Mental health assessment method, device, electronic device and storage medium
By obtaining and processing the response time data of the tested object to the test material and extracting the target characteristic values, the problem of low accuracy of existing mental health assessment methods is solved, and higher evaluation accuracy and user experience are achieved.
Patent Information
- Application Number
- CN202410017951.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-04
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-01-04
AI Technical Summary
The accuracy of existing mental health assessment methods is low, and the tested group often avoids or lies, resulting in the measurement results that do not match the real situation.
By obtaining the response time data of the test material presented by the test terminal device of the test object, performing invalid data processing, extracting the target characteristic value, and evaluating mental health status based on the characteristic value, avoiding the traditional questionnaire form of avoidance and lying.
It improves the accuracy of the assessment, realizes intelligent assessment of the mental health status of the subject being tested, and improves the user experience.
Smart Images

Figure CN117789986B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and specifically to a mental health assessment method, device, electronic device and storage medium. Background Art
[0002] At present, people are paying more and more attention to mental health issues, and mental health issues are becoming increasingly serious. In previous studies, it was found that some traditional mental health problem (such as suicide) assessment questionnaires have extremely high surface validity in testing. The test group showed obvious avoidance and self-protection, and there were non-real assessment results such as disguise, modification, and lying, which led to the measurement results not being consistent with the actual situation and unable to accurately reflect the real situation of the test subjects. It can be seen that the assessment methods for mental health in related technologies have the problem of low accuracy.
[0003] With respect to the technical problem of low accuracy of mental health assessment methods existing in relevant technologies, no effective solution has been proposed so far. Summary of the invention
[0004] The present application provides a mental health assessment method, device, electronic device and storage medium to at least solve the technical problem of low accuracy of mental health assessment methods existing in related technologies.
[0005] In a first aspect, the present application provides a method for psychological health assessment, comprising: obtaining a first test data set of a subject under test, wherein the first test data set includes data on the reaction time of the subject under test to a test material presented in a test terminal device; performing invalidation processing on the first test data set to obtain a target data set; obtaining a first target feature value of the subject under test based on the target data set; and assessing the psychological health status of the subject under test based on the first target feature value.
[0006] By adopting the above technical solution, the first test data set of the object under test is obtained, the invalid data in the first test data set is processed to obtain the target data set, and then the first target characteristic value of the object under test is extracted according to the target data set, and then the mental health status of the object under test is evaluated according to the first target characteristic value. It is realized that the data of the reaction time of the object under test to the test material is obtained through the test terminal device, which avoids the problem of low accuracy of the test results caused by the object under test often avoiding or lying in the form of an evaluation questionnaire in the related technology. At the same time, the technical solution also processes some invalid data in the first test data set, so that the accuracy of the target data set obtained is higher, and the corresponding first target characteristic value is extracted according to the target data set, and the mental health status of the object under test can be evaluated according to the first target characteristic value, so as to achieve the purpose of intelligent evaluation of the mental health status of the object under test and achieve the effect of improving the user experience.
[0007] Optionally, obtaining a first test data set of the subject under test includes: obtaining a first data set of the subject under test in an implicit association test, wherein the first test data set includes a first data set, and the first data set includes data on the reaction time of the subject under test to multiple first phrases appearing on the test terminal device, and each phrase in the multiple first phrases includes a concept word and an attribute word associated with the concept word; invalidating the first test data set to obtain a target data set, including: removing data that meets a first preset condition in the first data set to obtain a target data set, wherein the data of the first preset condition is used to represent data with a reaction time greater than a preset first reaction time threshold or less than a preset second reaction time threshold, and the preset first reaction time threshold is greater than the preset second reaction time threshold; obtaining a first target feature value of the subject under test according to the target data set, including: determining a first average reaction time according to the first data subset response time, and determining a second average reaction time according to a second data subset, wherein the first data subset is data on the reaction time of the subjects included in the target data set for compatible tasks in an implicit association test, and the second data subset is data on the reaction time of the subjects included in the target data set for incompatible tasks in an implicit association test; obtaining a first eigenvalue according to the first average reaction time, the second average reaction time and the target standard deviation, wherein the target standard deviation refers to the standard deviation value of the reaction time corresponding to all data in the target data set, and the first target eigenvalue includes the first eigenvalue; evaluating the mental health status of the subject based on the first target eigenvalue, including: when the first eigenvalue is greater than a first preset threshold, judging that the subject has a first type of psychological problem; when the first eigenvalue is less than or equal to the first preset threshold, judging that the subject does not have a first type of psychological problem.
[0008] By adopting the above technical solution, the first data set of the tested object in the implicit association test is obtained, that is, the reaction time of the tested object to each of the multiple first phrases is tested, and then the invalid data in the first data set is eliminated to obtain the target data set. The invalid data can be data that meets the first preset condition. The data of the first preset condition is data whose reaction time is greater than the preset first reaction time threshold or less than the preset second reaction time threshold, so that the purpose of eliminating the invalid data in the first data set can be achieved; then, the first data subset and the second data subset included in the target data set are determined, and the first average reaction time is determined according to the first data subset, and the second average reaction time is determined according to the second data subset, that is, the average reaction time of the tested object for the compatible task and the incompatible task is obtained, and then the first eigenvalue is obtained according to the first average reaction time, the second average reaction time and the target standard deviation. The first eigenvalue can be used to measure the implicit suicidal ideation of the tested object. Therefore, the first eigenvalue can be used to evaluate whether the tested object has the first type of psychological problem. The purpose of obtaining the average reaction time of the tested object for the compatible task and the incompatible task, and then intelligently evaluating whether the tested object has the first type of psychological problem is achieved.
[0009] Optionally, obtaining a first test data set of the subject under test includes: obtaining a second data set in a test of the subject's attention to emotional words, wherein the first test data set includes the second data set, and the second data set includes data on the subject's reaction time to each word in a plurality of second phrases appearing on the test terminal device, and each phrase in the plurality of second phrases includes a positive emotional word and a negative emotional word; invalidating the first test data set to obtain a target data set, including: removing data in the second data set that meets a second preset condition to obtain a target data set, wherein the data of the second preset condition is used to represent data with a reaction time greater than a preset third reaction time threshold or less than a preset fourth reaction time threshold, and the preset third reaction time threshold is greater than a preset fourth reaction time threshold; obtaining a first target feature value of the subject under test according to the target data set, including In summary: determining a third average reaction time according to a third data subset, and determining a fourth average reaction time according to a fourth data subset, wherein the third data subset is data on the reaction time of the subjects included in the target data set to positive emotional words in a test of the degree of attention to emotional words, and the fourth data subset is data on the reaction time of the subjects included in the target data set to negative emotional words in a test of the degree of attention to emotional words; obtaining a second eigenvalue according to the third average reaction time and the fourth average reaction time, wherein the first target eigenvalue includes the second eigenvalue; evaluating the mental health status of the subject based on the first target eigenvalue, including: when the second eigenvalue is less than a second preset threshold, judging that the subject has a second type of psychological problem; when the second eigenvalue is greater than or equal to the second preset threshold, judging that the subject does not have a second type of psychological problem.
[0010] By adopting the above technical solution, the second data set in the test of the degree of attention of the tested object to emotional words is obtained, that is, the reaction time of the tested object to each word in the plurality of second phrases is tested, and then the invalid data in the second data set is eliminated to obtain the target data set, and the invalid data can be data that meets the second preset condition, and the data of the second preset condition is data whose reaction time is greater than the preset third reaction time threshold or less than the preset fourth reaction time threshold, so that the purpose of eliminating the invalid data in the second data set can be achieved; then, the third data subset and the fourth data subset included in the target data set are determined, and the third average reaction time is determined according to the third data subset, and the fourth average reaction time is determined according to the fourth data subset, that is, the average reaction time of the tested object to positive emotional words and negative emotional words is obtained, and then the second characteristic value is obtained according to the third average reaction time and the fourth average reaction time. The second characteristic value can be used to measure the emotional tendency of the tested object, so the second characteristic value can be used to evaluate whether the tested object has the second type of psychological problems. The purpose of obtaining the average reaction time of the tested object to positive emotional words and negative emotional words, and then intelligently evaluating whether the tested object has the second type of psychological problems is achieved.
