Intelligent old-age care service system based on LORA technology

Abstract

The invention discloses an intelligent old-age care service system based on LORA technology, comprising a management center which comprises a data acquisition unit, a data processing unit, a data abnormity judgment unit and an emergency call unit. The data acquisition unit comprises a health data acquisition module, an emotion data acquisition module, a behavior acquisition module and a body feature acquisition module; the data processing unit comprises a data analysis module, a central processing unit, a storage module, an arithmetic logic module and a data correction module; the data anomaly judgment unit comprises an anomaly detection module, an early warning module, a feedback cycle module, a threshold setting module, a model training module and a daily record report module, and the emergency call unit comprises a trigger device, an LORA gateway, a positioning module, an alarm confirmation module and an image transmission module. The method has the advantages of high intelligent degree, high efficiency, high accuracy and the like.

Description

Technical Field

[0001] The present invention relates to the field of smart elderly care technology, and in particular to a smart elderly care service system based on LORA technology. Background Art

[0002] With the intensification of the aging trend of the population, the demand for elderly care services continues to grow; as a new model of elderly care service, smart elderly care service uses the Internet of Things technology to achieve all-round management and services in terms of life, health, safety, etc. of the elderly, which can realize the informatization and intelligence of elderly care services and effectively improve the quality of elderly care services. Due to the large number of elderly people in elderly care institutions, it is first necessary to cluster the elderly with similar physical index data into one category, and then arrange appropriate nursing services for them. In the prior art, the OPTICS clustering method is adopted to obtain the distance between the elderly's physical indexes by calculating the Euclidean distance, cluster the elderly with similar physical index data, and then arrange appropriate nursing services; however, since the correlation between different physical index data of the elderly may be different, the direct calculation of the Euclidean distance fails to obtain the accurate distance between the elderly's physical index data, resulting in poor clustering effect and low accuracy of smart elderly care service management. The use of cameras to monitor the daily life of the elderly has a large monitoring blind spot due to the need for personal privacy; it is necessary to observe the video data manually, which is costly on the one hand, and once the observer is negligent, it is easy to cause an accident; ignoring the physiological needs of the elderly, the customer experience is poor. The information collection of the elderly in nursing homes is not comprehensive, and the authenticity of the alarm information cannot be judged intelligently. It is possible that the elderly will send a distress message to the management center due to accidental touch, which will increase the false alarm rate.

[0003] Therefore, it is necessary to provide a smart elderly care service system based on LORA technology to solve the above technical problems. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract of the specification and the title of the invention of this application to avoid blurring the purpose of this section, the abstract of the specification and the title of the invention, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a smart elderly care service system based on LORA technology, including a management center, the management center includes a data acquisition unit, a data processing unit, a data abnormality judgment unit and an emergency call unit, the data acquisition unit includes a health data acquisition module, an emotional data acquisition module, a behavior acquisition module and a physical feature acquisition module; the health data acquisition module is used to collect the initial health data of the elderly in the nursing home; the emotional data acquisition module is used to collect the initial emotional data of the elderly in the nursing home; the behavior acquisition module is used to collect the initial behavior data of the elderly in the nursing home; the physical feature acquisition module is used to collect The initial vital sign data of the elderly in the nursing home are collected; the data collected by the data collection unit is fed back to the data processing unit in real time; the data processing unit includes a data analysis module, a central processing unit, a storage module, an operation logic module and a data correction module; the data analysis module is used to analyze the data collected by the data collection unit, the central processing unit is connected to the data analysis module, and the data collected by the data collection unit is analyzed and processed, the storage module and the operation logic module are connected to save the collected data, and the data is processed by mathematical operations and logical operations, and the data correction module is based on the collected initial health data and initial behavior data , correct the initial emotion data to obtain corrected emotion data; correct the initial behavior data based on the collected initial health data and initial emotion data to obtain corrected behavior data; correct the initial health data based on the collected initial behavior data and initial emotion data to obtain corrected health data; the data abnormality judgment unit includes an abnormality detection module, an early warning module, a feedback loop module, a threshold setting module, a model training module and a daily record reporting module, the abnormality detection module is connected to the early warning module, and the data in the data processing unit is applied with the trained model to detect abnormal conditions in the data in real time or in batches, and to issue an early warning for abnormal data; the threshold setting module is used to distinguish normal The threshold or decision boundary of normal data and abnormal data is formed, and the model training module is connected with the daily record reporting module, and the historical data is trained for the model of abnormality detection through statistical methods, machine learning algorithms or deep learning frameworks; the emergency call unit includes a trigger device, a LORA gateway, a positioning module, an alarm confirmation module and an image transmission module. The LORA gateway is connected with the positioning module and the image transmission module to transmit the distress information to the management center. At the same time, the early warning module in the data abnormality judgment unit starts to sound an alarm, which is realized through the LORA gateway through cellular networks, satellite communications, Wi-Fi, etc., and is responsible for sending emergency call signals to the management center or designated contacts.

