Emotion recognition system based on wearable intelligent equipment
The physiological and behavioral parameter information of the wearer is obtained through the smart wearable device, and the recognition and judgment module of the analysis management terminal are used to make emotional judgments, which solves the problem of difficulty in real-time emotional monitoring in the prior art, and realizes accurate judgment and real-time monitoring of emotions, which has important medical application value.
Patent Information
- Application Number
- CN202411818623.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-11
- Publication Date
- 2025-04-18
AI Technical Summary
Existing emotion recognition technologies are difficult to achieve real-time monitoring and accurate judgment of human emotional state, especially in the field of health care, where real-time data support is lacking in the diagnosis and treatment of diseases such as depression.
The wearer's physiological parameter information (such as heart rate, blood pressure, respiratory rate, skin temperature, skin electrical reaction) and behavioral parameter information (such as sleep length, sleep quality) are obtained through smart wearable devices, and the information is transmitted to the analysis management terminal, and the recognition module and judgment module are used to judge emotions category and detect emotional abnormalities.
Real-time and accurate judgment of the wearer's emotions, can promptly handle and monitor accordingly, and assist in the diagnosis and treatment of diseases in the field of health care.
Smart Images
Figure CN119837528A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of emotion recognition, and in particular relates to an emotion recognition system based on a wearable intelligent device. Background Art
[0002] Emotion recognition refers to the process of detecting, analyzing and judging human emotional states (such as basic emotions such as happiness, sadness, anger, fear, surprise, disgust, and complex mixed emotions) with the help of various technologies and methods.
[0003] In healthcare, emotion recognition can help diagnose and treat diseases. For example, patients with depression often remain in a sad and negative mood for a long time. Monitoring patients through emotion recognition can help doctors better understand the patient's emotional changes, thereby facilitating the patient's recovery. Existing emotion recognition is mostly analyzed and recognized through facial expressions or voice, and requires specific recognition software to make judgments, and cannot monitor changes in the patient's condition in real time. Summary of the invention
[0004] The purpose of the present invention is to provide an emotion recognition system based on a wearable intelligent device to solve the problems faced in the above-mentioned background technology.
[0005] The purpose of the present invention can be achieved through the following technical solutions: An emotion recognition system based on a wearable intelligent device, the system comprising: A smart wearable device, wherein the smart wearable device is used to obtain relevant parameter information generated by the wearer; An information transmission module, which transmits the generated relevant parameter information to the analysis management terminal; An analysis and management terminal, the analysis and management terminal comprising an identification module and a judgment module, the identification module judging the emotion category of the wearer according to the acquired relevant parameter information, the judgment module processing and analyzing the acquired relevant parameter information to generate a discrimination value, and judging whether the wearer's emotion is normal according to the size of the discrimination value; A display module is used to display the judgment result of the analysis management terminal.
[0006] Furthermore, the relevant parameter information includes physiological parameter information and behavioral parameter information of the wearer, wherein the physiological parameter information includes heart rate R, blood pressure B, respiratory rate H, skin temperature T and skin electrical response G, and the behavioral parameter information includes sleep time length TL and sleep quality Q.
[0007] Furthermore, the method by which the recognition module determines the emotion category of the wearer is: The wearer's heart rate R, blood pressure B, respiratory rate H, skin temperature T, and skin electrical response G are obtained through the relevant equipment worn; Establishing an emotion library, wherein the emotion library contains multiple emotion categories, and each emotion category has a corresponding value range of heart rate, blood pressure, respiratory rate, skin temperature and skin electrical response; The acquired heart rate, blood pressure, breathing rate, skin temperature and skin electrical response of the wearer are input into the emotion library, and the emotion category with the most matching numerical intervals is determined as the emotion category of the current wearer.
