Intelligent working track analysis system adopting wearable sensor

Abstract

The invention discloses an intelligent working track analysis system adopting a wearable sensor, and relates to the technical field of wearable sensors, posture, position, motion track and physiological data of a worker are acquired in real time, a data acquisition module transmits and stores the data, a data analysis module intelligently analyzes the transmitted data, and the intelligent working track analysis system is applied to the intelligent working track analysis system. Potential dangerous actions are recognized based on the working tracks and the behavior modes, adjustment reminding is carried out in time through the feedback module, the feedback module not only displays the working tracks and the motion states in real time, but also can intelligently adjust the feedback frequency and the analysis depth according to individual differences of workers, and a personalized visual report is generated, so that the working efficiency is improved, and the user experience is improved. According to the technical scheme, potential safety hazards are reduced, health management of workers is optimized, the influence of environmental interference on data accuracy is effectively solved, and the accuracy and reliability of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wearable sensors, and particularly to an intelligent working trajectory analysis system using wearable sensors. Background Art

[0002] With the development of intelligent wearable devices, wearable sensors have been widely used in fields such as health monitoring, sports tracking, and behavior analysis. In industrial and working environments, an intelligent working trajectory analysis system combines wearable sensors with a data collection and analysis platform to record the behavior, location, and movement trajectories of workers in real time, thereby optimizing work processes, improving efficiency, ensuring safety, and reducing accidents. In addition, such a system can also identify employees' work patterns, physical exertion, and potential occupational disease risks by analyzing the work trajectory data. With the development of Internet of Things (IoT) technology and big data analysis, the application prospects of intelligent working trajectory analysis systems are becoming increasingly broad, especially in industries such as manufacturing, logistics, and construction that require high-precision work monitoring.

[0003] The prior art has the following deficiencies: When using wearable sensors for intelligent working trajectory analysis, interference and error accumulation may occur in sensor data in complex working environments. Due to various factors in the working environment, such as high magnetic fields, extreme temperature changes, strong vibrations, or irregular movements, the sensor measurement data may be inaccurate. In addition, the fatigue effect that may occur after long-term wearing of the sensor (for example, due to poor skin contact or sweat affecting the sensor performance) causes serious deviations in the trajectory data, and even leads to the system misjudging the working trajectory or location. This error affects the accuracy of the intelligent analysis results, thereby reducing work efficiency and increasing potential safety hazards. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent working trajectory analysis system using wearable sensors to solve the deficiencies in the background art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: An intelligent working trajectory analysis system using wearable sensors, including a wearable sensor, a data collection module, a data analysis module, and a feedback module; The wearable sensor is used to collect the movement data of workers in real time. The sensor includes an acceleration sensor, a gyroscope, a GPS positioning sensor, and a heart rate sensor, and can detect the posture, location, movement trajectory, and physiological data of workers. The data collection module is used to receive and store the movement data and physiological data collected by the wearable sensor. The data collection module is wirelessly connected to the sensor. A data analysis module for analyzing and processing the data transmitted by the data collection module, identifying potential dangerous actions of the staff based on the movement trajectories and behavior patterns of the staff, and reminding the staff to make adjustments in real time through a feedback module; A feedback module for displaying the work trajectories and movement states of the staff in real time, intelligently adjusting the feedback frequency and analysis depth in combination with the individual difference degree of the staff, and generating a visualization report of the adjusted results.

[0006] Preferably, in the data analysis module, a high-frequency action repetition risk index is generated by analyzing the repetitive high-frequency actions of the staff. The acquisition method of the high-frequency action repetition risk index is as follows: Collect the movement data x(t), y(t), z(t) of the staff: which respectively represent the acceleration data in the x, y, and z directions, and t is the time. Perform Fourier transforms on the time series signals x(t), y(t), z(t) respectively to convert them from the time domain to the frequency domain. The expressions are: , , , where f is the frequency, T is the sampling interval, and N is the number of sampling points. is the kernel function of the fast Fourier transform; for the complex results X(f), Y(f), Z(f) obtained through the Fourier transform, calculate the spectrum: , , ; where , , respectively represent the spectrum amplitudes in the x, y, and z directions, indicating the movement intensity of the staff at this frequency; Set the frequency range to as the high-frequency band. The calculation formula of the high-frequency action repetition risk index is: ; in the formula, is the high-frequency action repetition risk index, is the lower limit frequency of the high-frequency component, indicating the lowest frequency at which the action starts to repeat, is the upper limit frequency of the high-frequency component, indicating the highest frequency at which the action repeats.

