Psychological health assessment monitoring and AI early warning block chain storage system and method

Abstract

The invention relates to the technical field of data processing, and discloses a mental health assessment monitoring and AI early warning block chain storage system and method. According to the method, a sample set Q is constructed by collecting psychological health data of a user, the psychological health data of the user in the sample set Q are preprocessed, meanwhile, various behavior data weights of the psychological health data of the user in the sample set Q are set, and historical psychological health data of the user in the sample set Q are quantized based on the set weights; a psychological health dynamic evaluation model is constructed based on the quantified user psychological health data and set behavior data weight, monitoring and early warning are carried out on the psychological health state of the user based on the constructed psychological health dynamic evaluation model, and finally a monitoring result and an early warning result are uploaded to a cloud in real time. And optimized storage is carried out through a block chain technology, so that the real-time performance of mental health assessment monitoring is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and specifically to a mental health assessment and monitoring, AI early warning blockchain storage system and method. Background Art

[0002] Traditional single assessment methods are difficult to meet the needs of mental health management. Therefore, there is an urgent need for a comprehensive and efficient mental health monitoring and early warning system that can integrate multi-party data, perform efficient calculations and analyses, and ensure the mental health and safety of students.

[0003] The existing publicly applied patent CN113239050A is used to obtain medical data including personal information and corresponding disease information, and at the same time obtain mental data including heart rate variability detection data and psychological assessment scales, and store them in a database; at the same time, a data integration method is used to integrate medical and mental data, and classify, count and analyze them to establish an association relationship between medical data and mental data; however, due to the lack of multi-dimensional psychological data analysis and only judging from a clinical perspective, it is easy to lead to insufficient data analysis and has certain limitations. Summary of the Invention

[0004] (I) Technical Problems to be Solved

[0005] In view of the deficiencies of the prior art, the present invention provides a mental health assessment and monitoring, AI early warning blockchain storage system and method, which has the advantages of accuracy, real-time, efficiency, etc., and solves the problem that traditional single assessment methods are difficult to meet the needs of mental health management.

[0006] (II) Technical Solutions

[0007] To solve the above technical problem that traditional single assessment methods are difficult to meet the needs of mental health management, the present invention provides the following technical solutions:

[0008] The present invention discloses a mental health assessment and monitoring, AI early warning blockchain storage method, which specifically includes the following steps:

[0009] S1. Collect user mental health data to construct a sample set Q, and preprocess the user mental health data in the sample set Q to obtain preprocessed user mental health data;

[0010] S2. Set the weights of various behavior data of the user mental health data in the sample set Q, and quantify the user historical mental health data in the sample set Q based on the set weights;

[0011] S3. Construct a mental health dynamic assessment model based on the quantified user mental health data and the set behavior data weights;

[0012] S4. Monitor and give early warnings about the mental health status of users based on the constructed dynamic mental health assessment model;

[0013] S5. Upload the monitoring results and early warning results to the cloud in real time and optimize the storage through blockchain technology;

[0014] S51. Filter redundant data;

[0015] S52. Optimize blockchain cloud storage.

[0016] The present invention constructs a sample set Q by collecting users' mental health data, preprocesses the users' mental health data in the sample set Q, sets the weights of various behavioral data of the users' mental health data in the sample set Q, quantifies the users' historical mental health data in the sample set Q based on the set weights, and then constructs a dynamic mental health assessment model based on the quantified users' mental health data and the set behavioral data weights, monitors and gives early warnings about the mental health status of users based on the constructed dynamic mental health assessment model, and finally uploads the monitoring results and early warning results to the cloud in real time and optimizes the storage through blockchain technology, improving the real-time performance of mental health assessment and monitoring.

[0017] Preferably, the steps of collecting users' mental health data to construct a sample set Q and preprocessing the users' mental health data in the sample set Q to obtain preprocessed users' mental health data include the following steps:

[0018] S11. Obtain the user device number and assessment data;

[0019] Use the device number information as the unique identification information of the user;

[0020] S12. Extract the historical mental health data in the user assessment data based on the unique user identification information;

[0021] S13. Preprocess the historical mental health data in the user assessment data.

