Contactless Daily Living Status Monitoring Method, System, Computing Device and Medium

Abstract

The present invention relates to a contactless method, system, computing device and medium for monitoring daily living status, which includes: simultaneously obtaining channel state information of a sensing target through at least two receiving devices; determining the spatial position and behavior state of the sensing target according to the channel state information; obtaining a <time, space, behavior state> daily living triple of the sensing target within a preset time period based on the spatial position and behavior state to form a daily living log; obtaining a habit matrix of the sensing target according to the daily living log, extracting a quantitative daily living index indicator based on the habit matrix, and reflecting the living pattern status of the sensing target and detecting the occurrence of abnormal situations by the daily living index indicator. The present invention can achieve continuous monitoring of the daily living status of the elderly for 7*24 hours without the monitoring target contacting any device. The present invention can be applied in the field of monitoring daily living status.

Description

Technical Field

[0001] The present invention relates to the technical field of daily living status monitoring, and in particular to a contactless daily living status monitoring method, system, computing device and medium based on commercial wireless local area network devices. Background Art

[0002] With the increasing aging of the population in China, the proportion of empty-nest elderly people is also increasing year by year. Most empty-nest elderly people still prefer home-based care, especially elderly patients with chronic diseases who are more inclined to receive long-term rehabilitation and treatment at home. Therefore, the health care of these home-based elderly people has become the top priority in solving the aging problem. In recent years, with the rapid development of Wi-Fi technology, using the Wi-Fi signals commonly existing in homes for non-contact sensing provides a new idea for the intelligent care of the elderly. It can achieve 7*24-hour all-weather monitoring without the elderly wearing any devices. Obviously, if the Wi-Fi signals can be used to identify the current daily behaviors (such as eating, sleeping, etc.) of the elderly, it is the most direct way to carry out intelligent care for the elderly. However, at present, the research on Wi-Fi-based behavior recognition still cannot be applied to the recognition of continuous daily behaviors in real life.

[0003] Although there are a large number of related works on behavior recognition in the prior art, due to the inability to achieve the segmentation of continuous behaviors and behavior classification independent of position and orientation, the current behavior recognition research is difficult to achieve fine behavior recognition, and there is still a certain distance from being applied to the health care of the elderly in real life. Summary of the Invention

[0004] Aiming at the above problems, the purpose of the present invention is to provide a contactless daily living status monitoring method, system, computing device and medium, which is based on commercial wireless local area network and can achieve continuous monitoring of the daily living status of the elderly for 7*24 hours without the monitoring target contacting any device.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions: A contactless daily living status monitoring method, which includes: simultaneously obtaining the channel state information of a sensing target through at least two receiving devices; determining the spatial position and behavior state of the sensing target according to the channel state information; obtaining the <time, space, behavior state> daily living triple of the sensing target within a preset time period according to the spatial position and behavior state to form a daily living log; obtaining the habit matrix of the sensing target according to the daily living log, extracting a quantitative daily living index index based on the habit matrix, and reflecting the living pattern status of the sensing target and detecting the occurrence of abnormal situations by the daily living index index.

[0006] Preferably, determining the spatial position of the sensing target according to the channel state information includes: based on the channel state information on each receiving device, extracting boundary sensing features or determining signal parameters, integrating the boundary sensing features or signal parameters on all receiving devices, and using a geometric mapping method to determine the position of the sensing target at a certain moment.

[0007] Preferably, determining the behavior state of the sensing target according to the channel state information includes: determining the static and dynamic state of the sensing target according to the channel state information; when the sensing target is in an active state, extracting Doppler velocity features based on the channel state information on each receiving device, integrating the Doppler velocity features on all receiving devices to obtain the displacement range of each receiving device; comparing the maximum displacement change with a threshold to perform a rough-grained state determination of walking and staying in place to obtain the behavior state.

[0008] Preferably, obtaining the habit matrix of the sensing target according to the daily log includes: mining various living habits of the sensing target according to the daily log; forming a feature vector describing the life of the sensing target on a certain day according to the living habits; and forming the habit matrix describing the living habits of the sensing target through the feature vectors of multiple days.

[0009] Preferably, extracting a quantitative daily living index index based on the habit matrix includes: extracting the feature vector of a new day of the sensing target; and obtaining the daily living index index according to the similarity between the feature vector of the new day and the habit matrix.

