Evaluation methods, devices, equipment and storage media for psychological assessment results

Abstract

This application discloses a method, apparatus, device, and storage medium for evaluating psychological assessment results. The evaluation method includes: obtaining assessment data filled out by an assessment subject in response to a psychological assessment questionnaire, as well as behavioral data of the assessment subject during the process of filling out the psychological assessment questionnaire; inputting the assessment data and behavioral data into a psychological state prediction model to obtain a predicted psychological state result of the assessment subject; and evaluating the psychological assessment result based on whether the psychological state prediction result is consistent with the psychological assessment result of the assessment subject. The psychological assessment result is a psychological assessment result obtained at least based on the assessment data. The method disclosed in this application can evaluate psychological assessment results to determine whether the psychological assessment results represent the true psychological state of the assessment subject.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, apparatus, device, and storage medium for evaluating psychological assessment results. Background Art

[0002] Currently, psychological assessments are conducted using questionnaires (such as questionnaires or freely written assessment questions). A good psychological assessment questionnaire should be both reliable and valid. Therefore, reliability and validity are important indicators for evaluating the quality of psychological assessment questionnaires. Reliability, in particular, is an indicator of the stability and consistency of psychological measurement results.

[0003] In actual testing, psychological assessments are always subject to error. This can lead to inaccurate results. Consequently, it's unclear whether the results obtained through psychological assessment questionnaires represent the subject's true psychological state. Summary of the Invention

[0004] The embodiments of the present application provide a method, apparatus, device, and storage medium for evaluating psychological assessment results, which can determine whether the psychological assessment results obtained through a psychological assessment questionnaire represent the true psychological state of the assessment subject.

[0005] On the one hand, embodiments of the present application provide a method for evaluating psychological assessment results, comprising:

[0006] Obtaining assessment data filled out by the assessment subject on the psychological assessment questionnaire, as well as behavioral data of the assessment subject in the process of filling out the psychological assessment questionnaire;

[0007] Inputting the evaluation data and the behavior data into a psychological state prediction model to obtain a psychological state prediction result of the evaluation subject;

[0008] The psychological evaluation result is evaluated according to whether the psychological state prediction result is consistent with the psychological evaluation result of the evaluation subject, and the psychological evaluation result is a psychological evaluation result obtained at least based on the evaluation data.

[0009] On the other hand, an embodiment of the present application provides an evaluation device for psychological assessment results, comprising:

[0010] The first acquisition module acquires the evaluation data filled out by the evaluation subject on the psychological evaluation questionnaire in that month, as well as the behavior data of the evaluation subject in the process of filling out the psychological evaluation questionnaire;

[0011] A data input module, configured to input the assessment data and the behavior data into a psychological state prediction model to obtain a psychological state prediction result of the assessment subject;

[0012] The evaluation module is used to evaluate the psychological evaluation result according to whether the psychological state prediction result is consistent with the psychological evaluation result of the evaluation object, and the psychological evaluation result is a psychological evaluation result obtained at least based on the evaluation data.

[0013] In another aspect, an embodiment of the present application provides a device for evaluating psychological assessment results, characterized in that the device includes: a processor and a memory storing computer program instructions;

[0014] When the processor executes the computer program instructions, the above-mentioned method for evaluating the psychological assessment results is implemented.

[0015] On the other hand, an embodiment of the present application provides a computer storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the above-mentioned method for evaluating psychological assessment results is implemented.

[0016] The evaluation method, device, equipment and storage medium of the psychological assessment results of the embodiment of the present application obtain the psychological state prediction result of the assessment subject through the psychological state prediction model. Since the data input into the psychological state prediction model includes not only the assessment data filled out by the assessment subject for the psychological assessment questionnaire, but also the behavioral data of the assessment subject in the process of filling out the psychological assessment questionnaire. Since the behavioral data of the assessment subject also reflects the psychological state of the assessment subject to a certain extent, the psychological state prediction model is a psychological state prediction result predicted based on the data of the assessment subject in various aspects. Therefore, the psychological state prediction result is relatively valuable for reference. Then, based on whether the psychological state prediction result is consistent with the psychological assessment result of the assessment subject, the psychological assessment result is evaluated to determine whether the psychological assessment result can represent the true psychological state of the assessment subject. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 This is a flowchart of an embodiment of a method for evaluating psychological assessment results provided by this application;

[0019] Figure 2 is a flowchart of an embodiment of the mental state prediction model of the present application;

[0020] Figure 3is a schematic diagram of an embodiment of data processing performed by the first data processing network of the present application;

[0021] Figure 4 is a schematic diagram of an embodiment of data processing performed by the second data processing network of the present application;

[0022] Figure 5 is a schematic diagram of an embodiment of data processing performed by the third data processing network of the present application;

[0023] Figure 6 This is a schematic structural diagram of an embodiment of a device for evaluating psychological assessment results provided by the present application;

[0024] Figure 7 This is a schematic diagram of the hardware structure of the evaluation equipment for the psychological assessment results provided by this application;

[0025] Figure 8 is a structural diagram of another embodiment of the device for evaluating psychological assessment results provided by the present application;

[0026] Figure 9 This is a structural diagram of an embodiment of a data acquisition module provided by the present application;

[0027] Figure 10 is a structural diagram of an embodiment of a storage module provided by the present application;

[0028] Figure 11 It is a structural diagram of another embodiment of the storage module provided by the present application. DETAILED DESCRIPTION

[0029] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present application by illustrating the examples of the present application.

[0030] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0031] When conducting psychological assessments, errors include random errors. These errors are caused by factors such as the subject's emotions during the assessment and external factors such as interference. The presence of errors in psychological assessments can lead to inaccurate results. Consequently, it's unclear whether the results obtained from psychological assessment questionnaires represent the subject's true psychological state.

[0032] To address the above technical issues, this application provides a method for evaluating psychological assessment results. In this method, assessment data from a subject's completed psychological assessment questionnaire, as well as behavioral data from the subject during the psychological assessment questionnaire, are obtained. This acquired data is then input into a psychological state prediction model to obtain a psychological state prediction result. Finally, once the psychological assessment result is obtained based on the assessment data from the subject's completed psychological assessment questionnaire, the psychological state prediction result and the psychological assessment result are compared for consistency, thereby evaluating the psychological assessment result.

[0033] Figure 1 This is a flow chart of an embodiment of the method for evaluating the psychological assessment results provided by this application. Figure 1 As shown, the evaluation methods for psychological assessment results include:

[0034] S102, obtaining the evaluation data filled out by the evaluation subject on the psychological evaluation questionnaire, as well as the behavior data of the evaluation subject in the process of filling out the psychological evaluation questionnaire.

[0035] In S102, while the electronic device is displaying the web page of the psychological assessment questionnaire, the assessment data filled in by the assessment subject can be collected in the background, and behavioral data such as the time the assessment subject spends filling in each question of the psychological assessment questionnaire, the number of times the assessment subject corrects each question, and the number of times the assessment subject looks back at the question after filling in each question can be collected.

