Abnormal condition management method and system applied to large-scale smart old-age care community

Abstract

The invention relates to the technical field of community management, and particularly discloses an abnormal condition management method and system applied to a large intelligent old-age care community, and the method comprises the steps: obtaining the significant weak information of a marked old person, and marking the old person as a marked old user; generating potential abnormal scene information according to the significant weak item information; monitoring the scene information of the marked old person, and when the scene information is matched with the potential abnormal scene information, continuously obtaining physiological information based on a wearable intelligent device on the marked old person; judging or predicting whether the elderly user feels uncomfortable according to the physiological information and preset first early warning value information, and generating event processing information if the elderly user feels uncomfortable; according to the method, personalized risk assessment, intelligent scene recognition, real-time physiological monitoring and a quick response mechanism for marking the elderly are performed based on the significant weak item information, so that the management efficiency of the pension community is improved, and a safer and more comfortable living environment is provided for the elderly.

Description

Technical Field

[0001] The present application relates to the field of community management technology, and more specifically, to an abnormal situation management method and system applied to a large-scale smart elderly care community. Background Art

[0002] In the later years of life, mental health issues have become increasingly prominent as a complex and multi-dimensional challenge. These problems are often not caused by a single factor, but the result of the interweaving and interaction of multiple factors. As the main living residence for the elderly, the internal environment of the retirement community has a direct and far-reaching impact on the psychological and physiological state of the elderly.

[0003] Abnormal events that affect the mental and physical health of the elderly may occur in retirement communities. When these abnormal events occur, if community workers or family members fail to discover and properly handle them in a timely manner, they will often lead to greater conflicts and accidents, further aggravating the psychological or physical burden on the elderly.

[0004] There is currently no effective technical solution to the above problems. Summary of the invention

[0005] The purpose of this application is to provide a method and system for managing abnormal situations in large-scale smart elderly care communities, so as to improve the management efficiency of elderly care communities and provide a safer and more comfortable living environment for the elderly.

[0006] In a first aspect, the present application provides a method for managing abnormal conditions in a large-scale smart elderly care community, which is used to monitor abnormal conditions of elderly users. The method comprises the following steps: S1. Obtaining significant weakness information of the marked elderly, and marking the elderly as the marked elderly user; S2. Generate potential abnormal scenario information based on significant weakness information; S3, monitoring the scene information where the marked elderly person is located, and when the scene information matches the potential abnormal scene information, continuously acquiring physiological information based on the wearable smart device on the marked elderly person; S4. Determine or predict whether the elderly user is experiencing discomfort based on the physiological information and the preset first warning value information, and generate event processing information if so.

[0007] The abnormal situation management method applied to large-scale smart elderly care communities in this application builds a comprehensive abnormal situation management system. It can improve the management efficiency of elderly care communities and provide a safer and more comfortable living environment for the elderly through personalized risk assessment, intelligent scene recognition, real-time physiological monitoring and rapid response mechanism based on significant weakness information. Compared with the traditional elderly care management method that relies on regular physical examinations and fixed-time inspections, the abnormal situation management method applied to large-scale smart elderly care communities in this application can respond to problems at an early stage, greatly reducing the risk of serious accidents.

[0008] The abnormal situation management method applied to a large-scale smart elderly care community, wherein step S1 includes the following sub-steps: S11, obtaining characteristic information of different elderly users, where the characteristic information includes one or more of body shape information, health information, personality information, asset information, and family relationship information; S12, extracting the weakness features of each elderly user according to the feature information and a preset feature range; S13. Determine whether each elderly user is a marked elderly person by comprehensively considering the weakness features, and extract the significant weakness features of the marked elderly people as significant weakness information.

[0009] The above steps obtain multi-dimensional feature information of elderly users, extract weak features, and comprehensively determine whether they are marked elderly people, thereby identifying groups that need special attention.

[0010] The abnormal situation management method applied to a large-scale smart elderly care community, wherein step S13 includes the following sub-steps: S131, calculating a potential abnormality score for each elderly user according to the weak feature and the corresponding feature weight, and defining the elderly user as a marked elderly user when the potential abnormality score is greater than a preset score; S132. Extract the weak feature corresponding to the weighted feature value of the marked elderly person that is greater than a preset weighted value as significant weak feature information, wherein the weighted feature value is the product of the weak feature and the corresponding feature weight.