[0011] Optionally, obtaining a first test data set of the subject under test includes: obtaining a third data set in a test of the subject's attention to emotional faces, wherein the first test data set includes the third data set, and the third data set includes data on the subject's reaction time to multiple face groups appearing on the test terminal device, and each of the multiple face groups includes a positive emotional face and a negative emotional face; invalidating the first test data set to obtain a target data set, including: eliminating data that meets a third preset condition in the third data set to obtain a target data set, wherein the data of the third preset condition is used to represent data with a reaction time greater than a preset fifth reaction time threshold or less than a preset sixth reaction time threshold, and the preset fifth reaction time threshold is greater than the preset sixth reaction time threshold; obtaining a first target feature value of the subject under test according to the target data set, including: based on A fifth average reaction time is determined according to the fifth data subset, and a sixth average reaction time is determined according to the sixth data subset, wherein the fifth data subset is data on the reaction time of the subjects included in the target data set to positive emotional faces in a test of emotional face attention level, and the sixth data subset is data on the reaction time of the subjects included in the target data set to negative emotional faces in a test of emotional face attention level; a third eigenvalue is obtained according to the fifth average reaction time and the sixth average reaction time, wherein the first target eigenvalue includes the third eigenvalue; and the mental health status of the subject is evaluated based on the first target eigenvalue, including: when the third eigenvalue is less than a third preset threshold, judging that the subject has a third type of psychological problem; when the third eigenvalue is greater than or equal to the third preset threshold, judging that the subject does not have a third type of psychological problem.
[0012] By adopting the above technical solution, the third data set in the test of the degree of attention of the measured object to emotional faces is obtained, that is, the reaction time of the measured object to each emotional face in multiple emotional face groups is tested, and then the invalid data in the third data set is eliminated to obtain the target data set. The invalid data can be data that meets the third preset condition. The data of the third preset condition is data with a reaction time greater than the preset fifth reaction time threshold or less than the preset sixth reaction time threshold, so that the purpose of eliminating the invalid data in the third data set can be achieved; then, the fifth data subset and the sixth data subset included in the target data set are determined, and the fifth average reaction time is determined according to the fifth data subset, and the sixth average reaction time is determined according to the sixth data subset, that is, the average reaction time of the measured object to positive emotional faces and negative emotional faces is obtained, and then the third eigenvalue is obtained according to the fifth average reaction time and the sixth average reaction time. The third eigenvalue can be used to measure the degree of emotional tendency of the measured object. Therefore, the third eigenvalue can be used to evaluate whether the measured object has the third type of psychological problem. The purpose of obtaining the average reaction time of the measured object to positive emotional faces and negative emotional faces, and then intelligently evaluating whether the measured object has the third type of psychological problem is achieved. The purpose of testing the emotional tendencies of the subjects through different means is achieved.
[0013] Optionally, after evaluating the mental health status of the subject under test based on the first target eigenvalue, the method further includes: obtaining a second test data set of the subject under test, wherein the second test data set includes data in which the subject under test identifies a group of neutral expression pictures on the test terminal device as positive pictures or negative pictures; obtaining a first quantity and a second quantity based on the second test data set, wherein the first quantity is used to represent the number of pictures that the subject under test identifies as positive pictures, and the second quantity is used to represent the number of pictures that the subject under test identifies as negative pictures; obtaining a second target eigenvalue of the subject under test based on the first quantity and the second quantity, wherein the second target eigenvalue is used to represent the eigenvalue of the subject's reaction tendency to neutral expression pictures; when the second target eigenvalue is less than a fourth preset threshold, judging that the subject under test has a fourth type of psychological problem; when the second target eigenvalue is greater than or equal to the fourth preset threshold, judging that the subject under test does not have a fourth type of psychological problem.
[0014] By adopting the above technical solution, a second test data set of the tested object can also be obtained, wherein the second test data set includes data that the tested object identifies a group of neutral expression pictures on the test terminal device as positive pictures or negative pictures, respectively determining the first number of a group of neutral expression pictures identified as positive pictures by the tested object, and determining the second number of a group of neutral expression pictures identified as negative pictures by the tested object, and determining the second target feature value of the tested object according to the first number and the second number, the second target feature value is used to measure the reaction tendency of the tested object to the neutral expression pictures, and then according to the second target feature value, it can be evaluated whether the tested object has the fourth type of psychological problems. The purpose of enriching the test methods for mental health problems is achieved.
[0015] Optionally, after evaluating the mental health status of the subject based on the first target characteristic value, the method further includes: obtaining a third test data set of the subject, wherein the third test data set includes data of the subject in a self-encoding recall test, the self-encoding recall test being used to indicate a test in which the subject inputs a target vocabulary into an input box of the test terminal device after judging whether multiple words appearing in sequence on the test terminal device match the subject, the multiple words including at least one positive vocabulary and at least one negative vocabulary; obtaining a third quantity and a fourth quantity according to the third test data set, wherein the third quantity is used to indicate the number of positive vocabulary in the target vocabulary among multiple vocabulary, and the fourth quantity is used to indicate the number of negative vocabulary in the target vocabulary among multiple vocabulary; obtaining a third target characteristic value of the subject according to the third quantity and the fourth quantity, wherein the third target characteristic value is used to indicate the characteristic value of the subject's bias towards self-recall; when the third target characteristic value is less than a fifth preset threshold, judging that the subject has a fifth type of psychological problem; when the third target characteristic value is greater than or equal to the fifth preset threshold, judging that the subject does not have a fifth type of psychological problem.
[0016] By adopting the above technical solution, after obtaining whether the multiple words that appear in sequence on the test terminal device match the subject, the subject enters the relevant data of the target word in the input box of the test terminal device, that is, the self-recall data of the subject for positive words and negative words is obtained, and then the third number of recalled positive words and the fourth number of recalled negative words are determined respectively, and the third target characteristic value of the subject is determined according to the third number and the fourth number. The third target characteristic value is used to measure the self-recall bias of the subject, and then the third target characteristic value can be used to evaluate whether the subject has the fifth type of psychological problem. The purpose of enriching the test methods for mental health problems is achieved.
[0017] Optionally, after evaluating the mental health status of the subject based on the first target feature value, the method further includes: obtaining a fourth test data set of the subject, wherein the fourth test data set includes data of the subject in a self-encoding recognition test, the self-encoding recognition test being used to indicate that within a preset time period after each word in the third phrase is presented in sequence on the test terminal device, the subject reconfirms whether each word in the fourth phrase presented in the terminal device belongs to the words in the third phrase, and there is at least one identical positive word and at least one identical negative word in the third phrase and the fourth phrase; obtaining a fifth quantity and a sixth quantity based on the fourth test data set, wherein the fifth quantity includes The sum of the number of positive words in the fourth phrase belonging to the third phrase and the number of correctly identified positive words in the fourth phrase that do not belong to the third phrase, and the sixth number includes the sum of the number of negative words in the fourth phrase belonging to the third phrase and the number of correctly identified negative words in the fourth phrase that do not belong to the third phrase; the fourth target characteristic value of the subject is obtained according to the fifth number and the sixth number, wherein the fourth target characteristic value is used to represent the characteristic value of the subject's judgment on the self-schema type; when the fourth target characteristic value is less than the sixth preset threshold, it is judged that the subject has the sixth type of psychological problem; when the fourth target characteristic value is greater than or equal to the sixth preset threshold, it is judged that the subject does not have the sixth type of psychological problem.
[0018] By adopting the above technical solution, the subject reconfirms whether each word in the fourth word group presented on the test terminal device belongs to the third word group within the preset time after each word in the third word group is presented on the test terminal device in sequence, determines the number of positive words correctly recognized and positive words that do not belong to the third word group correctly identified according to the fourth test data set, obtains the fifth number, and determines the number of negative words correctly recognized and negative words that do not belong to the third word group correctly identified, obtains the sixth number, and then determines the fourth target characteristic value of the subject according to the fifth number and the sixth number, the fourth target characteristic value is used to measure the subject's judgment on the self-schema type, and then the subject can be evaluated whether the sixth type of psychological problem exists according to the fourth target characteristic value. The purpose of further enriching the test means of mental health problems is achieved, and the mental health status of the subject can be intelligently evaluated according to the obtained test data set.
[0019] In the second aspect of the present application, a mental health assessment device is also provided, including: an acquisition module for acquiring a first test data set of the subject under test, wherein the first test data set includes data on the reaction time of the subject under test to the test material presented in the test terminal device; a processing module for performing invalidation processing on the first test data set to obtain a target data set; an acquisition module for obtaining a first target feature value of the subject under test based on the target data set; and an evaluation module for evaluating the mental health status of the subject under test based on the first target feature value.
[0020] In a third aspect of the present application, an electronic device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, any one of the above methods is implemented.
[0021] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any of the above-described methods is executed.
