Psychological health evaluation method and system based on game scene

Abstract

The invention provides a psychological health evaluation method and system based on a game scene in the technical field of psychological health evaluation. The method comprises the steps that S1, a large number of psychological health scales are created and obtained and analyzed to obtain a plurality of psychological scale question and answer data; s2, converting the psychological scale question and answer data into corresponding game videos through a text video artificial intelligence technology; s3, classifying the game videos, and setting game scenes, game difficulty, interaction modes and scores corresponding to the interaction modes of the game videos; s4, performing mental health evaluation based on each game video, and obtaining interaction data and an accumulated score in the mental health evaluation process; and S5, generating a psychological health evaluation report based on the interaction data and the accumulated score, displaying the psychological health evaluation report, and pushing and storing the psychological health evaluation report. The method has the advantage that the accuracy and reliability of mental health evaluation are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mental health assessment, and in particular to a mental health assessment method and system based on game scenarios. Background Art

[0002] When people have mental health problems, they need to seek help from a psychologist, who will conduct a mental health assessment and then adopt corresponding psychological counseling or treatment plans based on the assessment results.

[0003] Traditionally, mental health assessment has been done using mental health scales, such as questionnaires and interviews. However, traditional methods usually rely on the subjective statements and completion of the test subjects, which may be affected by social desirability effects and memory biases, thereby reducing the accuracy and reliability of the assessment results.

[0004] Therefore, how to provide a mental health assessment method and system based on game scenarios to improve the accuracy and reliability of mental health assessment has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a mental health assessment method and system based on game scenarios to improve the accuracy and reliability of mental health assessment.

[0006] In a first aspect, the present invention provides a method for evaluating mental health based on a game scenario, comprising the following steps:

[0007] Step S1, creating a database, obtaining a large number of mental health scales, parsing each mental health scale to obtain a number of mental health scale question and answer data, and storing each mental health scale question and answer data in a structured manner in the database;

[0008] Step S2: using the Wensheng video artificial intelligence technology, converting each psychological scale question and answer data in the database into a corresponding game video, and storing each game video in a structured manner in the database;

[0009] Step S3, classifying each of the game videos, and setting the game scene, game difficulty, interaction mode and the score corresponding to the interaction mode of each of the game videos;

[0010] Step S4: performing a mental health assessment based on each of the game videos, and obtaining interaction data and accumulated scores during the mental health assessment;

[0011] Step S5: perform big data analysis of the interaction behavior on the interaction data, generate a mental health assessment report with the assessment time based on the big data analysis results and the cumulative score, display the mental health assessment report in real time on a display screen, encrypt the mental health assessment report into an encrypted report, push the encrypted report in real time to a pre-associated mobile terminal, and store and distribute the encrypted report.

[0012] Furthermore, in step S1, the psychological scale question and answer data includes psychological scale questions, psychological scale answers, and scores corresponding to each psychological scale answer.

[0013] Furthermore, the step S2 is specifically as follows:

[0014] The psychological scale question and answer data in the database are respectively input into a pre-trained text encoder to obtain the corresponding semantic vector:

[0015] Z T =E text (T);

[0016] Among them, Z T represents the semantic vector; E text () represents text encoder; T represents psychological scale question and answer data;

[0017] Each of the semantic vectors is converted into a corresponding video frame through a diffusion model; the conversion process of the diffusion model is as follows:

[0018] Get a real image, add noise to the real image step by step for forward diffusion, so as to obtain a completely random noise image:

[0019]

[0020] Among them, x t represents the noise image obtained by adding noise to the real image in t steps; x t-1 represents the noise image obtained by adding noise to the real image in t-1 steps; β t represents the noise parameter of the noise added in step t; I represents the identity matrix; q(x t x t-1 ) means generating x at step t t and generate x at step t-1 t-1 The probability distribution of ; N() represents the multivariate Gaussian distribution function; Indicates that from is the mean, and β t I is the covariance of the multivariate Gaussian distribution and x is obtained by sampling t ;

[0021] For the noise image xt Step by step, remove the noise and perform reverse diffusion to get the video frame x 0 :

[0022]

[0023] Among them, p θ (x t-1 |x t ,Z T ) means that given x t and Z T , generating x t-1 The conditional probability distribution of θ (x t ,Z T ) represents the pixel mean of the noise image predicted by the semantic vector; Indicates the noise size in the denoising process, which is a scalar parameter learned by the neural network; represents the covariance matrix of the normal distribution;

[0024] Based on each of the video frames x 0 Generate corresponding game videos, and store each of the game videos in a structured manner in a database.

