Elevator passenger health monitoring method and home elevator monitoring system and method
Patent Information
- Application Number
- CN202311084219.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-25
- Publication Date
- 2024-11-29
AI Technical Summary
The existing elevator health monitoring system mainly relies on video image data, and cannot monitor the internal physiological status of the elevator rider in real time and accurately. It is not applicable in places with high privacy requirements, and it is large in calculations, high cost, and cannot effectively utilize the elevator rider. Health assessment of human internal physiological indicators.
Using multi-sensor physiological data acquisition module, edge computing and cloud deployment unit, the physiological data of the elevator rider is obtained through the pre-constructed real-time elevator monitoring model, identity attribution recognition model and health status recognition model, and the physiological data of the elevator rider are obtained, and identity attribution and health status assessment are carried out. Conduct real-time threshold comparison and send early warning information to realize health monitoring of elevator riders.
It realizes that the health status of the stair rider is accurately reflected without obtaining image data, and is suitable for places with high privacy requirements, reducing the calculation amount and cost, and improving monitoring accuracy and scope of application.
Smart Images

Figure CN119038341A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to an elevator passenger health monitoring method and a household elevator monitoring system and method, belonging to the technical field of elevator equipment. Background Art
[0002] Coronary heart disease, cerebral thrombosis, hypertension, diabetes, and nervous system and cardiovascular diseases of the elderly are gradually devouring their normal lives. Although the ability to discover and diagnose diseases has been greatly improved, it is impossible for the elderly to go to the hospital for a long time to monitor and diagnose their own physiological health status. Therefore, they hope to be able to monitor their health status conveniently at home.
[0003] Furthermore, with the construction of self-built houses in rural areas and urban villas, my country has become the world's largest new market for home elevators. Installing elevators in self-built buildings and villas has become a requirement for most residents, and it has also become possible to normalize and make health checks a daily routine.
[0004] However, most of the current monitoring systems mainly focus on the design of system hardware circuits or the development of monitoring terminal systems, and rarely involve data display of multiple application systems and real-time monitoring of terminals; and there is no evaluation and decision-making on the physiological state of the human body, no classification of the physiological state of the human body, and they are still stuck in the extraction of physiological indicators and calculation of physiological parameters, so that users cannot perceive their own physical condition.
[0005] The Chinese patent (CN111232788B) discloses a full-factor health and safety monitoring system for elevators, including a phased array visible light and infrared integrated monitoring module, a sound pickup module, an intelligent processing module and an external control module; the phased array visible light and infrared integrated monitoring module is used to realize the identity recognition of the passengers inside the elevator, the detection of fever characteristics and the facial expressions and neck dynamic changes caused by cough symptoms, so as to realize real-time monitoring of the health status of the passengers inside the elevator, thereby effectively controlling the legacy of viruses inside the elevator and the mutual infection between the sick people; the dynamic change characteristics of the face and neck and the sound characteristics of the cough symptoms obtained by the fusion video are used to realize the cough symptom assessment of the passengers inside the elevator based on multi-feature information fusion, and the full-factor health assessment of the personnel is realized in combination with the fever characteristics, so that the assessment accuracy is high and the monitoring reliability is effectively guaranteed.
[0006] The above scheme mainly uses phased visible light, infrared integrated monitoring modules, and sound pickup modules to obtain the facial expressions and sound characteristics of the passengers, and realizes real-time monitoring of the health status of the passengers inside the elevator. Therefore, the above scheme mainly monitors the health status by obtaining the external performance of the passengers, and does not disclose how to use the internal physiological indicators of the passengers to conduct health assessments of the passengers. Internal physiological indicators generally reflect the health status of the human body better than external performance. Therefore, if the health status of the passengers is only monitored through the external performance of the passengers, there will be large errors, which is not conducive to promotion and use.
[0007] Furthermore, the above-mentioned scheme is based on video images for health monitoring, which requires obtaining image data of the elevator passengers. Therefore, the health monitoring scheme based on video images is not suitable for places or scenarios with extremely high requirements for privacy, such as home elevators and villa elevators, or some business places that focus on privacy, or certain scenarios that focus on privacy, etc., which makes the applicable places or scenarios of existing elevator health monitoring methods subject to many restrictions, which is not conducive to promotion and use.
[0008] Furthermore, the health monitoring system based on video images needs to process a large amount of image information, which requires a large amount of calculation, so it cannot perform health monitoring in real time and has high manufacturing costs.
[0009] The information disclosed in this Background Art is only for understanding the background of the inventive concept and therefore it may include information that does not constitute the prior art. Summary of the invention
[0010] In response to the above problem or one of the above problems, an object of the present invention is to provide a method for first acquiring physiological data of one or more elevator passengers; then processing the physiological data of the elevator passengers to obtain the identity information of the elevator passengers; then performing calculations based on the identity information and the physiological data of the elevator passengers to obtain the health status information of the elevator passengers; and then performing threshold comparison on the health status information of the elevator passengers to determine whether it is necessary to send an early warning message, thereby realizing health monitoring of elevator passengers, which is scientific, reasonable, and feasible.
[0011] In response to the above problem or one of the above problems, the second object of the present invention is to provide a physiological data acquisition module that integrates multiple sensors, an information collection module for edge computing, a digital-to-analog conversion module, a home elevator monitoring gateway, a cloud deployment unit and an information display module based on the HTTP protocol, which collects the physiological data of the passengers and judges the health status of the passengers through the physiological data of the passengers, thereby realizing early warning of the health status and data visualization, and is a simple and practical home elevator monitoring system.
