Interpersonal psychotherapy system based on cooperation of digital human-computer interaction and wearable equipment

Abstract

The invention relates to the technical field of intelligent medical treatment, and discloses an interpersonal psychological treatment system based on cooperation of digital human-computer interaction and wearable equipment, and the system comprises a user state sensing module which is used for obtaining basic information such as age distribution, psychological assessment levels and social behavior modes of a user group; the wearable equipment collaboration module is used for collecting data such as heart rate fluctuation, electrodermal response and respiratory rate through wearable equipment on the basis of the basic information; the interaction information processing module is used for performing multi-dimensional fusion processing on the acquired data to obtain a physiological-psychological associated feature set; the treatment scheme generation module is used for generating a standardized treatment scheme based on the feature set; and the collaborative execution feedback module is used for collaboratively executing the scheme and transmitting the process data to the monitoring terminal for recording. The system realizes digitization and individuation of psychotherapy through cooperation of digital man-machine interaction and wearable equipment, and improves the accuracy and effectiveness of the therapy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent medical treatment, in particular to an interpersonal psychological treatment system based on digital human-computer interaction and wearable device cooperation. BACKGROUND

[0002] In modern society, with the acceleration of life pace and the increase of pressure, psychological problems are increasingly common, and the demand for psychological treatment is also increasing. Traditional interpersonal psychological treatment mainly relies on face-to-face communication between therapists and patients, which has some limitations.

[0003] Traditional treatment methods are difficult to comprehensively and real-time obtain the physiological and psychological state of patients. Therapists mainly judge the psychological condition of patients through their language expression and behavior observation, but many changes in psychological state often accompany subtle changes in physiological indicators such as heart rate fluctuation, skin electrical response, and respiratory rate, which are difficult to observe with the naked eye, leading to therapists being unable to timely and accurately understand the real psychological state of patients, thereby affecting the treatment effect.

[0004] Traditional treatment programs lack individualization and precision. Different patients have different basic information such as age, psychological assessment level, and social behavior pattern, and their needs for treatment are also different. However, traditional treatment methods often use uniform treatment programs, which cannot be adjusted according to individual differences of patients, resulting in uneven treatment effects.

[0005] Data recording and analysis in the traditional treatment process are not comprehensive and systematic. Therapists usually record the treatment process through notes, which is not only inefficient, but also difficult to deeply analyze and mine a large amount of data, and cannot provide effective reference and support for subsequent treatment.

[0006] With the development of technology, digital human-computer interaction technology and wearable device technology have been widely applied. Digital human-computer interaction technology can realize natural and efficient interaction between people and computers, providing new means and methods for psychological treatment. Wearable device technology can collect physiological data of human body in real time, providing rich physiological indicator information for psychological treatment. However, the application of these technologies in the field of psychological treatment is not deep and extensive enough, and there is a lack of effective cooperation mechanism, which cannot fully exert its advantages. SUMMARY

[0007] The purpose of the present application is to provide an interpersonal psychological treatment system based on digital human-computer interaction and wearable device cooperation to solve the problems raised in the background art.

[0008] To achieve the above purpose, the present application provides the following technical solution: an interpersonal psychological treatment system based on digital human-computer interaction and wearable device cooperation, the system comprising:

[0009] a user state perception module configured to obtain basic information of a user group participating in psychological treatment, the basic information including age distribution, psychological assessment level, and social behavior pattern;

[0010] a wearable device coordination module configured to collect heart rate fluctuation data, skin electric response data, and breathing frequency data through wearable physiological monitoring devices based on the basic information of the user group;

[0011] an interactive information processing module configured to perform multi-dimensional interactive information fusion processing on the heart rate fluctuation data, the skin electric response data, and the breathing frequency data to obtain a set of physiological-psychological correlation features;

[0012] a treatment scheme generation module configured to generate a standardized interpersonal psychological treatment scheme based on the set of physiological-psychological correlation features;

[0013] a coordinated execution feedback module configured to execute the standardized interpersonal psychological treatment scheme through a digital interactive terminal and a wearable device in coordination, and transmit execution process data to a monitoring terminal for recording.

[0014] Preferably, the wearable device coordination module comprises:

[0015] a device configuration analysis unit configured to extract operating parameters of heart rate monitoring devices, skin electric response monitoring devices, and breathing frequency monitoring devices from a wearable device management platform;

[0016] a data type labeling unit configured to extract function descriptions of each monitoring device in the operating parameters to obtain a set of data type descriptions;

[0017] a feature encoding processing unit configured to perform feature encoding on the basic information of the user group and each data type description in the set of data type descriptions respectively to obtain a user parameter encoding vector and a set of data type encoding vectors;

[0018] a multi-source correlation analysis unit configured to perform multi-source correlation analysis on the user parameter encoding vector and the set of data type encoding vectors to obtain a user-device correlation optimization encoding vector;

[0019] a data collection regulation unit configured to generate collection rules of the heart rate fluctuation data, the skin electric response data, and the breathing frequency data based on the user-device correlation optimization encoding vector.

[0020] Preferably, the multi-source correlation analysis unit comprises:

[0021] a data type encoding feature integration sub-unit configured to perform feature integration processing based on hierarchical mapping on the set of data type encoding vectors to obtain a guide template;

[0022] a cross-domain collaborative coding subunit configured to perform cross-domain collaborative coding on the user parameter coding vector and the set of data type coding vectors based on the guide template to obtain the user-device association optimization coding vector.

[0023] Preferably, the data type coding feature integration subunit comprises:

[0024] a data type coding hierarchical mapping secondary subunit configured to perform hierarchical mapping processing on each data type coding vector in the set of data type coding vectors using a mapping matrix to obtain a set of hierarchical converted data type coding vectors;

[0025] a data type coding matrix arrangement secondary subunit configured to arrange the set of hierarchical converted data type coding vectors in a matrix to obtain a data type coding feature matrix;

[0026] a data type coding matrix key extraction secondary subunit configured to extract key values of each hierarchical converted data type coding vector in the data type coding feature matrix to obtain a data type coding feature matrix core vector as the guide template.

[0027] Preferably, the data type coding hierarchical mapping secondary subunit comprises:

[0028] performing point multiplication operation on the data type coding vector and the mapping matrix and then performing bitwise addition processing on the mapping offset vector to obtain a hierarchical converted data type coding vector.

