Artificial intelligence dynamic pressure emotion analysis method and system

Abstract

The invention relates to the technical field of psychology and physiology monitoring and data analysis, in particular to an artificial intelligence dynamic pressure emotion analysis method and system, and the method comprises the steps: collecting the physiological data and limb movement data of a student when the student carries out dangerous homework; based on a preset algorithm, the physiological data and the limb movement data are analyzed, whether the student has negative emotions or not is judged, and the negative emotions include anxiety, tension, fear, anger and cackie; when a negative emotion exists, an early warning signal is sent in a matched mode, a response program is started, and related personnel terminals are notified, and the related personnel terminals comprise a user terminal, a rescue personnel terminal and a student terminal; and generating a health feedback report and sending the health feedback report to a user side, wherein the user side comprises a teacher side, an instructor side and a project group leader side. The method has the effect of efficiently monitoring and analyzing the psychological stress and emotional state of large-scale crowds in real time in a complex and high-risk working environment, especially in educational practice training and emergency situations.

Description

Technical Field

[0001] The present application relates to the technical field of psychophysiological monitoring and data analysis, and in particular to an artificial intelligence dynamic stress emotion analysis method and system. Background Art

[0002] The application of smart wearable technology has penetrated into many areas of daily life, including medical monitoring, sports training, health management, etc., and its important role is self-evident. These technologies can monitor users' physiological indicators in real time, such as heart rate, blood pressure, etc., and play a key role in assessing users' health status and emotional responses. In most one-to-many monitoring environments, smart wearable technology faces similar challenges, although these challenges are not limited to a specific field. For example, in the field of medical monitoring, doctors may need to monitor the vital signs of multiple patients at the same time; in sports training, coaches may need to track the physical status of the entire team. In these cases, although smart wearable technology performs well in data collection, its speed and accuracy are often unsatisfactory when processing large amounts of data, resulting in delayed or inaccurate monitoring results.

[0003] However, in the field of vocational education, these limitations of smart wearable technology are particularly prominent. In professional teaching and practical operations such as rail transit, high-speed rail contact network operation, high-voltage power grid climbing, and high-altitude operations, students and operators face a high-risk working environment, which puts higher requirements on the application of smart wearable technology. First of all, in vocational education scenarios, the data processing speed of smart wearable technology is insufficient when processing a large number of data generated by students at the same time. This limitation in processing power leads to a delay in monitoring results, which is an urgent problem to be solved in vocational education situations where instant feedback is required to ensure student safety.

[0004] Secondly, accuracy is also a shortcoming of existing technologies in vocational education applications. In complex teaching environments, especially in one-to-many monitoring scenarios, it is difficult for algorithms to accurately identify changes in the psychological state of each student, and the presence of data noise further affects the accuracy of the monitoring results. These limitations are particularly prominent in high-risk vocational education environments, such as high-altitude operations on high-speed rail contact lines. In these scenarios, students and operators face great psychological pressure, and real-time and accurate tracking of their mental states is crucial to preventing accidents and ensuring personnel safety. However, existing smart wearable technology cannot yet meet the needs of efficient and accurate data processing in such a one-to-many complex environment. Therefore, improvements are needed. Summary of the invention

[0005] In order to solve the technical problem of lack of efficient and real-time monitoring and analysis of the psychological stress and emotional state of large-scale groups of people in complex and high-risk working environments, especially in educational practice training and emergency situations, the present application provides an artificial intelligence dynamic stress emotion analysis method and system.

[0006] The first object of the invention of this application is achieved through the following technical solutions:

[0007] An artificial intelligence dynamic stress emotion analysis method, comprising the steps of:

[0008] When students are doing dangerous tasks, collect students' physiological data and body movement data;

[0009] Based on a preset algorithm, the physiological data and the body movement data are analyzed to determine whether the student has negative emotions, including anxiety, tension, fear, anger, and depression;

[0010] When there is negative emotion, a warning signal is issued, and a response program is initiated to notify relevant personnel terminals, including user terminals, rescue personnel terminals, and student terminals;

[0011] Generate a health feedback report and send it to the user end, which includes the teacher end, the instructor end, and the project leader end.

[0012] In a preferred embodiment, the step of collecting students' physiological data and body movement data when students are performing dangerous tasks includes the following steps:

[0013] Based on GPS, input the student's specific location into the preset database to match the corresponding dangerous operation area;

[0014] Determine the type of dangerous operation based on the dangerous operation area;

[0015] Input the dangerous operation type into the preset database, match the corresponding preset frequency to collect students' physiological data and body movement data;

[0016] The types of dangerous work include high-altitude work, work involving contact with hazardous substances, mechanical operation, precision operation, and high-intensity physical work;

[0017] The physiological data includes heart rate data, blood pressure data, body temperature data, and skin conductivity data;

[0018] The limb movement data includes movement frequency data, movement amplitude data, and movement speed data.