[0012] In response to the above problem or one of the above problems, the third object of the present invention is to provide a detailed and feasible home elevator monitoring method, which first obtains the physiological data of one or more passengers, and judges the health status of the passengers through the physiological data of the passengers, and then realizes health status early warning and data visualization.
[0013] In response to the above problem or one of the above problems, the fourth object of the present invention is to provide an elevator passenger health monitoring method and a home elevator monitoring system and method that can utilize the internal physiological indicators of the elevator passenger to conduct a health assessment of the elevator passenger, which can more accurately reflect the health status of the elevator passenger and has high monitoring accuracy, and is conducive to the popularization and use of elevator passenger health monitoring methods and home elevator monitoring systems and methods.
[0014] To achieve one of the above purposes, the first technical solution of the present invention is:
[0015] A method for monitoring the health of elevator passengers comprises the following steps:
[0016] The first step is to use a pre-built elevator real-time monitoring model to obtain physiological data of one or more passengers; the passenger physiological data at least includes heart rate information and / or blood pressure information and / or blood oxygen information and / or height information and / or weight information and / or body temperature information;
[0017] The second step is to process the passenger's physiological data through the pre-built identity recognition model to obtain the passenger's identity information;
[0018] The third step is to calculate the passenger's health status information based on the identity information and the passenger's physiological data using the pre-built passenger health status recognition model;
[0019] The fourth step is to use the pre-built threshold warning model to compare the threshold of the health status information of the elevator passengers to determine whether it is necessary to send a warning message.
[0020] After continuous exploration and experimentation, the present invention obtains physiological data of one or more elevator passengers by constructing a real-time monitoring model for elevators, an identity recognition model, a passenger health status recognition model, and a threshold warning model; then processes the passenger's physiological data to obtain the passenger's identity information; then calculates based on the identity information and the passenger's physiological data to obtain the passenger's health status information; then performs a threshold comparison on the passenger's health status information to determine whether it is necessary to send a warning message, thereby realizing health monitoring of elevator passengers. The scheme is scientific, reasonable, and feasible.
[0021] Therefore, the present invention can utilize the internal physiological indicators of the elevator passengers to conduct health assessment of the elevator passengers, which can more accurately reflect the health status of the elevator passengers, has high monitoring accuracy, and is conducive to popularization and use.
[0022] Furthermore, the present invention performs health monitoring based on the physiological data of the elevator occupants, and can achieve health monitoring of the elevator occupants without obtaining the image data of the elevator occupants. It is particularly suitable for use in environments or scenarios with extremely high requirements for privacy, such as home elevators and villa elevators, or some business places that emphasize privacy, or certain scenarios that emphasize privacy, etc., thereby making the elevator occupant health monitoring method of the present invention applicable to a wide range of places or scenarios.
[0023] Furthermore, the health monitoring method based on the physiological data of the elevator passengers of the present invention does not need to process a large amount of image information, has a small amount of calculation, and can thus perform health monitoring in real time, and has a low manufacturing cost.
[0024] Furthermore, the present invention is not limited to installing cameras in elevators, but only limits some scenes or places where cameras can be used for health monitoring of passengers. Furthermore, in some places, elevators using the method of the present invention can also be equipped with cameras and can be matched with health monitoring solutions based on image data for users to reasonably choose in different scenes, so that the present invention can be applied to various places or scenes, with a wide range of use, which is conducive to promotion and use.
[0025] As the preferred technical measures:
[0026] In the first step, the elevator real-time monitoring model includes a contact electrode unit, a pressure sensing unit, and a height measurement unit;
[0027] The contact electrode unit is used to obtain the electrophysiological signal of at least one finger of the passenger.
[0028] The electrophysiological signals include blood oxygen signals, blood pressure signals, heart rate signals or body temperature signals;
[0029] Pressure sensing unit, used to collect the weight of passengers;
[0030] The height measurement unit is used to collect the height of passengers.
[0031] As the preferred technical measures:
[0032] In the second step, the method by which the identity recognition model obtains the passenger's identity information is as follows:
[0033] Step 21, obtaining physiological data of the passenger, which at least includes the passenger's height H, weight W and electrophysiological signal S;
[0034] Step 22, constructing a passenger feature vector X=[H, W, S] according to the passenger's height H, weight W and electrophysiological signal S;
[0035] Step 23, using cosine similarity to calculate the similarity between the passenger feature vector X and the pre-stored identity information feature vector Y, the calculation formula is as follows:
[0036] sim(X,Y)=(X*Y) / (||X||*||Y||);
[0037] Step 24, selecting the nearest K identity information feature vectors according to the similarity calculation result;
[0038] Step 25, judging the passenger's identity based on the identity label that appears most frequently among the K nearest neighbors, and generating a corresponding passenger's identity information feature vector to obtain the passenger's identity information.