[0011] The above steps achieve accurate identification of marked elderly people and extraction of key weaknesses by introducing the concepts of potential anomaly scores and weighted eigenvalues; when calculating potential anomaly scores, the weights of different weakness features are taken into account, which makes the identification process more accurate. At the same time, by setting a preset score as a threshold, the identification criteria of marked elderly people can be flexibly adjusted; in addition, after determining the marked elderly people, the process of extracting significant weakness information adopts the weighted eigenvalue method to ensure that only the most important weaknesses that are most likely to cause abnormal events are identified. This method takes into account the importance of the weaknesses themselves and the influence of feature weights, thereby improving the accuracy and relevance of significant weakness information.

[0012] The abnormal situation management method applied to a large-scale smart elderly care community, wherein step S13 includes the following sub-steps: S131', obtain the types of various abnormal events that have occurred in the smart elderly care community; S132', screening elderly users according to the weak features associated with the types of various abnormal events that have occurred, and defining elderly users who have at least one weak feature associated with the type of abnormal event that has occurred as marked elderly people; S133', extracting and marking all the weak features of the elderly that are associated with the types of abnormal events that have occurred as significant weak information.

[0013] The abnormal situation management method applied to a large-scale smart elderly care community, wherein the potential abnormal scene information includes: one or more of location information, time information, activity content information, number of people information and gender information of participants.

[0014] The abnormal situation management method applied to a large-scale smart elderly care community, wherein step S2 includes the following sub-steps: The potential abnormal scene information is extracted from a pre-constructed mapping table associated with the significant weakness information and the potential abnormal scene information based on the significant weakness information.

[0015] The abnormal situation management method applied to a large-scale smart elderly care community, wherein the step of judging or predicting whether the elderly user is uncomfortable based on the physiological information and the preset first warning value information includes the following sub-steps: S41. Continuously compare the physiological information with the preset first warning value information. If the physiological information is greater than the first warning value information, it is considered that the elderly user has or is about to have discomfort.

[0016] The abnormal situation management method applied to a large-scale smart elderly care community, wherein the event processing information includes a trigger signal, and the step of generating event processing information includes the following sub-steps: S42: Generate a trigger signal for triggering the scene monitoring component in the scene where the marked elderly person is located to start, so that the scene monitoring component collects and packages event information, and pushes the packaged event information to the target user.

[0017] The abnormal situation management method applied to a large-scale smart elderly care community, wherein the steps between step S3 and step S4 also include the following steps: S5. Determine whether the marked elderly person has ever felt uncomfortable in similar potential abnormal scene information. If yes, generate invitation information to invite the target user to be monitored through the scene monitoring component.

[0018] In the second aspect, the present application also provides an abnormal situation management system applied to a large-scale smart elderly care community, which is used to monitor abnormal situations of elderly users, and the system includes: The server side is used to obtain the significant weakness information of the marked elderly, mark the elderly as the marked elderly user, and generate potential abnormal scene information according to the significant weakness information; A scene monitoring component, connected to the server end for monitoring scene information where the marked elderly person is located; A wearable smart device is connected to the server end for communication and is worn on the elderly user to collect physiological information; The server is also used to determine whether the scene information matches the potential abnormal scene information, and if they match, obtain the physiological information through the wearable smart device; The server is also used to judge or predict whether the elderly user is experiencing discomfort based on the physiological information and the preset first warning value information, and generate event processing information if so.

[0019] This application is applied to the abnormal situation management system of large-scale smart elderly care communities through the collaborative work of multiple technical features to achieve the application of abnormal situation management in large-scale smart elderly care communities. The server side, as the core processing unit, is responsible for obtaining the information of marked elderly people, generating potential abnormal scene information, judging the scene matching degree, analyzing physiological data and generating early warnings. This enables the system to carry out personalized monitoring for the weaknesses of specific elderly users. The scene monitoring component monitors the environment of the marked elderly in real time, provides scene information to the server side, and enables the system to identify potential dangerous situations in a timely manner. Wearable smart devices collect physiological information of elderly users and provide real-time health data to the server side, so that the system can detect physical abnormalities of elderly users in a timely manner. The server side compares the actual scene with the preset potential abnormal scene, triggers the collection of physiological information when it matches, realizes targeted monitoring, and improves system efficiency. Finally, the server side makes judgments based on the collected physiological information and the preset early warning value, generates event processing information in a timely manner, and realizes a rapid response to abnormal situations of elderly users.