[0029] Preferably, the cross-domain collaborative coding subunit comprises:

[0030] a user parameter hierarchical mapping secondary subunit configured to perform hierarchical mapping processing on the user parameter coding vector using a query matrix and a numerical matrix to obtain a user parameter query vector and a user parameter numerical vector;

[0031] a template guide heterogeneous conversion coding secondary subunit configured to input the user parameter query vector, the user parameter numerical vector, each hierarchical converted data type coding vector in the data type coding feature matrix, and the guide template into a template guide-based heterogeneous conversion structure to obtain a sequence of user-device cross-domain collaborative coding vectors;

[0032] a position mean value calculation secondary subunit configured to calculate a bitwise mean vector of the sequence of user-device cross-domain collaborative coding vectors to obtain the user-device association optimization coding vector.

[0033] Preferably, the template guide heterogeneous conversion coding secondary subunit comprises:

[0034] Calculate the product between the user parameter query vector and the transpose of the hierarchically transformed data type encoding vector, and divide the resulting user-device association feature matrix bitwise by the magnitude of the core vector of the data type encoding feature matrix to obtain the user-device association weight matrix;

[0035] The user-device association weight matrix is ​​input into a normalization function for processing to obtain the user-device association normalized weight matrix;

[0036] The user-device association normalized weight matrix is ​​multiplied with the core vector of the data type encoding feature matrix, and the resulting feature vector is multiplied by the user parameter value vector by a pointwise multiplication to obtain the user-device cross-domain collaborative encoding vector.

[0037] Preferably, the data acquisition and control unit includes:

[0038] The user-device association optimization encoding vector is input into the decision-maker-based data acquisition rule recommendation module to obtain the acquisition rules for the heart rate fluctuation data, skin conductance response data, and respiratory rate data.

[0039] Based on the acquisition rules, the acquisition range of the heart rate fluctuation data, skin conductance response data, and respiratory rate data is determined.

[0040] Preferably, the treatment plan generation module includes:

[0041] The scheme framework construction unit is used to extract the core feature dimensions of the physiological-psychological correlation feature set to construct the basic framework of the treatment scheme.

[0042] A personalized adjustment unit is used to match and analyze the basic information of the user group with the basic framework of the treatment plan to obtain a personalized treatment plan template.

[0043] The collaborative strategy generation unit is used to generate a collaborative execution strategy between the digital interactive terminal and the wearable device based on the personalized treatment plan template.

[0044] Preferably, the collaborative execution feedback module includes:

[0045] An execution process planning unit is used to decompose the collaborative execution strategy into an executable sequence of steps to obtain a treatment execution process;

[0046] The feedback data acquisition unit is used to collect language and behavioral feedback information from users during the treatment process through a digital interactive terminal.

[0047] The execution effect recording unit is used to associate and record the completion status of the treatment execution process with the language feedback information and behavioral feedback information.

[0048] Compared with the prior art, the present application has the beneficial effects of:

[0049] In terms of user state awareness, the system can obtain basic information such as age distribution, psychological assessment level, and social behavior patterns of the user group, providing a comprehensive user portrait for subsequent treatment. This enables therapists to better understand the basic situation of patients, laying the foundation for developing personalized treatment plans.

[0050] The wearable device coordination module collects heart rate fluctuation data, skin electrical response data, and respiratory rate data based on user basic information through wearable physiological monitoring devices. The collection of these physiological data realizes real-time and dynamic monitoring of the patient's psychological state, making up for the shortcomings of traditional treatment relying only on language and behavior observation. For example, when a patient experiences nervousness during treatment, their heart rate and skin electrical response may change significantly, and the system can detect emotional fluctuations in patients in a timely manner by collecting these data, providing more accurate judgment basis for therapists.

[0051] The interactive information processing module performs multi-dimensional interactive information fusion processing on the collected physiological data to obtain a set of physiological- psychological correlation characteristics. This process realizes the correlation analysis of physiological data and psychological state, and can deeply explore the internal relationship between physiological indicators and psychological state. Through this correlation analysis, the system can more accurately assess the patient's psychological state, providing a more scientific basis for the generation of treatment plans.

[0052] The treatment plan generation module generates standardized interpersonal psychological treatment plans based on the set of physiological- psychological correlation characteristics. At the same time, this module also considers the user's basic information, and through steps such as scheme framework construction, personalized adjustment, and coordination strategy generation, it realizes the individualization and precision of the treatment plan. For example, for patients of different ages and psychological assessment levels, the system can generate different treatment plans, improving the targeting and effectiveness of treatment.

[0053] The collaborative execution feedback module executes the standardized treatment plan through digital interactive terminals and wearable devices, and transmits the execution process data to the monitoring terminal for recording. This module realizes the digital management of the treatment process, not only improving the efficiency of treatment, but also providing comprehensive data support for the evaluation of treatment effect and the adjustment of subsequent treatment plans. Through the analysis of execution process data, therapists can timely discover problems in the treatment process and adjust and optimize the treatment plan.

[0054] The various modules in the system cooperate with each other to form a complete closed-loop system. From user state perception to data collection, information processing, scheme generation, collaborative execution feedback, each link is closely connected, realizing the whole process digitization and intelligent management of psychological treatment. This closed-loop system can continuously optimize the treatment process and improve the treatment effect, providing more high-quality psychological treatment services for patients. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 A working principle diagram of the interpersonal psychological treatment system based on digital human-computer interaction and wearable device cooperation according to the present application is shown in the figure.

[0056] Figure 2 A detailed flowchart of the wearable device cooperation module is shown in the figure.

[0057] Figure 3 A detailed flowchart of the cross-domain collaborative coding subunit is shown in the figure.

[0058] Figure 4 An operation flowchart of the template-guided heterogeneous conversion coding secondary subunit is shown in the figure. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0060] Please refer to Figures 1-4 The interpersonal psychological treatment system based on digital human-computer interaction and wearable device cooperation according to the present application has the following specific implementation steps:

[0061] The user state perception module is used to obtain the basic information of the user group participating in psychological treatment, which includes age distribution, psychological assessment level and social behavior mode.

[0062] The wearable device cooperation module is used to collect heart rate fluctuation data, skin electrical response data and respiratory frequency data based on the basic information of the user group through wearable physiological monitoring devices.

