Online high-precision psychological assessment method and system based on big data

Abstract

The embodiment of the invention provides an online high-precision psychological assessment method and system based on big data, and relates to the technical field of psychological assessment. The online high-precision psychological assessment method based on big data comprises the following steps: acquiring user information, and generating a type label according to the user information; matching historical evaluation data and evaluation questions of corresponding types according to the type labels, and generating an initial question sequence; the user performs online question answering according to the initial question sequence, and characteristic data in the question answering process of the user is collected; obtaining the current psychological state of the user based on the feature data, updating the initial question sequence according to the psychological state of the user, and generating a dynamic question sequence; and generating a psychological assessment report of the user according to the answer result of the user. The problems of high manpower consumption, low preliminary screening efficiency, inaccurate evaluation result and the like in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the field of psychological assessment technology, and specifically to an online high-precision psychological assessment method and system based on big data. Background Art

[0002] In the recruitment process of modern enterprises, assessing the psychological quality of candidates has become an important part of ensuring the selection of suitable talents. Psychological assessment can fully understand the personality characteristics, stress tolerance, teamwork ability and other aspects of candidates, which helps enterprises to screen out candidates who meet the job requirements during the recruitment stage and improve the effectiveness and stability of human resource allocation. Through scientific psychological assessment, enterprises can not only reduce employee turnover, but also improve overall work efficiency and organizational cohesion, thereby gaining an advantage in the fierce market competition.

[0003] At present, companies mainly rely on two methods when conducting psychological assessments: one is through manual interviews, and the other is to use fixed test questions for assessment. Manual interviews often require a lot of human resources, and the subjective judgment of the interviewer may affect the fairness and consistency of the assessment, making it difficult to achieve large-scale preliminary screening. On the other hand, although the use of fixed test questions for psychological assessments has improved the standardization of assessments to a certain extent, since the content of the questions is fixed, applicants can cope with the test through prior preparation or simulation exercises, which leads to doubts about the accuracy and effectiveness of the test results. Summary of the invention

[0004] According to an embodiment of the present invention, an online high-precision psychological assessment method and system based on big data are provided to solve the problems raised by the above background technology.

[0005] In a first aspect of the present invention, an online high-precision psychological assessment method based on big data is provided.

[0006] The online high-precision psychological assessment method based on big data includes the following steps: S1. Obtain user information and generate a type tag based on the user information; S2. Obtain cloud data, wherein the cloud data includes historical evaluation data and evaluation topics; the historical evaluation data and the evaluation topics are divided into at least two categories according to type; S3. Matching the historical evaluation data and evaluation questions of the corresponding type according to the type label, and generating an initial question sequence; S4. The user answers questions online according to the initial question sequence, and collects characteristic data during the user's answering process; S5. Acquire the user's current psychological state based on the characteristic data, and update the initial question sequence according to the user's psychological state to generate a dynamic question sequence; S6. Generate a user psychological assessment report based on the user's answer results.

[0007] Preferably, the step S1 comprises: S1-1. Obtain user information, including name, age, gender, occupation and educational background; S1-2. Feature encoding is performed on the user information, wherein categorical variables (such as gender, occupation, and educational background) are processed by one-hot encoding, and continuous variables (such as age) are standardized; S1-3. Weight the user information after feature encoding and calculate the type matching score; the type matching score formula is: in, For type T i The matching score, F j is the jth encoded user feature, W j is the corresponding weight coefficient, n is the total number of features, T i is the i-th type label; S1-4. By comparing the matching scores of each type, select the type T with the highest score k As a type label for the user, that is: Among them, L is the user type label finally determined, and argmax is the i value that maximizes the expression.

[0008] Preferably, the historical evaluation data includes past user evaluation records, covering user type labels, answer content, and emotional response data.

[0009] Preferably, step S3 comprises: S3-1. According to the type label, filter out all evaluation records that match the type label in the historical evaluation data stored in the cloud, and extract the corresponding evaluation questions; S3-2. Classify the selected assessment questions according to different psychological dimensions, and each psychological dimension corresponds to an independent question group; S3-3. Select a number of questions from the question group of each psychological dimension in proportion to ensure that each psychological dimension is represented in the initial question sequence to fully cover the user's psychological state; S3-4. Arrange the selected questions in the order of importance of each psychological dimension to form a logically coherent and well-structured initial question sequence.

[0010] Preferably, the step S4 further comprises: S4-1. Classify the feature data; S4-2. Establish associations between features of different categories, match and combine associated feature data through preset association rules, and form a composite feature set to reveal the comprehensive behavior patterns of users in the process of answering questions; S4-3. According to psychological dimensions (such as attention, emotional stability, and cognitive load), the associated composite feature sets are hierarchically integrated. Each psychological dimension corresponds to a specific feature subset, and the features at each level are integrated and summarized to generate a comprehensive feature representation of each psychological dimension. S4-4. Process the comprehensive feature representation of each psychological dimension in time series according to the order of answering questions, and construct the feature evolution trajectory of the user in the process of answering questions; S4-5. Based on the feature evolution trajectory, the preset psychological state mapping rules are applied to transform the time-series comprehensive feature representation into specific psychological state indicators, including but not limited to indicators such as attention level, emotional stability, and cognitive load, so as to comprehensively reflect the changes in the user's psychological state during the answering process.

[0011] Preferably, step S5 comprises: S5-1. Based on the comprehensive feature representation of the psychological dimension generated in step S4, calculate the user's current psychological state score P t , where t represents the current answering stage; Where m is the total number of psychological dimensions, w i is the weight coefficient of the i-th psychological dimension, and , F i is the characteristic summary value of the i-th psychological dimension, C i is the characteristic interaction index of the i-th psychological dimension, D i is the standardized factor of the ith psychological dimension, is the nonlinear adjustment factor of the ith psychological dimension; S5-2. According to the user's current psychological state score, the user's current psychological state is classified into the first state, the second state and the third state; when the psychological state score is greater than or equal to the first threshold, the user's psychological state is the first state, when the psychological state score is greater than or equal to the second threshold and less than the first threshold, the user's psychological state is the second state, when the psychological state score is less than the second threshold, the user's psychological state is the third state; S5-3. Based on the user's current mental state, select questions that match the current mental state label from the cloud data, extract the mental dimension labels of the questions, select questions that are consistent with or highly relevant to the mental state labels and add them to the dynamic question sequence, and verify whether the selected questions cover all mental dimensions. If the number of questions for a certain mental dimension is insufficient, mark it as a potential missing dimension; S5-4. When the number of matching questions is insufficient or the questions of a certain psychological dimension are not fully covered, the new question generation process is triggered, and a new question is generated by calling the question template corresponding to the missing psychological dimension; when generating, the label of the current psychological state and the user's historical answer record are combined to ensure that the content of the new question is highly relevant to the psychological state and is not repeated; the generated new question is added to the dynamic question sequence; S5-5. Merge the matched questions and the generated new questions, and adjust the question order to ensure the progressiveness and logical coherence of the psychological dimension. Verify whether the length of the sequence and the coverage of the psychological dimension meet the assessment requirements, and finally generate a dynamic question sequence.

