Care automation platform

Abstract

This invention provides an automated care platform, comprising: a system host, a gateway, a Bluetooth wearable device, one or more millimeter-wave radars, one or more network-connected surveillance cameras (IP cameras), and a cloud database. Patient location information acquired by the Bluetooth wearable device, patient image data acquired by the network-connected surveillance cameras, and detection signals of patient movements or postures acquired by the millimeter-wave radar are all transmitted to the system host via the gateway, and then uploaded to the cloud database for fall detection calculations and judgments.

Description

Technical Field

[0001] This invention relates to an automated care platform, and more particularly to an automated care platform for 24 / 7 real-time monitoring of people with mobility impairments. Prior Technology

[0002] Existing fall detection systems cannot provide a comprehensive, real-time monitoring solution for patients in hospitals to prevent falls. Furthermore, traditional monitoring relies on reports from patients or caregivers, delaying rescue efforts.

[0003] Therefore, how to solve the above problems is an important issue that the industry needs to face and resolve. Summary of the Invention

[0004] In view of this, the purpose of this invention is to achieve all-weather automatic monitoring and alarm functions through Bluetooth wearable devices, network-connected IP cameras, and millimeter-wave radar. Furthermore, it aims to construct an automated care platform using Bluetooth wearable devices, IP cameras, millimeter-wave radar, gateways, system hosts, and cloud databases.

[0005] The fall detection system disclosed herein utilizes Bluetooth wearable devices, IP cameras, and millimeter-wave radar to achieve 24 / 7 automatic monitoring, promptly identifying fall events and notifying healthcare personnel. The use of millimeter-wave radar technology in a private space protects patient privacy. A cloud-based database records and analyzes data to help develop preventative measures. Innovations such as multimodal monitoring technology, seamless integration of multiple devices, and intelligent data management ensure the system's accuracy and effectiveness, enhancing patient safety.

[0006] Based on the foregoing, one embodiment of this disclosure provides an automated care platform, comprising: a system host; a gateway; a Bluetooth wearable device, mounted on a patient within a medical facility, for transmitting the patient's location information indoors to the system host via the gateway; one or more millimeter-wave radars, mounted on the ceiling of the ward, for acquiring detection signals of the patient's movements or postures, and transmitting these signals via WiFi through the gateway to the system host for fall detection calculations; one or more network-type surveillance cameras (IP cameras), mounted in a public area outside the ward, for acquiring image data of the patient, and transmitting this data via WiFi through the gateway to the system host for fall detection calculations; and a cloud database for storing image data and detection signals recorded by the network-type surveillance cameras and the millimeter-wave radars at different locations over a period of time, for subsequent analysis and retrieval.

[0007] According to one or more embodiments of this disclosure, the cloud database is a cloud computing platform (AWS).

[0008] According to one or more embodiments of this disclosure, the network surveillance camera utilizes machine learning and human backbone tracking technology for fall detection.

[0009] According to one or more embodiments of this disclosure, the Bluetooth wearable device is equipped with a patch antenna, and the gateway is used for triangulation to calculate the specific location of the Bluetooth wearable device.

[0010] This disclosure also discloses an automated care platform, comprising: a system host, a gateway, a Bluetooth wearable device, one or more millimeter-wave radars, one or more network surveillance cameras (IP cameras), and a cloud database; wherein, patient location information obtained by the Bluetooth wearable device, patient image data obtained by the network surveillance camera, and detection signals of patient movements or postures obtained by the millimeter-wave radar are all transmitted to the system host via the gateway, and then uploaded to the cloud database for fall recognition calculation and judgment.

[0011] According to one or more embodiments of this disclosure, the cloud database is a cloud computing platform (AWS).

[0012] According to one or more embodiments of this disclosure, the network surveillance camera utilizes machine learning and human backbone tracking technology for fall detection.

[0013] According to one or more embodiments of this disclosure, the Bluetooth wearable device is equipped with a patch antenna, and the gateway is used for triangulation to calculate the specific location of the Bluetooth wearable device.