[0008] Furthermore, the method by which the judging module judges whether the wearer is in a normal mood is: Set a monitoring period and obtain the heart rate curve over time within the monitoring period , Blood pressure change curve over time , Respiratory frequency versus time curve , Skin temperature change curve over time And the curve of skin electrical response changing over time ; By formula Get the discriminant value ; The discriminant value obtained Compared with the preset emotion discrimination threshold To compare: when When the wearer is in an abnormal mood, Otherwise, it is judged that the wearer is in a normal mood; in, is the start time of the monitoring cycle, The end time of the monitoring period. , , , , They are the preset wearer's standard heart rate, standard blood pressure, standard respiratory rate, standard skin temperature, and standard skin electrical response curves over time. , , , , They are respectively the preset heart rate, blood pressure, respiratory rate, skin temperature, and skin galvanic response deviation comparison values. Furthermore, the analysis management terminal is also provided with an analysis module, which is used to analyze the wearer's condition according to the obtained discrimination value and behavior parameter information.
[0009] Furthermore, the working method of the analysis module is: When it is judged that the wearer is in an abnormal mood, corresponding treatment and intervention are carried out, and then the discrimination value within n monitoring cycles is obtained, so as to formulate a curve of the variation of the discrimination value with the number of monitoring cycles x. , and obtain the sleep time length in each monitoring cycle and sleep quality ; By formula Get the first status value ; when When the wearer's condition is judged to have improved; in, is the slope value, For the entire monitoring period Maximum value, For the entire monitoring period Minimum value, For the first monitoring cycle, For the last monitoring cycle, is a preset first condition threshold.
[0010] Furthermore, the working method of the analysis module also includes: When it is judged that the wearer is in a normal mood, the discrimination value within n monitoring cycles is obtained. , and by the formula Obtain the sleep status value of each monitoring cycle ; So through the formula Get the second status value ; when When the wearer's condition is stable, in, as well as is the preset coefficient, is a preset second condition threshold.
[0011] Beneficial effects of the present invention: The present invention obtains relevant parameter information generated by the wearer through the intelligent wearable device, and judges whether the wearer's emotions are abnormal in real time and accurately according to the changes in the wearer's heart rate, blood pressure, respiratory rate, skin temperature, and skin electrical response, so as to perform corresponding processing. The wearer can be monitored in real time to facilitate recovery from the disease.
[0012] The present invention can monitor and feedback the wearer's condition changes according to the wearer's normal and abnormal mood conditions based on the obtained discrimination values and sleep status values, so as to better ensure the wearer's recovery from the condition.
[0013] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0015] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION
[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0017] In one embodiment, an emotion recognition system based on a wearable smart device is disclosed, such as Figure 1 As shown, the system includes: Smart wearable devices are used to obtain relevant parameter information generated by the wearer, including physiological parameter information and behavioral parameter information of the wearer, wherein the physiological parameter information includes heart rate R, blood pressure B, respiratory rate H, skin temperature T and skin electrical response G, and the behavioral parameter information includes sleep time TL and sleep quality Q; An information transmission module transmits the generated relevant parameter information to the analysis management terminal; The analysis and management terminal includes an identification module and a judgment module. The identification module determines the emotional category of the wearer according to the acquired relevant parameter information. The judgment module processes and analyzes the acquired relevant parameter information to generate a discrimination value, and determines whether the wearer's emotion is normal according to the size of the discrimination value. Display module, the display module is used to display the judgment results of the analysis management terminal.
[0018] Through the above technical scheme, the present application obtains relevant parameter information generated by the wearer through smart wearable devices such as bracelets, various sensors, etc., including the wearer's physiological parameter information and behavioral parameter information, wherein the physiological parameter information includes heart rate, blood pressure, respiratory rate, skin temperature and skin electrical response, and the behavioral parameter information includes sleep time length and sleep quality, etc., and then transmits it to the analysis and management terminal. The recognition module in the analysis and management terminal can judge the wearer's emotional category based on the acquired relevant parameter information, and display it on the display module. When it is found that the wearer's emotional category is abnormal, a corresponding alarm reminder is made. In this way, the wearer's emotional state can be identified based on the wearer's physiological information, thereby reminding the wearer to make corresponding self-adjustments, facilitate management of their own emotions, and help rehabilitation; at the same time, the judgment module of the analysis and management terminal can process and analyze the acquired relevant parameter information to judge whether the wearer's emotions are normal, and display it on the display module. When it is judged that the emotions are abnormal, corresponding processing can be carried out in time, and the patient's condition can be tracked and monitored in real time, so as to better facilitate the patient's rehabilitation.