[0012] Preferably, the adjustment of the question order is performed by giving priority to the questions of the psychological dimension corresponding to the current psychological state, and inserting the questions of the low-correlated psychological dimension between the previous and next highly-correlated questions to maximize the change of psychological load; after each question is inserted, the difference of the psychological dimension with the previous question is detected to ensure that the alternation of the psychological dimension between every two adjacent questions is minimized, and the questions of the psychological dimension that have not been touched in the user's answer record are inserted at the end of the sequence to obtain a dynamic question sequence. Gradually complete the dimension coverage; at the end of the sorting, adjust the position of the high psychological load questions and disperse them to discontinuous nodes in the dynamic sequence to avoid excessive concentration of psychological load and improve the consistency and adaptability of the assessment.

[0013] In a second aspect of the present invention, an online high-precision psychological assessment system based on big data is provided.

[0014] The system is used to implement the above-mentioned online high-precision psychological assessment method, including: The user side is configured as: Obtaining user information and transmitting the user information to a server; Receive the initial question sequence generated by the server and present it to the user; Collecting characteristic data of the user during the question-answering process, and evaluating the user's psychological state based on the characteristic data; transmitting the user's mental state to a server; The server side is configured as: Store historical assessment data and assessment questions; Generate an initial question sequence based on the user information, and transmit the initial question sequence to the user terminal; A dynamic question sequence is generated based on the user's psychological state, and the dynamic question sequence is transmitted to the user terminal.

[0015] Preferably, the user terminal includes: A display screen, used to display assessment questions; A camera, used to capture facial features of a user, obtain feature data, and connect to the first data processing unit via an internal data bus; The information input module is used to receive information input by the user and transmit it to the server through the first network communication module; A first network communication module, used for data communication with the server, wherein the first network communication module is connected to the server via a network; The first data processing unit is configured to generate a user's psychological state according to characteristic data in the process of the user answering questions, and transmit the user's psychological state to the server through the first network communication module.

[0016] The server side includes: A database, used to store historical assessment data and assessment questions, and connected to the second data processing unit via an internal data bus; A second network communication module, used for data communication with the user terminal, wherein the second network communication module is connected to the user terminal via a network; The second data processing unit comprises: An initial question sequence generation module is configured to screen evaluation questions in a database based on the user information and generate an initial question sequence; The dynamic question sequence generation module is configured to generate a dynamic question sequence based on the user's psychological state.

[0017] Preferably, the dynamic question sequence generation module includes: A matching submodule, for selecting, according to the current psychological state of the user, questions that match the psychological state label from the database, and adding the selected questions to the dynamic question sequence; The coverage verification submodule is used to verify whether the selected questions cover all psychological dimensions. If it is found that the number of questions for a certain psychological dimension is insufficient, the psychological dimension is marked as a potential missing dimension; A new topic generation submodule is used to call a topic template corresponding to the missing psychological dimension to generate a new topic when the number of matching topics is insufficient or the topics of a certain psychological dimension are not fully covered, and to add the new topic to the dynamic topic sequence; The sorting submodule is used to sort the questions in the dynamic question sequence to ensure the progressiveness and logical coherence of the psychological dimension, and to verify whether the length of the sequence and the psychological dimension coverage meet the assessment requirements, and finally generate the dynamic question sequence.

[0018] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present invention provides an online high-precision psychological evaluation method based on big data, which realizes the rapid preliminary screening of large-scale applicants through automated user information acquisition and type label generation, and significantly reduces the resource investment of enterprises in human interviews. Secondly, the classified historical evaluation data and dynamic question generation mechanism stored in the cloud are used to ensure the personalization and flexibility of the evaluation process, and the question sequence can be dynamically adjusted according to the real-time feature data of the applicant in the process of answering questions, avoiding the problem that fixed questions are easy to be dealt with and lead to inaccurate evaluation results. In addition, the multi-dimensional feature data of users is deeply analyzed by big data analysis and machine learning algorithms, which greatly enhances the accuracy and reliability of the evaluation results and ensures the scientificity and practicality of the psychological evaluation report. The interactivity and personalized experience of the online evaluation platform not only enhance the applicant's sense of participation and evaluation experience, but also provide enterprises with intuitive and objective recruitment decision-making basis through visual evaluation reports. In summary, the present invention solves the problems of large manpower consumption, low efficiency of preliminary screening and inaccurate evaluation results in the prior art through an efficient, accurate and dynamic psychological evaluation method, and provides strong technical support for the optimization of enterprise recruitment process and scientific human resource management. .

[0019] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein: Figure 1 A flowchart of an online high-precision psychological assessment method based on big data according to an embodiment of the present invention is shown; Figure 2 A flowchart showing step S1 of the online high-precision psychological assessment method based on big data according to an embodiment of the present invention is shown; Figure 3 A flowchart showing step S3 of the method for online high-precision psychological assessment based on big data according to an embodiment of the present invention is shown; Figure 4 A flowchart of step S4 of the online high-precision psychological assessment method based on big data according to an embodiment of the present invention is shown; Figure 5 A flowchart of step S5 of the online high-precision psychological assessment method based on big data according to an embodiment of the present invention is shown; Figure 6A block diagram of an online high-precision psychological assessment system based on big data according to an embodiment of the present invention is shown; Figure 7 A structural schematic diagram of a user end of an online high-precision psychological assessment system based on big data according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0023] like Figure 1 As shown, in the first aspect of the present invention, an online high-precision psychological assessment method based on big data is provided.

[0024] The online high-precision psychological assessment method based on big data includes the following steps: S1. Obtain user information and generate type labels based on the user information; first obtain user information, use the user information as input data, analyze and process the user information. Generate corresponding type labels for subsequent matching of appropriate assessment data and assessment questions. The generation of type labels can adopt classification algorithms, such as decision trees, support vector machines (SVMs) or neural networks, to ensure the accuracy and effectiveness of the labels, thereby providing a personalized basis for psychological assessment.