[0007] Preferably, in the data analysis module, a heart rate change abnormality index is generated by analyzing the heart rate change situation of the staff. The acquisition method of the heart rate change abnormality index is as follows: Obtain the real-time heart rate data H(t) of the staff, where t is the time and H(t) is the heart rate value at a certain moment. Set the normal heart rate range: According to the physiological data, set the normal fluctuation range Hmin and Hmax of the heart rate. Set the heart rate data H(t) of the staff, where t is the time and H(t) is the heart rate value at each moment. are n heart rate data points collected within a time period. Calculate the deviation degree PH(t) of the heart rate change, that is, calculate the standard deviation of the heart rate data within the time period. If PH(t) exceeds the normal range, it is considered that there is an abnormality in the heart rate change. The heart rate change abnormality index is generated by calculating the time persistence and amplitude of the heart rate exceeding the normal range. The expression is: ; where is the average value of the heart rate. is the heart rate data at each moment, M is the total number of data points, and XDS is the heart rate change abnormality index.

[0008] Preferably, convert the high-frequency action repetition risk index and the heart rate change abnormality index into a comprehensive feature vector. Use the comprehensive feature vector as the input of the machine learning model. The machine learning model takes predicting the potential dangerous action coefficient value label of the staff for each group of comprehensive feature vectors as the prediction target, and takes minimizing the sum of the prediction errors of the potential dangerous action coefficient value labels of all staff as the training target. Train the machine learning model until the sum of the prediction errors reaches convergence and then stop the model training. Determine the potential dangerous action coefficient value of the staff according to the model output result. Among them, the machine learning model is a polynomial regression model.

[0009] Preferably, compare the obtained potential dangerous action coefficient value of the staff with the reference threshold of the dangerous action coefficient preset according to the historical data. If the potential dangerous action coefficient value of the staff is greater than or equal to the set reference threshold of the dangerous action coefficient, it indicates that the potential dangerous action coefficient value of the staff is high and the staff has potential dangerous actions. At this time, generate a warning signal; if the potential dangerous action coefficient value of the staff is less than the set reference threshold of the dangerous action coefficient, it indicates that the potential dangerous action coefficient value of the staff is low and the staff does not have potential dangerous actions. At this time, do not generate a warning signal.

[0010] Preferably, in the feedback module, it is used to display the work trajectory and motion state of the staff in real time, and intelligently adjust the feedback frequency and analysis depth in combination with the individual difference degree of the staff. Specifically: Take the work trajectory and motion state of the staff and the individual difference degree of the staff as the input items of fuzzy logic, and divide them into different fuzzy sets respectively. Take the feedback frequency and analysis depth as the output items of fuzzy logic, and divide them into different fuzzy sets respectively. Formulate fuzzy rules to describe the influence of the working trajectory and motion state of the staff and the degree of individual differences of the staff on the feedback frequency and analysis depth; Perform fuzzy reasoning according to the fuzzy rules to determine the adjustment strategy of the feedback frequency and analysis depth.

[0011] In the above technical solution, the technical effects and advantages provided by the present invention are as follows: 1. The intelligent working trajectory analysis system of the present invention using wearable sensors solves the problems of sensor data interference and error accumulation caused by complex working environments in the prior art. By collecting the motion data and physiological data of the staff in real time, including acceleration, gyroscope, GPS positioning, and heart rate, the system can accurately identify the posture, position, motion trajectory, and physiological state of the staff. The data analysis module analyzes high-frequency actions based on Fourier transform to generate a high-frequency action repetition risk index; at the same time, an abnormal heart rate change index is also generated by calculating the deviation degree of heart rate change. These data can effectively evaluate potential dangerous actions and timely remind the staff, thereby reducing work injuries and health risks and improving work efficiency.

