A mental health assessment system and method

Abstract

The present invention discloses a mental health assessment system and method, and the system includes: a generation module obtains multiple psychological assessment indicators, generates mental health description data according to the multiple psychological assessment indicators, and generates multiple mental health assessment questions based on the mental health description data; a construction module collects the reply content to the mental health assessment questions under different mental health states and constructs a mental health assessment network model according to the mental health assessment questions and the reply content and the assessment rules; an assessment module obtains the assessment answer of the target user to the mental health assessment question, and evaluates the assessment answer using the mental health assessment network model; a determination module determines the comprehensive mental health assessment result of the target user according to the assessment result and the performance mapping sequence of the target user. Accurate assessment is achieved by combining the performance sequence of the target user during the assessment, and the attitude tendency of the user when answering the question can be evaluated, and then the accuracy and objectivity of the user's assessment answer can be judged.

Description

Technical Field

[0001] The present invention relates to the technical field of mental health assessment, and in particular to a mental health assessment system and method. Background Art

[0002] In today's society, competition is fierce, and the overload of study and work has caused almost everyone to be in a sub-healthy state physically, and to often have negative emotions psychologically. Intermittent negative emotions are often ignored soon after they appear. Once negative emotions continue to accumulate, they are likely to cause mental illness. Mental health issues have become the most important part of personal safety. How to quickly and timely screen users' mental health problems and avoid psychological crises and extreme events has become a top priority. At present, mental health assessments are mainly conducted in the form of scale assessments. However, due to the lack of understanding of the scale by some users, the concealment of users' scale answers, and the accuracy of the scale's own threshold, the accuracy and effectiveness of the scale assessment results have been questioned, making it impossible to conduct accurate mental health assessments on the population, reducing practicality. Summary of the invention

[0003] In response to the above-mentioned problems, the present invention provides a mental health assessment system and method to solve the problem mentioned in the background technology that the accuracy and validity of the scale assessment results are questioned due to the lack of understanding of the scale by some users, the concealment of users' scale answers, and the accuracy of the scale's own threshold, making it impossible to conduct accurate mental health assessments on the population, thereby reducing practicality.

[0004] A mental health assessment system comprises the following steps:

[0005] A generation module is used to obtain multiple psychological evaluation indicators, generate mental health description data according to the multiple psychological evaluation indicators, and generate multiple mental health evaluation questions based on the mental health description data;

[0006] A construction module is used to collect responses to mental health assessment questions under different mental health states and to construct a mental health assessment network model based on the mental health assessment questions, responses and assessment rules;

[0007] The evaluation module is used to obtain the target user's evaluation answers to the mental health evaluation test questions, evaluate the evaluation answers using the mental health evaluation network model, and obtain the evaluation results;

[0008] The determination module is used to determine the comprehensive mental health assessment result of the target user based on the assessment result and the performance mapping sequence of the target user.

[0009] Preferably, the generating module comprises:

[0010] A first acquisition submodule is used to determine a plurality of reference dimensions for reflecting mental health and to acquire standard data items for each reference dimension;

[0011] The first generation submodule is used to obtain multiple psychological evaluation indicators according to the standard data items, determine the text mapping content of each psychological evaluation indicator, and generate psychological health description data according to the text mapping content;

[0012] A first determination submodule is used to determine a mental health assessment target based on the mental health description data;

[0013] The second generation submodule is used to generate multiple mental health assessment test questions based on the mental health assessment objectives.

[0014] Preferably, the building blocks include:

[0015] The selection submodule is used to determine the test type of the mental health assessment test questions and select the target population of the corresponding type and with different mental health status according to the test type;

[0016] The second acquisition submodule is used to use the mental health assessment questions to conduct a mental health assessment on the target population and obtain the response content;

[0017] The first construction submodule is used to determine the difference between the reply content and the standard answer, determine the concept change description index of people with different mental health status according to the difference, and construct the evaluation rules for distinguishing different mental health status according to the concept change description index;

[0018] The second construction submodule is used to construct a mental health assessment network model based on the long short-term memory network according to the mental health assessment questions and answer content and assessment rules.

[0019] Preferably, the evaluation module comprises:

[0020] The analysis submodule is used to obtain the target user's evaluation answers to the mental health assessment questions through online answering or offline interviews, and analyze the evaluation answers using natural language processing technology;

[0021] The extraction submodule is used to extract key information and features from the evaluation answers based on the analysis results;

[0022] A matching submodule, used for inputting the key information and features into the mental health assessment network model for data matching and obtaining matching results;

[0023] The second determination submodule is used to determine the current mental health status of the target user according to the matching result.

