Intelligent psychosomatic assessment system and method for psychosomatic syndrome

Abstract

The invention discloses an intelligent psychosomatic assessment system and method for psychosomatic syndromes, and relates to the technical field of psychological health assessment, and the system comprises a data collection module which is used for collecting personal information and psychosomatic symptom information, and transmitting the personal information and the psychosomatic symptom information to a data analysis system; the data analysis module is used for carrying out multi-dimensional comprehensive analysis on the personal information and the psychosomatic symptom information to obtain a data score and sending the data score to the data application module, and the multi-dimensional comprehensive analysis comprises facial expression analysis, language expression analysis, sound feature analysis and voice and intonation analysis; and the data application module is used for inputting the data score into a pre-established risk prediction model to obtain a psychosomatic assessment result.

Description

Technical Field

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

[0002] During the course of medical illness, psychological, social, and biological factors interact in a variety of ways. Their different influences determine the patient's unique experience and attitude during a specific illness episode. In the past 10 years, psychosomatic disease has received increasing attention as a major public health issue. Psychosomatic disease is found in all clinical departments and involves various organs and systems of the human body. Foreign surveys have found that the prevalence of psychosomatic disease is 10%-60%; somatization affects up to 30%-40% of medical patients, which is likely to make it the most expensive comorbidity.

[0003] At present, there is a lack of non-psychiatric clinical physicians who are well trained in psychosomatic medicine in China. A large number of patients with psychosomatic diseases repeatedly visit various departments of general hospitals, and their symptoms are lingering, which not only brings great pain to patients, but also wastes medical resources and increases the burden of disease. Due to the low recognition rate of psychosomatic disorders by physicians in general departments or primary medical workers, a considerable number of patients with psychological disorders have no access to medical treatment or are in a "sick" state of repeatedly seeking medical treatment. The existing technology currently has limitations in the classification of psychological distress in medical diseases by diagnostic systems developed in psychiatric settings, especially when physical symptoms are believed to be caused, aggravated or maintained by psychosocial factors. Summary of the invention

[0004] In order to solve the deficiencies mentioned in the above background technology, the object of the present invention is to provide an intelligent psychosomatic assessment system and method for psychosomatic syndrome.

[0005] In a first aspect, the purpose of the present invention can be achieved by the following technical solution: an intelligent psychosomatic assessment system for psychosomatic syndrome, comprising:

[0006] A data collection module, used to collect personal information and psychosomatic symptom information, and send the personal information and psychosomatic symptom information to a data analysis system;

[0007] A data analysis module, used to conduct a comprehensive multi-dimensional analysis of personal information and psychosomatic symptom information, obtain a data score, and send the data score to a data application module, wherein the comprehensive multi-dimensional analysis includes facial expression analysis, language expression analysis, sound feature analysis, and voice intonation analysis;

[0008] The data application module is used to input data scores into a pre-established risk prediction model to obtain psychosomatic assessment results.

[0009] In combination with the first aspect, in certain implementations of the first aspect, the system further includes: the data collection module includes a personal information collection unit and a psychosomatic symptom assessment unit.

[0010] In combination with the first aspect, in certain implementations of the first aspect, the system further includes: the personal information collection unit includes information such as name, gender, age, height, weight, education level, marital status, occupation, past medical history, and smoking and drinking history;

[0011] The psychosomatic symptom assessment unit includes a multi-dimensional psychosomatic symptom assessment scale for stress, disease behavior, psychological performance and personality traits. The output end of the data acquisition module is connected to the input end of the data analysis module through a central management server.

[0012] In combination with the first aspect, in certain implementations of the first aspect, the system also includes: the data analysis module includes a depression assessment unit, an anxiety assessment unit, a sleep disorder assessment unit, a stress assessment unit, an illness behavior assessment unit, a personality trait assessment unit, a happiness assessment unit and a physical and mental health index assessment unit.

