Intelligent nursing system based on falling risk early warning

Abstract

The invention discloses an intelligent nursing system based on fall risk early warning, and the system comprises the steps: monitoring the current behavior information of a user in real time, and obtaining each behavior parameter; after obtaining each piece of behavior information, establishing a first risk early warning model, inputting each behavior parameter value, and outputting a risk value; obtaining a risk value, comparing the risk value with a risk threshold value, and judging whether the current state of the user is in a falling risk range or not; when the comparison module judges that the user is in the falling risk, corresponding intervention measures are taken; and transmitting the comparison result and the implemented intervention measures to intelligent terminal equipment of nursing personnel. A mode of combining multiple sensors is adopted, the motion state of the old people can be monitored in real time, environment information can be obtained, and therefore the falling risk can be judged more accurately; a concept of a falling risk index is introduced, the falling risk index is calculated through comprehensive analysis of motion state parameters and environment information, and an early warning mechanism is triggered according to the size of the index.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent nursing, and in particular to an intelligent nursing system based on fall risk warning. Background Art

[0002] As the problem of population aging becomes increasingly serious, the incidence of falls among the elderly is gradually increasing. Falls not only cause physical harm to the elderly, but may also lead to death, bringing serious burdens to society and families.

[0003] Most existing nursing systems rely on manual monitoring and inspection, which has the following limitations: Inability to monitor in real time: Manual patrols cannot monitor the activity status of the elderly 24 hours a day, resulting in an inability to respond in time when a fall occurs.

[0004] Insufficient early warning capabilities: Relying on manual judgment of fall risks, lacking objective and accurate data support, and limited early warning capabilities.

[0005] High resource consumption: Manual monitoring requires a lot of nursing staff and time resources and is not efficient.

[0006] Therefore, it is necessary to study an intelligent nursing system based on fall risk warning to improve nursing effect and safety. Summary of the invention

[0007] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0008] In view of the above problems existing in the existing nursing system, the present invention is proposed.

[0009] Therefore, the technical problem solved by the present invention is to solve the problems of the existing nursing system that cannot be monitored in real time, has insufficient early warning capability and consumes a lot of resources.

[0010] To solve the above technical problems, the present invention provides the following technical solutions: an intelligent nursing system based on fall risk warning, comprising the following components: a group of sensor modules, which monitor the user's current behavior information in real time through a group of signal sensors configured around the user, and obtain various behavior parameters; a data processing module, which is wirelessly connected to a group of the sensor modules, establishes a first risk warning model after obtaining various behavior information, inputs various behavior parameter values, and outputs risk values; a comparison module, which is wirelessly connected to the data processing module, compares the risk value with the risk threshold after obtaining the risk value, and determines whether the user's current state is within the risk of falling; an intervention module, which is signal-connected to the comparison module, and when the comparison module When the block determines that the user is at risk of falling, corresponding intervention measures are implemented; the communication module is connected to the comparison module and the intervention module signal, and the comparison result and the implemented intervention measures are transmitted to the smart terminal device of the nursing staff; wherein, it also includes an environmental impact module, which obtains the current environmental state of the user in real time through a preset environmental sensor monitor, obtains the corresponding environmental parameters, establishes an environmental impact model, and outputs the environmental impact value; wherein the environmental parameters obtained are specifically: an optical sensor, which obtains the illumination; a humidity sensor, which obtains the ground humidity; an obstacle recognition sensor, which obtains the obstacle ratio in the user's environment; wherein the environmental impact model is specifically:

[0011] Among them, λ is the environmental impact value; β is the illumination, lx; ε is the ground humidity, %; π is the obstacle ratio in the user's environment, %; 1.2, -2.701 and -1.34 are all adjustment constants; dx is the corresponding integral operation function.

[0012] As a preferred solution of the intelligent nursing system based on fall risk warning described in the present invention, a group of sensor modules specifically includes: a speed sensor, used to measure the user's current travel speed in real time; an acceleration sensor, used to measure the user's average travel acceleration within the current rated time in real time; an angular velocity sensor, used to measure the user's average angular velocity within the current rated time in real time.

[0013] As a preferred solution of the intelligent nursing system based on fall risk warning according to the present invention, the first risk warning model established by the data processing module is specifically:

[0014] Wherein, μ is the risk value; v is the user's current speed, m / s; a is the user's average acceleration within the current rated time, m / s²; α is the user's average angular velocity within the current rated time, rad / s; 1.88, 0.967 and 1.32 are adjustment constants; dx and dv are the corresponding integral operation functions.

