Mental health dialogue model evaluation method, equipment and medium

Abstract

The invention relates to the technical field of model evaluation, in particular to a psychological health dialogue model evaluation method and device and a medium, and the method comprises the steps: obtaining a psychological consultation data set, extracting the psychological archive of a visitor from the psychological consultation data set, and building a role information base; selecting a visitor psychological file, setting role playing cues, and establishing a virtual visitor and a virtual psychological counselor; inputting the virtual visitor and the virtual psychological counselor into the psychological health dialogue model, setting dialogue constraints, and generating a psychological counseling dialogue; scoring the psychological counseling dialogue by adopting a plurality of different psychological counseling scales to obtain a psychological counseling dialogue score; and calculating the passing rate of all the psychological counseling dialogues by adopting the psychological counseling dialogue scores. According to the method, a psychological counseling dialogue is generated by establishing a virtual visitor and a virtual psychological counseling teacher, and evaluation of a psychological health dialogue model is completed based on the psychological counseling dialogue.

Description

Technical Field

[0001] The present invention relates to the technical field of model evaluation, and in particular to a method, device and medium for evaluating a mental health dialogue model. Background Art

[0002] The mental health dialogue model is often used to provide psychological counseling services. In order to ensure that the mental health dialogue model does not affect the client, it is usually necessary to evaluate the psychological counseling ability of the mental health dialogue model. The evaluation of psychological counseling ability often relies on psychological counseling dialogues. The professional level, communication skills, empathy and adaptability of the mental health dialogue model will be reflected in the actual psychological counseling dialogue. In traditional psychological counseling training and evaluation, it is often necessary to conduct simulated dialogues or experiments with real clients. However, real clients have certain limitations in evaluation. First, each client has large individual differences, such as emotional state, psychological problems, cultural background, etc., which may lead to inconsistent evaluation results and even interfere with the performance of psychological counselors. Secondly, the evaluation process of real clients may be restricted due to privacy protection, emotional fluctuations or ethical issues, and recruiting and matching real clients requires a lot of time and resources. In addition, the feedback cycle of real clients is long, and effective suggestions for improving the mental health dialogue model may not be provided in time.

[0003] In summary, there is an urgent need for a mental health dialogue model evaluation method, device and medium to solve the problems in the existing technology. Summary of the invention

[0004] The present invention aims to provide a method, device and medium for evaluating a psychological health dialogue model. The specific technical scheme is as follows: A method for evaluating a mental health dialogue model comprises the following steps: S1: Obtain a psychological counseling dataset, extract the client's psychological profile from the psychological counseling dataset, and establish a role information database based on the client's psychological profile; S2: Extract a visitor's psychological profile from the role information database, set the visitor's role-playing prompts, and obtain a virtual visitor through the large language model; set the counselor's role-playing prompts, and obtain a virtual counselor through the mental health dialogue model; S3: Input the virtual visitor and virtual counselor into the mental health dialogue model, set dialogue constraints, and generate psychological counseling dialogue; S4: Use multiple different psychological counseling scales to score the psychological counseling dialogue in S3 to obtain a psychological counseling dialogue score, and use the psychological counseling dialogue score to determine whether the psychological counseling dialogue is qualified; S5: Repeat steps S2 to S4 to obtain psychological counseling dialogue scores of multiple psychological counseling dialogues, and use the psychological counseling dialogue scores to calculate the pass rate of all psychological counseling dialogues.

[0005] Optionally, in S1, the elements of the client's psychological profile include gender, age, occupation, cultural background, personality traits, emotions, current distress, and details of distress.

[0006] Optionally, in S1, based on the elements of the client's psychological profile, a large language model is used to extract multiple client psychological profiles from the psychological counseling dataset.

[0007] Optionally, in S2, the client's role-playing prompts include at least one of the following: Talking to a counselor; Simulate natural language expressions based on emotions; Model the client's speaking style and tone based on personality traits; A counseling conversation consists of 25 to 30 rounds of interaction; Psychological counseling dialogues are divided into initial dialogues, mid-term dialogues and late dialogues. Initial dialogues are used to establish trust and emotional connections, mid-term dialogues are used to explain cultural background and current problems, and late dialogues are used to summarize the counseling process. Responses are limited to 2 to 3 sentences per round of interaction.

[0008] Optionally, in S2, the counselor role-playing prompts include at least one of the following: A conversation is ongoing with the visitor; A counseling conversation consists of 25 to 30 rounds of interaction; Psychological counseling dialogues are divided into initial dialogues, mid-term dialogues and late dialogues. In the late dialogue, the counseling is reviewed and the client is guided to summarize. One question is asked at a time during each round of interaction.