[0039] As the preferred technical measures:
[0040] In the third step, the method for the passenger health status recognition model to obtain the passenger health status information is as follows:
[0041] Step 31, obtaining identity information and physiological data of the passenger;
[0042] Identity information includes at least age, gender, height and weight;
[0043] The passenger's physiological data includes at least heart rate information, blood pressure information and blood oxygen information;
[0044] Step 32, cleaning the physiological data of the passengers, removing outliers, and extracting features to obtain multi-dimensional data of the passengers after dimension reduction;
[0045] Step 33, construct a multidimensional feature vector of the passengers based on the multidimensional data and identity information of the passengers, and its expression is as follows:
[0046] x=[x1,x2,...x n ],
[0047] where x i Represents the i-th feature of the multidimensional feature vector of the passenger;
[0048] Step 34, inputting the multi-dimensional feature vector of the passenger into a pre-trained logistic regression model to predict the passenger's health status and obtain a prediction result;
[0049] The calculation formula of the logistic regression model is as follows:
[0050] p=Sigmoid(w*x+b) (4)
[0051] Among them, Sigmoid is the activation function of the S-shaped curve, w is the model parameter vector, x is the multi-dimensional feature vector of the passengers, and b is the bias term of the model;
[0052] Step 35, based on the prediction result p, it is mapped to the corresponding health status category to obtain the health status information of the elevator passenger; the health status category includes healthy, sub-healthy or with disease risk.
[0053] As the preferred technical measures:
[0054] The logistic regression model uses the labeled health status dataset for model training and selects logistic regression as the classification algorithm;
[0055] The expression of the model parameter vector is as follows:
[0056] w=[w1,w2,...w n ], where w i Represents the i-th feature weight of the model.
[0057] As the preferred technical measures:
[0058] In the fourth step, the threshold warning model performs threshold comparison as follows:
[0059] The normal range of blood oxygen saturation SpO2 is above 95%, and below 90% indicates insufficient oxygen supply;
[0060] The normal range for systolic blood pressure is usually between 120-140 mmHg, and the normal range for diastolic blood pressure is usually between 80-90 mmHg;
[0061] The normal range of heart rate is usually between 60-100 beats / minute. The heart rhythm should be regular and without abnormal arrhythmias.
[0062] The normal range of body temperature is usually between 36.5-37.5 degrees Celsius;
[0063] The normal range of body mass index (BMI) is 18.5 to 24.9.
[0064] To achieve one of the above purposes, the second technical solution of the present invention is:
[0065] A method for monitoring the health of elevator passengers, comprising the following contents:
[0066] Obtaining physiological data of one or more passengers;
[0067] Process the passenger's physiological data to obtain the passenger's identity information;
[0068] Obtain the passenger's health status information through identity information and passenger's physiological data;
[0069] Determine whether to send an early warning message based on the health status of the elevator passengers.
[0070] After continuous exploration and experimentation, the present invention first obtains the physiological data of one or more elevator passengers; then processes the physiological data of the elevator passengers to obtain the identity information of the elevator passengers; then calculates based on the identity information and the physiological data of the elevator passengers to obtain the health status information of the elevator passengers; then compares the threshold value of the health status information of the elevator passengers to determine whether it is necessary to send an early warning message, thereby realizing health monitoring of elevator passengers. The scheme is scientific, reasonable and feasible.
[0071] Therefore, the present invention can utilize the internal physiological indicators of the elevator passengers to conduct health assessment of the elevator passengers, which can more accurately reflect the health status of the elevator passengers, has high monitoring accuracy, and is conducive to popularization and use.
[0072] Furthermore, the present invention performs health monitoring based on the physiological data of the elevator occupants, and can achieve health monitoring of the elevator occupants without obtaining the image data of the elevator occupants. It is particularly suitable for use in environments or scenarios with extremely high requirements for privacy, such as home elevators and villa elevators, or some business places that emphasize privacy, or certain scenarios that emphasize privacy, etc., thereby making the elevator occupant health monitoring method of the present invention applicable to a wide range of places or scenarios.
[0073] Furthermore, the health monitoring method based on the physiological data of the elevator passengers of the present invention does not need to process a large amount of image information, has a small amount of calculation, and can thus perform health monitoring in real time, and has a low manufacturing cost.
[0074] To achieve one of the above purposes, the third technical solution of the present invention is:
[0075] A household IoT elevator passenger health monitoring system.
[0076] It includes a physiological data acquisition module integrating multiple sensors, an information collection module for edge computing, a digital-to-analog conversion module, a home elevator monitoring gateway, a cloud deployment unit, and an information display module based on the HTTP protocol;
[0077] The physiological data collection module is provided with a plurality of sensors that can be installed in the home IoT elevator to collect the physiological data of the passengers;
[0078] An edge computing-oriented information collection module is used to collect and label the physiological data of elevator passengers in home elevator scenarios;
[0079] The digital-to-analog conversion module is used to perform AD conversion on the collected and labeled physiological data of the passengers to obtain digital physiological data;
[0080] Home elevator monitoring gateway, used to collect and upload digital physiological data in real time through wireless transmission module;
[0081] The cloud deployment unit is used to build a passenger health status recognition model to determine the passenger's health status;
[0082] The information display module based on the HTTP protocol is used to realize data sharing between the server and / or the mobile phone and / or the computer, and can perform health status warning and / or data visualization.
[0083] After continuous exploration and experimentation, the present invention sets up a physiological data acquisition module integrating multiple sensors, an information collection module for edge computing, a digital-to-analog conversion module, a home elevator monitoring gateway, a cloud deployment unit and an information display module based on the HTTP protocol to collect the physiological data of elevator passengers, and judge the health status of the elevator passengers through the physiological data of the elevator passengers, thereby realizing early warning of health status and data visualization, and the structure is simple and practical.