[0063] The interactive information processing module is used to perform multi-dimensional interactive information fusion processing on the heart rate fluctuation data, skin electrical response data and respiratory frequency data, so as to obtain a physiological-psychological correlation feature set.

[0064] The treatment scheme generation module is used to generate a standardized interpersonal psychological treatment scheme based on the physiological-psychological correlation feature set.

[0065] The standardized interpersonal psychotherapy program is executed through the digital interactive terminal and the wearable device in cooperation, and the execution process data is transmitted to the monitoring terminal for recording by the cooperative execution of the feedback module.

[0066] Embodiment 1:

[0067] In the interpersonal psychotherapy system based on digital human-computer interaction and wearable device cooperation, the present embodiment mainly aims at the specific implementation mode of the wearable device cooperation module. This module undertakes the key function of realizing data acquisition based on user group basic information through wearable physiological monitoring devices in the whole system, and its specific implementation process is as follows:

[0068] The device configuration analysis unit needs to extract the operating parameters of the relevant monitoring devices from the wearable device management platform. The devices involved here include heart rate monitoring devices, skin conductance monitoring devices, and respiratory rate monitoring devices. For heart rate monitoring devices, the extracted operating parameters include sampling frequency, such as the number of samples per second, which directly affects the time resolution of heart rate data; accuracy range, which relates to the accuracy of the data, i.e. the error range allowed by the device when measuring heart rate; working voltage, which ensures that the device operates within the normal voltage range, avoiding data collection failure or inaccuracy due to abnormal voltage, etc. The operating parameters of the skin conductance monitoring device include the measurement range, such as the upper and lower limits of the skin resistance change that can be sensed, to adapt to the physiological characteristics of different users; resolution, which determines the ability to capture subtle changes in skin conductance; noise level, which ensures the reliability of the data. The operating parameters of the respiratory rate monitoring device include the sampling period, i.e. the time interval for collecting respiratory data; the measurement method, such as through chest and abdominal movement sensors or impedance-based respiratory measurement; and the data transmission rate, which ensures that respiratory data can be transmitted to the system in a timely manner for processing.

[0069] The data type specification unit extracts the function descriptions of each monitoring device from the extracted operating parameters. For heart rate monitoring devices, the function description is to monitor the frequency changes of the user's heartbeats in real time, which can reflect the user's heart activity status and stress response. The function of the skin conductance monitoring device is to sense the changes in skin resistance, which is usually related to the activity of the autonomic nervous system of the human body and can indirectly reflect the user's emotional arousal level. The respiratory rate monitoring device is used to measure the number of breaths per unit time of the user, and the changes in breathing pattern can be used as one of the important indicators of psychological state. Through the extraction of these function descriptions, a set of data type descriptions is formed, which clearly defines the data types provided by each device and their physiological significance.

[0070] The feature coding processing unit respectively codes the basic information of the user group and each data type description in the data type description set. In processing the basic information of the user group, for age distribution, different age groups are divided into several numerical intervals, such as 0-12 years old, 13-18 years old, 19-35 years old, etc., and each interval is assigned a specific coding value to facilitate computer processing and analysis; the psychological assessment level is represented by different numerical sequences according to the results of professional psychological assessment scales, such as mild, moderate, and severe psychological problems corresponding to 1, 2, and 3, etc. numerical coding; social behavior patterns are coded through a pre-set feature vector, which includes social frequency, social occasion preference, social interaction mode, etc. dimensions, each dimension is assigned a corresponding weight value according to the actual situation of the user, and finally forms a multi-dimensional user parameter coding vector. For each data type description in the data type description set, it is coded according to its functional characteristics and attributes. For example, heart rate monitoring data type can be coded as a vector containing real-time, physiological relevance, numerical range, etc. attributes; skin conductance data type coding highlights its relevance to emotional state, measurement unit, change amplitude, etc. attributes, thereby forming a set of data type coding vectors.

[0071] The multi-source association analysis unit performs multi-source association analysis on the user parameter coding vector and the set of data type coding vectors. Through specific algorithms and models, this unit deeply mines the potential association relationship between user features and device data types. Specifically, the adaptability and correlation of user characteristics such as age distribution, psychological assessment level, and social behavior patterns with each device data type are analyzed. For example, for users with high psychological assessment level, more accurate skin conductance data may be needed to monitor their emotional changes, so the association weight between this user feature and the skin conductance data type coding vector will be increased in the association analysis. Through such multi-source association analysis, the user-device association optimization coding vector is finally obtained, which takes into account the individual differences of users and the characteristics of device data, providing an optimized basis for subsequent data collection.

[0072] The data acquisition regulation unit optimizes the coding vector based on the user-device association to generate the acquisition rules of heart rate fluctuation data, galvanic skin response data, and respiratory rate data, and determines the corresponding acquisition range. The data acquisition rule recommendation module takes the decision maker as the core, takes the user-device association optimization coding vector as the input, generates specific acquisition rules through the preset decision logic and rules. These rules include the time interval of acquisition, such as setting a shorter time interval to obtain more intensive data for users who need close monitoring; the sampling frequency, which is determined according to the performance of the device and the user's demand; the acquisition duration, which explicitly specifies the duration of each data acquisition. At the same time, based on the generated acquisition rules, the acquisition range of the data is determined, including the time starting point and the ending point of the acquisition, such as data acquisition in a specific time period during treatment, and the required data volume and accuracy requirements in that time period. For example, for younger users, considering their shorter attention span, the acquisition duration may be set to a shorter time period, while ensuring sufficient sampling frequency within that time period to obtain effective physiological data.

[0073] Throughout the process, the units work closely together to achieve precise acquisition of user physiological data by the wearable device collaboration module through extraction of device operating parameters, data type calibration, feature coding, multi-source data association analysis, and generation and regulation of acquisition rules, providing a reliable data foundation for subsequent interactive information processing, treatment plan generation, and collaborative execution feedback modules. The implementation of this module fully considers individual differences of users and device characteristics, ensuring the relevance and effectiveness of data acquisition, thereby improving the operation efficiency and treatment effect of the entire psychological treatment system.