[0010] Preferably, reflecting the living pattern status of the sensing target and detecting the occurrence of abnormal situations by the daily living index index includes: when the daily living index index is greater than or equal to a preset threshold, it indicates that the life of the new day is more regular; when the daily living index index is less than the preset threshold, it indicates that the regularity of the new day is poor and abnormal situations occur.

[0011] Preferably, when abnormal situations occur, locating the specific abnormal features describing living habits: if a certain FeatureDis i > γ, then the i-th feature is an abnormal feature, and the specific feature causing the abnormality of that day is determined through the normalized distance.

[0012] A contactless daily living status monitoring system, comprising: a channel state information acquisition module, a location and behavior determination module, a daily living log acquisition module, and a status monitoring module; the channel state information acquisition module simultaneously acquires the channel state information of a sensing target through at least two receiving devices; the location and behavior determination module determines the spatial location and behavior state of the sensing target according to the channel state information; the daily living log acquisition module obtains a <time, space, behavior state> daily living triple of the sensing target within a preset time period according to the spatial location and behavior state, and forms a daily living log; the status monitoring module obtains a habit matrix of the sensing target according to the daily living log, extracts a quantitative daily living index indicator based on the habit matrix, and the daily living index indicator reflects the living pattern status of the sensing target and detects the occurrence of abnormal situations.

[0013] A computer-readable storage medium storing one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to execute any of the above methods.

[0014] A computing device, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the above methods.

[0015] Due to the above technical solutions adopted by the present invention, it has the following advantages:

[0016] 1. The present invention utilizes a commercial Wi-Fi network card to continuously monitor the daily living status of a target without the need for the target to contact any device, providing an important reference for the health monitoring of the elderly.

[0017] 2. The present invention has low requirements for devices and is implemented on some common commercial wireless signal transceivers without the need to modify the hardware. Therefore, the technical solution provided by the present invention can be deployed on common commercial wireless devices (such as Wi-Fi network cards, Wi-Fi routers, RFID readers, etc.), and is implemented quickly, conveniently, with low cost and high benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is the overall flowchart of the daily living status monitoring method in an embodiment of the present invention;

[0019] Figure 2 is the example implementation flowchart block diagram of the daily living status monitoring method in an embodiment of the present invention;

[0020] Figure 3 is the structural schematic diagram of the computing device in an embodiment of the present invention. Detailed implementation manners

[0021] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the described embodiments of the present invention fall within the scope of protection of the present invention.

[0022] It should be noted that the terms used herein are only for describing specific implementation manners and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0023] In order to achieve the health care of the elderly, the present invention proposes a non-contact daily living state monitoring method, system, computing device and medium, which can convert complex behavior recognition problems into spatio-temporal daily living state monitoring problems, and realize the life habits and health conditions of people by statistically analyzing the coarse-grained daily living states. For example, the variation laws (daily living states) of the behavior states of the elderly in time and space are closely related to their living habits and disease development. For example, regular three meals a day, regular toilet use, appropriate walking and sufficient sleep reflect a healthy daily living state of an elderly person. When the daily activities of the elderly suddenly decrease or they get up frequently at night, it may imply that there is a health problem or other abnormal situations. Therefore, the present invention obtains a daily living triple including <time, space, atomic behavior state>, and then statistically analyzes the long-term daily living triples, realizes the inference of the user's living habits, and quantitatively extracts the daily living index indicators to measure the user's living regularity and detect the occurrence of abnormal conditions, so as to achieve the purpose of continuous monitoring of the daily living state.