[0013] In combination with the first aspect, in certain implementations of the first aspect, the system also includes: the pre-established risk prediction model of the data application module constructs a multifactor logistic regression equation based on multiple factors such as age, gender, education level, body mass index, marital status, occupation, annual family income, smoking status, drinking status and place of residence.

[0014] In combination with the first aspect, in some implementations of the first aspect, the system further includes: the function of the pre-established risk prediction model is as follows:

[0015] ln(p / 1-p)=0.90+1.05*PHQ-9+1.14*GAD-7+1.09*Stress+1.27*Abnormalillness behavior-0.70*Global well-being

[0016] Wherein, ln() is the natural logarithm function, p is the probability of an event occurring, 1-p is the probability of an event not occurring, p / (1-p) is the probability ratio, PHQ-9 is a 9-item health questionnaire, GAD-7 is the Generalized Anxiety Disorder Scale-7, Stress is stress, Abnormal illness behavior is abnormal illness behavior, and Global well-being is overall well-being.

[0017] In combination with the first aspect, in certain implementations of the first aspect, the system also includes: the data application module fits the nonlinear relationship between the independent variable and the dependent variable, and applies restricted cubic spline regression. When the stress score reaches 5 points, the patient's risk of developing psychosomatic disorders increases significantly by 73% compared with the baseline level; when the PHQ-9 score reaches 11 points, the patient's risk of developing psychosomatic disorders increases significantly by 39% compared with the baseline level; when the GAD-7 score reaches 7 points, the patient's risk of developing psychosomatic disorders increases significantly by 53% compared with the baseline level; when the Abnormal illness behavior score reaches 3 points, the patient's risk of developing psychosomatic disorders increases significantly by 130% compared with the baseline level.

[0018] In a second aspect, in order to achieve the above-mentioned object, the present invention discloses an intelligent psychosomatic assessment method for psychosomatic syndrome, the method comprising the following steps:

[0019] Obtain personal information and psychosomatic symptom information;

[0020] Conducting a comprehensive multi-dimensional analysis of personal information and psychosomatic symptom information to obtain a data score, wherein the comprehensive multi-dimensional analysis includes facial expression analysis, language expression analysis, voice feature analysis, and voice intonation analysis;

[0021] The data scores are input into a pre-established risk prediction model to obtain the psychosomatic assessment results.

[0022] In another aspect of the present invention, in order to achieve the above-mentioned purpose, a terminal device is disclosed, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the memory stores a computer program capable of running on the processor, and when the processor loads and executes the computer program, an intelligent psychosomatic assessment system for psychosomatic syndrome as described above is adopted.

[0023] In another aspect of the present invention, in order to achieve the above-mentioned purpose, a computer-readable storage medium is disclosed, in which a computer program is stored. When the computer program is loaded and executed by a processor, the intelligent psychosomatic assessment system for psychosomatic syndrome as described above is adopted.

[0024] Beneficial effects of the present invention:

[0025] The present invention combines multiple artificial intelligence technologies and virtual AI characters to conduct psychosomatic assessments in different clinical populations. At the same time, a new modeling framework is constructed using binary logistic regression and restricted spline regression, which has good prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0028] Figure 2 is a schematic diagram of the nonlinear relationship between at least three DCPR-R diagnoses and different mental health and behavioral indicators in the multivariate restricted spline regression analysis of the present invention;

[0029] Figure 3 It is a schematic diagram of the calibration curve of the prediction model of the present invention;

[0030] Figure 4 is a schematic diagram of the receiver operating characteristic of the prediction model of the present invention;

[0031] Figure 5 It is a schematic diagram of the Bootstrap ROC curve of the prediction model of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] Embodiment 1:

[0034] like Figure 1 As shown, an intelligent psychosomatic assessment system for psychosomatic syndrome comprises:

[0035] A data collection module, used to collect personal information and psychosomatic symptom information, and send the personal information and psychosomatic symptom information to a data analysis system;

[0036] The data collection module includes a personal information collection unit and a psychosomatic symptom assessment unit.

