Personalized psychological rehabilitation plan making method and device

Abstract

The invention provides a personalized psychological rehabilitation plan making method and device, relates to the field of plan making, and solves the technical problem that in the prior art, the execution condition, psychological state change and rehabilitation effect of a user are difficult to master in time, so that the treatment effect of a rehabilitation scheme is poor. The method comprises the following steps: acquiring basic information, psychological state information and previous rehabilitation information of a user; data cleaning is carried out; features are extracted from the screened data, the users are classified into corresponding recovery pools, and rehabilitation portraits of the users are matched; and determining a review interval according to the rehabilitation portrait and the rehabilitation effect of the user. Information concealing is accurately avoided, and the data authenticity is improved; the limitation of a general scheme is broken through, and personalized adaptation is realized; the quantification effect facilitates efficient decision making, and personnel burden is reduced; the previous and real-time data are associated, the rehabilitation period is shortened, and the sense of participation of the user is enhanced.

Description

Technical Field

[0001] This application relates to the field of planning, and more particularly to a method and apparatus for developing personalized psychological rehabilitation plans. Background Technology

[0002] With increasing social pressure, the incidence of mental health problems is rising year by year, and the need for mental health rehabilitation is becoming increasingly urgent. At present, most existing mental health rehabilitation methods are based on generalized solutions, such as standardized psychological courses and standardized consultation procedures. These solutions do not fully consider individual differences such as age, gender, type of mental health problem (such as anxiety, depression, post-traumatic stress disorder, etc.), severity, living environment, personality traits, and past rehabilitation experiences.

[0003] On the one hand, standardized solutions cannot accurately match users' actual rehabilitation needs, resulting in poor rehabilitation outcomes and prolonged rehabilitation periods for some users. In some cases, the low compatibility between the solution and the user may even lead to resistance and affect the rehabilitation process. On the other hand, the existing rehabilitation process lacks a real-time dynamic monitoring and feedback mechanism. Professionals find it difficult to keep track of the user's implementation of the solution, changes in psychological state, and rehabilitation effects in a timely manner, and cannot adjust the rehabilitation solution according to the user's real-time situation, further reducing the scientific nature and effectiveness of psychological rehabilitation. Summary of the Invention

[0004] This application provides a method and apparatus for developing personalized psychological rehabilitation plans, which solves the technical problem that existing technologies make it difficult to timely grasp the user's implementation, changes in psychological state, and rehabilitation effects, resulting in poor therapeutic effects of rehabilitation plans.

[0005] To achieve the above objectives, this application adopts the following technical solution: Firstly, it provides a method for developing personalized psychological rehabilitation plans, including: The system obtains the user's basic information, psychological state information, and past rehabilitation information; wherein, the psychological state information includes the emotional score, stressors, and daily routine duration obtained from the user's self-reported emotional log. The user's basic information, psychological state information, and past rehabilitation information are cleaned to obtain filtered data; Key features are extracted from the filtered data to build user profiles and categorize them into the corresponding recovery pools. User recovery profiles are then matched based on the user profiles. The follow-up interval is determined based on the user's rehabilitation profile and rehabilitation effect; wherein, the rehabilitation effect is based on psychological state information and past rehabilitation information.

[0006] It should be noted that: basic information includes user age, family structure, occupation, and health status; past rehabilitation information includes the duration and results of psychological rehabilitation; and the filtered data includes cleaned basic information, psychological status information, and past rehabilitation information.

[0007] Based on the above technical solution, in the personalized psychological rehabilitation planning method provided in this application, by cleaning the data filled in by the user, it is possible to avoid providing accurate data when judging the subsequent rehabilitation effect. However, obtaining the rehabilitation effect based on the emotion score and past rehabilitation information can more accurately judge the current user's rehabilitation effect, and thus enable the formulation of a rehabilitation plan that is more suitable for the user.

[0008] In conjunction with the first aspect above, in one possible implementation, the data cleaning of the user's basic information, psychological state information, and past rehabilitation information includes: basic information cleaning and psychological state information cleaning. The method for cleaning the basic information includes: The emotional score obtained from the user's self-reported emotional log. The emotion score obtained from the user's self-reported emotion log last time. ; emotional change value Compared with the change threshold, if If the value is less than the change threshold, the basic information entered by the user will be retained; if... If the value exceeds the change threshold, the basic information previously entered by the user will be retained; wherein, the emotion change value... Through calculation formula Calculations show that It is the absolute value symbol; The method for cleaning psychological state information is rationality verification.