[0006] As a preferred solution of the smart elderly care service system based on LORA technology described in the present invention, the trigger device includes a manual button, voice activation and automatic sensing.

[0007] As a preferred solution of the smart elderly care service system based on LORA technology described in the present invention, the data acquisition unit is a wearable device integrating several sensors, environmental detection equipment and emergency call equipment. The types of sensors include at least heart rate sensors, blood oxygen sensors, blood pressure sensors and pedometer sensors, which can monitor the physical condition of the elderly in real time. The environmental detection equipment detects environmental parameters such as air quality, temperature and humidity, and harmful gases to ensure that the elderly care environment is comfortable and safe.

[0008] As a preferred solution of the smart elderly care service system based on LORA technology described in the present invention, the emotion data acquisition module collects facial image data in real time, and performs expression-based image analysis on the facial image data; the behavior acquisition module collects behavior image data in real time, including abnormal behavior and normal behavior; the body feature acquisition module collects body feature image data in real time, and the body feature image data includes: standing time, walking time, sitting time and lying time.

[0009] As a preferred solution of the smart elderly care service system based on LORA technology described in the present invention, the data abnormality judgment unit, based on the standard data of the threshold setting module and the model training module, brings the corrected data into the threshold setting module and the model training module, calculates a judgment value through the operation logic module, and compares the judgment value with the preset second threshold range. If it is outside the second threshold range, it is judged that the elderly has abnormal behavior, otherwise, it is judged that the elderly's behavior is not abnormal. Its mathematical expression formula is as follows:

[0010] Y=M(X)

[0011] Among them, Y is the judgment value, M is the model, and X is the feature vector;

[0012] For the threshold setting, a range of "normal" behavior is set as the second threshold range, based on an interval {Y min ,Y max}, where Y min With Y max Represent the lowest and highest judgment values ​​of normal behavior respectively;

[0013] For behavioral judgment, if Y < Y min or Y>Y max : It is believed that the behavior of the elderly is abnormal;

[0014] If Y min ≤Y≤Y max: The behavior of the elderly is considered to be within the normal range.

[0015] As a preferred solution of the smart elderly care service system based on LORA technology described in the present invention, the management center checks the health data of the elderly in real time through mobile applications or management platforms, and receives abnormal alarms and health reports.

[0016] The beneficial effects of the present invention are as follows: the data acquisition unit, data processing unit, data anomaly judgment unit and emergency call unit are connected with the management center and the elderly's sensor equipment through LORA technology, so as to realize 24-hour health monitoring of hospitalized elderly or elderly in nursing homes. Low-latency data transmission can be realized through LORA technology to ensure the safety of the elderly; environmental information is sent to the LORA gateway and data analysis is performed through the cloud server. If there is any abnormality, the nursing staff will be notified immediately to ensure the health of the elderly's living environment. The data anomaly judgment unit improves the accuracy, real-time and stability of the alarm call, reduces the false alarm rate, and ensures the safety and efficiency of the intelligent elderly care service system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0018] in:

[0019] Figure 1 This is a schematic diagram of the connections between the various units of the management center of a smart elderly care service system based on LORA technology disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, 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 accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0023] Furthermore, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0024] Example 1

