MBTI intelligent questionnaire method and system based on MindSpore and personality analysis device

Abstract

The invention belongs to the technical field of artificial intelligence, and particularly relates to an MBTI intelligent questionnaire method and system based on MindSpore and a personality analysis device. According to the scheme, the personality type of a user is analyzed through an MBTI scale, and in order to collect answers of the user on all questions in the MBTI scale, historical behavior data of the user on the Internet are firstly captured, then related data of the user are analyzed through a language large model, and answers of part of the questions in the MBTI scale are determined. And then organizing topics according to the remaining questions in combination with the hobbies and interests of the user, performing continuous dialogues with the user by utilizing an AI dialogue tool, and knowing answers of the user on the remaining questions through the dialogues with the user. And finally, classifying personality types of the user according to the collected feature information corresponding to the answers of all the questions. The problems that an existing questionnaire survey mode is prone to being affected by the social sponsoring effect and the fatigue effect, and the evaluation result is inaccurate are solved.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence technology, and in particular relates to a MBTI intelligent questionnaire method, system and personality analysis device based on MindSpore. Background Art

[0002] MBTI (Myers-Briggs Type Indicator) is a personality assessment psychological scale used for psychometrics and is a self-report personality classification tool. Based on the psychological type theory of Swiss psychologist Carl Jung, it divides users into 16 different personality types according to four dimensions and two opposing states, including: extroversion (E) / introversion (I), the way individuals obtain energy; sensing (S) / intuition (N), the way information is received; thinking (T) / feeling (F), the description of the decision-making process; judgment (J) / perception (P), the attitude towards the outside world. Nowadays, MBTI is incorporated into employment guidance tools, job selection for professionals, talent recruitment for human resources, and personalized needs for product design. However, the popular versions on the market are only suitable for popular hobbies of the general public, and there are problems with the reliability and validity of its psychological dimensions.

[0003] In actual application, the traditional MBTI personality type assessment relies on traditional questionnaire surveys and subjects manually filling out questionnaires. It often encounters many practical problems such as the social desirability effect and fatigue effect, which leads to challenges in authenticity and continuity of the assessment. Among them, the social desirability effect refers to the tendency of people to show behaviors and attitudes that meet social expectations when they self-evaluate or accept surveys in order to gain social recognition and acceptance. This effect is both idiosyncratic and situational, and is mainly manifested as the phenomenon of "pretending to be good". When answering survey questions, people tend to deny their behaviors that are not accepted by society, and affirm their positive traits in order to meet social needs. The fatigue effect refers to the phenomenon that the emotions and motivation of the subjects are weakened due to the long experiment or too many experimental projects, which is manifested as the decline of the subjects' scores, resulting in deviations from the actual evaluation results. Summary of the invention

[0004] In order to solve the problem that the existing method of obtaining MBTI scale information through questionnaire survey to evaluate user personality is easily affected by social desirability effect and fatigue effect, and the evaluation result is inaccurate, the present invention provides an MBTI intelligent questionnaire method, system and personality analysis device based on MindSpore.

[0005] The technical solution provided by the present invention is:

[0006] An MBTI intelligent questionnaire method based on MindSpore comprises the following steps:

[0007] S1: The 93 questions in the MBTI standard question bank are divided into four dimensions according to Extraversion E and Introversion I, Sensing S and Intuition N, Thinking T and Feeling F, Judging J and Perceiving P.

[0008] S2: According to the decision-making tendency of the user, a variety of characteristic information is determined for evaluating the personality attributes of the user in four dimensions.

[0009] Among them, (1) the characteristics of evaluating extroversion and introversion include: social frequency, social breadth, and psychological resources required for social interaction. (2) The characteristics of evaluating perception and intuition include: information processing methods and attention placement. (3) The characteristics of evaluating thinking and emotion include: individual value orientation, individual decision-making basis, and problem-solving orientation. (4) The characteristics of evaluating judgment and perception include: life behavior style, attitude towards life events, and individual adaptability.

[0010] S3: Based on MindSpore, a corresponding weak classifier is designed for each question of MBTI. The weak classifier is used to identify the various features contained in the answers provided by users in the questions of the specified dimension, and classify the personality attributes of the corresponding dimension into corresponding categories according to the tendency of each feature.

[0011] S4: Obtain the user's authorization and use information extraction tools to capture the user's browsing history and interactive content on the specified social platform.