[0009] In conjunction with the first aspect above, in one possible implementation, the method for obtaining the change threshold includes: Several historical sentiment scores were obtained and linearly fitted to obtain the fitted curve F(s). Find the first derivative curve of the fitted curve F(s), and obtain the rate of change of several historical sentiment scores on the first derivative curve and the rate of change of several similar user profiles. Calculate the average μ and the average σ of the mean of the rate of change of several historical user sentiment scores and the rate of change of several similar user profiles. Through calculation formula Calculate the change threshold Where k is the sensitivity value; the sensitivity value is obtained as follows: ; This represents the average of several historical user sentiment change rates. This represents the average rate of change in sentiment across several similar user profiles. The standard value for the rate of change in sentiment among a number of historical users. Standard values ​​for the rate of change of emotions among several similar user profiles.

[0010] It should be noted that, , .

[0011] In conjunction with the first aspect above, in one possible implementation, the method for obtaining the rehabilitation effect includes: Extract fitted curves corresponding to several historical sentiment scores, and perform stage integration and total integration on the fitted curve F(s) to obtain the final negative sentiment level and the total negative sentiment level; wherein, the final negative sentiment level is... The total amount of negative emotions is F(x) is the baseline score. Count the total number m of users' stress sources and classify the stress sources into stress levels. The division extracts the number h of pressure sources for the current user and the corresponding pressure level of each pressure source. ; Extract the user's daily routine duration T and calculate the change in daily routine. The calculation method for the changes in daily routines is as follows: ; A recovery score is obtained by weighting and summing the final negative emotion level, total negative emotion level, total stress level of stressors, current stress level of user's stressors, and changes in daily routine; the recovery score is then used to match the recovery effect.

[0012] It should be noted that the baseline score F(x) is the emotional score obtained from the emotional log filled out by a mentally healthy person, and the baseline bisector F(x) is a horizontal straight line; while the rehabilitation effects corresponding to the effect labels mentioned above include significantly effective, effective, needing improvement, and ineffective.

[0013] Furthermore, the pressure source can be classified into pressure levels according to the duration of pressure or a preset type, that is, according to a preset mapping table.

[0014] In conjunction with the first aspect above, in one possible implementation, the rehabilitation score is calculated as follows:

[0015] Hs represents the rehabilitation score; , , All are weighting coefficients; j∈m, l∈h, q is the number of times the daily routine duration is counted, p∈q.

[0016] In conjunction with the first aspect above, in one possible implementation, the step of extracting key features from the filtered data, constructing user profiles, and classifying them into corresponding recovery pools includes: Map the filtered basic information and psychological state information in the filtered data to basic labels; User profiles are obtained by matching demand tags with priority based on psychological state tags; wherein, the priority of the psychological state tags is to rank the importance of basic information and psychological state information. User profiles are vectorized using an embedding model, and the cosine similarity between the user profiles and the vectors of several recovery pools is calculated. The user profiles are then assigned to the recovery pool corresponding to the maximum cosine similarity.

[0017] In conjunction with the first aspect above, in one possible implementation, matching the user's recovery profile based on the user profile includes: Extract the similarity between the user profile and each recovery pool and iterate through them to extract the two recovery pools with the highest similarity. Extract the standard recovery plan corresponding to the two recovery pools and combine the two standard recovery plans according to the similarity ratio to obtain the user recovery profile. The standard recovery plan is a preset treatment plan.

[0018] In conjunction with the first aspect above, in one possible implementation, the method for obtaining the review interval includes: The historical mood score, total number of stressors, stress level of stressors, final negative emotion amount, total negative emotion amount, and changes in daily routine were included. The data is input into a time prediction model to obtain the review interval time; wherein, the time prediction model is constructed based on a deep learning network model; the time prediction model is trained based on sample data.

[0019] Secondly, a processing device is provided, comprising: a communication unit and a processing unit; the communication unit is used to acquire basic information, psychological state information and past rehabilitation information of a user; wherein, the psychological state information includes emotional scores, stressors and daily routine duration obtained from the user's self-reported emotional log; The processing unit is used to clean the user's basic information, psychological state information and past rehabilitation information to obtain filtered data; Key features are extracted from the filtered data to build user profiles and categorize them into the corresponding recovery pools. User recovery profiles are then matched based on the user profiles. The follow-up interval is determined based on the user's rehabilitation profile and rehabilitation effect, wherein the rehabilitation effect is based on psychological state information and past rehabilitation information.