[0025] Reference Figure 1The first embodiment of the present invention is a smart elderly care service system based on LORA technology, including a management center, the management center includes a data acquisition unit, a data processing unit, a data abnormality judgment unit and an emergency call unit, the data acquisition unit includes a health data acquisition module, an emotional data acquisition module, a behavior acquisition module and a physical feature acquisition module; the health data acquisition module is used to collect the initial health data of the elderly in the nursing home; the emotional data acquisition module is used to collect the initial emotional data of the elderly in the nursing home; the behavior acquisition module is used to collect the initial behavior data of the elderly in the nursing home; the physical feature acquisition module is used to collect the elderly in the nursing home The data collected by the data acquisition unit is fed back to the data processing unit in real time; the data processing unit includes a data analysis module, a central processing unit, a storage module, an operation logic module and a data correction module; the data analysis module is used to analyze the data collected by the data acquisition unit, the central processing unit is connected to the data analysis module, and analyzes and processes the data collected by the data acquisition unit, the storage module and the operation logic module are connected to save the collected data, and the data is processed by mathematical operations and logical operations, and the data correction module will be based on the collected initial health data and initial behavior data. The data is corrected to obtain corrected emotional data; the initial behavioral data is corrected based on the collected initial health data and initial emotional data to obtain corrected behavioral data; the initial health data is corrected based on the collected initial behavioral data and initial emotional data to obtain corrected health data; the data abnormality judgment unit includes an abnormality detection module, an early warning module, a feedback loop module, a threshold setting module, a model training module and a daily record reporting module, the abnormality detection module is connected to the early warning module, and the data in the data processing unit is applied with the trained model to detect abnormal conditions in the data in real time or in batches, and to issue an early warning for abnormal data; the threshold setting module is used to distinguish normal data The model training module is connected to the daily record reporting module, and the historical data is trained to form a model for abnormal detection through statistical methods, machine learning algorithms or deep learning frameworks; the emergency call unit includes a trigger device, a LORA gateway, a positioning module, an alarm confirmation module and an image transmission module. The LORA gateway is connected to the positioning module and the image transmission module, and transmits the call information to the management center. At the same time, the early warning module in the data abnormality judgment unit starts to sound an alarm, which is implemented through the LORA gateway through cellular networks, satellite communications, Wi-Fi, etc., and is responsible for sending emergency call signals to the management center or designated contacts. The trigger device includes manual buttons, voice activation and automatic sensing. The data acquisition unit includes a wearable device: with sensors such as heart rate, blood oxygen and pedometers to monitor the physical condition of the elderly in real time. And it has a voice intercom function.Environmental detection equipment: It can detect environmental parameters such as air quality, temperature, humidity and harmful gases, and ensure that the elderly care environment is comfortable and safe. Emergency call equipment: It is equipped with an emergency call button. If the elderly encounter an emergency, they can call for help with one click. When in use, it can realize 24-hour health monitoring of hospitalized elderly people or elderly people in nursing homes. Through LORA technology, low-latency data transmission can be achieved to ensure the safety of the elderly. The elderly can wear wearable devices to monitor the physical condition of the elderly in real time, and transmit the data to the LORA gateway and analyze the data through the cloud server. If there is any abnormality, the caregiver will be notified immediately to ensure the health of the elderly. If the elderly encounter an emergency, they can call for help with one click. Since the device has an intercom function, the caregiver can use the intercom function to remotely remind the elderly with voice. For example, if it is detected that the elderly have not gotten out of bed for a long time, remote voice reminders can be made, or intimate greetings can be made. If the elderly are inconvenient to move, they can also find caregivers through voice intercom. For example, if the elderly are thirsty, they can directly send voice to the caregiver through the intercom to let the caregiver take it. Due to the ultra-low power consumption of LORA, the frequency of battery replacement of the device can be reduced. Environmental monitoring equipment can be installed in the living environment of the elderly, and environmental information can be sent to the LORA gateway and analyzed through the cloud server. If there is any abnormality, the nursing staff will be notified immediately to ensure the health of the elderly's living environment. Emergency call equipment can be installed in the elderly's bedside and bathroom and other places where the elderly are active. If the elderly encounter an emergency, they can immediately call for help with one click. Community elderly care: There are relatively many elderly people in the community, and LORA technology can be used to establish a unified health monitoring system to improve the level of community elderly care.

[0026] In order to better understand the changing trend of body indicators over time, the present invention obtains multiple curve segments of each body indicator curve according to the changing trend of each body indicator curve; matches two body indicator curves as a matching pair to obtain multiple matching curve segments of each curve segment between the two body indicator curves, which helps to reduce the deviation caused by the difference in data volume and improve the accuracy of analysis; obtains the local correlation between each pair of body indicator curves of each elderly person according to the slope difference and the number of matches between each curve segment and the corresponding matching curve segment, and has a deeper understanding of the health status of each elderly person by analyzing the changing characteristics between the body indicators; obtains the overall correlation between each pair of body indicators according to the local correlation between each pair of body indicator curves of all elderly people, evaluates the correlation between the body indicators of all elderly people, and provides a more comprehensive correlation Analysis of physical indicators; According to the overall correlation between physical indicators, highly correlated indicator pairs are screened out, and the correlation between each physical indicator and other physical indicators is obtained, which is helpful to understand the relationship between different physical indicators and identify physical indicators with significant correlation effects on the elderly; According to the correlation between each physical indicator and other physical indicators and the number of corresponding highly correlated indicator pairs, the weight value of each physical indicator is obtained, which reflects the importance of each physical indicator to the health status of the elderly; At each moment, according to the difference in physical indicator data between each elderly person in each dimension and the weight value of the corresponding physical indicator, the physical indicator distance between each elderly person is obtained, which more accurately highlights the physical health differences between the elderly; All elderly people are clustered, and elderly care service management is performed, and elderly people with similar characteristics and needs are classified into the same group, so as to more effectively perform elderly care service management. The present invention improves the clustering effect and optimizes the efficiency and quality of elderly care services by obtaining the accurate distance between the physical indicator data of the elderly.