[0019] In a preferred embodiment, the step of analyzing the physiological data and the body movement data based on a preset algorithm to determine whether the student has negative emotions, wherein the negative emotions include anxiety, tension, fear, anger, and malaise, comprises the following steps:

[0020] Preprocessing the physiological data and the limb motion data based on an adaptive filtering method, wherein the adaptive filtering method is combined with a deep learning technology;

[0021] Extracting features from the preprocessed physiological data and limb motion data based on time series analysis technology;

[0022] The forward propagation process formula based on deep neural network is f(x)=σ(W T ·φ(X)+b), where f(x) is the output feature vector, W is the weight matrix, φ(X) is the input feature vector, b is the bias term, and σ is the activation function, which fuses the extracted features into a multidimensional feature vector;

[0023] Based on a machine learning algorithm, the multidimensional feature vector is optimized to output an optimal combination of features;

[0024] Based on the adaptive weight allocation mechanism and optimal combination, a preset weight is assigned to each element of the multidimensional feature vector, the weighted sum is calculated, and the score is output.

[0025] In a preferred embodiment, the step of extracting features from the pre-processed physiological data and the limb motion data based on time series analysis technology comprises the steps of:

[0026] Extracting heart rate features from the preprocessed heart rate data, wherein the heart rate features include heart rate average, heart rate variability, and heart rate peak;

[0027] Extracting blood pressure features from the preprocessed blood pressure data, the blood pressure features including blood pressure variability, blood pressure fluctuation amplitude, and blood pressure load;

[0028] Extracting body temperature features from the preprocessed body temperature data, wherein the body temperature features include body temperature average, body temperature variability, and body temperature peak;

[0029] Extracting skin conductivity features from the preprocessed skin conductivity data, wherein the skin conductivity features include skin conductivity fluctuation amplitude, skin conductivity variability, and skin conductivity peak value;

[0030] Extracting motion frequency features from the preprocessed motion frequency data, wherein the motion frequency features include motion frequency average value, motion frequency variability, and motion frequency peak value;

[0031] Extracting motion amplitude features from the preprocessed motion amplitude data, wherein the motion amplitude features include motion amplitude variability, motion amplitude fluctuation amplitude, and motion amplitude load;

[0032] The motion speed features are extracted from the pre-processed motion speed data, wherein the motion speed features include motion speed variability, motion speed average, and motion speed peak.

[0033] In a preferred embodiment, the step of analyzing the physiological data and the body movement data based on a preset algorithm to determine whether the student has negative emotions, wherein the negative emotions include anxiety, tension, fear, anger, and malaise, further includes the steps of:

[0034] Input the student information into the preset database and match the corresponding emotional response group;

[0035] The student information includes student number and name;

[0036] Based on the emotional response group, the corresponding preset threshold is matched in the preset database;

[0037] The score is compared with a preset threshold, and when the score is greater than 25% of the preset threshold, there is a negative emotion.

[0038] In a preferred embodiment, when there is a negative emotion, a warning signal is issued, and a response program is started to notify the relevant personnel end, and the relevant personnel end includes the steps of the user end, the rescuer end, and the student end, including the steps of:

[0039] When there is negative emotion, judge the degree of negative emotion;

[0040] The degree of negative emotion includes mild negative emotion, moderate negative emotion, and severe negative emotion;

[0041] Based on preset fuzzy logic rules, the scores are input into a preset fuzzy rule base and mapped to corresponding fuzzy sets of negative emotion levels;

[0042] Based on the preset defuzzification method, the negative sentiment level is output;

[0043] The preset fuzzy logic rules include:

[0044] When the score accounts for 25%-50% of the preset threshold, the score is judged to be low, which is a mild negative emotion;

[0045] When the score accounts for 50%-75% of the preset threshold, the score is judged as medium, which is a moderate negative emotion;

[0046] When the score is greater than 75% of the preset threshold, the score is judged to be high, which is a severe negative emotion.

[0047] In a preferred embodiment, when there is a negative emotion, a warning signal is matched and a response program is started to notify the relevant personnel end, and the relevant personnel end includes the steps of the user end, the rescuer end, and the student end, and also includes the steps of:

[0048] Based on the negative emotion level and GPS, a corresponding warning signal is issued, wherein the warning signal is combined with positioning information;

[0049] The warning signals include yellow warning signals, orange warning signals, and red warning signals;

[0050] When there is mild negative emotion, a yellow warning signal combined with positioning information is sent out and the basic response procedure is initiated;

[0051] The basic response procedure includes sending relaxation exercise instructions to the student terminal;

[0052] When there is moderate negative emotion, the match sends out an orange warning signal combined with positioning information and initiates the general response procedure;

[0053] The general response procedure includes notifying the user end and sending relaxation exercise instructions to the student end;

[0054] When there is severe negative emotion, a red warning signal combined with location information is matched and an emergency response procedure is initiated;

[0055] The emergency response procedure includes notifying a rescuer terminal, notifying a user terminal, and sending emergency instructions to a student terminal.