[0020] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0021] This application provides a method and device for developing a personalized psychological rehabilitation plan. By linking emotional fluctuations with the consistency of basic information, it can avoid deviations in the plan caused by users with mental illnesses often concealing key information due to resistance or shame, and avoid inefficient rehabilitation caused by false information. Through multi-dimensional weighted rehabilitation scoring, emotions, stress, and daily routines are converted into quantifiable Hs values ​​to accurately match the level of effectiveness. Then, through a time prediction model, the follow-up interval is output, which avoids both over-reviewing when rehabilitation is effective and missing follow-up when the effect needs improvement.

[0022] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0023] Figure 1 An architecture diagram of a personalized psychological rehabilitation planning system provided in this application embodiment; Figure 2 A flowchart illustrating a personalized psychological rehabilitation planning method provided in this application embodiment; Figure 3 This is a schematic diagram of the basic information cleaning process provided in the embodiments of this application; Figure 4 A schematic diagram illustrating the process of obtaining rehabilitation effects provided in an embodiment of this application; Figure 5 This is a schematic diagram of the processing apparatus provided in the embodiments of this application; Detailed Implementation In the description of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. The "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "multiple" means two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences.

[0024] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0025] The personalized psychological rehabilitation planning method provided in this application embodiment can be applied to, for example... Figure 1 The personalized psychological rehabilitation planning system 100 shown includes, for example... Figure 1 As shown, the personalized psychological rehabilitation planning system includes: terminal device 100 and cloud processing device 200.

[0026] The terminal device 100 is used to send basic information, psychological state information, and past rehabilitation information filled in by the user; and to display the rehabilitation profile and follow-up interval processed by the cloud processing device 200; wherein the psychological state information includes the emotional score, stress source, and daily routine duration obtained from the emotional log filled in by the user.

[0027] Cloud processing device 200 is used to clean and filter user's basic information, psychological state information and past rehabilitation information to obtain filtered data. Key features are extracted from the filtered data to build user profiles and categorize them into the corresponding recovery pools. User recovery profiles are then matched based on the user profiles. The follow-up interval is determined based on the user's rehabilitation profile and rehabilitation effect, wherein the rehabilitation effect is based on psychological state information and past rehabilitation information.

[0028] To address the technical problem in existing technologies where it is difficult to promptly grasp the user's performance, changes in psychological state, and rehabilitation effects, leading to inadequate therapeutic effects of rehabilitation plans, this application provides a method for developing a personalized psychological rehabilitation plan. This method includes: acquiring the user's basic information, psychological state information, and past rehabilitation information; wherein the psychological state information includes the user's self-reported emotional log, resulting in an emotional score, stressors, and daily routine duration. The user's basic information, psychological state information, and past rehabilitation information are cleaned to obtain filtered data; Key features are extracted from the filtered data to build user profiles and categorize them into the corresponding recovery pools. User recovery profiles are then matched based on the user profiles. The follow-up interval is determined based on the user's rehabilitation profile and rehabilitation effect; wherein, the rehabilitation effect is based on psychological state information and past rehabilitation information, based on which a more suitable plan can be formulated for each user.

[0029] like Figure 2 As shown in the embodiments of this application, the method for developing a personalized psychological rehabilitation plan includes: S201. Obtain the user's basic information, psychological state information, and past rehabilitation information; The psychological state information includes the emotional score, stressors, and daily routine duration obtained from the user's self-reported emotional log; the basic information includes the user's age, family structure, occupation, and health status; the past rehabilitation information includes the duration and results of psychological rehabilitation; and the filtered data includes the cleaned basic information, psychological state information, and past rehabilitation information.

[0030] In another preferred embodiment, the emotion score is a score obtained from the emotion questions voluntarily submitted by the user.

[0031] It should be noted that the past rehabilitation information mentioned above refers to the rehabilitation information after the last treatment, while the daily routine duration refers to the average rest duration of the user each day during the treatment phase.

[0032] S202. Clean the user's basic information, psychological state information, and past rehabilitation information to obtain filtered data.

