Monitoring and early warning method and system based on wearable device information interaction
By introducing data sensing, evaluation monitoring and pulse activation modules into wearable devices, real-time sensing and generation of state change matrices, state transfer optimization, identification and sending of early warning information to control pulse current, the problem of weak targeted monitoring and early warning functions of wearable devices is solved, and the utilization rate of monitoring data is improved.
Patent Information
- Application Number
- CN202310771904.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-28
- Publication Date
- 2025-09-26
- Estimated Expiration
- 2043-06-28
AI Technical Summary
The monitoring and early warning functions of existing wearable devices during information interaction are weakly targeted, resulting in low utilization of monitoring data.
By introducing data sensing modules, evaluation and monitoring modules and pulse activation modules into wearable devices, user data is sensed in real time, a state change matrix is generated, state transition optimization is performed, multiple state optimization results are identified, and early warning information is sent through the terminal to control the pulse activation module to generate pulse current.
It enhances the pertinence of the monitoring and early warning functions of wearable devices during the information interaction process and improves the utilization rate of monitoring data.
Smart Images

Figure CN116740909B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a monitoring and early warning method and system based on wearable device information interaction. Background Art
[0002] With the development of science and technology, especially wearable devices, wearable devices refer to portable digital products that are worn directly on the body or placed in clothing and accessories. They primarily process information, can be controlled by humans, and achieve powerful and continuous functions through software support and cloud interaction. They are the inevitable product of the concept of "people-oriented, human-machine integration", and embody the optimal state of human-machine collaboration. Wearable products far exceed the scope of traditional mobile products in many aspects, including concept, human-machine relationship, interaction mode, function, application field, design and development method. Today, they are a brand-new concept and model. However, the monitoring and early warning functions of wearable devices in existing technologies are weakly targeted during the information interaction process, and there are technical problems that reduce the utilization rate of monitoring data. Summary of the Invention
[0003] The present application provides a monitoring and early warning method and system based on wearable device information interaction, which is used to solve the problem in the prior art that the monitoring and early warning functions of wearable devices are weakly targeted during the information interaction process, resulting in low utilization of monitoring data.
[0004] In view of the above problems, the present application provides a monitoring and early warning method and system based on wearable device information interaction.
[0005] In the first aspect, the present application provides a monitoring and early warning method based on information interaction of wearable devices, the method comprising: connecting to a first wearable device of a first user, wherein the first wearable device comprises a data sensing module, an evaluation monitoring module and a pulse activation module, and the data sensing module is a stress patch contact carrier sensor; performing real-time data sensing of the first user according to the data sensing module, and outputting a first real-time monitoring data set; inputting the first real-time monitoring data set into the terminal of the evaluation monitoring module for data fusion of various evaluation indicators, and generating a state change matrix, the state change matrix comprising a state change matrix based on multiple evaluation indicators; performing state transfer optimization according to the state change matrix, and outputting multiple state optimization results of multiple evaluation indicators; identifying the multiple state optimization results, generating a first early warning information, and sending the first early warning information to the first user through the terminal of the first wearable device to obtain a first activation instruction; controlling the pulse activation module according to the first activation instruction to generate a first pulse current.
[0006] In a second aspect, the present application provides a monitoring and early warning system based on wearable device information interaction, the system comprising: a device module, the device module being used to connect to a first wearable device of a first user, wherein the first wearable device comprises a data sensing module, an evaluation monitoring module and a pulse activation module, and the data sensing module is a stress patch contact carrier sensor; a real-time sensing module, the real-time sensing module being used to perform real-time data sensing of the first user according to the data sensing module, and output a first real-time monitoring data set; a data fusion module, the data fusion module being used to input the first real-time monitoring data set into the terminal of the evaluation monitoring module for data fusion of various evaluation indicators, and generate a state change matrix, the state change matrix including a state change matrix based on multiple evaluation indicators; a state transition optimization module, the state transition optimization module being used to perform state transition optimization according to the state change matrix, and output multiple state optimization results for multiple evaluation indicators; an identification module, the identification module being used to identify the multiple state optimization results, generate a first warning message, and send the first warning message to the first user through the terminal of the first wearable device to obtain a first activation instruction; a control module, the control module being used to control the pulse activation module according to the first activation instruction to generate a first pulse current.
