Old people behavior safety monitoring method and system

Abstract

The invention is suitable for the technical field of safety monitoring, and particularly relates to an old people behavior safety monitoring method and system, and the method comprises the steps: obtaining the monitoring information of old people; according to the monitoring information, physiological safety information of the old people is obtained; obtaining psychological safety information of the old people according to the monitoring information; and performing safety rating according to the physiological safety information and the psychological safety information to obtain alarm information. Physiological and psychological health problems of the elderly are found by analyzing the multi-dimensional monitoring information, the danger level of the alarm information is determined, and guardians or medical staff are informed in time.

Description

Technical Field

[0001] The present application belongs to the field of security monitoring technology, and in particular, to a method and system for security monitoring of elderly people's behavior. Background Art

[0002] It is generally believed internationally that when the elderly population over 60 years old in a country or region accounts for 10% of the total population, or the elderly population over 65 years old accounts for 7% of the total population, it means that the population of this country or region is in an aging society. According to China's seventh national census, the proportion of China's population over 60 years old is 18.70%, and the proportion of the population over 65 years old is 13.50%. China's pension demand is growing at a rate that is increasing, and the pension burden on young people is increasing.

[0003] As the burden of caring for the elderly on young people is increasing, children often do not have time to accompany and supervise the elderly, resulting in the elderly being unable to inform guardians in time when accidents or emergencies occur, and the elderly's psychological needs are not met, resulting in the increasingly prominent mental health problems of the elderly in society. Psychological problems and physical health are two sides of the same coin and are closely related. In the existing technology, there is a method of using deep learning models to determine when the elderly have fallen and notify guardians, but the existing technology ignores the mental health of the elderly, and the judgment of emergency situations for the elderly is not comprehensive enough. Summary of the invention

[0004] The embodiments of the present application provide a method and system for monitoring the safety of elderly people's behavior, which can solve the problems of failure to timely detect abnormalities in the elderly's physical and mental health, and incomplete judgment of the elderly's emergency situations.

[0005] In a first aspect, the present application provides a method for monitoring elderly people's behavior safety, including: Acquire monitoring information of the elderly; wherein the monitoring information is used to reflect the behavior and physical condition of the elderly; According to the monitoring information, the physiological safety information of the elderly is obtained; wherein the physiological safety information is used to reflect the physical safety of the elderly; According to the monitoring information, psychological safety information of the elderly is obtained; wherein the psychological safety information is used to reflect the psychological safety of the elderly; A safety rating is performed based on the physiological safety information and the psychological safety information to obtain alarm information; wherein the alarm information is used to prompt a guardian and / or warn the elderly person being supervised.

[0006] The above technical solutions in the embodiments of the present application have at least the following technical effects: The method for monitoring the behavior and safety of the elderly provided in the present application first obtains monitoring information of the elderly, and the monitoring information is information that can reflect the behavior and physical condition of the elderly. Secondly, based on the monitoring information, the physiological safety information of the elderly is obtained, and by analyzing the monitoring information, accidents that occur to the elderly can be discovered in a timely manner. Subsequently, based on the monitoring information, the psychological safety information of the elderly is obtained, and by analyzing the monitoring information, psychological problems of the elderly can be discovered. Finally, a safety rating is performed based on the physiological safety information and the psychological safety information to obtain alarm information, and the danger level of the alarm information is determined by performing a safety rating on the degree of danger of the physiological safety information and the psychological safety information, and the alarm information includes details of the relevant physiological or psychological problems. By analyzing multi-dimensional monitoring information, the physiological and psychological health problems of the elderly are discovered, and the danger level of the alarm information is determined, and the guardian or medical staff is informed in a timely manner.

[0007] In a second aspect, the present application embodiment provides a system for monitoring elderly people's behavior safety, including: An acquisition unit, used to acquire monitoring information of the elderly; wherein the monitoring information is used to reflect the elderly's movements, sounds, body temperature and location; A first processing unit is used to obtain physiological safety information of the elderly according to the monitoring information; wherein the physiological safety information is used to reflect the physical safety of the elderly; A second processing unit is used to obtain psychological safety information of the elderly according to the monitoring information; wherein the psychological safety information is used to reflect the psychological safety of the elderly; An alarm unit is used to perform safety rating according to the physiological safety information and the psychological safety information to obtain alarm information; wherein the alarm information is used to prompt the guardian and / or warn the elderly person under guardianship.

[0008] In the third aspect, an embodiment of the present application provides a device for monitoring the behavior of the elderly, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the methods described in the first aspect when executing the computer program.

[0009] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the first aspects above is implemented.

[0010] In the fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on a behavior safety monitoring device for the elderly, the behavior safety monitoring device for the elderly executes the behavior safety monitoring method for the elderly described in any one of the first aspects above.

[0011] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0013] Figure 1 is a schematic flow chart of a method for monitoring elderly people's behavior safety provided in an embodiment of the present application; Figure 2 It is a positive emotion score graph of step S341 in the elderly behavior safety monitoring method provided in one embodiment of the present application; Figure 3 It is a negative emotion score graph of step S341 in the elderly behavior safety monitoring method provided in one embodiment of the present application; Figure 4 It is a structural diagram of the elderly behavior safety monitoring system provided in the embodiment of the present application.

[0014] Figure 5 It is a structural diagram of the elderly behavior safety monitoring device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0015] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0016] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0017] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0018] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0019] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0020] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0021] In the related technologies, there are methods that can detect the elderly's accidental falls or other unexpected situations in time and alarm, but these methods ignore the mental health of the elderly, and mental health and physical health often affect each other. In the related technologies of psychological testing, some high-end instruments are often required, such as blood oxygen meters, heart rate monitors, etc., which are not suitable for most elderly people. Therefore, a lightweight method is needed to detect the physical and mental health problems of the elderly.

[0022] To solve the above problems, the embodiment of the present application provides a method and system for monitoring the behavior safety of the elderly. In the method, first, the monitoring information of the elderly is obtained, and the monitoring information is information that can reflect the behavior and physical condition of the elderly. Secondly, based on the monitoring information, the physiological safety information of the elderly is obtained, and by analyzing the monitoring information, accidents that occur to the elderly can be discovered in time. Subsequently, based on the monitoring information, the psychological safety information of the elderly is obtained, and by analyzing the monitoring information, psychological problems of the elderly can be discovered. Finally, a safety rating is performed based on the physiological safety information and the psychological safety information to obtain alarm information. By performing a safety rating on the degree of danger of the physiological safety information and the psychological safety information, the danger level of the alarm information is determined, and the alarm information includes details of the relevant physiological or psychological problems. By analyzing multi-dimensional monitoring information, the physiological and psychological health problems of the elderly are discovered, and the danger level of the alarm information is determined, and the guardian or medical staff is informed in time.

[0023] The elderly behavior safety monitoring method provided in the embodiment of the present application can be applied to the elderly behavior safety monitoring device. In this case, the elderly behavior safety monitoring device is the executor of the elderly behavior safety monitoring method provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the elderly behavior safety monitoring device.

[0024] For example, the elderly behavior safety monitoring equipment may include a collection device and a control device that is in communication with the collection device. The collection device may include a high-performance camera with functions such as thermal imaging, sound collection, and networking, and the control device may include a processor, a memory, and a computer program stored in the memory and run on the processor. The control device may control the high-performance camera to collect videos of the elderly and the surrounding environment, may control the high-performance camera to collect sounds of the elderly and the surrounding environment, may control the high-performance camera to collect thermal images of the elderly, and may control the high-performance camera to send the location of the elderly.

[0025] The control device can be a single-chip microcomputer, a microprocessor, a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a desktop computer, a smart large screen, a smart TV, etc.

[0026] In order to better understand the elderly behavior safety monitoring method provided in the embodiment of the present application, the specific implementation process of the elderly behavior safety monitoring method provided in the embodiment of the present application is exemplarily introduced below.