[0024] Preferably, the determining module includes:

[0025] The third determination submodule is used to determine the current mental health status of the target user according to the evaluation results, and judge the preliminary mental health status of the target user according to the current mental health status;

[0026] The third generation submodule is used to obtain the behavior pattern habit description parameters and thinking pattern habit description parameters of the target user when answering questions, and generate the performance mapping sequence of the target user according to the behavior pattern habit description parameters and thinking pattern habit description parameters;

[0027] A processing submodule, used for performing average pooling on the feature sequence to obtain a feature vector, and combining the feature vector and a preset weight vector with a psychological warning event mask to obtain a psychological state vector;

[0028] The evaluation submodule is used to determine the comprehensive mental health evaluation result of the target user based on the mental state vector and the preliminary mental health condition of the target user.

[0029] Preferably, the second generation submodule includes:

[0030] The first determination unit is used to determine the problem type and assessment field according to the mental health assessment objectives, and to determine the macro-descriptive items and micro-descriptive items according to the assessment field;

[0031] The second determination unit is used to determine the distribution of people in different mental health states and determine the difficulty level range of the test questions according to the distribution of people;

[0032] The first generation unit is used to generate question descriptions and options according to question types and macro-description items and micro-description items based on psychological knowledge;

[0033] The second generation unit is used to generate multiple mental health assessment test questions based on the difficulty level range of the test questions according to the question description and options.

[0034] Preferably, after obtaining the target user's evaluation answer to the mental health evaluation test question, the evaluation answer is evaluated using the mental health evaluation network model, and before obtaining the evaluation result, the system is also used to:

[0035] Obtain the characteristic word tendency of the target user when filling in the mental health assessment test questions;

[0036] Invalid data are screened out from the evaluation answers based on the tendency of characteristic words and deleted, and the processed evaluation answers are used as evaluation samples for the mental health assessment network model.

[0037] Preferably, after generating a plurality of mental health assessment test questions based on the difficulty level range of the test questions according to the question description and the options, the system is further used to:

[0038] Perform feature extraction on each mental health assessment question to obtain text features of each mental health assessment question;

[0039] Parse the text features to obtain the first parsing parameter, and obtain the test evaluation data of each mental health assessment test question based on psychology knowledge;

[0040] Parsing the test question evaluation data, obtaining a second parsing parameter, and determining a bias correlation coefficient between the first parsing parameter and the second parsing parameter;

[0041] Determine the eligibility of each mental health assessment question according to the bias correlation coefficient between the first analytical parameter and the second analytical parameter, delete the unqualified first mental health assessment questions, and retain the second mental health assessment questions;

[0042] Obtaining the test information and solution information of each second mental health assessment test question, and determining the characteristics of the problem-solving process according to the test information and solution information;

[0043] Based on the characteristics of the problem-solving process, the target group characteristics of each second mental health assessment question are determined, and the rationality of each second mental health assessment question is determined according to the characteristics of the target group, and the unreasonable third mental health assessment question is eliminated, and the fourth mental health assessment question is retained;

[0044] Acquire the emotional characteristic attribute of each fourth mental health assessment question, and determine the emotional weight of each fourth mental health assessment question according to the emotional characteristic attribute;

[0045] Eliminate and sort out the fifth mental health assessment data whose emotional weights are outside the preset numerical range, and retain the sixth mental health assessment questions;

[0046] Determine the event elements of each sixth mental health assessment question, determine the sensitive elements from the event elements, eliminate and sort out the seventh mental health assessment questions with sensitive elements, and retain the eighth mental health assessment questions;

[0047] Use the eighth mental health assessment question as the final mental health assessment question.

[0048] Preferably, determining the bias correlation coefficient between the first analytical parameter and the second analytical parameter comprises:

[0049] Obtain a test question feature vector representation according to the first analytical parameter, and obtain an answer feature vector representation according to the second analytical parameter;

[0050] Obtain the digital eigenvalue of the test question according to the test question eigenvector representation, and obtain the digital eigenvalue of the solution according to the answer eigenvector representation;

[0051] The discrete degree thresholds of the first analytical parameter and the second analytical parameter are calculated based on the numerical eigenvalues ​​of the test question and the numerical eigenvalues ​​of the solution:

[0052]

[0053] Among them, a represents the first parsing parameter, b represents the second parsing parameter, It is represented as the discrete degree threshold of the first analytical parameter and the second analytical parameter, It is represented as the resolution coefficient, N is the number of related question types corresponding to the first analytical parameter, i is the i-th type of question, It is expressed as the characteristic matching coefficient of the first analytical parameter for the i-th type of test question, Expressed as the numerical eigenvalue of the test question, It is expressed as the characteristic matching coefficient of the i-th type of test question for the second analytical parameter, Expressed as the numerical eigenvalue of the problem, Expressed as approximate eigenvalues;

[0054] The bias correlation coefficient between the first analytical parameter and the second analytical parameter is determined by back-calculating according to the discrete degree threshold.