[0022] Preferably, the steps of extracting the historical mental health data in the user assessment data based on the unique user identification information include the following steps:

[0023] Establish a set of the historical mental health data and set it as N = {n1, n2, n3, n4,... n m}, and each item of historical mental health data includes: H = {h1, h2, h3, h4};

[0024] Among them, H represents the set of historical mental health evaluation data of users, h1 represents the self-evaluation data in the historical mental health data of users, h2 represents the peer evaluation data in the historical mental health data of users, h3 represents the teacher evaluation data in the historical mental health data of users, h4 represents the parent evaluation data in the historical mental health data of users, N represents the set of historical mental health data, and n m represents the mth group of mental health data in the set of historical mental health data;

[0025] It is set that each group of mental health data is collected by the person responsible for collection logging in to the question bank of the interface.

[0026] Preferably, the preprocessing of the historical mental health data in the user evaluation data includes the following steps:

[0027] Set the time interval threshold T for each group of mental health data, and count the specific time collected for various evaluations of the historical mental health data within the set time interval threshold;

[0028] Set the effective range of each group of mental health data within the time interval threshold T;

[0029] Set the effective range of mental health data to [0, 1, 2, 3, 4, 5];

[0030] Based on the set time interval threshold T and the effective range of each group of mental health data within the time interval threshold, sort out the historical mental health data in the user evaluation data.

[0031] The present invention improves the accuracy of mental health assessment and monitoring by collecting the user device number and evaluation data in real time, extracting the historical mental health data in the user evaluation data based on the user's unique identification information, and preprocessing the historical mental health data in the user evaluation data at the same time.

[0032] Preferably, setting the weights of each evaluation data of the user mental health data in the sample set Q and quantifying the historical mental health data of the users in the sample set Q based on the set weights includes the following steps:

[0033] The weight R = r1 + r2 + r3 + r4. Set the weight of self-evaluation data as r1, the weight of peer evaluation data as r2, the weight of teacher evaluation data as r3, and the weight of parent evaluation data as r4;

[0034] Within the set time interval threshold T, the historical mental health data of the users quantified based on the set weights is:

[0035] u i = r1 × h i,1 + r2 × h i,2 + r3 × hi,3 +r4×h i,4 ;

[0036] Among them, u i represents the user's historical mental health data after quantification for user i, and h i,1 represents the self-assessment data in the user's historical mental health data for user i, and h i,2 represents the peer evaluation data in the user's historical mental health data for user i, and h i,3 represents the teacher evaluation data in the user's historical mental health data for user i, and h i,4 represents the parent evaluation data in the user's historical mental health data for user i.

[0037] In the present invention, by setting the weights of various evaluation data of the user's mental health data in the sample set Q and quantifying the historical mental health data, the mental health status of the user is intuitively represented by the quantified historical mental health data, thereby improving the reliability of the representation of the user's mental health status.

[0038] Preferably, the construction of the mental health dynamic evaluation model based on the quantified user mental health data and the setting of behavior data weights includes the following steps:

[0039] The formula of the mental health dynamic evaluation model is as follows:

[0040]

[0041] Among them, K represents the mental health status score data calculated by the mental health dynamic evaluation model.

[0042] Preferably, the monitoring and early warning of the user's mental health status based on the constructed mental health dynamic evaluation model includes the following steps:

[0043] Based on the mental health dynamic evaluation model, calculate the mental health status score data of the user in real time;

[0044] Set the threshold of the mental health status score data. When the calculated mental health status score data is less than or equal to the threshold, it indicates that the current user's mental health status is dangerous and an alarm needs to be issued; when the calculated mental health status score data is higher than the threshold, it indicates the current user's mental health status and continuous monitoring is required.

[0045] In the present invention, by constructing a mental health dynamic evaluation model based on the quantified user mental health data and the setting of behavior data weights, and at the same time setting the threshold of the mental health status score data, the mental health status of the user is monitored and early warned based on the set threshold through the mental health dynamic evaluation model, thereby improving the safety of psychological detection.

[0046] Preferably, the step of uploading the monitoring results and early warning results to the cloud in real time and optimizing the storage through blockchain technology includes the following steps:

[0047] S51. Redundant data filtering;

[0048] Establish an array with a length of g, and select hash functions to calculate each data of the uploaded monitoring results and early warning results, and save the calculation results in the array, where c represents the number of hash functions, and η represents the number of data in the collected mental health status scoring data;

[0049] During the calculation process of the hash function, when the calculation results of two groups of data are the same, compare each data in these two groups of data;

[0050] When the comparison results are the same, set the current two groups of data as the same data;

[0051] When the two groups of data are the same data, compare the collection times of the two groups of data, and keep the most recent group of data;

[0052] After the calculation is completed, summarize the calculated monitoring results and early warning results to obtain the filtered monitoring results and early warning results;

[0053] S52. Blockchain cloud storage optimization.