[0084] Therefore, the present invention can utilize the internal physiological indicators of the passengers to conduct health assessment of the passengers, which can more accurately reflect the health status of the passengers, has high monitoring accuracy, and is conducive to popularization and use. As preferred technical measures:
[0085] The physiological data acquisition module integrating multiple sensors is a contact integrated sensor, which includes multiple contact electrodes for touching the fingers of passengers, a pressure sensor for fixing at the bottom of the elevator, an ultrasonic sensor for fixing at the top of the elevator, a blood oxygen sensor module and an electrocardiogram sensor;
[0086] The edge computing-oriented information collection module includes a microprocessor, a server, and a connection portion for fixing on an inner wall of one side of the elevator;
[0087] The pressure sensor is connected to the microprocessor through ADC, the ultrasonic sensor is connected to the microprocessor through the I2C bus, and the blood oxygen sensor module and the electrocardiogram sensor are connected to the microprocessor through the serial port wired;
[0088] The microprocessor is connected to Ethernet through the WiFi module and uses the transmission control protocol TCP / IP to send data to the server;
[0089] The wireless transmission module transmits the raw data collected by the sensor and the results of edge computing to the cloud deployment unit through the MQTT protocol, realizing network communication between the two.
[0090] To achieve one of the above purposes, the fourth technical solution of the present invention is:
[0091] A method for monitoring the health of elevator passengers using the Internet of Things for a household elevator comprises the following steps:
[0092] S1. For the home IoT elevator scenario, multiple sensors are deployed to sense and monitor the health information of passengers, forming a physiological data collection module;
[0093] S2. When a passenger enters the elevator and contacts the sensor, the physiological data collection module is used to collect the passenger's physiological data; the passenger's physiological data includes heart rate and / or blood pressure and / or blood oxygen and / or height and / or weight and / or body temperature;
[0094] S3, the edge computing-oriented information collection module collects and labels the physiological data of elevator passengers in the home elevator scenario;
[0095] S4, performing AD conversion on the collected and labeled physiological data of the passengers to obtain digital physiological data;
[0096] S5. Build a stable and scalable home elevator monitoring gateway, and upload digital physiological data to the cloud deployment unit in real time through a wireless transmission module;
[0097] S6. The cloud deployment unit builds a passenger health status recognition model based on the collected digital physiological data to determine the passenger's health status;
[0098] S7. Using the information display module based on HTTP protocol, data sharing between the server and / or the mobile phone and / or the computer can be realized, and health status warning and / or data visualization can be performed;
[0099] S8. Repeat S2-S7.
[0100] After continuous exploration and experimentation, the present invention first obtains physiological data of one or more passengers, and judges the health status of the passengers through the physiological data of the passengers, and then realizes early warning of health status and data visualization. The scheme is detailed and feasible.
[0101] Therefore, the present invention can utilize the internal physiological indicators of the elevator passengers to conduct health assessment of the elevator passengers, which can more accurately reflect the health status of the elevator passengers, has high monitoring accuracy, and is conducive to popularization and use.
[0102] Compared with the prior art solutions, the present invention has the following beneficial effects:
[0103] After continuous exploration and experimentation, the present invention first obtains physiological data of one or more passengers, and judges the health status of the passengers through the physiological data of the passengers, and then realizes early warning of health status and data visualization. The scheme is detailed and feasible.
[0104] Furthermore, after continuous exploration and experimentation, the present invention first obtains the physiological data of one or more elevator passengers; then processes the physiological data of the elevator passengers to obtain the identity information of the elevator passengers; then calculates based on the identity information and the physiological data of the elevator passengers to obtain the health status information of the elevator passengers; then compares the thresholds of the health status information of the elevator passengers to determine whether it is necessary to send an early warning message, thereby realizing health monitoring of elevator passengers. The scheme is scientific, reasonable and feasible.
[0105] After continuous exploration and experimentation, the present invention sets up a physiological data acquisition module integrating multiple sensors, an information collection module for edge computing, a digital-to-analog conversion module, a home elevator monitoring gateway, a cloud deployment unit and an information display module based on the HTTP protocol to collect the physiological data of elevator passengers, and judge the health status of the elevator passengers through the physiological data of the elevator passengers, thereby realizing early warning of health status and data visualization, and the structure is simple and practical.
[0106] Therefore, the present invention can utilize the internal physiological indicators of the elevator passengers to conduct health assessment of the elevator passengers, which can more accurately reflect the health status of the elevator passengers, has high monitoring accuracy, and is conducive to popularization and use.
[0107] Furthermore, the present invention performs health monitoring based on the physiological data of the elevator occupants, and can achieve health monitoring of the elevator occupants without obtaining the image data of the elevator occupants. It is particularly suitable for use in environments or scenarios with extremely high requirements for privacy, such as home elevators and villa elevators, or some business places that emphasize privacy, or certain scenarios that emphasize privacy, etc., thereby making the elevator occupant health monitoring method of the present invention applicable to a wide range of places or scenarios.
[0108] Furthermore, the health monitoring method based on the physiological data of the elevator passengers of the present invention does not need to process a large amount of image information, has a small amount of calculation, and can thus perform health monitoring in real time, and has a low manufacturing cost. BRIEF DESCRIPTION OF THE DRAWINGS
[0109] Figure 1 It is a flow chart of the elevator passenger health monitoring method of the present invention;
[0110] Figure 2 This is a structural block diagram of the household IoT elevator passenger health monitoring system of the present invention;
[0111] Figure 3 It is a flow chart of the method for monitoring the health of passengers in a household Internet of Things elevator of the present invention. DETAILED DESCRIPTION
[0112] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0113] On the contrary, the present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention as defined by the claims. Further, in order to make the public have a better understanding of the present invention, some specific details are described in detail in the detailed description of the present invention below. Those skilled in the art can fully understand the present invention without the description of these details.
