Old people tumble alarm system based on multi-mode artificial intelligence model

Abstract

The invention discloses an old man falling alarm system based on a multi-modal artificial intelligence model. The old man falling alarm system comprises a data acquisition module, a multi-modal fusion module, an artificial intelligence analysis module, an alarm module and a background management system. The data acquisition module acquires video image data, wearable equipment data and environment data of the elderly; the multi-modal fusion module carries out fusion processing on data of different modals to generate a multi-modal feature vector; the artificial intelligence analysis module analyzes the feature vectors based on a multi-modal artificial intelligence model, and outputs the probability and confidence of falling of the old; when it is judged that the old fall down and the confidence reaches a preset threshold, the alarm module starts to give an alarm; and the background management system configures, manages and monitors the system. According to the invention, by fusing various modal data, efficient and accurate detection and timely alarm of the falling condition of the elderly are realized by using a deep learning technology, a powerful guarantee is provided for the safety and health of the elderly, and the method is suitable for the scenes of old-age care institutions, community old-age care service centers, families of the elderly living alone and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring and alarm systems, and in particular to an elderly fall alarm system based on a multimodal artificial intelligence model. Background Art

[0002] Traditional elderly care monitoring methods often rely on manual patrols or simple sensor devices, which are subject to high labor costs, delayed response times, and high false alarm rates. In recent years, monitoring systems based on artificial intelligence (AI) technology have gradually emerged. However, most existing systems rely on a single modality of data, such as analysis based solely on video images or wearable device data. These systems are easily affected by environmental factors and device performance, resulting in insufficient accuracy and reliability in fall detection. Therefore, there is an urgent need for an alarm system that can integrate multimodal data to improve the accuracy and timeliness of elderly fall detection. Summary of the Invention

[0003] The purpose of the present invention is to provide an elderly fall alarm system based on a multimodal artificial intelligence model to solve the problems existing in the prior art and achieve efficient and accurate detection of elderly falls and timely alarm.

[0004] The elderly fall alarm system of the present invention includes the following modules:

[0005] Data acquisition module: This module is used to collect multiple modal data from the elderly, including video and image data, wearable device data (such as accelerometers and heart rate sensors), and environmental data (such as indoor temperature, humidity, and light). Video and image data can be collected through cameras installed in nursing homes or areas where the elderly spend time. Wearable device data is transmitted in real time by devices worn by the elderly, and environmental data is obtained through corresponding environmental sensors.

[0006] Multimodal Fusion Module: This module fuses collected data from different modalities, enabling the system to analyze the elderly's condition from multiple perspectives and dimensions. This fusion method utilizes multimodal feature extraction and fusion technology based on deep learning. This method organically integrates posture information from video images, motion and physiological information from wearable devices, and background information from environmental data to generate a multimodal feature vector that comprehensively reflects the elderly's condition.

[0007] Artificial Intelligence Analysis Module: This module builds a fall detection algorithm based on a multimodal AI model. This algorithm uses a fused multimodal feature vector as input and, through learning and training on a large amount of labeled and unlabeled data, intelligently identifies falls in the elderly. This model utilizes a deep neural network architecture, such as a combination of a convolutional neural network (CNN) and a recurrent neural network (RNN) or Transformer network, to process the spatiotemporal information of video images, as well as the temporal characteristics of wearable device and environmental data. After sufficient training, it can accurately distinguish between normal activity and falls, and output the probability and confidence level of a fall.

[0008] Alarm Module: When the AI ​​analysis module determines that an elderly person has fallen and the confidence level reaches a preset threshold, the alarm module promptly activates the alarm mechanism. This alarm can include local audible and visual alarms to alert staff within the nursing home or those in the same area. Simultaneously, an alarm message is sent via the network to a designated guardian, family member, or emergency rescue agency. This message can include the elderly person's identity, the time and location of the fall, and relevant on-site images or video clips, allowing rescuers to quickly obtain accurate information and take appropriate measures.

