Intelligent old-age care service and emergency response system and method

Abstract

The invention relates to the technical field of emergency response, in particular to an intelligent old-age care service and emergency response system and method. The method comprises the following steps: collecting multi-source real-time data of a target person, extracting behavior characteristics, dividing a current behavior type, marking abnormal data, identifying the current behavior characteristics and generating a report; setting multi-level trigger conditions according to the behavior feature recognition report, generating corresponding-level emergency judgment requests, judging emergency situations through multi-dimensional fusion logic and outputting emergency judgment results; a risk-service matching mechanism is constructed according to an emergency judgment result, multiple subjects are linked, early warning and observation conditions are dynamically tracked, and services are adjusted; the system comprises a current behavior feature recognition module, an emergency judgment request module and a service providing and emergency response module. The current data is subjected to behavior feature recognition, the emergency situation judgment request is triggered according to the recognition result, and then emergency response and corresponding service providing are performed, so that the emergency response efficiency of smart pension is improved.

Description

Technical Field

[0001] This invention relates to the field of emergency response technology, and in particular to a smart elderly care service and emergency response system and method. Background Technology

[0002] With the accelerating aging of the population, the demand for safety monitoring and services for the elderly under home-based and community-based elderly care models is becoming increasingly urgent. Traditional elderly care models have many limitations, such as high costs of manual monitoring, untimely emergency response, and insufficient personalized services.

[0003] While existing smart elderly care solutions have incorporated sensor data collection, they largely remain at the level of single-data monitoring, such as judging abnormalities solely based on physiological indicators or location information, lacking dynamic identification and in-depth analysis of the elderly's current behavioral characteristics. Furthermore, existing solutions operate in a fragmented manner between emergency assessment and service provision: emergency assessments often rely on preset thresholds and are not correlated with real-time behavioral characteristics, making them prone to misjudgments or omissions, resulting in low emergency response efficiency. Summary of the Invention

[0004] The purpose of this invention is to provide a smart elderly care service and emergency response system and method, aiming to solve the technical problem of low emergency response efficiency in the prior art.

[0005] To achieve the above objectives, the present invention employs a smart elderly care service and emergency response method, comprising the following steps: Collect multi-source real-time data of target personnel, extract behavioral features, classify current behavior types and label abnormal data, identify current behavioral features based on historical behavior baselines and generate reports; Based on the behavioral feature recognition report, set multi-level trigger conditions, generate corresponding level emergency judgment requests and transmit them in encrypted form, determine the emergency situation through multi-dimensional fusion logic and output the emergency judgment result; A risk-service matching mechanism is established based on emergency assessment results, linking multiple stakeholders, and dynamically tracking and adjusting services based on early warning and observation situations.

[0006] Among the steps are: collecting multi-source real-time data of target personnel, extracting behavioral features, classifying current behavior types and labeling abnormal data, identifying current behavioral features based on historical behavioral baselines, and generating reports; Collect data on the target person's limb movements and activity status to generate behavioral feature vectors; Build a behavioral feature database, match the extracted behavioral feature vectors with the database, and classify the category to which the current behavior belongs; A historical behavior baseline is established based on the target personnel's historical normal behavior data. The current labeled behavior characteristics are compared with the historical behavior baseline to determine the degree of deviation between the current behavior and the baseline.

[0007] In the step of collecting target personnel's limb movement data and activity status data to generate behavioral feature vectors: Feature extraction and continuous motion data processing are performed on the collected real-time data to generate behavioral feature vectors that include motion coherence, motion amplitude stability, and spatial behavior rationality.

[0008] Among them, after establishing a historical behavior baseline based on the target personnel's historical normal behavior data, comparing the currently labeled behavioral characteristics with the historical behavior baseline, and determining the degree of deviation between the current behavior and the baseline: Integrate information on behavior category, anomaly labeling, and degree of deviation to generate a current behavior feature recognition report.