[0036] Psychological assessment results are evaluated using:

[0037] S104: Input the assessment data and behavior data into a psychological state prediction model to obtain a psychological state prediction result of the assessment subject.

[0038] In S104, the psychological state prediction model can extract feature data for characterizing the psychological state characteristics of the evaluation subject from the evaluation data and behavior data, and then obtain the psychological state prediction result of the evaluation subject based on the feature data.

[0039] The prediction result of the psychological state of the evaluation subject may include: a first confidence level that the psychological state of the evaluation subject is in a normal state, and the first confidence level may represent the probability that the psychological state of the evaluation subject is in a normal state.

[0040] The predicted result of the subject's mental state may further include a second confidence level indicating that the subject is in an abnormal mental state. This second confidence level may indicate the probability that the subject is in an abnormal mental state. Since there are many types of abnormal mental states, the number of second confidence levels may be multiple. The predicted result of the subject's mental state may include the second confidence level indicating that the subject is in each type of abnormal mental state.

[0041] Assuming that abnormal psychological states include: compulsion, interpersonal sensitivity, depression, anxiety, and hostility, the predicted results of the psychological state of the evaluation subject may include: the confidence level that the evaluation subject has compulsive characteristics, the confidence level that the evaluation subject has interpersonal sensitivity, the confidence level that the evaluation subject is depressed, the confidence level that the evaluation subject is anxious, and the confidence level that the evaluation subject has hostile emotions.

[0042] Psychological assessment results are evaluated using:

[0043] S106, evaluating the psychological evaluation result based on whether the psychological state prediction result is consistent with the psychological evaluation result of the evaluation subject, wherein the psychological evaluation result is a psychological evaluation result obtained at least based on the evaluation data.

[0044] In S106, the psychological state prediction result is compared with the psychological assessment result of the subject to determine whether they are consistent. If the psychological state prediction result and the psychological assessment result of the subject are consistent, it can be determined that the psychological assessment result obtained through the psychological assessment questionnaire is accurate and can represent the true psychological state of the subject. If the psychological state prediction result and the psychological assessment result of the subject are inconsistent, it indicates that the psychological assessment result may be inaccurate and the subject's psychological state needs to be reassessed or another method needs to be used to assess the subject's psychological state.

[0045] In the embodiment of the present application, the data input into the psychological state prediction model includes not only the evaluation data filled out by the evaluation subject in response to the psychological evaluation questionnaire, but also the behavioral data of the evaluation subject during the process of filling out the psychological evaluation questionnaire. Since the evaluation subject's behavioral data also reflects the evaluation subject's psychological state to a certain extent, the psychological state prediction model is a psychological state prediction result predicted based on the evaluation subject's data from multiple aspects. Therefore, the psychological state prediction result is relatively valuable for reference. Then, based on whether the psychological state prediction result is consistent with the evaluation subject's psychological evaluation result, the psychological evaluation result is evaluated to determine whether the psychological evaluation result represents the evaluation subject's true psychological state.

[0046] In order to better illustrate the technical effects of the embodiments of the present application, a comparative example is provided below.

[0047] In the comparative examples of the related art, the physiological characteristics of the evaluation subject may be collected; and the psychological evaluation results may be evaluated based on the physiological characteristics.

[0048] However, since the solution in the comparative example relies on third-party equipment to collect the physiological characteristics of the evaluation subjects, it has significant limitations in application and promotion. In contrast, in the embodiment of the present application, the behavioral data of the evaluation subjects during the process of filling out the psychological evaluation questionnaire can be obtained in the background, without relying on third-party equipment to collect data, thus facilitating subsequent application and promotion.

[0049] On the other hand, due to the large differences in physiological characteristics between individuals, and the random errors inherent in physiological characteristics collected by third-party devices, evaluating psychological assessment results based on physiological characteristics with random errors will lead to fundamental errors in the evaluation results. However, in the embodiments of the present application, the behavioral data of the assessment subject can be obtained in the background without relying on third-party equipment to collect data, and the obtained behavioral data does not contain errors, thus making the evaluation of psychological assessment results more accurate.

[0050] On the other hand, the physiological characteristics in the comparative example are more susceptible to external factors, and therefore, the psychological assessment results based on physiological characteristics are less accurate. In contrast, in the embodiments of the present application, behavioral data is less susceptible to external factors than physiological characteristics, making the psychological assessment results based on behavioral data more accurate. For example, if a subject takes a certain medication, their heart rate will increase, but the behavioral data of the subject when filling out the questionnaire is basically unaffected by the medication.

[0051] In one or more embodiments of the present application, S106 may include:

[0052] Determining whether the psychological state of the subject in the psychological evaluation result matches at least one of the first confidence level and the second confidence level, and obtaining a matching result;

[0053] Based on the matching results, the psychological assessment results are evaluated.

[0054] In an embodiment of the present application, by determining whether the psychological state of the subject in the psychological evaluation result matches at least one of the first confidence level and the second confidence level, if there is no match, it indicates that the psychological evaluation result is inconsistent with the psychological state prediction result, and it is possible that the psychological evaluation result cannot represent the true psychological state of the subject, and further evaluation of the psychological state of the subject is required.

[0055] In one or more embodiments of the present application, evaluating the psychological assessment results based on the matching results may include:

[0056] When the matching result includes that the psychological state of the subject in the psychological evaluation result is normal, the first confidence level is less than the first preset threshold, and the maximum second confidence level is greater than the second preset threshold, then determining that the psychological evaluation result is inaccurate;

[0057] When the matching result includes that the psychological state of the subject is normal in the psychological evaluation result, the first confidence level is less than the first preset threshold, and the largest second confidence level is not greater than the second preset threshold, the psychological evaluation result is evaluated according to the difference between the largest second confidence level and the second largest second confidence level;

[0058] When the matching result includes that the psychological state of the evaluated subject in the psychological evaluation result is normal and the first confidence level is greater than the first preset threshold, the psychological evaluation result is determined to be accurate;

[0059] When the matching result includes that the psychological state of the evaluated subject in the psychological evaluation result is abnormal, and the first confidence level is greater than the first preset threshold, it is determined that the psychological evaluation result is inaccurate;

[0060] When the matching result includes that the psychological state of the evaluated subject in the psychological evaluation result is abnormal, the first confidence is less than the first preset threshold, and the maximum second confidence is greater than the second preset threshold, the psychological evaluation result is determined to be accurate.

[0061] The following is an example of whether the psychological assessment results match the psychological state prediction results.

[0062] As an example, when the matching result includes that the psychological state of the subject in the psychological assessment result is normal, and the first confidence level is less than a first preset threshold (such as 0.5), it means that the psychological state prediction model predicts that the psychological state of the subject has only a small probability of being normal.