[0074] Embodiment 2:

[0075] This embodiment mainly focuses on the specific implementation of the multi-source association analysis unit, which plays a key role in integrating user parameters and device data type coding and generating optimized association vectors in the wearable device collaboration module. The specific implementation is as follows:

[0076] The core function of the multi-source association analysis unit is completed by the data type coding feature integration sub-unit and the cross-domain collaborative coding sub-unit. First, the data type coding feature integration sub-unit needs to perform feature integration processing based on hierarchical mapping on the set of data type coding vectors. The set of data type coding vectors originates from the coding results of the feature coding processing unit in the wearable device collaboration module for each device function description, such as the coding vector of a heart rate monitoring device, which may contain dimensions such as sampling frequency, accuracy level, etc., and the coding vector of a galvanic skin response device, which involves measurement range, response time, etc.

[0077] The operation of the data type coding level mapping secondary subunit is based on a preset mapping matrix and a mapping offset vector. The mapping matrix is usually a multi-dimensional matrix, the dimensions of which are set to match the feature dimensions of the data type coding vector, for spatial transformation of the original coding vector. In the specific process, each data type coding vector is subjected to a point multiplication operation with the mapping matrix, which can achieve weight adjustment and dimension conversion of the features of each dimension of the original coding vector, and then subjected to a bitwise addition operation with the mapping offset vector. Each element of the mapping offset vector corresponds to the offset of each dimension of the coding vector, and through this operation, the transformed data can be mapped to a specific numerical interval, thereby obtaining the data type coding vector after level conversion. For example, if the "measurement range" dimension value in the original skin electric response data coding vector is [10-100 kΩ], it may be converted to the normalized interval [0.2-0.8] after weighting by the mapping matrix, and then adjusted to [0.3-0.9] by the offset vector, to adapt to the subsequent processing requirements.

[0078] After completing the level mapping, the data type coding matrix arrangement secondary subunit arranges all the data type coding vectors after level conversion in a matrix. This arrangement process follows a specific logic, usually taking the dimensions of the coding vector as rows or columns, combining the data type coding vectors of multiple devices in order to form a multi-dimensional data type coding feature matrix. For example, if there are coding vectors of heart rate, skin electricity, and respiratory rate devices, each vector contains 5 feature dimensions, then after arrangement, a 3x5 matrix is formed, and each element in the matrix corresponds to the coding value of a certain feature dimension of a certain device.

[0079] The data type coding matrix key extraction secondary subunit needs to extract a core vector from the data type coding feature matrix as a guide template. In the specific operation, for each data type coding vector after level conversion in the matrix, the distribution characteristics and importance of each dimension are analyzed, and the key value is extracted from each coding vector through a preset key value extraction rule (such as selecting the mean, median, or weighted value based on weight of each dimension), and finally combined to form the data type coding feature matrix core vector. The core vector condenses the key features of all device data types, for example, it may contain representative coding values of the main function dimensions of each device, which is used to guide the subsequent cross-domain collaborative coding process.

[0080] The processing of the cross-domain collaborative coding subunit is based on a guide template, realizing the associated fusion of the user parameter coding vector and the data type coding vector. The user parameter hierarchical mapping secondary subunit performs double mapping processing on the user parameter coding vector, in which the query matrix and the numerical matrix bear different mapping functions. The query matrix is usually used to extract the category or mode features in the user parameters, for example, the user's social behavior mode coding vector is mapped to the user parameter query vector through the query matrix, which may highlight the user's active degree, interaction preference and other features in social occasions; the numerical matrix is used to process the numerical features in the user parameters, such as age distribution, psychological assessment level, etc., which are mapped to the user parameter numerical vector, which retains the numerical relationship and magnitude information of the original data.

[0081] The processing flow of the template-guided heterogeneous conversion coding secondary subunit involves multi-layer operation. First, the product of the user parameter query vector and the transposed vector of the data type coding vector after hierarchical conversion is calculated, obtaining the user-device association feature matrix. Each element of the matrix reflects the association degree of a user feature and a device data type feature, for example, the product value of the user's "psychological assessment level" feature and the skin conductance response device "emotion correlation" feature can represent the demand intensity of the user for emotion monitoring data. Subsequently, the matrix is divided by the module length of the data type coding feature matrix core vector by bit, and the module length is calculated based on the square sum of the elements of the core vector. Through this operation, the association feature matrix can be normalized to eliminate the influence of the magnitude difference of different device data type features, obtaining the user-device association weight matrix.

[0082] Then, the association weight matrix is input into a normalization function (such as Softmax function or linear normalization function) for processing, so that the values of the elements in the matrix are mapped to the [0, 1] interval, forming the user-device association normalized weight matrix. The weight values in the matrix directly reflect the association strength of the user features and the device data type features. After that, the normalized weight matrix is multiplied by the data type coding feature matrix core vector, obtaining the weight-based feature vector, which integrates the weighted influence of the user features on the device data type. Finally, the feature vector is processed by bit-by-bit point multiplication with the user parameter numerical vector, retaining the original numerical features of the user while integrating the association features of the device data type, thereby generating the user-device cross-domain collaborative coding vector.

[0083] The position mean value calculation secondary sub-unit sequentially processes all generated user-equipment cross-domain collaborative coding vectors, obtains the final user-equipment associated optimized coding vector by calculating the mean vector of the sequence at each position. For example, if 10 cross-domain collaborative coding vectors are generated, each vector contains 8 dimensions, the mean value of the 10 values in each dimension is calculated to form an 8-dimensional mean vector, which integrates the characteristics of all collaborative coding vectors, and realizes the optimized association of user parameters and device data types.

[0084] During the entire process, the multi-source association analysis unit deeply fuses the individual characteristics of the user and the data type characteristics of the device through steps such as hierarchical mapping, matrix operation, and weight calculation, and generates an optimized coding vector that reflects the personalized needs of the user for data collection and integrates the functional characteristics of the device. This provides a key basis for the subsequent data collection regulation unit to generate accurate collection rules, ensuring the pertinence and efficiency of the wearable device collaboration module in the data collection link.

[0085] Embodiment 3:

[0086] This embodiment mainly focuses on the specific implementation method of the data collection regulation unit. This unit is in a key end execution link in the wearable device collaboration module and undertakes the important function of converting the user-equipment associated optimized coding vector into specific data collection rules and ranges. Its specific implementation process is as follows:

[0087] The core operation of the data collection regulation unit begins with the reception and processing of the user-equipment associated optimized coding vector. This coding vector is derived from the output of the multi-source association analysis unit and is a multi-dimensional vector formed by integrating the basic information of the user group (such as age distribution, psychological assessment level, social behavior pattern, etc.) and the data type characteristics of the wearable device (such as the function code of heart rate monitoring devices, skin electrical response monitoring devices, and respiratory rate monitoring devices). For example, this vector may contain dimensions reflecting the correlation between user psychological assessment level and skin electrical response data collection frequency, or dimensions reflecting the matching degree of age distribution and heart rate data sampling accuracy, etc. The numerical value of each dimension represents the association weight or optimization parameter between user characteristics and device data types.