[0033] In some implementations, the methods for cleaning basic information include: The emotional score obtained from the user's self-reported emotional log. The emotion score obtained from the user's self-reported emotion log last time. ; emotional change value Compared with the change threshold, if If the value is less than the change threshold, the basic information entered by the user will be retained; if... If the value exceeds the change threshold, the basic information previously entered by the user will be retained; wherein, the emotion change value... Through calculation formula Calculations show that It is the absolute value symbol; The method for cleaning psychological state information is rationality verification.

[0034] It should be noted that past rehabilitation information can be extracted from a historical database, rather than being filled in by the user, so there is no need to clean it; in this embodiment, the higher the emotion score, the better the user's psychological rehabilitation effect.

[0035] The aforementioned rationality check describes a contradiction. For example, if a user's occupation is a student, and the source of stress is mortgage pressure, then a "reconfirm" prompt will be triggered. Past rehabilitation information provides a method for developing personalized psychological rehabilitation plans, therefore no cleaning is required.

[0036] Since users with mental illnesses often conceal relevant information about themselves, changes in emotional scores obtained from emotional logs can reveal whether the basic information provided by the user in the initial submission was consistent. If inconsistencies are found, it indicates concealment, and adjusting the corresponding information will help to make the subsequent rehabilitation plan more suitable for the user.

[0037] Furthermore, the method for obtaining the change threshold includes: Several historical sentiment scores were obtained and linearly fitted to obtain the fitted curve F(s). Find the first derivative curve of the fitted curve F(s), and obtain the rate of change of several historical sentiment scores on the first derivative curve and the rate of change of several similar user profiles. Calculate the average μ and the average σ of the mean of the rate of change of several historical user sentiment scores and the rate of change of several similar user profiles. Through calculation formula Calculate the change threshold Where k is the sensitivity value; the sensitivity value is obtained as follows: ; This represents the average of several historical user sentiment change rates. This represents the average rate of change in sentiment across several similar user profiles. The standard value for the rate of change in sentiment among a number of historical users. The standard value for the rate of change of emotions among several similar user profiles. , .

[0038] For example, Zhang's historical emotion scores (last 20 times) were collected and linearly fitted to obtain the fitted curve F(s) = 0.3s + 3.5; Find the first derivative curve F'(s) = 0.3 and extract the historical rate of change in sentiment. , Standard value of historical sentiment change rate , Therefore, k=3.5. If Zhang's emotional change value is 2, it means that the emotional fluctuation is beyond the reasonable range, and there may be concealment of basic information (subsequent verification found that Zhang did not mention "rent pressure"). In accordance with the rules, the previous basic information is maintained ("rent pressure" is added to the current information) to ensure the authenticity of the data.

[0039] In existing technologies, users with mental illnesses often conceal key information due to resistance or shame (such as Zhang initially concealing "rent pressure"), leading to deviations in treatment plans. By verifying "emotional change values ​​and dynamic thresholds," the consistency between emotional fluctuations and basic information is linked. When information adjustments are triggered, the "rent pressure" information is ultimately supplemented, improving the accuracy of subsequent profile construction and plan matching, and avoiding "ineffective rehabilitation" caused by false information (such as developing plans only for work pressure, ignoring the cumulative impact of economic pressure).

[0040] By integrating historical emotion score data from similar groups for fitting, the method avoids fitting biases that may arise from relying solely on individual user historical data, making the fitted curve more accurately reflect the emotional change patterns of users with these psychological characteristics. The dynamic threshold, determined based on the mean and standard deviation, can be adjusted according to the actual emotional changes of similar user groups. Furthermore, by introducing a sensitivity value k, it prevents users' emotional states from deviating too much from their own. Compared to fixed thresholds, this method is more accurate and adaptable, effectively reducing misjudgments or omissions caused by unreasonable threshold adjustments to basic information.

[0041] S203. Extract key features from the screened data, construct user profiles, and classify them into the corresponding recovery pools. Match user recovery profiles based on user profiles.

[0042] In some implementations, key features are extracted from the filtered data to build user profiles and categorize them into corresponding recovery pools, including: Map the filtered basic information and psychological state information in the filtered data to basic labels; such as "age 28 years old → 26-35 years old label"; User profiles are obtained by matching demand tags with priority based on psychological state tags; wherein, the priority of the psychological state tags is to rank the importance of basic information and psychological state information. User profiles are vectorized using an embedding model, and the cosine similarity between the user profiles and the vectors of several recovery pools is calculated. The user profiles are then assigned to the recovery pool corresponding to the maximum cosine similarity.