[0055] A mental health assessment method comprises the following steps:

[0056] Acquire multiple psychological assessment indicators, generate mental health description data according to the multiple psychological assessment indicators, and generate multiple mental health assessment questions based on the mental health description data;

[0057] Collect responses to mental health assessment questions under different mental health conditions and build a mental health assessment network model based on the mental health assessment questions, responses and assessment rules;

[0058] Obtain the target user's answers to the mental health assessment test questions, evaluate the answers using the mental health assessment network model, and obtain the evaluation results;

[0059] Determine the comprehensive mental health assessment result of the target user based on the assessment result and the performance mapping sequence of the target user.

[0060] Through the above technical means, the present invention can achieve the following beneficial effects:

[0061] By constructing a mental health assessment model, we can accurately assess the mental health status of target users based on the reference responses to assessment questions of different mental health statuses according to the target users' assessment answers, thereby improving the assessment efficiency. At the same time, we can combine the performance sequence of the target users during the assessment to achieve accurate assessment. We can evaluate the user's attitude tendencies when answering questions and then judge the accuracy and objectivity of the user's assessment answers, thereby ensuring the quality of the assessment answers, laying a solid reference condition for subsequent mental health assessments, and improving practicality and assessment accuracy.

[0062] By obtaining multiple psychological assessment indicators based on the standard data items of each reference dimension, a person's mental health status can be evaluated more comprehensively, making the assessment results more comprehensive. Furthermore, by determining the text mapping of the indicators and generating mental health description data, determining the mental health assessment goals and generating multiple mental health assessment test questions, highly targeted test questions can be designed to help users understand their mental health status in all aspects more comprehensively and increase the validity and reliability of the measurement.

[0063] According to the test type of the mental health assessment test, the target population with corresponding type and different mental health status is selected, and the mental health assessment is conducted on them, the reply content is obtained, the difference between the reply content and the standard answer is determined, and the assessment rules for distinguishing different mental health status are constructed. The mental health assessment network model can be continuously based on the patient's condition, thereby realizing real-time mental health assessment and improving the assessment effect of the model.

[0064] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0065] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0067] Figure 1 A schematic diagram of the structure of a mental health assessment system provided by the present invention;

[0068] Figure 2 This is a schematic diagram of the structure of a generation module in a mental health assessment system provided by the present invention;

[0069] Figure 3A schematic diagram of the structure of a building block in a mental health assessment system provided by the present invention;

[0070] Figure 4 This is a workflow diagram of a mental health assessment method provided by the present invention. DETAILED DESCRIPTION

[0071] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0072] The current society is highly competitive, and the overload of study and work has caused almost everyone to be not only in a sub-healthy state physically, but also to often produce negative emotions psychologically. Intermittent negative emotions are often ignored soon after they appear. Once negative emotions continue to accumulate, they are likely to cause mental illness. Mental health issues have become the most important part of personal safety. How to quickly and timely screen users' mental health problems and avoid psychological crises and extreme events has become a top priority. The current mental health assessment is mainly carried out in the form of scale evaluation, but due to the lack of understanding of the scale by some users, the concealment of users' scale answers, and the accuracy of the scale's own threshold, the accuracy and effectiveness of the scale evaluation results are questioned, making it impossible to conduct accurate mental health assessments on the population, reducing practicality. In order to solve the above problems, this embodiment discloses a mental health assessment method.

[0073] A mental health assessment system, such as Figure 1 As shown, the system includes:

[0074] A generating module 101 is used to obtain a plurality of psychological evaluation indicators, generate mental health description data according to the plurality of psychological evaluation indicators, and generate a plurality of mental health evaluation questions based on the mental health description data;

[0075] A construction module 102 is used to collect the answers to the mental health assessment questions under different mental health states and to construct a mental health assessment network model according to the mental health assessment questions, the answers and the assessment rules;

[0076] The evaluation module 103 is used to obtain the evaluation answers of the target user to the mental health evaluation test questions, evaluate the evaluation answers using the mental health evaluation network model, and obtain the evaluation results;

[0077] The determination module 104 is used to determine the comprehensive mental health assessment result of the target user according to the assessment result and the performance mapping sequence of the target user.