[0088] The user-device association optimization encoding vector input-based decision maker data collection rule recommendation module is the key first step. The module is internally constructed with pre-set decision logic and rule models, which is essentially an intelligent processing component based on machine learning or rule engine. The core function of the decision maker is to analyze the dimensional parameters in the encoding vector, and based on the user and device association information contained in these parameters, to deduce the physiological data collection rules suitable for the user group. The rule construction of the decision maker is usually based on the professional knowledge and historical data experience in the field of psychological therapy, for example, for users of different psychological assessment levels, combined with their possible emotional fluctuation characteristics, the physiological data collection frequency, duration, etc. rule framework corresponding to them is preset.

[0089] In the specific processing process, the decision maker first disassembles the encoding vector by dimension, identifying various parameters related to heart rate fluctuation data, skin conductance response data, and respiratory frequency data collection. Taking the encoding dimension corresponding to the psychological assessment level as an example, if the dimension value is high, it indicates that the user may have obvious psychological stress response, and the decision maker will automatically match to the rule branch that needs to increase the skin conductance response data collection frequency according to the pre-set rules, for example, adjusting the regular 1 collection per minute to 1 collection every 30 seconds, to capture the user's emotional physiological signals more densely. For the encoding dimension corresponding to the age distribution, if the value points to the youth group, considering the physiological characteristics and attention concentration time characteristics of this group, the decision maker may generate rules to shorten the single collection duration but increase the sampling frequency, such as adjusting 5 minutes each time to 3 minutes each time but increasing the sampling frequency per second, to obtain more effective data within a limited time.

[0090] After analysis and deduction by the decision maker, the collection rules for the three types of physiological data are finally generated. These rules contain multiple specific parameters: for heart rate fluctuation data, the rule may involve sampling frequency (such as 256 samples per second), collection time window (such as 2 minutes of continuous collection every 10 minutes during treatment), data precision requirement (such as heart rate value with two decimal places), etc.; the rule for skin conductance response data may include baseline value calibration period (such as calibration once every 30 minutes), dynamic range setting (such as 0-10 microsiemens), noise filtering threshold (such as fluctuations less than 0.5 microsiemens are considered as noise), etc.; the rule for respiratory frequency data may cover collection method (such as impedance or chest strap), respiratory cycle calculation method (such as based on peak detection or cycle mean), abnormal respiratory pattern trigger threshold (such as triggering warning collection when respiratory frequency exceeds 30 times / minute or is less than 8 times / minute), etc.

[0091] After generating the collection rules, the data collection regulation unit needs to further determine the specific collection range based on these rules. The determination of the collection range involves the dual definition of the time dimension and the data dimension. In the time dimension, the starting time point, the ending time point and the collection period of data collection need to be clarified. For example, if the treatment plan is set to be carried out from 2:00 pm to 3:00 pm every day, the collection range may be set to start the preheating collection 5 minutes before the treatment, collect for 5 minutes every 20 minutes during the treatment, and collect for 10 minutes after the treatment to monitor the recovery state. For users with high psychological assessment level, intermittent collection during night sleep, such as 10 minutes every hour, may be additionally added outside the regular treatment period to capture physiological signals in sleep state.

[0092] In the data dimension, the collection range needs to clarify the collection amount, accuracy requirement and data format of each type of physiological data. Taking heart rate fluctuation data as an example, if the rule sets the sampling frequency to 256 Hz and the collection time to 2 minutes each time, the data amount of a single collection is 256 x 120 = 30720 data points, and the collection range needs to clearly require the device to generate data at this frequency and time length, and stipulate that the data is stored in CSV format, including two columns of time stamp and heart rate value. For skin conductance data, the collection range may require the device to record baseline value, real-time response value and environmental temperature data synchronously during each collection to exclude the interference of environmental factors on skin conductance. The collection range of respiratory frequency data may stipulate that respiratory waveform data and frequency calculation results need to be recorded simultaneously to facilitate multi-dimensional analysis by the subsequent interactive information processing module.

[0093] In addition, the data collection regulation unit also needs to have a mechanism for dynamically adjusting the collection range. When some parameters in the user-device association optimization encoding vector change (such as the psychological assessment level of the user decreases after a period of treatment), the decision maker will re-analyze the encoding vector and update the collection rules, and then adjust the collection range. For example, if the psychological assessment level of the user improves from severe to moderate, the collection frequency of skin conductance data may be adjusted from once every 30 seconds to once every minute, and the collection time is also shortened accordingly. At this time, the collection range needs to be updated synchronously in terms of time window and data amount requirement to ensure that data collection can meet the treatment monitoring needs and will not cause excessive burden to the user.

[0094] Throughout the whole process, the data acquisition regulation unit realizes the data acquisition regulation function of the wearable device coordination module by converting the abstract optimization code vector into specific executable acquisition rules and ranges. This process not only considers the matching of individual characteristics of users and device performance, but also combines the professional needs of psychological therapy, ensuring that the collected heart rate fluctuation data, skin electric response data and respiratory frequency data are targeted, effective and standardized, providing a high-quality data foundation for the subsequent interactive information processing module to extract physiological-psychological correlation features, thereby ensuring the operation effect of the whole psychological therapy system.

[0095] Embodiment 4:

[0096] This embodiment mainly focuses on the specific implementation of the treatment plan generation module. This module undertakes the core function of converting the physiological-psychological correlation feature set into a standardized interpersonal psychological treatment plan in the system. Its specific implementation process needs to combine the user group basic information and physiological data features to realize the construction, adjustment and coordination strategy generation of the plan through multi-level processing. The following will be explained in detail in combination with specific examples:

[0097] The starting operation of the treatment plan generation module is performed by the plan framework construction unit. The core task of this unit is to extract the core feature dimensions from the physiological-psychological correlation feature set output by the interactive information processing module. Taking the treatment scene of a certain group of adolescent depression as an example, suppose the physiological-psychological correlation feature set contains features such as heart rate variability (HRV) reduction, skin electric response (SCR) baseline value increase, respiratory frequency (RR) abnormal fluctuation, etc. The plan framework construction unit will identify the most representative feature dimensions for depression state through feature importance evaluation algorithms (such as feature sorting based on information gain or decision tree), such as the low frequency (LF) and high frequency (HF) power ratio of HRV, the burst amplitude of SCR, the inspiration-expiration time ratio (I / E ratio) of RR, etc. These features will be used as the core elements to build the basic framework of the treatment plan.