[0020] From the above, it can be seen that the present application provides a method and system for managing abnormal situations in large-scale smart elderly care communities, wherein the method can improve the management efficiency of elderly care communities and provide a safer and more comfortable living environment for the elderly by performing personalized risk assessment, intelligent scene recognition, real-time physiological monitoring and rapid response mechanism based on significant weakness information to mark the elderly. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flowchart of an abnormal situation management method applied to a large-scale smart elderly care community provided in some embodiments of the present application.

[0022] Figure 2 A flowchart of an abnormal situation management method applied to a large-scale smart elderly care community provided in some other embodiments of the present application.

[0023] Figure 3 A schematic diagram of the structure of an abnormal situation management system for a large-scale smart elderly care community provided in an embodiment of the present application.

[0024] Figure numerals: 201, server side; 202, scene monitoring component; 203, wearable smart device. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0026] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0027] In smart elderly care communities, the mental health and personal safety of the elderly face complex challenges. Due to their physical and psychological vulnerabilities, some elderly people are more susceptible to various forms of impact. Current elderly care management systems often lack the ability to accurately identify and respond to these potential risks in a timely manner.

[0028] Especially for elderly people with specific weaknesses, existing management methods are difficult to provide personalized protection. For example, elderly people with limited mobility may be more likely to fall in certain scenarios; while elderly people with reduced cognitive abilities may be more vulnerable to psychological harm in complex social environments. The lack of this targeted protection makes it difficult for retirement communities to provide the most suitable care and support for each elderly person.

[0029] In daily life, the elderly may encounter various potential risk scenarios. For example, when participating in group activities at a community activity center, due to cognitive impairment, he may misunderstand the goodwill of others and experience unnecessary anxiety or depression. Or, when taking a walk alone, he may feel unwell due to a sudden increase in blood pressure, but no one around him notices it in time.

[0030] Existing management systems have difficulty accurately predicting the risks in these specific scenarios, and are unable to monitor changes in the physiological and psychological states of the elderly in real time. This makes it impossible for managers to take targeted preventive measures, or to respond quickly when emergencies occur. In addition, due to the lack of personalized risk assessment, the system cannot distinguish the special needs of different elderly people, and thus cannot provide the most suitable protection measures.

[0031] First, please refer to Figure 1 and Figure 2 In view of the above phenomenon, some embodiments of the present application provide an abnormal situation management method applied to a large-scale smart elderly care community, which is used to monitor abnormal situations of elderly users. The method includes the following steps: S1. Obtaining significant weakness information of the marked elderly, and marking the elderly as the marked elderly user; S2. Generate potential abnormal scenario information based on significant weakness information; S3, monitoring the scene information where the marked elderly person is located, and when the scene information matches the potential abnormal scene information, continuously acquiring physiological information based on the wearable smart device on the marked elderly person; S4. Determine or predict whether the elderly user is experiencing discomfort based on the physiological information and the preset first warning value information, and generate event processing information if so.

[0032] Specifically, obtain information on the significant weaknesses of the marked elderly: This step can be achieved in a variety of ways. For example, information on the elderly's physical condition, cognitive ability, social ability, etc. can be collected through medical records, daily observations, psychological assessments, etc. It is also possible to use smart devices to record the elderly's behavior patterns for a long time and analyze potential weaknesses from them. In addition, regular questionnaires or interviews can be used to obtain the weaknesses perceived by the elderly themselves.

[0033] More specifically, the elderly users are the elderly people living in the smart elderly care community. Step S1 actually determines which elderly users in the smart elderly care community are marked elderly people, and determines what kind of significant weakness information these marked elderly people have. In fact, the marked elderly people can be understood as elderly users in the smart elderly care community who are at risk of having their mental and physical health affected due to exposure to significant weakness information. The significant weakness information is the more prominent or more likely to cause weaknesses of the marked elderly people.