[0012] 2. The present invention combines the high-frequency action repetition risk index and the abnormal heart rate change index through a machine learning model to predict the potential dangerous action coefficient value of the staff and issue a warning based on this coefficient value. The feedback module intelligently adjusts the feedback frequency and analysis depth according to the individual differences of the staff to ensure personalized health management and safety guarantee. The fuzzy logic system plays an important role in this process. By fuzzy reasoning to adjust the feedback strategy, the system can respond more flexibly and accurately to the needs of different staff. This intelligent and personalized work safety and health monitoring system effectively improves the safety of the working environment, reduces potential risks, and enhances work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0014] Figure 1 It is a system module diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0016] For the embodiments, please refer to Figure 1 As shown, the intelligent work trajectory analysis system using wearable sensors in this embodiment includes a wearable sensor, a data acquisition module, a data analysis module, and a feedback module; The wearable sensor is used to collect the motion data of the staff in real time. The sensor includes an acceleration sensor, a gyroscope, a GPS positioning sensor, and a heart rate sensor, and can detect the posture, position, motion trajectory, and physiological data of the staff; The data acquisition module is used to receive and store the motion data and physiological data collected by the wearable sensor. The data acquisition module is wirelessly connected to the sensor; The data analysis module is used to analyze and process the data transmitted by the data acquisition module. Based on the motion trajectory and behavior pattern of the staff, it identifies potential dangerous actions of the staff and reminds the staff to make adjustments in real time through the feedback module; The feedback module is used to display the work trajectory and motion state of the staff in real time, and intelligently adjust the feedback frequency and analysis depth in combination with the individual difference degree of the staff, and generate a visual report of the adjusted result.

[0017] The wearable sensor is a device for collecting the motion data of the staff in real time. It combines multiple sensor technologies and can provide comprehensive monitoring of work behavior, position, and physiological state to ensure accurate tracking and analysis of the motion, health, and work state of the staff.

[0018] The acceleration sensor is used to detect the motion speed and direction of the staff and can record the acceleration changes in three-dimensional space in real time. By analyzing the acceleration data, the type of action, motion intensity, and body position changes of the staff can be identified. For example, it can detect whether the staff is in a stationary state, walking, running, or other dynamic activities. The acceleration sensor can help the system identify the work rhythm and posture changes of the staff, and then evaluate their work efficiency, whether the posture meets the standards, or whether there are abnormal actions caused by work fatigue.

[0019] The gyroscope sensor is used to detect the angular changes and rotational movements of the staff. By measuring the angular velocity of an object in three axes, it can provide more accurate attitude and orientation data. For example, rotational and turning movements of the staff's head, arms, hands, etc. will be captured. The gyroscope is mainly used to analyze the working postures and operation techniques of the staff, and to judge whether there are bad postures (such as excessive bending, wrong angles) or non-standard working movements. In addition, the gyroscope can assist in determining the relative direction of the staff in space and help draw their precise working trajectories.

[0020] The GPS sensor is used to accurately locate the position of the staff and provide high-precision geographical coordinate data. Through real-time positioning, it can accurately track the movement trajectory of the staff in the workplace and monitor their activity range. In a complex working environment, GPS positioning can help monitor whether the staff is within the predetermined area, whether they have deviated from the working area, or whether they have entered a dangerous area. This is of great significance for ensuring work safety and improving work efficiency. For example, on a construction site, the system can judge whether the staff has entered a dangerous high-altitude operation area through GPS data.

[0021] The heart rate sensor is used to monitor the physiological state of the staff in real time, especially the changes in heart rate. By measuring the heart rate of the staff, it can reflect physiological information such as their physical exertion, stress level, and fatigue status. The heart rate sensor can provide feedback on the physiological health of the staff. For example, if the heart rate of the staff is too high, it may be due to physical exhaustion caused by overwork or high-intensity work. The system can issue a timely reminder and suggest that the staff take appropriate rest or adjust their work rhythm. This plays an important role in preventing occupational diseases and improving work safety.

[0022] By combining the acceleration sensor, gyroscope, GPS positioning, and heart rate sensor, the wearable sensor can comprehensively monitor the movement state, working trajectory, working posture, and physiological condition of the staff, providing data support for the intelligent working trajectory analysis system. The data complementarity and fusion between the sensors enable the system to accurately evaluate the work performance and health status of the staff and make intelligent feedback based on real-time data. For example, the system can judge whether the staff is too fatigued based on their heart rate and movement state, and then suggest rest or adjustment of the work intensity. Through this multi-sensor fusion method, the wearable sensor can not only improve work efficiency, but also monitor the health and safety of the staff in real time, reduce the risk of work-related injuries, optimize the working environment, and improve work quality.

[0023] The data acquisition module is one of the core components of the intelligent work trajectory analysis system, responsible for receiving, storing, and processing various data from wearable sensors. The main function of this module is to ensure the accurate transmission and reliable storage of sensor data, providing a basis for subsequent data analysis and processing.