[0012] S5: Based on MindSpore's natural language processing function, the captured information is matched with the keywords in the question bank, and then the answers to several questions after successful matching are automatically generated based on the user's browsing history and interactive content on the designated social platform.

[0013] S6: Use the AI ​​dialogue tool designed based on MindSpore to organize the remaining unmatched questions into a continuous dialogue task according to the user's interests and hobbies, and interact with the user to collect answers to the remaining questions.

[0014] S7: Input the answers to each question automatically generated and interactively collected into the specified weak classifier, and perform weighted fusion on the outputs of each weak classifier to determine the type of the user in each dimension, and generate a personality type assessment report for the user based on the assessment results of the four dimensions.

[0015] As a further improvement of the present invention, in step S1, the standard question bank of MBTI has 21 questions related to the extraversion or introversion dimension, 26 questions related to the sensing or intuition dimension, 24 questions related to the thinking or feeling dimension, and 22 questions related to the judgment or perception dimension.

[0016] As a further improvement of the present invention, in step S2, the characteristics of social frequency refer to the frequency and duration of an individual's participation in social activities; the characteristics of social breadth refer to the groups of people an individual tends to socialize with and the number of people involved in social activities; and the characteristics of psychological resources required for social interaction refer to the psychological energy an individual uses in social activities.

[0017] As a further improvement of the present invention, in step S2, the characteristics of information processing means refer to whether an individual tends to adopt superficial senses to obtain information, or to perceive it at a deep subconscious level, and whether the individual processing is based on practical experience or theoretical concepts; the characteristics of attention placement refer to whether an individual tends to focus on current real problems, or on the overall situation and future possibilities.

[0018] As a further improvement of the present invention, in step S2, the characteristics of individual value orientation refer to whether the individual is more inclined to objective standards or subjective emotions; the characteristics of individual decision-making basis refer to whether the individual tends to make decisions based on logic or personal values ​​and emotions; the characteristics of problem-solving orientation refer to whether the individual tends to adopt systematic analysis and solutions or interpersonal relationships when solving problems.

[0019] As a further improvement of the present invention, in step S2, the characteristics of life behavior patterns are used to distinguish whether an individual tends to have a planned and organized lifestyle or a flexible and adaptable lifestyle; the characteristics of life event attitudes are used to evaluate whether an individual tends to plan in advance or to improvise when faced with event arrangements; and the characteristics of individual adaptability are intended to identify whether an individual tends to follow traditional paths or is more willing to explore new possibilities when faced with new situations.

[0020] As a further improvement of the present invention, in step S3, the corresponding question is split into multiple atomic questions according to the multiple features involved in each question, and then a classifier is designed for each atomic question.

[0021] As a further improvement of the present invention, in step S7, the option results under each weak classifier are classified, and the contribution of the factors of each problem under the four dimensions is obtained through factor analysis, which is converted into a weight ratio; in the two opposing states of a single dimension, the number of factors of the options is multiplied by the weight ratio, and the product with a larger result is used as the classification result of the current dimension.

[0022] The present invention also includes an MBTI intelligent questionnaire system based on MindSpore, which adopts the aforementioned MBTI intelligent questionnaire method based on MindSpore to analyze the personality type of the user. The MBTI intelligent questionnaire system includes: a database, a signal acquisition crawler, an intelligent dialogue module, a classification module and an evaluation module.

[0023] The database is used to classify and store the characteristic information corresponding to each question in the MBTI standard question bank.

[0024] The signal acquisition crawler is used to capture the user's browsing history and interactive content on the specified social platform after the user's authorization, and then match the captured information with the keywords of the question bank; finally, key information is extracted from the user's browsing history and interactive content on the specified social platform, and stored in the corresponding table in the database.

[0025] The intelligent dialogue module is designed based on a large language model and is used to obtain items in the database that the signal acquisition crawler has failed to complete. It calls the AI ​​dialogue tool to generate dialogue tasks with the user; then it automatically generates feature information for the corresponding questions based on the interactive content during the dialogue with the user.

[0026] The classification module contains multiple classifiers corresponding to each question in the MBTI standard question bank; each classifier outputs the classification result of the question based on the feature information of the corresponding question in the database.

[0027] The evaluation module is used to calculate the classification results of each dimension based on the classification results of each question under the four dimensions and the preset weights, and generate a personality analysis report for the corresponding user.