[0098] The construction of the basic framework needs to integrate the professional knowledge system in the field of psychological therapy. Still taking the adolescent depression group as an example, the basic framework may include the core modules of cognitive behavioral therapy (CBT), such as emotion recognition training, cognitive restructuring exercises, social skills training, etc. In the framework structure, it is usually divided into three stages: evaluation period, intervention period, and consolidation period. The evaluation period is set for the first 2 weeks, focusing on collecting HRV, SCR and other data through wearable devices to determine the baseline level; the intervention period is from the 3rd to the 8th week, and the CBT group therapy is designed twice a week, combined with the emotion log recording function of the digital interactive terminal; the consolidation period is from the 9th to the 12th week, and the family support module is introduced to monitor the physiological indicators under the home state through the wearable device. The treatment goals of each stage in the framework also need to be clearly defined, such as the evaluation period goal is to complete the correlation analysis of psychological assessment level and physiological indicators, and the intervention period goal is to increase the HF power of HRV by 20% (Note: This is only a logical example and does not involve specific data effects).

[0099] The work of the personalized adjustment unit is to match and analyze the basic information of the user group with the basic framework of the treatment plan. Taking a user group containing 15-18 year old adolescents as an example, the basic information may show that the age distribution is concentrated around 16 years old, the psychological assessment level is mainly moderate depression, and the social behavior pattern is characterized by low offline social interaction frequency but active online interaction. The personalized adjustment unit will adaptively modify the basic framework according to these characteristics: in the group therapy of cognitive behavioral therapy, the traditional face-to-face role-playing is replaced by virtual reality (VR) based social scene simulation to match the preference of adolescents for digital interaction; considering the shorter attention span of this age group, the duration of single group therapy is shortened from 60 minutes to 45 minutes, and the instant feedback link of the digital interactive terminal is increased, such as real-time labeling of emotional state during therapy through tablet devices.

[0100] For the sub-group of users with introverted social behavior patterns, the personalized adjustment unit will further refine the program template. For example, in the social skills training module, initial interaction is carried out through the text chat function of the digital interactive terminal, and after the user's physiological indicators (such as HRV, SCR) show a decrease in stress level, gradual transition to voice or video interaction is made. This phased intervention strategy is based on the feedback of physiological data collected by wearable devices to ensure that the intervention intensity matches the user's psychological tolerance. If the user group contains a large age difference (such as 12-year-old children and 18-year-old adolescents), the personalized adjustment unit will generate differentiated program templates, designing emotion recognition training with game elements for children (such as matching emotional states through cartoon characters), and designing more autonomous cognitive restructuring tasks for adolescents (such as recording negative thoughts and attempting to refute them).

[0101] The task of the collaborative strategy generation unit is to generate a collaborative execution strategy for the digital interactive terminal and the wearable device based on the personalized treatment plan template. Taking the mood journaling function as an example, the digital interactive terminal (such as a dedicated APP) will push a log filling reminder at 8 pm every day, and the user needs to record the main emotional events and emotional intensity (1-10 points) in the APP, while the wearable device (such as a smart bracelet) will automatically upload the HRV variability curve and SCR peak value of the day, and the system will timestamp align the user's subjective log and physiological data to form an "emotional event-subjective score-physiological response" association record. This collaborative strategy realizes the synchronous collection of subjective psychological state and objective physiological indicators, providing multi-dimensional data for subsequent treatment effect evaluation.

[0102] In the group therapy scenario, the collaborative strategy is embodied in the real-time data interaction between the device and the terminal. For example, when conducting VR social scene simulation, the wearable device will collect the participant's heart rate, skin electric reaction and other data in real time and transmit them to the background system of the digital interactive terminal. The system will automatically trigger the intervention mechanism of the interactive terminal according to the preset physiological stress threshold (such as heart rate exceeding 100 times / minute and SCR amplitude > 0.5 microsiemens), and insert a guide sentence (such as "please try deep breathing") in the VR scene, and send a vibration reminder on the participant's bracelet at the same time. This real-time collaborative mechanism ensures the timeliness of the treatment intervention, avoiding psychological discomfort of the user in high stress state.

[0103] Taking the treatment of the family consolidation period as an example, the collaborative strategy may involve the linkage of the wearable device and the family terminal. The smart watch will automatically generate a sleep breathing frequency data report of the previous night every morning, which is transmitted to the family terminal APP through Bluetooth, and the parents can view the child's sleep quality indicators (such as apnea frequency, deep sleep period RR stability, etc.) in the APP, while the digital interactive terminal will push family intervention suggestions for sleep problems (such as turning off electronic devices 1 hour before sleep, creating a quiet environment, etc.). This collaborative strategy extends the treatment scene from professional institutions to family environment, and realizes continuous treatment supervision and support through cross-scene transmission of device data.

[0104] The operation of each unit in the whole implementation process of the treatment plan generation module is based on the combination of data-driven and domain knowledge. The plan framework construction unit relies on the objective analysis of physiological-psychological correlation characteristics, the personalized adjustment unit combines the specific characteristics of the user group for adaptive modification, and the collaborative strategy generation unit focuses on the integration of the functions of the equipment and the terminal. Taking the treatment plan for the adolescent depression group as an example, through the processing of the module, the finally generated plan not only contains the standardized CBT treatment framework, but also is personalized adjusted according to the age characteristics, psychological state and social mode of adolescents, and through the collaborative execution strategy of the digital interactive terminal and the wearable device, the whole-process digital management of physiological data acquisition, treatment intervention implementation and effect feedback is realized, which provides an operable treatment plan basis for the subsequent collaborative execution feedback module.