[0063] In this case, further judgment is required based on the second maximum confidence level. The judgment results are divided into two cases:

[0064] The first scenario is when the maximum second confidence level is greater than the second preset threshold (e.g., 0.7), indicating that the psychological state prediction model predicts a high probability that the subject's psychological state is abnormal. Therefore, the psychological state prediction result does not match the subject's psychological state with the first and second confidence levels, meaning that the psychological assessment result and the psychological state prediction result are inconsistent. In this case, it can be assumed that the subject intentionally interfered with completing the psychological assessment questionnaire, potentially indicating an abnormal psychological state corresponding to the maximum second confidence level.

[0065] The second scenario is when the largest second confidence level is no greater than the second preset threshold, indicating that the psychological state prediction model has a low probability of predicting the subject's psychological state to be abnormal. In this case, the psychological assessment results are evaluated based on the difference between the largest second confidence level and the second largest second confidence level.

[0066] Specifically, if the difference between the largest second confidence level and the second largest second confidence level is not greater than a third preset threshold value (for example, 0.3), it indicates that the second confidence levels of the two types of abnormal states are relatively close. In this case, there may be a problem with the prediction result of the psychological state prediction model. In this case, the prediction result of the psychological state prediction model can be ignored, and the psychological assessment result can be determined to be accurate.

[0067] If the difference between the largest second confidence level and the second largest second confidence level is greater than a third preset threshold (e.g., 0.3), indicating that the psychological state prediction model predicts the correct result, the psychological assessment result can be determined to be inaccurate. A recommendation can then be output, recommending that the subject complete a specialized questionnaire targeting the type of abnormal state corresponding to the largest second confidence level to further analyze whether the subject is experiencing that type of abnormal state. If the specialized questionnaire is unavailable, the subject can be recommended to seek intervention from a psychologist.

[0068] As another example, if the first confidence level is greater than a first preset threshold (e.g., 0.5), then the psychological state prediction model predicts that the subject's psychological state is likely normal. Additionally, if the psychological state prediction result indicates that the subject's psychological state is normal, then the psychological state prediction result matches the first confidence level, meaning that the psychological state prediction result is consistent with the subject's psychological assessment result. In this case, the psychological assessment result can be determined to be accurate.

[0069] As another example, if the first confidence level is greater than a first preset threshold (e.g., 0.5), the psychological state prediction model predicts that the subject's psychological state is likely normal. However, if the psychological state prediction result indicates that the subject's psychological state is abnormal, this indicates that the psychological state prediction result does not match the first confidence level, i.e., the psychological state prediction result is inconsistent with the subject's psychological assessment result. It is very likely that the psychological assessment result is inaccurate and cannot represent the subject's true psychological state. In this case, the subject can be asked to re-evaluate and, if necessary, request the intervention of a psychologist.

[0070] As another example, if the matching result includes a finding that the psychological assessment result indicates that the subject's psychological state is abnormal, the first confidence level is less than a first preset threshold, and the maximum second confidence level is greater than a second preset threshold, then the psychological assessment result is determined to be accurate. In one embodiment, it can be determined that the subject has a psychological problem of the abnormal state type corresponding to the maximum second confidence level.

[0071] In the embodiment of the present application, by comparing whether the psychological state prediction results are consistent with the psychological evaluation results of the evaluation subject, the interference of external factors in the process of the evaluation subject filling out the psychological evaluation questionnaire is taken into account, and the psychological evaluation results are evaluated, thereby improving the reliability and validity of the psychological evaluation results.

[0072] In one or more embodiments of the present application, after evaluating the psychological assessment results based on the matching results, the psychological assessment result evaluation method may further include:

[0073] In the case that the psychological state prediction result is inconsistent with the psychological evaluation result of the evaluation subject, the psychological evaluation result is corrected according to the matching between the psychological state of the evaluation subject in the psychological state prediction result and the first confidence level and the second confidence level.

[0074] In embodiments of the present application, psychological assessment results can be corrected. For example, if the psychological assessment results indicate that the subject's psychological state is normal, the first confidence level is less than a first preset threshold, and the maximum second confidence level is greater than a second preset threshold, the psychological assessment results can be corrected to indicate that the subject is in an abnormal state of the type corresponding to the maximum second confidence level. This ensures that the psychological assessment results represent the subject's true psychological state, improving the reliability and validity of the psychological assessment results.

[0075] In one or more embodiments of the present application, Figure 2 As shown, the assessment data and behavior data are input into the psychological state prediction model to obtain the psychological state prediction results of the assessment subject, which may include:

[0076] Inputting the assessment data and behavioral data into the first data processing network in the psychological state prediction model to obtain target data;

[0077] Inputting the target data into the second data processing network in the psychological state prediction model to obtain target feature data for characterizing the psychological state features of the evaluation subject;

[0078] The target feature data is input into the third data processing network in the psychological state prediction model to obtain the psychological state prediction result.

[0079] In one or more embodiments of the present application, the aforementioned behavioral data includes multiple behavioral data of the subject, each behavioral data representing a different behavior of the subject. For example, some behavioral data may include the length of time the subject spent completing each question in a psychological assessment questionnaire, other behavioral data may include the number of times the subject corrected each question in the psychological assessment questionnaire, and other behavioral data may include the number of times the subject reviewed each question after completing it.

[0080] Based on the above behavioral data, the assessment data and behavioral data are input into the first data processing network in the psychological state prediction model to obtain target data, which may include:

[0081] Performing convolution processing on the evaluation data and the first behavior data among the plurality of behavior data through a first convolution kernel in the first data processing network to obtain target data for representing the evaluation data and the first behavior data;

[0082] The target data obtained by the previous convolution processing and the second behavior data in the multiple behavior data are convolved with the second convolution kernel in the first data processing network to obtain new target data, until the convolution processing is completed on each behavior data in the multiple behavior data.

[0083] As an example, before convolution processing is performed on the evaluation data and the first behavioral data among multiple behavioral data through the first convolution kernel in the first data processing network, the evaluation data can be first convolution processed and pooled, and then the evaluation data after convolution processing and pooling processing is input into the first convolution kernel for processing.

[0084] The following combination Figure 3 The example illustrates the data flow of the first data processing network in the embodiment of the present application.

[0085] Assume that the behavioral data includes behavioral data L1 of the time the subject spends filling in each question, behavioral data L2 of the number of times the subject corrects each question, behavioral data L3 of the number of times the subject reviews the question after filling in each question, and behavioral data L4 of the time the subject takes to complete the entire psychological assessment questionnaire.