[0028] The present invention also includes a personality analysis device, which includes a memory, a processor, and a computer program stored in the memory and running in the processor. When the processor executes the computer program, the MBTI intelligent questionnaire method based on MindSpore as described above is used to analyze the user's personality type and generate a corresponding personality analysis report.

[0029] The technical solution provided by the present invention has the following beneficial effects:

[0030] The present invention uses the MBTI scale to analyze the user's personality type. In order to collect the user's answers to various questions in the MBTI scale, the present invention first captures the user's historical behavior data on the Internet, and then analyzes the user's relevant data through a large language model to determine the answers to some questions in the MBTI scale. Then, according to the remaining questions and the user's interests and hobbies, the topic is organized, and a continuous dialogue is conducted with the user using an AI dialogue tool. Through the dialogue with the user, the user's answers to the remaining questions are learned. Finally, the user's personality type is classified according to the feature information corresponding to the answers to all the questions collected.

[0031] The solution of the present invention changes the original information collection method based on questionnaire surveys, and instead uses artificial intelligence technology to automatically fill in answers to questions, and obtain information through easier AI dialogues. This method can overcome the shortcomings of existing solutions that are easily affected by social desirability and fatigue effects, obtain more accurate user information, and improve the reliability of evaluation results.

[0032] The present invention does not need to store the user's direct answer to each question during the user personality analysis, which can reduce the risk of privacy leakage of the user during the personality analysis process and has stronger data security performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a flowchart of the steps of the MBTI intelligent questionnaire method based on MindSpore provided in Example 1 of the present invention.

[0034] Figure 2 This is a system architecture diagram of the MBTI intelligent questionnaire system based on MindSpore provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0036] Example 1

[0037] According to the social desirability effect, users are motivated to choose favorable answers when answering questions in the MBTI scale; according to the fatigue effect, users will be affected by fatigue and emotions when answering many questions in the MBTI scale. Therefore, whether from a subjective or objective perspective, the characteristic information of the MBTI scale obtained by questionnaires about users may deviate from the actual situation of the users.

[0038] With the in-depth learning and increasing maturity of deep learning frameworks, more and more natural language processing tasks can be completed well. For example, the deep learning framework MindSpore meets the full coverage of cloud, edge and end scenarios, providing high-performance models and automatic parallel capabilities. At the same time, it supports the customization and adjustment of data enhancement operations during data processing, and assists in the coordinated training of large models through federated learning capabilities, realizing the "available but invisible" data and the protection of privacy information.

[0039] Based on MindSpore, this embodiment is based on the complete version of the MBTI scale (93 questions), and uses MindSpore to realize the task of collecting characteristic information corresponding to each question in the MBTI scale. The present invention does not adopt the traditional questionnaire survey method when collecting information, so it can effectively avoid the influence of social desirability effect and fatigue effect in psychological evaluation, improve the authenticity and timeliness of MBTI psychological evaluation, ensure the integrity of information collection, and improve the reliability of the final evaluation result.

[0040] Specifically, Figure 1 As shown, the MBTI intelligent questionnaire method based on MindSpore provided in this embodiment includes the following steps:

[0041] S1: The 93 questions in the MBTI standard question bank are divided into four dimensions according to Extraversion E and Introversion I, Sensing S and Intuition N, Thinking T and Feeling F, Judging J and Perceiving P.

[0042] In the standard question bank of MBTI, there are 21 questions related to the extraversion or introversion dimension, namely questions 3, 7, 10, 13, 16, 19, 23, 26, 32, 38, 42, 57, 62, 68, 74, 77, 79, 81, 83, 85, and 91.

[0043] There are 26 questions related to the sensing or intuition dimension; they are questions 2, 5, 9, 11, 18, 22, 25, 27, 30, 34, 39, 44, 46, 48, 50, 52, 54, 60, 63, 65, 67, 69, 71, 73, 82, and 92.

[0044] There are 24 questions related to the thinking or feeling dimension, namely, questions 6, 15, 21, 29, 31, 33, 35, 37, 40, 43, 45, 47, 49, 51, 53, 56, 58, 61, 66, 70, 72, 75, 87, and 89.

[0045] There are 22 questions related to the judgment or perception dimension, namely questions 1, 4, 8, 12, 14, 17, 20, 24, 28, 36, 41, 55, 59, 64, 76, 78, 80, 84, 86, 88, 90, and 93.