[0022] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. It realizes obtaining the data of the reaction time of the subject under test to the test material through the test terminal device, avoiding the problem of low accuracy of the test results caused by the subject under test often avoiding or lying in the form of an evaluation questionnaire in the related technology. At the same time, the technical solution also processes some invalid data in the first test data set, so the accuracy of the target data set obtained is higher, and the purpose of intelligently evaluating the mental health status of the subject under test is achieved, achieving the effect of improving the user experience. 2. By obtaining various test data sets of the subject under test, and then intelligently evaluating whether the subject under test has psychological problems, the purpose of enriching the test methods for mental health problems is achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 It is a flowchart of a mental health assessment method provided in an embodiment of the present application;
[0024] Figure 2 This is a schematic diagram of the process of the mental health assessment method provided in the embodiment of the present application. Figure 1 ;
[0025] Figure 3 This is a schematic diagram of the process of the mental health assessment method provided in the embodiment of the present application. Figure 2 ;
[0026] Figure 4 This is a schematic diagram of the process of the mental health assessment method provided in the embodiment of the present application. Figure 3 ;
[0027] Figure 5 This is a schematic diagram of the process of the mental health assessment method provided in the embodiment of the present application. Figure 4 ;
[0028] Figure 6 This is a schematic diagram of the process of the mental health assessment method provided in the embodiment of the present application. Figure 5 ;
[0029] Figure 7 This is a schematic diagram of the process of the mental health assessment method provided in the embodiment of the present application. Figure 6 ;
[0030] Figure 8 is a structural schematic diagram of a mental health detection system provided in an embodiment of the present application;
[0031] Fig. 9 It is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application.
[0032] Description of the reference numerals: 900 - electronic device; 901 - processor; 902 - communication bus; 903 - user interface; 904 - network interface; 905 - memory. DETAILED DESCRIPTION
[0033] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.
[0034] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.
[0035] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.
[0036] This application provides a method for mental health assessment, referring to Figure 1 , Figure 1 : is a flowchart of a mental health assessment method provided in an embodiment of the present application, comprising the following steps:
[0037] Step S101, obtaining a first test data set of a tested object, wherein the first test data set includes data of a reaction time of the tested object to a test material presented in a test terminal device;
[0038] Step S102, performing invalidation processing on the first test data set to obtain a target data set;
[0039] Step S103, obtaining a first target feature value of the object under test according to the target data set;
[0040] Step S104: Evaluate the mental health status of the subject based on the first target characteristic value.
[0041] Among them, the execution subject of the above steps can be a system, such as a mental health assessment system, or a testing system, or other terminal devices, but is not limited to this.
[0042] In the above embodiment, a first test data set of the tested object is obtained, wherein the first test data set includes data on the reaction time of the tested object to the test material presented in the test terminal device, and invalid data in the first test data set is processed to obtain a target data set; for example, the first test data set may be a data set obtained by the tested object in an implicit association test, such as data on the reaction time of the tested object to each group of concept words and attribute words, the first test data set may also be a data set obtained by the tested object in a test on the degree of attention to emotional words, such as data on the reaction time of the tested object to positive emotional words and negative emotional words, the first test data set may also be a data set obtained by the tested object in a test on the degree of attention to emotional faces, Such as the data of the reaction time of the subject to positive emotional faces and negative emotional faces; then the invalid data in the first data set is deleted to obtain the target data set, for example, some data with obviously abnormal or unreasonable reaction time in the first data set is eliminated, or some abnormal or unreasonable reaction time data is replaced with other reaction time data; then the first target feature value of the subject is extracted according to the target data set, for example, the feature value of the subject's implicit suicidal ideation can be extracted, or the feature value of the subject's emotional tendency can be extracted; then the mental health status of the subject is evaluated according to the first target feature value, for example, when the first target feature value is greater than a preset value or a preset standard range, it is considered that the subject has psychological problems. It is achieved that the data of the reaction time of the subject to the test material is obtained through the test terminal device, which avoids the problem of low accuracy of the test result caused by the subject often evading or lying in the form of an evaluation questionnaire in the related technology. At the same time, the technical solution also processes some invalid data in the first test data set, so that the obtained target data set has higher accuracy, and the corresponding first target feature value is extracted according to the target data set, and the mental health status of the subject can be evaluated according to the first target feature value, thereby achieving the purpose of intelligent evaluation of the mental health status of the subject and improving the user experience.
[0043] In an optional embodiment, obtaining a first test data set of the subject under test includes: obtaining a first data set of the subject under test in an implicit association test, wherein the first test data set includes a first data set, and the first data set includes data on the reaction time of the subject under test to multiple first phrases appearing on a test terminal device, and each phrase in the multiple first phrases includes a concept word and an attribute word associated with the concept word; invalidating the first test data set to obtain a target data set, including: removing data that meets a first preset condition in the first data set to obtain a target data set, wherein the data of the first preset condition is used to represent data with a reaction time greater than a preset first reaction time threshold or less than a preset second reaction time threshold, and the preset first reaction time threshold is greater than the preset second reaction time threshold; obtaining a first target feature value of the subject under test according to the target data set, including: determining a first Average reaction time, and determining a second average reaction time according to a second data subset, wherein the first data subset is data on the reaction time of the subjects included in the target data set for compatible tasks in an implicit association test, and the second data subset is data on the reaction time of the subjects included in the target data set for incompatible tasks in an implicit association test; obtaining a first eigenvalue according to the first average reaction time, the second average reaction time and a target standard deviation, wherein the target standard deviation refers to the standard deviation value of the reaction time corresponding to all data in the target data set, and the first target eigenvalue includes the first eigenvalue; evaluating the mental health status of the subject based on the first target eigenvalue, including: when the first eigenvalue is greater than a first preset threshold, judging that the subject has a first type of psychological problem; when the first eigenvalue is less than or equal to the first preset threshold, judging that the subject does not have a first type of psychological problem.
[0044] In the above embodiment, a first data set of the subject in an implicit association test is obtained, that is, the reaction time of the subject to each of a plurality of first phrases is tested, wherein each phrase includes a concept word and associated attribute words; for example, "self" is used as the concept word, and "death" and "alive" are used as attribute words, and the subject's implicit connection between them is tested respectively. In practical applications, the test can be divided into four stages, wherein the first and third stages are practice stages, and the second and fourth stages are formal test stages. The first and second stages are compatible tasks, and the third and fourth stages are incompatible tasks. Then, the reaction time of the test subject for each phrase in the compatible tasks and the incompatible tasks is obtained respectively. Then, the invalid data in the first data set is eliminated to obtain the target data set. The invalid data may be data that meets the first preset condition. For example, the data of the first preset condition is data whose reaction time is greater than the preset first reaction time threshold or less than the preset second reaction time threshold. This can achieve the purpose of eliminating the invalid data in the first data set, thereby achieving the purpose of ensuring the accuracy of the test data. For example, the preset first reaction time threshold is 10000ms (or other values), and the preset second reaction time threshold is 350ms (or other values). Then, the first data subset and the second data subset included in the target data set are determined. A data subset is data on reaction time for compatible tasks in an implicit association test, and a second data subset is data on reaction time for incompatible tasks in an implicit association test. A first average reaction time is determined based on the first data subset, and a second average reaction time is determined based on the second data subset, that is, the average reaction time of the tested object for compatible tasks and incompatible tasks is obtained, and then a first eigenvalue is obtained based on the first average reaction time, the second average reaction time and the target standard deviation. For example, the target standard deviation is the average reaction time of all data in the target data set. The first eigenvalue can be used to measure the implicit suicidal ideation of the tested object. Therefore, the first eigenvalue can be used to evaluate whether the tested object has a first type of psychological problem. For example, when the first eigenvalue is greater than a first preset threshold, it is judged that the tested object has a first type of psychological problem. When the first eigenvalue is less than or equal to the first preset threshold, it is judged that the tested object does not have a first type of psychological problem. The first preset threshold can be set according to actual needs. The purpose of obtaining the average reaction time of the tested object for compatible tasks and incompatible tasks, and then intelligently evaluating whether the tested object has a first type of psychological problem is achieved.
[0045] In an optional embodiment, a first test data set of the subject is obtained, including: obtaining a second data set in a test of the subject's attention to emotional words, wherein the first test data set includes the second data set, and the second data set includes data on the subject's reaction time to each word in a plurality of second phrases appearing on the test terminal device, and each phrase in the plurality of second phrases includes a positive emotional word and a negative emotional word; invalidating the first test data set to obtain a target data set, including: removing data in the second data set that meets a second preset condition to obtain a target data set, wherein the data of the second preset condition is used to represent data with a reaction time greater than a preset third reaction time threshold or less than a preset fourth reaction time threshold, and the preset third reaction time threshold is greater than the preset fourth reaction time threshold; obtaining the first target characteristic of the subject according to the target data set. The method comprises the following steps: determining a third average reaction time according to a third data subset and determining a fourth average reaction time according to a fourth data subset, wherein the third data subset is data on the reaction time of the subjects included in the target data set to positive emotional words in a test on the degree of attention to emotional words, and the fourth data subset is data on the reaction time of the subjects included in the target data set to negative emotional words in a test on the degree of attention to emotional words; obtaining a second eigenvalue according to the third average reaction time and the fourth average reaction time, wherein the first target eigenvalue includes the second eigenvalue; and evaluating the mental health status of the subjects based on the first target eigenvalue, comprising: when the second eigenvalue is less than a second preset threshold, judging that the subjects have a second type of psychological problem; and when the second eigenvalue is greater than or equal to the second preset threshold, judging that the subjects do not have a second type of psychological problem.