[0027] Figure 1A schematic flow chart of a method for monitoring elderly behavior safety provided in an embodiment of the present application is shown, and the method for monitoring elderly behavior safety includes: S100, obtaining monitoring information of the elderly, wherein the monitoring information is used to reflect the behavior and physical condition of the elderly.

[0028] It can be understood that monitoring information includes the elderly's movement information, sound information, body temperature information and location information. The elderly's movement, sound, thermal imaging and location information can be obtained simultaneously through an integrated multifunctional high-performance camera to obtain monitoring information. Different sensors can also be used to obtain monitoring information separately.

[0029] For example, the motion information may refer to the body skeleton information obtained by the human skeleton extraction algorithm after taking an image of the elderly and then performing image processing on the image of the elderly. The sound information may refer to the audio information of the amplitude-time of the elderly's sound. The body temperature information may be a thermal imaging picture. The location information may be the three-dimensional location information of the elderly in the map.

[0030] Exemplarily, the image of an elderly person is captured by the image capture function of a high-performance camera to obtain the elderly person's movement information, the recording function of a high-performance camera is used to obtain the elderly person's voice information, the thermal imaging function of a high-performance camera is used to obtain the elderly person's body temperature information, and the networking function of a high-performance camera is used to obtain the location information of the camera and the elderly person.

[0031] For example, the control device can control the high-performance camera to collect videos of the elderly and their surroundings, can also control the high-performance camera to collect sounds of the elderly and their surroundings, can also control the high-performance camera to collect thermal images of the elderly, and can also control the high-performance camera to send the location of the elderly. The control device is connected to the high-performance camera for communication, and the high-performance camera can be set in the elderly's home or other activity areas. The high-performance camera can automatically shoot the elderly and the surrounding terrain through intelligent focusing.

[0032] S200, obtaining physiological safety information of the elderly according to the monitoring information, wherein the physiological safety information is used to reflect the physical safety of the elderly.

[0033] It is understandable that the elderly often encounter some accidents due to their age, such as falls, foreign objects stuck in the throat, etc. By analyzing the monitoring information, it is possible to infer whether the elderly have had an accident or are engaging in dangerous behavior, so as to obtain the elderly's physiological safety information.

[0034] Such a setting can avoid tragedies caused by the elderly being unable to call for help or judge danger on their own due to physical reasons.

[0035] In a possible implementation, in step S200, the physiological safety information of the elderly is obtained according to the monitoring information, including: S210, performing motion recognition on the monitoring information to determine the first state of the elderly, wherein the first state includes a standing state, a sitting state, a lying state, and a falling state.

[0036] It is understandable that the action information in the monitoring information can be input into the deep learning model to output the category of the first state of the elderly through the deep learning model, such as the falling state or the sitting state, etc., and the first state of the elderly at the same time can only be one of the standing state, sitting state, lying state and falling state. The body skeleton of the elderly in the monitoring information can also be extracted (the body skeleton refers to the simplified human body model obtained by the body skeleton extraction algorithm, which can effectively represent the human body movement and simplify the processing), and the first state of the elderly can be judged in the continuous joint angles of the body skeleton.

[0037] Exemplarily, the motion information in the monitoring information is represented in the form of data of a body skeleton. When the knees of the elderly person's body skeleton are not bent and the body is upright, the first state is determined to be a standing state; when the knees of the elderly person's body skeleton are bent within a predetermined angle range and the hip joints are also bent within a predetermined angle range, the first state is determined to be a sitting state; when the acceleration of the elderly person's upper body in consecutive elderly person's body skeletons is less than a preset value and the angle between the body skeleton and the ground is less than a preset value, the first state is determined to be a lying state; when the acceleration of the elderly person's upper body in consecutive elderly person's body skeletons is greater than a preset value and the angle between the body skeleton and the ground is less than a preset value, the first state is determined to be a falling state.

[0038] The deep learning model can use a CNN convolutional neural network, and then obtain a video data set of people in four states: standing, sitting, lying and falling, and ensure that the number of data sets in the four states is one-fourth each, and randomly select 90% of the data sets as training sets, and the remaining 10% as test sets. The training set is input to train the deep learning model. The input is the video signal of the person in the training set, and the output is the person's first state. The trained model is tested on the test set. When the accuracy rate does not meet the standard, it is retrained. When the accuracy rate meets the standard, the model training is completed. The trained deep learning model can judge the first state of the elderly.

[0039] Such a setting can improve the accuracy of judging the first state of the elderly.

[0040] S220, when the first state is a fall state, obtain limb information of the elderly in the monitoring information, and obtain the first sub-physiological safety information in the physiological safety information according to the limb information. The limb information is used to reflect the activities of the elderly's limbs, and the first sub-physiological safety information is used to reflect the physiological safety of the elderly after falling.

[0041] It is understandable that the characteristic information of the limbs can be separated from the results of motion recognition, or the motion recognition can be re-performed and focused on the limb movements of the elderly to obtain the limb information of the elderly. After the elderly fall, there may be a variety of situations, such as fainting after falling, fractures after falling, or no serious injuries after falling, etc. If the elderly are rashly helped up or helped without knowing their physical condition, it is likely to cause secondary injuries. Therefore, the limb movements of the elderly in the state of falling are analyzed to obtain the first sub-physiological safety information.

[0042] Exemplarily, skeleton extraction may be performed on the monitoring information, and the limb information includes the joint angles and joint angle changes of the limb skeletons.

[0043] Such an arrangement completes the basic physical condition measurement of the elderly after they fall, can reduce the first aid steps, and improve the safety rescue efficiency of the elderly in emergency situations.

[0044] In a possible implementation, in step S220, obtaining the first sub-physiological safety information in the physiological safety information according to the limb information includes: S221, when the first state is a fall state, the first sub-physiological safety information is obtained as a red safety level, and the left hand movement information, the right hand movement information, the left foot movement information and the right foot movement information in the limbs information are obtained.

[0045] It can be understood that when the elderly falls, the first sub-physiological safety information is set to a red safety level. The safety level is divided into three levels, which are red, yellow, and green safety levels from severe to mild. The limb information includes left hand action information, right hand action information, left foot action information, and right foot action information. In this application, the left hand refers to the left hand in a broad sense, including the entire limbs including the left arm; the same is true for the remaining right hand, left foot, and right foot in this application, which are the right hand, left foot, and right foot in a broad sense.

[0046] Exemplarily, the left hand motion information may be the joint angles and joint angle changes of the left hand skeleton after skeleton extraction, and the same applies to the remaining right hand motion information, left foot motion information, and right foot motion information.

[0047] With this arrangement, the health conditions of the four limbs of the elderly after a fall can be analyzed, which is conducive to more detailed determination of the elderly's primary physiological safety information.

[0048] S222: If any of the left hand motion information, the right hand motion information, the left foot motion information, and the right foot motion information indicates that the elderly person has made a motion, it is determined that the consciousness safety information in the first sub-physiological safety information reflects that the elderly person is conscious; otherwise, it is determined that the consciousness safety information in the first sub-physiological safety information reflects that the elderly person is unconscious. The consciousness safety information is used to reflect whether the elderly person has self-awareness after falling.

[0049] It can be understood that after the elderly person falls, it can be determined whether the elderly person is conscious based on whether the limb information indicates that the elderly person has limb movements. A movement amplitude threshold can be set. When the limb information indicates that the elderly person has movements exceeding the movement amplitude threshold, it means that the elderly person has autonomous movements. And the first sub-physiological safety information is continuous in time and will be updated with the movement of the elderly person. For example, within the first ten seconds before the elderly person falls, the limb information indicates that there is no movement, then the consciousness safety information obtained in the first sub-physiological safety information for each period of time is that the elderly person is unconscious, but at the eleventh second, the limb information indicates that there is movement, then the consciousness safety information in the first sub-physiological safety information is updated to the elderly person is conscious. If the limb information indicates that there is no movement within the preset threshold time after the eleventh second, the consciousness safety information in the first sub-physiological safety information is updated again to the elderly person is unconscious. A physiological accident has a first sub-physiological safety information timeline, and the guardian can view the first sub-physiological safety information at any time point on the timeline.