[0056] In a preferred embodiment, the steps of generating a health feedback report and sending it to a user end, wherein the user end includes a teacher end, an instructor end, and a project leader end, include the following steps:

[0057] The health feedback report includes the negative emotion level and the early warning signal;

[0058] Encrypting the health feedback report based on a preset encryption algorithm;

[0059] Based on the preset secure communication channel, the encrypted health feedback report is sent to the authorized user end.

[0060] The second object of the invention is achieved by the following technical solutions:

[0061] Collection module: collects students' physiological data and body movement data when they are doing dangerous work;

[0062] Judgment module: Based on a preset algorithm, the physiological data and the body movement data are analyzed to determine whether the student has negative emotions, including anxiety, tension, fear, anger, and malaise;

[0063] Matching module: when there is negative emotion, match and send out warning signal, start response program, and notify relevant personnel end, said relevant personnel end includes user end, rescuer end, and student end;

[0064] Sending module: Generates health feedback report and sends it to the user end, which includes the teacher end, instructor end, and project leader end.

[0065] The third objective of the present application is achieved through the following technical solutions:

[0066] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned artificial intelligence dynamic stress emotion analysis method when executing the computer program.

[0067] The fourth objective of the present application is achieved through the following technical solutions:

[0068] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned artificial intelligence dynamic stress emotion analysis method.

[0069] In summary, the present application includes at least one of the following beneficial technical effects:

[0070] By monitoring students' physiological and physical movement data in real time when performing dangerous tasks, the system uses preset algorithm analysis to identify negative emotions. Once negative emotions are detected, the system will issue an early warning and initiate a response program to notify relevant personnel. At the same time, the system generates a health feedback report and sends it to the user end in encryption to ensure information security and privacy. This process can monitor students' emotional changes in real time and respond quickly to prevent psychological problems and safety accidents, allowing users to understand students' psychological status in a timely manner, provide appropriate support, and ensure student well-being and a safe learning environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 This is a flowchart of an implementation of an artificial intelligence dynamic stress emotion analysis method embodiment of the present application;

[0072] Figure 2 This is a flowchart of an implementation of step S10 in an embodiment of an artificial intelligence dynamic stress emotion analysis method of the present application;

[0073] Figure 3This is a flowchart for implementing step S20 in an embodiment of an artificial intelligence dynamic stress emotion analysis method of the present application;

[0074] Figure 4 This is a flowchart for implementing step S202 in an embodiment of an artificial intelligence dynamic stress emotion analysis method of the present application;

[0075] Figure 5 This is another implementation flow chart of step S20 in an embodiment of an artificial intelligence dynamic stress emotion analysis method of the present application;

[0076] Figure 6 This is a flowchart for implementing step S30 in an embodiment of an artificial intelligence dynamic stress emotion analysis method of the present application;

[0077] Figure 7 This is another implementation flow chart of step S30 in an embodiment of an artificial intelligence dynamic stress emotion analysis method of the present application;

[0078] Figure 8 This is a flowchart for implementing step S40 in an embodiment of an artificial intelligence dynamic stress emotion analysis method of the present application;

[0079] Fig. 9 This is a principle block diagram of a computer device of the present application. DETAILED DESCRIPTION

[0080] The following is combined with Figure 1-9 This application is described in further detail.

[0081] In one embodiment, if Figure 1 As shown, the present application discloses an artificial intelligence dynamic stress emotion analysis method, which specifically includes the following steps:

[0082] S10: When students are performing dangerous tasks, collect students’ physiological data and body movement data;

[0083] S20: Analyze the physiological data and the body movement data based on a preset algorithm to determine whether the student has negative emotions, including anxiety, tension, fear, anger, and malaise;

[0084] S30: When there is a negative emotion, a warning signal is issued, and a response program is started to notify the relevant personnel end, which includes the user end, the rescuer end, and the student end;

[0085] S40: Generate a health feedback report and send it to the user end, which includes the teacher end, the instructor end, and the project leader end.

[0086] In this embodiment, the physiological and physical movement data of students when performing dangerous tasks are monitored in real time, and the preset algorithm analysis is used to identify negative emotions. Once negative emotions are detected, the system will issue an early warning and start the response program to notify relevant personnel. At the same time, the system generates a health feedback report and sends it to the user end in encryption to ensure information security and privacy. This process can monitor students' emotional changes in real time, respond quickly to prevent psychological problems and safety accidents, and enable users to understand students' psychological state in a timely manner, provide appropriate support, and ensure students' well-being and a safe learning environment.

[0087] Figure 2 , step S10, comprising the steps of:

[0088] S101: Based on GPS, input the specific location of the student into the preset database to match the corresponding dangerous operation area;

[0089] S102: Determine the type of dangerous operation based on the dangerous operation area;

[0090] S103: Input the dangerous operation type into the preset database, and match the corresponding preset frequency to collect the student's physiological data and body movement data;

[0091] S104: The types of dangerous work include high-altitude work, work involving contact with hazardous substances, mechanical operation work, precision operation work, and high-intensity physical work;

[0092] S105: The physiological data includes heart rate data, blood pressure data, body temperature data, and skin conductivity data;

[0093] S106: The limb movement data includes movement frequency data, movement amplitude data, and movement speed data.