[0025] S2. Obtain cloud data, which includes historical evaluation data and evaluation questions; the historical evaluation data and the evaluation questions are divided into at least two categories according to type; the historical evaluation data includes the evaluation results, answer records and related feature data of previous users, and these data are classified and stored according to different type labels. For example, the data can be divided into multiple categories according to the user's occupation type, industry background or psychological characteristics. Evaluation questions are also classified by type to ensure that each type of question can effectively evaluate the psychological state of a specific type of user. The storage and management of cloud data adopts a distributed database system to ensure high availability and scalability of data.

[0026] S3. Match the historical evaluation data and evaluation questions of the corresponding type according to the type label, and generate an initial question sequence; after obtaining the user's type label, the system will match the historical evaluation data and evaluation questions of the corresponding type from the cloud data according to these labels. The matching process involves screening data and questions that are highly relevant to the user's type label to ensure the pertinence and effectiveness of the evaluation. By sorting and combining the matched evaluation questions, the system generates an initial question sequence that is designed to comprehensively cover all aspects of the user's psychological characteristics. The generation of the initial question sequence can be combined with factors such as question difficulty, question type diversity, and evaluation objectives to optimize the evaluation process and user experience.

[0027] S4. The user answers questions online according to the initial question sequence, and characteristic data of the user's answering process is collected, where the characteristic data includes but is not limited to: Answering time: records the time it takes the user to answer each question, reflecting the user's thinking speed and decision-making efficiency.

[0028] Answer accuracy: Count the user's correct answer rate and evaluate their knowledge mastery and comprehension ability.

[0029] Facial expression changes: The camera monitors the user's emotional fluctuations during the answering process, such as tension, relaxation, etc.

[0030] Behavioral characteristics: record the user's mouse click frequency, keyboard input speed, etc., reflecting the user's concentration and operating habits.

[0031] S5. Based on the characteristic data, the user's current psychological state is obtained, and according to the user's psychological state, the initial question sequence is updated to generate a dynamic question sequence; in the process of the user answering questions, based on the characteristic data of the user answering questions, big data analysis technology and machine learning algorithms, such as cluster analysis, regression analysis or deep learning models, are used to evaluate the user's current psychological state. Based on the real-time evaluation results, the selection and order of subsequent questions will be adjusted immediately to generate a dynamic question sequence. This dynamic adjustment mechanism enables the evaluation process to push personalized questions according to the user's real-time performance and psychological state, thereby deeply exploring the user's psychological characteristics. The generation of a dynamic question sequence not only takes into account the relevance and difficulty of the questions, but also optimizes the evaluation path according to the user's immediate feedback, ensuring the comprehensiveness and depth of the evaluation, and improving the accuracy and credibility of the evaluation results.

[0032] S6. Generate a user psychological assessment report based on the user's answer results. After completing all the assessment questions, the system will comprehensively analyze the user's answer results and characteristic data to generate a detailed psychological assessment report. The report includes the user's scores in various psychological dimensions, personality characteristics analysis, stress tolerance assessment, teamwork ability analysis, etc. The assessment report uses a combination of visual charts and text descriptions to intuitively display the user's psychological state and potential strengths and weaknesses. The report can also provide personalized suggestions and improvement measures to help users better understand their own psychological characteristics and provide companies with a scientific basis for recruitment decisions. The entire assessment report generation process relies on big data analysis and intelligent algorithms to ensure the objectivity, accuracy and practicality of the report content.

[0033] The online high-precision psychological assessment method based on big data provided by the present invention significantly improves the efficiency and accuracy of the recruitment process. First, through the automated acquisition of user information and generation of type labels, a rapid preliminary screening of large-scale applicants is achieved, significantly reducing the resource investment of enterprises in human interviews. Secondly, the classified historical assessment data and dynamic question generation mechanism stored in the cloud are used to ensure the personalization and flexibility of the assessment process, and the question sequence can be dynamically adjusted according to the real-time feature data of the applicant during the answering process, avoiding the problem that fixed questions are easily dealt with and lead to inaccurate assessment results. In addition, the multi-dimensional feature data of users is deeply analyzed by big data analysis and machine learning algorithms, which greatly enhances the accuracy and reliability of the assessment results and ensures the scientificity and practicality of the psychological assessment report. The interactivity and personalized experience of the online assessment platform not only enhance the applicant's sense of participation and assessment experience, but also provide enterprises with intuitive and objective recruitment decision-making basis through visual assessment reports. In summary, the present invention solves the problems of high manpower consumption, low efficiency of preliminary screening and inaccurate evaluation results in the prior art through an efficient, accurate and dynamic psychological assessment method, and provides strong technical support for the optimization of corporate recruitment processes and the scientific management of human resources.

[0034] like Figure 2 As shown, in this embodiment, step S1 includes: S1-1. Obtain user information, including name, age, gender, occupation and educational background; S1-2. Feature encoding is performed on the user information, where categorical variables (such as gender, occupation, and educational background) are processed by One-Hot Encoding, and continuous variables (such as age) are standardized; further, in order to facilitate subsequent algorithm processing and analysis, the collected user information needs to be feature encoded. The specific processing method is as follows: Categorical variable encoding: For categorical variables (such as gender, occupation, and educational background), the **One-Hot Encoding** method is used. One-Hot Encoding converts each categorical variable into multiple binary variables, each corresponding to one category. For example, the gender variables "male" and "female" will be encoded as 1,0 and 0,1 respectively.

[0035] Continuous variable standardization: For continuous variables (such as age), standardization is used. Standardization converts continuous variables into a standard normal distribution with a mean of 0 and a standard deviation of 1 to eliminate the influence of different variable dimensions and improve the training effect of the model. The standardization formula is as follows: Among them, X is the original age data, is the mean of age data, is the standard deviation of the age data.

[0036] Through feature coding, the original user information is converted into a numerical feature vector, which is convenient for subsequent algorithm processing and analysis.

[0037] S1-3. Weight the user information after feature encoding and calculate the type matching score; the type matching score formula is: in, For type T i The matching score, F j is the jth encoded user feature, W j is the corresponding weight coefficient, n is the total number of features, T i is the i-th type label; The contribution of each feature to the type of matching is combined by weighted summation to obtain the matching score of each type. The weight coefficient is assigned according to the degree of influence of each feature on the psychological state. S1-4. After obtaining the matching scores of all types, the system needs to determine the type label that best matches the user's characteristics. Compare the user's matching scores on each type and select the type Ti with the highest score as the user's type label, that is: Among them, L is the user type label finally determined, and argmax is the i value that maximizes the expression.

[0038] In this embodiment, the historical evaluation data includes past user evaluation records, including user type labels, answer content, and emotional response data.