[0078] In this embodiment, the psychological assessment index is represented as a reference index for evaluating mental health, such as intelligence, emotion, etc.;

[0079] In this embodiment, the mental health description data is represented by the description data of each evaluation index under the mental health state;

[0080] In this embodiment, the evaluation rules are expressed as evaluation rules for distinguishing different mental health states;

[0081] In this embodiment, the performance mapping sequence is represented as a mapping sequence of parameters related to the target user's thinking mode and behavior mode when answering questions;

[0082] The working principle of the above technical solution is: first, obtain multiple psychological assessment indicators through the generation module, generate mental health description data according to the multiple psychological assessment indicators, and generate multiple mental health assessment questions based on the mental health description data; secondly, use the construction module to collect the response content to the mental health assessment questions under different mental health conditions and construct a mental health assessment network model according to the mental health assessment questions and the response content and the evaluation rules; then, obtain the target user's evaluation answers to the mental health assessment questions based on the evaluation module, evaluate the evaluation answers using the mental health assessment network model, and obtain the evaluation results; finally, use the determination module to determine the comprehensive mental health assessment results of the target user according to the evaluation results and the performance mapping sequence of the target user.

[0083] The beneficial effects of the above technical solution are: by constructing a mental health assessment model, the mental health status of the target user can be accurately assessed according to the target user's assessment answers based on the reference response content of the assessment questions with different mental health status, thereby improving the assessment efficiency, and at the same time combining the target user's performance sequence during the assessment to achieve accurate assessment, which can evaluate the user's attitude tendencies when answering questions and then judge the accuracy and objectivity of the user's assessment answers, thereby ensuring the quality of the assessment answers, laying a solid reference condition for subsequent mental health assessments, improving practicality and assessment accuracy, and solving the problem in the prior art that the accuracy and validity of the scale assessment results are questioned due to the lack of understanding of the scale by some users, the concealment of the user's scale answers, and the accuracy of the scale's own threshold, making it impossible to conduct accurate mental health assessments on the population, thereby reducing practicality.

[0084] In one embodiment, Figure 2 As shown, the generating module 101 includes:

[0085] A first acquisition submodule 1011 is used to determine multiple reference dimensions for reflecting mental health and acquire standard data items for each reference dimension;

[0086] The first generation submodule 1012 is used to obtain multiple psychological evaluation indicators according to the standard data items, determine the text mapping content of each psychological evaluation indicator, and generate psychological health description data according to the text mapping content;

[0087] A first determination submodule 1013 is used to determine a mental health assessment target based on the mental health description data;

[0088] The second generation submodule 1014 is used to generate a plurality of mental health assessment questions according to the mental health assessment objectives.

[0089] In this embodiment, the reference dimension may be a behavior dimension and a communication dimension, etc.;

[0090] The beneficial effects of the above technical solution are: by obtaining multiple psychological assessment indicators based on the standard data items of each reference dimension, a person's mental health status can be evaluated more comprehensively, making the assessment results more comprehensive. Furthermore, the text mapping of the indicators is determined and mental health description data is generated, the mental health assessment goals are determined and multiple mental health assessment test questions are generated. Targeted test questions can be designed to help users understand their mental health status in all aspects more comprehensively and increase the validity and reliability of the measurement.

[0091] In one embodiment, Figure 3 As shown, the building module 102 includes:

[0092] A selection submodule 1021 is used to determine the test type of the mental health assessment test questions, and select the target population of the corresponding type and with different mental health status according to the test type;

[0093] The second acquisition submodule 1022 is used to conduct a mental health assessment on the target population using the mental health assessment questions and obtain the response content;

[0094] The first construction submodule 1023 is used to determine the difference between the reply content and the standard answer, determine the concept change description index of people with different mental health status according to the difference, and construct an evaluation rule for distinguishing different mental health status according to the concept change description index;

[0095] The second construction submodule 1024 is used to construct a mental health assessment network model based on the long short-term memory network according to the mental health assessment test questions and answer content and assessment rules.

[0096] The beneficial effects of the above technical solution are: according to the test type of the mental health assessment test, the corresponding type of target population with different mental health status is selected, and the mental health assessment is conducted on them, the reply content is obtained, the distinction between the reply content and the standard answer is determined, and the assessment rules for distinguishing different mental health status are constructed. The mental health assessment network model can be continuously based on the patient's condition, thereby realizing real-time mental health assessment and improving the assessment effect of the model.

[0097] In one embodiment, the evaluation module comprises:

[0098] The analysis submodule is used to obtain the target user's evaluation answers to the mental health assessment questions through online answering or offline interviews, and analyze the evaluation answers using natural language processing technology;

[0099] The extraction submodule is used to extract key information and features from the evaluation answers based on the analysis results;

[0100] A matching submodule, used for inputting the key information and features into the mental health assessment network model for data matching and obtaining matching results;

[0101] The second determination submodule is used to determine the current mental health status of the target user according to the matching result.