[0094] In this embodiment, the student's position is located by GPS and matched with the dangerous operation area database to identify the potential dangerous environment. The system sets the collection frequency according to the operation type and monitors the physiological and body movement data in real time. By monitoring the status of students in risky operations such as high-altitude operations and contact with hazardous substances, the system can timely warn of abnormalities, prevent accidents, ensure student safety, and improve the efficiency of dangerous operation safety management.

[0095] Figure 3 , step S20, comprising the steps of:

[0096] S201: Preprocessing the physiological data and the limb motion data based on an adaptive filtering method, wherein the adaptive filtering method is combined with a deep learning technology;

[0097] S202: extracting features from the pre-processed physiological data and the limb motion data based on time series analysis technology;

[0098] S203: Forward propagation process formula based on deep neural network f(x) = σ(W T ·φ(X)+b), where f(x) is the output feature vector, W is the weight matrix, φ(X) is the input feature vector, b is the bias term, and σ is the activation function, which fuses the extracted features into a multidimensional feature vector;

[0099] S204: Optimizing the multidimensional feature vector based on a machine learning algorithm and outputting an optimal combination of features;

[0100] S205: Based on the adaptive weight allocation mechanism and the optimal combination, a preset weight is assigned to each element of the multidimensional feature vector, the weighted sum is calculated, and the score is output.

[0101] In this embodiment, before preprocessing the physiological data and body movement data, the data need to be normalized. S201: The adaptive filtering method is combined with the deep learning technology for data preprocessing. This method can dynamically adjust the parameters of the filter according to the characteristics of the physiological data and body movement data to effectively remove noise and irrelevant information and improve data quality. The application of deep learning technology enables the filter to learn more complex patterns and features from the data, so as to more accurately capture signals related to emotional states. S202: Time series analysis technology is used to extract features from the preprocessed data, which includes time series analysis of data such as heart rate, blood pressure, body temperature, skin conductivity, movement frequency, amplitude and speed to identify the periodicity, trend and abnormal points of the data, which are crucial for understanding emotional states. S203: A deep neural network is used to fuse the extracted features into a multidimensional feature vector. This network can learn the complex relationship between features and combine them into a high-dimensional representation, which helps to improve the accuracy of subsequent emotion recognition. S204: The machine learning algorithm is used to optimize the multidimensional feature vector and output the optimal combination of features. By training different machine learning models, the feature combination that contributes most to emotion prediction can be found, thereby improving the performance of the model. S205: The adaptive weight assignment mechanism assigns a preset weight to each element of the multidimensional feature vector based on the optimal feature combination. This mechanism can dynamically adjust the weights according to the importance of different features to the prediction of emotional state, and output a score by calculating the weighted sum, which reflects the student's emotional state.

[0102] Figure 4 , step S202, comprising the steps of:

[0103] SA1: extracting heart rate features from the preprocessed heart rate data, wherein the heart rate features include heart rate average, heart rate variability, and heart rate peak;

[0104] SA2: extracting blood pressure features from the preprocessed blood pressure data, wherein the blood pressure features include blood pressure variability, blood pressure fluctuation amplitude, and blood pressure load;

[0105] SA3: extracting body temperature features from the preprocessed body temperature data, wherein the body temperature features include body temperature average, body temperature variability, and body temperature peak;

[0106] SA4: extracting skin conductivity features from the preprocessed skin conductivity data, wherein the skin conductivity features include skin conductivity fluctuation amplitude, skin conductivity variability, and skin conductivity peak value;

[0107] SA5: extracting motion frequency features from the preprocessed motion frequency data, wherein the motion frequency features include motion frequency average value, motion frequency variability, and motion frequency peak value;

[0108] SA6: extracting motion amplitude features from the preprocessed motion amplitude data, wherein the motion amplitude features include motion amplitude variability, motion amplitude fluctuation amplitude, and motion amplitude load;

[0109] SA7: Extract motion speed features from the preprocessed motion speed data, wherein the motion speed features include motion speed variability, motion speed average, and motion speed peak.

[0110] In this embodiment, steps SA1-SA7 quantify emotional states by analyzing preprocessed physiological and limb movement data and extracting key features. Characteristics of heart rate, blood pressure, body temperature, skin conductivity, and movement frequency, amplitude, and speed, such as average, variability, peak, etc., can reveal the dynamic changes of emotions. These features are respectively associated with cardiac activity, vascular pressure, metabolism, sweat gland activity, and limb movement, and together constitute a comprehensive assessment of emotional states. After feature extraction, normalization is performed to facilitate subsequent analysis and early warning, effectively improving the monitoring accuracy and response speed of individual emotional states.