[0027] At the same time, in order to improve the accuracy of abnormal data alarm, the present invention uses a data abnormality judgment unit to judge and analyze the abnormal alarm data. Based on the standard data of the threshold setting module and the model training module, the corrected data is brought into the threshold setting module and the model training module, and a judgment value is calculated by the operation logic module. The judgment value is compared with the preset second threshold range. If it is outside the second threshold range, it is judged that the elderly has abnormal behavior. Otherwise, it is judged that the elderly's behavior is not abnormal. Its mathematical expression formula is as follows:

[0028] Y=M(X)

[0029] Among them, Y is the judgment value, M is the model, and X is the feature vector;

[0030] For the threshold setting, a range of "normal" behavior is set as the second threshold range, based on an interval {Y min ,Ymax}, where Y min With Y max Represent the lowest and highest judgment values ​​of normal behavior respectively;

[0031] For behavioral judgment, if Y < Y min or Y>Y max : It is believed that the behavior of the elderly is abnormal;

[0032] If Y min ≤Y≤Y max : The behavior of the elderly is considered to be within the normal range.

[0033] The management center can check the health data of the elderly in real time through mobile applications or management platforms, and receive abnormal alarms and health reports. The alarm data and the person who made the alarm will be automatically recorded and archived. According to the data collected by the data acquisition unit, the physical condition of the elderly can be judged to make timely adjustments and intelligent and reasonable arrangements. The abnormal monitoring module uses the trained model to detect abnormalities in the data in real time or in batches. Commonly used abnormality detection methods include but are not limited to:

[0034] Statistical methods (such as Z-Score, box plot)

[0035] Time series analysis (such as ARIMA models)

[0036] Machine learning methods (e.g., Isolation Forest, Support Vector Machines)

[0037] Deep learning methods (such as autoencoders)

[0038] The positioning module uses GPS, Beidou or other positioning technologies to determine the location of the emergency, and sends the location information along with the emergency call to the rescue personnel. When the relevant rescue personnel of the management center receive the rescue information, they can click the confirmation button to prevent the alarm from being sounded. At the same time, the nearby monitoring equipment will track and locate the alarm personnel, and the rescue personnel can remotely call the rescue personnel through the monitoring equipment.

[0039] In this embodiment, different abnormal behaviors correspond to different abnormal troubleshooting task generation templates. The content filled in the abnormal troubleshooting report is evaluated based on whether the problem corresponding to the abnormal behavior can be solved. If it can be solved, the corresponding abnormal troubleshooting task is completed. If the abnormal behavior is still not solved after uploading the abnormal troubleshooting report, the supervision module is started, and the supervisor is notified based on the GSM communication module to assist in the abnormal troubleshooting task. It also includes: a safety range limitation module, which is used to define different safety activity ranges according to different elderly people, and then generate corresponding safety activity maps according to the safety activity range. When the positioning data fed back by the elderly is about to exceed or exceeds the preset safety range, the early warning module is started to remind the management personnel to communicate with the elderly to guide the elderly back to the safe activity range or to arrive at the current location of the elderly in time to guide the elderly back to the safe activity range.

[0040] LoRa gateways are usually deployed in fixed locations outdoors or indoors, and can cover terminal devices within a few kilometers. These terminal devices can be various types of sensors or other IoT devices used in a variety of fields such as monitoring environmental data, asset tracking, and smart city applications. LoRa gateways are designed to provide reliable, low-cost long-range communication solutions suitable for large-scale IoT deployments.

[0041] In summary, when analyzing and calculating the distance, the present invention considers and calculates in segments, and fully screens and analyzes, so that the calculation results are more accurate and the assignment instructions are issued more timely. It has the advantages of high intelligence, high efficiency, and high accuracy.

[0042] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0043] It will be appreciated that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will be a routine task of design, fabrication, and production for those of ordinary skill having the benefit of this disclosure without undue experimentation.