[0009] Among them, in the steps of setting multi-level triggering conditions based on behavioral feature recognition reports, generating corresponding level emergency judgment requests and transmitting them in encrypted form, determining the emergency situation through multi-dimensional fusion logic and outputting the emergency judgment results: Based on the behavior category and degree of deviation in the current behavior feature identification report, set multi-level emergency judgment request triggering conditions; An emergency assessment request of the corresponding level is generated based on the triggering conditions.

[0010] In the step of generating an emergency judgment request of the corresponding level based on the triggering conditions: The request is pushed using an encrypted transmission protocol; the request content includes a current behavior feature identification report, real-time data fragments of abnormal behavior, and a historical behavior baseline comparison table.

[0011] After the step of generating an emergency assessment request of the corresponding level based on the triggering conditions: Upon receiving an emergency assessment request, the system retrieves the target individual's real-time physiological data to determine whether abnormal behavior is accompanied by abnormal physiological indicators.

[0012] After receiving an emergency assessment request, accessing the target individual's real-time physiological data, and determining whether the abnormal behavior is accompanied by abnormal physiological indicators: By accessing the emergency case database and matching the current abnormal behavior with the characteristics of historical cases, and by combining physiological, environmental, and case matching results, the risk type and response recommendations are determined.

[0013] Among these steps, the process involves establishing a risk-service matching mechanism based on emergency assessment results, linking multiple stakeholders, and dynamically tracking and adjusting services based on early warning and observation conditions: A risk-service matching mechanism is constructed based on the risk levels in the emergency assessment results; the risk levels include observation, emergency, and early warning. The risk level is linked to multiple entities to conduct tiered early warnings and obtain feedback data.

[0014] This invention also provides a smart elderly care service and emergency response system, including a current behavior feature recognition module, an emergency judgment and request module, and a service provision and emergency response module; wherein: The current behavior feature recognition module is used to collect multi-source real-time data of target personnel, extract behavioral features, classify current behavior types and label abnormal data, identify current behavior features based on historical behavior baselines and generate reports; The emergency judgment request module is used to set multi-level triggering conditions based on the behavioral feature recognition report, generate corresponding level emergency judgment requests and transmit them in encrypted form, determine the emergency situation through multi-dimensional fusion logic and output the emergency judgment result. The service provision and emergency response module is used to construct a risk-service matching mechanism based on emergency assessment results, link multiple entities, dynamically track and adjust services based on early warning and observation conditions.

[0015] This invention discloses a smart elderly care service and emergency response system and method, which employs a current behavior feature identification module, an emergency judgment request module, and a service provision and emergency response module to perform the following steps: Collecting multi-source real-time data of target personnel, extracting behavioral features, classifying current behavior types and labeling abnormal data; identifying current behavioral features based on historical behavior baselines and generating a report; setting multi-level trigger conditions based on the behavioral feature identification report, generating corresponding level emergency judgment requests and transmitting them encrypted; determining emergency situations through multi-dimensional fusion logic and outputting emergency judgment results; constructing a risk-service matching mechanism based on the emergency judgment results, linking multiple entities, dynamically tracking and adjusting services based on early warning and observation situations; and improving the efficiency of smart elderly care emergency response by identifying behavioral features of current data, triggering emergency situation judgment requests based on the identification results, and then providing emergency responses and corresponding services. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of the steps of the smart elderly care service and emergency response method of the present invention.

[0018] Figure 2 This is a flowchart of steps S100 of the present invention.

[0019] Figure 3 This is a flowchart of steps S200 of the present invention.

[0020] Figure 4 This is a flowchart of steps S300 of the present invention.

[0021] Figure 5 This is a structural schematic diagram of the smart elderly care service and emergency response system of the present invention.

[0022] Figure 6 This is a schematic diagram of the electronic device of the present invention.

[0023] 401 - Current Behavior Feature Recognition Module, 402 - Emergency Judgment Request Module, 403 - Service Provision and Emergency Response Module. Detailed Implementation

[0024] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0025] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0026] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0027] Please see Figures 1-4 This invention provides a smart elderly care service and emergency response method, comprising the following steps: S100: Collect multi-source real-time data of target personnel, extract behavioral features, classify current behavior types and label abnormal data, identify current behavioral features based on historical behavior baselines and generate reports.