[0025] Furthermore, the step S3 is specifically as follows:

[0026] Classifying each of the game videos based on a preset game type, wherein the game type at least includes adventure, puzzle, and role-playing;

[0027] Setting a game background story, task objectives and game elements based on the psychological scale question and answer data, and associating them with each video frame in the game video to set a game scene for each game video; the game elements include at least characters, environments and props;

[0028] Then, the game difficulty, interaction mode and score corresponding to the interaction mode of each game video are set; the interaction mode is selection, clicking, dragging or voice input.

[0029] Furthermore, the step S4 is specifically as follows:

[0030] The selected game videos are displayed in sequence based on a preset display order, and mental health assessment is performed by interaction through the game videos. Interaction data including at least interaction operations, reaction time of each interaction operation, selection preference and accuracy rate in the mental health assessment process are obtained, the game difficulty of the game video is dynamically adjusted based on the reaction time, and the scores obtained from each game video are accumulated to obtain a cumulative score.

[0031] In a second aspect, the present invention provides a mental health assessment system based on a game scenario, comprising the following modules:

[0032] A psychological scale question and answer data acquisition module is used to create a database, acquire a large number of psychological health scales, parse each of the psychological health scales to obtain a number of psychological scale question and answer data, and store each of the psychological scale question and answer data in a structured manner in the database;

[0033] A game video generation module, used to convert each psychological scale question and answer data in the database into a corresponding game video through the Wensheng video artificial intelligence technology, and store each of the game videos in a structured manner in the database;

[0034] A game video configuration module, used to classify each of the game videos, and set the game scene, game difficulty, interaction mode and the score corresponding to the interaction mode of each of the game videos;

[0035] A mental health assessment module, used to conduct a mental health assessment based on each of the game videos, and obtain interaction data and accumulated scores during the mental health assessment process;

[0036] A mental health assessment report generation module is used to perform big data analysis of the interactive behavior of the interactive data, generate a mental health assessment report with the assessment time based on the big data analysis results and the cumulative score, display the mental health assessment report in real time through a display screen, encrypt the mental health assessment report into an encrypted report, push the encrypted report in real time to a pre-associated mobile terminal, and store and distribute the encrypted report.

[0037] Furthermore, in the psychological scale question and answer data acquisition module, the psychological scale question and answer data includes psychological scale questions, psychological scale answers, and scores corresponding to each psychological scale answer.

[0038] Furthermore, the game video generation module is specifically used for:

[0039] The psychological scale question and answer data in the database are respectively input into a pre-trained text encoder to obtain the corresponding semantic vector:

[0040] Z T =E text (T);

[0041] Among them, Z T represents the semantic vector; E text () represents text encoder; T represents psychological scale question and answer data;

[0042] Each of the semantic vectors is converted into a corresponding video frame through a diffusion model; the conversion process of the diffusion model is as follows:

[0043] Get a real image, add noise to the real image step by step for forward diffusion, so as to obtain a completely random noise image:

[0044]

[0045] Among them, x t represents the noise image obtained by adding noise to the real image in t steps; x t-1 represents the noise image obtained by adding noise to the real image in t-1 steps; β t represents the noise parameter of the noise added in step t; I represents the identity matrix; q(x t x t-1 ) means generating x at step t t and generate x at step t-1 t-1 The probability distribution of ; N() represents the multivariate Gaussian distribution function; Indicates that from is the mean, and β t I is the covariance of the multivariate Gaussian distribution and x is obtained by sampling t ;

[0046] For the noise image x t Step by step, remove the noise and perform reverse diffusion to get the video frame x 0 :

[0047]

[0048] Among them, p θ (x t-1 |x t ,Z T ) means that given x t and Z T , generating x t-1 The conditional probability distribution of θ (x t ,Z T ) represents the pixel mean of the noise image predicted by the semantic vector; Indicates the noise size in the denoising process, which is a scalar parameter learned by the neural network; represents the covariance matrix of the normal distribution;

[0049] Based on each of the video frames x 0 Generate corresponding game videos, and store each of the game videos in a structured manner in a database.