[0114] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention pertains. The terms used herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "or / and" as used herein includes any and all combinations of one or more of the associated listed items.
[0115] like Figure 1 As shown, the first specific embodiment of the elevator passenger health monitoring method of the present invention is:
[0116] A method for monitoring the health of elevator passengers, comprising the following contents:
[0117] Obtaining physiological data of one or more passengers;
[0118] Process the passenger's physiological data to obtain the passenger's identity information;
[0119] Obtain the passenger's health status information through identity information and passenger's physiological data;
[0120] Determine whether to send an early warning message based on the health status of the elevator passengers.
[0121] like Figure 1 As shown, the second specific embodiment of the elevator passenger health monitoring method of the present invention is:
[0122] A method for monitoring the health of elevator passengers comprises the following steps:
[0123] The first step is to use the pre-built elevator real-time monitoring model to obtain the physiological data of one or more elevator passengers;
[0124] The second step is to process the passenger's physiological data through the pre-built identity recognition model to obtain the passenger's identity information;
[0125] The third step is to calculate the passenger's health status information based on the identity information and the passenger's physiological data using the pre-built passenger health status recognition model;
[0126] The fourth step is to use the pre-built threshold warning model to compare the threshold of the health status information of the elevator passengers to determine whether it is necessary to send a warning message.
[0127] like Figure 2 As shown, an embodiment of a household IoT elevator passenger health monitoring system using the monitoring method of the present invention is as follows:
[0128] A household Internet of Things elevator passenger health monitoring system comprises a physiological data acquisition module integrating multiple sensors, an information collection module for edge computing, a digital-to-analog conversion module, a household elevator monitoring gateway, a cloud deployment unit and an information display module based on the HTTP protocol.
[0129] The physiological data collection module is provided with a plurality of sensors that can be installed in the home IoT elevator to collect the physiological data of the passengers;
[0130] An edge computing-oriented information collection module is used to collect and label the physiological data of elevator passengers in home elevator scenarios;
[0131] The digital-to-analog conversion module is used to perform AD conversion on the collected and labeled physiological data of the passengers to obtain digital physiological data;
[0132] Home elevator monitoring gateway, used to collect and upload digital physiological data in real time through wireless transmission module;
[0133] The cloud deployment unit is used to build a passenger health status recognition model to determine the passenger's health status;
[0134] The information display module based on the HTTP protocol is used to realize data sharing between the server and / or the mobile phone and / or the computer, and can perform health status warning and / or data visualization.
[0135] The physiological data acquisition module is an integrated sensor that can monitor a variety of human physiological data (such as heart rate / blood pressure / blood oxygen / height / weight / body temperature) in real time. Taking heart rate data acquisition as an example, heart rate refers to the number of times the heart beats in one minute. The information revealed by the human heart rate can reflect the health of the human heart. In a quiet state, the heart rate value range of a normal adult is generally 60 to 100 times a minute, but the heart rate of the elderly will decrease to a certain extent due to the aging of their organs. If the heart rate value is too high, it may cause serious problems such as fainting and stroke; if the heart rate value is too slow, it may cause problems such as insufficient blood flow to the brain. The present invention uses the photoelectric capacitance method to measure the heart rate of the fingertips. The basic principle of this method is that different tissues of the human body can present different light transmittances in blood vessels, and then the heart rate value is determined according to the different light transmittances.
[0136] The collected information is then continuously stored in the cloud storage space, and the MQTT protocol is used as the standard communication protocol between the device and the cloud platform to achieve data interaction and command transmission between the two. The cloud system of the Internet of Things is built based on the OneNET cloud platform, Web development technology and Vue+MySQL+Node.js technology.
[0137] In addition, the collected data needs to be analyzed with the information pre-stored in the cloud storage space. First, according to the height H, weight W and physiological signal S of the passenger, the feature vector X = [H, W, S] can be constructed; secondly, the cosine similarity is used to calculate the similarity between the passenger feature vector X and the pre-stored identity information feature vector Y, expressed as sim(X,Y) = (X*Y) / (||X||*||Y||); where X = [X1,X2,...,X n ] and Y=[Y1,Y2,...,Y n ] represent the eigenvalues of feature vectors X and Y respectively; then select the nearest K identity information feature vectors based on the similarity calculation results; finally, make a judgment based on the identity label that appears most frequently among the K nearest neighbors, i.e. argmax(Count(Label)). In this way, the identity of the passenger is determined and the identity information feature vector corresponding to the passenger is generated.
[0138] In addition, building a passenger health status recognition model based on the collected physiological data includes two steps: the first is the model training process, and the second is the monitoring process.
[0139] Finally, the C / S architecture is used to develop cloud devices and background management systems, so that multiple terminals (Web pages or mobile apps) can be used to visualize the device data. If it is detected that a certain physical information of the passenger exceeds the set change threshold, this information will be alerted to the terminal user.
[0140] Taking this scenario as an example, the normal range of blood oxygen saturation (SpO2) is usually above 95%. Below 90% may indicate insufficient oxygen supply; the normal range of systolic blood pressure (high pressure) is usually between 120-140 mmHg, and the normal range of diastolic blood pressure (low pressure) is usually between 80-90 mmHg; the normal range of heart rate is usually between 60-100 beats / minute, and the heart rhythm should remain regular under normal circumstances without abnormal arrhythmia; the normal range of body temperature is usually between 36.5-37.5 degrees Celsius; the normal range of BMI is 18.5-24.9.