[0054] Preferably, the blockchain cloud storage optimization includes the following steps:

[0055] Construct y data blocks to store the filtered monitoring results and early warning results, and then allocate y - 1 blocks to y - 1 storage nodes in the blockchain network;

[0056] Set the rules followed for uploading the monitoring results and early warning results;

[0057]

[0058] Among them, P y ' represents the selection probability of the yth storage node, d represents the distance between storage nodes, and Cov represents the covariance;

[0059] Furthermore, calculate the storage scheduling time and set the storage scheduling time threshold;

[0060] The formula for calculating the storage scheduling time is as follows:

[0061] T r = p' a 'T a + p' b 'T b ;

[0062] Among them, T r represents the storage scheduling time, and p' a ' represents the occurrence probability of data read operations, and p' b ' represents the occurrence probability of data write operations. T a , T b respectively represent the time consumed by data read operations and write operations;

[0063] Furthermore, based on the calculated storage scheduling time, the stored data in each block is adjusted in real time.

[0064] The present invention sets the following rules for uploading monitoring results and warning results and calculates the storage scheduling time through redundant data filtering and blockchain cloud storage optimization methods. By using the calculated storage scheduling time, the storage data location is adjusted, improving the efficiency of data access and storage.

[0065] The present invention also discloses a mental health assessment monitoring and AI warning blockchain storage system for implementing the mental health assessment monitoring and AI warning blockchain storage method. The system includes: a data collection module, a data processing module, a mental health dynamic assessment module, a status monitoring and warning module, and a cloud storage optimization module;

[0066] The data collection module is used to collect users' mental health data in real time;

[0067] The data processing module is used to process the users' mental health data collected in real time;

[0068] The mental health dynamic assessment module is used to construct a mental health dynamic assessment model based on the processed mental health data;

[0069] The status monitoring and warning module is used to monitor and warn the mental health status of users based on the constructed mental health dynamic assessment model;

[0070] The cloud storage optimization module is used to optimize storage through blockchain technology.

[0071] (III) Beneficial Effects

[0072] Compared with the prior art, the present invention provides a mental health assessment monitoring and AI warning blockchain storage system and method, having the following beneficial effects:

[0073] 1. The invention constructs a sample set Q by collecting users' mental health data, preprocesses the users' mental health data in the sample set Q, sets the weights of various behavioral data of the users' mental health data in the sample set Q, quantifies the users' historical mental health data in the sample set Q based on the set weights, then constructs a mental health dynamic assessment model based on the quantified users' mental health data and the set behavioral data weights, monitors and warns the users' mental health status based on the constructed mental health dynamic assessment model, and finally uploads the monitoring results and warning results to the cloud in real time and optimizes the storage through blockchain technology, improving the real-time performance of mental health assessment and monitoring.

[0074] 2. The invention improves the accuracy of mental health assessment and monitoring by collecting the user device numbers and assessment data in real time, extracting the historical mental health data in the user assessment data based on the user's unique identification information, and preprocessing the historical mental health data in the user assessment data.

[0075] 3. The invention improves the reliability of representing the users' mental health status by setting the weights of various evaluation data of the users' mental health data in the sample set Q, quantifying the historical mental health data, and intuitively representing the users' mental health status through the quantified historical mental health data.

[0076] 4. The invention improves the security of psychological detection by constructing a mental health dynamic assessment model based on the quantified users' mental health data and the set behavioral data weights, setting the threshold of the mental health status scoring data, and monitoring and warning the users' mental health status through the mental health dynamic assessment model based on the set threshold.

[0077] 5. The invention improves the efficiency of data access and storage by filtering redundant data and optimizing blockchain cloud storage, setting the rules for uploading the monitoring results and warning results and calculating the storage scheduling time, and adjusting the storage data location based on the calculated storage scheduling time. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 It is a schematic structural diagram of the mental health assessment, monitoring and AI warning blockchain storage process of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0079] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0080] Embodiment 1

[0081] Please refer to Figure 1 , this embodiment discloses a mental health assessment monitoring and AI early warning blockchain storage method, which specifically includes the following steps:

[0082] S1. Collect the user's mental health data to construct a sample set Q, and preprocess the user's mental health data in the sample set Q to obtain the preprocessed user's mental health data;

[0083] S2. Set the weights of various behavior data of the user's mental health data in the sample set Q, and quantify the user's historical mental health data in the sample set Q based on the set weights;