[0050] Furthermore, the game video configuration module is specifically used for:

[0051] Classifying each of the game videos based on a preset game type, wherein the game type at least includes adventure, puzzle, and role-playing;

[0052] Setting a game background story, task objectives and game elements based on the psychological scale question and answer data, and associating them with each video frame in the game video to set a game scene for each game video; the game elements at least include characters, environments and props;

[0053] Then, the game difficulty, interaction mode and score corresponding to the interaction mode of each game video are set; the interaction mode is selection, clicking, dragging or voice input.

[0054] Furthermore, the mental health assessment module is specifically used to:

[0055] The selected game videos are displayed in sequence based on a preset display order, and mental health assessment is performed by interaction through the game videos. Interaction data including at least interaction operations, reaction time of each interaction operation, selection preference and accuracy rate in the mental health assessment process are obtained, the game difficulty of the game video is dynamically adjusted based on the reaction time, and the scores obtained from each game video are accumulated to obtain a cumulative score.

[0056] The advantages of the present invention are:

[0057] 1. Obtain a large number of mental health scales, parse each mental health scale to obtain several psychological scale question and answer data, and store each psychological scale question and answer data in a structured manner in the created database; then, through the Wensheng video artificial intelligence technology, convert each psychological scale question and answer data in the database into corresponding game videos, and store each game video in a structured manner in the database; then classify each game video, and set the game scene, game difficulty, interaction method and the score corresponding to the interaction method for each game video; then conduct a mental health assessment based on each game video, obtain the interaction data and cumulative score during the mental health assessment process; finally, conduct an interactive operation on the interaction data For big data analysis, based on the big data analysis results and the accumulated scores, a mental health assessment report with the assessment time is generated, the mental health assessment report is displayed in real time through the display screen, the mental health assessment report is encrypted into an encrypted report and pushed to the pre-associated mobile terminal, and the encrypted report is stored and distributedly backed up; that is, the traditional mental health scale is converted into a game video for mental health assessment, so as to improve the interactivity and fun of the mental health assessment, increase the participation of the test subjects, reduce fatigue and resistance during the assessment process, and minimize the impact of social expectation effect and memory bias, ultimately greatly improving the accuracy and reliability of the mental health assessment.

[0058] 2. By encrypting the mental health assessment report into an encrypted report, pushing the encrypted report to the pre-associated mobile terminal in real time, and storing and distributing the encrypted report, it not only ensures the security of the storage and push of the mental health assessment report, thereby protecting user privacy, but also facilitates later traceability. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The present invention will be further described below in conjunction with embodiments with reference to the accompanying drawings.

[0060] Figure 1 It is a flow chart of a mental health assessment method based on a game scenario of the present invention.

[0061] Figure 2 It is a structural schematic diagram of a mental health assessment system based on a game scenario of the present invention. DETAILED DESCRIPTION

[0062] The overall idea of ​​the technical solution in the embodiments of the present application is as follows: converting the traditional mental health scale into a game video for mental health assessment to improve the interactivity and fun of the mental health assessment, minimize the impact of the social expectation effect and memory bias, and thereby improve the accuracy and reliability of the mental health assessment.

[0063] Please refer to Figure 1 to Figure 2 As shown, a preferred embodiment of a mental health assessment method based on a game scenario of the present invention comprises the following steps:

[0064] Step S1, creating a database, obtaining a large number of mental health scales, parsing each mental health scale to obtain a number of mental health scale question and answer data, and storing each mental health scale question and answer data in a structured manner in the database;

[0065] Step S2: using the Wensheng video artificial intelligence technology, converting each psychological scale question and answer data in the database into a corresponding game video, and storing each game video in a structured manner in the database; that is, reconstructing the psychological scale question and answer data and presenting it in the form of a game video;

[0066] Step S3, classifying each of the game videos, and setting the game scene, game difficulty, interaction mode and the score corresponding to the interaction mode of each of the game videos;

[0067] Step S4: performing a mental health assessment based on each of the game videos, and obtaining interaction data and accumulated scores during the mental health assessment;

[0068] Step S5: perform big data analysis of the interaction behavior on the interaction data, generate a mental health assessment report with the assessment time based on the big data analysis results and the cumulative score, display the mental health assessment report in real time on a display screen, encrypt the mental health assessment report into an encrypted report, push the encrypted report in real time to a pre-associated mobile terminal, and store and distribute the encrypted report.

[0069] By encrypting the mental health assessment report into an encrypted report, pushing the encrypted report to the pre-associated mobile terminal in real time, and storing and distributing the encrypted report, it not only ensures the security of the storage and push of the mental health assessment report, thereby protecting user privacy, but also facilitates subsequent traceability.