[0039] like Figure 3 As shown, in this embodiment, step S3 includes: S3-1. According to the type tag, all evaluation records matching the type tag are screened out from the historical evaluation data stored in the cloud, and the corresponding evaluation questions are extracted; using the user's type tag, all evaluation records matching the type tag are screened out from the historical evaluation data. The historical evaluation data includes the evaluation records of past users, and each record covers the user's type tag, answer content and emotional response data. The type tag is used to identify the psychological type to which the user belongs, the answer content records the user's answer to each evaluation question, and the emotional response data reflects the user's emotional changes during the evaluation process. The system searches for historical evaluation records corresponding to the type of expression based on the current user's type tag, which can be implemented through database query statements, such as SELECT statements in SQL, to screen out all records that meet the type tag matching conditions. From the screened matching evaluation records, the corresponding evaluation questions are extracted. Since different records may contain different questions, it is necessary to ensure that the extracted questions cover diversity for subsequent classification and selection. The extraction process also includes removing duplicate questions and retaining a unique set of questions to optimize the diversity and coverage of the question library.

[0040] S3-2. Classify the selected evaluation questions according to different psychological dimensions, and each psychological dimension corresponds to an independent question group; further, multiple psychological dimensions need to be defined in advance, and each dimension corresponds to a specific psychological trait or behavior pattern. For example, common psychological dimensions include emotional stability, extroversion, responsibility, openness, and agreeableness. According to the content and evaluation objectives of each evaluation question, it is assigned to the corresponding psychological dimension group. This process can be achieved through methods such as keyword matching, topic analysis, or expert annotation to ensure that each question is correctly classified into the corresponding psychological dimension. Each psychological dimension corresponds to an independent question group, ensuring that when selecting questions later, the questions of each dimension can independently and comprehensively evaluate the user's psychological characteristics.

[0041] S3-3. Select a number of questions from the question group of each psychological dimension in proportion to ensure that each psychological dimension is represented in the initial question sequence to fully cover the user's psychological state; further, according to the importance and evaluation needs of different psychological dimensions, pre-set the proportion of each dimension in the initial question sequence. For example, some dimensions may require more questions to obtain a more detailed evaluation. In the question group of each psychological dimension, select a number of questions randomly according to the set proportion. Random selection helps to increase the diversity of the evaluation and avoid the influence of the order of questions on the evaluation results. By selecting in proportion, it is ensured that each psychological dimension has representative questions in the initial question sequence, thereby fully covering the various psychological dimensions of the user and improving the comprehensiveness and accuracy of the evaluation.

[0042] S3-4. Arrange the selected questions in the order of importance of each psychological dimension to form a logically coherent and well-structured initial question sequence. Set the order of importance of each psychological dimension according to the assessment objectives and application scenarios. For example, in some job recruitments, responsibility and teamwork ability may be more important than openness. Arrange the selected questions in the order of importance of each psychological dimension. Prioritize questions corresponding to dimensions with higher importance to ensure that key psychological traits are fully assessed. In the process of question sorting, consider the logical relationship of the questions and the coherence of the assessment process, avoid abrupt jumps or repetitions between questions, and improve the user's answering experience. Ensure that the initial question sequence is reasonably distributed in structure, avoid too much concentration or dispersion of questions in the same psychological dimension, and maintain the balance and systematicness of the assessment process.

[0043] like Figure 4 As shown, in this embodiment, step S4 further includes: S4-1. Classify the characteristic data; the characteristic data includes but is not limited to answering time and emotional data. To reflect the user's behavior and psychological reaction during the answering process.

[0044] S4-2. Establish associations between features of different categories, match and combine associated feature data through preset association rules to form a composite feature set to reveal the comprehensive behavior pattern of users in the process of answering questions; Generate a composite feature set by establishing associations between features of different categories to reveal the comprehensive behavior pattern of users in the process of answering questions. Emotional fluctuations may be related to an increase in cognitive load (such as longer answering time). According to preset association rules, match and combine associated feature data. For example: If a user shows emotional fluctuations in multiple consecutive questions, these emotion-related features will be combined into a composite feature "emotional instability". Generate multiple composite feature sets by matching and combining association rules. These composite feature sets can more comprehensively reflect the comprehensive behavior pattern of users in the process of answering questions, surpassing the analysis of a single feature, and provide richer information for subsequent psychological state assessment.

[0045] S4-3. The associated composite feature sets are hierarchically integrated according to psychological dimensions (such as attention, emotional stability, and cognitive load). Each psychological dimension corresponds to a specific feature subset, and the features at each level are integrated and summarized to generate a comprehensive feature representation of each psychological dimension.

[0046] Going a step further, multiple psychological dimensions are predefined, each corresponding to a specific psychological trait or behavior pattern. For example: Attention: reflects the user's concentration in the process of answering questions.

[0047] Emotional stability: reflects the user's emotional fluctuations during the answering process.

[0048] Cognitive load: reflects the user's mental burden and processing ability during the answering process.

[0049] According to the definition of each psychological dimension, the associated composite feature set is divided into corresponding feature subsets. For example: Attention feature subset: including the stability of answering time, consistency of page dwell time, etc.

[0050] Emotional stability feature subset: includes the frequency and amplitude of emotional fluctuations in emotional response data.

[0051] Cognitive load feature subset: including changes in answering speed, extended thinking time, etc.

[0052] For each feature subset of psychological dimension, an integration method is used to summarize and integrate the features, and a comprehensive feature representation of each psychological dimension is generated.

[0053] S4-4. The comprehensive feature representation of each psychological dimension is processed into a time series according to the order of answering questions, and the feature evolution trajectory of the user in the process of answering questions is constructed.

[0054] Furthermore, the comprehensive feature representation of the user on each question is regarded as data at a time point, and arranged in the order in which the user answers the questions to form a time series. For each psychological dimension, the system connects its comprehensive feature representation in the order of answering the questions to form a continuous time series. For example: Represents the comprehensive characteristics of the user's attention on the 1st to nth questions.

[0055] Represents the comprehensive characteristics of the user's emotional stability on questions 1 to n.

[0056] Represents the comprehensive characteristics of the user's cognitive load on questions 1 to n.

[0057] The comprehensive feature representations of each question are arranged in order using a sliding window or accumulation method to ensure the continuity and integrity of the feature evolution trajectory. The constructed feature evolution trajectory is stored as multidimensional time series data to facilitate subsequent analysis and mapping. For example, the trajectory data of attention, emotional stability, and cognitive load can be stored as three independent time series, or they can be integrated into one multidimensional time series.