[0086] like Figure 3 As shown, the data processing flow of the first data processing network includes:

[0087] S202: Perform convolution of the evaluation data with a convolution kernel of scale 5*5*64 with a step length of 2, and then pass it to the maximum pooling layer;

[0088] S204, performing pooling with a step size of 2 on the result obtained by processing S202 using a 3*3 convolution kernel in a maximum pooling layer;

[0089] S206, convolution kernel A is used to convolve the pooled data in S204 and the behavior data L1 with a step size of 2 to obtain target data 1, which represents the evaluation data L0 and the behavior data L1. The convolution kernel A can be a convolution kernel of size 3*3*64;

[0090] S208, convolving the target data 1 and the behavior data L2 obtained in the previous convolution process with a step size of 2 using convolution kernel B to obtain target data 2, where the target data 2 represents the evaluation data L0, the behavior data L1, and the behavior data L2. Convolution kernel B may be a convolution kernel of size 3*3*128;

[0091] S210, convolving the target data 2 and the behavior data L3 obtained in the previous convolution process with a step size of 2 using a convolution kernel C to obtain target data 3, where the target data 3 represents the evaluation data L0, the behavior data L1, the behavior data L2, and the behavior data L3. The convolution kernel C may be a convolution kernel of size 3*3*256;

[0092] S212, convolving the target data 3 and the behavior data L2 obtained in the previous convolution process with a step size of 2 using a convolution kernel D to obtain target data 4, where the target data 4 represents the evaluation data L0, the behavior data L1, the behavior data L2, the behavior data L3, and the behavior data L4. The convolution kernel D may be a convolution kernel of size 3*3*512;

[0093] S214: Perform average pooling with a step size of 2 on the target data 4.

[0094] This completes the data processing flow of the first data processing network. Since the input assessment and behavioral data are high-dimensional, convolution and pooling operations can reduce the high-dimensionality of the data to lower-dimensional data, making it easier for the second data processing network to process. Furthermore, combining the assessment data with the behavioral data allows the second data processing network to extract feature data that characterizes the psychological state of the assessed individual.

[0095] Afterwards, the second data processing network processes the target data obtained by the first data processing network. In one or more embodiments of the present application, the target data is input into the second data processing network in the psychological state prediction model to obtain target feature data for characterizing the psychological state characteristics of the evaluation subject, which may include:

[0096] When the target data are arranged in the order in which they are obtained, starting from the last target data, the following processing is performed on each target data in turn:

[0097] For the i-th target data, downsample the combined data corresponding to the i+1-th target data to obtain the sampled data; calculate the i-th target data and the sampled data to obtain the combined data corresponding to the i-th target data, i∈[1, N-2], N is the total number of target data;

[0098] After obtaining the combined data corresponding to each target data, extracting the feature data corresponding to each target data from the combined data corresponding to each target data;

[0099] The characteristic data corresponding to each target data are connected to obtain the target characteristic data used to characterize the psychological state characteristics of the evaluation object.

[0100] The following combination Figure 4 The example illustrates how to obtain target feature data through the second data processing network in the embodiment of the present application.

[0101] like Figure 4 As shown in FIG, since target data 1, target data 2, target data 3, target data 4 and target data 5 are obtained in sequence, these target data are arranged in the order in which they are obtained. Then, for the last two target data (i.e., target data 4 and target data 5), Figure 3 It can be seen that since both target data include evaluation data and behavior data L1 to behavior data L4, that is, the data included in these two target data are relatively comprehensive, there is no need to combine the data. Target data 4 is directly used as its corresponding combination data 4, and target data 5 is directly used as its corresponding combination data 5.

[0102] Then, for target data 3, a 1*1 convolution is performed on target data 3. Since the dimension of the data obtained by the convolution is different from the dimension of the combined data 4, the combined data 4 is downsampled to obtain sampled data so that the dimension of the data obtained by the convolution is the same as the dimension of the sampled data. Then, a layer (such as an Eltwise layer) is used to add, multiply, and take the maximum value of the convolution data and the sampled data to obtain the combined data 3 corresponding to the target data 3. The combined data 3 can represent the relationship between the target data 3 and the target data 4.

[0103] A similar method to obtaining combined data 3 is used to obtain combined data 2 corresponding to target data 2, and combined data 1 corresponding to target data 1, which will not be repeated here.

[0104] Then, after obtaining the combination data corresponding to target data 1 to target data 5, each combination data is input into the corresponding region proposal network (RPN), and corresponding feature data can be extracted from each combination data.

[0105] Connect multiple feature data to obtain target feature data used to characterize the psychological state characteristics of the evaluation object.

[0106] After obtaining the target feature data, the target feature data is input into the third data processing network to obtain the psychological state prediction result.

[0107] Figure 5 FIG. 1 is a schematic diagram of an embodiment of data processing performed by the third data processing network of the present application. Figure 5 As shown, the target feature data is input into two classifiers to obtain psychological state prediction results. One classifier is used to predict whether the subject's psychology is normal, and a first confidence level is obtained for the subject's psychology being normal. The other classifier is used to predict whether the subject's psychology is in various types of abnormal states, and a second confidence level is obtained for the subject's psychology being in various types of abnormal states.

[0108] The processing of each classifier in the third data processing network may include convolution using a convolution kernel of size 3*3*256 and maximum pooling with a stride of 2.

[0109] In one or more embodiments of the present application, the assessment data includes assessment data filled out by the assessment subject for each assessment question in the psychological assessment questionnaire, and the behavior data includes the behavior data of the assessment subject when filling out each assessment question.

[0110] Before evaluating the psychological assessment results, based on whether the psychological state prediction results are consistent with the psychological assessment results of the assessment subject, the assessment methods of the psychological assessment results may also include:

[0111] For each assessment topic, the assessment data and behavior data of the assessment topic are merged to obtain the comprehensive assessment data of the assessment topic;

[0112] Determine the evaluation result score corresponding to the evaluation question based on the comprehensive evaluation data of the evaluation question and the reference evaluation data corresponding to the evaluation question;

[0113] The psychological assessment results are determined based on the assessment results scores corresponding to each assessment topic.

[0114] In the embodiments of the present application, the comprehensive evaluation data may be a vector. In this case, before determining the evaluation result score corresponding to the evaluation question based on the comprehensive evaluation data of the evaluation question and the reference evaluation data corresponding to the evaluation question, the comprehensive evaluation data needs to be normalized to obtain a numerical value. After obtaining this numerical value, the evaluation result score can be calculated using the following formula.

[0115]

[0116] Among them, Z represents the evaluation result score of a certain evaluation question, and X represents the value obtained by normalizing the comprehensive evaluation data. represents the mean of the sample evaluation data collected in advance, and S represents the standard deviation of the sample evaluation data collected in advance.

[0117] After calculating and obtaining the evaluation result scores of each evaluation question in the psychological evaluation questionnaire, the psychological evaluation results can be determined. The following is an exemplary description of how to determine the psychological evaluation results.

[0118] As an example, the scores of assessment questions related to the same abnormal psychological state can be used to determine whether the subject has the abnormal psychological problem. For example, the scores of assessment questions used to assess depression can be summed to obtain a total, and the total can be used to determine whether the subject has depression.