[0111] Figure 5 , step S20 further includes the steps of:

[0112] SB1: Input the student information into the preset database and match the corresponding emotional response group;

[0113] SB2: The student information includes student ID and name;

[0114] SB3: Based on the emotional response group, matching the corresponding preset threshold in the preset database;

[0115] SB4: Compare the score with a preset threshold, and when the score is greater than 25% of the preset threshold, there is a negative emotion.

[0116] In this embodiment, potential emotional problems are identified through steps SB1-SB4, combined with student personal information and emotional scores. The system matches the student's basic information with the emotional response group, and extracts the corresponding threshold for score comparison. If the score exceeds 25% of the threshold, it is judged as a negative emotion. This process effectively identifies the emotional state of students, especially the early detection of negative emotions, helps teachers quickly identify students who need attention, and provide timely support. This mechanism improves the response speed to students' emotional problems, helps promote mental health, reduces the negative impact of emotional problems on learning and socializing, and creates a caring and supportive environment.

[0117] Figure 6 , step S30, comprising the steps of:

[0118] SB1: When there is negative emotion, judge the degree of negative emotion;

[0119] SB2: The degree of negative emotion includes mild negative emotion, moderate negative emotion, and severe negative emotion;

[0120] SB3: Based on the preset fuzzy logic rules, the scores are input into the preset fuzzy rule base and mapped to the corresponding fuzzy sets of negative emotion levels;

[0121] SB4: Output the degree of negative emotion based on the preset defuzzification method;

[0122] SB5: The preset fuzzy logic rules include:

[0123] SB6: When the score accounts for 25%-50% of the preset threshold, the score is judged to be low, which is a mild negative emotion;

[0124] SB7: When the score accounts for 50%-75% of the preset threshold, the score is judged as medium, which is moderate negative emotion;

[0125] SB8: When the score is greater than 75% of the preset threshold, the score is judged to be high, which is a severe negative emotion.

[0126] In this embodiment, the system evaluates the degree of negative emotions through fuzzy logic method, which is divided into mild, moderate and severe. First, the system identifies negative emotions and calculates scores, and then applies the preset fuzzy logic rule base to map the scores to the corresponding fuzzy sets of emotional levels. The defuzzification step converts the fuzzy sets into specific emotional level classifications, and divides the scores into three levels: low, medium and high, to achieve accurate judgment of the emotional level. This method effectively solves the problem of emotion quantification, improves the accuracy and practicality of emotion recognition, and enables the system to handle the uncertainty and ambiguity of emotional states more flexibly.

[0127] Figure 7 , step S30 further includes the steps of:

[0128] SD1: Based on the negative emotion level and GPS, a corresponding warning signal is matched and issued, and the warning signal is combined with positioning information;

[0129] SD2: The warning signals include yellow warning signal, orange warning signal and red warning signal;

[0130] SD3: When there is mild negative emotion, a yellow warning signal combined with positioning information is issued and the basic response procedure is initiated;

[0131] SD4: The basic response procedure includes sending relaxation exercise instructions to the student terminal;

[0132] SD5: When there is moderate negative emotion, an orange warning signal combined with positioning information is issued and the general response procedure is initiated;

[0133] SD6: The general response procedure includes notifying the user terminal and sending relaxation exercise instructions to the student terminal;

[0134] SD7: When there is severe negative emotion, a red warning signal combined with location information is issued and an emergency response procedure is initiated;

[0135] SD8: The emergency response procedure includes notifying the rescuer end, notifying the user end, and sending emergency instructions to the student end.

[0136] In this embodiment, in principle, SD1-SD8 of step S30 is a process of triggering warning signals and response programs based on the degree of negative emotions. In step SD1, the system automatically matches and issues warning signals of corresponding colors according to the degree of negative emotions (mild, moderate, severe) previously judged. In step SD2, the warning signals of corresponding colors are yellow warning signals, orange warning signals, and red warning signals. SD3, SD5, and SD7 respectively define the warning signal colors and response programs corresponding to different emotional levels: the yellow warning signal corresponds to mild negative emotions, and the basic response program (SD4) is started, the orange warning signal corresponds to moderate negative emotions, and the general response program (SD6) is started, and the red warning signal corresponds to severe negative emotions, and the emergency response program (SD8) is started. These response programs include but are not limited to sending relaxation exercise instructions to students, notifying users, and contacting rescuers. The effect that can be achieved is that this process can respond to students' emotional states quickly and specifically, ensuring that students get timely help when they encounter emotional distress. By issuing warning signals of different colors, the system can intuitively convey the severity of emotional problems and initiate corresponding response procedures, thereby effectively providing students with necessary support. The basic response procedure helps students to self-regulate when emotional problems first appear, the general response procedure strengthens the user's understanding and intervention of the student's situation, and the emergency response procedure ensures that when students face serious emotional crises, they can quickly obtain professional rescue and user attention. Such a system design helps to improve the school's efficiency in handling emotional crises and protect students' mental health and safety.