[0070] The step of encrypting the mental health assessment report into an encrypted report is specifically as follows:

[0071] The mental health assessment report is encrypted into first-level encrypted data by the RC6 algorithm, each character of the first-level encrypted data is shifted right by 9 bits to obtain second-level encrypted data, the second-level encrypted data is encrypted by the 3DES algorithm to obtain third-level encrypted data, the third-level encrypted data is mapped based on a preset mapping rule to obtain fourth-level encrypted data, the number 8 and the letter B in the fourth-level encrypted data are swapped to obtain fifth-level encrypted data, and the fifth-level encrypted data is encrypted by the ChaCha20 algorithm to obtain an encrypted report.

[0072] The mental health assessment report is encrypted into first-level encrypted data through the RC6 algorithm, and each character of the first-level encrypted data is shifted right by 9 bits to obtain second-level encrypted data. The second-level encrypted data is encrypted through the 3DES algorithm to obtain third-level encrypted data. The third-level encrypted data is encrypted based on the mapping rule to obtain fourth-level encrypted data. The number 8 and the letter B in the fourth-level encrypted data are swapped to obtain fifth-level encrypted data. The fifth-level encrypted data is encrypted through the ChaCha20 algorithm to obtain an encrypted report. If the corresponding encryption algorithm or data transformation rule is not known, the encrypted report cannot be cracked. At least 6 security measures are taken before and after (RC6 algorithm, character shift right by 9 bits, 3DES algorithm, mapping rule, swapping the number 8 and the letter B, ChaCha20 algorithm), which greatly improves the security of the storage and push of the mental health assessment report.

[0073] The decryption process of the encrypted report is as follows: decrypt the encrypted report through the ChaCha20 algorithm to obtain level-five encrypted data, swap the number 8 and the letter B in the level-five encrypted data to obtain level-four encrypted data, map the level-four encrypted data based on a preset mapping rule to obtain level-three encrypted data, decrypt the level-three encrypted data through the 3DES algorithm to obtain level-two encrypted data, shift each character of the level-two encrypted data to the left by 9 bits to obtain level-one encrypted data, and decrypt the level-one encrypted data into a mental health assessment report through the RC6 algorithm.

[0074] In step S1, the psychological scale question and answer data includes psychological scale questions, psychological scale answers, and scores corresponding to each psychological scale answer.

[0075] The step S2 is specifically as follows:

[0076] The psychological scale question and answer data in the database are respectively input into a pre-trained text encoder to obtain the corresponding semantic vector:

[0077] Z T =E text (T);

[0078] Among them, Z T represents the semantic vector; E text () represents a text encoder; T represents psychological scale question and answer data; the text encoder adopts CLIP (Contrast ive Language-Image Pretraining);

[0079] Each of the semantic vectors is converted into a corresponding video frame through a diffusion model; the conversion process of the diffusion model is as follows:

[0080] Get a real image, add noise to the real image step by step for forward diffusion, so as to obtain a completely random noise image:

[0081]

[0082] Among them, x t represents the noise image obtained by adding noise to the real image in t steps; x t-1 represents the noise image obtained by adding noise to the real image in t-1 steps; β t represents the noise parameter of the noise added in step t; I represents the identity matrix; q(x t x t-1 ) means generating x at step t t and generate x at step t-1 t-1 The probability distribution of ; N() represents the multivariate Gaussian distribution function; Indicates that from is the mean, and β t I is the covariance of the multivariate Gaussian distribution and x is obtained by sampling t ;

[0083] For the noise image x t Step by step, remove the noise and perform reverse diffusion to get the video frame x 0 :

[0084]

[0085] Among them, p θ (x t-1 x t ,Z T ) means that given x t and Z T , generating x t-1 The conditional probability distribution of θ (x t ,Z T ) represents the pixel mean of the noise image predicted by the semantic vector; Indicates the noise size in the denoising process, which is a scalar parameter learned by the neural network; represents the covariance matrix of the normal distribution;

[0086] Based on each of the video frames x 0 Generate corresponding game videos, and store each of the game videos in a structured manner in a database.