[0024] In an embodiment of the present invention, a contactless daily living status monitoring method is provided. In this embodiment, taking the application of this method to a terminal as an example, it can be understood that this method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. The contactless daily living status monitoring method provided in this embodiment can not only be used for monitoring the daily living status, but also be applied to other fields to monitor the status of other populations. For example, it can monitor the status of people in the office and the status of inpatients in the hospital. In this embodiment, taking the monitoring of the daily living status of the elderly as an example, the monitoring of the status of other populations is not limited. In this embodiment, this method is in an ordinary home environment, based on commercial wireless local area network devices, and can achieve continuous monitoring of the daily living status for 7*24 hours without the monitoring target contacting any device. As Figure 1 shown, this method includes the following steps:

[0025] Step 1: Simultaneously obtain the channel state information of the sensing target through at least two receiving devices;

[0026] Step 2: Determine the spatial position and behavior state of the sensing target according to the channel state information;

[0027] Step 3: Obtain the <time, space, behavior state> daily living triple of the sensing target within a preset time period according to the spatial position and behavior state, and form a daily living log;

[0028] Step 4: Obtain the habit matrix of the sensing target according to the daily living log, extract the quantitative daily living index indicators based on the habit matrix, and reflect the living pattern status of the sensing target and detect the occurrence of abnormal situations by the daily living index indicators.

[0029] In the above step 1, in this embodiment, the transmitter used is a Wi-Fi signal transmitter in a Wi-Fi transceiver environment, and the receiving device is a Wi-Fi signal receiver corresponding to the transmitter, and the Wi-Fi transceiver device is used for daily living status monitoring.

[0030] The Wi-Fi receiving device uses more than two antennas to simultaneously receive data packets and measure the channel state information (CSI); among them, the data packets are transmitted by the Wi-Fi transmitting device using one antenna; the Wi-Fi transmitting device can use a traditional commercial Wi-Fi device with more than one antenna; the Wi-Fi receiving device can use a traditional commercial Wi-Fi device with more than two antennas.

[0031] In this embodiment, the Wi-Fi transmitting device can be any device including a Wi-Fi network card, such as a mobile phone, a tablet, a computer, a smart watch, etc.; the Wi-Fi receiving device uses the same frequency as the Wi-Fi transmitting device. Common commercial devices generally support connecting three antennas, so it can well meet the requirement of using one antenna at the transmitting end and two antennas at the receiving end.

[0032] Channel state information is used to describe the changes in amplitude and phase after the signal is transmitted through the wireless channel; for example, on commercial Wi-Fi devices, the channel state information reflects the amplitude attenuation and phase drift generated when the wireless signal is transmitted from the transmitting end through the wireless channel and reaches the receiving end. At each sampling moment t0, each receiving antenna collects its own channel state information. The channel state information H(t0) of one antenna is as follows:

[0033]

[0034] In the formula, θ offset represents the phase error brought to the phase of the CSI due to the asynchronous clocks of the Wi-Fi transmitting end and the receiving end; represents the static signal (A s represents the amplitude attenuation of the static signal, represents the phase offset of the static signal) generated by the superposition of the direct path in the environment and the reflection of static objects (furniture, ceiling, etc.); represents the superposition of all dynamic signals generated by the reflection of moving targets, and α d (t0) represents the amplitude attenuation of the d-th dynamic signal at the moment t0, represents the phase offset of the d-th dynamic signal, and D represents the total number of dynamic paths.

[0035] In the above step 2, determining the spatial position of the sensing target according to the channel state information includes: based on the channel state information on each receiving device, extracting the boundary sensing features or determining the signal parameters, and comprehensively using the boundary sensing features or signal parameters on all receiving devices, and using the geometric mapping method to determine the position of the sensing target at a certain moment.

[0036] At the moment t0, use the channel state information on multiple receiving devices to determine the spatial position of the sensing target. Specifically:

[0037] Based on the channel state information on the i-th receiving device, use the WiBorder algorithm to extract the boundary sensing feature Rayleigh iOr use the joint channel parameter estimation algorithm to determine signal parameters such as Angle of Arrival (AoA), Time of Flight (ToF), or Doppler Frequency Shift i , and integrate the boundary perception features Rayleigh on each receiving device i or signal parameters i , and use the method of geometric mapping to determine the position Loc(t0) of the perceived target at time t0.

[0038] In step 2 above, determining the behavior state of the perceived target according to the channel state information includes the following steps:

[0039] Step 21: Determine the static and dynamic state of the perceived target according to the channel state information;

[0040] Based on the channel state information on the i-th receiving device, use the Doppler MUSIC algorithm to extract the Doppler energy feature Dmotion i , or use the CSI amplitude autocorrelation algorithm to extract the amplitude autocorrelation feature Dmotion i , and integrate the Dmotion on each receiving device i , and determine the static and dynamic state Activity(t0) of the perceived target at time t0 according to the following formula:

[0041]

[0042] where δ is the threshold for static and dynamic judgment set according to the corresponding static and dynamic judgment method.