[0024] The data acquisition module receives the motion data collected by wearable sensors through wireless communication protocols (such as Bluetooth, Wi-Fi, Zigbee, etc.), including the output data of acceleration sensors, gyroscopes, and GPS positioning modules. This data includes information such as the motion trajectory, position, speed, posture, and direction of the staff, helping the system to track the dynamic behavior of the staff in real-time. In addition to motion data, the data acquisition module also receives physiological data from devices such as heart rate sensors, such as physiological indicators such as the heart rate frequency, body temperature, and physical exertion of the staff. This data can provide important feedback on the health status of the staff. The data acquisition module and the wearable sensors perform data transmission through a wireless connection (such as Bluetooth, Wi-Fi, or other wireless protocols). This wireless communication method not only makes the device more convenient and flexible but also eliminates the spatial limitations in traditional wired connections, enabling accurate data collection even when the staff is moving.

[0025] The data acquisition module can store the motion data and physiological data received from the sensors in real-time. The data is generally stored in the internal memory or external storage device of the module and is identified according to information such as the timestamp and staff ID to ensure the orderliness and integrity of the data. To save storage space and improve data transmission efficiency, the data acquisition module usually compresses and optimizes the collected data. This is especially important for scenarios of long-term monitoring and large amounts of data accumulation, ensuring the efficient storage and processing of data.

[0026] The acquisition module can perform preliminary noise filtering and signal processing on the sensor data to remove inaccuracies caused by environmental interference, sensor errors, or data loss. For example, the error of the GPS signal can be corrected through a calibration algorithm, and the high-frequency noise of the sensor can be removed through a filter. The data acquisition module also needs to ensure the synchronization of data from different sensors. Through methods such as timestamps, it ensures that the motion data, positioning data, and physiological data can be accurately matched and form a complete record of the work trajectory and physiological changes.

[0027] Once the data is collected and stored, the data acquisition module will transmit this data to the data analysis module for further processing and analysis. Usually, the data transmission will be completed through wireless networks (such as Bluetooth, Wi-Fi) or mobile networks (such as 4G / 5G). Ensuring real-time performance and efficiency is the focus of the design of the data acquisition module. In some application scenarios, the data acquisition module may also upload the data to the cloud platform for centralized storage and big data analysis, providing more powerful data processing capabilities and analysis functions. Cloud storage can also achieve cross-device data synchronization and management, facilitating remote monitoring and analysis.

[0028] To ensure the security and privacy protection of the staff's data, the data acquisition module will use encryption technologies (such as AES encryption, SSL / TLS encryption, etc.) to encrypt the data during transmission and storage. Prevent the data from being intercepted or tampered with during transmission and ensure the security of the information. To prevent data leakage and illegal access, the data acquisition module may incorporate an identity authentication and authorization management mechanism, allowing only authenticated users and devices to access the data.

[0029] The data acquisition module generally supports the access of multiple wearable sensors and different types of devices. For example, it not only supports the sensors on the staff, but can also integrate environmental sensors (such as temperature, humidity, gas concentration sensors) to provide more comprehensive monitoring of the working environment. With the increase in the types and functions of sensors, the data acquisition module has a certain degree of scalability and can add more sensor interfaces or upgrade the communication protocol according to requirements to adapt to the expansion needs of the system.

[0030] As a key component of the intelligent work trajectory analysis system, the data acquisition module plays the role of receiving, storing, processing, and transmitting the data from wearable sensors in real time. Through wireless connection, the module can efficiently and stably collect motion and physiological data from various sensors and ensure the accuracy and security of the data. After being preprocessed, these data are transmitted to the analysis module to form a precise monitoring and health assessment of the staff, providing strong support for subsequent data analysis, feedback, and decision-making.

[0031] The data analysis module is the core part of the intelligent work trajectory analysis system. Its main function is to analyze and process the motion data and physiological data from the data acquisition module, identify whether there are potential dangerous actions or health hazards of the staff, and provide adjustment suggestions or safety warnings to the staff in a timely manner through the feedback module. This module can integrate data from multiple aspects and evaluate the work behavior through advanced algorithms, thereby optimizing work efficiency and ensuring the safety of the staff.