[0087] The step S3 is specifically as follows:

[0088] Classifying each of the game videos based on a preset game type, wherein the game type at least includes adventure, puzzle, and role-playing;

[0089] Setting a game background story, task objectives and game elements based on the psychological scale question and answer data, and associating them with each video frame in the game video to set a game scene for each game video; the game elements at least include characters, environments and props;

[0090] Then, the game difficulty, interaction mode and score corresponding to the interaction mode of each game video are set; the interaction mode is selection, clicking, dragging or voice input.

[0091] The step S4 is specifically as follows:

[0092] The selected game videos are displayed in sequence based on a preset display order, and mental health assessment is performed by interaction through the game videos. Interaction data including at least interaction operations, reaction time of each interaction operation, selection preference and accuracy rate in the mental health assessment process are obtained. The game difficulty of the game video is dynamically adjusted based on the reaction time to ensure that the test subject is not likely to feel uncomfortable, and the scores obtained from each game video are accumulated to obtain a cumulative score.

[0093] In specific implementation, the corresponding game video can be selected for mental health assessment based on the user portrait generated based on age, gender, occupation, educational background, and marital status.

[0094] A preferred embodiment of a mental health assessment system based on a game scenario of the present invention includes the following modules:

[0095] A psychological scale question and answer data acquisition module is used to create a database, acquire a large number of psychological health scales, parse each of the psychological health scales to obtain a number of psychological scale question and answer data, and store each of the psychological scale question and answer data in a structured manner in the database;

[0096] A game video generation module is used to convert each psychological scale question and answer data in the database into a corresponding game video through the Wensheng video artificial intelligence technology, and store each of the game videos in a structured manner in the database; that is, to reconstruct the psychological scale question and answer data and present it in the form of a game video;

[0097] A game video configuration module, used to classify each of the game videos, and set the game scene, game difficulty, interaction mode and the score corresponding to the interaction mode of each of the game videos;

[0098] A mental health assessment module, used to conduct a mental health assessment based on each of the game videos, and obtain interaction data and accumulated scores during the mental health assessment process;

[0099] A mental health assessment report generation module is used to perform big data analysis of the interactive behavior of the interactive data, generate a mental health assessment report with the assessment time based on the big data analysis results and the cumulative score, display the mental health assessment report in real time through a display screen, encrypt the mental health assessment report into an encrypted report, push the encrypted report in real time to a pre-associated mobile terminal, and store and distribute the encrypted report.

[0100] By encrypting the mental health assessment report into an encrypted report, pushing the encrypted report to the pre-associated mobile terminal in real time, and storing and distributing the encrypted report, it not only ensures the security of the storage and push of the mental health assessment report, thereby protecting user privacy, but also facilitates subsequent traceability.

[0101] The step of encrypting the mental health assessment report into an encrypted report is specifically as follows:

[0102] The mental health assessment report is encrypted into first-level encrypted data by the RC6 algorithm, each character of the first-level encrypted data is shifted right by 9 bits to obtain second-level encrypted data, the second-level encrypted data is encrypted by the 3DES algorithm to obtain third-level encrypted data, the third-level encrypted data is mapped based on a preset mapping rule to obtain fourth-level encrypted data, the number 8 and the letter B in the fourth-level encrypted data are swapped to obtain fifth-level encrypted data, and the fifth-level encrypted data is encrypted by the ChaCha20 algorithm to obtain an encrypted report.

[0103] The mental health assessment report is encrypted into first-level encrypted data through the RC6 algorithm, and each character of the first-level encrypted data is shifted right by 9 bits to obtain second-level encrypted data. The second-level encrypted data is encrypted through the 3DES algorithm to obtain third-level encrypted data. The third-level encrypted data is encrypted based on the mapping rule to obtain fourth-level encrypted data. The number 8 and the letter B in the fourth-level encrypted data are swapped to obtain fifth-level encrypted data. The fifth-level encrypted data is encrypted through the ChaCha20 algorithm to obtain an encrypted report. If the corresponding encryption algorithm or data transformation rule is not known, the encrypted report cannot be cracked. At least 6 security measures are taken before and after (RC6 algorithm, character shift right by 9 bits, 3DES algorithm, mapping rule, swapping the number 8 and the letter B, ChaCha20 algorithm), which greatly improves the security of the storage and push of the mental health assessment report.