[0034] More specifically, potential abnormal scene information is generated based on significant weakness information: This step can be achieved by establishing a weakness-scene mapping database. For example, for elderly people with limited mobility, potential abnormal scenes may include bathrooms, stairs, etc.; for elderly people with cognitive impairments, potential abnormal scenes may include complex social activities or tasks that require memory. The system can also continuously optimize and update this mapping relationship based on historical data through machine learning algorithms. Potential abnormal scene information is a scene that may affect the psychological and physical health of the marked elderly with corresponding significant weakness information, and may include data such as location, time, and activity content.

[0035] More specifically, monitor the scene information where the marked elderly are located: This can be achieved through a variety of technical means, such as indoor positioning systems, smart home sensors, GPS of wearable devices, cameras, etc., which can be selected individually or in combination according to the specific composition of the potential abnormal scene information. The system needs to compare the scene where the marked elderly are currently located with the scene corresponding to the potential abnormal scene information in real time. Once a match is found, the next step of physiological information monitoring is initiated.

[0036] More specifically, wearable smart devices can be smart watches, smart bracelets, or specially designed medical-grade monitoring devices. These devices can monitor multiple physiological indicators such as heart rate, blood pressure, body temperature, and activity level in real time.

[0037] More specifically, judging or predicting discomfort based on physiological information and preset first warning value information: This step involves data analysis and the establishment of a prediction model. Other implementations may also set multiple levels of warning values, such as mild warning, moderate warning, and severe warning. The first warning value information may be personalized based on the specific circumstances of each elderly person.

[0038] More specifically, event processing information is generated: once it is determined that the elderly may be unwell, the abnormal situation management method applied to a large-scale smart elderly care community in the embodiment of the present application can generate various types of event processing information. For example, for a mild warning, it may only send a reminder message to the caregiver; for a serious warning, the system may automatically call emergency medical services and notify family members at the same time.

[0039] More specifically, in the embodiment of the present application, step S1 and step S2 belong to the data preparation process, which is used to determine the elderly users who need attention and the corresponding scenarios, and step S3 and step S4 belong to the management process, which is used to monitor and process the scenarios that may affect the psychological and physical health of the marked elderly. Among them, the significant weakness information of the marked elderly directly affects the generation of potential abnormal scene information, and the scene monitoring and the acquisition of physiological information cooperate with each other. Only in the potential risk scenario will more intensive physiological monitoring be initiated, which not only ensures the targeted monitoring, but also avoids unnecessary interference.

[0040] More specifically, from a holistic perspective, the abnormal situation management method applied to large-scale smart elderly care communities in the embodiment of the present application builds a comprehensive abnormal situation management system. It uses personalized risk assessment, intelligent scene recognition, real-time physiological monitoring, and rapid response mechanisms to mark the elderly based on significant weakness information. Compared with the traditional elderly care management method that relies on regular physical examinations and fixed-time inspections, the abnormal situation management method applied to large-scale smart elderly care communities in the embodiment of the present application can respond to problems at an early stage, greatly reducing the risk of serious accidents.

[0041] More specifically, the abnormal situation management method applied to large-scale smart elderly care communities in the embodiment of the present application realizes highly personalized risk management by combining personal characteristics, scene information and physiological data. This precise management method not only improves safety, but also avoids unnecessary interference, allowing the elderly to maintain a high degree of life autonomy while being fully protected, and effectively solves the technical problems of timely identification and management of abnormal situations.

[0042] In some preferred embodiments, step S1 includes the following sub-steps: S11, obtaining characteristic information of different elderly users, where the characteristic information includes one or more of body shape information, health information, personality information, asset information, and family relationship information; S12, extracting the weak features of each elderly user according to the feature information and the preset feature range; S13. Determine whether each elderly user is a marked elderly person by comprehensively considering the weakness features, and extract the significant weakness features of the marked elderly people as significant weakness information.