[0032] The data analysis module receives and processes the motion data and physiological data transmitted from the data acquisition module. The motion data includes information such as acceleration, speed, motion trajectory, direction, and position, while the physiological data includes physiological indicators such as heart rate, body temperature, and physical exertion. Through the comprehensive analysis of these two types of data, the data analysis module can comprehensively evaluate the behavior patterns and physiological states of the staff.

[0033] The identification of dangerous actions is one of the key tasks of the data analysis module and generally includes the following aspects: Motion data analysis: First, the module analyzes the motion trajectory of the staff to identify abnormal behavior patterns during their movement. Through the acceleration sensor and gyroscope data, it can be detected whether the actions of the staff meet the normal work requirements. For example, whether there are violent rotations, sudden accelerations, or overloaded joint movements caused by incorrect postures, etc., which may indicate potential dangers.

[0034] Physiological data analysis: The module also analyzes in combination with the physiological data of the staff, especially the changes in indicators such as heart rate and body temperature. For example, when the heart rate of the staff is too high or the physical exertion is too large, it may indicate that they are in a state of excessive fatigue or are performing strenuous physical labor, and this situation will lead to a higher risk of injury. Through the abnormal fluctuations in heart rate data, the system can infer whether there are health risks for the staff caused by overwork or improper operations.

[0035] Analysis of the working behavior from the angle: In addition to the conventional motion speed and acceleration, the module also comprehensively analyzes the motion direction and posture angle of the staff. For example, it detects whether the staff has excessive bending, repetitive high-frequency actions, or long-term single postures, which may increase certain types of injury risks (such as muscle strains, joint injuries, etc.).

[0036] After analyzing the repetitive high-frequency actions of the staff, a high-frequency action repetition risk index is generated. The method for obtaining the high-frequency action repetition risk index is as follows: First, it is necessary to collect the motion data of the staff. Usually, an acceleration sensor (in the x, y, and z directions) is used to obtain the acceleration signal. The data is usually time-series data collected over time, representing the acceleration or motion state of the staff. x(t), y(t), z(t): represent the acceleration data in the x, y, and z directions respectively, and t is the time, usually in seconds. A filter (such as a low-pass filter) is used to remove the high-frequency noise in the signal. The acceleration data is normalized to ensure that the signals are processed on the same magnitude.

[0037] Perform Fourier transforms on the time series signals x(t), y(t), and z(t) respectively, converting them from the time domain to the frequency domain. The main purpose of the Fourier transform is to identify the intensities of different frequency components in the signals.

[0038] Apply the Fast Fourier Transform (FFT) to the signals x(t), y(t), and z(t) respectively: , , , where f is the frequency, T is the sampling interval, and N is the number of sampling points. is the kernel function of the Fast Fourier Transform; for the complex results X(f), Y(f), and Z(f) obtained through the Fourier transform, calculate the spectrum (amplitude): , , ; where , , represent the spectral amplitudes in the x, y, and z directions respectively, indicating the movement intensity of the staff at that frequency; Set the frequency range to as the high-frequency band (e.g., 2 Hz to 10 Hz). The stronger the high-frequency components within this range, the more frequent the repetitive actions are, and the higher the risk index. The calculation formula for the high-frequency action repetition risk index is: ; In the formula, is the high-frequency action repetition risk index, is the lower limit frequency of the high-frequency components, indicating the lowest frequency at which the actions start to repeat (e.g., 2 Hz), is the upper limit frequency of the high-frequency components, indicating the highest frequency at which the actions repeat (e.g., 10 Hz). The larger the risk index value, the more high-frequency repetitive actions the staff performs, and the higher the potential occupational injury or risk caused by poor postures.

[0039] Deep data on physiological states: By deeply analyzing uncommon changes in physiological data, such as extreme heart rate fluctuations, slow physical recovery, and the accumulation of long-term fatigue, the data analysis module can further evaluate whether the staff is on the verge of health risks. These abnormal changes in physiological data are often precursors to potential dangers during the work process.

[0040] After analyzing the heart rate changes of the staff, generate an abnormal heart rate change index. The method for obtaining the abnormal heart rate change index is as follows: Obtain the real-time heart rate data H(t) of the staff, where t is the time and H(t) is the heart rate value at a certain moment. Set the normal heart rate range: According to physiological data or health standards, set the normal fluctuation range Hmin and Hmax of the heart rate. For example, the normal heart rate range is 60 to 100 bpm.