[0119] As another example, the evaluation result scores of all evaluation questions in the psychological evaluation questionnaire are added together to obtain a total, and the total is used to determine whether the evaluation subject has psychological problems.

[0120] In one or more embodiments of the present application, the evaluation data and behavior data of the evaluation question are combined to obtain comprehensive evaluation data of the evaluation question, which may include:

[0121] Obtaining a first vector corresponding to the evaluation data of the evaluation question and a second vector corresponding to the behavior data of the evaluation question;

[0122] The first vector and the second vector of the evaluation question are spliced ​​in the target direction to obtain comprehensive evaluation data of the evaluation question, and the target direction is the direction that matches the first vector and the second vector.

[0123] If the first vector and the second vector are row vectors, the target direction is the row direction; if the first vector and the second vector are column vectors, the target direction is the column direction.

[0124] The following example illustrates how to obtain the first vector corresponding to the assessment data of an assessment question.

[0125] As an example, suppose a test question has five options: A, B, C, and D. If the test subject chooses AD, the first vector corresponding to the test data for this test question is [1, 0, 0, 1, 0]. Furthermore, if the test subject takes 5 seconds to complete the test question, then this time is added to the end of the first vector, forming the comprehensive test data [1, 0, 0, 1, 0, 5].

[0126] As another example, if the subject only chooses B, the first vector corresponding to the evaluation data for this evaluation question is [0, 1, 0, 0, 0]. Furthermore, if the subject takes 10 seconds to complete the evaluation question, this time is added to the end of the first vector, forming the comprehensive evaluation data [0, 1, 0, 0, 0, 10].

[0127] In addition to the method for evaluating psychological assessment results provided in this application, this application also provides an evaluation device for psychological assessment results.

[0128] Figure 6 FIG. 1 is a schematic diagram of an embodiment of a device for evaluating psychological assessment results provided by this application. Figure 6 As shown, the psychological assessment result evaluation device 300 includes:

[0129] The first acquisition module 302 acquires the evaluation data filled out by the evaluation subject on the psychological evaluation questionnaire that month, as well as the behavior data of the evaluation subject in the process of filling out the psychological evaluation questionnaire;

[0130] The data input module 304 is used to input the assessment data and behavior data into the psychological state prediction model to obtain the psychological state prediction result of the assessment subject;

[0131] The evaluation module 306 is used to evaluate the psychological evaluation result according to whether the psychological state prediction result is consistent with the psychological evaluation result of the evaluation subject. The psychological evaluation result is a psychological evaluation result obtained based on at least the evaluation data.

[0132] In the embodiment of the present application, the data input into the psychological state prediction model includes not only the evaluation data filled out by the evaluation subject in response to the psychological evaluation questionnaire, but also the behavioral data of the evaluation subject during the process of filling out the psychological evaluation questionnaire. Since the evaluation subject's behavioral data also reflects the evaluation subject's psychological state to a certain extent, the psychological state prediction model is a psychological state prediction result predicted based on the evaluation subject's data from multiple aspects. Therefore, the psychological state prediction result is relatively valuable for reference. Then, based on whether the psychological state prediction result is consistent with the evaluation subject's psychological evaluation result, the psychological evaluation result is evaluated to determine whether the psychological evaluation result represents the evaluation subject's true psychological state.

[0133] In one or more embodiments of the present application, the psychological state prediction result includes: a first confidence level that the psychological state of the evaluated subject is in a normal state, and a second confidence level that the psychological state of the evaluated subject is in various types of abnormal states.

[0134] The assessment and evaluation module 306 may include:

[0135] A first determining unit is configured to determine whether the psychological state of the subject in the psychological evaluation result matches at least one of the first confidence level and the second confidence level, and obtain a matching result;

[0136] The evaluation unit is used to evaluate the psychological assessment results based on the matching results.

[0137] In the embodiment of the present application, by comparing whether the psychological state prediction results are consistent with the psychological evaluation results of the evaluation subject, the interference of external factors in the process of the evaluation subject filling out the psychological evaluation questionnaire is taken into account, and the psychological evaluation results are evaluated, thereby improving the reliability and validity of the psychological evaluation results.

[0138] In one or more embodiments of the present application, the evaluation unit includes:

[0139] a first determining subunit, configured to determine that the psychological evaluation result is inaccurate when the matching result includes that the psychological state of the evaluation subject in the psychological evaluation result is normal, the first confidence level is less than a first preset threshold, and the maximum second confidence level is greater than a second preset threshold;

[0140] a second determining subunit, configured to, when the matching result includes that the psychological state of the subject in the psychological evaluation result is normal, the first confidence level is less than the first preset threshold, and the largest second confidence level is not greater than the second preset threshold, evaluate the psychological evaluation result according to a difference between the largest second confidence level and the second largest second confidence level;

[0141] a third determining subunit, configured to determine that the psychological evaluation result is accurate when the matching result includes that the psychological state of the evaluation subject in the psychological evaluation result is normal and the first confidence level is greater than a first preset threshold;

[0142] a fourth determining subunit, configured to determine that the psychological evaluation result cannot represent the true psychological state of the evaluation subject when the matching result includes that the psychological state of the evaluation subject in the psychological evaluation result is abnormal and the first confidence level is greater than a first preset threshold;

[0143] The fifth determining subunit is used to determine that the psychological evaluation result is accurate when the matching result includes that the psychological state of the evaluation subject in the psychological evaluation result is abnormal, the first confidence is less than the first preset threshold, and the maximum second confidence is greater than the second preset threshold.

[0144] In one or more embodiments of the present application, the psychological assessment result evaluation device 300 may further include:

[0145] The correction module is used to correct the psychological evaluation result according to the matching between the psychological state of the evaluation subject in the psychological state prediction result and the first confidence level and the second confidence level when the psychological state prediction result and the psychological evaluation result of the evaluation subject are inconsistent.

[0146] In embodiments of the present application, psychological assessment results can be corrected. For example, if the psychological assessment results indicate that the subject's psychological state is normal, the first confidence level is less than a first preset threshold, and the maximum second confidence level is greater than a second preset threshold, the psychological assessment results can be corrected to indicate that the subject is in an abnormal state of the type corresponding to the maximum second confidence level. This ensures that the psychological assessment results represent the subject's true psychological state, improving the reliability and validity of the psychological assessment results.

[0147] In one or more embodiments of the present application, the data input module 304 may include:

[0148] A first input unit is used to input the assessment data and behavior data into the first data processing network in the psychological state prediction model to obtain target data;

[0149] A second input unit is used to input the target data into the second data processing network in the psychological state prediction model to obtain target feature data for characterizing the psychological state features of the evaluation subject;

[0150] The third input unit is used to input the target feature data into the third data processing network in the psychological state prediction model to obtain the psychological state prediction result.

[0151] In one or more embodiments of the present application, the behavior data includes multiple behavior data of the evaluation subject, and each behavior data represents a different behavior of the evaluation subject.

