A psychological risk assessment early warning model construction method

Abstract

The application belongs to the technical field of psychological assessment. A psychological risk assessment early warning model construction method is provided, comprising: obtaining first behavior data of a first test object, using a psychological risk assessment model to perform risk assessment on the first behavior data, obtaining a plurality of first psychological risk types and corresponding first assessment values; screening out the first psychological risk types with first assessment values higher than a first assessment threshold, adding label data to the first behavior data according to the screened first psychological risk types, and obtaining first training data; when the first quantity of the first training data corresponding to each type of label data reaches a target quantity, constructing each first training data corresponding to the label data of the type into a training data set; and using each training data set to sequentially train the psychological risk assessment early warning model. The psychological risk assessment early warning model in the application has the ability to accurately identify the psychological risks of a plurality of complex test objects.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of psychological assessment, in particular to a psychological risk assessment and early warning model construction method. BACKGROUND

[0002] Psychological risk assessment and early warning is a method for identifying and preventing potential mental health problems, which can help individuals or organizations to discover the signals that may lead to mental problems as soon as possible and take appropriate intervention measures. The psychological risks mainly include anxiety, depression, inferiority, paranoia, compulsion, dependence, social attack, social withdrawal, etc.

[0003] In order to improve the efficiency and accuracy of psychological risk assessment, the current psychological risk assessment model is mainly used to assess the psychological risk of the assessed object, and the corresponding early warning is carried out when there is a corresponding psychological risk. In constructing the psychological risk assessment and early warning model, the current method is to collect the behavior data of personnel with a specific psychological risk type, to construct a corresponding type of training data set, and to use the training data set to train the psychological risk assessment model. The psychological risk assessment model trained in this way can only identify objects with a single type of psychological risk. However, in reality, many risk personnel have more than one type of psychological risk, such as anxiety + paranoia, inferiority + compulsion, etc. The psychological risk assessment model trained based on the data of a single psychological risk type cannot accurately identify it. The present application aims to solve this technical problem. SUMMARY

[0004] To this end, the present application provides a psychological risk assessment and early warning model construction method, an electronic device, a computer storage medium and a computer program product to solve at least one of the above technical problems.

[0005] The present application provides a psychological risk assessment and early warning model construction method, which comprises the following steps:

[0006] Obtain the first behavior data of the first measured object, use the psychological risk assessment model to assess the risk of the first behavior data, and obtain a plurality of first psychological risk types and corresponding first assessment values; wherein the psychological risk assessment model has multiple, which is used to assess the risk of a single type of psychological risk;

[0007] The first psychological risk type with the first assessment value higher than the first assessment threshold is screened out, and the first training data is obtained by adding label data to the first behavior data according to the screened first psychological risk type;

[0008] when a first quantity of the first training data corresponding to each type of the label data reaches a target quantity, constructing each of the first training data corresponding to the type of the label data into a training data set;

[0009] sequentially training a psychological risk assessment early warning model using each of the training data sets;

[0010] The trained psychological risk assessment early warning model is used for psychological risk analysis on second behavior data of a second testee, to obtain a second psychological risk type and a corresponding second evaluation value, and if any of the second evaluation values exceeds a second evaluation threshold, an early warning signal is output.

[0011] Optionally, the first behavior data of the first testee is obtained by:

[0012] obtaining historical evaluation records of the first testee;

[0013] If the historical evaluation records are empty or all normal, a first evaluation topic set is used to communicate with the first testee; otherwise, a second evaluation topic set is used to communicate with the first testee; wherein the first evaluation topic set is more likely to arouse emotional fluctuations of the testee than the second evaluation topic set;

[0014] During the communication process, the first behavior data of the first testee is collected, including response data to specific questions, body movement data, and facial expression data.

[0015] Optionally, a psychological risk assessment model is used to perform risk assessment on the first behavior data, to obtain a plurality of first psychological risk types and corresponding first evaluation values, including:

[0016] The psychological risk assessment model is used to perform risk assessment on the first behavior data, to obtain a plurality of the first psychological risk types and corresponding third evaluation values;

[0017] The first behavior data from different collection sources is determined, and the distance mean of the Euclidean distance between each of the first behavior data and corresponding second behavior data is calculated; wherein the second behavior data is behavior data corresponding to each collection source collected before the first testee is communicated using the first evaluation topic set or the second evaluation topic set;

[0018] An adjustment coefficient is determined according to the distance mean, and the third evaluation value corresponding to each of the first psychological risk types is adjusted to the first evaluation value using the adjustment coefficient.