[0137] Figure 8 , step S40, comprising the steps of:

[0138] S401: The health feedback report includes the negative emotion level and the early warning signal;

[0139] S402: Encrypting the health feedback report based on a preset encryption algorithm;

[0140] S403: Based on the preset secure communication channel, the encrypted health feedback report is sent to the authorized user end.

[0141] In this embodiment, step S40 ensures the secure processing and transmission of students' emotional health data. In S401, the system generates a health feedback report containing negative emotion levels and early warning signals to provide teachers with an overview of their emotional status. S402 protects the report content through an encryption algorithm to prevent data leakage. S403 sends the encrypted report to authorized users through a secure channel. This process not only protects students' privacy, but also ensures data security, allowing teachers to obtain students' emotional information in a timely manner while protecting their privacy, take appropriate measures, improve service quality and promote students' mental health.

[0142] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0143] In one embodiment, an artificial intelligence dynamic stress emotion analysis method is provided, and the artificial intelligence dynamic stress emotion analysis system corresponds to the artificial intelligence dynamic stress emotion analysis method in the above embodiment. The artificial intelligence dynamic stress emotion analysis method includes:

[0144] Collection module: collects students' physiological data and body movement data when they are doing dangerous work;

[0145] Judgment module: Based on a preset algorithm, the physiological data and the body movement data are analyzed to determine whether the student has negative emotions, including anxiety, tension, fear, anger, and malaise;

[0146] Matching module: when there is negative emotion, match and send out warning signal, start response program, and notify relevant personnel end, said relevant personnel end includes user end, rescuer end, and student end;

[0147] Sending module: Generates health feedback report and sends it to the user end, which includes the teacher end, instructor end, and project leader end.

[0148] Optionally, also include:

[0149] The first matching module: Based on GPS, input the specific location of the student into the preset database and match the corresponding dangerous operation area;

[0150] The first judgment module: judging the type of dangerous operation based on the dangerous operation area;

[0151] The second matching module: input the dangerous operation type into the preset database, match the corresponding preset frequency to collect students' physiological data and body movement data;

[0152] The first module includes: the types of dangerous work include high-altitude work, work with harmful substances, mechanical operation, precision operation, and high-intensity physical work;

[0153] The second module includes: the physiological data includes heart rate data, blood pressure data, body temperature data, and skin conductivity data;

[0154] The third module includes: the limb movement data includes movement frequency data, movement amplitude data, and movement speed data.

[0155] Optionally, also include:

[0156] Adaptive module: pre-processing the physiological data and the limb motion data based on an adaptive filtering method, wherein the adaptive filtering method is combined with deep learning technology;

[0157] Feature extraction module: extracting features from the pre-processed physiological data and the limb movement data based on time series analysis technology;

[0158] Fusion vector module: Based on the forward propagation process formula of deep neural network f(x) = σ(W T ·φ(X)+b), where f(x) is the output feature vector, W is the weight matrix, φ(X) is the input feature vector, b is the bias term, and σ is the activation function, which fuses the extracted features into a multidimensional feature vector;

[0159] Optimal combination module: Based on the machine learning algorithm, the multi-dimensional feature vector is optimized and the optimal combination of features is output;

[0160] Preset weight module: Based on the adaptive weight allocation mechanism and optimal combination, a preset weight is assigned to each element of the multidimensional feature vector, the weighted sum is calculated, and the score is output.

[0161] Optionally, also include:

[0162] The first extraction module extracts heart rate features from the preprocessed heart rate data, wherein the heart rate features include heart rate average, heart rate variability, and heart rate peak;

[0163] The second extraction module extracts blood pressure features from the pre-processed blood pressure data, wherein the blood pressure features include blood pressure variability, blood pressure fluctuation amplitude, and blood pressure load;

[0164] The third extraction module is used to extract body temperature features from the pre-processed body temperature data, wherein the body temperature features include body temperature average value, body temperature variability, and body temperature peak value;

[0165] The fourth extraction module extracts skin conductivity features from the preprocessed skin conductivity data, wherein the skin conductivity features include skin conductivity fluctuation amplitude, skin conductivity variability, and skin conductivity peak value;

[0166] The fifth extraction module: extracts the motion frequency features from the pre-processed motion frequency data, wherein the motion frequency features include the motion frequency average, the motion frequency variability, and the motion frequency peak;

[0167] The sixth extraction module: extracts the motion amplitude characteristics from the pre-processed motion amplitude data, wherein the motion amplitude characteristics include motion amplitude variability, motion amplitude fluctuation amplitude, and motion amplitude load;

[0168] The seventh extraction module: extracts motion speed features from the preprocessed motion speed data, wherein the motion speed features include motion speed variability, motion speed average, and motion speed peak.

[0169] Optionally, also include:

[0170] The third matching module: input the student information of the students into the preset database and match the corresponding emotional response group;

[0171] The fourth module includes: the student information includes student number and name;

[0172] The fourth matching module: based on the emotional response group, matches the corresponding preset threshold in the preset database;

[0173] The first judgment module: compares the score with a preset threshold, and when the score is greater than 25% of the preset threshold, there is a negative emotion.