[0152] The first input unit may include:

[0153] a first convolution subunit, configured to perform convolution processing on the evaluation data and first behavior data among the plurality of behavior data using a first convolution kernel in the first data processing network to obtain target data for representing the evaluation data and the first behavior data;

[0154] The second convolution subunit is used to perform convolution processing on the target data obtained by the previous convolution processing and the second behavior data in the multiple behavior data through the second convolution kernel in the first data processing network to obtain new target data, until the convolution processing of each behavior data in the multiple behavior data is completed.

[0155] In one or more embodiments of the present application, the second input unit may include:

[0156] The second determining subunit is configured to, when the target data are arranged in the order in which they are obtained, start from the last target data and sequentially perform the following processing on the target data: for the last two target data, treat each target data as its own combined data;

[0157] The sampling calculation subunit is used to downsample the combined data corresponding to the i+1th target data for the i-th target data to obtain sampled data; calculate the i-th target data and the sampled data to obtain the combined data corresponding to the i-th target data, i∈[1, N-2], where N is the total number of target data;

[0158] The feature extraction subunit is used to extract feature data corresponding to each target data from the combined data corresponding to each target data after obtaining the combined data corresponding to each target data;

[0159] The connection subunit is used to connect the feature data corresponding to each target data to obtain target feature data used to characterize the psychological state characteristics of the evaluation object.

[0160] In one or more embodiments of the present application, the assessment data includes assessment data filled out by the assessment subject for each assessment question in the psychological assessment questionnaire, and the behavior data includes the behavior data of the assessment subject when filling out each assessment question.

[0161] The psychological assessment result evaluation device 300 may further include:

[0162] A merging module is used to merge the evaluation data and behavior data of each evaluation question to obtain comprehensive evaluation data of the evaluation question;

[0163] The first determination module is used to determine the evaluation result score corresponding to the evaluation question based on the comprehensive evaluation data of the evaluation question and the reference evaluation data corresponding to the evaluation question;

[0164] The second determination module is used to determine the psychological assessment results based on the assessment result scores corresponding to each assessment topic.

[0165] In one or more embodiments of the present application, the merging module may include:

[0166] An acquisition unit, configured to acquire a first vector corresponding to the evaluation data of the evaluation question and a second vector corresponding to the behavior data of the evaluation question;

[0167] The splicing unit is used to splice the first vector and the second vector of the evaluation question in a target direction to obtain comprehensive evaluation data of the evaluation question, and the target direction is a direction that matches the first vector and the second vector.

[0168] The present application provides a device for evaluating psychological assessment results, which includes: a processor and a memory storing computer program instructions. When the processor executes the computer program instructions, it implements any of the above-mentioned methods for evaluating psychological assessment results.

[0169] Figure 7 This is a schematic diagram of the hardware structure of the evaluation equipment for the psychological assessment results provided in this application.

[0170] like Figure 7 As shown, the device for evaluating psychological assessment results may include a processor 401 and a memory 402 storing computer program instructions.

[0171] Specifically, the processor 401 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0172] Memory 402 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 402 may include removable or non-removable (or fixed) media. Where appropriate, memory 402 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, memory 402 is a non-volatile solid-state memory.

[0173] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0174] The processor 401 reads and executes the computer program instructions stored in the memory 402 to implement any one of the psychological assessment result evaluation methods in the above embodiments.

[0175] In one example, the psychological assessment result evaluation device may further include a communication interface 403 and a bus 410. Figure 7 As shown, the processor 401 , the memory 402 , and the communication interface 403 are connected via a bus 410 and communicate with each other.

[0176] The communication interface 403 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0177] Bus 410 includes hardware, software or both, and the components of online data flow metering equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industry standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industry standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 410 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0178] Figure 8 FIG. 1 is a schematic diagram of another embodiment of the device for evaluating the psychological evaluation results provided by the present application. Figure 8 As shown, the psychological assessment result evaluation device 500 includes:

[0179] Questionnaire module 502, used to display psychological assessment questionnaires;

[0180] The data collection module 504 is used to collect the evaluation data filled out by the evaluation subject based on the psychological evaluation questionnaire, as well as the behavior data of the evaluation subject in the process of filling out the psychological evaluation questionnaire;

[0181] The data analysis module 506 is used to calculate the evaluation result score corresponding to each evaluation topic based on the evaluation data and behavior data of the evaluation topic;

[0182] The storage module 508 is used to store the evaluation data and behavior data of the evaluation object, as well as the evaluation result scores corresponding to each evaluation topic;

[0183] Processing module 510 is used to input the assessment data and behavioral data into the psychological state prediction model to obtain the psychological state prediction results of the assessment subject; determine the psychological assessment results of the assessment subject based on the assessment result scores corresponding to each assessment topic; and then evaluate the psychological assessment results based on whether the psychological state prediction results are consistent with the psychological assessment results of the assessment subject.

[0184] The data acquisition module 504 may be as follows: Figure 9 The high-speed data acquisition module shown in the figure includes a field-programmable gate array (FPGA), which is connected to an analog-to-digital converter and a clock module. The FPGA is also connected to memory, such as erasable programmable read-only memory (EPROM). The FPGA is also connected to a bus, such as the Compact Peripheral Component Interconnect (CPCI) bus and CPCIe bus. FPGA3 is loaded with fixed EPROM. The high-speed analog-to-digital converter performs analog-to-digital conversion in a four-way interleaved manner, generating 8-bit data per channel at a 750MHz frequency. The data throughput per channel is 750MHz x 8 bits. Due to FPGA resource limitations, I / O pin frequency, and pin size constraints, each data channel is first divided by four on an FPGA, generating 16 channels of 8-bit data at 187.5MHz. This increases data transmission speed.

[0185] One of the key indicators that influence the dynamic performance of an ADC is the clock module, which must exhibit minimal clock jitter and phase noise. The greater the timing uncertainty / clock jitter, the more severe the impact on the ADC's noise floor, resulting in a lower signal-to-noise ratio (SNR). During implementation, select a clock module that is deterministic or exhibits minimal jitter to improve the SNR.

[0186] In terms of electrical characteristics, the CPCI bus, based on the Peripheral Component Interconnect (PCI) standard, resolves the incompatibility issues between bus technologies like VME (Versa Module Eurocard) and the PCI bus, enabling the use of PC-based x86 architectures and hard disk storage technologies in the industrial sector. Furthermore, due to significant improvements in interfaces and other areas, servers and industrial computers using CPCI technology boast high reliability and high density. CPCI is an upgraded version of the CPCI standard based on the PCI bus. By combining CPCI and CPCI, it enables modules to achieve high processing performance.