[0019] Optionally, the target quantity is determined by:

[0020] a second quantity of each of the first psychological risk types is calculated, and the target quantity is calculated by substituting the second quantity into the following conversion formula:

[0021]

[0022] In the formula, the target quantity, the second quantity of each of the first psychological risk types, the number of all known psychological risk types.

[0023] Optionally, the psychological risk assessment and early warning model is established by a Transformer model.

[0024] Optionally, the Transformer model comprises a plurality of attention heads, a feedforward layer and a prediction network; wherein the plurality of attention heads and the feedforward layer are connected in sequence to form a multi-layer encoder.

[0025] The attention head is used to convert the input first training data into a query vector, a key vector and a value vector, and the output of the attention head is calculated based on an activation function, and the outputs of the plurality of attention heads are connected to form a target output.

[0026] The feedforward layer is used to process the target output to obtain hidden features of the first training data.

[0027] The prediction network is used to process the input hidden features and predict a plurality of psychological risk types and corresponding evaluation values.

[0028] The present application also provides a psychological risk assessment and early warning model construction system, comprising an acquisition module, a first processing module, a second processing module and a training module.

[0029] The acquisition module is used to acquire first behavior data of a first test object, perform risk assessment on the first behavior data by using a psychological risk assessment model, and obtain a plurality of first psychological risk types and corresponding first evaluation values; wherein the psychological risk assessment model is multiple and is used to perform risk assessment on a single type of psychological risk.

[0030] The first processing module is used to screen out the first psychological risk types whose first evaluation values are higher than a first evaluation threshold, add label data to the first behavior data according to each of the screened first psychological risk types, and obtain first training data.

[0031] The second processing module is configured to construct each of the first training data corresponding to the label data of each type as a training data set when a first quantity of the first training data corresponding to the label data of each type reaches a target quantity.

[0032] The training module is configured to sequentially train a psychological risk assessment early warning model using each of the training data sets.

[0033] The trained psychological risk assessment early warning model is configured to perform psychological risk analysis on second behavior data of a second subject to obtain a second psychological risk type and a corresponding second evaluation value, and output an early warning signal if any of the second evaluation values exceeds a second evaluation threshold.

[0034] The present application also provides an electronic device comprising at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program is configured to implement the method according to any one of the preceding embodiments when executed by the processor.

[0035] The present application also provides a computer storage medium storing a computer program executable by a processor, wherein the computer program is configured to implement the method according to any one of the preceding embodiments when executed by the processor.

[0036] The present application also provides a computer program product comprising a computer program executable by a processor, wherein the computer program is configured to implement the method according to any one of the preceding embodiments when executed by the processor.

[0037] The present application uses the behavior data of a first subject comprising a plurality of psychological risk types to construct a training data set, so that the trained psychological risk assessment early warning model has the ability to accurately identify each psychological risk type of a second subject of a plurality of psychological risk types. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0039] Figure 1 is a flowchart of a psychological risk assessment early warning model construction method disclosed by the embodiments of the present application;

[0040] Figure 2 is a structural diagram of a psychological risk assessment early warning model disclosed by the embodiments of the present application;

[0041] Figure 3 is a structural schematic diagram of a psychological risk assessment early warning model construction system disclosed by an embodiment of the present application. DETAILED DESCRIPTION

[0042] The embodiments of the present application will be described in detail by specific embodiments, and those skilled in the art can easily understand other advantages and effects of the present application from the disclosed content of the specification. Obviously, the described embodiments are part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0043] In addition, the technical features involved in different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0044] Reference Figure 1 The embodiment of the present application discloses a psychological risk assessment early warning model construction method, which comprises the following steps:

[0045] Obtain the first behavior data of the first measured object, use the psychological risk assessment model to perform risk assessment on the first behavior data, and obtain a plurality of first psychological risk types and corresponding first evaluation values; wherein the psychological risk assessment model has multiple, and is used for risk assessment on a single type of psychological risk;