[0084] S3. Construct a mental health dynamic assessment model based on the quantified user's mental health data and the set behavior data weights;

[0085] S4. Monitor and early warn the user's mental health status based on the constructed mental health dynamic assessment model;

[0086] S5. Upload the monitoring results and early warning results to the cloud in real time, and optimize the storage through blockchain technology;

[0087] S51. Redundant data filtering;

[0088] S52. Blockchain cloud storage optimization;

[0089] Further, please refer to Figure 1 , collecting the user's mental health data to construct a sample set Q, and preprocessing the user's mental health data in the sample set Q to obtain the preprocessed user's mental health data includes the following steps:

[0090] S11. Obtain the user device number and assessment data;

[0091] Take the device number information as the unique identification information of the user;

[0092] S12. Extract the historical mental health data in the user's assessment data based on the user's unique identification information;

[0093] Establish a set of the historical mental health data and set it as N = {n1, n2, n3, n4,..., m}, and each item of historical mental health data includes: H = {h1, h2, h3, h4};

[0094] Among them, H represents the set of historical mental health evaluation data of users. h1 represents the self-evaluation data in the historical mental health data of users, h2 represents the peer evaluation data in the historical mental health data of users, h3 represents the teacher evaluation data in the historical mental health data of users, h4 represents the parent evaluation data in the historical mental health data of users, N represents the set of historical mental health data, and n m represents the m-th group of mental health data in the set of historical mental health data;

[0095] Furthermore, it is set that each group of mental health data is collected by the personnel responsible for collection logging in to the question bank on the interface;

[0096] S13. Preprocess the historical mental health data in the user evaluation data;

[0097] Set the time interval threshold T for each group of mental health data, and count the specific time collected for various evaluations of the historical mental health data within the set time interval threshold;

[0098] Set the effective range of each group of mental health data within the time interval threshold T;

[0099] Set the effective range of mental health data to [0, 1, 2, 3, 4, 5];

[0100] Based on the set time interval threshold T and the effective range of each group of mental health data within the time interval threshold, organize the historical mental health data in the user evaluation data;

[0101] Furthermore, please refer to Figure 1 , set the weights of each evaluation data of the user mental health data in the sample set Q, and quantify the historical mental health data of the users in the sample set Q based on the set weights, including the following steps:

[0102] The weight R = r1 + r2 + r3 + r4. Set the weight of self-evaluation data as r1, the weight of peer evaluation data as r2, the weight of teacher evaluation data as r3, and the weight of parent evaluation data as r4;

[0103] Within the set time interval threshold T, the historical mental health data of users quantified based on the set weights is:

[0104] u i = r1×h i,1 + r2×h i,2 + r3×h i,3 + r4×h i,4 ;

[0105] Among them, u i represents the historical mental health data of user i after quantification, h i,1Denote the self-assessment data in user i's historical mental health data as h i,2 Denote the peer-assessment data in user i's historical mental health data as h i,3 Denote the teacher-assessment data in user i's historical mental health data as h i,4 Denote the parent-assessment data in user i's historical mental health data

[0106] Furthermore, please refer to Figure 1 , constructing a mental health dynamic assessment model based on the quantified user mental health data and setting the behavior data weights includes the following steps:

[0107] The formula of the mental health dynamic assessment model is as follows:

[0108]

[0109] where K represents the mental health status score data calculated by the mental health dynamic assessment model;

[0110] Furthermore, please refer to Figure 1 , monitoring and warning the user's mental health status based on the constructed mental health dynamic assessment model includes the following steps:

[0111] Calculate the mental health status score data of the user in real time based on the mental health dynamic assessment model;

[0112] Set the threshold of the mental health status score data. When the calculated mental health status score data is less than or equal to the threshold, it indicates that the current user's mental health condition is dangerous and an alarm needs to be issued; when the calculated mental health status score data is higher than the threshold, it indicates the current user's mental health condition and continue to monitor;

[0113] Furthermore, please refer to Figure 1 , uploading the monitoring results and warning results to the cloud in real time and optimizing the storage through blockchain technology includes the following steps:

[0114] S51. Redundant data filtering;

[0115] Establish an array with a length of g, select hash functions to calculate each data of the uploaded monitoring results and warning results, and save the calculation results in the array, where c represents the number of hash functions and η represents the number of data in the collected mental health status score data;

[0116] During the calculation process of the hash function, when the calculation results of two groups of data are the same, compare each data in these two groups of data;