[0141] like Figure 3 As shown, a method embodiment of applying the system of the present invention:
[0142] A method for monitoring the health of passengers in a household IoT elevator is proposed. Aiming at the scenario of a household IoT elevator, the feasibility of monitoring the health status of passengers by integrating multi-sensor perception is considered. The method is divided into three parts: information collection, information judgment and information display. It includes six units: collection, conversion, storage, judgment, transfer and display. The following is an example of the elevator operation process in real life:
[0143] Step S1: First, it is necessary to select sensors and build a multi-sensor fusion physiological data (such as heart rate / blood pressure / blood oxygen / height / weight / body temperature) acquisition system;
[0144] Step S2: When the passenger enters the elevator and contacts the sensor, the edge computing-oriented information collection module will collect and annotate data in the home elevator scenario;
[0145] Step S3, performing AD conversion on the signal collected by the sensor through Arduino hardware;
[0146] Step S4, constructing a stable and scalable home elevator monitoring gateway, and realizing real-time collection and uploading of physiological data of passengers through a wireless transmission module;
[0147] Step S5: When the monitoring system is running, the collected data and the result information obtained by judgment are continuously stored in the cloud storage space;
[0148] Step S6: Deploy in the cloud a model for identifying the passenger's health status (e.g., healthy / sub-healthy / at risk of disease) based on the collected physiological data to determine the passenger's health status;
[0149] Step S7: Using HTTP protocol to realize data sharing between the server, the mobile phone and the computer, and realizing visualization of the collected data, thus providing sufficient basis for disease prevention;
[0150] Step S8, repeat S2-S7.
[0151] In addition, the information collection module for edge computing is arranged on the inner wall of one side of the elevator, and uses a contact integrated sensor to collect the physiological condition data of the passengers, while using edge computing to improve the data quality of the collected data;
[0152] The contact integrated sensor comprises a plurality of contact electrodes, and acquires the electrophysiological signal of the passenger by contacting at least one finger of the passenger, and the electrophysiological signal includes a blood oxygen signal, a blood pressure signal, a heart rate signal, and a body temperature signal; at the same time, a pressure sensor is arranged at the bottom of the elevator to collect the weight of the passenger, and an ultrasonic sensor is arranged at the top of the elevator to collect the height of the passenger;
[0153] The data measured by the pressure sensor will be analyzed together with the data measured by the ultrasonic sensor. If the ultrasonic sensor measures two or more data, the current data will not be used, and the weight and height data of the elevator passenger stored in the system will still be used;
[0154] The method for labeling data by the edge computing-oriented information collection module is data quality labeling, which is used to label the quality of data collected by sensors, such as the signal strength, noise level, sampling frequency, etc. of the sensor. By labeling the quality indicators of data, it can be used for data filtering, anomaly detection, signal processing, etc.
[0155] Specifically, RSSI is used to measure the received signal strength, generally in decibels (dBm). If the signal strength deviates significantly from the expected range, it may indicate a problem with the sensor or signal transmission. As shown in formula (1):
[0156] RSSI = P_rx - P_ref (1)
[0157] Where P_rx is the received signal power and P_ref is the reference power.
[0158] Taking this scenario as an example, the expected range is -50dBm to -10dBm, and the reference power used is 15dBm to 18dBm.
[0159] Noise power: Indicates the noise level in the signal, usually in decibels (dBm). As shown in formula (2):
[0160] Noise=P_noise-P_ref (2)
[0161] Where P_noise is the noise power in the signal and P_ref is the reference power.
[0162] Taking this scenario as an example, the normal noise power is between -100dBm and -70dBm, and noise outside this range is considered abnormal.
[0163] Sampling period: represents the number of samples or time interval per second. As shown in formula (3):
[0164] SamplingRate=1 / SamplingPeriod (3)
[0165] Among them, SamplingPeriod is the sampling time interval.
[0166] Taking this scenario as an example, the normal sampling period is 10 samples per second. If the labeled sampling period data shows inconsistent changes or extremely unreasonable values (such as very high sampling frequency or very low sampling frequency), it may indicate a sensor failure or data collection error.
[0167] The edge computing layer includes an STM32 series microprocessor and a server. The pressure sensor is connected to the microprocessor through the ADC, the ultrasonic sensor is connected to the microprocessor through the I2C bus, the blood oxygen sensor module and the electrocardiogram sensor are connected to the microprocessor through the serial port wired, and the microprocessor is connected to the Ethernet through the WiFi module, and the transmission control protocol (TCP / IP) is used to send data to the server;
[0168] In order to achieve stability and scalability of the home elevator monitoring gateway, we can first adopt a modular design to divide the gateway functions into independent modules, use a microservice architecture, and deploy services with different functions as independent service units to achieve loose coupling and scalability. Use message queues or event-driven architectures to achieve asynchronous communication and decoupling between modules; secondly, configure redundant network devices, use backup connections and redundant paths to ensure network availability and stability, and use VRRP to achieve fast switching and fault recovery of devices; finally, for data security considerations, the AES data encryption algorithm can be used to encrypt sensitive data stored in the gateway or during transmission;
[0169] The wireless transmission module transmits the raw data collected by the sensor and the results of edge computing to the OneNET cloud through the MQTT protocol to achieve network communication between them;
[0170] The passenger health status (e.g., healthy / sub-healthy / disease risk) identification model is specifically divided into the following contents:
[0171] (1) Input data:
[0172] Physiological data: such as heart rate, blood pressure, blood oxygen and other physiological parameters, which have been cleaned, outliers removed, features extracted and dimension reduced.