[0019] As an embodiment of the present invention, the method for the recognition module to determine the emotion category of the wearer is: The wearer's heart rate R, blood pressure B, respiratory rate H, skin temperature T, and skin electrical response G are obtained through the relevant equipment worn; Establish an emotion library, which contains multiple emotion categories, and each emotion category has a corresponding value range for heart rate, blood pressure, respiratory rate, skin temperature and skin electrical response; The acquired heart rate, blood pressure, breathing rate, skin temperature and skin electrical response of the wearer are input into the emotion library, and the emotion category with the most matching numerical intervals is determined as the emotion category of the current wearer.
[0020] Through the above technical scheme, this embodiment provides a method for the recognition module to determine the emotion category of the wearer. First, according to the historical information of the wearer and the relevant data in the big data, an emotion library is established. The emotion library contains multiple emotion categories, including happiness, sadness, anger, fear and other categories. Each emotion category has a corresponding heart rate, blood pressure, respiratory rate, skin temperature and skin electrical response corresponding numerical range. Then, the wearer's heart rate R, blood pressure B, respiratory rate H, skin temperature T and skin electrical response G are obtained through the relevant equipment worn by the wearer, and then the acquired wearer's heart rate, blood pressure, respiratory rate, skin temperature and skin electrical response are input into the emotion library, and the emotion category with the most matching degree of numerical range is determined as the emotion category of the current wearer. In this way, the wearer's current emotional state can be judged based on the wearer's physiological condition and comprehensive analysis, which can effectively reduce judgment errors and facilitate the wearer to make corresponding emotional management adjustments.
[0021] As an embodiment of the present invention, the method in which the judging module judges whether the wearer is in a normal mood is as follows: Set a monitoring period and obtain the heart rate curve over time within the monitoring period , Blood pressure change curve over time , Respiratory frequency versus time curve , Skin temperature change curve over time And the curve of skin electrical response changing over time ; By formula Get the discriminant value ; The discriminant value obtained Compared with the preset emotion discrimination threshold To compare: when When the wearer is in an abnormal mood, Otherwise, it is judged that the wearer is in a normal mood; in, is the start time of the monitoring cycle, The end time of the monitoring period. , , , , They are the preset wearer's standard heart rate, standard blood pressure, standard respiratory rate, standard skin temperature, and standard skin electrical response curves over time. , , , , They are respectively the preset deviation comparison values of heart rate, blood pressure, respiratory rate, skin temperature and skin electrical response.
[0022] Through the above technical solution, this embodiment provides a method for the judgment module to judge whether the wearer's mood is normal. Due to the influence of the environment and other external factors, people's physiological conditions will change in a short period of time. For example, when watching a happy video, people's physiological parameters will change briefly. At this time, there will be errors in judging whether the wearer's mood is normal. Therefore, this application sets a monitoring period, the duration of which can be artificially set, and obtains the heart rate change curve over time within the monitoring period. , Blood pressure change curve over time , Respiratory frequency versus time curve , Skin temperature change curve over time And the curve of skin electrical response changing over time , and then through the formula through the formula Get the discriminant value , the obtained changes in heart rate, blood pressure, respiratory rate, skin temperature, and skin electrical response are compared with their respective standard changes, and a comprehensive analysis is performed to obtain the discrimination value; it can be seen that the greater the difference between the two, the greater the gap between the wearer's emotional state during the monitoring period and the standard normal emotion, indicating that the emotion during this monitoring period is abnormal, so the obtained discrimination value Compared with the preset emotion discrimination threshold Compare: When If the wearer is in an abnormal mood, the wearer is judged to be in a normal mood. Otherwise, the wearer is judged to be in a normal mood.