[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0008] The monitoring and early warning method and system based on information interaction of wearable devices provided in this application relate to the field of data processing technology. They solve the technical problem in the prior art that the monitoring and early warning functions of wearable devices are weakly targeted during the information interaction process, resulting in low utilization rate of monitoring data. They achieve the goal of enhancing the functional targeting of monitoring and early warning functions of wearable devices in information interaction and improving the utilization rate of monitoring data. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] Figure 1 This application provides a flow chart of a monitoring and early warning method based on wearable device information interaction;
[0010] Figure 2 This application provides a schematic diagram of the output state change matrix flow in the monitoring and early warning method based on wearable device information interaction;
[0011] Figure 3 This application provides a schematic diagram of the process of outputting multiple state optimization results in a monitoring and early warning method based on wearable device information interaction;
[0012] Figure 4 This application provides a schematic diagram of the process of outputting the second warning information in the monitoring and warning method based on wearable device information interaction;
[0013] Figure 5 A schematic diagram of the structure of a monitoring and early warning system based on information interaction of wearable devices is provided for this application.
[0014] Explanation of the accompanying drawings: equipment module 1, real-time sensing module 2, data fusion module 3, state transition optimization module 4, identification module 5, control module 6. DETAILED DESCRIPTION
[0015] The present application provides a monitoring and early warning method and system based on information interaction of wearable devices, which is used to solve the technical problem in the prior art that the monitoring and early warning functions of wearable devices are weakly targeted during the information interaction process, resulting in low utilization of monitoring data.
[0016] Example 1
[0017] like Figure 1 As shown, the embodiment of the present application provides a monitoring and early warning method based on wearable device information interaction, the method comprising:
[0018] Step S100: connecting a first wearable device of a first user, wherein the first wearable device includes a data sensing module, an evaluation and monitoring module, and a pulse activation module, and the data sensing module is a stress patch contact carrier sensor;
[0019] Specifically, the monitoring and early warning method based on wearable device information interaction provided in the embodiment of the present application is applied to a monitoring and early warning system based on wearable device information interaction. In order to ensure the functional targeting of the wearable device in the later information interaction process, the system can first be connected to the first wearable device of the first user. The first user refers to the target user who uses the wearable device. The first wearable device refers to multiple wearable devices that can be used simultaneously on the first user. A wearable device used by the first user is randomly selected from the multiple wearable devices and recorded as the first wearable device. The first wearable device includes a data sensing module, an evaluation and monitoring module, and a pulse activation module. The data sensing module is a stress patch contact carrier sensor used to sense data between the first user and the wearable device. The evaluation and monitoring module is used to perform abnormal information evaluation and monitoring on the first wearable device used by the first user during the information interaction process. The pulse activation module is used to activate the wearable device with pulse current according to the state of the first user, so that the state of the first user changes in a preset direction.
[0020] Furthermore, the first wearable device can interact with other wearable devices and, in combination with the basic information of the first user, better monitor and warn the wearable device during the information interaction process.
[0021] Through the information interaction of multiple wearable devices and combined with the basic information of users, the multi-level warning interval is determined, and the warning adjustment of the multi-level warning interval is carried out according to the sensitivity and stability of the wearable devices to monitor and warn users.
[0022] Step S200: performing real-time data sensing on the first user according to the data sensing module, and outputting a first real-time monitoring data set;
[0023] Specifically, the data sensing module in the first wearable device is used as the basic module for data collection, so as to perform real-time data sensing of the first user through the data sensing module, which means that the skin quality parameters of the first user, the BMI parameters of the first user and the ECG+PPG monitoring parameters of the first user are sensed through the data sensing module in the first wearable device used by the first user. The skin quality parameters of the first user may include the pore parameters of the first user's skin quality, the dryness parameters of the first user's skin quality, the color spot parameters of the first user's skin quality, the skin age parameters of the first user's skin quality, the blackhead parameters of the first user's skin quality, the wrinkle parameters of the first user's skin quality, the BM parameters of the first user The I parameters may include body mass index parameters, body type parameters, standard weight parameters, body age parameters, body fat percentage parameters, protein parameters, fat control parameters, total water parameters, bone parameters, fat-free body mass parameters, basal metabolic rate parameters, weight control parameters, body condition index parameters, and visceral fat parameters. The ECG+PPG monitoring parameters of the first user may include heart rate, blood pressure, blood oxygen, electrocardiogram, spleen, stomach, kidney, liver and other visceral detection parameters. At the same time, the real-time sensing parameters collected by the data sensing module are summarized and integrated and recorded as the first real-time monitoring data set, thereby ensuring the monitoring and early warning of wearable devices during the information interaction process.