[0043] It should be noted that the priority of psychological state labels is not limited to basic information and psychological state information; it can also include negative emotion level labels and emotion change trend labels. The emotion change trend label can be determined by the slope of the fitted curve of F(s). The basic tags mentioned above are pre-set tags based on basic information and psychological state information; similarly, the recovery pool is also pre-set with multiple categories and multiple word vectors.

[0044] Example of a negative emotion level label: High negative emotions: ,and This means that both recent and overall negative sentiment have exceeded the standard. Low negative emotions: This means that the overall negative emotions are slightly excessive and can be improved in the near future; No negative emotions: Overall, negative emotions are within a healthy range.

[0045] Sentiment change trend tags: Upward trend: The slope of the fitted curve is >0.2, indicating that the sentiment score continues to rise and negative sentiment decreases; Stable trend: 0.2 ≥ slope of fitted curve ≥ -0.2, indicating no significant fluctuation in sentiment; Downward trend: The slope of the fitted curve is less than -0.2, indicating that the sentiment score continues to decrease and negative sentiment increases.

[0046] In conjunction with the first aspect above, in one possible implementation, matching the user's recovery profile based on the user profile includes: Extract the similarity between the user profile and each recovery pool and iterate through them to extract the two recovery pools with the highest similarity. Extract the standard recovery plan corresponding to the two recovery pools and combine the two standard recovery plans according to the similarity ratio to obtain the user recovery profile. The standard recovery plan is a preset treatment plan.

[0047] The above technical solution can avoid using the same treatment template for people with different situations. It can adjust the rehabilitation profile according to the specific situation of the user profile, making it more suitable for the user's situation.

[0048] S204. Determine the follow-up examination interval based on the user's recovery profile and recovery effect; The rehabilitation effect is based on psychological state information and past rehabilitation information.

[0049] The specific methods for obtaining the results are as follows: These include methods for obtaining information about the recovery process. Extract fitted curves corresponding to several historical sentiment scores, and perform stage integration and total integration on the fitted curve F(s) to obtain the final negative sentiment level and the total negative sentiment level; wherein, the final negative sentiment level is... The total amount of negative emotions is F(x) is the baseline score. Count the total number m of users' stress sources and classify the stress sources into stress levels. The division extracts the number h of pressure sources for the current user and the corresponding pressure level of each pressure source. ; Extract the user's daily routine duration T and calculate the change in daily routine. The calculation method for the changes in daily routines is as follows: ; A recovery score is obtained by weighting and summing the final negative emotion level, total negative emotion level, total stress level of stressors, current stress level of user's stressors, and changes in daily routine; the recovery score is then used to match the recovery effect.

[0050] It should be noted that the baseline score F(x) is the emotional score obtained from the emotional log filled out by a mentally healthy person, and the baseline bisector F(x) is a horizontal straight line; while the rehabilitation effects corresponding to the effect labels mentioned above include significantly effective, effective, needing improvement, and ineffective.

[0051] By distinguishing between short-term fluctuations and long-term accumulation through "negative emotional intensity stages / full-term scores", avoiding subjective rating bias through "standardized stress level classification" (by duration / preset type), and capturing dynamic trends through "changes in daily routines" instead of relying on static data, the limitations of traditional subjective judgment are completely eliminated, thus improving the accuracy of effect evaluation.

[0052] Furthermore, the pressure source can be classified into pressure levels according to the duration of pressure or a preset type, that is, according to a preset mapping table.

[0053] Furthermore, the rehabilitation score is calculated as follows:

[0054] Hs represents the rehabilitation score; , , All are weighting coefficients; j∈m, l∈h, q is the number of times the daily routine duration is counted, p∈q.

[0055] It should be noted that, regarding the weighting coefficients , , Data can be obtained through AHP tomography or expert scoring; it can also be obtained by training a model using basic information and past rehabilitation information as input data.

[0056] Furthermore, the methods for obtaining the follow-up examination interval include: The historical emotion scores, total number of stressors, stress level of stressors, final negative emotion amount, total negative emotion amount, and changes in daily routine are input into an LSTM time prediction model to obtain the follow-up interval. The LSTM time prediction model is constructed based on a deep learning network model and is trained using sample data. Specifically, the sample data includes historical emotion scores, total number of stressors, stress level of stressors, final negative emotion amount, total negative emotion amount, and changes in daily routine as training input data, and the follow-up interval provided by the psychologist as training output data.