[0046] In the above embodiment, a second data set is obtained in a test of the subject's attention to emotional words, that is, the reaction time of the subject to each word in a plurality of second phrases is tested, wherein each phrase includes a positive emotional word and a negative emotional word, and it can also be that after a positive word or a negative word appears on the test terminal device (such as after the positive word or the negative word disappears), a gray dot randomly appears on the test terminal device, and the subject judges the position where the gray dot appears, so as to obtain the reaction time of the subject to the appearance of the dot after the positive emotional word, and obtain the reaction time of the subject to judge the appearance of the dot after the negative word. The embodiment of the present application does not limit the specific collection method of the reaction time; then, invalid data in the second data set is eliminated to obtain a target data set, and the invalid data can be data that meets the second preset condition. For example, the data of the second preset condition is data with a reaction time greater than a preset third reaction time threshold or less than a preset fourth reaction time threshold, so as to achieve the purpose of eliminating the invalid data in the second data set, thereby achieving the purpose of ensuring the accuracy of the test data. For example, the preset third reaction time threshold is 3000ms (or other values), and the preset fourth reaction time threshold is 4000ms (or other values). The reaction time threshold is 300ms (or other values); then, determine the third data subset and the fourth data subset included in the target data set, the third data subset is the data of the reaction time to positive emotional words in the test of the degree of attention to emotional words, and the fourth data subset is the data of the reaction time to negative emotional words in the test of the degree of attention to emotional words, and determine the third average reaction time based on the third data subset, and determine the fourth average reaction time based on the fourth data subset, that is, obtain the average reaction time of the tested object to positive emotional words and negative emotional words, and then calculate the average reaction time of the tested object based on the third average reaction time and the fourth average reaction time. The second characteristic value is obtained by the reaction time. For example, the second characteristic value is the difference between the third average reaction time and the fourth average reaction time. The second characteristic value can be used to measure the emotional tendency of the subject, that is, to measure whether the subject has a negative emotional tendency or a positive emotional tendency. Therefore, the second characteristic value can be used to evaluate whether the subject has a second type of psychological problem. For example, when the second characteristic value is less than the second preset threshold, it is judged that the subject has a second type of psychological problem. When the second characteristic value is greater than or equal to the second preset threshold, it is judged that the subject does not have a second type of psychological problem. The second preset threshold can be set according to actual needs. The purpose of obtaining the average reaction time of the subject to positive emotional words and negative emotional words, and then intelligently evaluating whether the subject has a second type of psychological problem is achieved.
[0047] In an optional embodiment, obtaining a first test data set of the subject under test includes: obtaining a third data set in a test of the subject's attention to emotional faces, wherein the first test data set includes the third data set, and the third data set includes data on the subject's reaction time to multiple face groups appearing on the test terminal device, and each of the multiple face groups includes a positive emotional face and a negative emotional face; invalidating the first test data set to obtain a target data set, including: eliminating data that meets a third preset condition in the third data set to obtain a target data set, wherein the data of the third preset condition is used to represent data with a reaction time greater than a preset fifth reaction time threshold or less than a preset sixth reaction time threshold, and the preset fifth reaction time threshold is greater than the preset sixth reaction time threshold; obtaining a first target feature value of the subject under test according to the target data set, The method comprises: determining a fifth average reaction time according to a fifth data subset, and determining a sixth average reaction time according to a sixth data subset, wherein the fifth data subset is data on the reaction time of the subjects included in the target data set to positive emotional faces in a test of the degree of attention to emotional faces, and the sixth data subset is data on the reaction time of the subjects included in the target data set to negative emotional faces in a test of the degree of attention to emotional faces; obtaining a third eigenvalue according to the fifth average reaction time and the sixth average reaction time, wherein the first target eigenvalue includes the third eigenvalue; evaluating the mental health status of the subject based on the first target eigenvalue, comprising: when the third eigenvalue is less than a third preset threshold, judging that the subject has a third type of psychological problem; when the third eigenvalue is greater than or equal to the third preset threshold, judging that the subject does not have a third type of psychological problem.
[0048] In the above embodiment, a third data set is obtained in a test of the degree of attention paid to emotional faces by the subject, that is, the reaction time of the subject to each emotional face (referring to emotional face pictures) in a plurality of emotional face groups is tested, wherein each emotional face group includes a positive emotional face and a negative emotional face, and it can also be that after a positive emotional face or a negative emotional face appears on the test terminal device (such as after the positive emotional face or the negative emotional face disappears), a gray dot randomly appears on the test terminal device, and the subject judges the position where the gray dot appears, so as to obtain the reaction time of the subject to judge the appearance of the dot after the positive emotional face, and obtain the reaction time of the subject to judge the appearance of the dot after the negative emotional face. The embodiment of the present application does not limit the specific collection method of the reaction time; then, invalid data in the third data set is eliminated to obtain a target data set, and the invalid data can be data that meets the third preset condition, for example, the data of the second preset condition is data with a reaction time greater than the preset fifth reaction time threshold or less than the preset sixth reaction time threshold, so as to achieve the purpose of eliminating the invalid data in the third data set, thereby achieving the purpose of ensuring the accuracy of the test data, for example, the preset fifth reaction time threshold The time threshold is 3000ms (or other values), and the sixth reaction time threshold is preset to be 300ms (or other values); then, the fifth data subset and the sixth data subset included in the target data set are determined, the fifth data subset is the data of the reaction time to positive emotional faces in the test of emotional face attention, and the sixth data subset is the data of the reaction time to negative emotional faces in the test of emotional face attention, and the fifth average reaction time is determined according to the fifth data subset, and the sixth average reaction time is determined according to the sixth data subset, that is, the respective average reaction times of the tested subjects to positive emotional faces and negative emotional faces are obtained. The third eigenvalue is obtained based on the average reaction time of the fifth average reaction time and the sixth average reaction time. For example, the third eigenvalue is the difference between the fifth average reaction time and the sixth average reaction time. The third eigenvalue can be used to measure the degree of the emotional tendency of the subject. Therefore, the third eigenvalue can be used to evaluate whether the subject has a third type of psychological problem. For example, when the third eigenvalue is less than the third preset threshold, it is judged that the subject has a third type of psychological problem. When the third eigenvalue is greater than or equal to the third preset threshold, it is judged that the subject does not have a third type of psychological problem. The third preset threshold can be set according to actual needs. The purpose of obtaining the average reaction time of the subject to positive emotional faces and negative emotional faces, and then intelligently evaluating whether the subject has a third type of psychological problem is achieved. The purpose of testing the emotional tendency of the subject by different means is achieved.
[0049] In an optional embodiment, after evaluating the mental health status of the subject under test based on the first target feature value, the above method also includes: obtaining a second test data set of the subject under test, wherein the second test data set includes data of the subject under test identifying a group of neutral expression pictures on the test terminal device as positive pictures or negative pictures; obtaining a first number and a second number according to the second test data set, wherein the first number is used to represent the number of pictures that the subject under test identifies as positive pictures, and the second number is used to represent the number of pictures that the subject under test identifies as negative pictures; obtaining a second target feature value of the subject under test according to the first number and the second number, wherein the second target feature value is used to represent the feature value of the subject under test's reaction tendency to neutral expression pictures; when the second target feature value is less than a fourth preset threshold, judging that the subject under test has a fourth type of psychological problem; when the second target feature value is greater than or equal to the fourth preset threshold, judging that the subject under test does not have a fourth type of psychological problem.
[0050] In the above embodiment, a second test data set of the subject under test can also be obtained, wherein the second test data set includes data that the subject under test identifies a group of neutral expression pictures on the test terminal device as positive pictures or negative pictures. In actual applications, expression pictures representing different emotions can be presented in sequence on the test terminal device to ask the subject under test to judge the emotion type of the pictures as an exercise. For example, the expression pictures include positive emotion pictures, negative emotion pictures and neutral pictures, and then a certain number (such as 20, or 50, or other numbers) of neutral pictures are selected to ask the subject under test to identify which type of emotion the pictures are; the first number of times the subject under test identifies a group of neutral expression pictures as positive pictures is determined respectively. The method comprises the following steps: a) determining a second number of a group of neutral expression pictures that the subject identifies as negative pictures; b) determining a second target feature value of the subject according to the first number and the second number, for example, the second target feature value is the difference between the first number and the second number, and the second target feature value is used to measure the subject's reaction tendency to neutral expression pictures, and then evaluating whether the subject has a fourth type of psychological problem according to the second target feature value, for example, when the second target feature value is less than the fourth preset threshold, the subject is judged to have a fourth type of psychological problem, and when the second target feature value is greater than or equal to the fourth preset threshold, the subject is judged to have no fourth type of psychological problem, and the fourth preset threshold can be set according to actual needs. The purpose of enriching the test methods for mental health problems is achieved.