[0043] Step 22: When the perceived target is in the active state, based on the channel state information on each receiving device, take out the Doppler velocity feature, and integrate the Doppler velocity features on all receiving devices to obtain the displacement range of each receiving device;

[0044] Step 23: Compare the maximum displacement change with the threshold to perform a rough-grained state judgment of walking and stationary activity to obtain the behavior state.

[0045] In this embodiment, when the perceived target is in the active state, use the channel state information on multiple devices to determine the behavior state of the perceived target, such as determining whether it is walking or stationary;

[0046] When Activity(t0) = 1, based on the channel state information on the i-th receiving device, use the Doppler MUSIC algorithm to extract the Doppler velocity feature Velocity i, as shown in Equation (3), integrate the Velocity on each receiving device to obtain the displacement range of each receiving device. By comparing the maximum displacement change with a threshold, a coarse-grained state judgment of walking and in-place activities can be performed. More fine-grained behavior state judgments such as eating and sleeping can also be performed through other technical means. i Among them, w is the window size for calculating the displacement change, and Δ is the set displacement change threshold.

[0047]

[0048] In step 3 above, combined with time information, record the long-term <time, space, behavior state> living triad of the perceived target to form a living log.

[0049] Specifically: combined with the current time point t0, and the obtained spatial position Loc(t0) and behavior state Activity(t0), the living triad <t0, Loc(t0), Activity(t0)> of the perceived target can be obtained, and then the long-term living triad of the target can be recorded to form the living log of the perceived target.

[0050] In step 4 above, obtaining the habit matrix of the perceived target according to the living log includes the following steps:

[0051] Step 411: Mine various living habits of the perceived target according to the living log;

[0052] Step 412: Form a feature vector describing the life of the perceived target on a certain day according to the living habits;

[0053] Step 413: Form a habit matrix describing the living habits of the perceived target through the feature vectors of multiple days.

[0054]

[0055] In this embodiment, visualize the living log of the target every 24 hours and analyze it to mine the daily living habits of the target. For example, if the longest time the target stays in the bedroom and most of it is in a stationary state, then this time period probably corresponds to the sleeping time of the perceived target, and the time when the target goes to the bathroom in the early morning probably corresponds to the nocturia behavior. The corresponding times of the three meals a day of the target can also be mined from the activity time of the target in the kitchen. Through the mined sleeping time Feature1, waking-up time Feature2, nocturia time Feature3, number of nocturia times Feature4, three-meal times Feature5, activity proportion Feature i in a day, and the walking proportion Feature i+1 in a day, etc., a feature vector V j describing the life of the target on the jth day can be formed., and when the feature vectors of multiple days are accumulated, a habit matrix V describing the target's living habits can be formed.

[0056]

[0057] In step 4 above, extracting the quantitative daily living index indicators based on the habit matrix includes the following steps:

[0058] Step 421: Extract the feature vector of the target's new day;

[0059] Step 422: Obtain the daily living index indicators according to the similarity between the feature vector of the new day and the habit matrix.

[0060] In this embodiment, extracting the quantitative daily living index indicators reflecting the living pattern based on the mined habit matrix is specifically as follows:

[0061] When a new day NewDay ends, the feature vector V can also be extracted newDay to describe the target's life on the new day. The distance between V newDay and the habit matrix V reflects the regularity of the target's life. Preferably, the Mahalanobis Distance can be used to measure the similarity between the feature vector V newDay and the habit matrix, and then construct the following daily living index indicator Habit(NewDay) to describe the regularity of the target's life on the new day:

[0062]

[0063] where m is the mean vector of the habit matrix V, ε is a constant, and T is the transpose.

[0064] In step 4 above, the daily living index indicators reflect the living pattern of the target and detect the occurrence of abnormal situations, including:

[0065] When the daily living index indicator is greater than or equal to the preset threshold, it indicates that the life on the new day is more regular;

[0066] When the daily living index indicator is less than the preset threshold, it indicates that the regularity of the new day is poor and abnormal situations occur.