[0043] Specifically, the above steps obtain multi-dimensional feature information of elderly users, extract weak features, and comprehensively judge whether they are marked elderly people, so as to identify groups that need special attention; specifically, first, by collecting information such as the body shape, health, personality, assets and family relationships of elderly users, we can fully understand the situation of each elderly person. This information provides basic data for subsequent analysis. Then, according to the preset feature range, the weak features of each elderly user are extracted from the acquired feature information to identify potential risk points that may exist for each elderly person. Next, the weak features are comprehensively analyzed to determine whether each elderly user belongs to the marked elderly, and the elderly groups that need special attention and protection are screened out. Finally, for users who are judged to be marked elderly people, their significant weak features are further extracted as significant weak information for subsequent risk prevention and management.

[0044] It should be noted that, in step S12, different types of feature information pairings have different feature ranges.

[0045] More specifically, in the step of obtaining characteristic information, the present application can collect information in a variety of ways. For example, the body shape information and health information of elderly users, including height, weight, blood pressure, heart rate and other data, can be collected through smart wearable devices. Personality information can be obtained through psychological tests or daily behavior analysis, asset information can be obtained through financial records authorized by elderly users, and family relationship information can be obtained through questionnaires or information provided by family members. This multi-dimensional information collection ensures a comprehensive understanding of the status of elderly users.

[0046] More specifically, in the step of extracting weak features, the present application pre-sets a feature range. For example, for health information, blood pressure exceeding 140 / 90 mmHg or below 90 / 60 mmHg can be defined as a weak feature. For personality information, personality traits of being overly withdrawn or irritable can be defined as a weak feature. This method of pre-setting a range makes the extraction of weak features more objective and standardized.

[0047] More specifically, in the step of extracting significant weakness information, the present application not only considers the existence of weakness features, but also their severity. For example, for health-related weakness features, their significance can be judged according to the degree of deviation from normal values. This ensures that the extracted significant weakness information truly reflects the aspects that the marked elderly need to pay most attention to.

[0048] More specifically, the abnormal situation management method applied to large-scale smart elderly care communities in the embodiment of the present application adopts multi-dimensional feature information collection, which not only includes health status, but also takes into account factors such as personality, assets and family relationships. This makes the assessment of elderly users more comprehensive and accurate, and the practice of comprehensively identifying and marking elderly people and extracting corresponding significant weakness information provides a clear direction for subsequent targeted care and risk prevention, allowing smart elderly care communities to more effectively allocate elderly care resources and improve the accuracy and efficiency of elderly care services.

[0049] In some preferred embodiments, step S13 includes the following sub-steps: S131, calculating the potential abnormality score of each elderly user according to the weak feature and the corresponding feature weight, and defining the elderly user as a marked elderly when the potential abnormality score is greater than a preset score; S132. Extract the weak feature corresponding to the weighted feature value of the marked elderly person that is greater than the preset weighted value as the significant weak feature information, where the weighted feature value is the product of the weak feature and the corresponding feature weight.

[0050] Specifically, the above steps achieve accurate identification of marked elderly people and extraction of key weaknesses by introducing the concepts of potential anomaly scores and weighted eigenvalues; when calculating potential anomaly scores, the weights of different weakness features are taken into account, which makes the identification process more accurate. At the same time, by setting a preset score as a threshold, the identification criteria of marked elderly people can be flexibly adjusted; in addition, after determining the marked elderly people, the process of extracting significant weakness information adopts the weighted eigenvalue method to ensure that only the most important weaknesses that are most likely to cause abnormal events are identified. This method takes into account the importance of the weaknesses themselves and takes into account the influence of feature weights, thereby improving the accuracy and relevance of significant weakness information.

[0051] It should be noted that in the process of weighted calculation, weak features need to be normalized first.

[0052] More specifically, in the specific implementation process, the present application first obtains the weakness characteristics of each elderly user, which correspond to the relatively weak parts of the aforementioned feature information, and is compared and determined through the feature range of step S12. For example, body shape information that exceeds the feature range will produce a weakness characteristic of obesity or thinness, and the weakness characteristic includes a characteristic value that indicates the strength of the corresponding weakness. Weakness characteristics may include physical condition, cognitive ability, social ability, economic status, and other aspects. For example, physical condition may include mobility, vision, hearing, etc.; cognitive ability may include memory, comprehension, judgment, etc.; social ability may include communication ability, emotional control ability, etc.; economic status may include income level, asset status, etc.