[0009] Backend Management System: This system is used to configure, manage, and monitor the system. It enables functions such as setting parameters for data acquisition equipment, adjusting multimodal fusion strategies, training and optimizing AI models, setting alarm thresholds, and querying and compiling alarm records. The backend management system also provides a user interface, allowing managers and family members to easily view the patient's status and system operation status at any time.

[0010] The beneficial effects of the present invention are

[0011] By integrating multiple modal information such as video images, wearable devices and environmental data, the limitations of single modal data such as susceptibility to interference and incomplete information are overcome, and the accuracy and reliability of elderly fall detection are improved.

[0012] The multimodal artificial intelligence model based on deep learning can automatically learn the normal activity patterns and fall characteristics of the elderly. It has strong adaptability and generalization capabilities and can effectively meet the needs of elderly fall detection in different scenarios and individual differences.

[0013] A timely alarm mechanism can ensure that when an elderly person falls, relevant personnel can be quickly notified and take rescue actions, providing strong protection for the elderly person's life safety.

[0014] The modular design of the system facilitates expansion and optimization according to actual needs, such as adding new data acquisition modalities, improving fusion algorithms, or upgrading artificial intelligence models, and has good scalability and maintainability. DETAILED DESCRIPTION

[0015] The elderly fall alarm system of the present invention is described in detail below.

[0016] The elderly fall alarm system of the present invention mainly includes a data acquisition module, a multimodal fusion module, an artificial intelligence analysis module, an alarm module and a background management system.

[0017] In the data acquisition module, cameras are installed in corridors, rooms, activity rooms and other areas where the elderly often move around in the nursing home to capture all-round video image data of the elderly; wearable devices are worn by the elderly to monitor their physiological and motion data such as acceleration, heart rate, body temperature, etc. in real time, and transmit the data to the system via Bluetooth or wireless network; environmental sensors are distributed in different locations indoors to collect environmental data such as temperature, humidity, and light. These data are collected to the central processing unit of the data acquisition module through wired or wireless communication.

[0018] After receiving the various data transmitted by the data acquisition module, the multimodal fusion module first performs data preprocessing, including data cleaning, normalization, and time synchronization, to eliminate discrepancies and noise interference. It then uses a deep learning-based multimodal feature extraction method to extract the elderly person's posture, movement, and behavioral features from the video images, motion status and physiological characteristics from the wearable device data, and background features related to the elderly person's activities from the environmental data. These features from different modalities are then fused using a fusion strategy, such as an attention mechanism or feature splicing, to generate a multimodal feature vector that comprehensively reflects the elderly person's status. This vector is then input into the artificial intelligence analysis module.

[0019] The AI ​​analysis module builds a multimodal AI model based on a deep neural network. During the model training phase, a large amount of multimodal data, including daily activities and fall scenarios of the elderly, is collected and annotated. The annotated data is divided into training, validation, and test sets. The model is trained using the training set, and its parameters are adjusted through an optimization algorithm, enabling it to learn the associations between different modal data and the representation of fall characteristics. The model is evaluated and tuned on the validation set to determine the optimal model structure and hyperparameters. Finally, the trained model is tested on the test set to verify its performance metrics such as accuracy and recall for fall detection. When the system is running, the fused multimodal feature vector is input into the trained model, which then calculates and outputs the probability and confidence level of a fall. If the confidence level reaches a preset alarm threshold, for example, 80%, a fall is determined, triggering the alarm module.

[0020] Upon receiving the alarm command, the alarm module immediately activates the local audio and visual alarm system, emitting dazzling lights and loud sounds in the corresponding area of ​​the nursing home to alert on-site staff and other personnel. Simultaneously, the alarm information is transmitted via the network to the designated guardian, family members, and emergency rescue agencies. This information includes the individual's name, room number, specific time and location of the fall, and on-site images or video clips captured by the camera, allowing relevant personnel to quickly understand the situation and respond. For example, family members can receive an alarm notification via a mobile app, view the individual's real-time status and on-site video, and promptly communicate with nursing home staff and arrange for rescue. Rescue agencies can then use the alarm information to quickly locate the individual and dispatch an ambulance.