[0058] S4-5. Based on the feature evolution trajectory, the preset psychological state mapping rules are applied to transform the time-series comprehensive feature representation into specific psychological state indicators, including but not limited to indicators such as attention level, emotional stability, and cognitive load, so as to comprehensively reflect the changes in the user's psychological state during the answering process.

[0059] Furthermore, a set of mental state mapping rules is preset to convert the comprehensive feature representation into a specific mental state indication. These rules can be formulated based on psychological theory, expert experience or data-driven methods. For example: Attention level mapping: If the comprehensive attention feature is continuously higher than a certain threshold at multiple time points, it is mapped as "high attention". If the comprehensive attention feature is lower than a certain threshold at multiple time points, it is mapped as "low attention".

[0060] Emotional stability mapping: If the emotional stability comprehensive feature fluctuates slightly during the entire test-taking process, it is mapped as "emotionally stable". If the emotional stability comprehensive feature fluctuates greatly, it is mapped as "emotionally unstable".

[0061] Cognitive load mapping: If the comprehensive characteristics of cognitive load are above a certain threshold at most time points, it is mapped as "high cognitive load". If the comprehensive characteristics of cognitive load are below a certain threshold at most time points, it is mapped as "low cognitive load". According to the preset psychological state mapping rules, the characteristic evolution trajectory of each psychological dimension is analyzed and mapped. Based on the mapping results, specific psychological state indications are generated, including but not limited to the following: Attention level: such as "high attention", "medium attention", "low attention".

[0062] Emotional stability: such as "emotional stability" and "mood fluctuations".

[0063] Cognitive load: such as "high cognitive load", "medium cognitive load", "low cognitive load".

[0064] The psychological state indicators of each psychological dimension are combined to form a picture of the overall psychological state changes of the user during the answering process. For example, the user may show different psychological state combinations such as "high attention, emotional stability, low cognitive load" or "low attention, emotional fluctuations, high cognitive load".

[0065] By classifying, associating, integrating, and time-series processing the multi-dimensional feature data collected during the user's online answering process, and applying the psychological state mapping rules based on the feature evolution trajectory, specific psychological state indications are generated. This process not only deeply reveals the user's comprehensive behavior patterns and psychological state changes during the answering process, but also provides rich and accurate data support for the subsequent dynamic question generation and the generation of the final psychological assessment report. Through scientific feature processing and psychological state mapping mechanisms, the efficiency, accuracy, and practicality of the psychological assessment method are ensured.

[0066] like Figure 5 As shown, in this embodiment, step S4 has generated comprehensive feature representations of various psychological dimensions (such as attention, emotional stability, cognitive load, etc.). These comprehensive feature representations can fully reflect the performance and changes of the user in various psychological dimensions. The step S5 includes: S5-1. Based on the comprehensive feature representation of the psychological dimension generated in step S4, calculate the user's current psychological state score P t , where t represents the current answering stage; Where m is the total number of psychological dimensions, w i is the weight coefficient of the i-th psychological dimension, and , F i is the characteristic summary value of the i-th psychological dimension, C i is the characteristic interaction index of the i-th psychological dimension, D i is the standardized factor of the ith psychological dimension, is the nonlinear adjustment factor of the ith psychological dimension; through the above formula, the psychological state score calculation ensures the dynamics and accuracy of the psychological assessment, and provides a scientific basis for the dynamic adjustment of the subsequent question sequence S5-2. According to the user's current psychological state score, the user's current psychological state is classified into the first state, the second state and the third state; when the psychological state score is greater than or equal to the first threshold, the user's psychological state is the first state, when the psychological state score is greater than or equal to the second threshold and less than the first threshold, the user's psychological state is the second state, and when the psychological state score is less than the second threshold, the user's psychological state is the third state.

[0067] The psychological state scores of the users are compared to determine the score interval of the psychological state scores, and the psychological state of the user is marked as the first state, the second state or the third state according to the score interval.

[0068] S5-3. Based on the user's current mental state, filter out questions that match the current mental state label from the cloud data, extract the psychological dimension label of the question, select questions that are consistent with or highly relevant to the psychological state label and add them to the dynamic question sequence, and verify whether the selected questions cover all psychological dimensions. If the number of questions for a certain psychological dimension is insufficient, mark it as a potential missing dimension.

[0069] Furthermore, based on the user's current psychological state classification results (first state, second state or third state), the evaluation questions that match the state label are screened out from the cloud data. Each evaluation question is pre-labeled with the corresponding psychological dimension label, and these labels are extracted to ensure that the question is highly relevant to the user's psychological state. Select questions that are consistent with or highly relevant to the current psychological state label to ensure the pertinence and effectiveness of the evaluation. In the process of selecting questions, it is necessary to verify whether the selected questions cover all psychological dimensions. If the number of questions for a certain psychological dimension is insufficient, the system will mark it as a potential missing dimension and prepare to supplement it in subsequent steps.

[0070] S5-4. When the number of matching questions is insufficient or the questions of a certain psychological dimension are not fully covered, the new question generation process is triggered, and new questions are generated by calling the question template corresponding to the missing psychological dimension; when generating, the label of the current psychological state and the user's historical answer record are combined to ensure that the content of the new question is highly relevant to the psychological state and is not repeated; the generated new question is added to the dynamic question sequence.

[0071] Furthermore, when the number of matching questions is insufficient or the questions of a certain psychological dimension are not fully covered, a new question generation process is initiated to supplement the dynamic question sequence. According to the potential missing dimensions marked in step S5-3, the psychological dimensions that need to be supplemented are determined, and the question template corresponding to the missing psychological dimension is called. A new question is generated through a preset question generation algorithm, and the generated new question is added to the dynamic question sequence to ensure that the number and coverage of questions of all psychological dimensions meet the preset standards. At the same time, the generated new questions will be added to the cloud data to achieve the update of the cloud data.

[0072] S5-5. Merge the matched questions and the generated new questions, and adjust the question order to ensure the progressiveness and logical coherence of the psychological dimension. Verify whether the length of the sequence and the coverage of the psychological dimension meet the assessment requirements, and finally generate a dynamic question sequence.

[0073] Merge the selected matching questions with the generated new questions, and adjust the order of the questions to ensure the progressiveness of the psychological dimensions and the logical coherence of the assessment process. Merge the matching questions selected in step S5-3 with the new questions generated in step S5-4 to form a complete set of questions. Set the progressive order of the questions according to the importance of each psychological dimension and the needs of the assessment process. For example, first evaluate basic psychological traits, and then deeply evaluate complex psychological states. Ensure the logical coherence between the questions in terms of content and assessment objectives, avoid abrupt jumps in the order of questions, and improve the user's answering experience.