[0046] The first psychological risk type with the first evaluation value higher than the first evaluation threshold is screened out, and label data is added to the first behavior data according to each of the screened first psychological risk types, to obtain first training data;

[0047] When the first number of the first training data corresponding to each type of label data reaches the target number, each of the first training data corresponding to the label data of this type is constructed into a training data set;

[0048] Each of the training data sets is used to train the psychological risk assessment early warning model in turn;

[0049] Among them, the trained psychological risk assessment early warning model is used for psychological risk analysis on the second behavior data of the second measured object, to obtain the second psychological risk type and the corresponding second evaluation value, and if any of the second evaluation values exceeds the second evaluation threshold, an early warning signal is output.

[0050] The design goal of the psychological risk assessment early warning model is to accurately analyze the psychological risk type and the corresponding risk assessment value of the measured object with multiple psychological risk types. To this end, the first behavior data of the first measured object is collected, which includes response data to specific questions, body movement data in the conversation process, facial expression data, etc.; a plurality of psychological risk assessment models are used to preliminarily analyze the first behavior data, and a plurality of first psychological risk types and corresponding first assessment values are obtained. Each psychological risk assessment model is trained based on the behavior data of the measured object of a specific psychological risk type, and can only be used to accurately identify a single type of psychological risk. After analysis by multiple psychological risk assessment models, the plurality of first psychological risk types corresponding to a piece of first behavior data can be known, i.e., the plurality of types of psychological risks that the first measured object may have, and the first psychological risk types with first assessment values higher than a first assessment threshold are filtered out, and a plurality of first psychological risk types are automatically constructed into label data. The first behavior data and the label data constitute the first training data, and the first training data = [first behavior data, label 1, …, label n], and label n is the nth first psychological risk type.

[0051] By continuously obtaining the first behavior data of the first measured object until the first quantity of the first training data corresponding to a specific type of label data combination (for example, [label 1, label 2], [label 1, label 2, label 3]) reaches the target quantity, these first training data can be constructed into a training data set, and then the psychological risk assessment early warning model is trained using the training data set. When the first quantity of the first training data corresponding to other types of label data also reaches the target quantity, another training data set can be constructed, so that the psychological risk assessment early warning model can be trained in turn. After training by multiple training data sets, the psychological risk assessment early warning model has the risk analysis of multiple complex types of psychological risks.

[0052] After the training of the psychological risk assessment early warning model is completed, the second behavior data of the second measured object can be received, and the psychological risk analysis of the psychological risk assessment early warning model is performed to obtain the psychological risk type and the corresponding second assessment value. If any second assessment value exceeds the second assessment threshold, an early warning signal is output. The early warning signal can be output to the management personnel on the test site, or to the guardian of the second measured object.

[0053] Optionally, the first behavior data of the first measured object is obtained, including:

[0054] Obtaining the historical evaluation record of the first measured object;

[0055] If the historical evaluation record is empty or all normal, a first evaluation topic set is used to communicate with the first testee; otherwise, a second evaluation topic set is used to communicate with the first testee; wherein the first evaluation topic set is more likely to arouse emotional fluctuations of the testee than the second evaluation topic set;

[0056] In the communication process, the first behavior data of the first testee is collected, including response data, body movement data, and facial expression data to specific questions.

[0057] In the embodiment, when testing the testee, the corresponding evaluation topic set needs to be used to communicate with the testee, and the evaluation topic set has multiple types, including topics with different stimulation intensities and quantities. The probability of arousing emotional fluctuations of the testee corresponding to each evaluation topic set is evaluated in advance based on the stimulation intensity of the topic and the quantity of high stimulation intensity topics. Different evaluation topic sets need to be used for different types of testees. In this regard, the application first searches the database for the historical evaluation record of the first testee. The database contains networked shared data from multiple test units. If there is no historical evaluation record of the first testee in the database, or the historical evaluation record indicates that the first testee has no psychological risk, it means that the probability of the first testee having psychological risk is low, or the psychological risk of the first testee is not easy to be triggered and recognized. Therefore, the application uses the first evaluation topic set which is more likely to arouse emotional fluctuations of the testee for the currently determined normal first testee, and uses the second evaluation topic set which is less likely to arouse emotional fluctuations of the testee for the first testee who has psychological risk warning records. The more the number of psychological risk warning records, the more the second evaluation topic set which is less likely to arouse emotional fluctuations of the testee is selected.