[0187] The FPGA is also connected to an external DDR2 memory board. A DDR2 memory module is used as the storage medium. Each DDR2 memory module has a data throughput of 400MHz x 64 bits and a storage capacity of 2GB. A Xilinx FPGA-based controller implements read, write, and verification of the DDR2 memory module. DDR2 memory chips are reserved outside the FPGA for data trigger caching and redundancy.

[0188] The CPCI bus is J1 CPCI, and the CPCIe bus is PXIe XJ3 or XJ4. The FPGA is also connected to a trigger. The FPGA is also connected to a backplane connector, supporting 32GB of storage and customizable bus connections. The FPGA is a Xilinx V5 FPGA, which offers excellent performance and functionality.

[0189] The storage module 508 may be Figure 10 or Figure 11 The VPX high-speed storage module shown is based on a 6U VPX standard card board and is equipped with an FPGA and a power supply (PowerPC). The power supply is connected to the FPGA through an external SSD storage group. The SSD storage group includes 16 SSD solid-state hard drives connected to the FPGA via SATA3.0 data cables. Each SSD has a capacity of 1TB. The FPGA is connected to the power supply via a PCIe3.0 data cable.

[0190] The FPGA model is XC7VX690T-2FFG1927I. This model of FPGA has 80 GTHs (GTH is a high-speed serial transceiver), and the speed of a single GTH can reach 28.05Gb / s. It also integrates 3 PCIe3.0 controllers. The power supply model is T2080NXN8TTB. This model of power supply has 4 cores and 8 threads, a single core of 1.8GHz, provides 16 serializer / deserializer high-speed interfaces, and supports PCIe, XFI, SRIO and other interfaces. The SSD solid-state drive has the following specific features: a single disk of 1TB, a write rate of up to 520MB / s, and a read rate of up to 540MB / s. The standard rate of SATA3.0 is 6Gb / s, and its performance is higher than that of SATA2.0 data cable. There isn't much difference in appearance between SATA 2.0 and SATA 3.0 data cables. Cables produced by different manufacturers may have colors and markings on them to clearly indicate whether they support SATA 2.0 or SATA 3.0. However, whether a SATA 2.0 cable is used between a SATA 3.0 hard drive and motherboard, or a SATA 3.0 cable is used between a SATA 2.0 hard drive and motherboard, they are both compatible and will not have any compatibility issues. However, if both the hard drive and motherboard support the SATA 3.0 device standard but a SATA 2.0 cable is used, the actual effect will be the SATA 2.0 standard. Only when a SATA 3.0 data cable is used to connect a SATA 3.0-supported hard drive and motherboard can the SATA 3.0 standard be achieved.

[0191] The FPGA leverages its concurrency and high data bit width to achieve high-speed data acquisition, storage, and playback. It operates 16 SSDs in RAID 0 mode, achieving theoretically high read and write speeds. Furthermore, the FPGA exchanges data with the SSDs via the SATA 3.0 interface. The PCI 3.0 interface between the FPGA and the PowerPC provides a high-speed channel for exchanging file management information. The standard SATA 3.0 speed is 6Gb / s. A single SSD has a capacity of 1TB, while 16 SSDs have a capacity of 16TB.

[0192] The storage module 508 can achieve a storage capacity of 16TB and a data read and write bandwidth of 6Gb / s.

[0193] Both the interfaces and optical interfaces on the VPX can realize data acquisition and playback.

[0194] Among them, data recording (storage bandwidth or recording bandwidth) is data input from the board's external interface (such as GTH, MPO), reaches the FPGA, and is then written to the SSD by the FPGA.

[0195] Data playback (playback bandwidth) is when the FPGA reads data from the SSD and outputs it through the external interface.

[0196] Every link in the data recording and playback path affects data bandwidth, which is primarily limited by three factors: external interface performance (interface bandwidth), processor performance (processor hardware and software performance), and SSD performance. Achieving 6Gb / s continuous data recording and playback bandwidth requires each link to operate at near-theoretical speed, which presents significant design challenges.

[0197] The 6Gb / s storage module, based on a single-slot VPX architecture, utilizes an FPGA + PowerPC architecture, with the FPGA attached to an SSD storage group, to implement data storage. The FPGA implements a high-speed data acquisition and playback interface and SSD read and write functionality, while the power supply implements file system management and a 10G network data import and export interface. Data exchange between the FPGA and power supply occurs via the PCIe 3.0 bus. Storage module 508 primarily features the following: support for recording and playback of optical fiber data; support for circular overwrites to disks; support for up to 16 solid-state drives, each with a capacity of 1TB; 6Gb / s data read and write bandwidth; support for the export and deletion of collected data; and support for power failure recovery.

[0198] In addition, in conjunction with the psychological assessment result evaluation method in the above embodiments, embodiments of the present application may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, the method for evaluating any of the psychological assessment results in the above embodiments is implemented.

[0199] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0200] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. Programs or code segments can be stored in machine-readable media, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable media" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0201] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0202] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit. It is also understood that each box in the block diagram and / or flowchart and the combination of the boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0203] The above is only a specific implementation method of the present application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the scope of protection of the present application is not limited to this. Any technician familiar with this technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the scope of protection of this application.

Claims

1. A method for evaluating psychological assessment results, characterized in that: include: Obtaining assessment data filled out by the assessment subject on the psychological assessment questionnaire, as well as behavioral data of the assessment subject during the process of filling out the psychological assessment questionnaire, the behavioral data including the time the assessment subject spent filling out each question, the number of times the assessment subject corrected each question, and the number of times the assessment subject reviewed each question after filling out the question; Inputting the evaluation data and the behavior data into a psychological state prediction model to obtain a psychological state prediction result of the evaluation subject; evaluating the psychological evaluation result based on whether the psychological state prediction result is consistent with the psychological evaluation result of the evaluation subject, wherein the psychological evaluation result is a psychological evaluation result obtained at least based on the evaluation data; The psychological state prediction result includes: a first confidence level that the psychological state of the evaluated subject is in a normal state, and a second confidence level that the psychological state of the evaluated subject is in various types of abnormal states; The step of evaluating the psychological evaluation result based on whether the psychological state prediction result is consistent with the psychological evaluation result of the evaluation subject includes: determining whether the psychological state of the subject in the psychological evaluation result matches at least one of the first confidence level and the second confidence level, and obtaining a matching result; evaluating the psychological assessment results according to the matching results; The step of evaluating the psychological assessment results according to the matching results includes: When the matching result includes that the psychological state of the evaluation subject in the psychological evaluation result is normal, the first confidence level is less than a first preset threshold, and the largest second confidence level is not greater than a second preset threshold, evaluating the psychological evaluation result according to a difference between the largest second confidence level and the second largest second confidence level; When the difference between the largest second confidence level and the second largest second confidence level is greater than a third preset threshold, determining that the psychological state prediction result is accurate and determining that the psychological assessment result is inaccurate; Output recommendation information, which is used to recommend the evaluation subject to take a special questionnaire on psychological problems related to the abnormal state of the type corresponding to the second maximum confidence level, so as to further analyze whether the evaluation subject's psychology is in this type of abnormal state.