[0074] Verify whether the total length of the dynamic question sequence meets the assessment requirements to avoid too many questions causing user fatigue or too few questions affecting the assessment accuracy. Check whether the question sequence covers all preset psychological dimensions to ensure the comprehensiveness of the assessment. Through the above sorting and verification process, the system finally generates a dynamic question sequence that meets the assessment requirements, ensuring the scientific nature of the assessment process and the optimization of user experience.

[0075] Based on the user's real-time psychological state score during the test, the initial question sequence is dynamically updated to generate an adaptive dynamic question sequence. This process not only achieves the personalization and precision of the assessment, but also improves the comprehensiveness of the assessment and the user's test experience by ensuring diversity and coverage. The introduction of the dynamic adjustment mechanism ensures the real-time and flexibility of the assessment process, and provides richer and more accurate data support for the generation of the final psychological assessment report.

[0076] For example, before the assessment begins, basic information needs to be filled in, including name "Wang", age "28 years old", gender "female", occupation "data analyst", and educational background "Master". This information is collected and transmitted to the assessment system through the platform's user information acquisition module.

[0077] User information is feature encoded. Gender "female" is converted to 0, 1 through one-hot encoding. Occupation "data analyst" has multiple possible categories. It is assumed that there are five occupation types, which are encoded as 0, 0, 1, 0, 0. Education background "master" is assumed to have three educational levels, which are encoded as 0, 1, 0.

[0078] The age of 28 years old is standardized. Assuming that the mean μ of the age data is 30 years old and the standard deviation σ is 5 years old, the standardized age data is: Through the above encoding, Wang's original user information is converted into a numerical feature vector: [0,1,0,0,1,0,−0.4], where each dimension corresponds to the unique hot encoding of gender, occupation and educational background and the standardized age. According to the preset weight distribution mechanism, each encoded user feature is assigned a corresponding weight coefficient. Assume that the weight coefficients are as follows: The gender-related feature weight W1 is 0.2; The occupation-related characteristic weight W2 is 0.3; The weight of educational background-related features W3 is 0.3; The age feature weight W4 is 0.2; For each type T i , calculate its matching score S i ; Assume that the system presets three types of labels: Type A, Type B, and Type C, each type corresponds to different feature weights and matching criteria The calculation is as follows: By weighted summation, the matching scores of each type are obtained: type A is 0.22, type B is 0.42, and type C is 0.22; The system compares the matching scores of all types and selects the type with the highest score as the user's type label. For Wang, type B has the highest matching score of 0.42, so the final user type label type L = type B.

[0079] The historical assessment data and assessment questions are obtained from the cloud database. These data are divided into at least two categories according to type, ensuring that the assessment data and questions related to type B are selected first.

[0080] According to type label B, the system selects assessment records matching type B from historical assessment data, extracts corresponding assessment questions, and classifies them according to different psychological dimensions (such as logical thinking, stress management, and innovation ability). The system selects a number of questions from the question group of each psychological dimension in proportion to ensure that each dimension is representative in the initial question sequence, and finally generates a logically coherent initial question sequence.

[0081] When answering questions online, the system displays the initial questions on the display screen 11, and uses the camera 12 to capture Wang's facial features in real time, collecting feature data such as facial expression changes. The information input module 13 receives Wang's answer input, and transmits the user information and feature data to the server 2 through the network communication module 14.

[0082] Based on the collected characteristic data, the psychological state score of Wang at the current stage of answering questions is calculated, assuming that there are three psychological dimensions: attention (weight coefficient 0.3), emotional stability (weight coefficient 0.4), and cognitive load (weight coefficient 0.3).

[0083] Wang’s feature summary values ​​in each dimension: Attention F1 = 0.8; Emotional stability F2=0.6; Cognitive load F3=0.7; Feature interaction index C i and the normalization factor D i They are: C1=0.2,D1=1.1 C2= 0.1,D2= 0.9 C3=0.3,D3;= 1.0; The final calculated psychological state score is 1.3. The first threshold is proposed to be 1.5, and the second threshold is 1.0, so the current psychological state is the second state.

[0084] Select questions that match the second state from the cloud database, extract the psychological dimension labels of these questions (such as stress management, logical thinking, etc.), and check whether all psychological dimensions are covered. It is found that the number of questions in the "innovation ability" dimension is insufficient, and it is marked as a potential missing dimension. Then call the question template corresponding to "innovation ability", generate new related questions, and add them to the dynamic question sequence to ensure that all psychological dimensions are covered by enough questions.

[0085] Prioritize the "stress management" questions corresponding to the current psychological state "second state", and insert the low-correlation "logical thinking" questions between the "stress management" questions to maximize the change in psychological load. After each question is inserted, the system detects the difference in psychological dimensions from the previous question to ensure that the psychological dimensions of adjacent questions are alternating at a minimum. The untouched "innovation ability" questions are inserted at the end of the sequence to gradually complete the dimension coverage. At the end of the sorting, the system disperses high psychological load questions (such as "stress management" questions) to discontinuous nodes in the sequence to avoid excessive concentration of psychological load and improve the coherence and adaptability of the assessment. Finally, a dynamic question sequence with logical coherence and reasonable psychological load distribution is generated and transmitted back to the user terminal 1. After completing all the assessment questions, Wang's answer results and real-time psychological state scores are comprehensively analyzed to generate a detailed psychological assessment report.

[0086] In this embodiment, the adjustment of the question order is to prioritize the questions corresponding to the psychological dimension of the current psychological state, and insert the questions of low-correlated psychological dimensions between the previous and next highly correlated questions to maximize the change of psychological load; after each question is inserted, the difference in psychological dimension with the previous question is detected to ensure that the alternation of psychological dimensions between every two adjacent questions is minimized, and the questions of psychological dimensions that have not been touched in the user's answer record are inserted at the end of the sequence to obtain a dynamic question sequence. Gradually complete the dimension coverage; at the end of the sorting, adjust the position of the high psychological load questions and disperse them to discontinuous nodes in the dynamic sequence to avoid excessive concentration of psychological load and improve the consistency and adaptability of the assessment.

[0087] like Figure 6 As shown, in the second aspect of the present invention, an online high-precision psychological assessment system based on big data is provided.