[0009] Optionally, in S2, the conversation constraint includes at least one of the following: A counseling conversation consists of 25 to 30 rounds of interaction; The number of rounds in the initial dialogue, mid-term dialogue, and late-term dialogue is limited to 7-10 rounds; The output length of the virtual counselor's response in each round of interaction is 60-100 words.

[0010] Optionally, in S3, the psychological counseling scale includes the client evaluation scale, the supervisor evaluation scale, and the psychological counselor self-evaluation scale.

[0011] Optionally, for the psychological counseling dialogue, the client evaluation scale, the supervisor evaluation scale and the psychological counselor self-evaluation scale are used for scoring. Each scale includes multiple dimension scores. The role score is obtained by averaging the scores of each dimension. The expression is as follows: ; in, Indicates the rating result of the role. Indicates that the role is Ratings for each dimension, It indicates the number of dimensions of the scale, and the role is one of the client, supervisor, and counselor; The role score is compared with a first threshold value, if it exceeds the first threshold value, the evaluation is passed, and if it is lower than the first threshold value, the evaluation is failed; The score of each role is weighted and calculated to obtain the score of the psychological consultation dialogue. The expression is as follows: ; in, For the role The weight and , It indicates the score of psychological consultation dialogue; The psychological counseling dialogue score is compared with a second threshold value, if it exceeds the second threshold value, the evaluation is passed, and if it is lower than the second threshold value, the evaluation is failed; Repeat the above process to obtain the role scores and psychological counseling dialogue scores of all psychological counseling dialogues, and calculate the pass rate of the role scores and psychological counseling dialogue scores of all psychological counseling dialogues.

[0012] In addition, the present invention also includes a computer device, including a memory and a processor; The memory is used to store a computer program executable on the processor; The processor is used to implement the steps of the mental health dialogue model evaluation method as described above when executing the computer program.

[0013] In addition, a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the mental health dialogue model evaluation method as described above are implemented.

[0014] The application of the technical solution of the present invention has the following beneficial effects: The present invention discloses a method for evaluating a mental health dialogue model. The method of the present invention constructs a virtual visitor and a virtual psychological counselor based on a large language model, constructs a psychological counselor dialogue through the mental health dialogue model, and scores the psychological counseling dialogue to evaluate the psychological counseling ability of the mental health dialogue model. The method of the present invention can comprehensively evaluate the coping strategies and the ability to handle complex psychological problems of the mental health dialogue model in different situations by simulating real psychological counseling dialogues, thereby realizing the evaluation of the psychological counseling ability of the mental health dialogue model.

[0015] In addition to the above-described purposes, features and advantages, the present invention has other purposes, features and advantages. The present invention will be further described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of the steps of the mental health dialogue model evaluation method in the preferred embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the scheme of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present invention.

[0019] A method for evaluating a mental health dialogue model comprises the following steps: S1: Obtain a psychological counseling dataset, extract the client's psychological profile from the psychological counseling dataset, and establish a role information database based on the client's psychological profile.

[0020] In this embodiment, the elements of the visitor's psychological profile include gender, age, occupation, cultural background, personality traits, emotions, current distress, distress details and theme. The elements of the visitor's psychological profile are shown in Table 1.

[0021] Table 1 Elements and descriptions of client psychological profiles

[0022] In this embodiment, a large language model can be used to extract multiple visitor psychological profiles from the psychological counseling dataset based on the elements of the visitor's psychological profile. The preferred large language model in this embodiment is GPT-4o mini, and the psychological counseling dataset is the PsyQA dataset. The PsyQA dataset is a Chinese mental health support question and answer dataset that provides rich assistance strategy annotations and can be used to generate long counseling texts rich in assistance strategies. At the same time, the PsyQA dataset contains a variety of common mental health disorders, covering 9 topics, including self-growth, emotions, love problems, interpersonal relationships, behavior, family, treatment, marriage, and career.

[0023] S2: Extract a visitor's psychological profile from the role information library, set the visitor's role-playing prompt words, and obtain a virtual visitor through the large language model; set the counselor's role-playing prompt words, and obtain a virtual counselor through the large language model. Further, in this embodiment, the large language model used to simulate the virtual visitor or virtual counselor can be GPT-4o mini.

[0024] In this embodiment, the visitor role-playing prompt words include at least one of the following: Talking to a counselor; Simulate natural language expressions based on emotions; Model the client's speaking style and tone based on personality traits; A counseling conversation consists of 25 to 30 rounds of interaction; Psychological counseling dialogues are divided into initial dialogues, mid-term dialogues and late dialogues. Initial dialogues are used to establish trust and emotional connections, mid-term dialogues are used to explain cultural background and current problems, and late dialogues are used to summarize the counseling process. Responses are limited to 2 to 3 sentences per round of interaction.