[0067] In this embodiment, when Habit(NewDay) ≥ δ(TH), it indicates that the life on the new day is more regular. If Habit(NewDay) < δ(TH), it indicates that the regularity of the new day is poor and abnormal situations occur, where δ(TH) represents the threshold of the daily living index indicator.

[0068] When an abnormal situation occurs, locate the specific abnormal features that describe living habits: If a certain FeatureDis i > γ (γ represents the set feature distance threshold), then the i-th feature is an abnormal feature, and the specific feature causing the abnormality on that day is determined through the normalized distance; where,

[0069]

[0070] where, FeatureDis i represents the distance between the i-th feature on the abnormal day and the i-th feature on the normal day, Feature i represents the value of the i-th feature in the feature vector corresponding to the abnormal day, μ i is the mean value of the i-feature values corresponding to other days, is the variance of the i-th feature value, and finally the specific feature causing the abnormality on this day can be determined through the normalized distance.

[0071] Example:

[0072] This embodiment uses multiple daily Wi-Fi devices as receivers (such as mobile phones, routers, computers, TVs, etc. In this embodiment, a small computer is taken as an example, but it is not limited to a small computer), and uses 2 antennas to receive signals. Use 1 common Wi-Fi device (such as mobile phones, routers, computers, TVs, etc. In this embodiment, a router is taken as an example, but it is not limited to a router) as the signal transmitter, and use 1 antenna to transmit signals. The method for determining the perception boundary provided by the present invention is as follows:

[0073] 1) Build the system:

[0074] Use the router as the Wi-Fi transmitting device, and use a small computer equipped with a commercial Wi-Fi network card supporting two antenna interfaces as the receiving device. The two antenna ports are respectively connected to two antennas. In the example of the present invention, an Intel5300 network card is used to build the system, and the Wi-Fi transceiver device operates at a frequency of 5 GHz and uses a 20 MHz bandwidth for communication. This example consists of 1 transmitter, 5 receivers, and 1 server.

[0075] The method flow for monitoring the daily living state using the built system is as Figure 2 shown, including the following steps:

[0076] 2) Determine the regional location of the perception target at time t0:

[0077] For the channel state information of the 5 receivers, the WiBorder algorithm is used to extract the boundary perception feature Rayleigh i , and integrate the Rayleigh on the 5 receiving devicesi The position of the perceived target at time t0 is determined as "bathroom".

[0078] 3) Determine the static / dynamic state of the perceived target at time t0;

[0079] The Doppler energy features are extracted from the channel state information on 5 receiving devices using the Doppler MUSIC algorithm (Dmotion1 = -3.7, Dmotion2 = -4.0, Dmotion3 = -3.2, Dmotion4 = -4.001, Dmotion5 = -3.96). The Dmotion on the 5 receiving devices i is compared with the threshold C = -3.98. Since Dmotion1 > C, it is determined that the static / dynamic state of the perceived target at time t0 is Activity(t0) = 1.

[0080] 4) When Activity(t0) = 1, that is, when the perceived target is in an active state, the Doppler velocity features are extracted from the channel state information on each receiving device using the Doppler MUSIC algorithm (Velocity1 = 0.5, Velocity2 = 0.5, Velocity3 = 0.8, Velocity4 = 0, Velocity5 = 1). Since it is determined that the static / dynamic state of the perceived target at time t0 is Activity(t0) = 2, which is a walking state.

[0081] 5) Combine the time information and record the long-term living triple of the perceived target, such as <t0, bathroom, walking>, to form a living log.

[0082] 6) Form the feature vector V that describes the target's life on the jth day j , and after accumulating the feature vectors for multiple days (10 days) according to the living log, form the habit matrix V that describes the target's living habits.

[0083]

[0084] 7) When a new day ends on May 20th, the feature vector V can also be extracted newDay to describe the target's life on the new day. The Mahalanobis distance is used to measure the similarity between the vector and the matrix, and the living index Habit(NewDay) = 0.2

[0085] 8) Since Habit(NewDay) < δ(TH) = 0.5, it indicates that the regularity of this day is poor and an abnormal situation has occurred.

[0086] 9) By calculating the normalized distances between the features of the day, the abnormal feature of the day is determined to be "body movement during sleep", indicating the insomnia condition of the sensing target on that day.