[0102] The beneficial effects of the above technical solution are: obtaining the target user's evaluation answers to the mental health assessment questions and analyzing them using natural language processing technology, obtaining key information and features in the answers, and matching the data with the mental health assessment network model to determine the target user's current mental health status, which can more accurately identify the user's possible psychological problems and risk factors, thereby formulating more effective mental health test questions.

[0103] In one embodiment, the determining module includes:

[0104] The third determination submodule is used to determine the current mental health status of the target user according to the evaluation results, and judge the preliminary mental health status of the target user according to the current mental health status;

[0105] The third generation submodule is used to obtain the behavior pattern habit description parameters and thinking pattern habit description parameters of the target user when answering questions, and generate the performance mapping sequence of the target user according to the behavior pattern habit description parameters and thinking pattern habit description parameters;

[0106] A processing submodule, used for performing average pooling on the feature sequence to obtain a feature vector, and combining the feature vector and a preset weight vector with a psychological warning event mask to obtain a psychological state vector;

[0107] The evaluation submodule is used to determine the comprehensive mental health evaluation result of the target user based on the mental state vector and the preliminary mental health condition of the target user.

[0108] The beneficial effects of the above technical solution are: judging the preliminary mental health status of the target user based on the evaluation results, being able to promptly discover the user's existing psychological problems, and improving the accuracy of the user's comprehensive mental health evaluation results; generating the target user's performance mapping sequence based on the behavior pattern habit description parameters and the thinking pattern habit description parameters, and performing average pooling on the feature sequence to obtain the psychological state vector, thereby determining the target user's comprehensive mental health evaluation results, which can provide a more comprehensive and in-depth understanding of the user's current psychological state and problems, and help to conduct more accurate mental health evaluations.

[0109] In one embodiment, the second generation submodule includes:

[0110] The first determination unit is used to determine the problem type and assessment field according to the mental health assessment objectives, and to determine the macro-descriptive items and micro-descriptive items according to the assessment field;

[0111] The second determination unit is used to determine the distribution of people in different mental health states and determine the difficulty level range of the test questions according to the distribution of people;

[0112] The first generation unit is used to generate question descriptions and options according to question types and macro-description items and micro-description items based on psychological knowledge;

[0113] The second generation unit is used to generate multiple mental health assessment test questions based on the difficulty level range of the test questions according to the question description and options.

[0114] The beneficial effects of the above technical solution are: determining the type of questions according to the mental health assessment objectives and determining the macro-descriptive items and micro-descriptive items according to the assessment field, generating question descriptions and options, improving the relevance and accuracy of the questions, and at the same time, determining the difficulty level range of the test questions according to the distribution of people under different mental health conditions, thereby generating multiple mental health assessment test questions, which can ensure that the generated test questions are easier to understand and use, and formulate corresponding test questions for people with different mentalities, thereby improving the applicability of the test questions.

[0115] In one embodiment, after obtaining the target user's evaluation answer to the mental health evaluation test question, the evaluation answer is evaluated using the mental health evaluation network model. Before obtaining the evaluation result, the system is further used to:

[0116] Obtain the characteristic word tendency of the target user when filling in the mental health assessment test questions;

[0117] Invalid data are screened out from the evaluation answers based on the tendency of characteristic words and deleted, and the processed evaluation answers are used as evaluation samples for the mental health assessment network model.

[0118] The beneficial effects of the above technical solution are: invalid data is screened out and deleted from the evaluation answers based on the characteristic word frequency tendency when the user fills in the test questions, and the processed evaluation answers are used as evaluation samples for the evaluation network model, which can improve the accuracy and reliability of the model, thereby accurately evaluating the accuracy of the results.

[0119] In one embodiment, after generating a plurality of mental health assessment test questions based on the difficulty level range of the test questions according to the question description and the options, the system is further used to:

[0120] Perform feature extraction on each mental health assessment question to obtain text features of each mental health assessment question;

[0121] Parse the text features to obtain the first parsing parameter, and obtain the test evaluation data of each mental health assessment test question based on psychology knowledge;

[0122] Parsing the test question evaluation data, obtaining a second parsing parameter, and determining a bias correlation coefficient between the first parsing parameter and the second parsing parameter;

[0123] Determine the eligibility of each mental health assessment question according to the bias correlation coefficient between the first analytical parameter and the second analytical parameter, delete the unqualified first mental health assessment questions, and retain the second mental health assessment questions;

[0124] Obtaining the test information and solution information of each second mental health assessment test question, and determining the characteristics of the problem-solving process according to the test information and solution information;

[0125] Based on the characteristics of the problem-solving process, the target group characteristics of each second mental health assessment question are determined, and the rationality of each second mental health assessment question is determined according to the characteristics of the target group, and the unreasonable third mental health assessment question is eliminated, and the fourth mental health assessment question is retained;

[0126] Acquire the emotional characteristic attribute of each fourth mental health assessment question, and determine the emotional weight of each fourth mental health assessment question according to the emotional characteristic attribute;

[0127] Eliminate and sort out the fifth mental health assessment data whose emotional weights are outside the preset numerical range, and retain the sixth mental health assessment questions;

[0128] Determine the event elements of each sixth mental health assessment question, determine the sensitive elements from the event elements, eliminate and sort out the seventh mental health assessment questions with sensitive elements, and retain the eighth mental health assessment questions;

[0129] Use the eighth mental health assessment question as the final mental health assessment question.