[0025] Furthermore, the psychological counselor role-playing prompts include at least one of the following: A conversation is ongoing with the visitor; A counseling conversation consists of 25 to 30 rounds of interaction; Psychological counseling dialogues are divided into initial dialogues, mid-term dialogues and late dialogues. In the late dialogue, the counseling is reviewed and the client is guided to summarize. One question is asked at a time during each round of interaction.

[0026] Furthermore, the conversation constraints include at least one of the following: A counseling conversation consists of 25 to 30 rounds of interaction; The number of rounds in the initial dialogue, mid-term dialogue, and late-term dialogue is limited to 7-10 rounds; The output length of the virtual counselor's response in each round of interaction is 60-100 words.

[0027] It should be noted that the initial dialogue in this embodiment corresponds to the trust building stage in the psychological counseling dialogue, the mid-term dialogue corresponds to the counseling diagnosis stage, and the late dialogue corresponds to the solution consolidation stage. The descriptions of the three stages are as follows: Trust building stage: Trust building is a crucial step in the consultation process, which provides a foundation for subsequent in-depth discussions and emotional expression. In this stage, the counselor establishes an initial relationship with the client and uses effective communication skills and positive emotional support to make the client feel safe and trusted.

[0028] Consultation and diagnosis stage: In this stage, the counselor will help the client identify the root cause of psychological distress through further dialogue and evaluation. In this process, the counselor will conduct an in-depth analysis of the client's cultural background, emotional state, behavioral patterns and other factors to fully understand the client's psychological condition. This stage not only helps to identify the nature of the problem, but also provides a scientific basis for formulating personalized intervention strategies.

[0029] Solution and consolidation stage: In this stage, the counselor and the client jointly develop a targeted treatment plan and use a series of psychological intervention methods to help the client cope with and solve the problem. In this process, the counselor not only helps the client explore solutions to the problem, but also strives to enhance his ability to cope with stress and emotions to ensure that the problem is effectively alleviated. At the end of this stage, the counselor guides the client to review and summarize the entire counseling process, helping him reflect on his personal growth, consolidate the skills he has learned, and prepare for future challenges.

[0030] S3: Input the virtual visitor and virtual counselor into the mental health dialogue model, set dialogue constraints, and generate psychological counseling dialogue.

[0031] In this embodiment, the psychological counseling scale includes a visitor evaluation scale, a supervisor evaluation scale, and a psychological counselor self-evaluation scale.

[0032] S4: Use multiple different psychological counseling scales to score the psychological counseling dialogue in S3 to obtain a psychological counseling dialogue score, and use the psychological counseling dialogue score to determine whether the psychological counseling dialogue is qualified.

[0033] For psychological counseling conversations, the client evaluation scale, supervisor evaluation scale and counselor self-evaluation scale are used for scoring respectively. This embodiment adopts GPT-4o for scale scoring. Specifically, the client evaluation scale makes a quantitative assessment based on the client's own counseling experience and emotional changes, the supervisor evaluation scale makes a quantitative assessment based on the dimensions of the counselor's professional skills, technical application and ethical norms, and the counselor self-evaluation scale makes a self-reflective assessment based on the counselor's own performance.

[0034] In this embodiment, GPT-4o is used for scale scoring, and the scoring prompt words are set as follows: GPT-4o plays the role of visitor scoring prompts: <task>You are a client with psychological problems. You have just finished a consultation with a psychologist. Please strictly follow the The conversation history and The 16 dimensions in the questionnaire were used to score the psychological consultation. The scoring criteria are: each dimension is scored from 0 to 4, never = 0, rarely = 1, sometimes = 2, most of the time = 3, and always = 4. Note that the scoring should be strictly based on the scoring criteria. Only when the scoring criteria are fully met can the corresponding score be given. Do not give a score other than 0-4. Output each dimension in the following format: \n[Dimension] Dimension name and its specific requirements. \n[Analysis] Dimension scoring analysis. \n[Score] Dimension scoring result.

[0035] <Dialogue History> {Assessed counseling conversation}; <dimensions>{Content of visitor scale}.

[0036] GPT-4o plays the role of supervisor scoring prompts: <task>You are a professional psychological supervisor. I will provide you with the history of psychological counseling dialogues. Please strictly follow The conversation history and The 8 dimensions in the grading system are used to score the competence of psychological counselors. The grading standard is: each dimension is scored from 0 to 4, never = 0, rarely = 1, sometimes = 2, most of the time = 3, and always = 4. Note that the grading should be strictly based on the grading standard. Only when the grading standard is fully met can the corresponding score be given. Do not give a score other than 0-4. Output each dimension in the following format: \n[Dimension] Dimension name and its specific requirements. \n[Analysis] Dimension scoring analysis. \n[Score] Dimension scoring result.