[0173] Other relevant information: such as age, gender, height, weight and other basic personal information.
[0174] (2) Feature vector representation:
[0175] Combine the preprocessed and dimension-reduced physiological data and other related information into a feature vector. Assume that the feature vector is x = [x1, x2, ... x n ], where x i represents the i-th feature of the feature vector.
[0176] (3) Model training:
[0177] Use the labeled health status dataset to train the model. Select logistic regression as the classification algorithm, assuming that the model parameters are w = [w1, w2, ... w n ], where w i Represents the i-th feature weight of the model.
[0178] (4) Health status prediction:
[0179] For new passenger data, input its feature vector x into the trained logistic regression model. The health status is predicted by calculating formula (4):
[0180] p=Sigmoid(w*x+b) (4)
[0181] Among them, Sigmoid is the Sigmoid function, w is the model parameter vector, x is the input feature vector, and b is the bias term of the model.
[0182] (5) Output results:
[0183] According to the prediction result p, it is mapped to the corresponding health status category, such as healthy, sub-healthy, at risk of disease, etc.
[0184] The information judgment storage module for cloud storage stores the passenger's heart rate, blood pressure, blood oxygen, body temperature, height, and weight data transmitted by the device on the cloud platform, and then uses the passenger health status recognition model to analyze the data stored in the cloud, and the results are also stored in the cloud;
[0185] The information display module based on the HTTP protocol is used to process the relevant data returned from the cloud and display it on the terminal interface, so that passengers can intuitively understand their physiological data and health status.
[0186] To sum up, with the help of the above-mentioned technical scheme of the present invention, the home elevator is regarded as an important part of the smart home, and the multi-sensor sensing technology is integrated to build a physical health monitoring system for elevator passengers. The real-time collection and uploading of the physiological data of the elevator passengers can be realized, which solves the problem of single and incoherent data collection in traditional measurement methods. At the same time, by storing and analyzing the data in the cloud, data visualization is truly achieved. When abnormal and emergency situations occur, family members and medical institutions can be notified in time to protect the health of the elderly.
[0187] Furthermore, by applying the present invention, home elevators can be regarded as an important part of smart homes, and a physical health monitoring system for elevator passengers can be constructed by integrating multi-sensor sensing technology. Real-time collection and uploading of physiological data of elevator passengers can be realized, solving the problem of single and incoherent data collection in traditional measurement methods. At the same time, by storing and analyzing data in the cloud, data visualization is truly achieved. When abnormal and emergency situations occur, family members and medical institutions can be notified in time, thus safeguarding the health of the elderly.
[0188] An embodiment of a device applying the method of the present invention:
[0189] A computer device comprising:
[0190] one or more processors;
[0191] A storage device for storing one or more programs;
[0192] When the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned method for monitoring the health of elevator passengers.
[0193] A computer medium embodiment using the method of the present invention:
[0194] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned method for monitoring the health of elevator passengers.
[0195] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, and computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0196] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram and the combination of the processes and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0197] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0198] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0199] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
Claims
1. A method for monitoring the health of elevator passengers. It is characterized in that The following steps are involved: The first step is to use a pre-built elevator real-time monitoring model to obtain physiological data of one or more passengers; the passenger physiological data at least includes heart rate information and / or blood pressure information and / or blood oxygen information and / or height information and / or weight information and / or body temperature information; The second step is to process the passenger's physiological data through the pre-built identity recognition model to obtain the passenger's identity information; The third step is to calculate the passenger's health status information based on the identity information and the passenger's physiological data using the pre-built passenger health status recognition model; The fourth step is to use the pre-built threshold warning model to compare the threshold of the health status information of the elevator passengers to determine whether it is necessary to send a warning message.
2. The method for monitoring the health of elevator passengers according to claim 1, characterized in that: In the first step, the elevator real-time monitoring model includes a contact electrode unit, a pressure sensing unit, and a height measurement unit; The contact electrode unit is used to obtain the electrophysiological signal of at least one finger of the passenger. The electrophysiological signals include blood oxygen signals, blood pressure signals, heart rate signals or body temperature signals; The pressure sensing unit is used to collect the weight of the passengers; Height measurement unit, used to collect the height of passengers; The passenger's physiological data at least includes heart rate information and / or blood pressure information and / or blood oxygen information and / or height information and / or weight information and / or body temperature information.
3. The method for monitoring the health of elevator passengers according to claim 1, characterized in that: In the second step, the method by which the identity recognition model obtains the passenger's identity information is as follows: Step 21, obtaining physiological data of the passenger, which at least includes the passenger's height H, weight W and electrophysiological signal S; Step 22, constructing a passenger feature vector X=[H, W, S] according to the passenger's height H, weight W and electrophysiological signal S; Step 23, using cosine similarity to calculate the similarity between the passenger feature vector X and the pre-stored identity information feature vector Y, the calculation formula is as follows: sim(X,Y)=(X*Y) / (||X||*||Y||); Step 24, selecting the nearest K identity information feature vectors according to the similarity calculation result; Step 25, judging the passenger's identity based on the identity label that appears most frequently among the K nearest neighbors, and generating a corresponding passenger's identity information feature vector to obtain the passenger's identity information.