[0050] With this setting, not only can the safety status of the elderly after a fall be quickly obtained, but also the elderly can be kept under constant attention and the first sub-physiological safety information can be updated, thereby improving the dimension of the first sub-physiological safety information and facilitating timely reporting of the elderly's physiological safety status and improving the accuracy of the reported physiological safety status.

[0051] S223, when it is determined that the first sub-physiological safety information indicates that the elderly person is conscious, the body safety information in the first sub-physiological safety information is determined according to the limb movement range in the limb information. The limb movement range refers to the movement range of each of the elderly person's limbs, and the body safety information is used to reflect whether the elderly person's body is fractured or dislocated after falling.

[0052] It is understandable that if an elderly person is conscious after falling, the range of motion of the elderly person's limbs can be analyzed to determine whether the elderly person's body has fractures or dislocations.

[0053] For example, the movement range of the elderly's limbs can be accumulated. When the sum of the movement range of the limbs reaches a threshold, the movement range ratio of each limb is calculated. If the movement range ratio of a limb or multiple limbs is too small, the physical safety information in the first sub-physiological safety information is judged according to the specific situation. A minimum threshold can be set. When the movement range ratio of a limb is less than the minimum threshold, it means that the limb is affected by a fracture, and possible fracture conditions are listed. For example, as shown in Table 1: Table 1 It should be noted that the body safety information in the first sub-physiological safety information requires data accumulation. In short, it takes a certain amount of time to obtain the body safety information in the first sub-physiological safety information.

[0054] Such an arrangement can improve the accuracy of the body safety information in the obtained first sub-physiological safety information.

[0055] S224, when it is determined that the first sub-physiological safety information is that the elderly person is unconscious, if any of the left hand motion information, the right hand motion information, the left foot motion information, and the right foot motion information indicates that the elderly person has limb stiffness or convulsion, it is determined that the central nervous system safety information in the first sub-physiological safety information reflects central nervous system injury. The central nervous system safety information is used to reflect whether the elderly person has suffered central nervous system injury after falling.

[0056] It can be understood that the central nervous system refers to the brain and spine. When the central nervous system function is damaged, limb stiffness or convulsion often occurs. After the elderly fall, the limb information is analyzed to see whether any limb is stiff or convulsed, which can determine whether the elderly have suffered central nervous system injury after falling. The limb bone joint angles of the body skeleton in the limb information can be extracted to determine whether there are abnormal conditions in the limb bone joint angles (such as limb tonic extension, shoulder depression, upper arm adduction and internal rotation, or even opisthotonos, etc.) and whether the bone joint angles have not changed for a continuous period of time to determine whether the elderly are stiff. Deep learning models can also be used to determine whether the elderly are stiff.

[0057] Exemplarily, a database is established to store special limb joint angles generated when the human body is rigid, such as the limb joint angles when the limbs are rigidly extended, etc. The limb bone joint angles of the body skeleton in the elderly limb information are matched with the database, and when the match with any item in the database is successful and maintained for a preset time, the elderly person is determined to be rigid.

[0058] The deep learning model can use a CNN convolutional neural network, and then obtain a video data set of people in a normal state and a rigid state, and ensure that the number of data sets in the two states is half each, and randomly select 90% of the data sets as training sets, and the remaining 10% as test sets. The training set is input to train the deep learning model. The input is the video signal of the people in the training set, and the output is whether the person is in a rigid state. The trained model is tested on the test set. When the accuracy rate does not meet the standard, it is retrained. When the accuracy rate meets the standard, the model training is completed. The trained deep learning model can determine whether the elderly are rigid.

[0059] Such an arrangement can improve the accuracy of the central nervous system safety information in the obtained first sub-physiological safety information.

[0060] S230, when the first state is the standing state, the standing information of the elderly in the monitoring information is obtained, and the second sub-physiological safety information in the physiological safety information is obtained according to the standing information. The standing information is used to reflect the information of the standing position of the elderly, and the second sub-physiological safety information is used to reflect the safety risk level of the standing position of the elderly.

[0061] It is understandable that the terrain of the standing position is the most important factor in the cause of the elderly falling down. It is difficult for the elderly to maintain balance, and often a small pit may cause the elderly to fall down. The standing information of the elderly can be obtained through visual measurement methods, and the safety risk level of the elderly standing position can be analyzed. The specific analysis steps are shown in the subordinate steps of S230.

[0062] It should be noted that the visual measurement method can be either passive visual measurement or active visual measurement. Passive visual measurement refers to a method that does not require a special lighting projection device, only uses a camera to shoot a video of the object to be measured, establishes a relative position relationship between the object to be measured and the camera, and thus obtains three-dimensional information of the surface of the object to be measured. Active visual measurement is a method in which a light source (points, stripes, patterns, speckles, etc.) is projected onto the object to be measured, and the camera shoots a video of the surface of the object to be measured containing the reflected light or transmitted light of the light source, and uses a mathematical model established by the imaging geometric relationship to solve the three-dimensional information of the object to be measured. The specific implementation steps belong to the prior art and will not be repeated here.

[0063] Such a setting can prevent most of the falls among the elderly, thus improving the practicality and scientificity of the method.

[0064] In a possible implementation, in step S230, obtaining the second sub-physiological safety information in the physiological safety information according to the standing information includes: S231, when the first state is the standing state, obtain the standing height information, the standing slope information, and the standing surface filling rate information in the standing information. The standing height information is used to indicate the height of the standing position from the ground or floor, the standing slope information is used to indicate the slope of the standing position, and the standing surface filling rate information is used to indicate the area filling rate of the plane where the standing position is located within the threshold area range. It can be understood that the terrain features of a standing position may include height, slope, and the size of the standing surface. The size of the standing surface can be expressed as the area filling rate of the plane where the standing position is located within the threshold area range. For example, the threshold area is 4π square meters, and the area of ​​the plane where the standing position is located within the 4π square meter circle with the standing center as the center is 10 square meters, then the area filling rate is 10 / 4π≈80%.

[0065] In this way, the terrain characteristics of the standing position are represented by the three characteristics of height, slope, and size of the standing surface, which is conducive to quantifying the safety risk level of the standing position of the elderly.

[0066] S232: Perform weighted calculation on the value corresponding to the standing height, the value corresponding to the standing slope, and the value corresponding to the standing surface filling rate to obtain a standing danger index, wherein the standing danger index is used to reflect the degree of danger of the standing position of the elderly.

[0067] It can be understood that the standing height, standing slope and standing surface filling rate can be analyzed. According to the theorem of conservation of mechanical energy, , g refers to the acceleration of gravity, h refers to the standing height, and v refers to the landing speed during free fall. The landing speed is proportional to the impulse at the time of landing (impulse theorem). Therefore, the hazard weight value of the standing height can be expressed as the landing speed, and 10m / s is set as the upper limit of the landing speed to normalize the hazard weight value of the standing height. The most common way to express the standing slope is slope = (elevation difference / horizontal distance) × 100%. For example, a slope of 3% means that for every 100 meters of horizontal distance, the vertical direction rises (descends) by 3 meters. Therefore, the hazard weight value of the standing slope can be expressed as the size of the standing slope, and no normalization is required. The hazard weight value of the standing surface filling rate can also be directly expressed as (1-standing surface filling rate), and no normalization is required. Standing hazard index = hazard weight value of standing height + hazard weight value of standing slope + hazard weight value of standing surface filling rate.

[0068] For example, the standing height indication is 3m, the standing slope indication is 30%, and the standing surface filling rate indication is 90%. The calculated landing speed v=7.7m / s, normalized to the hazard weight value of the standing height = 77%, the hazard weight value of the standing slope is 30%, and the hazard weight value of the standing surface filling rate is 1-90%=10%, so the standing hazard index = 77%+30%+10%=117%.

[0069] With such an arrangement, the degree of danger of the standing position can be quantified, and the accuracy of the obtained standing danger index can be improved.