[0087] In an embodiment of the present invention, a non-contact daily living state monitoring system is provided, which includes: a channel state information acquisition module, a location behavior determination module, a daily living log acquisition module, and a state monitoring module;

[0088] The channel state information acquisition module simultaneously acquires the channel state information of the sensing target through at least two receiving devices;

[0089] The location behavior determination module determines the spatial location and behavior state of the sensing target according to the channel state information;

[0090] The daily living log acquisition module obtains the <time, space, behavior state> daily living triple of the sensing target within a preset time period according to the spatial location and behavior state, and forms a daily living log;

[0091] The state monitoring module obtains the habit matrix of the sensing target according to the daily living log, extracts the quantitative daily living index indicators based on the habit matrix, and the daily living index indicators reflect the living regularity condition of the sensing target and detect the occurrence of abnormal situations.

[0092] The system provided in this embodiment is used to execute the above method embodiments. For the specific process and detailed content, please refer to the above embodiments, and will not be elaborated here.

[0093] Such as Figure 3As shown in the figure, it is a schematic structural diagram of a computing device provided in an embodiment of the present invention. The computing device may be a terminal, which may include: a processor, a communications interface, a memory, a display screen, and an input device. Among them, the processor, the communications interface, and the memory complete communication with each other through a communication bus. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. When the computer program is executed by the processor, it is used to implement a monitoring method; the internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communications interface is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen may be a liquid crystal display screen or an electronic ink display screen. The input device may be a touch layer covering the display screen, or may be a button, a trackball, or a touchpad provided on the housing of the computing device, or may also be an external keyboard, a touchpad, or a mouse, etc. The processor can call the logical instructions in the memory to execute the following method:

[0094] Simultaneously obtain the channel state information of the sensed target through at least two receiving devices; determine the spatial position and behavior state of the sensed target according to the channel state information; obtain the <time, space, behavior state> living triple of the sensed target within a preset time period according to the spatial position and behavior state, and form a living log; obtain the habit matrix of the sensed target according to the living log, extract a quantitative living index indicator based on the habit matrix, and reflect the living pattern status of the sensed target and detect the occurrence of abnormal situations by the living index indicator.

[0095] In addition, when the logical instructions in the above-mentioned memory are implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. And the foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0096] Those skilled in the art can understand,Figure 3 The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computing device to which the solution of this application is applied. The specific computing device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0097] In an embodiment of the present invention, a computer program product is provided. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the methods provided in the above method embodiments, for example, including: simultaneously obtaining the channel state information of a sensing target through at least two receiving devices; determining the spatial position and behavior state of the sensing target according to the channel state information; obtaining the <time, space, behavior state> living triple of the sensing target within a preset time period according to the spatial position and behavior state to form a living log; obtaining the habit matrix of the sensing target according to the living log, extracting a quantitative living index indicator based on the habit matrix, and reflecting the living pattern status of the sensing target and detecting the occurrence of abnormal situations by the living index indicator.

[0098] In an embodiment of the present invention, a non-transitory computer-readable storage medium is provided. The non-transitory computer-readable storage medium stores server instructions. The computer instructions cause the computer to execute the methods provided in the above embodiments, for example, including: simultaneously obtaining the channel state information of a sensing target through at least two receiving devices; determining the spatial position and behavior state of the sensing target according to the channel state information; obtaining the <time, space, behavior state> living triple of the sensing target within a preset time period according to the spatial position and behavior state to form a living log; obtaining the habit matrix of the sensing target according to the living log, extracting a quantitative living index indicator based on the habit matrix, and reflecting the living pattern status of the sensing target and detecting the occurrence of abnormal situations by the living index indicator.

[0099] For the computer-readable storage medium provided in the above embodiment, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be elaborated here.

[0100] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows 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 the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementation in the processFigure 1 one process or multiple processes and / or blocks Figure 1 a device for the functions specified in one block or multiple blocks.

[0101] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device that implements the functions in the process Figure 1 one process or multiple processes and / or blocks Figure 1 the functions specified in one block or multiple blocks.