[0046] S2: According to the user's decision-making tendency, determine a variety of characteristic information used to evaluate the user's personality attributes in four dimensions. Among them,

[0047] (1) Characteristics of assessing extroversion and introversion include: frequency of social interaction, breadth of social interaction, and psychological resources required for social interaction.

[0048] In this embodiment, the characteristics of social frequency refer to the frequency and duration of an individual's participation in social activities. The characteristics of social breadth refer to the groups of people that an individual tends to socialize with and the number of people that he or she socializes with. The characteristics of psychological resources required for social interaction refer to the psychological energy that an individual uses in social activities.

[0049] (2) Characteristics of evaluating perception and intuition include: information processing methods and attention placement.

[0050] In this embodiment, the characteristics of information processing methods refer to whether individuals tend to use the surface form of five senses to obtain information, or perceive it at a deep subconscious level, and whether the individual's processing is based on actual experience or theoretical concepts. The characteristics of attention placement refer to whether individuals tend to focus on current real problems, or on the overall situation and future possibilities.

[0051] (3) Characteristics of evaluation thinking and emotion include: individual value orientation, individual decision-making basis, and problem-solving orientation.

[0052] In this embodiment, the characteristics of individual value orientation refer to whether the individual is more inclined to objective standards or subjective emotions; the characteristics of individual decision-making basis refer to whether the individual tends to make decisions based on logic or personal values ​​and emotions; the characteristics of problem-solving orientation refer to whether the individual tends to adopt systematic analysis and solutions or interpersonal relationships when solving problems.

[0053] (4) Characteristics of evaluation, judgment and perception include: life behavior patterns, attitudes towards life events, and individual adaptability.

[0054] In this embodiment, the characteristics of life behavior style are used to distinguish whether an individual tends to have a planned and organized lifestyle or a flexible and adaptable lifestyle; the characteristics of life event attitudes are used to assess whether an individual tends to plan in advance or improvise when faced with event arrangements; the characteristics of individual adaptability are intended to identify whether an individual tends to follow traditional paths or is more willing to explore new possibilities when faced with new situations.

[0055] S3: Based on MindSpore, a corresponding weak classifier is designed for each question of MBTI. The weak classifier is used to identify the various features contained in the answers provided by users in the questions of the specified dimension, and classify the personality attributes of the corresponding dimension into corresponding categories according to the tendency of each feature.

[0056] In this embodiment, the four-dimensional questions are split into multiple atomic questions according to their respective measurement methods through natural language processing technology (NLP), and a classifier is designed for each atomic question to improve the accuracy of psychological assessment. In this embodiment, different options under the weak classifier provide different perspectives, providing more choices for understanding and answering the original questions, thereby reducing ambiguity and more accurately capturing the specific behavior of individuals in social situations.

[0057] S4: Obtain the user's authorization and use information extraction tools to capture the user's browsing history and interactive content on the specified social platform.

[0058] S5: Based on MindSpore's natural language processing function, the captured information is matched with the keywords in the question bank, and then the answers to several questions after successful matching are automatically generated based on the user's browsing history and interactive content on the designated social platform.

[0059] In the solution of this embodiment, the user's direct answer to each question in the MBTI psychological scale is no longer obtained directly through a questionnaire survey, but the user's answer to different questions on each dimension is obtained indirectly through active analysis and dialogue communication. Specifically,

[0060] "Active analysis" refers to using the user's historical data on social networks to analyze the user's answers. The content and browsing data of users on social networks are usually generated autonomously based on the user's wishes, so the authenticity of these data is higher. From the perspective of personality analysis, these historical data are not affected by social approval and are closer to the user's true psychological state. In practical applications, the historical data posted by users on social networks can be captured with the user's authorization, and then key information can be extracted from it to determine the user's true answers to certain questions in the MBTI psychological scale.

[0061] S6: Use the AI ​​dialogue tool designed based on MindSpore to organize the remaining unmatched questions into a continuous dialogue task according to the user's interests and hobbies, and interact with the user to collect answers to the remaining questions.

[0062] In most cases, even if all the comments or browsing history of the user on the social network is obtained, it is not enough to determine the user's answers to all the questions in the MBTI psychological scale. Therefore, this embodiment will determine the user's interests and hobbies based on the social data of the user that has been obtained, and then organize the corresponding dialogue tasks for the purpose of obtaining the user's answers to the remaining questions in the MBTI psychological scale, and select topics based on the user's preferences, and then determine the user's answers to the remaining questions in the MBTI psychological scale during the dialogue with the user.