[0070] S233, determining whether the standing danger index is greater than or equal to the first alarm threshold, if it is greater than or equal to the first alarm threshold, the second sub-physiological safety information is obtained as a yellow safety level, and if it is less than the first alarm threshold, the second sub-physiological safety information is obtained as a green safety level. The first alarm threshold is used to reflect the alarm threshold size of the standing danger index.

[0071] It can be understood that when the standing danger index is greater than or equal to the first alarm threshold, it means unsafe and the safety level is set to yellow; when the standing danger index is less than the first alarm threshold, it means safe and the safety level is set to green.

[0072] This arrangement can determine whether the elderly are standing in an unsafe position in order to prevent falls.

[0073] S240, when the first state is the sitting state, obtain the eating information of the elderly in the monitoring information, and obtain the third sub-physiological safety information in the physiological safety information according to the eating information. The eating information is used to reflect the eating situation of the elderly, and the third sub-physiological safety information is used to reflect the physiological safety situation of the elderly during eating.

[0074] It is understandable that the eating information can be obtained during the eating time period of the elderly in the monitoring information. The eating information refers to the information collected by the collection device when the elderly eat, which belongs to a sub-information of the monitoring information. The monitoring device can also be placed at the elderly's eating position to obtain the eating information, etc., but not limited to this. Most elderly people have symptoms of dysphagia due to their age, and foreign objects often get stuck in the throat. Therefore, it is necessary to analyze the elderly's eating information to obtain the third sub-physiological safety information. The specific analysis process is shown in the subordinate steps of S240.

[0075] Such a setting can timely detect emergency situations where foreign objects are stuck in the throat of the elderly, and can ensure the safety of the elderly's eating.

[0076] In a possible implementation, in step S240, the third sub-physiological safety information in the physiological safety information is obtained according to the eating information, including: S241, when the first state is the sitting state, obtaining the eating audio information and the eating video information in the eating information, wherein the eating audio information refers to the sound information of the elderly when eating, and the eating video information refers to the video information of the elderly when eating.

[0077] It can be understood that the eating information includes eating audio information and eating video information, which can be analyzed separately or jointly to analyze the eating habits of the elderly.

[0078] Such an arrangement improves the dimension of the eating information and can improve the accuracy of the obtained third sub-physiological safety information.

[0079] S242, determining eating status information according to the eating audio information, wherein the eating status information is used to reflect whether the elderly person has a foreign object stuck in the throat.

[0080] It is understandable that when a foreign object is stuck in the throat, the human body will instinctively cough. We can analyze whether there is coughing in the audio information of eating to determine whether the elderly have a foreign object stuck in the throat.

[0081] For example, the audio information of multiple elderly people coughing can be analyzed, and the audio amplitude-time relationship diagram of the elderly people coughing can be obtained statistically. The maximum positive slope of the amplitude when the elderly people cough in each relationship diagram is recorded, and then the multiple slope values ​​are listed as a distribution diagram. According to the central theorem, the distribution diagram satisfies the normal distribution. A point is selected in the normal distribution diagram as the positive slope amplitude threshold (which can be Etc.), and the negative slope amplitude threshold is obtained by analogy to the maximum negative slope of the audio amplitude-time relationship diagram. If the audio information has a sound amplitude rising slope greater than the positive slope amplitude threshold within the human voice frequency band (100 Hz to 500 Hz) and within a predetermined time (average coughing time), and the sound amplitude falling slope is greater than the positive slope amplitude threshold, it means that the elderly cough.

[0082] For example, a deep learning model can be used to determine whether an elderly person coughs in audio information about eating.

[0083] The deep learning model can use a CNN convolutional neural network, and then obtain an audio data set including people coughing, and add some miscellaneous human voice audio data sets, so that the two data sets are half in number, and randomly select 90% of the data sets as training sets, and the remaining 10% as test sets. The training set is input to train the deep learning model. The input is the audio signal of the person in the training set, and the output is whether the person is coughing. The trained model is tested on the test set. When the accuracy rate does not meet the standard, it is retrained. When the accuracy rate meets the standard, the model training is completed. The trained deep learning model can determine whether the elderly in the audio is coughing.

[0084] Such an arrangement can improve the accuracy of judging the state of foreign matter stuck in the throat.

[0085] S243, when the eating status information indicates that the elderly person has a foreign object stuck in the throat, the time information of the foreign object stuck in the throat is obtained according to the eating video information.

[0086] It is understandable that when the foreign object is stuck in the throat seriously, it may block the trachea, resulting in insufficient air in the lungs to support the second cough after the first cough. At this time, the video information of the elderly eating can be analyzed to determine the time when the foreign object is stuck in the throat.

[0087] Exemplarily, the body skeleton of an elderly person while eating can be extracted from video information. When the tilt angle of the upper body of the body skeleton is within a preset range and is in a top-down style, it means that the foreign object stuck in the throat has not yet completely disappeared. When the upper body is upright and the tilt angle is outside the preset range, it means that the foreign object stuck in the throat has completely disappeared. Timing is performed to obtain the time information of the foreign object stuck in the throat.

[0088] For example, a deep learning model can be used to determine whether an elderly person in a video of an eating meal is in a state of having a foreign object stuck in the throat, and the duration of the foreign object stuck in the throat can be obtained by timing.

[0089] The deep learning model can use a CNN convolutional neural network, and then obtain a video data set of people in a normal eating state and a foreign object stuck in the throat state, and ensure that the number of data sets in the two states is half each, and randomly select 90% of the data sets as training sets, and the remaining 10% as test sets. The training set is input to train the deep learning model. The input is the video information of the people in the training set, and the output is the person's eating state. The trained model is tested on the test set. When the accuracy rate does not meet the standard, it is retrained. When the accuracy rate meets the standard, the model training is completed. The trained deep learning model can determine whether the elderly in the video has a foreign object stuck in the throat.

[0090] This setting improves the accuracy of the time when foreign objects are stuck in the throat and can prevent misjudgment when the foreign objects are stuck in the throat and the patient is unable to cough.

[0091] S244, determine whether the foreign object stuck in the throat time is greater than zero and less than the second alarm threshold. If it is greater than zero and less than the second alarm threshold, the third sub-physiological safety information is obtained as a yellow safety level. If the foreign object stuck in the throat time is greater than or equal to the second alarm threshold, the third sub-physiological safety information is obtained as a red safety level.

[0092] It can be understood that the time when foreign objects are stuck in the throat is a continuously increasing quantity, so the third sub-physiological safety information is continuous in time (similar to the first sub-physiological safety information, see step S222), and the safety level of the third sub-physiological safety information is determined according to the time when foreign objects are stuck in the throat.

[0093] Such a setting can not only promptly detect emergency situations where foreign objects are stuck in the throat of the elderly, but also the guardian can observe the frequency and duration of foreign objects stuck in the throat of the elderly, and can infer whether the elderly have eating-related diseases, which can improve the quality of elderly care.

[0094] S250, when the first state is the lying state, obtain the body temperature information of the elderly in the monitoring information, and obtain the fourth sub-physiological safety information in the physiological safety information according to the body temperature information. The body temperature information refers to the information including the body temperature of multiple parts of the elderly, and the fourth sub-physiological safety information is used to reflect the physiological safety of the elderly in the lying down resting state. At the same time, there can only be one sub-physiological safety information in the physiological safety information.

[0095] It is understandable that the monitoring information includes the thermal imaging of the elderly, and the body temperature information of the elderly can be obtained. When lying down, the elderly often doze off, may fall asleep in an inappropriate place, or fall asleep without covering themselves with clothes and quilts, which may cause hypothermia. Therefore, the body temperature information of the elderly can be analyzed to prevent hypothermia from occurring when the elderly fall asleep. The specific analysis process is shown in the subordinate steps of S250.

[0096] Such a setting can prevent the elderly from suffering from hypothermia when they fall asleep, and improve the dimension of their physiological safety information.

[0097] In a possible implementation, in step S250, obtaining fourth sub-physiological safety information in the physiological safety information according to the body temperature information includes: S251, when the first state is the lying state, obtain facial temperature information and exposed body temperature information in the body temperature information, wherein the facial temperature information is used to indicate the facial temperature of the elderly, and the exposed body temperature information is used to indicate the temperature of other exposed parts except the head.