[0057] The foregoing mainly describes the solutions of the embodiments of this application from the perspective of device implementation. It is understood that each device, such as a processing apparatus, includes at least one of the hardware structures and software modules corresponding to the execution of each function in order to achieve the above-mentioned functions. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0058] This application embodiment can divide the processing device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0059] When using integrated units, Figure 5 A possible structural schematic diagram of the processing device (referred to as processing device 50) involved in the above embodiments is shown. The processing device 50 includes a processing unit 501 and a communication unit 502, and may also include a storage unit 503. Figure 5 The schematic diagram shown can be used to illustrate the structure of the processing device involved in the above embodiments.

[0060] when Figure 5 The schematic diagram shown is used to illustrate the structure of the processing device involved in the above embodiments. The processing unit 501 is used to control and manage the operation of the processing device, the communication unit 502 is used for the processing device to communicate with other devices, and the storage unit 503 is used to store the program code and data of the processing device.

[0061] For example, the communication unit 502 is used to obtain the user's basic information, psychological state information, and past rehabilitation information; wherein, the psychological state information includes the emotional score, stressors, and daily routine duration obtained from the user's self-reported emotional log. The processing unit 501 is used to clean the user's basic information, psychological state information and past rehabilitation information to obtain filtered data. Key features are extracted from the filtered data to build user profiles and categorize them into the corresponding recovery pools. User recovery profiles are then matched based on the user profiles. The follow-up interval is determined based on the user's rehabilitation profile and rehabilitation effect, wherein the rehabilitation effect is based on psychological state information and past rehabilitation information.

[0062] The processing unit 501 can be a processor or a controller, and the communication unit 502 can be a communication interface, transceiver, transceiver circuit, transceiver device, etc. The term "communication interface" is a general term and may include one or more interfaces. The storage unit 503 can be a memory. When the processing device 50 is a chip, the processing unit 501 can be a processor or a controller, and the communication unit 502 can be an input interface and / or an output interface, pins, or circuits, etc. The storage unit 503 can be a storage unit within the chip (e.g., a register, cache, etc.) or a storage unit located outside the chip (e.g., read-only memory (ROM), random access memory (RAM, etc.).

[0063] The communication unit can also be called a transceiver unit. The antenna and control circuit with transceiver functions in the processing device 5050 can be considered as the communication unit 502 of the processing device 50, and the processor with processing functions can be considered as the processing unit 501 of the processing device 50. Optionally, the device in the communication unit 502 that implements the receiving function can be considered as a communication unit. The communication unit is used to execute the receiving steps in the embodiments of this application, and the communication unit can be a receiver, a receiver circuit, etc. The device in the communication unit 502 that implements the transmitting function can be considered as a transmitting unit. The transmitting unit is used to execute the transmitting steps in the embodiments of this application, and the transmitting unit can be a transmitter, a transmitter, a transmitting circuit, etc.

[0064] Figure 5If the integrated units in the process are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. Storage media for storing computer software products include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0065] Figure 5 The units in the process can also be called modules; for example, a processing unit can be called a processing module.

[0066] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0067] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. A method for developing a personalized psychological rehabilitation plan, characterized in that, include: Obtain the user's basic information, psychological state information, and past rehabilitation information; wherein, the psychological state information includes the emotional score, stressors, and daily routine duration obtained from the emotional information self-reported by the user; The user's basic information, psychological state information, and past rehabilitation information are cleaned to obtain filtered data; Key features are extracted from the filtered data to build user profiles and categorize them into the corresponding recovery pools. User recovery profiles are then matched based on the user profiles. The follow-up interval is determined based on the user's rehabilitation profile and rehabilitation effect; wherein, the rehabilitation effect is based on psychological state information and past rehabilitation information.

2. The method for developing a personalized psychological rehabilitation plan according to claim 1, characterized in that, The process of cleaning the user's basic information, psychological state information, and past rehabilitation information includes: cleaning the basic information and cleaning the psychological state information. The method for cleaning the basic information includes: The emotional score obtained from the user's self-reported emotional log. The emotion score obtained from the user's self-reported emotion log last time. ; emotional change value Compared with the change threshold, if If the value is less than the change threshold, the basic information entered by the user will be retained; if... If the value exceeds the change threshold, the basic information previously entered by the user will be retained; wherein, the emotion change value... Through calculation formula Calculations show that It is the absolute value symbol; The method for cleaning psychological state information is rationality verification.