[0105] Embodiment 5:

[0106] This embodiment mainly focuses on the specific implementation mode of the collaborative execution feedback module. The module undertakes the important functions of converting the treatment plan into a specific execution process and collecting feedback data to record the treatment effect in the system, and its specific implementation process needs to combine the collaborative operation of the digital interactive terminal and the wearable device, realize the whole-cycle management of the treatment process through process planning, data acquisition and effect recording, which will be described in detail below in combination with specific examples:

[0107] The starting operation of the collaborative execution feedback module is responsible for the execution process planning unit, which needs to decompose the collaborative execution strategy output by the treatment plan generation module into an executable step sequence. Taking the cognitive behavioral therapy plan for a certain adult social anxiety disorder as an example, the collaborative execution strategy may include "VR social scene exposure training", "breathing relaxation guidance", "real-time physiological feedback" and other modules. The execution process planning unit will decompose these modules into specific steps: 10 minutes before treatment, the digital interactive terminal (such as VR headset) loads the preset social scene (such as company meeting speaking scene), and the wearable device (such as chest strap breathing sensor, wrist skin electricity monitor) performs initialization calibration; during the first 15 minutes of treatment, the user enters the VR scene to perform the speaking task, and the wearable device collects real-time breathing frequency and skin electricity response data and transmits them to the terminal; during the 16th-20th minute of treatment, the terminal generates relaxation guidance audio according to the collected physiological data, and the user follows the guidance to perform deep breathing training; during the 21st-30th minute of treatment, the VR scene task is repeated and the difficulty is adjusted (such as increasing the number of virtual audience), and the whole process forms a "scene exposure-physiological monitoring-intervention adjustment-re-exposure" cycle execution process.

[0108] The decomposition of the step sequence needs to consider the time node and task dependency relationship. For example, in a group therapy scenario, if the therapy plan includes three links of "individual speech - group discussion - collective feedback", the execution flow planning unit will set specific time windows for each link (such as 3 minutes for individual speech and 10 minutes for group discussion), and determine the synchronization node of the wearable device data collection - in the individual speech stage, the heart rate variability data of the speaker is collected, in the group discussion stage, the skin conductance baseline value of all members is collected, and in the collective feedback stage, the facial expression video (through the terminal camera) and physiological indicator fluctuation of the user are recorded. The execution instructions of each step are sent synchronously to the digital interaction terminal and the wearable device through the API interface, ensuring that the device action is strictly aligned with the therapy process.

[0109] The feedback data collection unit collects language feedback information and behavior feedback information of the user during the therapy process through the digital interaction terminal. Taking online group therapy as an example, the digital interaction terminal can be a special video conference platform with functions such as speech-to-text, chat record saving, and screen sharing. During the therapy process, the language feedback information of the user includes speech content, questions, emotional expression, etc. These information will be transcribed into text in real time and stored, and time stamps are also marked. For example, the user said "my heart rate was very fast and my palms were sweating after speaking" after exposure in the VR scene, which will be transcribed into a text record and associated with the heart rate (such as 110 beats per minute) and skin conductance (such as 1.2 microsiemens) data collected by the wearable device at the same time point.

[0110] The collection of behavior feedback information covers multi-modal data. The camera of the digital interaction terminal will capture the facial expressions (such as frowning, smiling) and body movements (such as finger tremor, changes in sitting posture) of the user, and extract features such as expression intensity and movement frequency through computer vision algorithms; the touch screen of the terminal will record the user's interaction behavior, such as the number of times the "skip" button is clicked and the frequency of sliding the progress bar. The wearable device provides physiological behavior feedback, such as sudden acceleration of breathing rate and sudden rise of skin conductance. Taking the "eye contact training" in social anxiety therapy as an example, the smart glasses worn by the user will record the duration of eye contact with the virtual object, the digital interaction terminal will record the facial expression tension of the user (by analyzing the frequency of eye muscle contraction through the camera), and the wearable device will collect the heart rate variability at that time, forming a multi-dimensional behavior feedback data set.

[0111] The core task of the execution effect recording unit is to record the completion status of the treatment execution process and the language and behavior feedback information. Taking the treatment of adult social anxiety as an example, the completion status of the "three VR scene exposure" task set by the execution process planning unit needs to be recorded as "number of completed times / total number of times", such as "2 / 3", and the reason for not completing (such as the user quitting in the middle) is marked. At the same time, the language feedback information (such as the user describing "the second scene is more nervous than the first") and the behavior feedback information (such as the eye contact time increasing from 15 seconds in the first time to 25 seconds, and the skin conductance response peak decreasing from 1.8 microsiemens to 1.4 microsiemens) corresponding to each exposure task will be integrated into the record of the task in chronological order.

[0112] The implementation of the association record is based on a unified timestamp system. The digital interactive terminal and the wearable device synchronize the clock at the beginning of the treatment, ensuring that the timestamp of all data is accurate to the millisecond level. For example, when the user completes a speaking task in the VR scene (the execution process time node is 10:05:30), the wearable device records the heart rate peak of 115 times per minute at 10:05:32, and the terminal captures the user's behavior of clicking the "end task" button at 10:05:35. These events will be associated with the record entry of "VR scene exposure task-2nd", forming a chain record of "time-event-physiological data-behavior data".

[0113] In the family therapy scene, the association record function of the execution effect recording unit is particularly important. For example, when the user uses the digital interactive terminal to complete the "daily mood log" task at home, the terminal will record the log filling time, mood score, and text description, as well as the language feedback information, while the wearable device automatically uploads the activity amount, sleep quality, and resting heart rate of the day. The system will associate the "mood improved after talking to friends today" recorded in the log with the increased heart rate variability and decreased skin conductance response baseline during the call period, forming a record of the treatment effect in the home environment. If the user does not complete the log filling on time, the execution effect recording unit will mark "task missing", and in combination with the wearable device data, it will determine whether there is an abnormal physiological indicator (such as high heart rate all day), providing a basis for subsequent treatment plan adjustment.

[0114] During the whole implementation process of the feedback module, the operations of each unit are closely related to the landing of the treatment plan and the data loop. The execution flow planning unit ensures the orderly execution of the treatment steps, the feedback data acquisition unit realizes the comprehensive capture of multi-source feedback information, and the execution effect recording unit constructs a complete treatment process archive through timestamp association. Taking the treatment of social anxiety disorder as an example, through the processing of the module, the therapist can check the execution flow completion situation, real-time physiological data curve, language and behavior feedback record of each user on the monitoring terminal. For example, if a user's heart rate is continuously higher than 120 times per minute and accompanied by the language feedback of "want to escape" during VR scene exposure, the difficulty of the scene in the subsequent treatment plan can be adjusted in time to realize the dynamic optimization of the treatment plan based on data feedback. This closed-loop mechanism ensures the traceability and adjustability of the treatment process, and provides data support for improving the precision and effectiveness of interpersonal psychological treatment.