[0015] As a preferred solution of the intelligent nursing system based on fall risk warning described in the present invention, the risk threshold is specifically 2.89 or 2.891 or 2.8914.

[0016] As a preferred solution of the intelligent nursing system based on fall risk warning described in the present invention, wherein: after obtaining the environmental impact value and the risk value, a comprehensive warning model is established; The comprehensive early warning model is specifically:

[0017] Among them, δ is the comprehensive risk value; μ is the risk value; λ is the environmental impact value; 1.65 and 1.03 are adjustment constants; dx is the corresponding integral operation function.

[0018] As a preferred solution of the intelligent nursing system based on fall risk warning described in the present invention, when the comprehensive risk value is higher than the comprehensive impact threshold, the intervention module is turned on.

[0019] As a preferred solution of the intelligent nursing system based on fall risk warning described in the present invention, the comprehensive impact threshold is defined as 1.09.

[0020] The present invention provides an intelligent nursing system based on fall risk warning, which has the following beneficial effects: 1. The present invention adopts a combination of multiple sensors, which can not only monitor the movement status of the elderly in real time, but also obtain environmental information, so as to more accurately judge the risk of falling; 2. The present invention introduces the concept of fall risk index. By comprehensively analyzing the motion state parameters and environmental information, the fall risk index is calculated, and the early warning mechanism is triggered according to the size of the index; 3. The present invention transmits the warning signal to the terminal of the nursing staff or related equipment by wireless communication, thus realizing real-time warning and timely intervention; 4. The present invention has a user interface module that can intuitively display the fall risk index and warning information of the elderly, making it convenient for nursing staff to take corresponding measures in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them: Figure 1 This is an overall system module diagram of the intelligent nursing system based on fall risk warning provided by the present invention. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0023] Most existing nursing systems rely on manual monitoring and inspection, which has the following limitations: Inability to monitor in real time: Manual patrols cannot monitor the activity status of the elderly 24 hours a day, resulting in an inability to respond in time when a fall occurs.

[0024] Insufficient early warning capabilities: Relying on manual judgment of fall risks, lacking objective and accurate data support, and limited early warning capabilities.

[0025] High resource consumption: Manual monitoring requires a lot of nursing staff and time resources and is not efficient.

[0026] Therefore, please refer to Figure 1 The present invention provides an intelligent care system based on fall risk warning, comprising the following components: A set of sensor modules 100 monitors the user's current behavior information in real time through a set of signal sensors arranged around the user to obtain various behavior parameters; The data processing module 200 is connected to a group of sensor modules 100 by wireless signals, and establishes a first risk warning model after acquiring information of each behavior, inputs each behavior parameter value, and outputs a risk value; The comparison module 300 is wirelessly connected to the data processing module 200, obtains the risk value and compares it with the risk threshold to determine whether the user's current state is within the risk of falling; The intervention module 400 is connected to the comparison module 300 by signal, and implements corresponding intervention measures when the comparison module 300 determines that the user is at risk of falling; The communication module 500 is signal-connected to the comparison module 300 and the intervention module 400 to transmit the comparison results and the implemented intervention measures to the smart terminal device of the nursing staff.

[0027] It should be noted that: 1. A set of sensor modules 100 are configured around the user as needed. The configuration method is not required in this solution, and is intended to fully present the user's motion state parameters; 2. The data processing module 200 and the comparison module 300 both use conventional data processing units, and no further details are given here; 3. The intervention measures taken by the intervention module 400 may specifically include: Warning Notice: When the comparison module 300 determines that the fall risk index of the user exceeds a preset threshold, the intervention module 400 triggers a warning notification.

[0028] Sound warning: The connected speaker emits an alarm to alert the user and those around him.

[0029] Vibration reminder: Use the vibration function of wearable devices (such as smart watches or bracelets) to remind users to pay attention.

[0030] Visual signal: A warning message is shown on a display or indicator light, such as a flashing red light.

[0031] Automatic call for assistance: The intervention module 400 may automatically dial a preset emergency contact number or send a distress signal to an emergency response center.

[0032] Emergency call: Integrated emergency call function, one-click dial emergency service number (such as 120).

[0033] SMS / APP notification: Send a text message containing the user's location information or push notification to emergency contacts via APP.

[0034] Environmental adjustments: Lighting control: Automatically adjust room lighting to provide appropriate light and reduce the risk of falls.

[0035] Smart furniture adjustment: such as smart beds and smart chairs, which automatically adjust to a safe position to prevent users from falling.