[0051] In an optional embodiment, after evaluating the mental health status of the subject based on the first target characteristic value, the method further includes: obtaining a third test data set of the subject, wherein the third test data set includes data of the subject in a self-encoding recall test, the self-encoding recall test is used to indicate a test in which the subject inputs a target word in an input box of the test terminal device after judging whether multiple words appearing in sequence on the test terminal device match the subject, the multiple words including at least one positive word and at least one negative word; obtaining a third quantity and a fourth quantity according to the third test data set, wherein the third quantity is used to indicate the number of positive words in the target word among multiple words, and the fourth quantity is used to indicate the number of negative words in the target word among multiple words; obtaining a third target characteristic value of the subject according to the third quantity and the fourth quantity, wherein the third target characteristic value is used to indicate the characteristic value of the subject's bias towards self-recall; when the third target characteristic value is less than the fifth preset threshold, judging that the subject has a fifth type of psychological problem; when the third target characteristic value is greater than or equal to the fifth preset threshold, judging that the subject does not have a fifth type of psychological problem.
[0052] In the above embodiment, a third test data set of the subject can also be obtained, wherein the third test data set includes data of the subject in a self-encoding recall test, that is, after the subject judges whether a plurality of words appearing in sequence on the test terminal device are consistent with the subject, the relevant data of the target word is input into the input box of the test terminal device, that is, the self-recall data of the subject for positive words and negative words is obtained, and then the third number of recalled positive words and the fourth number of recalled negative words are determined respectively. In actual application, some words (including positive words and negative words) can be presented in sequence on the test terminal device first, and the subject is required to judge whether each word is consistent with the description of himself, and then the test is ended. Then, the subject is asked to write down as many words as possible that have just been presented in the input box of the test terminal device, and then the third number and the fourth number are determined respectively; the third target characteristic value of the subject is determined according to the third number and the fourth number, for example, the third target characteristic value is the difference between the third number and the fourth number, and the third target characteristic value is used to measure the self-recall bias of the subject, and then the third target characteristic value can be used to evaluate whether the subject has the fifth type of psychological problem. For example, when the third target characteristic value is less than the fifth preset threshold, it is judged that the subject has the fifth type of psychological problem, and when the third target characteristic value is greater than or equal to the fifth preset threshold, it is judged that the subject does not have the fifth type of psychological problem. The above fifth preset threshold can be set according to actual needs. The purpose of enriching the test methods for mental health problems is achieved.
[0053] In an optional embodiment, after evaluating the mental health status of the subject based on the first target feature value, the method further includes: obtaining a fourth test data set of the subject, wherein the fourth test data set includes data of the subject in a self-encoding recognition test, the self-encoding recognition test being used to indicate that within a preset time after each word in the third phrase is presented in sequence on the test terminal device, the subject reconfirms whether each word in the fourth phrase presented in the terminal device belongs to the words in the third phrase, and there is at least one identical positive word and at least one identical negative word in the third phrase and the fourth phrase; obtaining a fifth quantity and a sixth quantity according to the fourth test data set, wherein the fifth quantity The number includes the sum of the number of positive words in the fourth phrase belonging to the third phrase and the number of correctly identified positive words in the fourth phrase that do not belong to the third phrase, and the sixth number includes the sum of the number of negative words in the fourth phrase belonging to the third phrase and the number of correctly identified negative words in the fourth phrase that do not belong to the third phrase; the fourth target characteristic value of the subject is obtained according to the fifth and sixth quantities, wherein the fourth target characteristic value is used to represent the characteristic value of the subject's judgment on the self-schema type; when the fourth target characteristic value is less than the sixth preset threshold, it is judged that the subject has the sixth type of psychological problem; when the fourth target characteristic value is greater than or equal to the sixth preset threshold, it is judged that the subject does not have the sixth type of psychological problem.
[0054] In the above embodiment, a fourth test data set of the subject can also be obtained, wherein the fourth test data set includes data of the subject in the self-encoding recognition test, that is, after the subject presents each word in the third word group on the test terminal device in sequence, the subject reconfirms whether each word in the fourth word group presented on the test terminal device belongs to the word in the third word group within a preset time period, and the number of positive words correctly recognized and positive words correctly identified as not belonging to the third word group is determined according to the fourth test data set to obtain a fifth number, and the number of negative words correctly recognized and negative words correctly identified as not belonging to the third word group is determined to obtain a sixth number. In actual applications, some words (including positive words and negative words) can be randomly presented on the test terminal device first. Vocabulary), requiring the tested subject to judge whether each vocabulary is consistent with the description of himself, or a mathematical expression can be presented, requiring the tested subject to judge the result of the operation; after a preset time (such as 1 minute, or 3 minutes, or other time), some words (including positive words and negative words) are presented on the test terminal device, asking the tested subject to judge whether these words have appeared before, and then determine the fifth quantity and the sixth quantity respectively; then determine the fourth target characteristic value of the tested subject according to the fifth quantity and the sixth quantity, for example, the fourth target characteristic value is the difference between the correct rate of positive word recognition and the correct rate of negative word recognition, and the fourth target characteristic value is used to measure the tested subject's judgment on the type of self-schema, and then the tested subject can be evaluated whether the sixth type of psychological problem exists according to the fourth target characteristic value. The purpose of further enriching the test means of mental health problems is achieved, and the mental health status of the tested subject can be intelligently evaluated according to the obtained test data set.
[0055] It should be noted that the above-described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application will be described in detail below in conjunction with specific embodiments.
[0056] The present application provides an artificial intelligence-based mental health assessment cognitive level detection system, and provides an artificial intelligence-based mental health assessment method, for example, taking a suicide assessment detection system as an example for illustration.
[0057] The biggest advantage of psychological behavioral experiments is the concealment of their test purpose, which can reduce the subjectivity, concealment and social approval of the tester, thereby effectively improving the reliability and accuracy of the test. At the same time, it avoids the limitation of single text selection, enriches the means of testing, and thus reduces the resistance and fatigue of the subjects.
[0058] Implicit association test, emotion experiment and self-encoding task test have important clinical significance for screening suicidal tendencies. Individuals with positive results (having implicit suicidal ideation and / or negative emotion bias and / or negative self-schema) have a significantly increased suicide rate.
[0059] This system conducts standardized tests on individuals with suicidal tendencies. The test results show that the internal consistency validity of the six experiments is good (0.89-0.94), and the correlation with the Beck Suicidal Ideation Inventory (BSI) is high (0.57-0.70). Randomized controlled studies have found that based on the BSI score, the subjects were divided into an explicit ideation group and a control group. It was found that the subjects in the explicit suicidal ideation group and the control group had significant differences in the single-category implicit association test, emotional word point detection test, face point detection test, expression picture discrimination test, self-encoding recall test, and self-encoding recognition test (p<0.05).
[0060] This system can be used for both clinical and scientific research, and has the following advantages: ① The test terminal collects data efficiently; ② The host automatically analyzes data; ③ The original data is automatically entered into the database; ④ The data can be exported for easy integration and research.
[0061] refer to Figure 2 , the specific steps of how to extract individual characteristics in the first experimental stage in an artificial intelligence-based suicide assessment cognitive level detection system are described in detail.
[0062] The first experimental phase method will be used to measure individuals' implicit suicidal ideation.
[0063] Take "self" as the concept word, "death" and "alive" as the attribute words, and test the implicit connection between them respectively. This method is divided into four test stages, among which the first and third stages are the practice stages, and the second and fourth stages are the formal test stages.
[0064] The reaction time of the measured individuals to each concept word and attribute word in each stage is collected, and the trials with reaction time higher than 10000ms and lower than 350ms are judged and automatically deleted, and then the wrong reaction is replaced with the average reaction time of the correct reaction time in the test stage to which it belongs, and a penalty of 400ms is added on this basis. The first and second stages are compatible tasks, and the third and fourth stages are incompatible tasks. The difference between the average reaction time of the compatible task and the incompatible task is calculated, and then divided by the standard deviation of the reaction time of all correct reactions (excluding the original incorrect reactions) to generate the characteristics of the individuals to be processed in the first experimental stage and the characteristics set of the individuals to be processed in the first experimental stage.
[0065] After generating the feature set of individuals to be processed in the first experimental stage, it is necessary to preprocess the features of individuals to be processed in the first experimental stage to extract the features of individuals with suicidal ideation. Determine whether the feature value of individuals to be processed in the first experimental stage (represented by D) is greater than 0. For example, D is the difference between the average reaction time of the compatible task and the incompatible task calculated as above, divided by the standard deviation of the reaction time of all correct responses. If it is greater than 0, it means that there is implicit suicidal ideation, otherwise there is no implicit suicidal ideation. The larger the D value, the stronger the implicit suicidal ideation.