[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions in the process Figure 1 one process or multiple processes and / or blocks Figure 1 the functions specified in one block or multiple blocks.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A non-contact method for monitoring daily living status, characterized in that, Including: Simultaneously obtaining the channel state information of the perceived target through at least two receiving devices; Determining the spatial position and behavior state of the perceived target according to the channel state information; Obtaining the <time, space, behavior state> living triad of the perceived target within a preset time period based on the spatial position and behavior state, and forming a living log; Obtaining the habit matrix of the perceived target according to the living log, extracting a quantitative living index indicator based on the habit matrix, and reflecting the living pattern status of the perceived target and detecting the occurrence of abnormal situations by the living index indicator; The obtaining the habit matrix of the perceived target according to the living log includes: Mining various living habits of the perceived target according to the living log; Forming a feature vector describing the life of the perceived target on a certain day according to the living habits; Forming the habit matrix describing the living habits of the perceived target through the feature vectors of multiple days; The extracting a quantitative living index indicator based on the habit matrix includes: Extracting the feature vector of a new day of the perceived target; Obtaining the living index indicator according to the similarity between the feature vector of the new day and the habit matrix; The reflecting the living pattern status of the perceived target and detecting the occurrence of abnormal situations by the living index indicator includes: When the living index indicator is greater than or equal to a preset threshold, it indicates that the life of the new day is relatively regular; When the living index indicator is less than the preset threshold, it indicates that the regularity of the new day is poor and abnormal situations occur.

2. The monitoring method according to claim 1, characterized in that, The determining the spatial position of the perceived target according to the channel state information includes: Based on the channel state information on each receiving device, extracting boundary perception features or determining signal parameters, and comprehensively using all the boundary perception features or signal parameters on the receiving devices, and using a geometric mapping method to determine the position of the perceived target at a certain moment.

3. The monitoring method according to claim 1, characterized in that, The determining the behavior state of the perceived target according to the channel state information includes: Determining the static and dynamic state of the perceived target according to the channel state information; When the perceived target is in an active state, taking out the Doppler velocity features based on the channel state information on each receiving device, and integrating the Doppler velocity features on all the receiving devices to obtain the displacement range of each receiving device; Comparing the maximum displacement change with a threshold, making a rough-grained state judgment of walking and in-situ activities, and obtaining the behavior state.

4. The monitoring method according to claim 1, characterized in that, When abnormal situations occur, locating the specific abnormality describing the living habits Features: If a certain time, then the th feature is an abnormal feature, and the specific feature causing the abnormality on this day is determined through the normalized distance; represents the set feature distance threshold, represents the distance between the 𝑖th feature on the abnormal day and the 𝑖th feature on the normal day.

5. A non-contact daily living status monitoring system, characterized in that, Including: A channel state information acquisition module, a position and behavior determination module, a living log acquisition module, and a state monitoring module; The channel state information acquisition module simultaneously obtains the channel state information of the perceived target through at least two receiving devices; The position and behavior determination module determines the spatial position and behavior state of the perceived target according to the channel state information; The living log acquisition module obtains the <time, space, behavior state> living triad of the perceived target within a preset time period based on the spatial position and behavior state, and forms a living log; The state monitoring module obtains a habit matrix of the perceived target according to the daily log, extracts a quantitative daily living index index based on the habit matrix, and reflects the living pattern status of the perceived target and detects the occurrence of abnormal situations by the daily living index index; The obtaining of the habit matrix of the perceived target according to the daily log includes: Mining various living habits of the perceived target according to the daily log; Forming a feature vector describing the life of the perceived target on a certain day according to the living habits; Forming the habit matrix describing the living habits of the perceived target through the feature vectors of multiple days; The extracting of the quantitative daily living index index based on the habit matrix includes: Extracting the feature vector of a new day of the perceived target; Obtaining the daily living index index according to the similarity between the feature vector of the new day and the habit matrix; The reflecting of the living pattern status of the perceived target and detecting the occurrence of abnormal situations by the daily living index index includes: When the daily living index index is greater than or equal to a preset threshold, it indicates that the life of the new day is relatively regular; When the daily living index index is less than the preset threshold, it indicates that the regularity of the new day is poor and abnormal situations occur.

6. A computer-readable storage medium storing one or more programs, characterized in that, The one or more programs include instructions that, when executed by a computing device, cause the computing device to execute any of the methods described in claims 1 to 4.

7. A computing device, characterized in that, Including: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the methods described in claims 1 to 4.

Images