[0041] Set the heart rate data H(t) of the staff, where t is time and H(t) is the heart rate value at each moment. are n heart rate data points collected within a time period, and calculate the deviation degree PH(t) of the heart rate change, that is, calculate the standard deviation of the heart rate data within the time period. If PH(t) exceeds the normal range, it is considered that there is an abnormality in the heart rate change. The heart rate change abnormality index is generated by calculating the time persistence and amplitude of the heart rate exceeding the normal range. The expression is: ; where is the average value of the heart rate. is the heart rate data at each moment, M is the total number of data points, and XDS is the heart rate change abnormality index.

[0042] Convert the high-frequency action repetition risk index and the heart rate change abnormality index into a comprehensive feature vector, and use the comprehensive feature vector as the input of the machine learning model. The machine learning model takes predicting the potential dangerous action coefficient value label of the staff for each group of comprehensive feature vectors as the prediction target, and takes minimizing the sum of the prediction errors of the potential dangerous action coefficient value labels of all staff as the training target. Train the machine learning model until the sum of the prediction errors reaches convergence and then stop the model training. Determine the potential dangerous action coefficient value of the staff according to the model output result. Among them, the machine learning model is a polynomial regression model.

[0043] The method for obtaining the potential dangerous action coefficient value of the staff is: obtain the corresponding function expression from the comprehensive feature vector training data of the trained machine learning model: ; In the formula, is the output function of the model, XDS is the heart rate change abnormality index. is the high-frequency action repetition risk index. is the potential dangerous action coefficient value of the staff.

[0044] Compare the obtained potential dangerous action coefficient value of the staff with the reference threshold of the dangerous action coefficient preset according to historical data. If the potential dangerous action coefficient value of the staff is greater than or equal to the set reference threshold of the dangerous action coefficient, it means that the potential dangerous action coefficient value of the staff is high and the staff has potential dangerous actions. At this time, generate a warning signal; if the potential dangerous action coefficient value of the staff is less than the set reference threshold of the dangerous action coefficient, it means that the potential dangerous action coefficient value of the staff is low and the staff has no potential dangerous actions. At this time, do not generate a warning signal.

[0045] Once the data analysis module identifies potential dangerous actions or health problems, the system sends a real-time reminder to the staff through the feedback module. The feedback methods can be: Visual feedback: Through the screen display of the wearable device or the display screen of other devices, warning information is provided to the staff to prompt them to pay attention to their physical condition or adjust their working postures.

[0046] Sound feedback: When a dangerous action occurs, the system can remind the staff through sounds such as voice or beeping to avoid further injuries.

[0047] Vibration feedback: The wearable device reminds the staff through vibration, especially in emergency situations where immediate posture or movement correction is required. Timely feedback can help the staff make adjustments in a shorter time.

[0048] The core function of the feedback module is to monitor and analyze the working trajectories, motion states, and physiological health data of the staff in real time, and dynamically adjust the feedback frequency and analysis depth according to the individual differences of the staff. The design of this module not only takes into account the work performance of the staff, but also combines the physical conditions and work habits of each staff member, and makes intelligent decisions through a fuzzy logic system, so as to provide more accurate and personalized feedback to the staff.

[0049] Input items: The working trajectories and motion states of the staff; Working trajectories: The working trajectory data comes from the GPS module and motion sensors of the wearable sensor, providing the path, activity area, and position changes that the staff passes through during work. By analyzing these data, the system can identify the working scope, working hours, and task types of the staff.

[0050] Motion states: The motion state data includes the acceleration, posture, motion frequency, and motion intensity of the staff, etc. These data can help the system judge the activity level, work intensity of the staff, and whether there are problems such as overwork or improper postures.

[0051] Input items: The degree of individual differences of the staff; Physical differences: The physical strength, health status, and work adaptability of each staff member are different, which may affect their work performance and health status. For example, some staff members may be able to bear higher-intensity work due to better physical strength, while others may feel fatigued under the same work intensity. The feedback module will make dynamic adjustments according to the individual physical differences to ensure the health and safety of each staff member.

[0052] Differences in work habits: Different staff members have different work habits in their work. For example, some people like to work continuously with high intensity, while others may prefer to take frequent breaks. According to these work habits, the system will judge the appropriate feedback strategies and frequencies.

[0053] Physiological state: Individual differences also include physiological states, such as differences in data like heart rate and body temperature. These factors can affect the workload and health risks of the staff.