4. The method for monitoring the health of elevator passengers according to claim 1, characterized in that: In the third step, the method for the passenger health status recognition model to obtain the passenger health status information is as follows: Step 31, obtaining identity information and physiological data of the passenger; Identity information includes at least age, gender, height and weight; The passenger's physiological data includes at least heart rate information, blood pressure information and blood oxygen information; Step 32, cleaning the physiological data of the passengers, removing outliers, and extracting features to obtain multi-dimensional data of the passengers after dimension reduction; Step 33, construct a multidimensional feature vector of the passengers based on the multidimensional data and identity information of the passengers, and its expression is as follows: x=[x1,x2,...x n ], where x i Represents the i-th feature of the multidimensional feature vector of the passenger; Step 34, inputting the multi-dimensional feature vector of the passenger into a pre-trained logistic regression model to predict the passenger's health status and obtain a prediction result; The calculation formula of the logistic regression model is as follows: p=Sigmoid(w*x+b) (4) Among them, Sigmoid is the activation function of the S-shaped curve, w is the model parameter vector, x is the multi-dimensional feature vector of the passengers, and b is the bias term of the model; Step 35, based on the prediction result p, it is mapped to the corresponding health status category to obtain the health status information of the elevator passenger; the health status category includes healthy, sub-healthy or with disease risk.
5. The method for monitoring the health of elevator passengers according to claim 4, characterized in that: The logistic regression model uses the labeled health status dataset for model training and selects logistic regression as the classification algorithm; The expression of the model parameter vector is as follows: w=[w1,w2,...w n ], where w i Represents the i-th feature weight of the model.
6. The method for monitoring the health of elevator passengers according to claim 1, characterized in that: In the fourth step, the threshold warning model performs threshold comparison as follows: The normal range of blood oxygen saturation SpO2 is above 95%, and below 90% indicates insufficient oxygen supply; The normal range for systolic blood pressure is usually between 120-140 mmHg, and the normal range for diastolic blood pressure is usually between 80-90 mmHg; The normal range of heart rate is usually between 60-100 beats / minute. The heart rhythm should be regular and without abnormal arrhythmias. The normal range of body temperature is usually between 36.5-37.5 degrees Celsius; The normal range of body mass index (BMI) is 18.5 to 24.
9.
7. A method for monitoring the health of elevator passengers, characterized in that: Includes the following: Obtaining physiological data of one or more passengers; Process the passenger's physiological data to obtain the passenger's identity information; Obtain the passenger's health status information through identity information and passenger's physiological data; Determine whether to send an early warning message based on the health status of the elevator passengers.
8. A household IoT elevator passenger health monitoring system, characterized in that: It includes a physiological data acquisition module integrating multiple sensors, an information collection module for edge computing, a digital-to-analog conversion module, a home elevator monitoring gateway, a cloud deployment unit, and an information display module based on the HTTP protocol; The physiological data collection module is provided with a plurality of sensors that can be installed in the home IoT elevator to collect the physiological data of the passengers; An edge computing-oriented information collection module is used to collect and label the physiological data of elevator passengers in home elevator scenarios; The digital-to-analog conversion module is used to perform AD conversion on the collected and labeled physiological data of passengers to obtain digital physiological data; Home elevator monitoring gateway, used to collect and upload digital physiological data in real time through wireless transmission module; The cloud deployment unit is used to build a passenger health status recognition model to determine the passenger's health status; The information display module based on the HTTP protocol is used to realize data sharing between the server and / or the mobile phone and / or the computer, and can perform health status warning and / or data visualization.
9. A household IoT elevator passenger health monitoring system as claimed in claim 8, characterized in that: The physiological data acquisition module integrating multiple sensors is a contact integrated sensor, which includes multiple contact electrodes for touching the fingers of passengers, a pressure sensor for fixing at the bottom of the elevator, an ultrasonic sensor for fixing at the top of the elevator, a blood oxygen sensor module and an electrocardiogram sensor; The edge computing-oriented information collection module includes a microprocessor, a server, and a connection portion for fixing on an inner wall of one side of the elevator; The pressure sensor is connected to the microprocessor through ADC, the ultrasonic sensor is connected to the microprocessor through the I2C bus, and the blood oxygen sensor module and the electrocardiogram sensor are connected to the microprocessor through the serial port wired; The microprocessor is connected to Ethernet through the WiFi module and uses the transmission control protocol TCP / IP to send data to the server; The wireless transmission module transmits the raw data collected by the sensor and the results of edge computing to the cloud deployment unit through the MQTT protocol, realizing network communication between the two.
10. A method for monitoring the health of elevator passengers using the Internet of Things for household use, characterized in that: The following steps are involved: S1. For the home IoT elevator scenario, multiple sensors are deployed to sense and monitor the health information of passengers, forming a physiological data collection module; S2. When a passenger enters the elevator and contacts the sensor, the physiological data collection module is used to collect the passenger's physiological data; the passenger's physiological data includes heart rate and / or blood pressure and / or blood oxygen and / or height and / or weight and / or body temperature; S3, the edge computing-oriented information collection module collects and labels the physiological data of elevator passengers in the home elevator scenario; S4, performing AD conversion on the collected and labeled physiological data of the passengers to obtain digital physiological data; S5. Build a stable and scalable home elevator monitoring gateway, and upload digital physiological data to the cloud deployment unit in real time through a wireless transmission module; S6. The cloud deployment unit builds a passenger health status recognition model based on the collected digital physiological data to determine the passenger's health status; S7. Using the information display module based on HTTP protocol, data sharing between the server and / or the mobile phone and / or the computer can be realized, and health status warning and / or data visualization can be performed; S8. Repeat S2-S7.