[0028] In this implementation, multi-source real-time data of the target personnel is collected, behavioral features are extracted, and the current behavior type is classified and abnormal data is labeled. Based on the historical behavior baseline, the current behavioral features are identified and a report is generated. The specific process is as follows: S101: Collect limb movement data and activity status data of the target personnel, and perform feature extraction and continuous movement data processing on the collected real-time data to generate a behavioral feature vector that includes movement continuity, movement amplitude stability, and spatial behavior rationality. S102: Construct a behavioral feature database, match the extracted behavioral feature vectors with the database, and classify the category to which the current behavior belongs; S103: Establish a historical behavior baseline based on the target personnel's historical normal behavior data, compare the current labeled behavior characteristics with the historical behavior baseline, and determine the degree of deviation between the current behavior and the baseline; S104: Integrate behavior category, anomaly labeling, and deviation degree information to generate a current behavior feature recognition report.

[0029] In the above process, a dual-dimensional data collection device consisting of personal and fixed devices is deployed. The personal terminal uses a smart bracelet or name tag with multi-axis sensors to collect the target person's limb movement data (such as gait frequency, arm swing amplitude, and body tilt angle) and activity status data (such as walking speed, stillness duration, and number of times they get up). The fixed devices include AI cameras and ground pressure sensors installed in key residential areas to collect spatial behavior data (such as whether they are near dangerous areas, and whether their sitting or lying posture is abnormal) and interactive behavior data (such as whether they repeatedly operate objects, and whether they have not interacted with the outside world for a long time). All devices transmit data to the behavior analysis engine in real time via 5G or edge computing modules, ensuring that the data transmission latency is controlled within 100ms. Feature extraction is performed on the collected real-time data, and a temporal convolutional network is used to process the continuous action data to generate behavioral feature vectors that include action coherence (such as whether the gait is paused), action amplitude stability (such as whether the arm swing suddenly decreases), and spatial behavior rationality (such as whether the person frequently enters and exits the kitchen outside of mealtimes). A behavioral feature database was constructed, comprising a normal behavior database (e.g., steady walking, sitting rest, independent eating) and a potential abnormal behavior database (e.g., unsteady gait, sudden body tilting, prolonged curling up and immobility). An attention-based deep learning model was used to match the extracted behavioral feature vectors with the database, classifying the current behavior into categories (e.g., "normal walking," "suspected fall precursor," "abnormal immobility"). For data classified as "potential abnormal behavior," abnormal dimensions were labeled (e.g., "gait frequency below the normal threshold by 30%" "body tilt angle exceeding 45° and lasting for 5 seconds"). A historical behavior baseline is established based on the target personnel's historical normal behavior data over the past 7 to 14 days. The current labeled behavioral characteristics are compared with the historical behavior baseline to determine the degree of deviation between the current behavior and the baseline. The behavior category, abnormal labeling, and deviation degree information are integrated to generate a current behavior feature identification report.

[0030] S200: Based on the behavioral feature recognition report, set multi-level trigger conditions, generate corresponding level emergency judgment requests and transmit them in encrypted form, determine the emergency situation through multi-dimensional fusion logic and output the emergency judgment result.

[0031] In this implementation, multi-level triggering conditions are set based on the behavioral feature recognition report, corresponding emergency judgment requests are generated and transmitted encrypted, and the emergency situation is determined through multi-dimensional fusion logic, and the emergency judgment result is output. The specific process is as follows: S201: Based on the behavior category and degree of deviation in the current behavior feature identification report, set multi-level emergency judgment request triggering conditions; S202: Generate an emergency judgment request of the corresponding level based on the triggering conditions, and push the request using an encrypted transmission protocol; the request content includes the current behavior feature identification report, real-time data fragments of abnormal behavior, and a historical behavior baseline comparison table; S203: Receive an emergency assessment request, retrieve the target person's real-time physiological data, and determine whether the abnormal behavior is accompanied by abnormal physiological indicators. S204: Access the emergency case database, match the current abnormal behavior with the features of historical cases, and combine physiological, environmental and case matching results to determine the risk type and disposal recommendations.