[0063] In this embodiment, the AI ​​dialogue tool used constructs a psychological topic map through the MindSpore framework. The tool uses the concepts and technologies of heterogeneous information networks to expand the questions in the questionnaire and extract relevant topics, thereby improving the accuracy and efficiency of automatic answers in the intelligent questionnaire evaluation process. Through communication interaction and instruction settings, the language model behind the AI ​​dialogue tool can learn vocabulary related to scale dimensions such as emotions, attitudes, and behaviors, providing a rich knowledge base for map construction. Furthermore, this process achieves an in-depth understanding of individual psychological characteristics and the intelligent extraction and analysis of psychological dimensions.

[0064] In the scheme of this embodiment, on the one hand, the "dialogue communication" based on artificial intelligence can not only obtain the user's answers to the selected questions like the questionnaire survey. On the other hand, since the user will not be aware that this process is for analyzing the user's personality type during the dialogue process, the influence of the social desirability effect can be eliminated. In addition, since the dialogue communication process in this embodiment is carried out in combination with the user's interests and hobbies, the dialogue process with the user usually does not cause user fatigue or resistance, so the answers obtained are more reliable than those directly conducting a questionnaire survey.

[0065] S7: Input the answers to each question automatically generated and interactively collected into the specified weak classifier, and perform weighted fusion on the outputs of each weak classifier to determine the type of the user in each dimension, and generate a personality type assessment report for the user based on the assessment results of the four dimensions.

[0066] Classify the option results under each weak classifier, and obtain the contribution of the factors of each question under the four dimensions through factor analysis, and convert it into weight proportion; in the two opposing states of a single dimension, multiply the number of factors of the option by the weight proportion, and take the larger product as the classification result of the current dimension. For example, under the dimension of E (extroversion)-I (introversion), assuming that the score of type E is 11.35 and the score of type I is 9.65, the user personality classification result under this dimension is E (extroversion). In this real case, assuming that the user has the same score on two opposite types, further analysis can be performed based on the large amount of feature information obtained to determine the most likely result. Integrate each weak classifier to obtain the individual's MBTI type, and give the refined tendency under each dimension.

[0067] Example 2

[0068] Based on the solution in Example 1, this embodiment further provides an MBTI intelligent questionnaire system based on MindSpore, which uses the MBTI intelligent questionnaire method based on MindSpore in Example 1 to analyze the personality type of the user. The core feature of the MBTI intelligent questionnaire system in this embodiment is that it can collect the user's answers to each question in the MBTI psychological scale with the help of artificial intelligence technology without directly conducting a questionnaire survey on the user, and then analyze the user's personality type. These new intelligent questionnaire methods help to overcome the problem that traditional methods are susceptible to the social desirability effect and fatigue effect, and the reliability of the user personality analysis results obtained is lower.

[0069] like Figure 2 As shown, the MBTI intelligent questionnaire system based on MindSpore provided in this embodiment includes: a database, a signal acquisition crawler, an intelligent dialogue module, a classification module and an evaluation module.

[0070] The database is used to classify and store the characteristic information corresponding to each question in the standard question bank of MBTI. Specifically, for the complete version of the MBTI scale, the database of this embodiment includes 93 storage partitions, and each storage partition stores all characteristic information of the current user for one of the questions.

[0071] The signal acquisition crawler is used to capture the user's browsing history and interactive content on the specified social platform after the user's authorization, and then match the captured information with the keywords of the question bank; finally, key information is extracted from the user's browsing history and interactive content on the specified social platform, and stored in the corresponding table in the database.

[0072] In this embodiment, the signal acquisition crawler includes an information extraction unit and an information analysis unit. Among them, the information extraction unit can be implemented by calling various existing data capture tools. The information analysis unit is obtained by training a large language model. In practical applications, a large amount of feature information related to psychological analysis is collected in advance, and then these data are used to form a knowledge graph, and the attention network is trained using the knowledge graph to obtain a large model that can understand semantic information. This embodiment uses the trained large model to calculate the similarity between user network behavior information and topic graphs, which can realize the transformation of psychological dimensions to intelligent semantic extraction and realize intelligent filling of questionnaires.

[0073] The intelligent dialogue module is used to call the AI ​​dialogue tool to generate dialogue tasks with users for items in the database that the signal acquisition crawler has failed to fill; then, it automatically generates feature information for the corresponding questions based on the interactive content during the dialogue with the user.