[0117] When the comparison results are consistent, set the current two sets of data as the same data;

[0118] When the two sets of data are the same data, compare the collection times of the two sets of data and retain the most recent set of data;

[0119] After the calculation is completed, summarize the calculated monitoring results and warning results to obtain the filtered monitoring results and warning results;

[0120] S52. Blockchain cloud storage optimization;

[0121] Construct y data blocks to store the filtered monitoring results and warning results, and then allocate y - 1 blocks to y - 1 storage nodes in the blockchain network;

[0122] Set the rules for uploading the monitoring results and warning results;

[0123]

[0124] Among them, P y ' represents the selection probability of the y-th storage node, d represents the distance between storage nodes, and Cov represents the covariance;

[0125] Furthermore, calculate the storage scheduling time and set the storage scheduling time threshold;

[0126] The formula for calculating the storage scheduling time is as follows:

[0127] T r = p' a 'T a + p' b 'T b ;

[0128] Among them, T r represents the storage scheduling time, p' a ' represents the occurrence probability of data read operations, p' b ' represents the occurrence probability of data write operations, T a , T b respectively represent the time consumed by data read operations and write operations;

[0129] Furthermore, based on the calculated storage scheduling time, adjust the stored data in each block in real time.

[0130] Embodiment 2

[0131] Please refer to Figure 1, this embodiment also discloses a mental health assessment monitoring and AI warning blockchain storage system for implementing the mental health assessment monitoring and AI warning blockchain storage method. The system includes: a data collection module, a data processing module, a mental health dynamic assessment module, a status monitoring and warning module, and a cloud storage optimization module;

[0132] The data collection module is used to collect users' mental health data in real time;

[0133] The data processing module is used to process the users' mental health data collected in real time;

[0134] The mental health dynamic assessment module is used to construct a mental health dynamic assessment model based on the processed mental health data;

[0135] The status monitoring and warning module is used to monitor and warn the users' mental health status based on the constructed mental health dynamic assessment model;

[0136] The cloud storage optimization module is used to perform optimized storage through blockchain technology.

[0137] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A blockchain storage method for mental health assessment monitoring and AI early warning, characterized in that: The following steps are involved: S1. Collect user mental health data to construct a sample set Q, and preprocess the user mental health data in the sample set Q to obtain the preprocessed user mental health data; S2. Set weights for various types of behavioral data of user mental health data in sample set Q, and quantify the historical mental health data of users in sample set Q based on the set weights; S3. Construct a dynamic mental health assessment model based on the quantified user mental health data and the setting of behavioral data weights; S4. Monitor and warn the user's mental health status based on the constructed dynamic mental health assessment model; S5. Upload the monitoring results and early warning results to the cloud in real time and optimize the storage through blockchain technology; S51, redundant data filtering; S52. Blockchain cloud storage optimization.

2. According to claim 1, a method for storing mental health assessment monitoring and AI early warning blockchain, characterized in that: The collecting of user mental health data to construct a sample set Q, and preprocessing the user mental health data in the sample set Q to obtain the preprocessed user mental health data includes the following steps: S11, obtaining user device number and evaluation data; Use the device number information as the user's unique identification information; S12, extracting historical mental health data from the user evaluation data based on the user's unique identification information; S13. Preprocess the historical mental health data in the user evaluation data.

3. According to claim 2, a method for storing mental health assessment monitoring and AI early warning blockchain, characterized in that: The method of extracting historical mental health data from user evaluation data based on user unique identification information comprises the following steps: The historical mental health data set is set to N = {n1, n2, n3, n4, ..., n m }, each item of historical mental health data includes: H = {h1, h2, h3, h4}; Among them, H represents the user's historical mental health assessment data set, h1 represents the self-assessment data in the user's historical mental health data, h2 represents the user's mutual assessment data in the user's historical mental health data, h3 represents the teacher's assessment data in the user's historical mental health data, h4 represents the parent's assessment data in the user's historical mental health data, N represents the historical mental health data set, n m represents the mth group of mental health data in the historical mental health data set; Each set of mental health data is set to be collected by the person responsible for collecting the data through a multiple-choice question bank on the login interface.

4. According to claim 2, a method for storing mental health assessment monitoring and AI early warning blockchain, characterized in that: The preprocessing of the historical mental health data in the user evaluation data comprises the following steps: Set a time interval threshold T for each set of mental health data, and count the specific time when various assessments of historical mental health data were collected within the set time interval threshold; Set the effective range of each set of mental health data within the time interval threshold T; Set the effective range of mental health data to [0,1,2,3,4,5]; The historical mental health data in the user evaluation data is sorted out based on the set time interval threshold T and the effective range of each group of mental health data within the time interval threshold.