[0032] In the above process, based on the behavior category and degree of deviation in the current behavioral feature identification report, three levels of emergency judgment request triggering conditions are set. The first-level triggering condition corresponds to "high-risk abnormal behavior" (such as "confirmed fall", "unconscious lying down", "contact with dangerous items") or the deviation of behavioral features from the historical baseline exceeds 60%. The second-level triggering condition corresponds to "medium-risk abnormal behavior" (such as "unsteady gait", "repeated failure to get up", "long period without drinking water") or the deviation is between 30% and 60%. The third-level triggering condition corresponds to "low-risk abnormal behavior" (such as "reduced activity range" and "reduced interaction frequency") or the deviation is between 10% and 30%.

[0033] Based on the triggering conditions, an emergency judgment request of the corresponding level is automatically generated. The request content includes the current behavioral feature identification report, real-time data fragments of abnormal behavior (such as the movement trajectory within 10 seconds, pressure sensor data), and a historical behavior baseline comparison table. The request is pushed using the TLS1.3 encrypted transmission protocol and simultaneously synchronized to the mobile APP of the target person's family members.

[0034] Upon receiving the request, the system retrieves the target person's real-time physiological data (such as heart rate, blood oxygen, and blood pressure data collected by a smart bracelet) to determine whether the abnormal behavior is accompanied by abnormal physiological indicators (such as a sudden increase in heart rate and a decrease in blood oxygen after a fall).

[0035] By combining data on the target personnel's living environment (such as data from gas sensors, smoke sensors, and temperature and humidity sensors), it is determined whether the abnormal behavior is caused by environmental risks (such as dizziness or abnormal gait due to gas leaks). At the same time, it calls upon the emergency case database and uses feature similarity matching between the current abnormal behavior and historical cases (such as the similarity between "abnormal stillness" and "hypoglycemia leading to coma") to assist in the judgment. By combining the physiological, environmental, and case matching results, it clarifies the risk type (such as "fall injury", "physiological abnormality", "environmental hazard"), risk level (such as "emergency", "early warning", "observation"), and disposal recommendations, and outputs the emergency judgment result.

[0036] S300: Based on emergency assessment results, a risk-service matching mechanism is constructed, linking multiple stakeholders, and the early warning and observation situation is dynamically tracked and services are adjusted accordingly.

[0037] In this implementation, a risk-service matching mechanism is constructed based on emergency assessment results, linking multiple stakeholders, and dynamically tracking and adjusting services according to early warning and observation situations. The specific process is as follows: S301: Construct a risk-service matching mechanism based on the risk level in the emergency assessment results; where the risk level includes observation, emergency, and early warning. S302: Based on the risk level, multiple entities are linked to conduct tiered early warnings and obtain feedback data.

[0038] In the above process, a risk-service matching mechanism is constructed based on the risk level in the emergency assessment results. When the risk level is under observation, life assistance services (such as intelligent reminders of the target person's activities and increased health monitoring frequency) are matched; when the risk level is under warning, health intervention services (such as personalized rehabilitation guidance and appointment for home physical examinations) are matched; when the risk level is under emergency, regular services are suspended and emergency rescue services are matched first.

[0039] In response to the emergency risk level, a multi-party linkage mechanism is triggered within 1 minute, pushing emergency information (including the real-time location of the target person, behavioral characteristics report, emergency judgment results, and rescue channel guidance) to the preset emergency contact (family members, community grid workers), community emergency rescue station, and the emergency department of the nearest hospital. Within 3 minutes, community rescue personnel are dispatched to the scene with first aid kits. The target person's real-time video is received through a mobile APP to understand their status. If medical treatment is required within 10 minutes, the health records of the target person are synchronized with the hospital to prepare medical resources in advance.