[0088] The system is used to implement the above-mentioned online high-precision psychological assessment method, including: Client 1 is configured as: Obtain user information and transmit the user information to the server 2; receiving an initial question sequence generated by the server 2 and presenting it to the user; Collecting characteristic data of the user during the question-answering process, and evaluating the user's psychological state based on the characteristic data; Transmitting the user's psychological state to the server 2; Server 2 is configured as: Store historical assessment data and assessment questions; Generate an initial question sequence based on the user information, and transmit the initial question sequence to the user terminal 1; A dynamic question sequence is generated based on the user's psychological state, and the dynamic question sequence is transmitted to the user terminal 1.

[0089] In actual use, the user terminal 1 is responsible for collecting the user's basic information and transmitting it to the server terminal 2 through a secure transmission protocol; the server terminal 2 generates an initial question sequence based on the received user information, and dynamically generates an adjusted question sequence based on the user's real-time psychological state score during the answering process to ensure the personalization and accuracy of the assessment. The server terminal 2 transmits the initial question sequence to the user terminal 1, and the user terminal 1 receives and displays the initial and dynamic question sequences to guide the user to complete the online answering. In actual use, the user terminal 1 displays the questions through a graphical user interface and collects the user's answering behavior data, such as answering time, answering order, and interactive behavior, and transmits these feature data to the server terminal 2 in real time; the server terminal 2 evaluates the user's psychological state based on the received feature data, adjusts the question sequence and feeds it back to the user terminal 1, realizing dynamic optimization and continuous personalized adjustment of the assessment process, and ensuring the efficiency and scientificity of the entire psychological assessment process.

[0090] like Figure 7 As shown, in this implementation, the user terminal 1 includes: Display screen 11, used to display assessment questions; The camera 12 is used to capture the user's facial features, obtain feature data, and is connected to the first data processing unit 15 via an internal data bus; The information input module 13 is used to receive information input by the user and transmit it to the server 2 through the first network communication module 14; A first network communication module 14, used for data communication with the server 2, wherein the first network communication module 14 is connected to the server 2 via a network; The first data processing unit 15 is configured to generate a user psychological state according to characteristic data during the user's answering process, and transmit the user psychological state to the server end 2 through the first network communication module 14.

[0091] The server side 2 includes: The database 21 is used to store historical assessment data and assessment questions, and is connected to the second data processing unit 23 via an internal data bus; A second network communication module 22, used for data communication with the client 1, wherein the second network communication module 22 is connected to the client 1 via a network; The second data processing unit 23 includes: The initial question sequence generating module 151 is configured to screen the evaluation questions in the database 21 based on the user information and generate an initial question sequence; The dynamic question sequence generating module 152 is configured to generate a dynamic question sequence based on the user's psychological state.

[0092] In actual use, the user terminal 1 displays the assessment questions through the display screen 11, the camera 12 collects the user's facial feature data in real time, the information input module 13 receives the user's answer input, and the first data processing unit 15 evaluates the user's psychological state based on the collected feature data and transmits it to the server terminal 2; the server terminal 2 uses the historical assessment data and assessment questions in the database 21 to generate an initial question sequence through the initial question sequence generation module 151, and transmits it to the user terminal 1. During the user's answering process, the dynamic question sequence generation module 152 adjusts the subsequent assessment question sequence in real time according to the received user psychological state score to ensure the personalization and accuracy of the assessment, thereby realizing an efficient and scientific psychological assessment process.

[0093] In this embodiment, the dynamic question sequence generation module 152 includes a matching submodule, which is used to screen questions that match the psychological state label from the database 21 according to the current psychological state of the user, and add the selected questions to the dynamic question sequence; a coverage verification submodule, which is used to verify whether the selected questions cover all psychological dimensions. If it is found that the number of questions in a certain psychological dimension is insufficient, the psychological dimension is marked as a potential missing dimension; a new question generation submodule, which is used to call the question template corresponding to the missing psychological dimension to generate new questions when the number of matching questions is insufficient or the questions in a certain psychological dimension are not fully covered, and add the new questions to the dynamic question sequence; a sorting submodule, which is used to sort the questions in the dynamic question sequence to ensure the progressiveness and logical coherence of the psychological dimensions, and verify whether the length of the sequence and the psychological dimension coverage meet the evaluation requirements, and finally generate the dynamic question sequence. In actual use, the user terminal 1 displays the evaluation questions through the display screen 11, the camera 12 collects the user's facial feature data in real time, the information input module 13 receives the user's answer input, and transmits the user information and feature data to the server terminal 2 securely through the first network communication module 14; the server terminal 2 uses the historical evaluation data and evaluation questions in the database 21 to generate an initial question sequence through the initial question sequence generation module 151, and transmits it to the user terminal 1. During the user's answering process, the first data processing unit 15 evaluates the user's psychological state score based on the collected feature data, and transmits the score to the server terminal 2 through the first network communication module 14. Based on the psychological state score, the server terminal 2 screens, verifies, generates and sorts questions through each submodule in the dynamic question sequence generation module 152, dynamically adjusts the subsequent evaluation question sequence, ensures the personalization and accuracy of the evaluation, and transmits the adjusted dynamic question sequence back to the user terminal 1. The user terminal 1 receives and displays the initial and dynamic question sequences, guides the user to complete the online answering, and the entire evaluation process realizes the efficient collaboration between the user terminal and the server terminal, ensuring the scientificity, real-time nature and optimization of the user experience of the psychological evaluation.

[0094] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An online high-precision psychological assessment method based on big data, characterized in that: The following steps are involved: S1. Obtain user information and generate a type tag based on the user information; S2. Obtain cloud data, wherein the cloud data includes historical evaluation data and evaluation topics; the historical evaluation data and the evaluation topics are divided into at least two categories according to type; S3. Matching the historical evaluation data and evaluation questions of the corresponding type according to the type label, and generating an initial question sequence; S4. The user answers questions online according to the initial question sequence, and collects characteristic data during the user's answering process; S5. Acquire the user's current psychological state based on the characteristic data, and update the initial question sequence according to the user's psychological state to generate a dynamic question sequence; S6. Generate a user psychological assessment report based on the user's answer results.

2. The online high-precision psychological assessment method based on big data according to claim 1 is characterized in that: The step S1 comprises: S1-1. Obtain user information, including name, age, gender, occupation and educational background; S1-2 feature encoding of the user information; S1-3. Weight the user information after feature encoding and calculate the type matching score; the type matching score formula is: in, For type T i The matching score, F j is the jth encoded user feature, W j is the corresponding weight coefficient, n is the total number of features, T i is the i-th type label; S1-4. By comparing the matching scores of each type, select the type T with the highest score k As a type label for the user, that is: Among them, L is the user type label finally determined, and argmax is the i value that maximizes the expression.

3. The online high-precision psychological assessment method based on big data according to claim 1 is characterized in that: The historical evaluation data includes past user evaluation records, including user type labels, answer content, and emotional response data.