[0066] The values greater than 0 in the individual feature set to be processed in the first experimental stage are extracted in sequence to generate the individual features of the first experimental stage and the individual feature set of the first experimental stage. The individual feature can be an individual identifier, and the individual feature set can include identifiers of multiple individuals. The individual feature value can be understood as the test result of the individual in this experimental stage.
[0067] The principle of the test method in the first experimental stage is based on the neural network model. The model believes that information is organized at the nodes of neural connections according to semantic layers, and the distance between the nodes is used to evaluate the connection between two concepts (information). When two concepts are closely connected, people tend to make consistent responses; when the two concepts are not closely connected or even conflicting, it is difficult for people to make consistent responses. By measuring the evaluative connection between concept words and attribute words, the implicit cognitive tendency of individuals can be indirectly measured.
[0068] The following references Figure 3 , the specific steps of how to extract individual characteristics of the second experimental phase in an artificial intelligence-based suicide assessment cognitive level detection system are described in detail.
[0069] The second experimental phase method will be used to measure the degree of attention paid to the emotion words by individuals in the first experimental phase.
[0070] In the first experimental stage, when individuals are in different psychological states, they will have different degrees of attention bias towards different emotional information, that is, they are more inclined to process emotional information corresponding to their emotional state. According to this principle, the current emotional state of an individual can be judged by the attention bias of the individual in processing emotional information, thus laying the foundation for providing targeted psychological intervention.
[0071] In the second experimental stage, emotional words (one is a positive word and the other is a negative word) will appear on both sides of the screen for 800ms at the same time. After they disappear, a small gray dot will appear randomly on both sides of the screen, and the individual will judge where it appears. The first stage is the test stage, and the second stage is the formal stage. The reaction time of the measured individual to each positive word and negative word in each stage is collected, and the individual characteristics of error trials and reaction times higher than 3000ms and lower than 300ms are deleted. The average reaction time of the dot after the negative emotional words (A average reaction time) and the reaction time after the positive emotional words (B average reaction time) are calculated respectively. After calculating the difference (AB), the individual characteristics to be processed in the second experimental stage and the individual characteristics set to be processed in the second experimental stage are generated.
[0072] The average reaction time of A indicates the degree of attention paid to negative emotional words; the average reaction time of B indicates the degree of attention paid to positive emotional words; judge whether the characteristic value (AB) of each individual to be processed in the second experimental stage is less than 0. If it is less than 0, it indicates that the individual currently has a negative emotional tendency. If it is equal to 0, it indicates that the individual has no obvious emotional tendency. If it is greater than 0, it indicates that the individual currently has a positive emotional tendency.
[0073] The values less than 0 in the individual feature set to be processed in the second experimental stage are extracted in sequence to generate the individual features of the second experimental stage and the individual feature set of the second experimental stage.
[0074] refer to Figure 4 , the specific steps of how to extract individual characteristics of the third experimental stage in an artificial intelligence-based suicide assessment cognitive level detection system are described in detail.
[0075] The third experimental phase method will be used to measure the degree of attention paid by individuals to emotional faces in the second experimental phase.
[0076] In the second experimental stage, when individuals are in different psychological states, they will have different degrees of attention bias towards faces with different emotions, that is, they are more inclined to pay attention to the emotional faces corresponding to the current state. According to this principle, the current emotional state of the individual can be judged by the attention bias of the individual in processing faces, thus laying the foundation for providing targeted psychological intervention.
[0077] In the third experimental stage, the experimental materials are from the Chinese facial expression image stimulus library. Face images (one is a positive emotion face and the other is a negative emotion face) will appear on both sides of the screen for 800ms at the same time, and the ratio of male and female face images is 1:1. After the face image disappears, a small gray dot will appear randomly on both sides of the screen, and the individual will judge where it appears. The first stage is the test stage, and the second stage is the formal stage. The reaction time of the measured individual to each positive emotion face and negative emotion face in each stage will be collected, and the individual features with wrong trials and reaction times higher than 3000ms and lower than 300ms will be deleted. The average reaction time (E reaction average time) of the dot appearing behind the negative emotion face and the reaction time (F reaction average time) behind the positive emotion face will be calculated respectively. After calculating the difference (EF), the individual features to be processed in the third experimental stage and the individual feature set to be processed in the third experimental stage will be generated.
[0078] The average E reaction time indicates the degree of attention paid to negative emotional faces; the average F reaction time indicates the degree of attention paid to positive emotional faces; the eigenvalue (EF) of each individual to be treated in the third experimental stage is judged to be less than 0. If it is less than 0, it indicates that the individual currently has a negative emotional tendency. If it is equal to 0, it indicates that the individual has no obvious emotional face preference. If it is greater than 0, it indicates that the individual currently has a positive emotional tendency.
[0079] The values less than 0 in the individual feature set to be processed in the third experimental stage are extracted in sequence to generate the individual features of the third experimental stage and the individual feature set of the third experimental stage.
[0080] refer to Figure 5 , the specific steps of how to extract individual characteristics of the fourth experimental stage in an artificial intelligence-based suicide assessment cognitive level detection system are described in detail.
[0081] The fourth experimental phase method will be used to measure the third experimental phase individuals' ability to identify expression pictures.
[0082] In the third experimental stage, when individuals are in different psychological states, their processing of facial expressions is a combination of subjective and objective factors. That is, the individual's own emotional state will also affect the judgment of the facial expression itself. The facial expression picture discrimination experimental method judges the individual's current emotional state through the individual's discrimination of neutral facial expression pictures. Another feature of the method in this experimental stage is that it does not require text processing and can be applied to individuals with low cultural level.
[0083] The fourth experimental phase method will be used to measure the degree of attention paid to emotional faces by individuals in the second experimental phase.
[0084] In the fourth experimental stage method, facial expressions representing different emotions are presented in the center of the screen, divided into negative, neutral and positive. Individuals are required to judge the emotional type of the picture and make corresponding key responses. The first stage is the practice stage, and the second stage is the formal test stage. Among the 20 neutral pictures, the number of individuals who make positive reactions to the pictures (represented by J) and the number of individuals who make negative reactions (represented by K) are judged respectively. After calculating the difference (JK), the characteristics of the individuals to be processed in the fourth experimental stage and the characteristics set of the individuals to be processed in the fourth experimental stage are generated.
[0085] Positive reaction indicates the tendency to judge neutral pictures as positive pictures; negative reaction indicates the tendency to judge neutral pictures as negative pictures; judge whether the characteristic value (JK) of each individual to be processed in the fourth experimental stage is less than 0. If it is less than 0, it indicates that the individual currently tends to make a negative reaction. If it is equal to 0, it indicates that the individual has no obvious reaction tendency. If it is greater than 0, it indicates that the individual currently tends to make a positive reaction.
[0086] The values less than 0 in the individual feature set to be processed in the fourth experimental stage are extracted in sequence to generate individual features of the fourth experimental stage and the individual feature set of the fourth experimental stage.
[0087] refer to Figure 6 , the specific steps of how to extract individual characteristics of the fifth experimental stage in an artificial intelligence-based suicide assessment cognitive level detection system are described in detail.
[0088] The fifth experimental phase methods will be used to measure the self-encoding recall of individuals in the fourth experimental phase.
[0089] In the fourth experimental stage, when individuals are in different psychological states, they will be tested for self-encoding and recall. Among them, self-schema is a cognitive structure that affects individuals' encoding, storage and retrieval of information about themselves. It is an individual's internal description, understanding and application of specific things. When individuals face the outside world, schema is the main mechanism that affects individuals' processing of external information. Self-schema is formed in the process of processing relevant personal information, and the formed self-schema strongly affects individuals' cognition and behavior. The self-schema stored in the memory bank is not a passive memory representation. It has a mechanism for actively constructing information, which determines the selection of available information in the environment, the extraction, interpretation and synthesis of the meaning of information, and how to process information.
[0090] The information processing of self-schema has the following characteristics: ① It is highly sensitive to stimuli related to the self; ② It processes stimuli that are suitable for self-characteristics very quickly and with high confidence; ③ It can produce better recall and recognition of stimuli related to the self; ④ It has a high degree of confidence in predicting, attributing and inferring self-related behaviors; ⑤ It processes stimuli that are consistent with the self more effectively, and resists information that is inconsistent with the self-structure.
[0091] In the fifth experimental stage, some words (positive or negative) will be presented on the screen in sequence, and the individual is required to judge whether the words match the description of himself. Then, 500 minus 3 consecutive subtractions will be performed for 3 minutes. After completion, write down as many words as possible in the input box.