[0058] Optionally, the first behavior data is risk evaluated using a psychological risk evaluation model to obtain a plurality of first psychological risk types and corresponding first evaluation values, including:

[0059] The first behavior data is risk evaluated using the psychological risk evaluation model to obtain a plurality of first psychological risk types and corresponding third evaluation values;

[0060] The first behavior data from different collection sources is determined, and the distance mean of the Euclidean distance between each first behavior sub-data and the corresponding second behavior sub-data is calculated; wherein the second behavior sub-data is the behavior data corresponding to each collection source collected before communicating with the first testee using the first evaluation topic set or the second evaluation topic set;

[0061] The adjustment coefficient is determined according to the distance mean value, and the third evaluation value corresponding to each of the first psychological risk types is adjusted to the first evaluation value by using the adjustment coefficient.

[0062] In the embodiment, the psychological risk evaluation model is used to perform risk evaluation on the acquired first behavior data, and a plurality of first psychological risk types and corresponding third evaluation values can be obtained. Meanwhile, the first behavior data includes first behavior sub-data from a plurality of collection sources (the collection sources are the aforementioned response data, body movement data, and facial expression data). When the number of types of the first behavior sub-data is larger, the confidence of the psychological risk types predicted by the psychological risk evaluation model is higher, and vice versa, the probability of misrecognition caused by abnormal conditions is higher.

[0063] In the embodiment, the distance mean value of the Euclidean distance between each first behavior sub-data and corresponding second behavior sub-data is calculated. The second behavior sub-data is the behavior data of each corresponding collection source of the first measured object in a calm state collected before communication. When the distance mean value is larger, the emotional fluctuation of the first measured object after testing is larger, the characteristic significance of the corresponding type of psychological risk is more obvious, the confidence of the third evaluation value corresponding to the first psychological risk type is higher, and vice versa, the confidence of the third evaluation value corresponding to the first psychological risk type is lower. Therefore, a reasonable adjustment coefficient is determined according to the aforementioned distance mean value, and each third evaluation value obtained is adjusted by using the adjustment coefficient. Apparently, some of the adjusted third evaluation values can be lower than the first evaluation threshold or higher than the first evaluation threshold.

[0064] The distance mean value and the adjustment coefficient conform to a negative proportional function, for example, the adjustment coefficient=A / distance mean value, and A is a constant.

[0065] Optionally, the target number is determined by the following method:

[0066] The second number of each of the screened first psychological risk types is calculated, and the target number is calculated by substituting the second number into the following conversion formula:

[0067]

[0068] In the formula, the target number is the target number, the second number is the second number of each of the screened first psychological risk types, and the total number is the number of all known psychological risk types.

[0069] ​​​In the embodiment, the target quantity and the second quantity of each first psychological risk type screened are in a positive correlation, that is, the greater the second quantity, the more the corresponding target quantity. In other words, the more the labels annotated in the first training data in the training data set, the more the first training data should be contained in the training data set, so as to ensure that the prediction accuracy of the trained psychological risk assessment and early warning model reaches a high enough level; otherwise, the first training data should be contained in the training data set, so as to ensure that the prediction accuracy of the trained psychological risk assessment and early warning model reaches a high enough level.

[0070] Optionally, referring to Figure 2 , the psychological risk assessment and early warning model is established by a Transformer model.

[0071] Optionally, the Transformer model comprises a plurality of attention heads, a feedforward layer and a prediction network; wherein the plurality of attention heads and the feedforward layer are connected in sequence to constitute a multi-layer encoder.

[0072] The attention head is used to convert the input first training data into a query vector, a key vector and a value vector, and the output of the attention head is calculated based on an activation function, and the outputs of the plurality of attention heads are connected to constitute a target output.

[0073] The feedforward layer is used to process the target output to obtain the hidden features of the first training data.

[0074] The prediction network is used to process the input hidden features and predict a plurality of psychological risk types and corresponding evaluation values.