[0104] The decryption process of the encrypted report is as follows: decrypt the encrypted report through the ChaCha20 algorithm to obtain level-five encrypted data, swap the number 8 and the letter B in the level-five encrypted data to obtain level-four encrypted data, map the level-four encrypted data based on a preset mapping rule to obtain level-three encrypted data, decrypt the level-three encrypted data through the 3DES algorithm to obtain level-two encrypted data, shift each character of the level-two encrypted data to the left by 9 bits to obtain level-one encrypted data, and decrypt the level-one encrypted data into a mental health assessment report through the RC6 algorithm.

[0105] In the psychological scale question and answer data acquisition module, the psychological scale question and answer data includes psychological scale questions, psychological scale answers, and scores corresponding to each psychological scale answer.

[0106] The game video generation module is specifically used for:

[0107] The psychological scale question and answer data in the database are respectively input into a pre-trained text encoder to obtain the corresponding semantic vector:

[0108] Z T =Etext (T);

[0109] Among them, Z T represents the semantic vector; E text () represents a text encoder; T represents psychological scale question and answer data; the text encoder adopts CLIP (Contrast ive Language-Image Pretraining);

[0110] Each of the semantic vectors is converted into a corresponding video frame through a diffusion model; the conversion process of the diffusion model is as follows:

[0111] Get a real image, add noise to the real image step by step for forward diffusion, so as to obtain a completely random noise image:

[0112]

[0113] Among them, x t represents the noise image obtained by adding noise to the real image in t steps; x t-1 represents the noise image obtained by adding noise to the real image in t-1 steps; β t represents the noise parameter of the noise added in step t; I represents the identity matrix; q(x t x t-1 ) means generating x at step t t and generate x at step t-1 t-1 The probability distribution of ; N() represents the multivariate Gaussian distribution function; Indicates that from is the mean, and β t I is the covariance of the multivariate Gaussian distribution and x is obtained by sampling t ;

[0114] For the noise image x t Step by step, remove the noise and perform reverse diffusion to get the video frame x 0 :

[0115]

[0116] Among them, p θ (x t-1 x t ,Z T ) means that given x t and Z T , generating x t-1 The conditional probability distribution of θ (x t ,Z T ) represents the pixel mean of the noise image predicted by the semantic vector; Indicates the noise size in the denoising process, which is a scalar parameter learned by the neural network; represents the covariance matrix of the normal distribution;

[0117] Based on each of the video frames x 0 Generate corresponding game videos, and store each of the game videos in a structured manner in a database.

[0118] The game video configuration module is specifically used for:

[0119] Classifying each of the game videos based on a preset game type, wherein the game type at least includes adventure, puzzle, and role-playing;

[0120] Setting a game background story, task objectives and game elements based on the psychological scale question and answer data, and associating them with each video frame in the game video to set a game scene for each game video; the game elements at least include characters, environments and props;

[0121] Then, the game difficulty, interaction mode and score corresponding to the interaction mode of each game video are set; the interaction mode is selection, clicking, dragging or voice input.

[0122] The mental health assessment module is specifically used for:

[0123] The selected game videos are displayed in sequence based on a preset display order, and mental health assessment is performed by interaction through the game videos. Interaction data including at least interaction operations, reaction time of each interaction operation, selection preference and accuracy rate in the mental health assessment process are obtained. The game difficulty of the game video is dynamically adjusted based on the reaction time to ensure that the test subject is not likely to feel uncomfortable, and the scores obtained from each game video are accumulated to obtain a cumulative score.

[0124] In specific implementation, the corresponding game video can be selected for mental health assessment based on the user portrait generated based on age, gender, occupation, educational background, and marital status.

[0125] In summary, the advantages of the present invention are:

[0126] 1. Obtain a large number of mental health scales, parse each mental health scale to obtain several psychological scale question and answer data, and store each psychological scale question and answer data in a structured manner in the created database; then, through the Wensheng video artificial intelligence technology, convert each psychological scale question and answer data in the database into corresponding game videos, and store each game video in a structured manner in the database; then classify each game video, and set the game scene, game difficulty, interaction method and the score corresponding to the interaction method for each game video; then conduct a mental health assessment based on each game video, obtain the interaction data and cumulative score during the mental health assessment process; finally, conduct an interactive operation on the interaction data For big data analysis, based on the big data analysis results and the accumulated scores, a mental health assessment report with the assessment time is generated, the mental health assessment report is displayed in real time through the display screen, the mental health assessment report is encrypted into an encrypted report and pushed to the pre-associated mobile terminal, and the encrypted report is stored and distributedly backed up; that is, the traditional mental health scale is converted into a game video for mental health assessment, so as to improve the interactivity and fun of the mental health assessment, increase the participation of the test subjects, reduce fatigue and resistance during the assessment process, and minimize the impact of social expectation effect and memory bias, ultimately greatly improving the accuracy and reliability of the mental health assessment.