[0014] This disclosure also discloses an automated care platform, comprising: a system host; a gateway; a Bluetooth wearable device, configured on a patient within a medical facility, for transmitting the patient's location information indoors to the system host via the gateway; one or more millimeter-wave radars, configured on the ceiling of the ward, for acquiring detection signals of the patient's movements or postures, and transmitting them to the system host via WiFi through the gateway for fall detection calculations; one or more network-type surveillance cameras (IP cameras), configured in a public area outside the ward, for acquiring image data of the patient, and transmitting it to the system host via WiFi through the gateway for fall detection calculations; and a cloud database for storing image data and detection signals recorded by the network-type surveillance cameras and the millimeter-wave radars at different locations over a period of time for subsequent analysis and retrieval; wherein the network-type surveillance cameras utilize machine learning and human skeleton tracking technology for fall detection; wherein the Bluetooth wearable device is equipped with a patch antenna, and the gateway is used for triangulation to calculate the specific location of the Bluetooth wearable device.

[0015] This disclosure further discloses an automated care platform, comprising: a system host, a gateway, a Bluetooth wearable device, one or more millimeter-wave radars, one or more network-connected surveillance cameras (IP cameras), and a cloud database; wherein, patient location information obtained by the Bluetooth wearable device, patient image data obtained by the network-connected surveillance cameras, and detection signals of patient movements or postures obtained by the millimeter-wave radar are all transmitted to the system host via the gateway, and then uploaded to the cloud database for fall detection calculation and judgment; This network-based surveillance camera utilizes machine learning and human backbone tracking technology for fall detection; The device is equipped with a patch antenna, and the gateway is used for triangulation to calculate the exact location of the Bluetooth wearable device. Simple Explanation of the Diagram

[0016] Figure 1 is a schematic diagram of a care automation platform according to an embodiment of the present invention.

[0017] Figure 2 is a flowchart of the operation of the care automation platform in one embodiment of the present invention.

[0018] Figure 3 is a schematic diagram of the hardware architecture of the care automation platform in one embodiment of the present invention.

[0019] Figure 4 is a flowchart of the operation of the care automation platform in a specific situation according to an embodiment of the present invention.

[0020] Figure 5 is a flowchart of the operation of the care automation platform in a specific situation according to another embodiment of the present invention.

[0021] Figure 6 is a flowchart of the operation of the care automation platform in a specific situation according to another embodiment of the present invention. Implementation

[0022] The following disclosure provides different embodiments or examples to establish different features of the provided subject matter. The specific examples of the components and arrangements described below are for simplification and are not intended to constitute limitation; the size and shape of the components are not limited by the scope or values ​​disclosed, but may depend on the manufacturing conditions or desired characteristics of the components. For example, the technical features of the invention are described using cross-sectional views, which are schematic diagrams of idealized embodiments. Therefore, differences in the shapes shown in the drawings due to manufacturing processes and / or tolerances are foreseeable and should not be limiting.

[0023] Furthermore, spatial relative terms, such as "below," "under," "lower than," "above," and "higher than," are used to easily describe the relationship between elements or features depicted in the diagram. In addition, spatial relative terms include not only the directions depicted in the diagram but also the different directions in which the elements are used or operated.

[0024] First, please refer to Figure 1, which is a schematic diagram of a care automation platform according to an embodiment of the present invention. One embodiment of the present invention provides a care automation platform to ensure the safety of patients in hospitals.

[0025] As shown in Figure 1, in one embodiment of the present invention, the care automation platform 100 is a high-efficiency fall detection system, comprising: a system host 50, a gate 40, a Bluetooth wearable device 10, one or more millimeter-wave radars 30, one or more network surveillance cameras (IP cameras) 20, a cloud database 70, and an alarm device 60.

[0026] A Bluetooth wearable device 10 is worn by a patient in a medical setting to transmit the patient's location information indoors to the system host 50 via Bluetooth through a gateway 40. In one embodiment of the invention, the Bluetooth wearable device 10 may be a security bracelet with a Bluetooth Low Energy (BLE) module. In other embodiments of the invention, the Bluetooth wearable device 10 may be a Bluetooth Low Energy (BLE) module mounted on slippers or thermal underwear.