[0098] It is understandable that the face is uncovered during sleep, and the temperature of the nose and eyes can be maintained within the normal temperature range when the outside temperature is low. Therefore, the facial temperature can be used to reflect whether the elderly have hypothermia, and the exposed parts are often the limbs, so the exposed part temperature can be used to reflect whether the elderly may catch a cold. The body temperature information includes the facial temperature and the exposed part temperature. The facial temperature can be the average temperature of the entire face or the temperature of a certain facial feature point (such as the nose and eyes), and the exposed part temperature can be the average temperature of the exposed part.

[0099] In this way, by dividing the body temperature information into facial temperature and exposed part temperature, the dimension and accuracy of the fourth sub-physiological safety information can be improved.

[0100] S252: If the facial temperature is lower than the lowest normal temperature threshold, the fourth sub-physiological safety information is obtained as a red safety level, wherein the lowest normal temperature threshold is used to indicate the lowest normal temperature of a normal elderly person when asleep.

[0101] It can be understood that when the facial temperature is lower than the lowest normal temperature threshold, it means that the elderly person has hypothermia during sleep, so the fourth sub-physiological safety information is determined to be a red safety level. And the fourth sub-physiological safety information is continuous in time (similar to the first sub-physiological safety information, see step S222).

[0102] Such an arrangement can improve the accuracy of determining the fourth child's physiological safety information.

[0103] S253, if the facial temperature is greater than or equal to the lowest normal temperature threshold, but the exposed body temperature is lower than the lowest normal temperature threshold, the fourth sub-physiological safety information is obtained as a yellow safety level.

[0104] It can be understood that when the facial temperature is higher than or equal to the minimum normal body temperature threshold, it means that the elderly person is not hypothermic during sleep, and when the temperature of exposed parts is lower than the minimum normal body temperature threshold, it means that the elderly person may catch a cold during sleep. Therefore, the fourth sub-physiological safety information is determined to be a yellow safety level.

[0105] Such an arrangement can improve the accuracy of determining the fourth child's physiological safety information.

[0106] S300, obtaining psychological safety information of the elderly according to the monitoring information, wherein the psychological safety information is used to reflect the psychological safety of the elderly.

[0107] It is understandable that the elderly often experience bad things due to age and social factors, such as the death of old friends and infrequent visits from children. By analyzing the behavior or activities of the elderly at specific times and places in the monitoring information (such as analyzing appetite, insomnia, etc.), it is possible to infer whether the elderly's mental state is healthy and to obtain information on their psychological safety.

[0108] Such a setting can timely discover the mental health problems of the elderly, thereby improving the quality of elderly care in this method.

[0109] In a possible implementation, in step S300, psychological safety information of the elderly is obtained according to monitoring information, including: S310, performing behavior recognition on the monitoring information to determine a second state, wherein the second state is one of an eating state, a sleeping state, and a daily state.

[0110] It can be understood that the daily state refers to other states except the eating state and the sleeping state. A specific area can be set, and when the elderly are in this area, the second state of the elderly is determined to be the eating state. Another specific area can be set, and when the elderly are in this area, the second state of the elderly is determined to be the sleeping state. The sleeping state refers to sleep in a broad sense, including the wakefulness stage before falling asleep, the sleep stage after falling asleep, and the awakening stage during sleep.

[0111] Such a setting can improve the accuracy of judging the second state of the elderly.

[0112] S320, when the second state is the eating state, obtain the food intake information and eating time information of the elderly in the monitoring information, and obtain the first sub-psychological safety information according to the food intake information and the eating time information. The food intake information is used to indicate the food intake of the elderly, the eating time information is used to indicate the eating time of the elderly, and the first sub-psychological safety information is used to reflect the appetite of the elderly.

[0113] It is understandable that the number of times the elderly move their chopsticks during eating can be obtained from the monitoring information, and the number of times the elderly move their chopsticks can be used to represent the amount of food eaten. The amount of food eaten can also be obtained by calculating the change in the elderly's food before and after eating through a visual measurement method, etc., but not limited to this, and eating time = the first time to move chopsticks - the last time to move chopsticks. The amount of food eaten and the eating time can be analyzed to obtain the first sub-psychological safety information, and the specific analysis process is shown in the subordinate steps of S320.

[0114] This setting can determine whether the elderly have a poor appetite, thereby improving the dimension and accuracy of psychological safety information.

[0115] In a possible implementation, in step S320, first sub-psychological safety information is obtained according to the food intake information and the food intake time information, including: S321, when the second state is the eating state, obtain an average eating speed according to the food intake information and the eating time information, wherein the average eating speed is used to reflect the average food intake of the elderly per unit time.

[0116] It is understandable that the typical symptom of loss of appetite is eating very slowly. Therefore, the average eating speed is obtained based on the amount of food eaten and the time of eating, and then the loss of appetite of the elderly is determined based on the average eating speed.

[0117] Such an arrangement improves the dimension of the clue information for determining the first sub-psychological safety information and improves the accuracy of the obtained first sub-psychological safety information.

[0118] S322: If the average eating speed is lower than the minimum eating speed threshold, the first sub-psychological safety information is obtained as a yellow safety level.

[0119] It can be understood that when the average eating speed is lower than the minimum eating speed threshold, it means that the elderly person has a poor appetite. The minimum eating speed threshold can be adjusted by the guardian as needed.

[0120] With this setup, different situations were analyzed separately, and the situation where the average eating speed was too low was discussed first, which improved the accuracy of the psychological safety information obtained for the first child.

[0121] S323: If the average eating speed is higher than the minimum eating speed threshold, determine whether the food intake corresponding to the food intake information is lower than the minimum food intake threshold.

[0122] It can be understood that when the average eating speed is higher than the minimum eating speed threshold, it does not mean that the elderly do not have a loss of appetite. It is also possible that the food intake is too small and the error of the average eating speed is too large, causing it to be greater than the minimum eating speed threshold. Therefore, when the average eating speed is higher than the minimum eating speed threshold, it is judged whether the food intake is lower than the minimum eating amount threshold to determine whether the elderly have a loss of appetite.

[0123] With this setup, different situations are analyzed separately, followed by a discussion of whether the average eating speed is high enough and then whether the amount of food eaten is sufficient, which improves the accuracy of the first child psychological safety information obtained.

[0124] S324, if the food intake is lower than the minimum food intake threshold, the first sub-psychological safety information is obtained as a yellow safety level.

[0125] It can be understood that when the average eating speed is higher than the minimum eating speed threshold, if the food intake is lower than the minimum food intake threshold, it also means that the elderly have poor appetite.

[0126] With this setup, different situations were analyzed separately, and finally the situation where the average eating speed was high enough but the amount of food eaten was not enough was discussed, which improved the accuracy of the psychological safety information obtained for the first child.

[0127] S330, when the second state is a sleeping state, obtaining the body movement information of the elderly in the monitoring information, and obtaining the second sub-psychological safety information according to the body movement information. The body movement information is used to reflect the number of body movements of each part of the elderly during a sleep process, and the second sub-psychological safety information is used to reflect the sleep quality of the elderly.

[0128] It can be understood that body movement refers to the movement of the elderly's body with an amplitude greater than 5 cm (other amplitudes can also be set), and a long period of continuous body movement is also counted as one body movement. The number of body movements of various parts of the elderly in the sleep state can be obtained from the monitoring information to obtain body movement information, or an acceleration sensor can be worn on the elderly to obtain body movement information. The body movement information can be analyzed to obtain the elderly's second child psychological safety information. The specific analysis steps are shown in the subordinate steps of S330.

[0129] With this setting, the cause of insomnia in the elderly is often due to psychological factors. The symptoms of insomnia caused by psychological factors are difficulty falling asleep and tossing and turning. Whether the elderly suffer from insomnia can be judged from body movement information, which improves the dimension and accuracy of psychological safety information.