[0130] The beneficial effects of the above technical scheme are: by evaluating the eligibility, rationality, emotional weight and event elements of the mental health assessment questions in turn and then eliminating the relevant mental health assessment questions, it is possible to ensure the accuracy, quality and eligibility of the questions while avoiding emotional induction of the test takers, thereby ensuring the objectivity of the questions and avoiding the appearance of sensitive elements in the questions, further ensuring the quality of the questions and the health of the content.

[0131] In one embodiment, determining a bias correlation coefficient between a first analysis parameter and a second analysis parameter includes:

[0132] Obtain a test question feature vector representation according to the first analytical parameter, and obtain an answer feature vector representation according to the second analytical parameter;

[0133] Obtain the digital eigenvalue of the test question according to the test question eigenvector representation, and obtain the digital eigenvalue of the solution according to the answer eigenvector representation;

[0134] The discrete degree thresholds of the first analytical parameter and the second analytical parameter are calculated based on the numerical eigenvalues ​​of the test question and the numerical eigenvalues ​​of the solution:

[0135]

[0136] Among them, a represents the first parsing parameter, b represents the second parsing parameter, It is represented as the discrete degree threshold of the first analytical parameter and the second analytical parameter, It is represented as the resolution coefficient, N is the number of related question types corresponding to the first analytical parameter, i is the i-th type of question, It is expressed as the characteristic matching coefficient of the first analytical parameter for the i-th type of test question, Expressed as the numerical eigenvalue of the test question, It is expressed as the characteristic matching coefficient of the i-th type of test question for the second analytical parameter, Expressed as the numerical eigenvalue of the problem, Expressed as approximate eigenvalues;

[0137] The bias correlation coefficient between the first analytical parameter and the second analytical parameter is determined by back-calculating according to the discrete degree threshold.

[0138] The beneficial effect of the above technical solution is: by calculating the discrete degree threshold of the first analysis parameter and the second analysis parameter based on the number of related question types and the feature matching coefficient, the discreteness of the two in different question types can be determined, and then the correlation coefficient between the two can be determined, thereby ensuring the accuracy of the correlation coefficient with sufficient question type support.

[0139] In one embodiment, this embodiment also discloses a method for evaluating mental health. Figure 4 As shown, the following steps are included:

[0140] Step S401, obtaining a plurality of psychological evaluation indicators, generating mental health description data according to the plurality of psychological evaluation indicators, and generating a plurality of mental health evaluation test questions based on the mental health description data;

[0141] Step S401, collecting the answers to the mental health assessment questions under different mental health states and constructing a mental health assessment network model according to the mental health assessment questions, the answers and the assessment rules;

[0142] Step S403: obtaining the target user's evaluation answers to the mental health evaluation questions, evaluating the evaluation answers using the mental health evaluation network model, and obtaining evaluation results;

[0143] Step S404: Determine the comprehensive mental health assessment result of the target user according to the assessment result and the performance mapping sequence of the target user.

[0144] The working principle and beneficial effects of the above technical solution have been described in the system claims and will not be repeated here.