[0027] One or more millimeter-wave radars 30 are mounted on the ceiling of the ward to detect the patient's movements or postures. These signals are transmitted via WiFi through a gateway 40 to the system host 50 for fall detection calculations. In an embodiment of the present invention, the frequency of the one or more millimeter-wave radars 30 is 60 GHz.

[0028] One or more network surveillance cameras (IP cameras) 20 are installed in the public area outside the ward to acquire image data of patients and transmit it to the system host 50 via WiFi through the gateway 40 for fall detection calculation.

[0029] The cloud database 70 is used to store image data and detection signals recorded by network surveillance cameras 20 and millimeter-wave radar 30 at different locations over a period of time, for subsequent analysis and querying. In an embodiment of the present invention, the gateway 40, in addition to receiving patient location information from the Bluetooth wearable device 10 via Bluetooth, is also responsible for receiving WiFi signals from the network surveillance camera (IP camera) 20 and the millimeter-wave radar 30, and transmitting these signals to the system host 50, and then to the cloud database 70.

[0030] The system host 50, as the core component, receives image and radar data from the gate 40 and performs comprehensive analysis. If the host detects a fall, it will immediately notify medical personnel on the screen. As shown in Figure 1, the alarm device 60 receives the fall identification results from the system host 50 and issues an alarm message.

[0031] In an embodiment of the present invention, the care automation platform, through the collaborative work of Bluetooth wearable devices, IP cameras, millimeter-wave radar and cloud databases, enables 24 / 7 fall monitoring of patients in hospitals and can promptly notify medical staff to take measures, greatly improving patient safety.

[0032] Next, please refer to Figures 1 and 2. Figure 2 is a flowchart of the operation of the care automation platform in one embodiment of the present invention. As shown in Figure 2, in one embodiment of the present invention, the operation of the care automation platform 100 includes steps S1, S2, S3, S4, S5, S6, S7, and S8.

[0033] Step S1 is the start step. In step S1, the care automation platform 100 starts up and prepares to collect and process data.

[0034] Step S2 is the data collection step. In step S2, the system collects data from various Bluetooth wearable devices 10, a network-based IP camera 20, and a millimeter-wave radar 30. The various Bluetooth wearable devices 10 are respectively installed on the patient's wristband, slippers, and sanitary clothing, and the network-based IP camera 20 is installed on the ceiling of the public area, while the millimeter-wave radar 30 is installed on the ceiling of the ward.

[0035] Step S3 is the data transmission step. In step S3, the collected data is transmitted to the system host 50 through the gateway 40. Data from the Bluetooth wearable device 10 is transmitted to the gateway 40 via Bluetooth, while data from the network surveillance camera (IP camera) 20 and the millimeter-wave radar 30 are transmitted to the gateway 40 via WiFi.

[0036] Step S4 is the data processing step. In step S4, the system host 50 receives data from the gate 40 and processes and analyzes this data to detect whether a fall event has occurred.

[0037] Step S5 is the step of determining whether a fall has been detected. In step S5, the system host 50 determines whether a fall event has been detected. If a fall event is detected, the next step is performed.

[0038] Step S6 is the step of notifying medical staff. In step S6, if a fall event is detected, the system host 50 immediately notifies the medical staff so that they can take appropriate measures quickly.

[0039] Step S7 is the data storage step. In step S7, regardless of whether a fall event is detected, the system host 50 stores the data in the cloud database 70. This data includes images acquired from the network surveillance camera (IP camera) 20 and the millimeter-wave radar 30, as well as various detection signals, for subsequent analysis and retrieval.

[0040] Step S8 is the end step. In step S8, the entire process ends, and the care automation platform 100 is ready to perform the next data collection and processing.

[0041] Next, please refer to Figure 3, which is a schematic diagram of the hardware architecture of the care automation platform in one embodiment of the present invention. As shown in Figure 3, in one embodiment of the present invention, the hardware of the care automation platform 300 is respectively configured in the public area 310, the patient 320, and the ward 330.