[0130] In a possible implementation, in step S330, obtaining the second sub-psychological safety information according to the body movement information includes: S331, when the second state is a sleeping state, obtain limb movement information, head movement information and trunk movement information in the body movement information. The limb movement information is used to indicate the number of limb movements of the elderly, the head movement information is used to indicate the number of head movements of the elderly, and the trunk movement information is used to indicate the number of trunk movements of the elderly.

[0131] It can be understood that body movement includes limb movement, head movement and trunk movement. The effects of different body movements on insomnia are different. The number of body movements in each part can be analyzed specifically to determine whether the elderly have insomnia. The limb movement driven by the trunk movement is not counted as limb movement, and the head movement driven by the trunk movement is not counted as head movement.

[0132] This setting increases the dimension of body movement information, which is beneficial to improving the accuracy of the second child's psychological safety information.

[0133] S332, obtaining a body movement index according to the limb movement information, the head movement information and the trunk movement information, wherein the body movement index is used to reflect the quantitative value of the body movement degree of the elderly during sleep.

[0134] It can be understood that the body movement index = A1 × trunk movement times + A2 × limb movement times + A3 × head movement times. The movement degree of the trunk is the largest, followed by the limb movement, and the head movement is the smallest. The trunk movement includes the limb movement and the head movement (the limb movement driven by the trunk movement is not counted as the limb movement, and the head movement driven by the trunk movement is not counted as the head movement). Therefore, A1=0.8, A2=0.4, A3=0.3, and the remaining numbers are also acceptable, as long as A1>A2>A3>0, and A1>A2+A3 are satisfied.

[0135] This setting quantifies the degree of body movement of the elderly during sleep, which is beneficial for the subsequent step of obtaining the second sub-psychological safety information.

[0136] S333: If the body movement index is greater than the preset body movement threshold, the second sub-psychological safety information is obtained as a yellow safety level.

[0137] It can be understood that when the body movement index is greater than the preset body movement threshold, it means that the elderly person is insomniac, and the second sub-psychological safety information is obtained as a yellow safety level. The preset body movement threshold can be customized by the user.

[0138] S340, when the second state is the daily state, obtain the voice information of the elderly in the monitoring information, process the voice information through the emotion detection model, obtain the positive emotion index and the negative emotion index, and obtain the third sub-psychological safety information according to the positive emotion index and the negative emotion index. Among them, the positive emotion index is used to reflect the quantitative value of the positive emotions of the elderly in the daily state, the negative emotion index is used to reflect the quantitative value of the negative emotions of the elderly in the daily state, and the third sub-psychological safety information is used to reflect the emotional state of the elderly, and is a sub-information of the psychological safety information. Among them, at the same time, there can only be one sub-psychological safety information in the psychological safety information.

[0139] It can be understood that the voice information of the elderly in their daily state can be obtained from the monitoring information, and then the voice information in the daily state can be input into the emotion detection model to output the emotion type of the elderly through the emotion detection model. The positive emotion index = , where m refers to a total of m positive emotions, and f(n) refers to the duration of the nth positive emotion; the negative emotion index is similar and will not be described in detail. The positive emotion index and the negative emotion index can be analyzed to obtain the emotional status of the elderly over a period of time. The specific analysis process is shown in the subordinate steps of S340.

[0140] The emotion detection model can use a CNN convolutional neural network, and then obtain audio data sets including various positive emotions (such as laughter, excitement, etc.) and various negative emotions (such as anger, sadness, etc.), and ensure that the number of data sets for various emotions is equal, and randomly select 90% of the data sets as training sets, and the remaining 10% as test sets. The training set is input to train the deep learning model. The input is the audio signal of the person in the training set, and the output is the person's emotion category. The trained model is tested on the test set. When the accuracy rate does not meet the standard, it is retrained. When the accuracy rate meets the standard, the model training is completed, and the training obtains an emotion recognition model that can judge the emotion type, etc., but is not limited to this. Other methods can also be used to train the emotion detection model.

[0141] This setting quantifies the positive and negative emotions of the elderly in their daily lives, accurately reflects the emotional state of the elderly, and improves the accuracy of physiological safety information.

[0142] In a possible implementation, in step S340, obtaining third sub-psychological safety information according to the positive emotion index and the negative emotion index includes: S341, when the second state is the daily state, the positive emotion index is matched with the preset database to obtain a first emotion score, and the negative emotion index is matched with the preset database to obtain a second emotion score. The first emotion score is used to reflect the score of the elderly's positive emotions, and the second emotion score is used to reflect the score of the elderly's negative emotions.

[0143] It can be understood that the preset database includes a positive emotion score map and a negative emotion score map. The positive emotion score map is as follows: Figure 2 As shown in Figure 2, the positive emotion score increases with the increase of the positive emotion index; the negative emotion score is shown in Figure 2. Figure 3 As shown, the negative emotion scores decreased as the negative emotion index increased. Figure 2 and Figure 3 Describes the trend of positive sentiment scores and negative sentiment scores, and the specific values ​​are determined on demand.

[0144] With such a setting, the first emotion score and the second emotion score can be accurately obtained, which is helpful for determining the state of the third sub-psychological safety information of the elderly.

[0145] S342, the first emotion score and the second emotion score are added to obtain a total emotion score. If the total emotion score is lower than a preset score threshold, the third sub-psychological safety information is obtained as a yellow safety level.

[0146] It can be understood that the first emotion score can reflect the positive emotional state of the elderly, and the second emotion score can reflect the negative emotional state of the elderly. The first emotion score and the second emotion score are added to obtain the total emotion score. The total emotion score can reflect whether the emotional state of the elderly is positive. An adjustable preset score threshold can be set. When the total emotion score is lower than the preset score threshold, it means that there is a problem with the emotional state of the elderly, and the third sub-psychological safety information is obtained as a yellow safety level.

[0147] Such a setting can effectively reflect the emotional state of the elderly in daily situations and can promptly detect periods when the elderly are in a low mood.

[0148] S400: Perform safety rating according to the physiological safety information and the psychological safety information to obtain alarm information, wherein the alarm information is used to prompt the guardian and / or warn the elderly person being supervised.

[0149] It can be understood that after obtaining the physiological safety information and the psychological safety information, the next step is to conduct a safety rating on the safety information, alert the guardian or medical staff of critical situations, and alert the guardian and the elderly themselves of potential dangers. The alarm information is divided into red safety level, yellow safety level and green safety level. The specific safety rating process is shown in the subordinate steps of S400.

[0150] With this setting, different safety levels can be handled in different ways, which can improve the quality of care for the elderly.

[0151] In a possible implementation, in step S400, a safety rating is performed based on the physiological safety information and the psychological safety information to obtain alarm information, including: S410: When the physiological safety information indicates a non-green safety level, determine whether there is psychological safety information of a non-green safety level before the first time period.

[0152] It is understandable that mental health and physical health are closely related. Sometimes the cause of physical illness is a psychological problem, and the cause of psychological illness may also be a physiological problem. Therefore, it is necessary to consider the causal relationship between the two. The first time period is set to determine whether there is a causal relationship between the physiological problem and the psychological problem. When the time interval between the physiological problem and the psychological problem is within the first time period, it means that the two may have a causal relationship.

[0153] This setting takes into account the possible causal relationship between the physiological and psychological problems of the elderly, and improves the quality of elderly care.

[0154] S420: If it exists, then obtain alarm information, the safety level of the alarm information is a red safety level, and the alarm information includes sub-physiological safety information corresponding to the physiological safety information and sub-psychological safety information corresponding to the psychological safety information.

[0155] It can be understood that when physiological problems and psychological problems may be causally related, an alarm message is generated, which includes details of the corresponding physiological and psychological problems of the elderly, and the safety level of the alarm message is set to a red safety level.

[0156] This setting takes into account various health problems of the elderly, not only reducing the guardianship pressure of guardians, but also improving the elderly's retirement security.

[0157] S430: If it does not exist, then obtain alarm information, the security level of the alarm information is the security level corresponding to the physiological safety information, and the alarm information includes sub-physiological safety information corresponding to the physiological safety information.