[0127] 2. By encrypting the mental health assessment report into an encrypted report, pushing the encrypted report to the pre-associated mobile terminal in real time, and storing and distributing the encrypted report, it not only ensures the security of the storage and push of the mental health assessment report, thereby protecting user privacy, but also facilitates later traceability.

[0128] Although the specific implementation modes of the present invention are described above, those skilled in the art should understand that the specific implementation modes described are only illustrative and are not intended to limit the scope of the present invention. Equivalent modifications and changes made by those skilled in the art in accordance with the spirit of the present invention should be included in the scope of protection of the claims of the present invention.

Claims

1. A mental health assessment method based on game scenarios, characterized by: The steps include: Step S1, creating a database, obtaining a large number of mental health scales, parsing each mental health scale to obtain a number of mental health scale question and answer data, and storing each mental health scale question and answer data in a structured manner in the database; Step S2: using the Wensheng video artificial intelligence technology, converting each psychological scale question and answer data in the database into a corresponding game video, and storing each game video in a structured manner in the database; Step S3, classifying each of the game videos, and setting the game scene, game difficulty, interaction mode and the score corresponding to the interaction mode of each of the game videos; Step S4: performing a mental health assessment based on each of the game videos, and obtaining interaction data and accumulated scores during the mental health assessment; Step S5: perform big data analysis of the interaction behavior on the interaction data, generate a mental health assessment report with the assessment time based on the big data analysis results and the cumulative score, display the mental health assessment report in real time on a display screen, encrypt the mental health assessment report into an encrypted report, push the encrypted report in real time to a pre-associated mobile terminal, and store and distribute the encrypted report.

2. A method for evaluating mental health based on a game scenario as claimed in claim 1, characterized in that: In step S1, the psychological scale question and answer data includes psychological scale questions, psychological scale answers, and scores corresponding to each psychological scale answer.

3. A method for evaluating mental health based on game scenarios as claimed in claim 1, characterized in that: The step S2 is specifically as follows: The psychological scale question and answer data in the database are respectively input into a pre-trained text encoder to obtain the corresponding semantic vector: Z T =E text (T); Among them, Z T represents the semantic vector; E text () represents text encoder; T represents psychological scale question and answer data; Each of the semantic vectors is converted into a corresponding video frame through a diffusion model; the conversion process of the diffusion model is as follows: Get a real image, add noise to the real image step by step for forward diffusion, so as to obtain a completely random noise image: Among them, x t represents the noise image obtained by adding noise to the real image in t steps; x t-1 represents the noise image obtained by adding noise to the real image in t-1 steps; β t represents the noise parameter of the noise added in step t; I represents the identity matrix; q(x t |x t-1 ) means generating x at step t t and generate x at step t-1 t-1 The probability distribution of ; N( ) represents the multivariate Gaussian distribution function; Indicates that from is the mean, and β t I is the covariance of the multivariate Gaussian distribution and x is obtained by sampling t ; For the noise image x t Step by step, remove the noise and perform reverse diffusion to obtain the video frame x0: Among them, p θ (x t-1 |x t ,Z T ) means that given x t and Z T , generating x t-1 The conditional probability distribution of θ (x t ,Z T ) represents the pixel mean of the noise image predicted by the semantic vector; Indicates the noise size in the denoising process, which is a scalar parameter learned by the neural network; represents the covariance matrix of the normal distribution; Generate a corresponding game video based on each of the video frames x0, and store each of the game videos in a structured manner in a database.

4. A method for evaluating mental health based on game scenarios as claimed in claim 1, characterized in that: The step S3 is specifically as follows: Classifying each of the game videos based on a preset game type, wherein the game type at least includes adventure, puzzle, and role-playing; Setting a game background story, task objectives and game elements based on the psychological scale question and answer data, and associating them with each video frame in the game video to set a game scene for each game video; the game elements at least include characters, environments and props; Then, the game difficulty, interaction mode and score corresponding to the interaction mode of each game video are set; the interaction mode is selection, clicking, dragging or voice input.