[0037] The personal information collection unit includes the collection of information such as name, gender, age, height, weight, education level, marital status, occupation, past medical history, and smoking and drinking history;

[0038] The psychosomatic symptom assessment unit includes a multi-dimensional psychosomatic symptom assessment scale for stress, disease behavior, psychological performance and personality traits. The output end of the data acquisition module is connected to the input end of the data analysis module through a central management server.

[0039] The multi-dimensional mind-body assessment scale uses the voice and expression of the examinee when answering questions, combined with artificial intelligence technologies such as speech recognition technology, image micro-expression recognition, natural language understanding, and sound feature extraction and analysis, to conduct a multi-dimensional comprehensive analysis of the examinee's facial expression, language expression, sound characteristics, and voice intonation during the entire human-computer interview process. The AI ​​virtual person built into the psychological assessment and psychological counseling functions is formed by combining artificial intelligence with virtual image technology. It not only has a realistic appearance that conforms to the psychological industry, but can also simulate doctors to conduct interviews and assessments on users, and simulate counselors to conduct psychological intervention on users.

[0040] A data analysis module, used to conduct a comprehensive multi-dimensional analysis of personal information and psychosomatic symptom information, obtain a data score, and send the data score to a data application module, wherein the comprehensive multi-dimensional analysis includes facial expression analysis, language expression analysis, sound feature analysis, and voice intonation analysis;

[0041] The data analysis module includes depression assessment unit, anxiety assessment unit, sleep assessment unit, stress assessment unit, disease behavior assessment unit, personality trait assessment unit, happiness assessment unit and physical and mental health index assessment unit. The system comprehensively determines whether the subject is in a normal / depressed / anxious state / psychosomatic disorder and the classification, and analyzes the severity of his or her condition.

[0042] The psychological intervention module is based on CBT, and the training content covers work, study, family, interpersonal relationships, emotions, self-growth, etc. In different counseling theme modules, the artificial intelligence robot will discover the patient's emotional problems and psychological problems based on the patient's self-report, guide him to recognize his own irrational cognition and negative beliefs, and change his views and attitudes towards himself, others or events.

[0043] The data application module is used to input data scores into a pre-established risk prediction model to obtain psychosomatic assessment results.

[0044] The pre-established risk prediction model of the data application module constructs a multivariate logistic regression equation based on multiple factors including age, gender, education level, body mass index, marital status, occupation, annual household income, smoking status, drinking status, and place of residence;

[0045] The function of the pre-established risk prediction model is as follows:

[0046] ln(p / 1-p)=0.90+1.05*PHQ-9+1.14*GAD-7+1.09*Stress+1.27*Abnormalillness behavior-0.70*Global well-being

[0047] Where, ln: natural logarithm function (logarithm function with base e). p: probability of event occurrence. 1-p: probability of event not occurring. p / (1-p): probability ratio. PHQ-9: Patient Health Questionnaire-9. GAD-7: Generalized Anxiety Disorder 7-item Scale. Stress: Stress. Abnormal illness behavior: Abnormal Illness Behavior. Global well-being: Global Well-Being.

[0048] The data application module fits the nonlinear relationship between the independent variables and the dependent variables, and applies restricted cubic spline regression. When the stress score reaches 5 points, the risk of psychosomatic disorders in patients increases significantly by 73% compared with the baseline level; when the PHQ-9 score reaches 11 points, the risk of psychosomatic disorders in patients increases significantly by 39% compared with the baseline level; when the GAD-7 score reaches 7 points, the risk of psychosomatic disorders in patients increases significantly by 53% compared with the baseline level; when the Abnormalillness behavior score reaches 3 points, the risk of psychosomatic disorders in patients increases significantly by 130% compared with the baseline level.

[0049] Specifically, the present invention is further described below by way of embodiments:

[0050] The specific steps of constructing the risk prediction model are as follows:

[0051] After initial contact with interested participants through a general hospital or by telephone, they received an information packet containing general details of the project, an informed consent form, and a questionnaire. The minimum requirement for participation was personal willingness to complete the questionnaire. During the screening process, psychiatric disorders, pregnancy, or lactation were excluded. Eligible patients were clinically interviewed via an online assessment system, and the demographic and clinical characteristics of the subjects are shown in Table 1.