[0037] <Dialogue History> {Assessed counseling conversation}; <dimensions>{Supervision scale content}.

[0038] GPT-4o plays the role of a consultant and gives scoring prompts: <task>You are a professional psychologist. You have just finished a psychological consultation with a client who has psychological problems. Please strictly follow the The conversation history and The 9 dimensions in the questionnaire were used to conduct a self-assessment of psychological counseling ability. The scoring criteria are: each dimension is scored from 0 to 5, with completely unqualified = 0, somewhat unqualified = 1, somewhat unqualified = 2, somewhat compliant = 3, somewhat compliant = 4, and completely compliant = 5. Note that the scoring should be strictly based on the scoring criteria. Only when the scoring criteria are fully met can the corresponding score be given. Do not give any score other than 0-5. Output each dimension in the following format: \n[Dimension] Dimension name and its specific requirements. \n[Analysis] Dimension scoring analysis. \n[Score] Dimension scoring result.

[0039] <Dialogue History> {Assessed counseling conversation}; <dimensions>{Content of counselor scale}.

[0040] Each scale includes multiple dimension scores, and the role score is obtained by averaging the scores of each dimension. The expression is as follows: ; in, Indicates the rating result of the role. Indicates that the role is Ratings for each dimension, It indicates the number of dimensions of the scale, and the role is one of the client, supervisor, and counselor; The role score is compared with a first threshold value, if it exceeds the first threshold value, the evaluation is passed, and if it is lower than the first threshold value, the evaluation is failed; The score of each role is weighted and calculated to obtain the score of the psychological consultation dialogue. The expression is as follows: ; in, For the role The weight and , It indicates the score of psychological consultation dialogue; The psychological counseling dialogue score is compared with a second threshold value, if it exceeds the second threshold value, the evaluation is passed, and if it is lower than the second threshold value, the evaluation is failed; Repeat the above process to obtain the role scores and psychological counseling dialogue scores of all psychological counseling dialogues, and calculate the pass rate of the role scores and psychological counseling dialogue scores of all psychological counseling dialogues.

[0041] S5: Repeat steps S2 to S4 to obtain psychological counseling dialogue scores of multiple psychological counseling dialogues, and use the psychological counseling dialogue scores to calculate the pass rate of all psychological counseling dialogues.

[0042] The experiment of the method of this embodiment is as follows: First, the weight ratio of the visitor evaluation scale, supervisor evaluation scale, and counselor evaluation scale was determined to be 3:4:3, and the threshold was calculated to be 3.3. Based on this, 100 visitor roles were extracted according to different topics to evaluate the psychological counseling capabilities of the five models: GPT-3.5 Turbo, GPT-4o, Tongyi Qianwen 2.5-7B, GLM-4-Flash, and deepseek-chat. The evaluation results are shown in Table 2. The results show that although the deepseek model performs best, there is still a lot of room for improvement.

[0043] Table 2 Model evaluation results

[0044] In addition, this embodiment also discloses a computer device, including a memory and a processor; The memory is used to store a computer program executable on the processor; The processor is used to implement the steps of the above-mentioned mental health dialogue model evaluation method when executing the computer program.

[0045] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the computer device.

[0046] The computer device may be a computing device such as a mobile phone, a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may include, but is not limited to, a processor and a memory. For example, the computer device may also include an input / output device, a network access device, a bus, etc.

[0047] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the computer device, and uses various interfaces and lines to connect various parts of the entire computer device.

[0048] The memory can be used to store the computer program and / or module, and the processor implements the computer program by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0049] Wherein, if the module / unit integrated in the computer device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0050] In addition, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned mental health dialogue model evaluation method are implemented.

[0051] This embodiment discloses a method for evaluating a mental health dialogue model. The method of this embodiment constructs a virtual visitor and a virtual psychological counselor based on a large language model, and constructs a psychological counselor dialogue through a mental health dialogue model. By scoring the psychological counseling dialogue, the psychological counseling ability of the mental health dialogue model is evaluated. By simulating real psychological counseling dialogues, the method of this embodiment can comprehensively evaluate the coping strategies and ability to deal with complex psychological problems of the mental health dialogue model in different situations, thereby realizing the evaluation of the psychological counseling ability of the mental health dialogue model.