5. A method for evaluating mental health based on game scenarios as claimed in claim 1, characterized in that: The step S4 is specifically as follows: The selected game videos are displayed in sequence based on a preset display order, and mental health assessment is performed by interaction through the game videos. Interaction data including at least interaction operations, reaction time of each interaction operation, selection preference and accuracy rate in the mental health assessment process are obtained, the game difficulty of the game video is dynamically adjusted based on the reaction time, and the scores obtained from each game video are accumulated to obtain a cumulative score.

6. A mental health assessment system based on game scenarios, characterized by: Includes the following modules: A psychological scale question and answer data acquisition module is used to create a database, acquire a large number of psychological health scales, parse each of the psychological health scales to obtain a number of psychological scale question and answer data, and store each of the psychological scale question and answer data in a structured manner in the database; A game video generation module, used to convert each psychological scale question and answer data in the database into a corresponding game video through the Wensheng video artificial intelligence technology, and store each of the game videos in a structured manner in the database; A game video configuration module, used to classify each of the game videos, and set the game scene, game difficulty, interaction mode and the score corresponding to the interaction mode of each of the game videos; A mental health assessment module, used to conduct a mental health assessment based on each of the game videos, and obtain interaction data and accumulated scores during the mental health assessment process; A mental health assessment report generation module is used to perform big data analysis of the interactive behavior of the interactive data, generate a mental health assessment report with the assessment time based on the big data analysis results and the cumulative score, display the mental health assessment report in real time through a display screen, encrypt the mental health assessment report into an encrypted report, push the encrypted report in real time to a pre-associated mobile terminal, and store and distribute the encrypted report.

7. A game scenario-based mental health assessment system as claimed in claim 6, characterized in that: In the psychological scale question and answer data acquisition module, the psychological scale question and answer data includes psychological scale questions, psychological scale answers, and scores corresponding to each psychological scale answer.

8. A game scenario-based mental health assessment system as claimed in claim 6, characterized in that: The game video generation module is specifically used for: The psychological scale question and answer data in the database are respectively input into a pre-trained text encoder to obtain the corresponding semantic vector: Z T =E text (T); Among them, Z T represents the semantic vector; E text () represents text encoder; T represents psychological scale question and answer data; Each of the semantic vectors is converted into a corresponding video frame through a diffusion model; the conversion process of the diffusion model is as follows: Get a real image, add noise to the real image step by step for forward diffusion, so as to obtain a completely random noise image: Among them, x t represents the noise image obtained by adding noise to the real image in t steps; x t-1 represents the noise image obtained by adding noise to the real image in t-1 steps; β t represents the noise parameter of the noise added in step t; I represents the identity matrix; q(x t |x t-1 ) means generating x at step t t and generate x at step t-1 t-1 The probability distribution of ; N( ) represents the multivariate Gaussian distribution function; Indicates that from is the mean, and β t I is the covariance of the multivariate Gaussian distribution and x is obtained by sampling t ; For the noise image x t Step by step, remove the noise and perform reverse diffusion to obtain the video frame x0: Among them, p θ (x t-1 |x t ,Z T ) means that given x t and Z T , generating x t-1 The conditional probability distribution of θ (x t ,Z T ) represents the pixel mean of the noise image predicted by the semantic vector; Indicates the noise size in the denoising process, which is a scalar parameter learned by the neural network; represents the covariance matrix of the normal distribution; Generate a corresponding game video based on each of the video frames x0, and store each of the game videos in a structured manner in a database.

9. A game scenario-based mental health assessment system as claimed in claim 6, characterized in that: The game video configuration module is specifically used for: Classifying each of the game videos based on a preset game type, wherein the game type at least includes adventure, puzzle, and role-playing; Setting a game background story, task objectives and game elements based on the psychological scale question and answer data, and associating them with each video frame in the game video to set a game scene for each game video; the game elements at least include characters, environments and props; Then, the game difficulty, interaction mode and score corresponding to the interaction mode of each game video are set; the interaction mode is selection, clicking, dragging or voice input.

10. A game scenario-based mental health assessment system as claimed in claim 6, characterized in that: The mental health assessment module is specifically used for: The selected game videos are displayed in sequence based on a preset display order, and mental health assessment is performed by interaction through the game videos. Interaction data including at least interaction operations, reaction time of each interaction operation, selection preference and accuracy rate in the mental health assessment process are obtained, the game difficulty of the game video is dynamically adjusted based on the reaction time, and the scores obtained from each game video are accumulated to obtain a cumulative score.

Images