4. The online high-precision psychological assessment method based on big data according to claim 1 is characterized in that: The step S3 comprises: S3-1. According to the type label, filter out all evaluation records that match the type label in the historical evaluation data stored in the cloud, and extract the corresponding evaluation questions; S3-2. Classify the selected assessment questions according to different psychological dimensions, and each psychological dimension corresponds to an independent question group; S3-3. Select a number of questions from the question group of each psychological dimension in proportion to ensure that each psychological dimension is represented in the initial question sequence to fully cover the user's psychological state; S3-4. Arrange the selected questions in the order of importance of each psychological dimension to form a logically coherent and well-structured initial question sequence.

5. The online high-precision psychological assessment method based on big data according to claim 1 is characterized in that: The step S4 further comprises: S4-1. Classify the feature data; S4-2. Establish associations between features of different categories, match and combine associated feature data through preset association rules to form a composite feature set; S4-3. The associated composite feature set is hierarchically integrated according to the psychological dimension, each psychological dimension corresponds to a specific feature subset, and the features of each level are integrated and summarized to generate a comprehensive feature representation of each psychological dimension; S4-4. Process the comprehensive feature representation of each psychological dimension in time series according to the order of answering questions, and construct the feature evolution trajectory of the user in the process of answering questions; S4-5. Based on the feature evolution trajectory, the preset psychological state mapping rules are applied to transform the time-series comprehensive feature representation into a specific psychological state indication.

6. The online high-precision psychological assessment method based on big data according to claim 5 is characterized in that: The step S5 comprises: S5-1. Based on the comprehensive feature representation of the psychological dimension generated in step S4, calculate the user's current psychological state score P t , where t represents the current answering stage; Where m is the total number of psychological dimensions, w i is the weight coefficient of the i-th psychological dimension, and , F i is the characteristic summary value of the i-th psychological dimension, C i is the characteristic interaction index of the i-th psychological dimension, D i is the standardized factor of the ith psychological dimension, is the nonlinear adjustment factor of the ith psychological dimension; S5-2. According to the user's current psychological state score, the user's current psychological state is classified into the first state, the second state and the third state; when the psychological state score is greater than or equal to the first threshold, the user's psychological state is the first state, when the psychological state score is greater than or equal to the second threshold and less than the first threshold, the user's psychological state is the second state, when the psychological state score is less than the second threshold, the user's psychological state is the third state; S5-3. Based on the user's current mental state, select questions that match the current mental state label from the cloud data, extract the mental dimension labels of the questions, select questions that are consistent with or highly relevant to the mental state labels and add them to the dynamic question sequence, and verify whether the selected questions cover all mental dimensions. If the number of questions for a certain mental dimension is insufficient, mark it as a potential missing dimension; S5-4. When the number of matching questions is insufficient or the questions of a certain psychological dimension are not fully covered, a new question is generated by calling the question template corresponding to the missing psychological dimension; when generating, the label of the current psychological state and the user's historical answer record are combined; and the generated new question is added to the dynamic question sequence; S5-5. Merge the matched questions and the generated new questions, adjust the question order, and verify whether the sequence length and psychological dimension coverage meet the assessment requirements, and finally generate a dynamic question sequence.

7. The online high-precision psychological assessment method based on big data according to claim 6 is characterized in that: The described adjustment of the question order is achieved by giving priority to questions of the psychological dimension corresponding to the current psychological state, and inserting questions of the low-correlation psychological dimension between the previous and subsequent highly-correlation questions; after each question is inserted, the difference in the psychological dimension from the previous question is detected, and the questions of the psychological dimension that have not been touched upon in the user's answer record are inserted into the end of the sequence, thereby obtaining a dynamic question sequence.

8. An online high-precision psychological assessment system based on big data, characterized by: The system is used to implement the online high-precision psychological assessment method based on big data as described in any one of claims 1 to 7, comprising: The client (1) is configured as follows: Obtaining user information and transmitting the user information to a server (2); Receive the initial question sequence generated by the server (2) and present it to the user; Collecting characteristic data of the user during the question-answering process, and evaluating the user's psychological state based on the characteristic data; Transmitting the user's psychological state to a server (2); The server (2) is configured as follows: Store historical assessment data and assessment questions; Generating an initial question sequence based on the user information, and transmitting the initial question sequence to the user terminal (1); A dynamic question sequence is generated based on the user's psychological state, and the dynamic question sequence is transmitted to a user terminal (1).

9. The online high-precision psychological assessment system based on big data according to claim 8 is characterized in that: The user terminal (1) comprises: A display screen (11), used to display the assessment questions; A camera (12) is used to capture facial features of a user, obtain feature data, and is connected to a first data processing unit (15) via an internal data bus; An information input module (13) for receiving information input by a user and transmitting the information to the server (2) via a first network communication module (14); A first network communication module (14) is used to perform data communication with the server side (2), wherein the first network communication module (14) is connected to the server side (2) via a network; The first data processing unit (15) is configured to generate a user psychological state based on characteristic data during the user's answering process, and transmit the user psychological state to the server (2) via the first network communication module (14). The server side (2) comprises: A database (21) for storing historical assessment data and assessment questions, and connected to a second data processing unit (23) via an internal data bus; A second network communication module (22), used for performing data communication with the user terminal (1), wherein the second network communication module (22) is connected to the user terminal (1) via a network; The second data processing unit (23) comprises: An initial question sequence generating module (151) is configured to screen evaluation questions in a database (21) based on the user information and generate an initial question sequence; The dynamic question sequence generation module (152) is configured to generate a dynamic question sequence based on the user's psychological state.

10. The online high-precision psychological assessment system based on big data according to claim 9, characterized in that: The dynamic topic sequence generation module (152) comprises: A matching submodule, for selecting, according to the current psychological state of the user, questions that match the psychological state label from the database (21), and adding the selected questions to the dynamic question sequence; The coverage verification submodule is used to verify whether the selected questions cover all psychological dimensions. If it is found that the number of questions for a certain psychological dimension is insufficient, the psychological dimension is marked as a potential missing dimension; A new topic generation submodule is used to call a topic template corresponding to the missing psychological dimension to generate a new topic when the number of matching topics is insufficient or the topics of a certain psychological dimension are not fully covered, and to add the new topic to the dynamic topic sequence; The sorting submodule is used to sort the questions in the dynamic question sequence to ensure the progressiveness and logical coherence of the psychological dimension, and to verify whether the length of the sequence and the psychological dimension coverage meet the assessment requirements, and finally generate the dynamic question sequence.

Images