[0044] 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 may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A smart elderly care service system based on LORA technology, including a management center, characterized in that: The management center includes a data collection unit, a data processing unit, a data abnormality judgment unit and an emergency call unit, and the data collection unit includes a health data collection module, an emotional data collection module, a behavior collection module and a physical feature collection module; The health data collection module is used to collect initial health data of the elderly in the nursing home; the emotion data collection module is used to collect initial emotion data of the elderly in the nursing home; The behavior collection module is used to collect initial behavior data of the elderly in the nursing home; The body feature acquisition module is used to collect the initial data of the vital signs of the elderly in the nursing home; the data collected by the data acquisition unit is fed back to the data processing unit in real time; the data processing unit includes a data analysis module, a central processing unit, a storage module, an operation logic module and a data correction module; the data analysis module is used to analyze the data collected by the data acquisition unit, the central processing unit is connected to the data analysis module, and analyzes and processes the data collected by the data acquisition unit, the storage module and the operation logic module are connected to save the collected data, and the data is processed by mathematical operations and logical operations, the data correction module will correct the initial emotional data based on the collected initial health data and initial behavior data to obtain corrected emotional data; correct the initial behavior data based on the collected initial health data and initial emotion data to obtain corrected behavior data; correct the initial health data based on the collected initial behavior data and initial emotion data to obtain corrected health data; the data abnormality judgment module The fault detection unit includes an anomaly detection module, an early warning module, a feedback loop module, a threshold setting module, a model training module and a daily record reporting module. The anomaly detection module is connected to the early warning module, and the data in the data processing unit is applied with the trained model to detect anomalies in the data in real time or in batches, and an early warning is issued for the abnormal data; the threshold setting module is used to distinguish the threshold or decision boundary between normal data and abnormal data. The model training module is connected to the daily record reporting module, and the historical data is trained for the model of anomaly detection through statistical methods, machine learning algorithms or deep learning frameworks; the emergency call unit includes a trigger device, a LORA gateway, a positioning module, an alarm confirmation module and an image transmission module. The LORA gateway is connected to the positioning module and the image transmission module, and transmits the distress information to the management center. At the same time, the early warning module in the data anomaly judgment unit starts to sound an alarm, which is realized through the LORA gateway through cellular networks, satellite communications, and Wi-Fi, and is responsible for sending emergency call signals to the management center or designated contacts.

2. The smart elderly care service system based on LORA technology according to claim 1 is characterized by: The triggering device includes a manual button, voice activation and automatic sensing.

3. The smart elderly care service system based on LORA technology according to claim 1 is characterized by: The data acquisition unit is a wearable device that integrates several sensors, environmental detection equipment and emergency call equipment. The types of sensors include at least heart rate sensors, blood oxygen sensors, blood pressure sensors and pedometer sensors, which can monitor the physical condition of the elderly in real time. The environmental detection equipment detects environmental parameters such as air quality, temperature and humidity, and harmful gases to ensure that the elderly care environment is comfortable and safe.

4. The smart elderly care service system based on LORA technology according to claim 1 is characterized by: The emotion data acquisition module acquires facial image data in real time and performs expression-based image analysis on the facial image data. The behavior acquisition module acquires behavior image data in real time, including abnormal behavior and normal behavior. The body feature acquisition module acquires body feature image data in real time, and the body feature image data includes: standing time, walking time, sitting time and lying time.

5. According to claim 1, the smart elderly care service system based on LORA technology is characterized by: The data abnormality judgment unit, based on the standard data of the threshold setting module and the model training module, brings the corrected data into the threshold setting module and the model training module, calculates a judgment value through the operation logic module, and compares the judgment value with the preset second threshold range. If it is outside the second threshold range, it is judged that the elderly has abnormal behavior, otherwise, it is judged that the elderly's behavior is not abnormal. Its mathematical expression formula is as follows: Y=M(X) Among them, Y is the judgment value, M is the model, and X is the feature vector; For the threshold setting, a range of "normal" behavior is set as the second threshold range, based on an interval {Y min ,Y max }, where Y min With Y max Represent the lowest and highest judgment values ​​of normal behavior respectively; For behavioral judgment If Y < Y min or Y>Y max : It is believed that the behavior of the elderly is abnormal; If Y min ≤Y≤Y max : The behavior of the elderly is considered to be within the normal range.

6. The smart elderly care service system based on LORA technology according to claim 1 is characterized by: The management center can check the health data of the elderly in real time through mobile applications or management platforms, and receive abnormal alarms and health reports.

Images