[0174] Optionally, also include:

[0175] The second judgment module: when there is negative emotion, judge the degree of negative emotion;

[0176] The fifth module includes: the degree of negative emotion includes mild negative emotion, moderate negative emotion, and severe negative emotion;

[0177] Mapping module: Based on the preset fuzzy logic rules, the scores are input into the preset fuzzy rule base and mapped to the corresponding fuzzy sets of negative emotion levels;

[0178] The first output module: outputs the degree of negative emotion based on a preset defuzzification method;

[0179] The sixth module includes: the preset fuzzy logic rules include:

[0180] The third judgment module: when the score accounts for 25%-50% of the preset threshold, the score is judged to be low, which is a mild negative emotion;

[0181] Fourth judgment module: when the score accounts for 50%-75% of the preset threshold, the score is judged to be medium, which is a moderate negative emotion;

[0182] The fifth judgment module: When the score is greater than 75% of the preset threshold, the score is judged to be high, which is a severe negative emotion.

[0183] Optionally, also include:

[0184] A fifth matching module: based on the negative emotion level and GPS, matching and sending a corresponding warning signal, wherein the warning signal is combined with positioning information;

[0185] The seventh module includes: the warning signal includes a yellow warning signal, an orange warning signal, and a red warning signal;

[0186] The sixth matching module: when there is a mild negative emotion, the matching sends out a yellow warning signal combined with the positioning information and starts the basic response program;

[0187] The eighth module includes: the basic response program includes sending relaxation exercise instructions to the student terminal;

[0188] The seventh matching module: when there is moderate negative emotion, the matching sends out an orange warning signal combined with the positioning information and starts the general response procedure;

[0189] The ninth module includes: the general response procedure includes notifying the user terminal and sending relaxation exercise guidance to the student terminal;

[0190] The eighth matching module: when there is severe negative emotion, the matching sends out a red warning signal combined with the positioning information and initiates the emergency response procedure;

[0191] The tenth module includes: the emergency response procedure includes notifying the rescue personnel, notifying the user, and sending emergency instructions to the student.

[0192] Optionally, also include:

[0193] Comprising modules: the health feedback report includes the negative emotion level and the early warning signal;

[0194] Encryption processing module: encrypting the health feedback report based on a preset encryption algorithm;

[0195] The first sending module: based on a preset secure communication channel, sends the encrypted health feedback report to the authorized user end.

[0196] For the specific definition of an artificial intelligence dynamic stress emotion analysis system, please refer to the definition of an artificial intelligence dynamic stress emotion analysis method above, which will not be repeated here. Each module in the above-mentioned artificial intelligence dynamic stress emotion analysis system can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0197] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig. 9As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store health feedback reports. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an artificial intelligence dynamic stress emotion analysis method is implemented.

[0198] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, an artificial intelligence dynamic stress emotion analysis method is implemented.

[0199] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program is executed by a processor to perform an artificial intelligence dynamic stress emotion analysis method.

[0200] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0201] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

Claims

1. An artificial intelligence dynamic stress emotion analysis method, characterized in that: Includes steps: When students are doing dangerous tasks, collect students' physiological data and body movement data; Based on a preset algorithm, the physiological data and the body movement data are analyzed to determine whether the student has negative emotions, including anxiety, tension, fear, anger, and depression; When there is negative emotion, a warning signal is issued, and a response program is initiated to notify relevant personnel terminals, including user terminals, rescue personnel terminals, and student terminals; Generate a health feedback report and send it to the user end, which includes the teacher end, the instructor end, and the project leader end.

2. According to claim 1, an artificial intelligence dynamic stress emotion analysis method is characterized in that: The step of collecting students' physiological data and body movement data when students are performing dangerous tasks includes the following steps: Based on GPS, input the student's specific location into the preset database to match the corresponding dangerous operation area; Determine the type of dangerous operation based on the dangerous operation area; Input the dangerous operation type into the preset database, match the corresponding preset frequency to collect students' physiological data and body movement data; The types of dangerous work include high-altitude work, work involving contact with hazardous substances, mechanical operation, precision operation, and high-intensity physical work; The physiological data includes heart rate data, blood pressure data, body temperature data, and skin conductivity data; The limb movement data includes movement frequency data, movement amplitude data, and movement speed data.

3. The artificial intelligence dynamic stress emotion analysis method according to claim 1 is characterized in that: The step of analyzing the physiological data and the body movement data based on a preset algorithm to determine whether the student has negative emotions, wherein the negative emotions include anxiety, tension, fear, anger, and malaise, comprises the following steps: Preprocessing the physiological data and the limb motion data based on an adaptive filtering method, wherein the adaptive filtering method is combined with a deep learning technology; Extracting features from the preprocessed physiological data and limb motion data based on time series analysis technology; The forward propagation process formula based on deep neural network is f(x)=σ(W T ·φ(X)+b), where f(x) is the output feature vector, W is the weight matrix, φ(X) is the input feature vector, b is the bias term, and σ is the activation function, which fuses the extracted features into a multidimensional feature vector; Based on a machine learning algorithm, the multidimensional feature vector is optimized to output an optimal combination of features; Based on the adaptive weight allocation mechanism and optimal combination, a preset weight is assigned to each element of the multidimensional feature vector, the weighted sum is calculated, and the score is output.