[0075] In the embodiment, the psychological risk assessment and early warning model is established based on the Transformer model, and the psychological risk assessment and early warning model comprises a multi-layer encoder and a prediction network, wherein the multi-layer encoder comprises a plurality of attention heads and a feedforward layer, the outputs of the plurality of attention heads can be combined to constitute a target output, the feedforward layer can output corresponding hidden features according to the target output, and finally the prediction network processes the hidden features to predict a plurality of psychological risk types and corresponding evaluation values.

[0076] In addition, the psychological risk assessment model can also be established based on the Transformer model, which is not limited by the present application.

[0077] Referring to Figure 3 , the embodiment of the present application further discloses a psychological risk assessment and early warning model construction system, which comprises an acquisition module, a first processing module, a second processing module and a training module.

[0078] The acquisition module is configured to acquire first behavior data of a first measured object, perform risk assessment on the first behavior data using a psychological risk assessment model, and obtain a plurality of first psychological risk types and corresponding first assessment values; the psychological risk assessment model is used to perform risk assessment on a single type of psychological risk.

[0079] The first processing module is configured to filter out the first psychological risk types with the first assessment values higher than a first assessment threshold, add label data to the first behavior data according to the filtered first psychological risk types, and obtain first training data.

[0080] The second processing module is configured to, when a first number of the first training data corresponding to each type of label data reaches a target number, construct the first training data corresponding to each type of label data into a training data set.

[0081] The training module is configured to sequentially train a psychological risk assessment and early warning model using each training data set.

[0082] The trained psychological risk assessment and early warning model is used to perform psychological risk analysis on second behavior data of a second measured object, obtain a second psychological risk type and corresponding second assessment values, and output an early warning signal if any of the second assessment values exceeds a second assessment threshold.

[0083] The embodiment of the present application also discloses an electronic device, which comprises at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, and the computer program is used to realize the method according to any one of the preceding embodiments when executed by the processor.

[0084] The embodiment of the present application also discloses a computer storage medium, which stores a computer program executable by a processor, and the computer program is used to realize the method according to any one of the preceding embodiments when executed by the processor.

[0085] The embodiment of the present application also discloses a computer program product, which comprises a computer program executable by a processor, and the computer program is used to realize the method according to any one of the preceding embodiments when executed by the processor.

[0086] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been described in the above description in a general manner. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0087] The above merely describes specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any skilled person in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present application, and these modifications or replacements should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for constructing a psychological risk assessment and early warning model, characterized in that: The method comprises the following steps: Obtaining first behavioral data of a first subject, performing a risk assessment on the first behavioral data using a psychological risk assessment model, and obtaining a plurality of first psychological risk types and corresponding first assessment values; wherein the psychological risk assessment model may be multiple and used to perform risk assessment on a single type of psychological risk; screening out the first psychological risk types whose first evaluation values ​​are higher than a first evaluation threshold, and adding label data to the first behavior data according to the screened out first psychological risk types to obtain first training data; When the first number of the first training data corresponding to each type of the labeled data reaches a target number, constructing each of the first training data corresponding to the labeled data of the type into a training data set; Using each of the training data sets to train the psychological risk assessment and early warning model in sequence; The trained psychological risk assessment and early warning model is used to perform psychological risk analysis on the second behavioral data of the second measured subject to obtain a second psychological risk type and a corresponding second assessment value, and output a warning signal if any of the second assessment values ​​exceeds a second assessment threshold; Performing a risk assessment on the first behavior data using a psychological risk assessment model to obtain a plurality of first psychological risk types and corresponding first assessment values, including: Performing a risk assessment on the first behavior data using the psychological risk assessment model to obtain a plurality of first psychological risk types and corresponding third assessment values; Determining first behavioral sub-data from different collection sources in the first behavioral data, and calculating a mean of the Euclidean distances between each of the first behavioral sub-data and the corresponding second behavioral sub-data; wherein the second behavioral sub-data is behavioral data corresponding to each collection source and obtained before the first measured subject is communicated with using the first evaluation topic set or the second evaluation topic set; determining an adjustment coefficient according to the mean distance, and adjusting the third assessment value corresponding to each first psychological risk type to the first assessment value using the adjustment coefficient; The target quantity is determined as follows: Calculating a second number of each of the first psychological risk types screened out, and substituting the second number into the following conversion formula to calculate the target number; Where, is the target quantity, is the second number of each of the first psychological risk types screened out, is the number of all known psychological risk types.