[0054] The feedback module takes the work trajectory, motion state, and individual differences of the staff as input items for the fuzzy logic system, and intelligently adjusts the feedback frequency and analysis depth based on these input items. These input items will be fuzzified through fuzzy rules to generate an adaptive feedback output.

[0055] Fuzzification of input items: The work trajectory and motion state can be divided into multiple fuzzy categories according to different criteria such as work intensity and duration. For example, "away from the work area" or "frequent movement" of the work trajectory can be classified as "high intensity" or "low intensity"; while "excessive fatigue" or "continuous low-intensity exercise" of the motion state can be classified as "fatigue" or "healthy".

[0056] Fuzzification of individual differences: The individual differences of the staff (such as physical strength, health status, etc.) can also be fuzzily classified into three categories: "high endurance", "medium endurance", and "low endurance" according to specific thresholds. Changes in physiological data such as heart rate and body temperature can be classified as "normal", "high", or "abnormal", etc.

[0057] Output items: Feedback frequency and analysis depth; Based on the results of fuzzy logic processing, the feedback module will calculate the optimal output of the feedback frequency and analysis depth.

[0058] Feedback frequency: Based on the work intensity, motion state, and physical differences of the staff, the system determines the feedback frequency. For example, for staff with weaker physical strength or engaged in high-intensity work, the system will provide feedback more frequently; while for staff with good work performance and in a relatively relaxed state, the feedback frequency can be appropriately reduced.

[0059] Analysis depth: The analysis depth refers to the detail level of the feedback information. For staff with a higher degree of fatigue or a poorer health state, the system will provide a more in-depth analysis, detailedly evaluating data such as their work postures and heart rate fluctuations; while for staff with better health and normal work performance, the feedback can be kept relatively concise, highlighting the basic health status and work efficiency.

[0060] Generation and display of feedback information; According to the adjusted feedback frequency and analysis depth, the feedback module will generate personalized feedback reports for each staff member. These reports can be presented in forms such as text, charts, or voice to ensure that the staff can obtain timely reminders and suggestions from the system.

[0061] Real-time display: The feedback module will display the work trajectory, motion state, and health monitoring data of the staff on their devices in real time. If the work trajectory of the staff deviates from the predetermined area or there are improper postures, the system will immediately give feedback and reminders.

[0062] Visual report: The system will also generate a visual report based on the analysis results, showing the work performance, health status, and improvement suggestions of the staff. The report may include information such as charts, health indicators, and recommended rest times to help the staff make adjustments according to their own situations.

[0063] Dynamic adjustment: The feedback information will not only be adjusted according to the real-time status of the staff, but also through long-term tracking data analysis, formulate personalized work plans and health management suggestions for the staff.

[0064] In this embodiment, by combining wearable sensors, a data acquisition module, a data analysis module, and a feedback module, it is used to monitor and analyze the motion state and health status of the staff in real time. The wearable sensors include an acceleration sensor, a gyroscope, a GPS positioning sensor, and a heart rate sensor, which can collect the posture, position, motion trajectory, and physiological data of the staff. The data acquisition module receives and stores the data collected by the sensors through wireless connection. The data analysis module processes the transmitted data, identifies potential dangerous actions based on the motion trajectory and behavior pattern of the staff, and gives feedback in a timely manner. The feedback module displays the work trajectory and motion state of the staff in real time, and intelligently adjusts the feedback frequency and analysis depth according to the individual differences of the staff, and finally generates a visual report to provide personalized work and health management suggestions for the staff.

[0065] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula that is closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0066] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0067] As described above, the specific implementation manners of the present application are only described, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application.

Claims

1. Intelligent work trajectory analysis system using wearable sensors, characterized by: Including wearable sensors, data acquisition modules, data analysis modules and feedback modules; Wearable sensors are used to collect the worker's motion data in real time. The sensors include acceleration sensors, gyroscopes, GPS positioning sensors, and heart rate sensors, which can detect the worker's posture, position, motion trajectory, and physiological data; A data acquisition module, used to receive and store the motion data and physiological data collected by the wearable sensor, the data acquisition module being wirelessly connected to the sensor; A data analysis module is used to analyze and process the data transmitted by the data acquisition module, identify the potential dangerous actions of the staff based on the movement trajectory and behavior pattern of the staff, and remind the staff to make adjustments in real time through the feedback module; The feedback module is used to display the work trajectory and movement status of the staff in real time, and intelligently adjust the feedback frequency and analysis depth based on the individual differences of the staff, and generate a visual report of the adjusted results.