[0024] Step S300: inputting the first real-time monitoring data set into the terminal of the evaluation and monitoring module to perform data fusion of various evaluation indicators to generate a state change matrix, wherein the state change matrix includes a state change matrix based on multiple evaluation indicators;
[0025] Furthermore, if Figure 2 As shown, step S300 of this application also includes:
[0026] Step S310: Acquire multiple evaluation indicators and a historical evaluation matrix corresponding to each evaluation indicator in the multiple evaluation indicators, wherein each vector in the evaluation matrix is relevant data of the corresponding evaluation indicator;
[0027] Step S320: inputting the first real-time monitoring data set into the terminal of the evaluation and monitoring module, identifying the first real-time monitoring data set, and outputting an updated evaluation matrix based on the multiple evaluation indicators;
[0028] Step S330: Fusing the updated evaluation matrix with the historical evaluation matrix to output a fused evaluation matrix;
[0029] Step S340: Output the state change matrix using the historical evaluation matrix and the fusion evaluation matrix.
[0030] Specifically, in order to improve the monitoring and evaluation of the first wearable device of the first user, it is necessary to use the above-mentioned first real-time monitoring data set as input data and input it into the terminal of the evaluation and monitoring module in the first wearable device to perform data fusion of various evaluation indicators, which means first obtaining multiple evaluation indicators and the historical evaluation matrix corresponding to each evaluation indicator in the multiple evaluation indicators. The multiple evaluation indicators can be used to evaluate the first user's posture, the first user's body composition, and the first user's body dimension. At the same time, each evaluation indicator in the multiple evaluation indicators corresponds to a historical evaluation matrix, wherein the historical evaluation matrix refers to a matrix composed of a set of complex numbers or real numbers arranged in a rectangular array corresponding to the vectors corresponding to the evaluation index of the first user under the evaluation indicator. The larger the evaluation index, the better the physical condition of the first user, and each vector in the evaluation matrix is relevant data of the corresponding evaluation indicator. Further, the first real-time monitoring data set is input into the terminal of the evaluation and monitoring module. The terminal of the evaluation and monitoring module is a peripheral device connected to the wearable device. In the evaluation and monitoring module The terminal identifies the first real-time monitoring data set according to each evaluation indicator included in the multiple evaluation indicators, thereby outputting an evaluation matrix based on the multiple evaluation indicators. The output evaluation matrices are all updated evaluation matrices that meet the multiple evaluation indicators. Furthermore, the vectors included in the updated evaluation matrix are fused with the vectors included in the historical evaluation matrix. The computer is used to automatically analyze and synthesize the vectors included in the updated evaluation matrix obtained in time series with the vectors included in the historical evaluation matrix under certain criteria to complete the required decision-making and evaluation tasks, thereby outputting the fused evaluation matrix. The historical evaluation matrix and the fused evaluation matrix are used as the basic data for forming the matrix, and the historical evaluation matrix is compared and matched with the fused evaluation matrix. The matrix is formed according to the indicators that have changed in the comparison and matching results as vectors. Finally, the state change matrix is output, and the state change matrix is a state change matrix based on multiple evaluation indicators, which lays a solid foundation for the subsequent monitoring and early warning of wearable devices during information interaction.
[0031] Furthermore, step S300 of the present application also includes:
[0032] Step S350: Obtaining basic attribute information of the first user;
[0033] Step S360: extracting user features based on the basic attribute information of the first user and outputting a user feature set;
[0034] Step S370: Connecting to a big data management platform, searching for similar user feature data based on the user feature set, and building a first user database;
[0035] Step S380: uploading the first user database to the terminal of the evaluation and monitoring module, performing state transition evaluation on the state change matrix based on the first user database, and outputting a plurality of state evaluation results.