[0040] Based on the risk level warning, community caregivers will be arranged to communicate with the target person via telephone or video call within 5 minutes to confirm the cause of the abnormal behavior; if the target person is unable to clearly express the cause or the situation worsens within 30 minutes, caregivers will bring portable medical examination equipment to the site for testing and feed the results back to the emergency judgment module to update the judgment result.

[0041] Based on the observed risk level, the system continuously monitors changes in the behavioral characteristics of the target individuals within one hour. If the deviation further increases, it automatically escalates and triggers an emergency judgment request. Within 24 hours, a report on changes in behavioral characteristics is generated and pushed to family members and community nursing stations. The frequency of home visits is adjusted based on family feedback. At the same time, after all services corresponding to the risk level are provided, the service execution status and feedback from the target individuals are recorded to provide a basis for subsequent service adjustments.

[0042] Corresponding to the aforementioned embodiments of smart elderly care service and emergency response methods, this application also provides embodiments of smart elderly care service and emergency response systems.

[0043] Figure 5 This is a block diagram illustrating a smart elderly care service and emergency response system according to an exemplary embodiment. (Refer to...) Figure 5 The system may include: a current behavior feature recognition module 401, an emergency judgment request module 402, and a service provision and emergency response module 403; wherein: The current behavior feature recognition module 401 is used to collect multi-source real-time data of the target personnel, extract behavioral features, classify current behavior types and label abnormal data, identify current behavior features based on historical behavior baselines and generate reports; The emergency judgment request module 402 is used to set multi-level triggering conditions based on the behavioral feature recognition report, generate corresponding level emergency judgment requests and transmit them in encrypted form, determine the emergency situation through multi-dimensional fusion logic and output the emergency judgment result. The service provision and emergency response module 403 is used to construct a risk-service matching mechanism based on the emergency assessment results, link multiple entities, dynamically track and adjust services based on early warning and observation conditions.

[0044] In this embodiment, the current behavior feature recognition module 401 collects multi-source real-time data of the target personnel, extracts behavioral features, classifies current behavior types and labels abnormal data, identifies current behavioral features based on historical behavior baselines, and generates a report; the emergency judgment request module 402 sets multi-level triggering conditions based on the behavior feature recognition report, generates corresponding level emergency judgment requests and transmits them in encrypted form, determines the emergency situation through multi-dimensional fusion logic, and outputs the emergency judgment result; the service provision and emergency response module 403 constructs a risk-service matching mechanism based on the emergency judgment result, links multiple entities, dynamically tracks and adjusts services based on early warning and observation situations; by performing behavioral feature recognition on the current data, triggering emergency situation judgment requests based on the recognition results, and then providing emergency response and corresponding services, the efficiency of smart elderly care emergency response is improved.

[0045] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0046] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0047] Accordingly, this application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the smart elderly care service and emergency response method described above. Figure 6 The diagram shown is a hardware structure diagram of any device with data processing capabilities within a smart elderly care service and emergency response system provided in an embodiment of the present invention, except... Figure 6 In addition to the processor, memory, and network interface shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0048] Accordingly, this application also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the smart elderly care service and emergency response method described above. The computer-readable storage medium can be an internal storage unit of any data processing device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data processing device, and can also be used to temporarily store data that has been output or will be output.

[0049] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0050] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A smart elderly care service and emergency response method, characterized in that, Includes the following steps: Collect multi-source real-time data of target personnel, extract behavioral features, classify current behavior types and label abnormal data, identify current behavioral features based on historical behavior baselines and generate reports; Based on the behavioral feature recognition report, set multi-level trigger conditions, generate corresponding level emergency judgment requests and transmit them in encrypted form, determine the emergency situation through multi-dimensional fusion logic and output the emergency judgment result; A risk-service matching mechanism is established based on emergency assessment results, linking multiple stakeholders, and dynamically tracking and adjusting services based on early warning and observation situations.