[0036] Voice Assistant: Activate the voice assistant to provide users with gait guidance, balance training suggestions, etc.

[0037] The voice assistant can remind users to take safety measures, such as "Please walk slowly" and "Please pay attention to the ground conditions."

[0038] Remote Monitoring: Connected with the remote monitoring system, nursing staff can remotely view the user's status in real time.

[0039] Video surveillance: If the system is equipped with a camera, the user's real-time image can be viewed remotely.

[0040] Health Monitoring: Strengthen health monitoring of users, such as heart rate, blood pressure, etc., to assess the possible health impact after a fall.

[0041] Assistive Device Activation: If the user has assistive devices (such as crutches, wheelchairs), the intervention module 400 can automatically activate the safety locking mechanisms of these devices to prevent falls.

[0042] Personalized intervention: Provide personalized intervention strategies based on the user's historical data, such as fall history, health status, etc.

[0043] 4. The communication module 500 adopts a conventional signal connection method, and each communication receiving end is connected to the same network to achieve mutual communication, which will not be described in detail here.

[0044] Additionally, the sensor module 100 can be configured on a device in use, such as a smart watch, a smart bracelet, a shoe sole, or other wearable devices.

[0045] Sensors can be distributed, for example, different sensors can be installed on the wrist, ankle, waist, etc., so as to monitor the user's behavior from multiple angles. Specifically, a set of sensor modules 100 specifically includes: Speed ​​sensor, used to measure the user's current speed in real time; The acceleration sensor is used to measure the average acceleration of the user within the current rated time in real time; The angular velocity sensor is used to measure the average angular velocity of the user within the current rated time in real time.

[0046] It should be noted that the accelerometer and gyroscope sensors can monitor the user's movement acceleration, speed, direction and angle changes in real time, thereby obtaining the user's gait, exercise intensity, fall risk and other parameters. By analyzing the data from the accelerometer and gyroscope, the user's body posture can be estimated, such as standing, sitting, walking or running.

[0047] Furthermore, the first risk warning model established by the data processing module 200 is specifically:

[0048] Wherein, μ is the risk value; v is the user's current speed, m / s; a is the user's average acceleration within the current rated time, m / s²; α is the user's average angular velocity within the current rated time, rad / s; 1.88, 0.967 and 1.32 are adjustment constants; dx and dv are the corresponding integral operation functions.

[0049] Furthermore, the current rated time may be defined as parameter information within the current 10 seconds.

[0050] It should be noted that when generating the above model, it is necessary to first clarify the three basic factors (travel speed, average travel acceleration and average angular velocity), which are the three basic expressions that comprehensively consider the user's motion state; specifically, in the model, the three basic expressions correspond to the generation of three basic formulas. The first basic formula represents the degree of influence of acceleration on the velocity parameters at the current speed, reflecting the fusion expression of acceleration and velocity; the second represents the direct expression of the current speed; the third represents the degree of influence of angular velocity on the velocity parameters at the current speed, reflecting the fusion expression of angular velocity and velocity.

[0051] Specifically, the risk threshold is 2.89 or 2.891 or 2.8914.

[0052] Furthermore, it also includes an environmental impact module 600, which obtains the current environmental state of the user in real time through a preset environmental sensor monitor, obtains the corresponding environmental parameters, establishes an environmental impact model, and outputs the environmental impact value; The environmental parameters obtained are: Optical sensor to obtain illumination; Humidity sensor, to obtain ground humidity; Obstacle recognition sensor to obtain the obstacle ratio in the user's environment; The environmental impact model is as follows:

[0053] Among them, λ is the environmental impact value; β is the illumination, lx; ε is the ground humidity, %; π is the obstacle ratio in the user's environment, %; 1.2, -2.701 and -1.34 are all adjustment constants; dx is the corresponding integral operation function.

[0054] Furthermore, after obtaining the environmental impact value and risk value, a comprehensive early warning model is established; The comprehensive early warning model is as follows:

[0055] Among them, δ is the comprehensive risk value; μ is the risk value; λ is the environmental impact value; 1.65 and 1.03 are adjustment constants; dx is the corresponding integral operation function.

[0056] Specifically, when the comprehensive risk value is higher than the comprehensive impact threshold, the intervention module 400 is activated.

[0057] Specifically, the comprehensive impact threshold is defined as 1.09.

[0058] In order to verify the effect of the present invention, the following simulation test is now provided: Purpose of the test: Verify the accuracy of the intelligent care system's early warning of fall risks.

[0059] Test method: A certain number of elderly people were selected as experimental subjects.