[0052] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0053] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.< / dimensions> < / task> < / dimensions> < / task> < / dimensions> < / task>

Claims

1. A method for evaluating a mental health dialogue model, characterized in that: The following steps are involved: S1: Obtain a psychological counseling dataset, extract the client's psychological profile from the psychological counseling dataset, and establish a role information database based on the client's psychological profile; S2: Extract a visitor's psychological profile from the role information database, set the visitor's role-playing prompts, and obtain a virtual visitor through the large language model; set the counselor's role-playing prompts, and obtain a virtual counselor through the mental health dialogue model; S3: Input the virtual visitor and virtual counselor into the mental health dialogue model, set dialogue constraints, and generate psychological counseling dialogue; S4: Use multiple different psychological counseling scales to score the psychological counseling dialogue in S3 to obtain a psychological counseling dialogue score, and use the psychological counseling dialogue score to determine whether the psychological counseling dialogue is qualified; S5: Repeat steps S2 to S4 to obtain psychological counseling dialogue scores of multiple psychological counseling dialogues, and use the psychological counseling dialogue scores to calculate the pass rate of all psychological counseling dialogues.

2. The method for evaluating a mental health dialogue model according to claim 1, characterized in that: In S1, the elements of the client's psychological profile include gender, age, occupation, cultural background, personality traits, emotions, current distress, and details of distress.

3. The method for evaluating a mental health dialogue model according to claim 2, characterized in that: In S1, based on the elements of the client's psychological profile, a large language model is used to extract multiple client psychological profiles from the psychological counseling dataset.

4. The method for evaluating a mental health dialogue model according to claim 3, characterized in that: In S2, the client's role-playing prompts include at least one of the following: Talking to a counselor; Simulate natural language expressions based on emotions; Model the client's speaking style and tone based on personality traits; A counseling conversation consists of 25 to 30 rounds of interaction; Psychological counseling dialogues are divided into initial dialogues, mid-term dialogues and late dialogues. Initial dialogues are used to establish trust and emotional connections, mid-term dialogues are used to explain cultural background and current problems, and late dialogues are used to summarize the counseling process. Responses are limited to 2 to 3 sentences per round of interaction.

5. The method for evaluating a mental health dialogue model according to claim 4, characterized in that: In S2, the counselor role-playing prompts include at least one of the following: A conversation is ongoing with the visitor; A counseling conversation consists of 25 to 30 rounds of interaction; Psychological counseling dialogues are divided into initial dialogues, mid-term dialogues and late dialogues. In the late dialogue, the counseling is reviewed and the client is guided to summarize. One question is asked at a time during each round of interaction.

6. The method for evaluating a mental health dialogue model according to claim 5, characterized in that: In S2, the conversation constraints include at least one of the following: A counseling conversation consists of 25 to 30 rounds of interaction; The number of rounds in the initial dialogue, mid-term dialogue, and late-term dialogue is limited to 7-10 rounds; The output length of the virtual counselor's response in each round of interaction is 60-100 words.

7. The method for evaluating a psychological health dialogue model according to claim 6, characterized in that: In S3, the psychological counseling scale includes the client evaluation scale, the supervisor evaluation scale and the psychological counselor self-evaluation scale.

8. The method for evaluating a mental health dialogue model according to claim 7, characterized in that: For psychological counseling dialogues, the client evaluation scale, supervisor evaluation scale and psychological counselor self-evaluation scale are used for scoring. Each scale includes multiple dimension scores. The role score is obtained by averaging the scores of each dimension. The expression is as follows: ； in, Indicates the rating result of the role. Indicates that the role is Ratings for each dimension, It indicates the number of dimensions of the scale, and the role is one of the client, supervisor, and counselor; The role score is compared with a first threshold value, if it exceeds the first threshold value, the evaluation is passed, and if it is lower than the first threshold value, the evaluation is failed; The score of each role is weighted and calculated to obtain the score of the psychological consultation dialogue. The expression is as follows: ； in, For the role The weight and , It indicates the score of psychological consultation dialogue; The psychological counseling dialogue score is compared with a second threshold value, if it exceeds the second threshold value, the evaluation is passed, and if it is lower than the second threshold value, the evaluation is failed; Repeat the above process to obtain the role scores and psychological counseling dialogue scores of all psychological counseling dialogues, and calculate the pass rate of the role scores and psychological counseling dialogue scores of all psychological counseling dialogues.

9. A computer device, characterized in that: including memory and processor; The memory is used to store a computer program executable on the processor; The processor is used to implement the steps of the mental health dialogue model evaluation method as described in any one of claims 1 to 8 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the mental health dialogue model evaluation method as described in any one of claims 1 to 8.

Images