[0074] In this embodiment, the role of the intelligent dialogue module is to actively "ask" the remaining questions that have not been completed after the signal acquisition crawler completes the intelligent filling of the questionnaire according to the user's network behavior. Different from the questionnaire method, the process of asking the user's answer in this embodiment is achieved by continuous dialogue with the user with the help of artificial intelligence. For each "hard" question in the MBTI scale, the method of this embodiment can integrate each question into the specific affairs that the user is interested in, and through discussion and communication with the user, cleverly capture the user's answer to each question and extract the characteristic information provided by the user when answering the question.

[0075] The classification module contains multiple classifiers corresponding to each question in the MBTI standard question bank; each classifier outputs the classification result of the question based on the feature information of the corresponding question in the database. Each classifier can calculate the similarity between the feature information provided by the user and the keywords of different types of personality classification results based on the similarity algorithm according to the preset keywords in the scale, and generate the classification result of the corresponding question.

[0076] The evaluation module is used to calculate the classification results of the current user in each dimension based on the classification results of each question under the four dimensions and the preset weights, and generate a personality analysis report for the corresponding user.

[0077] Example 3

[0078] Based on Embodiments 1 and 2, this embodiment further provides a personality analysis device, which includes a memory, a processor, and a computer program stored in the memory and running in the processor. When the processor executes the computer program, the aforementioned MBTI intelligent questionnaire method based on MindSpore is used to analyze the user's personality type and generate a corresponding personality analysis report.

[0079] The personality analysis device provided in this embodiment is essentially a computer device for implementing the solution in Embodiment 1. The computer device can be an intelligent terminal capable of executing a program, a tablet computer, a laptop computer, a desktop computer, a rack server, a blade server, a tower server or a cabinet server (including an independent server or a server cluster composed of multiple servers), etc.

[0080] The computer device indicated in this embodiment includes at least but is not limited to: a memory and a processor that can be connected to each other through a system bus. Among them, the memory (i.e., a readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory can be an internal storage unit of a computer device, such as a hard disk or a memory of the computer device. In other embodiments, the memory can also be an external storage device of a computer device, such as a plug-in hard disk equipped on the computer device, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. Of course, the memory can also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the memory is generally used to store an operating system and various application software installed on the computer device. In addition, the memory can also be used to temporarily store various types of data that have been output or are to be output.

[0081] The processor may be a central processing unit (CPU), a graphics processing unit (GPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor is generally used to control the overall operation of a computer device. In this embodiment, the processor is used to run program codes stored in a memory or process data.

[0082] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A MBTI intelligent questionnaire method based on MindSpore, characterized in that: It includes the following steps: S1: The 93 questions in the MBTI standard question bank are divided into four dimensions according to Extraversion E and Introversion I, Sensing S and Intuition N, Thinking T and Feeling F, Judging J and Perceiving P; S2: According to the user's decision-making tendency, determine a variety of characteristic information used to evaluate the user's personality attributes in four dimensions; among them, (1) The characteristics of assessing extroversion and introversion include: frequency of social interaction, breadth of social interaction, and psychological resources required for social interaction; (2) The characteristics of assessing perception and intuition include: information processing methods and attention placement; (3) Characteristics of assessment thinking and emotion include: individual value orientation, individual decision-making basis, and problem-solving orientation; (4) Characteristics of evaluation judgment and perception include: life behavior style, attitude towards life events, and individual adaptability; S3: Based on MindSpore, a corresponding weak classifier is designed for each question of MBTI. The weak classifier is used to identify the various features contained in the answers provided by users in the questions of the specified dimension, and classify the personality attributes of the corresponding dimension into corresponding categories according to the tendency of each feature; S4: Obtain the user's authorization and use information extraction tools to capture the user's browsing history and interactive content on the specified social platform; S5: Based on the natural language processing function of MindSpore, the captured information is matched with the keywords in the question bank, and then the answers to several questions after successful matching are automatically generated based on the user's browsing history and interactive content on the designated social platform; S6: Use the AI ​​dialogue tool designed based on MindSpore to organize the remaining unmatched questions into a continuous dialogue task according to the user's interests and hobbies, and interact with the user to collect answers to the remaining questions; S7: Input the answers to each question automatically generated and interactively collected into the specified weak classifier, and perform weighted fusion on the outputs of each weak classifier to determine the type of the user in each dimension, and generate a personality type assessment report for the user based on the assessment results of the four dimensions.