[0053] More specifically, different types of weak features are assigned different feature weights, which can be set based on historical data analysis, expert experience, or machine learning algorithms. For example, you can analyze abnormal events that occurred in the past year, count the frequency of occurrence of each weak feature in these events, and use the frequency of occurrence as the basis for weights. In addition, you can also adjust the weights based on the severity of the impact that different weak features may cause.

[0054] More specifically, the potential anomaly score can be calculated by multiplying the value of each weak feature by its corresponding feature weight, and then adding all the results; the preset score is a judgment threshold for determining whether an elderly user is a marked elderly person, and the preset score can be adjusted according to the actual situation of the retirement community.

[0055] More specifically, for elderly users defined as marked elderly people, the abnormal situation management method applied to large-scale smart elderly care communities in the embodiment of the present application further extracts their corresponding significant weakness information. The extraction process is equivalent to screening out the weak features corresponding to the insignificant weighted eigenvalues, and taking the weak features whose remaining weighted eigenvalues ​​are greater than the preset weighted values ​​as the significant weakness information; the preset weighted value is the judgment threshold for defining whether the weakness feature is significant.

[0056] More specifically, step S131 and step S132 can not only accurately identify the marked elderly, but also accurately locate the key weaknesses of each marked elderly, which provides precise guidance for the formulation of subsequent preventive measures and emergency plans, so that the abnormal situation management method applied to large-scale smart elderly care communities in the embodiment of the present application has the advantages of high accuracy in identifying marked elderly and reliable service.

[0057] In addition, the abnormal situation management method applied to large-scale smart elderly care communities in the embodiment of the present application has strong flexibility and adjustability. By adjusting the feature weights, preset scores and preset weighted values, the identification criteria can be optimized according to the actual conditions and needs of different elderly care communities. This flexibility enables the method to adapt to elderly care communities of different sizes and types, and can also be continuously optimized and improved over time and with the accumulation of data.

[0058] In practical applications, the method of this application can be integrated into the management system of a smart elderly care community. The system can update the weakness feature data of elderly users regularly or in real time, automatically calculate potential abnormal scores and identify significant weakness information. This information can be presented to managers through a visual interface, or it can be linked with other subsystems (such as monitoring systems, emergency call systems, etc.) to form a comprehensive elderly user management system.

[0059] In some preferred embodiments, the feature weights of different weakness features are set based on the historical occurrence times or frequencies of various abnormal events in the smart elderly care community.

[0060] Specifically, the method of using historical data of various abnormal events in smart elderly care communities to set feature weights of different weak features has the advantages of data-driven, dynamic adjustment, improved accuracy and personalization; by associating historical data with weak features, it achieves more accurate identification of marked elderly people, taking into account not only the weak features themselves, but also the performance of these features in actual abnormal events, thereby improving the effectiveness and reliability of the entire abnormal situation management system.

[0061] More specifically, feature weights can be set by one or more of the following methods: frequency statistics, risk assessment, machine learning, time decay, and expert experience. These methods can be used alone or in combination according to specific circumstances. For example, frequency statistics can be used first to obtain preliminary weights, which can then be adjusted in combination with risk assessment methods, and finally fine-tuned through expert experience.

[0062] More specifically, the abnormal situation management method applied to large-scale smart elderly care communities in the embodiment of the present application sets feature weights by using historical data, fully considering the specific conditions of each elderly care community, making the identification of marked elderly people more accurate and personalized, and better reflecting the importance of different weak features in actual abnormal events; in addition, the method of the present application also has the advantage of dynamic adjustment. As new abnormal events occur and are recorded, the system can automatically update the weights of each feature, so that the identification of marked elderly people is always accurate and timely.

[0063] In some other embodiments, step S13 includes the following sub-steps: S131', obtain the types of various abnormal events that have occurred in the smart elderly care community; S132', screening elderly users according to the weak features associated with the types of various abnormal events that have occurred, and defining elderly users who have at least one weak feature associated with the type of abnormal event that has occurred as marked elderly people; S133', extracting and marking all the weak features of the elderly that are associated with the types of abnormal events that have occurred as significant weak information.