[0042] As shown in Figure 3, in one embodiment of the present invention, a network-connected IP camera 311 and a gateway 312 are configured in the public area 310. The IP camera 311 transmits image data to the gateway 312 via WiFi, and the gateway 312 then transmits the image data to the system host 313 via WiFi. The system host 313 then stores the data in a cloud database 314 or notifies medical personnel 315 to issue an alarm message.

[0043] As shown in Figure 3, in one embodiment of the present invention, a Bluetooth wearable device 321 is configured on the patient 320. The Bluetooth wearable device 321 can be a safety bracelet 322 with a low-power Bluetooth (BLE) module, or a low-power Bluetooth (BLE) module installed on slippers 323 or sanitary clothing 324.

[0044] As shown in Figure 3, in one embodiment of the present invention, the ward 330 is equipped with a millimeter-wave radar 331. The detection signals obtained from the actions or postures of the patient 320 are transmitted via WiFi to the gateway 312 and then to the system host 313. The system host 313 then stores the data in a cloud database 314 or notifies medical staff 315 to issue an alarm message.

[0045] Next, please refer to Figures 1 and 4. Figure 4 is a flowchart of the operation of the care automation platform in a specific scenario according to an embodiment of the present invention. As shown in Figure 4, in an embodiment of the present invention, the operation flow of the care automation platform 100 includes steps S41, S42, S43, S44, S45, S46, S47, S48, and S49.

[0046] Step S41 is the start step. In step S41, the care automation platform 100 starts up and prepares to capture images.

[0047] Step S42 is the image capture step. In step S42, the network surveillance camera (IP Camera) 20 continuously monitors the corridor and captures images in real time.

[0048] Step S44 is the image analysis step. In step S44, the system host 50 uses a machine learning model to analyze the human skeletal information in the image. Then, in step S46, it is further confirmed whether a fall event has occurred.

[0049] Step S43 is the signal detection step. In step S43, the millimeter-wave radar 30 emits a signal and receives the reflected signal to monitor moving objects in the corridor. Then, in step S45, the system host 50 analyzes the changes in the reflected signal to determine if there is an abnormal movement trajectory. Next, in step S46, it is further confirmed whether a fall event has occurred.

[0050] If a fall is confirmed in step S46, proceed to step S47 to trigger the alarm and notify relevant personnel, and then proceed to step S49.

[0051] Step S48 is the warning message display step. In step S48, a warning message is displayed on the monitoring screen, and the location of the fall is highlighted to facilitate a quick response from monitoring personnel.

[0052] If no fall event is confirmed in step S46, proceed to step S48 to continue monitoring.

[0053] Referring again to Figure 1, the data collected by the network surveillance camera (IP Camera) 20 and the millimeter-wave radar 30 is transmitted to the cloud database 70. In this embodiment of the invention, the cloud database 70 is a cloud computing platform (AWS) used for fall detection analysis, combining image and millimeter-wave data to improve identification accuracy.

[0054] Next, please refer to Figures 1 and 5. Figure 5 is a flowchart of the operation of the care automation platform in a specific scenario according to another embodiment of the present invention. As shown in Figure 5, in one embodiment of the present invention, the operation flow of the care automation platform 100 includes steps S50, S51, S52, S53, S54, S55, S56, S57, S58, and S59.

[0055] Step S50 is the start step. In step S50, the care automation platform 100 starts up and prepares for multi-sensor monitoring.

[0056] Step S51 is the monitoring step. In step S51, the network-type surveillance camera (IP Camera) 20 and the millimeter-wave radar 30 installed in the public area continuously monitor the activities in the area. The network-type surveillance camera (IP Camera) 20 then captures and analyzes images in step S52; the millimeter-wave radar 30 detects and analyzes signals in step S53.

[0057] Step S52 is the image analysis step. In step S52, the network surveillance camera (IP Camera) 20 captures images and uses machine learning to perform human skeleton analysis.