[0092] Calculation method: ① Calculate the positive and negative words that are correctly recalled separately; ② Calculate the recall bias.
[0093] Note: Recall bias = the number of positive words correctly recalled - the number of negative words correctly recalled.
[0094] The recall bias of the individual features of the fifth experimental stage is extracted in turn to generate the individual features to be processed in the fifth experimental stage and the individual feature set to be processed in the fifth experimental stage.
[0095] Determine whether the characteristics of the individuals to be treated in the fifth experimental stage are less than 0. If they are less than 0, it indicates that the individual has a negative self-schema. If they are equal to 0, it indicates that the individual has a neutral self-schema. If they are greater than 0, it indicates that the individual has a positive self-schema.
[0096] The values less than 0 in the individual feature set to be processed in the fifth experimental stage are extracted in sequence to generate individual features of the fifth experimental stage and the individual feature set of the fifth experimental stage.
[0097] refer to Figure 7 , the specific steps of how to extract individual characteristics of the sixth experimental stage in an artificial intelligence-based suicide assessment cognitive level detection system are described in detail.
[0098] The sixth experimental phase method will be used to measure the fifth experimental phase individuals to test their self-encoding recognition.
[0099] This paradigm was first created by Craik and Tulving. In SRET, emotional adjectives are presented to the subjects one by one, and the subjects are asked to judge whether the adjective can describe themselves. After all the adjectives are presented, a non-random recall task is conducted, requiring the subjects to recall all the adjectives just presented. The main indicators are recognition, recall, and reaction time. SRET believes that information consistent with the content of the self-schema has high self-recognition, fast processing speed, and good recall effect.
[0100] In the sixth experimental phase, the method of selecting test variables was innovated. The self-schema type of individuals was examined by recognition, so that individuals who were unwilling or unable to input Chinese characters could get the opportunity to be tested. First, mathematical expressions and four-character words (positive or negative) were randomly presented at the top or bottom of the screen at the same time, and the individuals were asked to judge whether the calculation results were correct. After that, a recognition test was conducted to determine whether the words on the screen had just appeared.
[0101] Calculation method: Calculate the recognition accuracy of positive vocabulary and negative vocabulary separately.
[0102] Note: Recognition accuracy = (correct recognition + correct rejection) / 24.
[0103] The recognition accuracy rates of the individual features of the sixth experimental stage are extracted in sequence to generate the individual features to be processed in the sixth experimental stage and the individual feature set to be processed in the sixth experimental stage.
[0104] Determine whether the positive word recognition accuracy rate of the individual characteristics to be treated in the sixth experimental stage is less than the negative word recognition accuracy rate. If it is less than, it indicates that the individual has a negative self-schema. If they are equal, it indicates that the individual has a neutral self-schema. If it is greater than, it indicates that the individual has a positive self-schema.
[0105] refer to Figure 8 ,Schematic diagram of the structure of a mental health detection system based on artificial intelligence.
[0106] This system is divided into a test terminal and a host. The tester performs the test at the test terminal, and the data is recorded, including the keystroke response, correctness, reaction time, and text records on the handwriting board for each trial. All data is uploaded to the host according to the tester's serial number. The host establishes a corresponding database, obtains the results of each experiment through calculation, and feeds the results back to the test terminal, so that the tester can understand his or her psychological state in a timely manner.
[0107] Separating the test terminal from the host helps to test multiple subjects at the same time without time and space constraints, broadening the application scope of the system. In addition, all data are processed on the host, which is conducive to data confidentiality.
[0108] The tester can browse the overview, test methods and result determination methods of each experiment in turn on the experiment introduction interface. According to the needs of the subject, select the corresponding experiment. The experiments will be presented in turn, and the subject will respond by pressing the buttons (left, right) according to the instructions. The system integrates mature psychological experimental methods with modern information technology, and can systematically and accurately scan the individual's psychological activity state.
[0109] The suicide assessment cognitive level detection system mainly includes six psychological behavioral experimental stages: ① The first experimental stage is the implicit association test; ② The second experimental stage is the emotional word point detection experiment; ③ The third experimental stage is the face point detection experiment; ④ The fourth experimental stage is the expression picture discrimination experiment; ⑤ The fifth experimental stage is the self-encoding recall test; ⑥ The sixth experimental stage is the self-encoding recognition test. The above experimental items are all derived from mature psychological paradigms or based on mature psychological theories, and have high reliability and validity.
[0110] It should be noted that the above embodiment is an optional embodiment. In actual applications, the above six experimental stages do not have a strict order. Optionally, only some of the experimental stages can be selected to test individuals. Of course, testing in the six experimental stages in the above embodiment in sequence can obtain better test results and can also more effectively improve the accuracy of the test or evaluation.
[0111] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.
[0112] The present application also provides a mental health assessment device, which includes: an acquisition module for acquiring a first test data set of a test subject, wherein the first test data set includes data on the reaction time of the test subject to a test material presented in a test terminal device; a processing module for performing invalidation processing on the first test data set to obtain a target data set; an acquisition module for obtaining a first target feature value of the test subject based on the target data set; and an evaluation module for evaluating the mental health status of the test subject based on the first target feature value.
[0113] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.
[0114] The present application also provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed, any one of the method steps described above is executed.
[0115] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.
[0116] The present application also discloses an electronic device. Fig. 9 As shown, Fig. 9 The electronic device 900 may include: at least one processor 901 , at least one network interface 904 , a user interface 903 , a memory 905 , and at least one communication bus 902 .
[0117] The communication bus 902 is used to realize the connection and communication between these components.
[0118] The user interface 903 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 903 may also include a standard wired interface and a wireless interface.
[0119] The network interface 904 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).
[0120] Among them, the processor 901 may include one or more processing cores. The processor 901 uses various interfaces and lines to connect various parts of the entire electronic device (such as a server), and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 905, and calling data stored in the memory 905. Optionally, the processor 901 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 901 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 901, and it can be implemented separately through a chip.
[0121] Among them, the memory 905 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 905 includes a non-transitory computer-readable storage medium. The memory 905 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 905 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 905 may optionally also be at least one storage device located away from the aforementioned processor 901. Refer to Fig. 9 , the memory 905 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of a mental health assessment method.
[0122] exist Fig. 9 In the electronic device 900 shown, the user interface 903 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 901 can be used to call an application of a mental health assessment method stored in the memory 905. When executed by one or more processors 901, the electronic device 900 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.
[0123] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0124] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0125] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0126] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0127] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.
[0128] This application is intended to cover any modifications, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the technical field not recorded in the present disclosure.
Claims
1. A method for evaluating mental health, characterized in that: include: Acquire a first test data set of the subject, wherein the first test data set includes data of the reaction time of the subject to the test material presented in the test terminal device, and the test material includes emotional words and emotional face pictures; Performing invalidation processing on the first test data set to obtain a target data set; Obtaining a first target feature value of the object under test according to the target data set; Assessing the mental health status of the subject based on the first target feature value; Wherein, obtaining a first test data set of the subject includes: obtaining a second data set of the subject in a test of the degree of attention paid to emotional words, wherein the first test data set includes the second data set, and the second data set includes data of the reaction time of the subject to each word in a plurality of second phrases appearing on the test terminal device, and each phrase in the plurality of second phrases includes a positive emotional word and a negative emotional word; Invalidating the first test data set to obtain a target data set includes: removing data that meets a second preset condition from the second data set to obtain the target data set, wherein the data of the second preset condition is used to represent data whose reaction time is greater than a preset third reaction time threshold or less than a preset fourth reaction time threshold, and the preset third reaction time threshold is greater than the preset fourth reaction time threshold; Obtaining a first target characteristic value of the subject according to the target data set, including: determining a third average reaction time according to a third data subset, and determining a fourth average reaction time according to a fourth data subset, wherein the third data subset is data on the reaction time of the subject to positive emotional words in the test of the degree of attention to emotional words included in the target data set, and the fourth data subset is data on the reaction time of the subject to negative emotional words in the test of the degree of attention to emotional words included in the target data set; obtaining a second characteristic value according to the third average reaction time and the fourth average reaction time, the second characteristic value=the fourth average reaction time-the third average reaction time, wherein the first target characteristic value includes the second characteristic value; The method further comprises: evaluating the mental health status of the subject under test based on the first target characteristic value, comprising: when the second characteristic value is less than a second preset threshold, judging that the subject under test has a second type of psychological problem; when the second characteristic value is greater than or equal to the second preset threshold, judging that the subject under test does not have the second type of psychological problem, wherein the second type of psychological problem is used to indicate that the subject under test has a negative emotional tendency; Wherein, after evaluating the mental health status of the subject based on the first target feature value, the method further includes: Acquire a second test data set of the subject under test, wherein the second test data set includes data that the subject under test identifies a group of neutral expression pictures on the test terminal device as positive pictures or negative pictures; Obtaining a first number and a second number according to the second test data set, wherein the first number is used to represent the number of the group of neutral expression pictures identified as the positive pictures by the test subject, and the second number is used to represent the number of the group of neutral expression pictures identified as the negative pictures by the test subject; Obtaining a second target feature value of the measured object according to the first quantity and the second quantity, wherein the second target feature value=the first quantity-the second quantity, wherein the second target feature value is used to represent a feature value of the reaction tendency of the measured object to the neutral expression picture; When the second target characteristic value is less than the fourth preset threshold, it is judged that the subject has the fourth type of psychological problem; when the second target characteristic value is greater than or equal to the fourth preset threshold, it is judged that the subject does not have the fourth type of psychological problem, wherein the fourth type of psychological problem is used to indicate that the subject currently tends to have a negative reaction.