[0145] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0146] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A mental health assessment system, characterized in that: The following steps are involved: A generation module is used to obtain multiple psychological evaluation indicators, generate mental health description data according to the multiple psychological evaluation indicators, and generate multiple mental health evaluation questions based on the mental health description data; A construction module is used to collect responses to mental health assessment questions under different mental health states and to construct a mental health assessment network model based on the mental health assessment questions, responses and assessment rules; The evaluation module is used to obtain the target user's evaluation answers to the mental health evaluation test questions, evaluate the evaluation answers using the mental health evaluation network model, and obtain the evaluation results; a determination module, for determining a comprehensive mental health assessment result of a target user according to the assessment result and a performance mapping sequence of the target user; Wherein, the generating module comprises: A first acquisition submodule is used to determine a plurality of reference dimensions for reflecting mental health and to acquire standard data items for each reference dimension; The first generation submodule is used to obtain multiple psychological evaluation indicators according to the standard data items, determine the text mapping content of each psychological evaluation indicator, and generate psychological health description data according to the text mapping content; A first determination submodule is used to determine a mental health assessment target based on the mental health description data; The second generation submodule is used to generate multiple mental health assessment test questions according to the mental health assessment objectives; Wherein, the second generation submodule includes: The first determination unit is used to determine the problem type and assessment field according to the mental health assessment objectives, and to determine the macro-descriptive items and micro-descriptive items according to the assessment field; The second determination unit is used to determine the distribution of people in different mental health states and determine the difficulty level range of the test questions according to the distribution of people; The first generation unit is used to generate question descriptions and options according to question types and macro-description items and micro-description items based on psychological knowledge; The second generation unit is used to generate a plurality of mental health assessment test questions based on the difficulty level range of the test questions according to the question description and options; After generating a plurality of mental health assessment test questions based on the difficulty level range of the test questions according to the question description and the options, the system is also used to: Perform feature extraction on each mental health assessment question to obtain text features of each mental health assessment question; Parse the text features to obtain the first parsing parameter, and obtain the test evaluation data of each mental health assessment test question based on psychology knowledge; Parsing the test question evaluation data, obtaining a second parsing parameter, and determining a bias correlation coefficient between the first parsing parameter and the second parsing parameter; Determine the eligibility of each mental health assessment question according to the bias correlation coefficient between the first analytical parameter and the second analytical parameter, delete the unqualified first mental health assessment questions, and retain the second mental health assessment questions; Obtaining the test information and solution information of each second mental health assessment test question, and determining the characteristics of the problem-solving process according to the test information and solution information; Based on the characteristics of the problem-solving process, the target group characteristics of each second mental health assessment question are determined, and the rationality of each second mental health assessment question is determined according to the characteristics of the target group, and the unreasonable third mental health assessment question is eliminated, and the fourth mental health assessment question is retained; Acquire the emotional characteristic attribute of each fourth mental health assessment question, and determine the emotional weight of each fourth mental health assessment question according to the emotional characteristic attribute; Eliminate and sort out the fifth mental health assessment data whose emotional weights are outside the preset numerical range, and retain the sixth mental health assessment questions; Determine the event elements of each sixth mental health assessment question, determine the sensitive elements from the event elements, eliminate and sort out the seventh mental health assessment questions with sensitive elements, and retain the eighth mental health assessment questions; Use the eighth mental health assessment question as the final mental health assessment question.

2. The mental health assessment system according to claim 1, characterized in that: The building blocks include: The selection submodule is used to determine the test type of the mental health assessment test questions and select the target population of the corresponding type and with different mental health status according to the test type; The second acquisition submodule is used to use the mental health assessment questions to conduct a mental health assessment on the target population and obtain the response content; The first construction submodule is used to determine the difference between the reply content and the standard answer, determine the concept change description index of people with different mental health status according to the difference, and construct the evaluation rules for distinguishing different mental health status according to the concept change description index; The second construction submodule is used to construct a mental health assessment network model based on the long short-term memory network according to the mental health assessment questions and answer content and assessment rules.

3. The mental health assessment system according to claim 1, characterized in that: The evaluation module comprises: The analysis submodule is used to obtain the target user's evaluation answers to the mental health assessment questions through online answering or offline interviews, and analyze the evaluation answers using natural language processing technology; The extraction submodule is used to extract key information and features from the evaluation answers based on the analysis results; A matching submodule, used for inputting the key information and features into the mental health assessment network model for data matching and obtaining matching results; The second determination submodule is used to determine the current mental health status of the target user according to the matching result.

4. The mental health assessment system according to claim 1, characterized in that: The determining module comprises: The third determination submodule is used to determine the current mental health status of the target user according to the evaluation results, and judge the preliminary mental health status of the target user according to the current mental health status; The third generation submodule is used to obtain the behavior pattern habit description parameters and thinking pattern habit description parameters of the target user when answering questions, and generate the performance mapping sequence of the target user according to the behavior pattern habit description parameters and thinking pattern habit description parameters; A processing submodule, used for performing average pooling on the feature sequence to obtain a feature vector, and combining the feature vector and a preset weight vector with a psychological warning event mask to obtain a psychological state vector; The evaluation submodule is used to determine the comprehensive mental health evaluation result of the target user based on the mental state vector and the preliminary mental health condition of the target user.

5. The mental health assessment system according to claim 1, characterized in that: After obtaining the target user's answer to the mental health assessment test, the mental health assessment network model is used to evaluate the answer. Before obtaining the evaluation result, the system is also used to: Obtain the characteristic word tendency of the target user when filling in the mental health assessment test questions; Invalid data are screened out from the evaluation answers based on the tendency of characteristic words and deleted, and the processed evaluation answers are used as evaluation samples for the mental health assessment network model.