[0058] Step S53 is the signal analysis step. In step S53, the millimeter-wave radar 30 monitors moving objects within the area and analyzes signal changes to detect anomalies.

[0059] Step S54 is the data transmission step. In step S54, the image analysis data from step S52 and the signal analysis data from step S53 are both transmitted to the cloud and further processed in step S55.

[0060] Step S55 is the cloud computing analysis step. In step S55, all data is transmitted in real time to the cloud database 70, i.e., the cloud computing platform (AWS), for comprehensive analysis. The cloud database 70 uses a fall detection algorithm, combined with image and millimeter-wave data, and then determines in step S56 whether a fall event has occurred.

[0061] If a fall is confirmed in step S56, the alarm triggering step is initiated in step S57, which triggers the alarm and notifies relevant personnel. Then, the process proceeds to step S59.

[0062] Step S59 is the warning message display step. In step S59, a warning message is displayed on the monitoring screen, and the location of the fall is highlighted to facilitate a quick response from monitoring personnel.

[0063] If it is confirmed in step S56 that no fall event has occurred, proceed to step S58 to continue monitoring.

[0064] Next, please refer to Figures 1 and 6. Figure 6 is a flowchart of the operation of the care automation platform in a specific situation in another embodiment of the present invention. As shown in Figure 6, in one embodiment of the present invention, the operation flow of the care automation platform 100 includes steps S60, S61, S62, S63, S64, S65, S66, S67, S68, and S69.

[0065] Step S60 is the start step. In step S60, the care automation platform 100 starts up, ready to monitor the wearable device. In one embodiment of the present invention, the Bluetooth wearable device 10 worn by the patient is equipped with a patch antenna and a Bluetooth Low Energy (BLE) module, continuously transmitting signals. Multiple gateways 40 (e.g., Bluetooth gateways) are arranged in a public area to receive signals from the Bluetooth wearable device 10.

[0066] Step S61 is the signal transmission step. In step S61, the Bluetooth wearable device 10 worn by the patient continuously transmits signals.

[0067] Step S62 is the signal reception and positioning step. In step S62, multiple gateways 40 receive the signal sent by the patient's Bluetooth wearable device 10 in step S61, and transmit the signal strength and reception time to the positioning system (not shown in the figure). Next, in step S63, the positioning system uses triangulation technology to calculate the position of the Bluetooth wearable device 10 to monitor the patient's position in real time. Then, in step S64, the patient's position data is transmitted to the cloud database 70, i.e., the cloud computing platform (AWS), for comprehensive data analysis. Next, in step S65, the data from the Bluetooth wearable device 10 is combined with images and millimeter-wave data from the millimeter-wave radar 30 to comprehensively determine whether a fall event has occurred.

[0068] If a fall is confirmed in step S66, the alarm triggering step is initiated in step S67, which triggers the alarm and notifies relevant personnel. Then, the process proceeds to step S69.

[0069] Step S69 is the warning message display step. In step S69, a warning message is displayed on the monitoring screen, and the location of the fall is selected by box. At the same time, the patient's specific location is displayed to ensure that rescuers can quickly find and provide assistance.

[0070] If it is confirmed in step S66 that no fall event has occurred, proceed to step S68 to continue monitoring.

[0071] In embodiments of this invention, the camera-based fall detection function primarily relies on cameras installed in corridors or public areas. This technology utilizes machine learning and human skeleton tracking technology for fall detection. The specific process includes: image capture, skeleton recognition, fall detection, and alert function. Image capture refers to the camera capturing images of the corridor or public area in real time. Skeleton recognition refers to the system using machine learning algorithms to analyze human posture in the images and extract human skeleton information. Fall detection refers to the machine learning model analyzing human posture based on the extracted skeleton data to determine whether a fall has occurred. The alert function means that when the system detects a fall, it immediately displays an alert message on the monitoring screen and selects the specific location of the fall, allowing monitoring personnel to quickly confirm and react.