[0158] It can be understood that when there is no causal relationship between physiological problems and psychological problems, an alarm message is generated, which includes the details of the corresponding physiological problems of the elderly, and the safety level of the alarm message is set to the safety level corresponding to the physiological safety information.

[0159] This setting reduces the guardianship pressure on guardians and improves the elderly's retirement security.

[0160] S440: When the psychological safety level is indicated as a non-green safety level, determine whether there is physiological safety information of a non-green safety level before the first time period.

[0161] It can be understood that the purpose is consistent with that of step S410, the difference is that this step takes the psychology of the elderly as the subject, and will not be repeated here.

[0162] This arrangement improves the quality of care for the elderly.

[0163] S450: If it exists, then obtain alarm information, the safety level of the alarm information is a red safety level, and the alarm information includes sub-physiological safety information corresponding to the physiological safety information and sub-psychological safety information corresponding to the psychological safety information.

[0164] It can be understood that the purpose is consistent with that of step S420, the difference is that this step takes the psychology of the elderly as the subject, and will not be repeated here.

[0165] This setting takes into account various health problems of the elderly, not only reducing the guardianship pressure of guardians, but also improving the elderly's retirement security.

[0166] S460: If it does not exist, then obtain alarm information, the safety level of the alarm information is the safety level corresponding to the psychological safety information, and the alarm information includes sub-psychological safety information corresponding to the psychological safety information.

[0167] It can be understood that the purpose is consistent with that of step S430, the difference is that this step takes the psychology of the elderly as the subject, and will not be repeated here.

[0168] This setting reduces the guardianship pressure on guardians and improves the elderly's retirement security.

[0169] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0170] Corresponding to the elderly behavior safety monitoring method described in the above embodiment, the embodiment of the present application also provides an elderly behavior safety monitoring system, and each unit of the system can implement each step of the elderly behavior safety monitoring method. Figure 4A flow chart of the elderly behavior safety monitoring system provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0171] Reference Figure 4 The system comprises: An acquisition unit, used to acquire monitoring information of the elderly, wherein the monitoring information is used to reflect the behavior and physical condition of the elderly; The first processing unit is used to obtain physiological safety information of the elderly according to the monitoring information. The physiological safety information is used to reflect the physical safety of the elderly; The second processing unit is used to obtain the psychological safety information of the elderly according to the monitoring information. The psychological safety information is used to reflect the psychological safety of the elderly; The alarm unit is used to perform safety rating according to the physiological safety information and the psychological safety information to obtain alarm information, wherein the alarm information is used to prompt the guardian and / or warn the elderly person being supervised.

[0172] It should be noted that the information interaction, execution process and other contents between the above-mentioned units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0173] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional units as needed, that is, the internal structure of the elderly behavior safety monitoring system can be divided into different functional units to complete all or part of the functions described above. The functional units in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0174] The present application also provides a device for monitoring elderly people's behavior and safety. Figure 5 This is a schematic diagram of the structure of the elderly behavior safety monitoring device provided in one embodiment of the present application. Figure 5 As shown, the control device 5 of the elderly behavior safety monitoring device of this embodiment includes: at least one processor 50 ( Figure 5 Only one is shown), at least one memory 51 ( Figure 5Only one is shown in the figure) and a computer program 52 stored in the at least one memory 51 and executable on the at least one processor 50. When the processor 50 executes the computer program 52, the control device 5 of the elderly behavior safety monitoring device implements the steps in any of the above-mentioned embodiments of the elderly behavior safety monitoring method, or the control device 5 of the elderly behavior safety monitoring device implements the functions of each unit in the above-mentioned device embodiments.

[0175] Exemplarily, the computer program 52 may be divided into one or more units, which are stored in the memory 51 and executed by the processor 50 to complete the present application. The one or more units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 52 in the control device 5 of the elderly behavior safety monitoring device.

[0176] The control device 5 of the elderly behavior safety monitoring device can be a single-chip microcomputer, a microprocessor, a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a desktop computer, a smart screen, a smart TV, or a handheld device with a wireless communication function. The control device 5 of the elderly behavior safety monitoring device can include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art can understand that Figure 5 It is only an example of the control device 5 of the elderly behavior safety monitoring equipment and does not constitute a limitation on the control device 5 of the elderly behavior safety monitoring equipment. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, buses, etc.

[0177] The processor 50 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0178] In some embodiments, the memory 51 may be an internal storage unit of the control device 5 of the elderly behavior safety monitoring device, such as a hard disk or memory of the control device 5 of the elderly behavior safety monitoring device. In other embodiments, the memory 51 may also be an external storage device of the control device 5 of the elderly behavior safety monitoring device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the control device 5 of the elderly behavior safety monitoring device. Further, the memory 51 may also include both an internal storage unit and an external storage device of the control device 5 of the elderly behavior safety monitoring device. The memory 51 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 51 may also be used to temporarily store data that has been output or is to be output.

[0179] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0180] An embodiment of the present application provides a computer program product. When the computer program product runs on a safety monitoring device for elderly behavior, the safety monitoring device for elderly behavior implements the steps in any of the above-mentioned method embodiments.

[0181] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the elderly behavior safety monitoring device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0182] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0183] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0184] In the embodiments provided in the present application, it should be understood that the disclosed elderly behavior safety monitoring method, elderly behavior safety monitoring device and elderly behavior safety monitoring equipment can be implemented in other ways. For example, the elderly behavior safety monitoring method, elderly behavior safety monitoring device and elderly behavior safety monitoring equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0185] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0186] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for monitoring elderly people's behavior safety, characterized in that: The method comprises: Acquire monitoring information of the elderly; wherein the monitoring information is used to reflect the behavior and physical condition of the elderly; According to the monitoring information, physiological safety information of the elderly is obtained; wherein the physiological safety information is used to reflect the physical safety of the elderly; According to the monitoring information, psychological safety information of the elderly is obtained; wherein the psychological safety information is used to reflect the psychological safety of the elderly; A safety rating is performed based on the physiological safety information and the psychological safety information to obtain alarm information; wherein the alarm information is used to prompt a guardian and / or warn the elderly person being supervised.

2. The method for monitoring elderly people's behavior safety as claimed in claim 1, characterized in that: The step of obtaining physiological safety information of the elderly based on the monitoring information includes: Performing action recognition on the monitoring information to determine a first state of the elderly; wherein the first state is one of a standing state, a sitting state, a lying state, and a falling state; In the case where the first state is a fall state, the limb information of the elderly person in the monitoring information is obtained, and the first sub-physiological safety information in the physiological safety information is obtained according to the limb information; wherein the limb information is used to reflect the activities of the limbs of the elderly person, and the first sub-physiological safety information is used to reflect the physiological safety status of the elderly person after falling; In the case where the first state is the standing state, the standing information of the elderly in the monitoring information is obtained, and the second sub-physiological safety information in the physiological safety information is obtained according to the standing information; wherein the standing information is used to reflect the information of the standing position of the elderly, and the second sub-physiological safety information is used to reflect the safety risk level of the standing position of the elderly; In the case where the first state is the sitting state, the eating information of the elderly in the monitoring information is obtained, and the third sub-physiological safety information in the physiological safety information is obtained according to the eating information; wherein the eating information is used to reflect the eating situation of the elderly, and the third sub-physiological safety information is used to reflect the physiological safety situation of the elderly during eating; When the first state is a lying state, the body temperature information of the elderly person in the monitoring information is obtained, and the fourth sub-physiological safety information in the physiological safety information is obtained based on the body temperature information; wherein, the body temperature information refers to information including the body temperatures of multiple parts of the elderly person, and the fourth sub-physiological safety information is used to reflect the physiological safety status of the elderly person in a lying down resting state; wherein, at the same time, only one sub-physiological safety information can exist in the physiological safety information.