2. The intelligent work trajectory analysis system using wearable sensors according to claim 1 is characterized in that: In the data analysis module, the high-frequency action repetition risk index is generated by analyzing the repetitive high-frequency actions of the staff. The method for obtaining the high-frequency action repetition risk index is as follows: Collect the motion data x(t), y(t), z(t) of the staff: they represent the acceleration data in the x, y, and z directions respectively, t is the time, and perform Fourier transform on the time series signals x(t), y(t), z(t) respectively, converting them from the time domain to the frequency domain. The expression is: , , , where f is the frequency, T is the sampling interval, and N is the number of sampling points. is the kernel function of the fast Fourier transform; the complex results X(f), Y(f), Z(f) obtained by Fourier transform are used to calculate the spectrum: , , ;in, , , They represent the spectrum amplitudes in the x, y, and z directions, respectively, indicating the intensity of the worker's motion at that frequency; Setting frequency range to It is a high frequency band. The calculation formula of high frequency action repetition risk index is: ; In the formula, It is the high-frequency action repetition risk index. is the lower limit frequency of the high-frequency component, indicating the lowest frequency at which the action begins to repeat. It is the upper limit frequency of the high-frequency component, indicating the highest frequency of action repetition.

3. The intelligent work trajectory analysis system using wearable sensors according to claim 2 is characterized in that: In the data analysis module, the heart rate change of the staff is analyzed to generate the heart rate change abnormality index. The method for obtaining the heart rate change abnormality index is as follows: Get the real-time heart rate data H(t) of the staff, where t is time and H(t) is the heart rate value at a certain moment. Set the normal range of heart rate: according to the physiological data, set the normal fluctuation range of heart rate Hmin and Hmax, set the heart rate data H(t) of the staff, where t is time and H(t) is the heart rate value at each moment. It is the n heart rate data points collected in the time period, and the deviation of the heart rate change PH(t) is calculated, that is, the standard deviation of the heart rate data in the time period is calculated; If PH(t) exceeds the normal range, it is considered that the heart rate change is abnormal. The heart rate change abnormality index is generated by calculating the duration and amplitude of the heart rate exceeding the normal range. The expression is: ;in is the average heart rate, is the heart rate data at each moment, M is the total number of data points, and XDS is the heart rate change abnormality index.

4. The intelligent work trajectory analysis system using wearable sensors according to claim 3 is characterized in that: The high-frequency action repetition hazard index and the heart rate change abnormality index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model predicts the potential dangerous action coefficient value label of the staff with each group of comprehensive feature vectors as the prediction target, and minimizes the sum of prediction errors for the potential dangerous action coefficient value labels of all staff as the training target. The machine learning model is trained until the sum of prediction errors converges and the model training is stopped. The potential dangerous action coefficient value of the staff is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

5. The intelligent work trajectory analysis system using wearable sensors according to claim 4 is characterized in that: The acquired potential dangerous action coefficient value of the staff is compared with the dangerous action coefficient reference threshold value pre-set according to historical data. If the potential dangerous action coefficient value of the staff is greater than or equal to the set dangerous action coefficient reference threshold value, it means that the potential dangerous action coefficient value of the staff is high and the staff has potential dangerous actions, and a warning signal is generated at this time; if the potential dangerous action coefficient value of the staff is less than the set dangerous action coefficient reference threshold value, it means that the potential dangerous action coefficient value of the staff is low and the staff does not have potential dangerous actions, and no warning signal is generated at this time.

6. The intelligent work trajectory analysis system using wearable sensors according to claim 5 is characterized in that: In the feedback module, it is used to display the work trajectory and movement status of the staff in real time, and intelligently adjust the feedback frequency and analysis depth based on the individual differences of the staff. Specifically: The work trajectory and motion state of the staff and the degree of individual differences of the staff are taken as the input items of fuzzy logic and divided into different fuzzy sets respectively; Feedback frequency and analysis depth are taken as output items of fuzzy logic and divided into different fuzzy sets respectively; Formulate fuzzy rules to describe the work trajectory and movement status of staff members and the impact of individual differences of staff members on feedback frequency and analysis depth; Fuzzy reasoning is performed based on fuzzy rules to determine the adjustment strategy for feedback frequency and analysis depth.

Images