[0072] In addition, in embodiments of the present invention, the millimeter-wave fall detection function relies on millimeter-wave sensors, i.e., millimeter-wave radar, installed in corridors or public areas. This technology utilizes the high-precision moving object detection capability of millimeter-wave radar for fall detection. The specific process includes: millimeter-wave signal capture, moving object analysis, fall detection, and warning function. Millimeter-wave signal capture refers to the millimeter-wave sensor emitting millimeter-wave signals and receiving the reflected signals. Moving object analysis refers to the system identifying the human movement trajectory and posture changes within the area by analyzing changes in the reflected signals. Fall detection refers to the system determining whether a fall event has occurred based on the human movement trajectory and posture changes. The warning function refers to the system triggering an alarm system and issuing warning messages to relevant personnel when a fall event is detected.

[0073] In an embodiment of the present invention, the combination of camera-based fall detection technology and millimeter-wave fall detection technology enables the system to accurately and efficiently detect falls under different environments and conditions, ensuring safety in public areas.

[0074] Furthermore, in this embodiment of the invention, Bluetooth positioning is a crucial component of the fall detection system, primarily used for accurately locating the patient's position. This function is achieved by installing a patch antenna on a wearable device and utilizing gateways for triangulation. Specific technical details include: the use of a wearable device, gateway deployment, signal reception and transmission, triangulation, and position detection. The wearable device refers to a device worn by the patient equipped with a Bluetooth Low Energy (BLE) module and a patch antenna, which continuously transmits Bluetooth signals. Gateway deployment refers to the placement of multiple Bluetooth gateways in public areas to receive Bluetooth signals from the wearable device. Signal reception and transmission refers to the gateway transmitting data such as signal strength and reception time to the positioning system after receiving the Bluetooth signal from the wearable device. Triangulation refers to the positioning system calculating the specific position of the wearable device by analyzing the signal strength and time difference received by multiple gateways using triangulation technology. Position detection refers to the system triggering an alarm and displaying the patient's accurate position on the monitoring screen when it detects an abnormal change in the patient's position or a match with the fall detection system's results. This Bluetooth positioning function can accurately monitor changes in the patient's location, especially in the event of a fall. It can quickly locate the patient's position, providing timely and accurate information for emergency rescue, and greatly improving the system's safety and response speed.

[0075] In summary, using the care automation platform described in the above embodiments of the present invention, when the network-type surveillance camera (IP Camera) 20 and millimeter-wave radar 30 detect a suspected fall in a corridor or public area, the data is immediately transmitted to the cloud database 70, i.e., the cloud computing platform (AWS), for analysis. The cloud database 70 uses a fall detection algorithm to determine whether a fall has actually occurred. Once a fall is confirmed, the care automation platform 100 immediately displays an alert message on the monitoring screen and outlines the specific location of the fall, allowing monitoring personnel to quickly confirm the location of the incident. This real-time video alert function not only improves the efficiency of fall event identification but also ensures that relevant personnel can react quickly and provide timely assistance, thereby greatly enhancing safety and emergency response capabilities in public areas.

[0076] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

[0077] 100: Care Automation Platform 50: System Host 40: Gate device 10: Bluetooth wearable devices 30: One or more millimeter-wave radars 20: One or more network-connected IP cameras 70: Cloud-based database 60: Alarm device 300: Care Automation Platform 310: Public Areas 320: Patient 330: Ward 311: Network-based surveillance camera (IP Camera) 312: Gate switch 313: System Host 314: Cloud Database 315: Medical staff 321: Bluetooth wearable devices 322: Safety Bracelet 323: Slippers 324: Sanitary Clothing 331: Millimeter-wave radar S1, S2, S3, S4, S5, S6, S7, S8, S41, S42, S43, S44, S45, S46, S47, S48, S49, S50, S51, S52 , S53, S54, S55, S56, S57, S58, S59, S60, S61, S62, S63, S64, S65, S66, S67, S68, S69: Steps