[0115] It should be noted that, in this document, the terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device.

[0116] Although the embodiments of the present application have been shown and described, it can be understood by those skilled in the art that various changes, modifications, replacements and variations can be made to the embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A system for interpersonal psychotherapy based on digital human-computer interaction and wearable device cooperation, characterized in that, The method comprises the following steps: a user state perception module is used to obtain basic information of a user group participating in psychological treatment, the basic information including age distribution, psychological assessment level and social behavior mode; a wearable device coordination module is used to collect heart rate fluctuation data, skin electric response data and breathing frequency data through wearable physiological monitoring devices based on the basic information of the user group; an interactive information processing module is used to perform multi-dimensional interactive information fusion processing on the heart rate fluctuation data, skin electric response data and breathing frequency data to obtain a physiological- psychological correlation feature set; a treatment scheme generation module is used to generate a standardized interpersonal psychological treatment scheme based on the physiological- psychological correlation feature set; a coordinated execution feedback module is used to execute the standardized interpersonal psychological treatment scheme through a digital interactive terminal and a wearable device, and transmit execution process data to a monitoring terminal for recording. 2.The system of claim 1, wherein, The wearable device coordination module comprises: a device configuration analysis unit is used to extract operating parameters of heart rate monitoring devices, skin electric response monitoring devices and breathing frequency monitoring devices from a wearable device management platform; a data type calibration unit is used to extract function descriptions of each monitoring device in the operating parameters to obtain a set of data type descriptions; a feature coding processing unit is used to perform feature coding on the basic information of the user group and each data type description in the set of data type descriptions to obtain a user parameter coding vector and a set of data type coding vectors; a multi-source correlation analysis unit is used to perform multi-source correlation analysis on the user parameter coding vector and the set of data type coding vectors to obtain a user- device correlation optimization coding vector; a data collection regulation unit is used to generate collection rules of the heart rate fluctuation data, skin electric response data and breathing frequency data based on the user- device correlation optimization coding vector. 3.The system of claim 2, wherein, The multi-source correlation analysis unit comprises: a data type coding feature integration subunit is used to perform feature integration processing based on hierarchical mapping on the set of data type coding vectors to obtain a guide template; a cross-domain collaborative coding subunit is used to perform cross-domain collaborative coding on the user parameter coding vector and the set of data type coding vectors based on the guide template to obtain the user- device correlation optimization coding vector. 4.The system of claim 3, wherein, The data type coding feature integration subunit comprises: a data type coding hierarchical mapping secondary subunit is used to perform hierarchical mapping processing on each data type coding vector in the set of data type coding vectors using a mapping matrix to obtain a set of hierarchical converted data type coding vectors; a data type coding matrix arrangement secondary subunit is used to arrange the set of hierarchical converted data type coding vectors in a matrix to obtain a data type coding feature matrix; a data type coding matrix key extraction secondary subunit is used to extract key values of each hierarchical converted data type coding vector in the data type coding feature matrix to obtain a data type coding feature matrix core vector as the guide template. 5.The system of claim 4, wherein, The data type coding hierarchical mapping secondary subunit comprises: The data type coding vector is point multiplied with the mapping matrix and then bitwise added with a mapping offset vector to obtain a hierarchical conversion data type coding vector. 6.The system of claim 5, wherein, The cross-domain collaborative coding subunit comprises: A user parameter hierarchical mapping secondary subunit configured to perform hierarchical mapping on the user parameter coding vector using a query matrix and a numerical matrix to obtain a user parameter query vector and a user parameter numerical vector; A template-guided heterogeneous conversion coding secondary subunit configured to input the user parameter query vector, the user parameter numerical vector, each hierarchical conversion data type coding vector in the data type coding feature matrix, and the guide template into a template-guided heterogeneous conversion structure to obtain a sequence of user-equipment cross-domain collaborative coding vectors; A position mean value calculation secondary subunit configured to calculate a bitwise mean vector of the sequence of user-equipment cross-domain collaborative coding vectors to obtain the user-equipment association optimization coding vector. 7.The system of claim 6, wherein, The template-guided heterogeneous conversion coding secondary subunit comprises: A product result of the user parameter query vector and a transposed vector of the hierarchical conversion data type coding vector is calculated, and a user-equipment association feature matrix obtained by dividing the product result by a module length of the data type coding feature matrix core vector is obtained to obtain a user-equipment association weight matrix; The user-equipment association weight matrix is input into a normalization function for processing to obtain a user-equipment association normalized weight matrix; The user-equipment association normalized weight matrix is multiplied with the data type coding feature matrix core vector, and a feature vector obtained by bitwise point multiplication of the product result and the user parameter numerical vector is obtained to obtain a user-equipment cross-domain collaborative coding vector. 8.The system of claim 7, wherein, The data collection regulation unit comprises: The user-equipment association optimization coding vector is input into a data collection rule recommendation module based on a decision maker to obtain a collection rule of the heart rate fluctuation data, the galvanic skin response data, and the respiratory frequency data. Based on the collection rule, a collection range of the heart rate fluctuation data, the galvanic skin response data, and the respiratory frequency data is determined. 9.The system of claim 8, wherein, The treatment scheme generation module comprises: A scheme framework construction unit configured to extract a core feature dimension in the physiological-psychological association feature set to construct a treatment scheme basic framework; A personalized adjustment unit configured to perform matching analysis on the basic information of the user group and the treatment scheme basic framework to obtain a personalized treatment scheme template; A collaborative strategy generation unit configured to generate a collaborative execution strategy of a digital interactive terminal and a wearable device based on the personalized treatment scheme template. 10.The system of claim 9, wherein, The collaborative execution feedback module comprises: An execution flow planning unit configured to decompose the collaborative execution strategy into an executable step sequence to obtain a treatment execution flow; A feedback data collection unit configured to collect language feedback information and behavior feedback information in a user treatment process through a digital interactive terminal; An execution effect recording unit configured to record a completion state of the treatment execution flow in association with the language feedback information and the behavior feedback information.

Images