2. The smart elderly care service and emergency response method as described in claim 1, characterized in that, In the steps of collecting multi-source real-time data on target personnel, extracting behavioral features, classifying current behavior types and labeling abnormal data, identifying current behavioral features based on historical behavioral baselines, and generating reports: Collect data on the target person's limb movements and activity status to generate behavioral feature vectors; Build a behavioral feature database, match the extracted behavioral feature vectors with the database, and classify the category to which the current behavior belongs; A historical behavior baseline is established based on the target personnel's historical normal behavior data. The current labeled behavior characteristics are compared with the historical behavior baseline to determine the degree of deviation between the current behavior and the baseline.

3. The smart elderly care service and emergency response method as described in claim 2, characterized in that, In the step of collecting limb movement data and activity status data of the target person to generate behavioral feature vectors: Feature extraction and continuous motion data processing are performed on the collected real-time data to generate behavioral feature vectors that include motion coherence, motion amplitude stability, and spatial behavior rationality.

4. The smart elderly care service and emergency response method as described in claim 2, characterized in that, After establishing a historical behavior baseline based on the target personnel's historical normal behavior data, comparing the currently labeled behavioral characteristics with the historical behavior baseline, and determining the degree of deviation between the current behavior and the baseline: Integrate information on behavior category, anomaly labeling, and degree of deviation to generate a current behavior feature recognition report.

5. The smart elderly care service and emergency response method as described in claim 1, characterized in that, In the steps of setting multi-level triggering conditions based on behavioral feature recognition reports, generating corresponding emergency judgment requests and transmitting them encrypted, determining the emergency situation through multi-dimensional fusion logic and outputting the emergency judgment results: Based on the behavior category and degree of deviation in the current behavior feature identification report, set multi-level emergency judgment request triggering conditions; An emergency assessment request of the corresponding level is generated based on the triggering conditions.

6. The smart elderly care service and emergency response method as described in claim 5, characterized in that, In the step of generating an emergency assessment request of the corresponding level based on the triggering conditions: The request is pushed using an encrypted transmission protocol; the request content includes a current behavior feature identification report, real-time data fragments of abnormal behavior, and a historical behavior baseline comparison table.

7. The smart elderly care service and emergency response method as described in claim 6, characterized in that, After the step of generating an emergency assessment request of the corresponding level based on the triggering conditions: Upon receiving an emergency assessment request, the system retrieves the target individual's real-time physiological data to determine whether abnormal behavior is accompanied by abnormal physiological indicators.

8. The smart elderly care service and emergency response method as described in claim 7, characterized in that, After receiving an emergency assessment request, accessing the target individual's real-time physiological data, and determining whether abnormal behavior is accompanied by abnormal physiological indicators: By accessing the emergency case database and matching the current abnormal behavior with the characteristics of historical cases, and by combining physiological, environmental and case matching results, the risk type and response recommendations are determined.

9. The smart elderly care service and emergency response method as described in claim 1, characterized in that, In the process of constructing a risk-service matching mechanism based on emergency assessment results, linking multiple stakeholders, and dynamically tracking and adjusting services based on early warning and observation: A risk-service matching mechanism is constructed based on the risk levels in the emergency assessment results; the risk levels include observation, emergency, and early warning. The risk level is linked to multiple entities to conduct tiered early warnings and obtain feedback data.

10. A smart elderly care service and emergency response system, applied to the smart elderly care service and emergency response method as described in claim 1, characterized in that, It includes a current behavior feature recognition module, an emergency judgment request module, and a service provision and emergency response module; among which: The current behavior feature recognition module is used to collect multi-source real-time data of target personnel, extract behavioral features, classify current behavior types and label abnormal data, identify current behavior features based on historical behavior baselines and generate reports; The emergency judgment request module is used to set multi-level triggering conditions based on the behavioral feature recognition report, generate corresponding level emergency judgment requests and transmit them in encrypted form, determine the emergency situation through multi-dimensional fusion logic and output the emergency judgment result. The service provision and emergency response module is used to construct a risk-service matching mechanism based on emergency assessment results, link multiple entities, dynamically track and adjust services based on early warning and observation conditions.

Images