[0023] In this way, the wearer's emotions can be accurately judged to be abnormal based on changes in the wearer's heart rate, blood pressure, respiratory rate, skin temperature, and skin electrical response, so that corresponding treatment can be taken. The patient can be monitored in real time to facilitate his recovery.
[0024] It should be noted that the preset wearer's standard heart rate, standard blood pressure, standard respiratory rate, standard skin temperature, and standard skin electrical response curves over time can all be formulated based on the wearer's historical physiological parameters under normal circumstances, while the preset heart rate, blood pressure, respiratory rate, skin temperature, skin electrical response deviation comparison value and emotion discrimination threshold can be determined based on empirical data, which will not be described in detail here.
[0025] As an embodiment of the present invention, an analysis module is further provided in the analysis management terminal, and the analysis module is used to analyze the medical condition of the wearer according to the obtained discrimination value and behavior parameter information; When it is judged that the wearer is in an abnormal mood, corresponding treatment and intervention are carried out, and then the discrimination value within n monitoring cycles is obtained, so as to formulate a curve of the variation of the discrimination value with the number of monitoring cycles x. , and obtain the sleep time length in each monitoring cycle and sleep quality ; By formula Get the first status value ; when When the wearer's condition is judged to have improved; in, is the slope value, For the entire monitoring period Maximum value, For the entire monitoring period Minimum value, For the first monitoring cycle, For the last monitoring cycle, is a preset first condition threshold; When it is judged that the wearer is in a normal mood, the discrimination value within n monitoring cycles is obtained. , and by the formula Obtain the sleep status value of each monitoring cycle ; So through the formula Get the second status value ; when When the wearer's condition is stable, in, as well as is the preset coefficient, is a preset second condition threshold.
[0026] Through the above technical solution, this embodiment provides a specific method for the analysis module to analyze the wearer's condition. First, when the wearer is judged to be emotionally abnormal, corresponding treatment and intervention are performed, and then the discrimination value within n monitoring cycles is obtained, so as to formulate a curve of the variation of the discrimination value with the number of monitoring cycles x. , and obtain the sleep time length in each monitoring cycle and sleep quality , through the formula Get the first status value , it can be seen from the formula that It indicates the change of the discrimination value in all monitoring cycles. The larger the value, the worse the condition of the wearer. It indicates the difference between the maximum slope and the minimum slope in all monitoring cycles. The larger the difference, the greater the change, which means the wearer's condition is getting better. The same formula Indicates the sleep status in all cycles. The larger the value, the better the condition. The larger the value is, the better the wearer's condition is during the entire monitoring period. Therefore, it is compared with the preset first condition threshold. When the comparison is When the wearer is judged to be in a normal mood, the judgment value within n monitoring cycles is obtained. , and by the formula Obtain the sleep status value of each monitoring cycle ; Thus, through the formula Get the second status value ;formula It indicates the fluctuation of the discrimination value in all monitoring cycles. The smaller the value, the smaller the fluctuation, which means the more stable the patient's condition. Indicates a fluctuation of the sleep status value in all monitoring cycles. The smaller the value, the more stable the wearer's mood is, and the more stable the wearer's condition is. Therefore, it is compared with the preset second condition threshold. When the wearer's condition is stable, the wearer's condition is judged to be relatively stable. In this way, the wearer's condition changes can be monitored and fed back according to the obtained discrimination value and sleep condition value when the wearer is in normal and abnormal mood, so as to better ensure the wearer's recovery. It should be noted that the preset coefficient, the first condition threshold and the second condition threshold can all be determined based on empirical data, which will not be described in detail here.
[0027] The present invention obtains relevant parameter information generated by the wearer through the intelligent wearable device, and accurately judges whether the wearer's mood is abnormal in real time according to the changes in the wearer's heart rate, blood pressure, respiratory rate, skin temperature, and skin electrical response, so as to perform corresponding processing, and can monitor the wearer in real time to facilitate recovery. At the same time, the present invention can monitor and feedback the wearer's condition changes according to the obtained discrimination value and sleep status value when the wearer is in normal mood or abnormal mood, so as to better ensure the wearer's recovery.