[0052] Table 1. Clinical demographics and clinical characteristics of the subjects

[0053]

[0054]

[0055] Multivariate binary logistic regression analysis was performed on all patients to evaluate predictors of 3 or more DCPR-Rs in the following psychosocial variables: PHQ-9, GAD-7, WHO-5, PSI. The analysis was adjusted for age, sex, education, BMI, marital status, work, annual household income, smoking status, drinking status, place of residence, and disease type. Variance inflation factors were used to assess collinearity for each covariate in the logistic model; there was no evidence of collinearity. The R package ResourceSelection (version 0.3-6) performed the Hosmer-Lemeshow goodness of fit test for binary logistic regression to assess the calibration of the model, and a calibration curve was plotted ( Figure 2 ). Establish a risk prediction model: ln(p / 1-p)=0.90+1.05*PHQ-9+1.14*GAD-7+1.09*Stress+1.27*Abnormal illness behavior-0.70*Global well-being.

[0056] In addition to calibration, the main aspects of evaluating the quality of the model are discrimination. The most common discrimination curve is the ROC curve (Receiver Operating Characteristic), which is drawn with sensitivity as the vertical axis and (1-specificity) as the horizontal axis. It is used to evaluate the prediction accuracy of X (test variable) for Y (state variable) ( Figure 4 ) (R package proc, version: 1.18.5), AUC = 0.908, 95% CI: 0.90-0.92, sensitivity = 0.833; specificity = 0.846, indicating that the model is highly accurate. The bootstrap method was further used for internal validation of the prediction model (R package Cairo, version: 1.6.2), resampling 1000 times, the gray curve is concentrated and close to the red curve, which means that the performance of this prediction model is stable ( Figure 5 ).

[0057] To examine possible nonlinear relationships between a DCPR-R ≥ 3 diagnosis and PSI, PHQ-9, or GAD-7 scores, we adjusted for age, sex, education, body mass index, marital status, occupation, annual household income, smoking status, drinking status, and place of residence using the rms software package (version 6.8-0, https: / / hbiostat.org / R / rms / ) and the ggrcs software package (version 0.3.8). When nonlinearity was detected, the inflection point of the relationship between each variable and a DCPR-R ≥ 3 diagnosis was calculated using a recursive algorithm, and two-stage binary logistic regression models were performed on both sides of the inflection point. Analyses were performed using R (version 4.3.3). P values ​​were two-sided and P values ​​less than 0.05 were considered significant.

[0058] The common predictors of the five clinical populations were analyzed, such as anxiety (GAD-7 score: OR, 1.14, 95% CI, 1.11-1.17; p < 0.01), abnormal illness behavior (OR, 1.27, 95% CI, 1.20-1.35; p < 0.01), and overall well-being (OR, 0.7, 95% CI, 0.66-0.74; p < 0.01) (Table 2).

[0059] Table 2 Common predictors of at least three DCPR-R diagnoses in all populations, multivariate logistic regression analysis

[0060]

[0061] exist Figure 2 The association of psychosocial scores with the risk of DCPR-R was analyzed in . We used restricted cubic splines to flexibly model and display the relationship between various psychosocial scores and the prevalence of having at least three DCPR-R diagnoses. Figure 2 As can be seen in A, the OR value increased with increasing stress scores (stress ≤ 5, OR = 1.73, nonlinear p < 0.001, 95% CI: 1.65 to 1.82); however, no significant association was observed when the stress score reached 5 (p = 0.456). The risk of at least three DCPR-R diagnoses increased steadily with increasing PHQ-9 scores, peaked at scores below 11 (PHQ-9 < 11, OR = 1.39, 95% CI: 1.35 to 1.43), and slightly moderated at higher scores (PHQ-9 ≥ 11, OR = 1.16, nonlinear P < 0.001, 95% CI: 1.12 to 1.20) ( Figure 2 B). A similar pattern was observed for GAD-7 scores ( Figure 2C), with the inflection point occurring at 7 points (OR for GAD-7 < 11 = 1.53, nonlinear P < 0.001, 95% CI: 1.48 to 1.60). When the score for disease behavior abnormality was less than 3, the odds increased significantly (OR = 2.30, nonlinear P < 0.001, 95% CI: 2.16 to 2.50), and when the score exceeded this critical value, the effect decreased (nonlinear P < 0.001), with each standard deviation of the OR increasing by 1.52 (95% CI: 1.39 to 1.67) ( Figure 2 D).