4. The artificial intelligence dynamic stress emotion analysis method according to claim 3 is characterized in that: The step of extracting features from the pre-processed physiological data and the limb motion data based on the time series analysis technology comprises the following steps: Extracting heart rate features from the preprocessed heart rate data, wherein the heart rate features include heart rate average, heart rate variability, and heart rate peak; Extracting blood pressure features from the preprocessed blood pressure data, the blood pressure features including blood pressure variability, blood pressure fluctuation amplitude, and blood pressure load; Extracting body temperature features from the preprocessed body temperature data, wherein the body temperature features include body temperature average, body temperature variability, and body temperature peak; Extracting skin conductivity features from the preprocessed skin conductivity data, wherein the skin conductivity features include skin conductivity fluctuation amplitude, skin conductivity variability, and skin conductivity peak value; Extracting motion frequency features from the preprocessed motion frequency data, wherein the motion frequency features include motion frequency average value, motion frequency variability, and motion frequency peak value; Extracting motion amplitude features from the preprocessed motion amplitude data, wherein the motion amplitude features include motion amplitude variability, motion amplitude fluctuation amplitude, and motion amplitude load; The motion speed features are extracted from the pre-processed motion speed data, wherein the motion speed features include motion speed variability, motion speed average, and motion speed peak.

5. The artificial intelligence dynamic stress emotion analysis method according to claim 1 is characterized in that: The step of analyzing the physiological data and the body movement data based on a preset algorithm to determine whether the student has negative emotions, wherein the negative emotions include anxiety, tension, fear, anger, and malaise, further includes the steps of: Input the student information into the preset database and match the corresponding emotional response group; The student information includes student number and name; Based on the emotional response group, the corresponding preset threshold is matched in the preset database; The score is compared with a preset threshold, and when the score is greater than 25% of the preset threshold, there is a negative emotion.

6. The artificial intelligence dynamic stress emotion analysis method according to claim 1 is characterized in that: When there is a negative emotion, a warning signal is issued, and a response program is started to notify the relevant personnel end, and the relevant personnel end includes the steps of the user end, the rescuer end, and the student end, including the steps of: When there is negative emotion, judge the degree of negative emotion; The degree of negative emotion includes mild negative emotion, moderate negative emotion, and severe negative emotion; Based on preset fuzzy logic rules, the scores are input into a preset fuzzy rule base and mapped to corresponding fuzzy sets of negative emotion levels; Based on the preset defuzzification method, the negative sentiment level is output; The preset fuzzy logic rules include: When the score accounts for 25%-50% of the preset threshold, the score is judged to be low, which is a mild negative emotion; When the score accounts for 50%-75% of the preset threshold, the score is judged as medium, which is a moderate negative emotion; When the score is greater than 75% of the preset threshold, the score is judged to be high, which is a severe negative emotion.

7. The artificial intelligence dynamic stress emotion analysis method according to claim 1 is characterized in that: When there is a negative emotion, a warning signal is issued, and a response program is started to notify the relevant personnel end, and the relevant personnel end includes the steps of the user end, the rescuer end, and the student end, and also includes the steps of: Based on the negative emotion level and GPS, a corresponding warning signal is issued, wherein the warning signal is combined with positioning information; The warning signals include yellow warning signals, orange warning signals, and red warning signals; When there is mild negative emotion, a yellow warning signal combined with positioning information is sent out and the basic response procedure is initiated; The basic response procedure includes sending relaxation exercise instructions to the student terminal; When there is moderate negative emotion, the match sends out an orange warning signal combined with positioning information and initiates the general response procedure; The general response procedure includes notifying the user end and sending relaxation exercise instructions to the student end; When there is severe negative emotion, a red warning signal combined with location information is matched and an emergency response procedure is initiated; The emergency response procedure includes notifying a rescuer terminal, notifying a user terminal, and sending emergency instructions to a student terminal.

8. The artificial intelligence dynamic stress emotion analysis method according to claim 1 is characterized in that: The step of generating a health feedback report and sending it to a user end, wherein the user end includes a teacher end, an instructor end, and a project leader end, includes the steps of: The health feedback report includes the negative emotion level and the early warning signal; Encrypting the health feedback report based on a preset encryption algorithm; Based on the preset secure communication channel, the encrypted health feedback report is sent to the authorized user end.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of an artificial intelligence dynamic stress emotion analysis method as described in any one of claims 1 to 8 when executing the computer program.

10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of an artificial intelligence dynamic stress emotion analysis method as described in any one of claims 1 to 8.

Images