2. A method for constructing a psychological risk assessment and early warning model according to claim 1, characterized in that: The obtaining of first behavior data of the first measured object includes: Obtaining historical evaluation records of the first measured object; If the historical evaluation records are empty or all are normal, then use the first evaluation topic set to communicate with the first measured subject; otherwise, use the second evaluation topic set to communicate with the first measured subject; wherein the first evaluation topic set is more likely to arouse emotional fluctuations in the measured subject than the second evaluation topic set; During the communication process, the first behavioral data of the first measured object is collected, and the first behavioral data includes response data to specific questions, body movement data, and facial expression data.

3. The method for constructing a psychological risk assessment and early warning model according to claim 1, wherein: The psychological risk assessment and early warning model is established by the Transformer model.

4. A method for constructing a psychological risk assessment and early warning model according to claim 3, characterized in that: The Transformer model includes multiple attention heads, feedforward layers, and a prediction network; wherein the multiple attention heads and feedforward layers are sequentially connected to form a multi-layer encoder; The attention head is used to convert the input first training data into a query vector, a key vector and a numerical vector, calculate the output of the attention head based on the activation function, and the outputs of multiple attention heads are connected to form a target output; The feedforward layer is used to process the target output to obtain the hidden features of the first training data; The prediction network is used to process the input hidden features and predict a number of psychological risk types and corresponding evaluation values.

5. A psychological risk assessment and early warning model construction system, characterized by: The system includes an acquisition module, a first processing module, a second processing module, and a training module; The acquisition module is configured to acquire first behavioral data of a first subject, perform risk assessment on the first behavioral data using a psychological risk assessment model, and obtain a plurality of first psychological risk types and corresponding first assessment values; wherein the psychological risk assessment model may be multiple and used to perform risk assessment on a single type of psychological risk; The first processing module is configured to screen out the first psychological risk types whose first evaluation values ​​are higher than a first evaluation threshold, and add label data to the first behavior data according to each screened out first psychological risk type to obtain first training data; The second processing module is configured to construct each of the first training data corresponding to the label data of each type into a training data set when the first number of the first training data corresponding to the label data of that type reaches a target number; The training module is used to train the psychological risk assessment and early warning model in sequence using each of the training data sets; The trained psychological risk assessment and early warning model is used to perform psychological risk analysis on the second behavioral data of the second measured subject to obtain a second psychological risk type and a corresponding second assessment value, and output a warning signal if any of the second assessment values ​​exceeds a second assessment threshold; Performing a risk assessment on the first behavior data using a psychological risk assessment model to obtain a plurality of first psychological risk types and corresponding first assessment values, including: Performing a risk assessment on the first behavior data using the psychological risk assessment model to obtain a plurality of first psychological risk types and corresponding third assessment values; Determining first behavioral sub-data from different collection sources in the first behavioral data, and calculating a mean of the Euclidean distances between each of the first behavioral sub-data and the corresponding second behavioral sub-data; wherein the second behavioral sub-data is behavioral data corresponding to each collection source and obtained before the first measured subject is communicated with using the first evaluation topic set or the second evaluation topic set; determining an adjustment coefficient according to the mean distance, and adjusting the third assessment value corresponding to each first psychological risk type to the first assessment value using the adjustment coefficient; The target quantity is determined as follows: Calculating a second number of each of the first psychological risk types screened out, and substituting the second number into the following conversion formula to calculate the target number; Where, is the target quantity, is the second number of each of the first psychological risk types screened out, is the number of all known psychological risk types.

6. An electronic device, characterized in that: The electronic device includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program implements the method according to any one of claims 1 to 4 when executed by the processor.

7. A computer storage medium, characterized in that: The computer storage medium stores a computer program executable by a processor, and the computer program implements the method according to any one of claims 1 to 4 when executed by the processor.

8. A computer program product, characterized in that: The computer program product includes a computer program that can be executed by a processor, and the computer program implements the method according to any one of claims 1 to 4 when executed by the processor.

Images