[0062] Embodiment 2: In a second aspect, in order to achieve the above-mentioned purpose, the present invention discloses an intelligent psychosomatic assessment method for psychosomatic syndrome, the method comprising the following steps:

[0063] Obtain personal information and psychosomatic symptom information;

[0064] Conducting a comprehensive multi-dimensional analysis of personal information and psychosomatic symptom information to obtain a data score, wherein the comprehensive multi-dimensional analysis includes facial expression analysis, language expression analysis, voice feature analysis, and voice intonation analysis;

[0065] The data scores are input into a pre-established risk prediction model to obtain the psychosomatic assessment results.

[0066] Specifically, the methods include:

[0067] Step 1: Set up the scale. The test scale includes 6 classic psychosomatic assessment test questions (Chinese version of the Diagnostic Criteria for Psychosomatic Research (CDCPR); Psychosomatic Symptom Scale (PSSS); 9-Item Health Questionnaire (PHQ-9); Generalized Anxiety Disorder Scale (GAD-7); WHO-5 Well-being Index Scale (WHO-5 Well-being Index); Psychosocial Index (PSI)-revised version;

[0068] Step 2: The examinee logs into the user system via PC, iPad or mobile phone and enters the assessor information, including name, gender, age, height, weight, education level, marital status, occupation, past medical history and smoking and drinking history, to collect information.

[0069] Step 3: The subject selects the assessment scale; during the assessment, the subject's voice and facial expression are simultaneously collected when answering questions.

[0070] Step 4: Combine artificial intelligence technologies such as speech recognition technology, image micro-expression recognition, natural language understanding, and sound feature extraction and analysis to conduct a multi-dimensional comprehensive analysis of the subject's facial expressions, language expressions, sound features, and voice intonation throughout the entire human-computer interview process.

[0071] Step 5: Generate an assessment report through multi-dimensional analysis and guide psychological intervention. At the same time, enter the scores in the data analysis module into the risk prediction model to predict individual psychosomatic disorder risk factors.

[0072] Step 6: According to the evaluation report, the system will then carry out a graded treatment. The system will match the corresponding psychological intervention according to the most prominent problem factors. The psychological intervention module is based on CBT, and the training content covers work, study, family, interpersonal relationships, emotions, mood, self-growth and other aspects.

[0073] Based on the same inventive concept, the present invention also provides a computer device, which includes: one or more processors, and a memory for storing one or more computer programs; the program includes program instructions, and the processor is used to execute the program instructions stored in the memory. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is used to implement one or more instructions, specifically for loading and executing one or more instructions in a computer storage medium to implement the above method.

[0074] It needs to be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium, on which a computer program is stored, and the computer program is executed by a processor to execute the above method. The storage medium can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electrical, magnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0075] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0076] The above shows and describes the basic principles, main features and advantages of the present disclosure. Those skilled in the art should understand that the present disclosure is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present disclosure. Without departing from the spirit and scope of the present disclosure, the present disclosure may have various changes and improvements, and these changes and improvements fall within the scope of the present disclosure to be protected.

Claims

1. An intelligent psychosomatic assessment system for psychosomatic syndrome, characterized in that: include: A data collection module, used to collect personal information and psychosomatic symptom information, and send the personal information and psychosomatic symptom information to a data analysis system; A data analysis module, used to conduct a comprehensive multi-dimensional analysis of personal information and psychosomatic symptom information, obtain a data score, and send the data score to a data application module, wherein the comprehensive multi-dimensional analysis includes facial expression analysis, language expression analysis, sound feature analysis, and voice intonation analysis; The data application module is used to input data scores into a pre-established risk prediction model to obtain psychosomatic assessment results.