5. According to claim 1, a method for storing mental health assessment monitoring and AI early warning blockchain, characterized in that: The step of setting weights of various evaluation data of user mental health data in the sample set Q and quantifying the user historical mental health data in the sample set Q based on the set weights includes the following steps: Weight R = r1 + r2 + r3 + r4, set the weight of self-assessment data to r1, user mutual assessment data to r2, teacher assessment data to r3, and parent assessment data to r4; Within the set time interval threshold T, the user's historical mental health data quantified based on the set weights is: in i =r1×h i,1 +r2×h i,2 +r3×h i,3 +r4×h i,4 ; Among them, u i represents the quantified historical psychological health data of user i, h i,1 represents the self-assessment data in the historical mental health data of user i, h i,2 represents the user mutual evaluation data in the historical mental health data of user i, h i,3 represents the teacher evaluation data in the historical mental health data of user i, h i,4 Represents the parent evaluation data in the historical mental health data of user i.

6. According to claim 1, a method for storing mental health assessment monitoring and AI early warning blockchain, characterized in that: The method of constructing a dynamic mental health assessment model based on quantified user mental health data and setting behavior data weights includes the following steps: The formula of the dynamic assessment model of mental health is as follows: Among them, K represents the mental health status score data calculated by the mental health dynamic assessment model.

7. According to claim 1, a method for storing mental health assessment monitoring and AI early warning blockchain, characterized in that: The monitoring and early warning of the user's mental health status based on the constructed mental health dynamic assessment model includes the following steps: Calculate the user's mental health status score data in real time based on the mental health dynamic assessment model; Set a threshold for the mental health status score data. When the calculated mental health status score data is less than or equal to the threshold, it indicates that the current user's mental health condition is dangerous and an alarm is required; when the calculated mental health status score data is higher than the threshold, it indicates that the current user's mental health condition should continue to be monitored.

8. According to claim 1, a method for storing mental health assessment monitoring and AI early warning blockchain, characterized in that: The real-time uploading of monitoring results and early warning results to the cloud and optimizing storage through blockchain technology includes the following steps: S51, redundant data filtering; Create an array of length g and select A hash function is used to calculate each data of the uploaded monitoring results and early warning results, and the calculation results are saved in an array, where c represents the number of hash functions and η represents the number of data in the collected mental health status score data; During the calculation of the hash function, when the calculation results of two sets of data are consistent, each data in the two sets of data is compared; When the comparison results are consistent, the two sets of data are set to be the same data; When two sets of data are the same, compare the collection time of the two sets of data and keep the most recent set of data; After the calculation is completed, the calculated monitoring results and early warning results are summarized to obtain the filtered monitoring results and early warning results; S52. Blockchain cloud storage optimization.

9. A method for storing mental health assessment monitoring and AI early warning blockchain according to claim 8, characterized in that: The blockchain cloud storage optimization includes the following steps: Build y data blocks to store the filtered monitoring results and warning results, and then distribute y-1 blocks to y-1 storage nodes in the blockchain network; Set the rules for uploading monitoring results and warning results; Among them, P y ' represents the selection probability of the yth storage node, d represents the distance between storage nodes, and Cov represents the covariance; Further, the storage scheduling time is calculated, and a storage scheduling time threshold is set; The formula for calculating storage scheduling time is as follows: T r =p' a 'T a +p' b 'T b ; Among them, T r represents the storage scheduling time, p' a ' represents the probability of data read operation, p' b ' represents the probability of data write operation, T a ,T b Respectively represent the time consumed by data reading and writing operations; Based on the calculation of storage scheduling time, the storage data in each block is adjusted in real time.

10. A system for implementing the mental health assessment monitoring and AI early warning blockchain storage method according to any one of claims 1 to 9, characterized in that: include: Data collection module, data processing module, mental health dynamic assessment module, status monitoring and early warning module, and cloud storage optimization module; The data collection module is used to collect user mental health data in real time; The data processing module is used to process the user's mental health data collected in real time; The mental health dynamic assessment module is used to construct a mental health dynamic assessment model based on the processed mental health data; The state monitoring and early warning module is used to monitor and warn the user's mental health state according to the constructed mental health dynamic assessment model; The cloud storage optimization module is used to optimize storage through blockchain technology.

Images