2. The method according to claim 1, characterized in that Acquiring a first test data set of the subject, including: acquiring a third data set of the subject in a test of the subject's attention to emotional faces, wherein the first test data set includes the third data set, and the third data set includes data of the subject's reaction time to multiple face groups appearing on the test terminal device, each of the multiple face groups includes a positive emotion face and a negative emotion face; Invalidating the first test data set to obtain a target data set includes: removing data that meets a third preset condition from the third data set to obtain the target data set, wherein the data of the third preset condition is used to represent data whose reaction time is greater than a preset fifth reaction time threshold or less than a preset sixth reaction time threshold, and the preset fifth reaction time threshold is greater than the preset sixth reaction time threshold; Obtaining a first target characteristic value of the measured object according to the target data set, including: determining a fifth average reaction time according to a fifth data subset, and determining a sixth average reaction time according to a sixth data subset, wherein the fifth data subset is data of the measured object's reaction time to positive emotional faces in the test of emotional face attention level included in the target data set, and the sixth data subset is data of the measured object's reaction time to negative emotional faces in the test of emotional face attention level included in the target data set; obtaining a third characteristic value according to the fifth average reaction time and the sixth average reaction time, the third characteristic value=the sixth average reaction time-the fifth average reaction time, wherein the first target characteristic value includes the third characteristic value; The mental health status of the measured object is evaluated based on the first target characteristic value, including: when the third characteristic value is less than the third preset threshold, judging that the measured object has the third type of psychological problem; when the third characteristic value is greater than or equal to the third preset threshold, judging that the measured object does not have the third type of psychological problem, wherein the third type of psychological problem is used to indicate that the measured object has a tendency towards negative emotions.
3. The method according to any one of claims 1 to 2, characterized in that After evaluating the mental health status of the subject based on the first target feature value, the method further includes: Acquire a third test data set of the subject, wherein the third test data set includes data of the subject in a self-encoding recall test, wherein the self-encoding recall test is used to indicate a test in which the subject inputs a target word in an input box of the test terminal device after judging whether a plurality of words appearing sequentially on the test terminal device match the subject, wherein the plurality of words include at least one positive word and at least one negative word; Obtaining a third quantity and a fourth quantity according to the third test data set, wherein the third quantity is used to represent the number of positive words in the target vocabulary belonging to the multiple words, and the fourth quantity is used to represent the number of negative words in the target vocabulary belonging to the multiple words; Obtaining a third target characteristic value of the measured object according to the third quantity and the fourth quantity, wherein the third target characteristic value=the third quantity-the fourth quantity, wherein the third target characteristic value is used to represent the characteristic value of the measured object's self-recall bias; When the third target characteristic value is less than the fifth preset threshold, it is judged that the subject under test has the fifth type of psychological problem; when the third target characteristic value is greater than or equal to the fifth preset threshold, it is judged that the subject under test does not have the fifth type of psychological problem, wherein the fifth type of psychological problem is used to indicate that the subject under test has a negative self-schema.
4. The method according to any one of claims 1 to 2, characterized in that After evaluating the mental health status of the subject based on the first target feature value, the method further includes: Acquire a fourth test data set of the subject, wherein the fourth test data set includes data of the subject in a self-encoding recognition test, wherein the self-encoding recognition test is used to indicate that within a preset time period after each word in a third phrase is sequentially presented on the test terminal device, the subject reconfirms whether each word in a fourth phrase presented on the terminal device belongs to the words in the third phrase, and the third phrase and the fourth phrase have at least one identical positive word and at least one identical negative word; Obtaining a fifth quantity and a sixth quantity according to the fourth test data set, wherein the fifth quantity includes the sum of the number of positive words in the fourth phrase belonging to the third phrase and the number of correctly identified positive words in the fourth phrase that do not belong to the third phrase, and the sixth quantity includes the sum of the number of negative words in the fourth phrase belonging to the third phrase and the number of correctly identified negative words in the fourth phrase that do not belong to the third phrase; Obtaining a fourth target characteristic value of the subject according to the fifth quantity and the sixth quantity, including: obtaining the correct rate of positive vocabulary recognition according to the fifth quantity, and obtaining the correct rate of negative vocabulary recognition according to the sixth quantity, the fourth target characteristic value=the correct rate of positive vocabulary recognition-the correct rate of negative vocabulary recognition, wherein the fourth target characteristic value is used to represent the characteristic value of the subject's judgment of the self-schema type; When the fourth target characteristic value is less than the sixth preset threshold, it is judged that the subject has the sixth type of psychological problem; when the fourth target characteristic value is greater than or equal to the sixth preset threshold, it is judged that the subject does not have the sixth type of psychological problem, wherein the sixth type of psychological problem is used to indicate that the subject has a negative self-schema.
5. A mental health assessment device, characterized in that: include: An acquisition module, configured to acquire a first test data set of a test subject, wherein the first test data set includes data of the reaction time of the test subject to a test material presented in a test terminal device, wherein the test material includes emotional words and emotional face pictures; A processing module, used for performing invalidation processing on the first test data set to obtain a target data set; An acquisition module, used for obtaining a first target characteristic value of the measured object according to the target data set; An evaluation module, used for evaluating the mental health status of the subject based on the first target feature value; The acquisition module is used to acquire a first test data set of the subject in the following manner: acquiring a second data set of the subject in a test of the degree of attention to emotional words, wherein the first test data set includes the second data set, and the second data set includes data on the reaction time of the subject to each word in a plurality of second phrases appearing on the test terminal device, and each phrase in the plurality of second phrases includes a positive emotional word and a negative emotional word; The processing module is used to obtain the target data set by: removing data that meets the second preset condition from the second data set to obtain the target data set, wherein the data of the second preset condition is used to represent data whose reaction time is greater than a preset third reaction time threshold or less than a preset fourth reaction time threshold, and the preset third reaction time threshold is greater than the preset fourth reaction time threshold; The acquisition module is used to obtain the first target characteristic value of the measured object in the following manner: determine the third average reaction time according to the third data subset, and determine the fourth average reaction time according to the fourth data subset, wherein the third data subset is the data of the reaction time of the measured object to positive emotional words in the test of the emotional word attention level included in the target data set, and the fourth data subset is the data of the reaction time of the measured object to negative emotional words in the test of the emotional word attention level included in the target data set; obtain the second characteristic value according to the third average reaction time and the fourth average reaction time, the second characteristic value=the fourth average reaction time-the third average reaction time, wherein the first target characteristic value includes the second characteristic value; The evaluation module is used to evaluate the mental health status of the measured object in the following manner: when the second characteristic value is less than a second preset threshold, it is judged that the measured object has a second type of psychological problem; when the second characteristic value is greater than or equal to the second preset threshold, it is judged that the measured object does not have the second type of psychological problem, wherein the second type of psychological problem is used to indicate that the measured object has a negative emotional tendency; The device is further configured to, after evaluating the mental health status of the subject based on the first target feature value, perform the following operations: Acquire a second test data set of the subject under test, wherein the second test data set includes data that the subject under test identifies a group of neutral expression pictures on the test terminal device as positive pictures or negative pictures; Obtaining a first number and a second number according to the second test data set, wherein the first number is used to represent the number of the group of neutral expression pictures identified as the positive pictures by the test subject, and the second number is used to represent the number of the group of neutral expression pictures identified as the negative pictures by the test subject; Obtaining a second target feature value of the measured object according to the first quantity and the second quantity, wherein the second target feature value=the first quantity-the second quantity, wherein the second target feature value is used to represent a feature value of the reaction tendency of the measured object to the neutral expression picture; When the second target characteristic value is less than the fourth preset threshold, it is judged that the subject has the fourth type of psychological problem; when the second target characteristic value is greater than or equal to the fourth preset threshold, it is judged that the subject does not have the fourth type of psychological problem, wherein the fourth type of psychological problem is used to indicate that the subject currently tends to have a negative reaction.
6. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the program, the method according to any one of claims 1 to 4 is implemented.
7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 4 is performed.