3. The method for developing a personalized psychological rehabilitation plan according to claim 2, characterized in that, The method for obtaining the change threshold includes: Several historical sentiment scores were obtained and linearly fitted to obtain the fitted curve F(s). Find the first derivative curve of the fitted curve F(s), and obtain the rate of change of several historical sentiment scores on the first derivative curve and the rate of change of several similar user profiles. Calculate the average μ and the average σ of the mean of the rate of change of several historical user sentiment scores and the rate of change of several similar user profiles. Through calculation formula Calculate the change threshold Where k is the sensitivity value; the sensitivity value is obtained as follows: ; This represents the average of several historical user sentiment change rates. This represents the average rate of change in sentiment across several similar user profiles. The standard value for the rate of change in sentiment among a number of historical users. Standard values ​​for the rate of change of emotions among several similar user profiles.

4. The method for developing a personalized psychological rehabilitation plan according to claim 1, characterized in that, The methods for obtaining the rehabilitation effect include: Extract fitted curves corresponding to several historical sentiment scores, and perform stage integration and total integration on the fitted curve F(s) to obtain the final negative sentiment level and the total negative sentiment level; wherein, the final negative sentiment level is... The total amount of negative emotions is F(x) is the baseline score. Count the total number m of users' stress sources and classify the stress sources into stress levels. The division extracts the number h of pressure sources for the current user and the corresponding pressure level of each pressure source. ; Extract the user's daily routine duration T and calculate the change in daily routine. The calculation method for the changes in daily routines is as follows: ; A recovery score is obtained by weighting and summing the final negative emotion level, total negative emotion level, total stress level of stressors, current stress level of user's stressors, and changes in daily routine; the recovery score is then used to match the recovery effect.

5. The method for developing a personalized psychological rehabilitation plan according to claim 4, characterized in that, The rehabilitation score is calculated as follows: Hs represents the rehabilitation score; , , All are weighting coefficients; j∈m, l∈h, q is the number of times the daily routine duration is counted, p∈q.

6. The method for developing a personalized psychological rehabilitation plan according to claim 1, characterized in that, The process of extracting key features from the filtered data, constructing user profiles, and categorizing them into corresponding recovery pools includes: Map the filtered basic information and psychological state information in the filtered data to basic labels; User profiles are obtained by matching demand tags with priority based on psychological state tags; wherein, the priority of the psychological state tags is to rank the importance of basic information and psychological state information. User profiles are vectorized using an embedding model, and the cosine similarity between the user profiles and the vectors of several recovery pools is calculated. The user profiles are then assigned to the recovery pool corresponding to the maximum cosine similarity.

7. The method for developing a personalized psychological rehabilitation plan according to claim 6, characterized in that, The process of matching user recovery profiles based on user profiles includes: Extract the similarity between the user profile and each recovery pool and iterate through them to extract the two recovery pools with the highest similarity. Extract the standard recovery plan corresponding to the two recovery pools and combine the two standard recovery plans according to the similarity ratio to obtain the user recovery profile. The standard recovery plan is a preset treatment plan.

8. The method for developing a personalized psychological rehabilitation plan according to claim 7, characterized in that, The methods for obtaining the review interval include: The historical mood score, total number of stressors, stress level of stressors, final negative emotion amount, total negative emotion amount, and changes in daily routine were included. The data is input into a time prediction model to obtain the review interval time; wherein, the time prediction model is constructed based on a deep learning network model; the time prediction model is trained based on sample data.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 8.

10. A processing apparatus, characterized in that, The device includes: a communication unit and a processing unit; The communication unit is used to acquire the user's basic information, psychological state information, and past rehabilitation information; wherein, the psychological state information includes the emotional score, stressors, and daily routine duration obtained from the user's self-reported emotional log. The processing unit is used to clean the user's basic information, psychological state information and past rehabilitation information to obtain filtered data; Key features are extracted from the filtered data to build user profiles and categorize them into the corresponding recovery pools. User recovery profiles are then matched based on the user profiles. The follow-up interval is determined based on the user's rehabilitation profile and rehabilitation effect, wherein the rehabilitation effect is based on psychological state information and past rehabilitation information.

Images