2. The method according to claim 1, characterized in that The step of evaluating the psychological assessment results according to the matching results includes: When the matching result includes that the psychological state of the evaluation subject in the psychological evaluation result is normal, the first confidence level is less than a first preset threshold, and the largest second confidence level is greater than a second preset threshold, then determining that the psychological evaluation result is inaccurate; When the matching result includes that the psychological state of the evaluation subject in the psychological evaluation result is normal, and the first confidence level is greater than a first preset threshold, then the psychological evaluation result is determined to be accurate; When the matching result includes that the psychological state of the evaluation subject in the psychological evaluation result is abnormal, and the first confidence level is greater than a first preset threshold, it is determined that the psychological evaluation result cannot represent the true psychological state of the evaluation subject; When the matching result includes that the psychological state of the evaluation subject in the psychological evaluation result is abnormal, the first confidence is less than a first preset threshold, and the maximum second confidence is greater than a second preset threshold, the psychological evaluation result is determined to be accurate.

3. The method according to claim 1, characterized in that After evaluating the psychological assessment results according to the matching results, the method further includes: When the psychological state prediction result is inconsistent with the psychological evaluation result of the evaluation subject, the psychological evaluation result is corrected according to the matching between the psychological state of the evaluation subject in the psychological state prediction result and the first confidence level and the second confidence level.

4. The method according to any one of claims 1 to 3, characterized in that The step of inputting the assessment data and the behavior data into a psychological state prediction model to obtain a psychological state prediction result of the assessment subject includes: Inputting the assessment data and the behavior data into the first data processing network in the mental state prediction model to obtain target data; Inputting the target data into a second data processing network in the psychological state prediction model to obtain target feature data for characterizing the psychological state features of the assessment subject; The target feature data is input into the third data processing network in the mental state prediction model to obtain the mental state prediction result.

5. The method according to claim 4, characterized in that The behavior data includes multiple behavior data of the evaluation subject, each behavior data represents a different behavior of the evaluation subject; Inputting the assessment data and the behavior data into the first data processing network in the mental state prediction model to obtain target data includes: Performing convolution processing on the evaluation data and first behavior data among the plurality of behavior data through a first convolution kernel in the first data processing network to obtain the target data for representing the evaluation data and the first behavior data; The target data obtained by the previous convolution processing and the second behavior data among the multiple behavior data are convolved with the second convolution kernel in the first data processing network to obtain new target data, until the convolution processing of each behavior data among the multiple behavior data is completed.

6. The method according to claim 4, characterized in that Inputting the target data into the second data processing network in the psychological state prediction model to obtain target feature data for characterizing the psychological state features of the evaluation subject includes: When the target data are arranged in the order in which they are obtained, starting from the last target data, the following processing is performed on each target data in turn: For the last two target data, each target data is used as respective combined data; For the i-th target data, downsample the combined data corresponding to the i+1-th target data to obtain sampled data; calculate the i-th target data and the sampled data to obtain the combined data corresponding to the i-th target data, i∈[1, N-2], N is the total number of target data; After obtaining the combination data corresponding to each of the target data, extracting the feature data corresponding to each of the target data from the combination data corresponding to each of the target data; The characteristic data corresponding to each of the target data are connected to obtain target characteristic data for characterizing the psychological state characteristics of the evaluation object.

7. The method according to any one of claims 1 to 3, characterized in that The assessment data includes the assessment data filled in by the assessment subject for each assessment question in the psychological assessment questionnaire, and the behavior data includes the behavior data of the assessment subject when filling in each assessment question; Before evaluating the psychological evaluation result based on whether the psychological state prediction result is consistent with the psychological evaluation result of the evaluation subject, the method further includes: For each of the evaluation questions, the evaluation data and behavior data of the evaluation question are combined to obtain comprehensive evaluation data of the evaluation question; Determine the evaluation result score corresponding to the evaluation topic based on the comprehensive evaluation data of the evaluation topic and the reference evaluation data corresponding to the evaluation topic; The psychological assessment results are determined according to the assessment result scores corresponding to the respective assessment questions.

8. The method according to claim 7, characterized in that The evaluation data and behavior data of the evaluation topic are combined to obtain comprehensive evaluation data of the evaluation topic, including: Obtaining a first vector corresponding to the evaluation data of the evaluation question and a second vector corresponding to the behavior data of the evaluation question; The first vector and the second vector of the evaluation question are spliced ​​in a target direction to obtain comprehensive evaluation data of the evaluation question, and the target direction is a direction that matches the first vector and the second vector.

9. A device for evaluating psychological assessment results, characterized in that: include: The first acquisition module acquires the assessment data of the assessment subject on the psychological assessment questionnaire completed that month, as well as the behavioral data of the assessment subject during the process of completing the psychological assessment questionnaire, the behavioral data including the time the assessment subject spent on filling out each question, the number of times the assessment subject corrected each question, and the number of times the assessment subject reviewed each question after completing it; a data input module, configured to input the assessment data and the behavior data into a psychological state prediction model to obtain a psychological state prediction result of the assessment subject, wherein the psychological state prediction result includes: a first confidence level that the assessment subject's psychology is in a normal state, and a second confidence level that the assessment subject's psychology is in various types of abnormal states; an evaluation module, configured to evaluate the psychological evaluation result based on whether the psychological state prediction result is consistent with the psychological evaluation result of the evaluation subject, wherein the psychological evaluation result is a psychological evaluation result obtained at least based on the evaluation data; The evaluation module is specifically used to: determining whether the psychological state of the subject in the psychological evaluation result matches at least one of the first confidence level and the second confidence level, and obtaining a matching result; evaluating the psychological assessment results according to the matching results; The evaluation module is further configured to: when the matching result includes that the psychological state of the evaluation subject in the psychological evaluation result is normal, the first confidence level is less than a first preset threshold, and the largest second confidence level is not greater than a second preset threshold, evaluate the psychological evaluation result according to a difference between the largest second confidence level and the second largest second confidence level; When the difference between the largest second confidence level and the second largest second confidence level is greater than a third preset threshold, determining that the psychological state prediction result is accurate and determining that the psychological assessment result is inaccurate; Output recommendation information, which is used to recommend the evaluation subject to take a special questionnaire on psychological problems related to the abnormal state of the type corresponding to the second maximum confidence level, so as to further analyze whether the evaluation subject's psychology is in this type of abnormal state.

10. A device for evaluating psychological assessment results, characterized in that: The device comprises: a processor and a memory storing computer program instructions, When the processor executes the computer program instructions, it implements the method for evaluating the psychological assessment results according to any one of claims 1 to 8.

11. A computer storage medium, characterized in that The computer storage medium stores computer program instructions, which, when executed by a processor, implement the method for evaluating psychological assessment results according to any one of claims 1 to 8.

Images