[0028] The above contents are merely examples and explanations of the concept of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.
Claims
1. An emotion recognition system based on wearable intelligent devices, characterized in that: The system comprises: A smart wearable device, wherein the smart wearable device is used to obtain relevant parameter information generated by the wearer; An information transmission module, which transmits the generated relevant parameter information to the analysis management terminal; An analysis and management terminal, the analysis and management terminal comprising an identification module and a judgment module, the identification module judging the emotion category of the wearer according to the acquired relevant parameter information, the judgment module processing and analyzing the acquired relevant parameter information to generate a discrimination value, and judging whether the wearer's emotion is normal according to the size of the discrimination value; A display module is used to display the judgment result of the analysis management terminal.
2. The emotion recognition system based on wearable intelligent device according to claim 1, characterized in that: The relevant parameter information includes physiological parameter information and behavioral parameter information of the wearer, wherein the physiological parameter information includes heart rate R, blood pressure B, respiratory rate H, skin temperature T and skin electrical response G, and the behavioral parameter information includes sleep time length TL and sleep quality Q.
3. The emotion recognition system based on wearable intelligent device according to claim 2, characterized in that: The method by which the recognition module determines the emotional category of the wearer is: The wearer's heart rate R, blood pressure B, respiratory rate H, skin temperature T, and skin electrical response G are obtained through the relevant equipment worn; Establishing an emotion library, wherein the emotion library contains multiple emotion categories, and each emotion category has a corresponding value range of heart rate, blood pressure, respiratory rate, skin temperature and skin electrical response; The acquired heart rate, blood pressure, breathing rate, skin temperature and skin electrical response of the wearer are input into the emotion library, and the emotion category with the most matching numerical intervals is determined as the emotion category of the current wearer.
4. The emotion recognition system based on wearable intelligent device according to claim 2, characterized in that: The method by which the judging module judges whether the wearer is in a normal mood is: Set a monitoring period and obtain the heart rate curve over time within the monitoring period , Blood pressure change curve over time , Respiratory frequency versus time curve , Skin temperature change curve over time And the skin electrical response curve over time ; By formula Get the discriminant value ; The discriminant value obtained Compared with the preset emotion discrimination threshold To compare: when When the wearer is in an abnormal mood, Otherwise, it is judged that the wearer is in a normal mood; in, is the start time of the monitoring cycle, The end time of the monitoring period. , , , , They are the preset wearer's standard heart rate, standard blood pressure, standard respiratory rate, standard skin temperature, and standard skin electrical response curves over time. , , , , They are respectively the preset deviation comparison values of heart rate, blood pressure, respiratory rate, skin temperature and skin electrical response.
5. The emotion recognition system based on wearable intelligent device according to claim 4, characterized in that: The analysis management terminal is also provided with an analysis module, which is used to analyze the medical condition of the wearer according to the obtained discrimination value and behavior parameter information.
6. The emotion recognition system based on wearable intelligent device according to claim 5, characterized in that: The working method of the analysis module is: When it is judged that the wearer is in an abnormal mood, corresponding treatment and intervention are carried out, and then the discrimination value within n monitoring cycles is obtained, so as to formulate a curve of the variation of the discrimination value with the number of monitoring cycles x. , and obtain the sleep time length in each monitoring cycle and sleep quality ; By formula Get the first status value ; when When the wearer's condition is judged to have improved; in, is the slope value, For the entire monitoring period Maximum value, For the entire monitoring period Minimum value, For the first monitoring cycle, For the last monitoring cycle, is a preset first condition threshold.
7. The emotion recognition system based on wearable intelligent device according to claim 5, characterized in that: The working method of the analysis module also includes: When it is judged that the wearer is in a normal mood, the discrimination value within n monitoring cycles is obtained. , and by the formula Obtain the sleep status value of each monitoring cycle ; So through the formula Get the second status value ; when When the wearer's condition is stable, in, as well as is the preset coefficient, is a preset second condition threshold.