2. An intelligent psychosomatic assessment system for psychosomatic syndrome according to claim 1, characterized in that: The data collection module includes a personal information collection unit and a psychosomatic symptom assessment unit.

3. An intelligent psychosomatic assessment system for psychosomatic syndrome according to claim 2, characterized in that: The personal information collection unit includes the collection of name, gender, age, height, weight, education level, marital status, occupation, past medical history, and smoking and drinking history; The psychosomatic symptom assessment unit includes a multi-dimensional psychosomatic symptom assessment scale for stress, disease behavior, psychological performance and personality traits. The output end of the data acquisition module is connected to the input end of the data analysis module through a central management server.

4. The intelligent psychosomatic assessment system for psychosomatic syndrome according to claim 1, characterized in that: The data analysis module includes a depression assessment unit, an anxiety assessment unit, a sleep disorder assessment unit, a stress assessment unit, an illness behavior assessment unit, a personality trait assessment unit, a happiness assessment unit and a physical and mental health index assessment unit.

5. The intelligent psychosomatic assessment system for psychosomatic syndrome according to claim 1, characterized in that: The pre-established risk prediction model of the data application module constructs a multi-factor logistic regression equation based on multiple factors such as age, gender, education level, body mass index, marital status, occupation, annual family income, smoking status, drinking status and place of residence.

6. The intelligent psychosomatic assessment system for psychosomatic syndrome according to claim 5, characterized in that: The function of the pre-established risk prediction model is as follows: ln(p / 1-p)=0.90+1.05*PHQ-9+1.14*GAD-7+1.09*Stress+1.27*Abnormal illnessbehavior-0.70*Globalwell-being Wherein, ln() is the natural logarithm function, p is the probability of an event occurring, 1-p is the probability of an event not occurring, p / (1-p) is the probability ratio, PHQ-9 is a 9-item health questionnaire, GAD-7 is the Generalized Anxiety Disorder Scale-7, Stress is stress, Abnormal illness behavior is abnormal illness behavior, and Global well-being is overall well-being.

7. An intelligent psychosomatic assessment system for psychosomatic syndrome according to claim 6, characterized in that: The data application module fits the nonlinear relationship between the independent variable and the dependent variable, and applies restricted cubic spline regression. When the stress score reaches 5 points, the risk of patients developing psychosomatic disorders increases significantly by 73% compared with the baseline level; when the PHQ-9 score reaches 11 points, the risk of patients developing psychosomatic disorders increases significantly by 39% compared with the baseline level; when the GAD-7 score reaches 7 points, the risk of patients developing psychosomatic disorders increases significantly by 53% compared with the baseline level; when the Abnormalillness behavior score reaches 3 points, the risk of patients developing psychosomatic disorders increases significantly by 130% compared with the baseline level.

8. An intelligent psychosomatic assessment method for psychosomatic syndrome, characterized in that: The method comprises the following steps: Obtain personal information and psychosomatic symptom information; Conducting a comprehensive multi-dimensional analysis of personal information and psychosomatic symptom information to obtain a data score, wherein the comprehensive multi-dimensional analysis includes facial expression analysis, language expression analysis, voice feature analysis, and voice intonation analysis; The data scores are input into a pre-established risk prediction model to obtain the psychosomatic assessment results.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: The memory stores a computer program that can be run on the processor. When the processor loads and executes the computer program, an intelligent psychosomatic assessment system for psychosomatic syndrome according to any one of claims 1 to 7 is adopted.

10. A computer-readable storage medium having a computer program stored therein, characterized in that: When the computer program is loaded and executed by the processor, an intelligent psychosomatic assessment system for psychosomatic syndrome according to any one of claims 1 to 7 is adopted.

Images