[0036] Specifically, in order to evaluate the state when the above-mentioned state change matrix is output, it is necessary to first obtain the basic attribute information of the first skin type. The basic attribute information of the first user refers to the division of users from the basic information of the first user, such as gender information, age information, skin information, allergen information, tolerance information, etc. Further, feature extraction of users is performed based on the basic attribute information of the first user, which means finding users with relatively high similarity with the current user's features in the basic attribute information of the first user, and using them as reference information for subsequent processing, thereby outputting a user feature set. The output user feature set contains the gender information, age information, skin information, allergen information, tolerance information, etc. corresponding to the division of the current user. Further, the system is communicated with the big data management platform, and the user is extracted through the big data management platform. The feature set is similarly matched with the user features contained in the big data, and the similarity matching degree between the user features contained in the big data management platform and the user feature set is obtained. The user feature data with a similarity matching degree between the two is greater than or equal to 80% is extracted, and the extracted user feature data is integrated and summarized to build a first user database. Furthermore, the data of the built first user database is synchronously uploaded to the evaluation and monitoring module in the wearable device to improve the evaluation indicators. At the same time, the first user database is used as the evaluation standard, and the vectors contained in the state change matrix are evaluated for the state transfer of the wearable device when the state transfer is performed. All state transfer evaluation results are summarized and recorded as multiple state evaluation results for output, which has a limited role in monitoring and early warning of wearable devices during information interaction.
[0037] Step S400: performing state transition optimization according to the state change matrix, and outputting multiple state optimization results of multiple evaluation indicators;
[0038] Furthermore, if Figure 3 As shown, step S400 of this application also includes:
[0039] Step S410: Acquire multiple preset state matrices of the first user;
[0040] Step S420: Utilizing a state transfer algorithm, perform state transfer optimization on the state change matrix based on the multiple preset state matrices, and output the multiple state optimization results, wherein each state optimization result corresponds to a vector with the best state transfer in an evaluation indicator.
[0041] Specifically, in order to improve the efficiency of using the wearable device, it is necessary to use the state change matrix as the basic data to optimize the state transition of the state change matrix. This means first obtaining multiple preset state matrices of the first user. The multiple preset state matrices of the first user are a target matrix set for the first user. When the state of the first user reaches a certain score, the matrix is used to combine the state indicators with excellent performance. Furthermore, based on the multiple preset state matrices of the first user, the state transition algorithm shown below is used to optimize the state transition of the state change matrix:
[0042] s k+1 =A k s k +B k u k
[0043] Among them, s k =(s1,s k ,…,s k ) T The state optimization result representing the current state, n is the total number of evaluation indicators; s k+1 A represents the state optimization result of the next transition state; k Characterize the state change matrix; B k Characterizes the preset state matrix; u k A function that represents the control variables under historical conditions.
[0044] After multiplying the output state change matrix by the state optimization result in the current state, the data obtained by adding the product of the preset state matrix and the function of the control variable in the historical state is used as the optimization result of the state change matrix for state transfer, and the function of the control variable in the historical state can be some external stimuli, such as the diet control and muscle current control performed by the first user. On this basis, the multiple state optimization results obtained by calculation are output, wherein each state optimization result included in the multiple state optimization results corresponds to a vector with the best state transfer in an evaluation indicator. The vector with the best state transfer in the evaluation indicator refers to the vector with the highest evaluation index in the process of state transfer of the state change matrix, which is extracted and recorded as the optimal vector in the process of state transfer. In the process of state transfer optimization, each change is recorded as a state transfer. Finally, multiple state optimization results of multiple evaluation indicators are output so as to serve as reference data for later monitoring and early warning of the wearable device during information interaction.
[0045] Step S500: Identify the multiple state optimization results, generate first warning information, send the first warning information to the first user through the terminal of the first wearable device, and obtain a first activation instruction;
[0046] Furthermore, if Figure 4 As shown, step S500 of this application also includes:
[0047] Step S510: Obtaining device sensitivity and device stability of the first wearable device;
[0048] Step S520: configuring a multi-level warning interval according to the device sensitivity and the device stability;
[0049] Step S530: Process the warning signal of the first warning information according to the multi-level warning interval and output second warning information.