[0021] The backend management system provides comprehensive management capabilities for system administrators. Administrators can use the backend management system to configure parameters for data acquisition devices such as cameras, wearable devices, and environmental sensors. These configurations include adjusting the camera's shooting angle, resolution, and frame rate, and setting the wearable device's data collection frequency and transmission interval. Furthermore, the multimodal fusion module's fusion algorithms and strategies can be adjusted to suit the data characteristics and detection requirements of different scenarios. Furthermore, the backend management system supports the training and optimization of artificial intelligence models. Administrators can import new training data, update model parameters, and improve detection performance. Alarm thresholds can also be set within the backend management system, allowing for flexible adjustment of alarm sensitivity based on actual needs and false alarm rates. The system also records all alarm events and system operation logs. Administrators can query and compile alarm records through the backend management system, analyzing information such as the frequency, time distribution, and location of falls, providing data support for nursing home safety management and care arrangements. Family members and authorized personnel can also use the backend management system's user interface to view real-time status information on residents, including video images, physiological data, and activity trajectories, to gain insights into their living and health status within the nursing home.

[0022] To sum up, the elderly fall alarm system based on the multimodal artificial intelligence model of the present invention integrates multiple modal data and uses advanced deep learning technology for intelligent analysis and judgment, thereby achieving efficient and accurate detection and timely alarm of elderly falls, providing strong protection for the safety and health of the elderly, and has broad application prospects in scenarios such as nursing homes, community elderly care service centers, and families of elderly people living alone.

Claims

1. An elderly fall alarm system based on a multimodal artificial intelligence model, characterized in that: include: Data acquisition module, used to collect video image data, wearable device data and environmental data of the elderly; The multimodal fusion module is used to fuse the collected data of different modalities and generate a multimodal feature vector; The AI ​​analysis module builds a fall detection algorithm based on a multimodal AI model. It uses the fused multimodal feature vector as input and outputs the probability and confidence level of an elderly person falling. An alarm module, when the artificial intelligence analysis module determines that the elderly person has fallen and the confidence level reaches a preset threshold, activates the alarm mechanism and sends an alarm message to relevant personnel; The backend management system is used to configure, manage and monitor the system.

2. The elderly fall alarm system based on a multimodal artificial intelligence model according to claim 1 is characterized in that: The data acquisition module includes: a camera installed in the elderly activity area, used to capture video image data of the elderly; Wearable devices are worn by the elderly to monitor their physiological and motion data such as acceleration, heart rate, and body temperature in real time; Environmental sensors are distributed in different locations indoors to collect environmental data such as temperature, humidity, and light.

3. The elderly fall alarm system based on a multimodal artificial intelligence model according to claim 1 is characterized in that: The multimodal fusion module adopts multimodal feature extraction and fusion technology based on deep learning, including the following steps: Preprocess data of different modalities, including data cleaning, normalization, and time synchronization; Extract posture, motion, and behavior features from video image data, motion state and physiological features from wearable device data, and background features from environmental data; Fusion strategies such as attention mechanism or feature splicing are used to fuse features of different modalities to generate multimodal feature vectors.

4. The elderly fall alarm system based on a multimodal artificial intelligence model according to claim 1 is characterized in that: The multimodal artificial intelligence model of the artificial intelligence analysis module adopts a deep neural network architecture, including a combination of a convolutional neural network and a recurrent neural network or a Transformer network, to process the spatiotemporal information of video images and the temporal characteristics of wearable device and environmental data.

5. The elderly fall alarm system based on a multimodal artificial intelligence model according to claim 1 is characterized in that: The alarm module's alarm modes include local sound and light alarms and network alarms. The local sound and light alarms are used to alert on-site personnel, and the network alarms send alarm information to preset guardians, family members or emergency rescue agencies through the network. The alarm information contains the elderly person's identity information, the time and location of the fall, and on-site images or video clips.

6. The elderly fall alarm system based on a multimodal artificial intelligence model according to claim 1 is characterized in that: The backend management system has the following functions: Parameter setting of data acquisition equipment; Adjustment of multimodal fusion strategy; Training and optimization of artificial intelligence models; Setting of alarm thresholds; Query and statistics of alarm records.