[0060] Under different environmental conditions (such as different lighting levels, ground humidity, and obstacle ratios), the subjects were asked to perform normal activities and activities that simulated falls.

[0061] The activities of the test subjects were monitored and the data were recorded using the smart care system.

[0062] Analyze the relationship between the system warning results and actual fall events.

[0063] Test data record: The following is an example of a simplified data table used to record and evaluate the warning effect of the system:

[0064] Result evaluation: Through the above data and analysis, the effectiveness of the intelligent care system in actual application is evaluated, its ability to accurately warn of fall risks is determined, and the system is optimized based on the test results.

[0065] The present invention provides an intelligent nursing system based on fall risk warning, which has the following beneficial effects: 1. The present invention adopts a combination of multiple sensors, which can not only monitor the movement status of the elderly in real time, but also obtain environmental information, so as to more accurately judge the risk of falling; 2. The present invention introduces the concept of fall risk index. By comprehensively analyzing the motion state parameters and environmental information, the fall risk index is calculated, and the early warning mechanism is triggered according to the size of the index; 3. The present invention transmits the warning signal to the terminal of the nursing staff or related equipment by wireless communication, thus realizing real-time warning and timely intervention; 4. The present invention has a user interface module that can intuitively display the fall risk index and warning information of the elderly, making it convenient for nursing staff to take corresponding measures in a timely manner.

[0066] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. An intelligent care system based on fall risk warning, characterized in that: Includes the following components: A set of sensor modules (100) monitors the user's current behavior information in real time through a set of signal sensors arranged around the user, and obtains various behavior parameters; A data processing module (200) is connected to a group of sensor modules (100) via wireless signals, acquires information about each behavior, establishes a first risk warning model, inputs a value of each behavior parameter, and outputs a risk value; A comparison module (300) is wirelessly connected to the data processing module (200) to obtain the risk value and compare it with the risk threshold to determine whether the user's current state is within the risk of falling; An intervention module (400) is connected to the comparison module (300) by signal, and implements corresponding intervention measures when the comparison module (300) determines that the user is at risk of falling; A communication module (500) is signal-connected to the comparison module (300) and the intervention module (400) to transmit the comparison result and the implemented intervention measures to the smart terminal device of the nursing staff; The invention also includes an environmental impact module (600), which obtains the current environmental state of the user in real time through a preset environmental sensor monitor, obtains the corresponding environmental parameters, establishes an environmental impact model, and outputs the environmental impact value; The environmental parameters obtained are specifically: Optical sensor to obtain illumination; Humidity sensor, to obtain ground humidity; Obstacle recognition sensor to obtain the obstacle ratio in the user's environment; The environmental impact model is specifically: ； Among them, λ is the environmental impact value; β is the illumination, lx; ε is the ground humidity, %; π is the obstacle ratio in the user's environment, %; 1.2, -2.701 and -1.34 are all adjustment constants; dx is the corresponding integral operation function.

2. The intelligent nursing system based on fall risk warning according to claim 1 is characterized in that: A set of sensor modules (100) specifically comprises: Speed ​​sensor, used to measure the user's current speed in real time; The acceleration sensor is used to measure the average acceleration of the user within the current rated time in real time; The angular velocity sensor is used to measure the average angular velocity of the user within the current rated time in real time.

3. The intelligent nursing system based on fall risk warning according to claim 2 is characterized in that: The first risk warning model established by the data processing module (200) is specifically: ； Wherein, μ is the risk value; v is the user's current speed, m / s; a is the user's average acceleration within the current rated time, m / s²; α is the user's average angular velocity within the current rated time, rad / s; 1.88, 0.967 and 1.32 are adjustment constants; dx and dv are the corresponding integral operation functions.

4. The intelligent nursing system based on fall risk warning according to claim 3 is characterized in that: The risk threshold is specifically 2.89 or 2.891 or 2.8914.

5. The intelligent nursing system based on fall risk warning according to claim 4 is characterized in that: After obtaining the environmental impact value and the risk value, establishing a comprehensive early warning model; The comprehensive early warning model is specifically: ； Among them, δ is the comprehensive risk value; μ is the risk value; λ is the environmental impact value; 1.65 and 1.03 are adjustment constants; dx is the corresponding integral operation function.

6. The intelligent nursing system based on fall risk warning according to claim 5 is characterized in that: When the comprehensive risk value is higher than the comprehensive impact threshold, the intervention module (400) is activated.

7. The intelligent nursing system based on fall risk warning according to claim 6 is characterized in that: The comprehensive impact threshold is defined as 1.09.

Images