[0050] Specifically, in order to ensure that the first user can achieve a benign state when using the wearable device, it is necessary to identify multiple state optimization results. This means identifying the indicators that have good state performance among the multiple state optimization results, that is, indicators that promote the physical recovery of the first user, by using the following formula to identify the multiple state optimization results, including:
[0051] y k+1 =f(s k+1 )+u k (i)
[0052] Among them, f(s k+1 ) represents the objective function based on the state optimization result, y k+1Characterizes the target evaluation index based on the state optimization result, u k (i) Characterizes the function of the intensity of the pulse current i under the historical state.
[0053] It refers to the sum of the results calculated by the objective function of the state optimization result and the function under the intensity band of the pulse current i under the historical state. The intensity of the pulse current i under the historical state can be regarded as a diet control or sleep variable. If it is diet control, the variable of the intensity of the pulse current i under the historical state can be the nutritional size of the diet under the historical state. If it is a sleep variable, the variable of the intensity of the pulse current i under the historical state can be the degree of sleep quality under the historical state. On this basis, the pulse current emitted by the wearable device is positioned according to the optimization result to improve the sub-health of the first user, and the first warning information is generated at the same time.
[0054] Furthermore, in order to improve the warning accuracy of the first warning information, it is also necessary to collect the device sensitivity and device stability of the first wearable device. The device sensitivity can refer to the degree of change in the response amount of the first wearable device to the sensor information of the first user, which can be calculated by the ratio of the response amount of the first wearable device to the corresponding sensor data amount. The device stability refers to the ability of the first wearable device to keep its characteristic of measuring the sensor information of the first user constant over time. The warning interval of the first wearable device is divided according to the device sensitivity and device stability of the first wearable device, and a multi-level warning interval configured with it is obtained. The multi-level warning interval can include a first-level warning interval, a second-level warning interval, and a third-level warning interval. When the device sensitivity is less than 60% and the device stability is less than 60%, it is set to In the first-level warning interval, the device sensitivity less than 60% is set as the second-level warning interval, and the device stability less than 60% is set as the third-level warning interval, among which the first-level warning interval has the highest warning level. Furthermore, on the basis of the divided multi-level warning intervals, the warning signal in the first warning information is interval-matched, so that it is recorded as the second warning information for output, and finally the obtained first warning information or the second warning information is sent to the first user through the terminal of the first wearable device for instruction matching, which means obtaining the first activation instruction according to the generated warning information. The first activation instruction is a system instruction for controlling the pulse activation module in the first wearable device, which can make the first user approach a benign state and improve the accuracy of monitoring and warning of the wearable device during the information interaction process in the later stage.
[0055] Step S600: controlling the pulse activation module according to the first activation instruction to generate a first pulse current.
[0056] Specifically, in order to ensure the pulse control of the first user, it is necessary to use the generated first activation instruction as the basic control data to control the pulse activation module contained in the first wearable device, which means that when the system issues the first activation instruction, the pulse activation module in the first wearable device will be activated accordingly, so that the pulse activation module will start to emit pulse current to the first user according to the state optimization result in the early warning information. A short and fluctuating electric shock is used in the pulse activation module, which can be voltage or current. The main characteristics of the pulse emitted are waveform, amplitude, width and repetition frequency, and the pulse is a signal that occurs in a short time within the entire signal cycle relative to the continuous signal emitted by the pulse activation module when the first wearable device is running. Therefore, the pulse current emitted to the first user at this time is recorded as the first pulse current, so as to achieve more accurate monitoring and early warning of the wearable device during information interaction based on the first pulse current.
[0057] To sum up, the monitoring and early warning method based on wearable device information interaction provided by the embodiment of the present application includes at least the following technical effects, which enhances the functional pertinence of monitoring and early warning of wearable devices in information interaction and improves the utilization rate of monitoring data.