2. The MBTI intelligent questionnaire method based on MindSpore as claimed in claim 1, characterized in that: In step S1, the MBTI standard question bank has 21 questions related to the extraversion or introversion dimension, 26 questions related to the sensing or intuition dimension, 24 questions related to the thinking or feeling dimension, and 22 questions related to the judging or perceiving dimension.

3. The MBTI intelligent questionnaire method based on MindSpore as claimed in claim 1, characterized in that: In step S2, the characteristics of social frequency refer to the frequency and duration of an individual's participation in social activities; the characteristics of social breadth refer to the groups of people an individual tends to socialize with and the number of people he or she socializes with; and the characteristics of psychological resources required for social interaction refer to the psychological energy an individual uses in social activities.

4. The MBTI intelligent questionnaire method based on MindSpore as claimed in claim 3, characterized in that: In step S2, the characteristics of information processing methods refer to whether individuals tend to use the surface form of five senses to obtain information, or perceive it at a deep subconscious level, and whether individual processing is based on practical experience or theoretical concepts; the characteristics of attention placement refer to whether individuals tend to focus on current real problems, or on the overall situation and future possibilities.

5. The MBTI intelligent questionnaire method based on MindSpore as claimed in claim 4, characterized in that: In step S2, the characteristics of individual value orientation refer to whether the individual is more inclined to objective standards or subjective emotions; the characteristics of individual decision-making basis refer to whether the individual tends to make decisions based on logic or personal values ​​and emotions; the characteristics of problem-solving orientation refer to whether the individual tends to adopt systematic analysis and solutions or interpersonal relationships when solving problems.

6. The MBTI intelligent questionnaire method based on MindSpore as claimed in claim 5, characterized in that: In step S2, the characteristics of the life behavior style are used to distinguish whether the individual tends to have a planned and organized lifestyle or a flexible and adaptable lifestyle; the characteristics of the attitude towards life events are used to evaluate whether the individual tends to plan in advance or to improvise when faced with event arrangements; the characteristics of individual adaptability are intended to identify whether the individual tends to follow the traditional path or is more willing to explore new possibilities when faced with new situations.

7. The MBTI intelligent questionnaire method based on MindSpore according to claim 6, characterized in that: In step S3, the corresponding problem is split into multiple atomic problems according to the multiple features involved in each problem, and then a classifier is designed for each atomic problem.

8. The MBTI intelligent questionnaire method based on MindSpore according to claim 6, characterized in that: In step S7, the option results under each weak classifier are classified, and the contribution of the factors of each problem under the four dimensions is obtained through factor analysis, which is converted into a weight ratio; in the two opposing states of a single dimension, the number of factors of the option is multiplied by the weight ratio, and the larger product is used as the classification result of the current dimension.

9. An MBTI intelligent questionnaire system based on MindSpore, characterized by: The method adopts the MBTI intelligent questionnaire method based on MindSpore as claimed in any one of claims 1 to 8 to analyze the personality type of the user; the method comprises: A database, which is used to classify and store the characteristic information corresponding to each question in the MBTI standard question bank; A signal acquisition crawler, which is used to crawl the user's browsing history and interactive content on the designated M social platform after the user's authorization, and then match the crawled information with the keywords of the question bank, and finally extract key information from the user's browsing history and interactive content on the designated social platform, and store it in the corresponding table in the database; An intelligent dialogue module, which is designed based on a large language model and is used to obtain items in the database that the crawler has failed to fill, call the AI ​​dialogue tool to generate a dialogue task with the user; and then automatically generate feature information of the corresponding question based on the interactive content during the dialogue with the user; The classification module includes multiple classifiers corresponding to each question in the MBTI standard question bank; each classifier outputs the classification result of the question according to the characteristic information of the corresponding question in the database; The evaluation module is used to calculate the classification results of each dimension according to the classification results of each question under the four dimensions and their preset weights, and generate a personality analysis report for the corresponding user.

10. A personality analysis device, comprising a memory, a processor, and a computer program stored in the memory and running in the processor, characterized in that: When the processor executes the computer program, the MBTI intelligent questionnaire method based on MindSpore as described in any one of claims 1 to 8 is used to analyze the personality type of the user and generate a corresponding personality analysis report.

Images