Claims

1. A care automation platform, comprising: a system host; a gateway; a Bluetooth wearable device configured on a patient within a medical facility, used to transmit the patient's location information indoors to the system host via the gateway; one or more millimeter-wave radars configured on the ceiling of the ward, acquiring detection signals of the patient's movements or postures, and transmitting them to the system host via WiFi through the gateway for fall detection calculations; one or more network-type surveillance cameras (IP cameras) configured in a public area outside the ward, acquiring image data of the patient, and transmitting it to the system host via WiFi through the gateway for fall detection calculations; and a cloud database for storing image data and detection signals recorded by the network-type surveillance cameras and the millimeter-wave radars at different locations over a period of time, for subsequent analysis and retrieval; wherein... The patient's location information, posture information, and image information obtained by the Bluetooth wearable device are comprehensively analyzed to determine whether a fall has occurred.

2. The care automation platform as described in claim 1, wherein the cloud database is a cloud computing platform (AWS).

3. The care automation platform as described in claim 1, wherein the network-based surveillance camera utilizes machine learning and human backbone tracking technology for fall detection.

4. The care automation platform as described in claim 1, wherein the Bluetooth wearable device is equipped with a patch antenna, and the gateway is used for triangulation to calculate the specific location of the Bluetooth wearable device.

5. A care automation platform, comprising: a system host, a gateway, a Bluetooth wearable device, one or more millimeter-wave radars, one or more network-connected surveillance cameras (IP cameras), and a cloud database; wherein, The patient location information obtained by the Bluetooth wearable device, the patient image data obtained by the network-type surveillance camera, and the detection signals of the patient's movements or postures obtained by the millimeter-wave radar are all transmitted to the system host through the gateway, and then uploaded to the cloud database for fall recognition calculation and judgment. Among them, the patient location information, posture information and image information obtained by the Bluetooth wearable device are comprehensively analyzed to determine whether a fall event has occurred.

6. The care automation platform as described in claim 5, wherein the cloud database is a cloud computing platform (AWS).

7. The care automation platform as described in claim 5, wherein the network-based surveillance camera utilizes machine learning and human backbone tracking technology for fall detection.

8. The care automation platform as described in claim 5, wherein the Bluetooth wearable device is equipped with a patch antenna, and the gateway is used for triangulation to calculate the specific location of the Bluetooth wearable device.

9. An automated care platform, comprising: a system host; a gateway; a Bluetooth wearable device, configured on a patient within a medical facility, for transmitting the patient's location information indoors to the system host via the gateway; one or more millimeter-wave radars, configured on the ceiling of the ward, for acquiring detection signals of the patient's movements or postures, and transmitting them to the system host via WiFi through the gateway for fall detection calculations; one or more network-type surveillance cameras (IP cameras), configured in a public area outside the ward, for acquiring image data of the patient, and transmitting it to the system host via WiFi through the gateway for fall detection calculations; and a cloud database for storing image data and detection signals recorded by the network-type surveillance cameras and the millimeter-wave radars at different locations over a period of time for subsequent analysis and retrieval; wherein the network-type surveillance cameras utilize machine learning and human skeleton tracking technology for fall detection; wherein the Bluetooth wearable device is equipped with a patch antenna, and the gateway is used for triangulation to calculate the specific location of the Bluetooth wearable device; in, The patient's location information, posture information, and image information obtained by the Bluetooth wearable device are comprehensively analyzed to determine whether a fall has occurred.

10. A care automation platform, comprising: a system host, a gateway, a Bluetooth wearable device, one or more millimeter-wave radars, one or more network-connected surveillance cameras (IP cameras), and a cloud database; wherein, The patient location information obtained by the Bluetooth wearable device, the patient image data obtained by the network surveillance camera, and the detection signals of patient movement or posture obtained by the millimeter-wave radar are all transmitted to the system host via the gateway, and then uploaded to the cloud database for fall detection calculation and judgment. The network surveillance camera uses machine learning and human skeleton tracking technology for fall detection. The Bluetooth wearable device is equipped with a patch antenna, and the gateway is used for triangulation to calculate the specific position of the Bluetooth wearable device. The patient location information, posture information, and image information obtained by the Bluetooth wearable device are comprehensively analyzed to determine whether a fall event has occurred.

Images