[0058] Example 2
[0059] Based on the same inventive concept as the monitoring and early warning method based on wearable device information interaction in the aforementioned embodiment, Figure 5 As shown, this application provides a monitoring and early warning system based on wearable device information interaction, the system includes:
[0060] Device module 1, the device module 1 is used to connect to a first wearable device of a first user, wherein the first wearable device includes a data sensing module, an evaluation and monitoring module, and a pulse activation module, and the data sensing module is a stress patch contact carrier sensor;
[0061] The device performs real-time data sensing on the first user according to the data sensing module and outputs the first real
[0062] A real-time sensing module 2, configured to perform real-time data sensing on the first user according to the data sensing module, and output a first real-time monitoring data set;
[0063] A data fusion module 3 is configured to input the first real-time monitoring data set into the terminal of the evaluation and monitoring module to perform data fusion of various evaluation indicators and generate a state change matrix, wherein the state change matrix includes a state change matrix based on multiple evaluation indicators;
[0064] A state transition optimization module 4 is configured to perform state transition optimization according to the state change matrix and output multiple state optimization results of multiple evaluation indicators;
[0065] an identification module 5, configured to identify the plurality of state optimization results, generate a first warning message, send the first warning message to the first user via a terminal of the first wearable device, and obtain a first activation instruction;
[0066] The control module 6 is configured to control the pulse activation module according to the first activation instruction to generate a first pulse current.
[0067] Furthermore, the system also includes:
[0068] An attribute acquisition module, configured to acquire basic attribute information of the first user;
[0069] a feature extraction module, configured to extract user features based on the basic attribute information of the first user and output a user feature set;
[0070] A data search module, the data search module is used to connect to the big data management platform, search for similar user feature data based on the user feature set, and build a first user database;
[0071] The first evaluation module is used to upload the first user database to the terminal of the evaluation and monitoring module, perform state transition evaluation on the state change matrix based on the first user database, and output multiple state evaluation results.
[0072] Furthermore, the system also includes:
[0073] A second evaluation module is configured to obtain a plurality of evaluation indicators and a historical evaluation matrix corresponding to each of the plurality of evaluation indicators, wherein each vector in the evaluation matrix is relevant data of the corresponding evaluation indicator;
[0074] a data identification module, configured to input the first real-time monitoring data set into a terminal of the evaluation and monitoring module, identify the first real-time monitoring data set, and output an updated evaluation matrix based on the multiple evaluation indicators;
[0075] A fusion module, configured to fuse the updated evaluation matrix with the historical evaluation matrix and output a fused evaluation matrix;
[0076] The first matrix module is used to output the state change matrix using the historical evaluation matrix and the fusion evaluation matrix.
[0077] Furthermore, the system also includes:
[0078] a second matrix module, the second matrix module being configured to obtain a plurality of preset state matrices of the first user;
[0079] A transfer optimization module, wherein the transfer optimization module is used to utilize a state transfer algorithm to perform state transfer optimization on the state change matrix based on the multiple preset state matrices, and output the multiple state optimization results, wherein each state optimization result corresponds to a vector with the best state transfer in an evaluation indicator.
[0080] Furthermore, the system also includes:
[0081] A device data module, configured to obtain device sensitivity and device stability of the first wearable device;
[0082] An interval module, the interval module is used to configure a multi-level warning interval according to the sensitivity and stability of the device;
[0083] A data processing module is used to process the warning signal of the first warning information according to the multi-level warning interval and output second warning information.
[0084] Through the above-mentioned detailed description of the monitoring and early warning method based on wearable device information interaction in this specification, those skilled in the art can clearly understand the monitoring and early warning system based on wearable device information interaction in this embodiment. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.
[0085] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A monitoring and early warning method based on wearable device information interaction, characterized in that: The method comprises: A first wearable device connected to a first user, wherein the first wearable device includes a data sensing module, an evaluation and monitoring module, and a pulse activation module, and the data sensing module is a stress patch contact carrier sensor; Performing real-time data sensing on the first user according to the data sensing module, and outputting a first real-time monitoring data set; Inputting the first real-time monitoring data set into the terminal of the evaluation monitoring module to perform data fusion of various evaluation indicators to generate a state change matrix, wherein the state change matrix includes a state change matrix based on multiple evaluation indicators; Perform state transfer optimization according to the state change matrix, and output multiple state optimization results of multiple evaluation indicators; Identifying the multiple state optimization results, generating a first warning message, sending the first warning message to the first user via a terminal of the first wearable device, and obtaining a first activation instruction; controlling the pulse activation module according to the first activation instruction to generate a first pulse current; wherein, obtaining a plurality of preset state matrices of the first user; A state transition algorithm is used to perform state transition optimization on the state change matrix based on the multiple preset state matrices, and the multiple state optimization results are output, wherein each state optimization result corresponds to a vector with the best state transition in an evaluation indicator. The expression of the state transition algorithm is as follows: in, The state optimization result representing the current state, n is the total number of evaluation indicators; The state optimization result representing the next transition state; Representation state change matrix; Characterizing a preset state matrix; A function that represents the control variables under historical conditions.
