer device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently.
[0106] Processor 501 is the control center of the computer device. It connects the various components of the computer device using various interfaces and circuits. By running or executing software programs and / or modules stored in storage unit 502 and accessing data stored in storage unit 502, it performs various functions of the computer device and processes data, thereby providing overall monitoring of the computer device. Optionally, processor 501 may include one or more processing cores. Preferably, processor 501 may integrate an application processor and a modem processor, with the application processor primarily processing the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 501.
[0107] The storage unit 502 can be used to store software programs and modules. The processor 501 executes various functional applications and data processing by running the software programs and modules stored in the storage unit 502. The storage unit 502 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as sound playback or image playback); the data storage area may store data generated based on the use of the computer device. Furthermore, the storage unit 502 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state memory device. Accordingly, the storage unit 502 may also include a memory controller to provide the processor 501 with access to the storage unit 502.
[0108] The computer device also includes a power supply 503 for supplying power to various components. Preferably, the power supply 503 can be logically connected to the processor 501 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 503 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.
[0109] The computer device may further include an input unit 504 , which may be configured to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.
[0110] Although not shown, the computer device may further include a display unit, etc., which will not be described in detail here. Specifically, in the embodiment of the present application, the processor 501 in the computer device will load the executable files corresponding to the processes of one or more application programs into the storage unit 502 according to the following instructions, and the processor 501 will run the application programs stored in the storage unit 502 to implement various functions, such as:
[0111] Obtain the current user's historical learning information and historical examination information; predict the keywords of the questions required by the current user based on the historical learning information and historical examination information to obtain target keywords; input the target keywords into a preset question generation model to receive multiple candidate questions output by the question generation model; output multiple candidate questions to determine the target question from the multiple candidate questions; input the target question into the AI tool of the architectural design industry to complete the questioning.
[0112] In a fifth aspect, embodiments of the present application provide a computer-readable storage medium, which may include: a read-only memory (ROM), a random access memory (RAM), a disk, or an optical disk. The computer-readable storage medium stores a computer program, which is configured to be executed by a processor to implement the questioning method of the AI tool as described in any of the above items, for example:
[0113] Obtain the current user's historical learning information and historical examination information; predict the keywords of the questions required by the current user based on the historical learning information and historical examination information to obtain target keywords; input the target keywords into a preset question generation model to receive multiple candidate questions output by the question generation model; output multiple candidate questions to determine the target question from the multiple candidate questions; input the target question into the AI tool of the architectural design industry to complete the questioning.
[0114] In a sixth aspect, embodiments of the present application provide a computer program product or computer program, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to execute the questioning method of the AI tool as described in any one of the above items, for example:
[0115] Obtain the current user's historical learning information and historical examination information; predict the keywords of the questions required by the current user based on the historical learning information and historical examination information to obtain target keywords; input the target keywords into a preset question generation model to receive multiple candidate questions output by the question generation model; output multiple candidate questions to determine the target question from the multiple candidate questions; input the target question into the AI tool of the architectural design industry to complete the questioning.
[0116] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of the present application. At the same time, for those skilled in the art, based on the ideas of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A questioning method of an AI tool, characterized in that: The questioning methods of the AI tool include: Obtain the current user's historical learning information and historical examination information; the historical learning information includes the current user's historical learning records of content in the architectural design industry; the historical examination information includes the current user's historical examination records of content in the architectural design industry; Predicting keywords for the target question required by the current user based on the historical learning information and the historical examination information to obtain target keywords; Inputting the target keyword into a preset question generation model to receive a plurality of candidate questions output by the question generation model; Outputting a plurality of the candidate questions to determine the target question from the plurality of the candidate questions; Input the target question into the AI tool of the architectural design industry to complete the questioning; The historical learning information includes a first knowledge point learned by the current user during a historical period, and the historical examination information includes a second knowledge point learned by the current user during an examination during the historical period, and a third knowledge point answered incorrectly by the current user in the second knowledge point. The method predicts the keywords of the target question required by the current user based on the historical learning information and the historical test information to obtain the target keywords, including: determining the first keywords in multiple first knowledge points, the second keywords in multiple second knowledge points, and the third keywords in multiple third knowledge points; deduplicating the multiple first keywords, the multiple second keywords, and the multiple third keywords to obtain multiple fourth keywords; obtaining the information entered in the question input column of the AI tool; obtaining the semantic similarity and / or text similarity between each fourth keyword and the information entered in the question input column of the AI tool; retaining the fourth keywords whose semantic similarity and / or text similarity is greater than a preset similarity threshold, deleting the fourth keywords whose semantic similarity and / or text similarity is less than or equal to the similarity threshold, and then determining the target keyword among the multiple fourth keywords.
2. The questioning method of the AI tool according to claim 1, wherein: The question generation model is generated by the following steps: Obtaining a model training data set of a neural network model, wherein the model training data set includes a plurality of preset keywords and a plurality of preset questions corresponding to each of the preset keywords; The neural network model is trained using the model training data set to obtain the problem generation model.
3. The questioning method of the AI tool according to claim 1, wherein: Determining the target keyword from the plurality of fourth keywords includes: For each fourth keyword, determining the number of occurrences of the fourth keyword in the plurality of first keywords, the plurality of second keywords, and the plurality of third keywords; Based on the number of occurrences, the target keyword is determined from a plurality of fourth keywords.
4. The questioning method of the AI tool according to claim 3, wherein: The step of determining the target keyword from a plurality of fourth keywords based on the number of occurrences includes: Determine a plurality of fifth keywords from the plurality of fourth keywords, wherein at least two of the occurrence counts of the fifth keywords in the plurality of first keywords, the plurality of second keywords, and the plurality of third keywords are non-zero; Based on the number of occurrences, the target keyword is determined from the plurality of fifth keywords.
5. The questioning method of the AI tool according to claim 4, wherein: The step of determining the target keyword from the plurality of fifth keywords based on the number of occurrences includes: For each of the fifth keywords, performing a weighted summation of the number of times the fifth keyword appears in the first keywords, the second keywords, and the third keywords to obtain a comprehensive number of occurrences; Based on the comprehensive number of occurrences, the target keyword is determined from the plurality of fifth keywords.
6. The questioning method of the AI tool according to claim 5, characterized in that: The weight of the fifth keyword when performing a weighted sum of the number of times it appears in the first keywords, the second keywords, and the third keywords is determined by: Determining a first historical moment of a first knowledge point most recently learned in the historical learning information; Determine a second historical moment of a second knowledge point of a most recent exam in the historical exam information; Determining a third historical moment of a third knowledge point in the historical test information where a third knowledge point was most recently answered incorrectly; Based on the chronological order between the first historical moment, the second historical moment, and the third historical moment, different weights are set for the number of times the fifth keyword appears in multiple first keywords, multiple second keywords, and multiple third keywords, respectively. Among them, in the chronological order, the closer the fifth keyword is to the historical moment of the current time point, the greater the weight of the number of times it appears in multiple corresponding keywords.
7. A computer device, characterized in that: The computer device includes a processor and a memory, wherein a computer program is stored in the memory, and the computer program is configured to be executed by the processor to implement the questioning method of the AI tool according to any one of claims 1 to 6.
8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is configured to be executed by a processor to implement the questioning method of the AI tool according to any one of claims 1 to 6.