6. The mental health assessment system according to claim 1, characterized in that: Determining a bias correlation coefficient between a first analytical parameter and a second analytical parameter includes: Obtain a test question feature vector representation according to the first analytical parameter, and obtain an answer feature vector representation according to the second analytical parameter; Obtain the digital eigenvalue of the test question according to the test question eigenvector representation, and obtain the digital eigenvalue of the solution according to the answer eigenvector representation; The discrete degree thresholds of the first analytical parameter and the second analytical parameter are calculated based on the numerical eigenvalues ​​of the test question and the numerical eigenvalues ​​of the solution: Among them, a represents the first parsing parameter, b represents the second parsing parameter, It is represented as the discrete degree threshold of the first analytical parameter and the second analytical parameter, It is represented as the resolution coefficient, N is the number of related question types corresponding to the first analytical parameter, i is the i-th type of question, It is expressed as the characteristic matching coefficient of the first analytical parameter for the i-th type of test question, Expressed as the numerical eigenvalue of the test question, It is expressed as the characteristic matching coefficient of the i-th type of test question for the second analytical parameter, Expressed as the numerical eigenvalue of the problem, Expressed as approximate eigenvalues; The bias correlation coefficient between the first analytical parameter and the second analytical parameter is determined by back-calculating according to the discrete degree threshold.

7. A method for evaluating mental health, characterized in that: The following steps are involved: Acquire multiple psychological assessment indicators, generate mental health description data according to the multiple psychological assessment indicators, and generate multiple mental health assessment questions based on the mental health description data; Collect responses to mental health assessment questions under different mental health conditions and build a mental health assessment network model based on the mental health assessment questions, responses and assessment rules; Obtain the target user's answers to the mental health assessment test questions, evaluate the answers using the mental health assessment network model, and obtain the evaluation results; Determine the comprehensive mental health assessment result of the target user according to the assessment result and the performance mapping sequence of the target user; Among them, multiple psychological evaluation indicators are obtained, mental health description data is generated according to the multiple psychological evaluation indicators, and multiple mental health evaluation questions are generated based on the mental health description data, including: Determine multiple reference dimensions for reflecting mental health, and obtain standard data items for each reference dimension; Acquire multiple psychological assessment indicators according to standard data items, determine text mapping content of each psychological assessment indicator, and generate psychological health description data according to the text mapping content; Determine mental health assessment goals based on mental health descriptive data; Generate multiple mental health assessment questions according to mental health assessment goals; Among them, multiple mental health assessment questions are generated according to the mental health assessment goals, including: Determine the question type and assessment field according to the mental health assessment objectives, and determine the macro-descriptive items and micro-descriptive items according to the assessment field; Determine the distribution of people in different mental health states, and determine the difficulty level range of the test questions based on the distribution of people; Generate question descriptions and options based on question types and macro-descriptive items and micro-descriptive items based on psychological knowledge; Generate multiple mental health assessment test questions based on the difficulty level range of the test questions according to the question description and options; Among them, after generating multiple mental health assessment questions based on the difficulty level range of the test questions according to the question description and options, it is also used to: Perform feature extraction on each mental health assessment question to obtain text features of each mental health assessment question; Parse the text features to obtain the first parsing parameter, and obtain the test evaluation data of each mental health assessment test question based on psychology knowledge; Parsing the test question evaluation data, obtaining a second parsing parameter, and determining a bias correlation coefficient between the first parsing parameter and the second parsing parameter; Determine the eligibility of each mental health assessment question according to the bias correlation coefficient between the first analytical parameter and the second analytical parameter, delete the unqualified first mental health assessment questions, and retain the second mental health assessment questions; Obtaining the test information and solution information of each second mental health assessment test question, and determining the characteristics of the problem-solving process according to the test information and solution information; Based on the characteristics of the problem-solving process, the target group characteristics of each second mental health assessment question are determined, and the rationality of each second mental health assessment question is determined according to the characteristics of the target group, and the unreasonable third mental health assessment question is eliminated, and the fourth mental health assessment question is retained; Acquire the emotional characteristic attribute of each fourth mental health assessment question, and determine the emotional weight of each fourth mental health assessment question according to the emotional characteristic attribute; Eliminate and sort out the fifth mental health assessment data whose emotional weights are outside the preset numerical range, and retain the sixth mental health assessment questions; Determine the event elements of each sixth mental health assessment question, determine the sensitive elements from the event elements, eliminate and sort out the seventh mental health assessment questions with sensitive elements, and retain the eighth mental health assessment questions; Use the eighth mental health assessment question as the final mental health assessment question.

Images