2. The method according to claim 1, wherein The method further comprises: Obtaining basic attribute information of the first user; Extracting user features based on the basic attribute information of the first user and outputting a user feature set; Connecting to a big data management platform, searching for similar user feature data based on the user feature set, and building a first user database; The first user database is uploaded to the terminal of the evaluation and monitoring module, and a state transition evaluation is performed on the state change matrix based on the first user database, and a plurality of state evaluation results are output.
3. The method according to claim 1, wherein Inputting the first real-time monitoring data set into the terminal of the evaluation and monitoring module to perform data fusion of various evaluation indicators, the method further includes: Obtaining multiple evaluation indicators and a historical evaluation matrix corresponding to each evaluation indicator in the multiple evaluation indicators, wherein each vector in the evaluation matrix is relevant data of the corresponding evaluation indicator; Inputting the first real-time monitoring data set into the terminal of the evaluation and monitoring module, identifying the first real-time monitoring data set, and outputting an updated evaluation matrix based on the multiple evaluation indicators; Fusing the updated evaluation matrix with the historical evaluation matrix to output a fused evaluation matrix; The state change matrix is output using the historical evaluation matrix and the fusion evaluation matrix.
4. The method according to claim 1, wherein Identifying the multiple state optimization results includes: in, Characterize the objective function based on the state optimization result, Characterizes the target evaluation index based on the state optimization result, Characterizes the function of the intensity of the pulse current i under the historical state.
5. The method according to claim 1, wherein Generating first warning information, the method further includes: Obtaining device sensitivity and device stability of the first wearable device; Configuring multi-level warning intervals according to the device sensitivity and the device stability; The warning signal of the first warning information is processed according to the multi-level warning interval, and second warning information is output.
6. The monitoring and early warning system based on wearable device information interaction is characterized by: The system comprises: A device module, the device module being configured to connect to a first wearable device of a first user, wherein the first wearable device comprises a data sensing module, an evaluation and monitoring module, and a pulse activation module, and the data sensing module is a stress patch contact carrier sensor; a real-time sensing module, configured to perform real-time data sensing on the first user according to the data sensing module and output a first real-time monitoring data set; a data fusion module, configured to input the first real-time monitoring data set into a terminal of the evaluation and monitoring module to perform data fusion of various evaluation indicators and generate a state change matrix, wherein the state change matrix includes a state change matrix based on multiple evaluation indicators; A state transition optimization module, configured to perform state transition optimization according to the state change matrix and output multiple state optimization results of multiple evaluation indicators; an identification module configured to identify the plurality of state optimization results, generate a first warning message, send the first warning message to the first user via a terminal of the first wearable device, and obtain a first activation instruction; a control module, configured to control the pulse activation module according to the first activation instruction to generate a first pulse current; a second matrix module, the second matrix module being configured to obtain a plurality of preset state matrices of the first user; A transfer optimization module is configured to use a state transfer algorithm to perform state transfer optimization on the state change matrix based on the multiple preset state matrices, and output the multiple state optimization results, wherein each state optimization result corresponds to a vector with the best state transfer in an evaluation indicator. The expression of the state transfer algorithm is as follows: in, The state optimization result representing the current state, n is the total number of evaluation indicators; The state optimization result representing the next transition state; Representation state change matrix; Characterizing a preset state matrix; A function that represents the control variables under historical conditions.
Citation Information
Patent Citations
Method and system for determining optimal state number of wind power modeling
CN108805319A
System and method of providing electronic pulse output mode
CN111494792A