3. The method for monitoring elderly people's behavior safety as claimed in claim 2, characterized in that: The obtaining the first sub-physiological safety information in the physiological safety information according to the limb information includes: In the case where the first state is a fall state, the first sub-physiological safety information is obtained as a red safety level, and the left hand motion information, the right hand motion information, the left foot motion information and the right foot motion information in the limbs information are obtained; If any of the left hand motion information, the right hand motion information, the left foot motion information and the right foot motion information indicates that the elderly person has made a motion, it is determined that the consciousness safety information in the first sub-physiological safety information reflects that the elderly person is conscious; otherwise, it is determined that the consciousness safety information in the first sub-physiological safety information reflects that the elderly person is unconscious; wherein the consciousness safety information is used to reflect whether the elderly person has self-awareness after falling; In the case where it is determined that the first sub-physiological safety information indicates that the elderly person is conscious, the body safety information in the first sub-physiological safety information is determined according to the limb movement amplitude in the limb information; wherein the limb movement amplitude refers to the movement amplitude of each of the elderly person's limbs, and the body safety information is used to reflect whether the elderly person has a fracture or dislocation after falling; When it is determined that the first sub-physiological safety information indicates that the elderly person is unconscious, if any of the left hand movement information, the right hand movement information, the left foot movement information and the right foot movement information indicates that the elderly person's limbs are stiff or convulsing, then it is determined that the central nervous system safety information in the first sub-physiological safety information reflects a central nervous system injury; wherein the central nervous system safety information is used to reflect whether the elderly person has suffered a central nervous system injury after falling.

4. The method for monitoring elderly people's behavior safety as claimed in claim 2, characterized in that: The obtaining the second sub-physiological safety information in the physiological safety information according to the standing information includes: In the case where the first state is the standing state, the standing height information, the standing slope information and the standing surface filling rate information in the standing information are obtained; wherein the standing height information is used to indicate the height of the standing position from the ground or the floor, the standing slope information is used to indicate the slope of the standing position, and the standing surface filling rate information is used to indicate the area filling rate of the plane where the standing position is located within the threshold area range; Performing weighted calculation on the value corresponding to the standing height, the value corresponding to the standing slope and the value corresponding to the standing surface filling rate to obtain a standing danger index; wherein the standing danger index is used to reflect the degree of danger of the standing position of the elderly; Determine whether the standing hazard index is greater than or equal to the first alarm threshold. If it is greater than or equal to the first alarm threshold, the second sub-physiological safety information is obtained as a yellow safety level; if it is less than the first alarm threshold, the second sub-physiological safety information is obtained as a green safety level; wherein, the first alarm threshold is used to reflect the alarm threshold size of the standing hazard index.

5. The method for monitoring elderly people's behavior safety as claimed in claim 1, characterized in that: The method of obtaining the psychological safety information of the elderly according to the monitoring information includes: Performing behavior recognition on the monitoring information to determine a second state; wherein the second state is one of an eating state, a sleeping state, and a daily state; In the case where the second state is the eating state, the food intake information and the eating time information of the elderly in the monitoring information are obtained, and the first sub-psychological safety information is obtained according to the food intake information and the eating time information; wherein the food intake information is used to indicate the food intake of the elderly, the eating time information is used to indicate the eating time of the elderly, and the first sub-psychological safety information is used to reflect the appetite of the elderly; When the second state is a sleeping state, the body movement information of the elderly in the monitoring information is obtained, and the second sub-psychological safety information is obtained according to the body movement information; wherein the body movement information is used to reflect the number of body movements of each part of the elderly during a sleep process, and the second sub-psychological safety information is used to reflect the sleep quality of the elderly; When the second state is the daily state, the voice information of the elderly in the monitoring information is obtained, and the voice information is processed through the emotion detection model to obtain a positive emotion index and a negative emotion index, and the third sub-psychological safety information is obtained according to the positive emotion index and the negative emotion index; wherein, the positive emotion index is used to reflect the quantitative value of the positive emotions of the elderly in the daily state, and the negative emotion index is used to reflect the quantitative value of the negative emotions of the elderly in the daily state, and the third sub-psychological safety information is used to reflect the emotional state of the elderly, and is a sub-information of the psychological safety information; wherein, at the same time, only one sub-psychological safety information can exist in the psychological safety information.

6. The method for monitoring elderly people's behavior safety as claimed in claim 5, characterized in that: The obtaining of the first sub-psychological safety information according to the food intake information and the food intake time information includes: In the case where the second state is an eating state, an average eating speed is obtained according to the food intake information and the eating time information; wherein the average eating speed is used to reflect the average food intake of the elderly per unit time; If the average eating speed is lower than the minimum eating speed threshold, the first sub-psychological safety information is obtained as a yellow safety level; If the average eating speed is higher than the minimum eating speed threshold, determining whether the food intake corresponding to the food intake information is lower than the minimum food intake threshold; If the food intake is lower than the minimum food intake threshold, the first sub-psychological safety information is obtained as a yellow safety level.

7. The method for monitoring elderly people's behavior safety as claimed in claim 5, characterized in that: The obtaining of the second sub-psychological safety information according to the body movement information includes: In the case where the second state is a sleeping state, obtaining limb movement information, head movement information and trunk movement information in the body movement information; wherein the limb movement information is used to indicate the number of limb movements of the elderly, the head movement information is used to indicate the number of head movements of the elderly, and the trunk movement information is used to indicate the number of trunk movements of the elderly; According to the limb movement information, the head movement information and the trunk movement information, a body movement index is obtained; wherein the body movement index is used to reflect the quantitative value of the body movement degree of the elderly during sleep; If the body movement index is greater than a preset body movement threshold, the second sub-psychological safety information is obtained as a yellow safety level.

8. The method for monitoring elderly people's behavior safety as claimed in claim 5, characterized in that: The obtaining of the third sub-psychological safety information according to the positive emotion index and the negative emotion index includes: When the second state is a daily state, the positive emotion index is matched with a preset database to obtain a first emotion score, and the negative emotion index is matched with a preset database to obtain a second emotion score; wherein the first emotion score is used to reflect the score of the elderly's positive emotions, and the second emotion score is used to reflect the score of the elderly's negative emotions; The first emotion score and the second emotion score are added together to obtain a total emotion score. If the total emotion score is lower than a preset score threshold, the third sub-psychological safety information is obtained as a yellow safety level.

9. The method for monitoring elderly people's behavior safety according to any one of claims 1 to 8, characterized in that: The step of performing safety rating according to the physiological safety information and the psychological safety information to obtain alarm information includes: When the physiological safety information indicates a non-green safety level, determining whether there is the psychological safety information of a non-green safety level before the first time period; If it exists, an alarm message is obtained, the security level of the alarm message is a red security level, and the alarm message includes sub-physiological safety information corresponding to the physiological safety information and sub-psychological safety information corresponding to the psychological safety information; If not, an alarm message is obtained, the security level of the alarm message is the security level corresponding to the physiological safety information, and the alarm message includes the sub-physiological safety information corresponding to the physiological safety information; When the psychological safety level is indicated as a non-green safety level, determining whether there is physiological safety information of a non-green safety level before a first time period; If it exists, an alarm message is obtained, the security level of the alarm message is a red security level, and the alarm message includes sub-physiological safety information corresponding to the physiological safety information and sub-psychological safety information corresponding to the psychological safety information; If it does not exist, an alarm message is obtained, the safety level of the alarm message is the safety level corresponding to the psychological safety information, and the alarm message includes sub-psychological safety information corresponding to the psychological safety information.

10. A behavior safety monitoring system for the elderly, characterized in that: include: An acquisition unit, used to acquire monitoring information of the elderly; wherein the monitoring information is used to reflect the behavior and physical condition of the elderly; A first processing unit is used to obtain physiological safety information of the elderly according to the monitoring information; wherein the physiological safety information is used to reflect the physical safety of the elderly; A second processing unit is used to obtain psychological safety information of the elderly according to the monitoring information; wherein the psychological safety information is used to reflect the psychological safety of the elderly; An alarm unit is used to perform safety rating according to the physiological safety information and the psychological safety information to obtain alarm information; wherein the alarm information is used to prompt the guardian and / or warn the elderly person under guardianship.

Images