[0064] Specifically, this implementation method obtains the types of abnormal events that have occurred and associates these event types with the weak features of elderly users, so as to more accurately identify and mark the elderly. This method identifies and marks the elderly based on actual events that have occurred in the smart elderly care community, improves the accuracy and specificity of the identification, and realizes strong correlation management of the smart elderly care community.

[0065] More specifically, in the implementation process, obtaining the types of abnormal events that have occurred in the smart elderly care community can be achieved in a variety of ways. For example, an event reporting system can be established, and community staff, caregivers or family members can record and report abnormal events in a timely manner.

[0066] More specifically, when screening elderly users based on the weak features associated with the types of abnormal events that have occurred, a dynamically updated association matrix can be established, which associates different types of abnormal events with the weak features that may have caused these events.

[0067] More specifically, when defining the marked elderly, the implementation adopts a flexible method: elderly users who have at least one weak feature associated with the type of abnormal event that has occurred are defined as marked elderly. This method takes into account the individual differences of the elderly and avoids overly strict or loose standards.

[0068] More specifically, the weakness features of all types of weakness associated with abnormal events that have occurred in the elderly are extracted and marked as significant weakness information. The weakness features include major weaknesses that directly lead to abnormal events and minor weaknesses that may indirectly affect or aggravate the impact, which effectively ensures that potential risk factors are not missed and provides comprehensive information support for subsequent prevention and management.

[0069] More specifically, in this embodiment, the method of the present application adopts a method based on actual data and dynamic updates to determine the marked elderly and the corresponding significant weakness information. It establishes a data foundation based on actual conditions by obtaining the types of abnormal events that have occurred, and then creates a dynamic screening mechanism by associating the types of abnormal events with the weakness characteristics of elderly users. This enables the abnormal situation management method applied to large-scale smart elderly care communities in the embodiment of the present application to be continuously optimized with the occurrence of new events and the accumulation of new data, thereby improving the accuracy of recognition.

[0070] In some preferred implementations, the potential abnormal scene information includes one or more of location information, time information, activity content information, number of people information, and gender information of participants.

[0071] It should be noted that step S3 continuously monitors the scene information of the marked elderly through scene monitoring components. The type composition of these scene information is consistent with the type composition of potential abnormal scene information or is included in the type composition of potential abnormal scene information. These scene monitoring components may include site equipment of the smart elderly care community, such as surveillance cameras, etc., and may also include remote devices that follow the movement of the marked elderly, such as mobile phones, wearable smart devices, etc.

[0072] Specifically, by defining the components of potential abnormal scene information in detail, this application provides a more comprehensive information basis for identifying and preventing potential dangerous situations. Specifically, location information helps to determine the specific environment in which the marked elderly are located, time information can reflect specific risks that may exist in different time periods, activity content information can indicate the specific activities that the elderly are doing, and the number of people information can reflect whether the elderly are alone or accompanied by someone. The gender information of the participants may be related to certain specific types of risks. This combination of multi-dimensional information greatly improves the accuracy of identifying potential dangerous situations.

[0073] More specifically, potential abnormal scene information can be implemented in a variety of ways. For example, location information can include specific locations such as indoors, outdoors, stairs, bathrooms, etc., and can also include GPS coordinates or indoor positioning information. Time information can be a specific time point or a time period, such as morning, late at night, etc. Activity content information can be predefined activity types, such as walking, dining, bathing, etc., or it can be an action type recognized by a smart device. Number information can be a specific number or classified information, such as being alone, group activities, etc. The gender information of the participants can be a single gender or mixed gender identification.

[0074] More specifically, there are close connections and interactions between these different types of information. For example, when the location information shows that the elderly is in the bathroom, the time information shows that it is late at night, the activity content information shows that it may be bathing, and the number of people information shows that it is alone, the system may determine that this is a high-risk scenario because the elderly bathing alone at night may be at risk of falling or other accidents. This combination of multi-dimensional information allows the system to more accurately identify potential dangerous situations.

[0075] More specifically, the complete potential abnormal scene information processing process can be described as follows: First, the abnormal situation management method applied to a large-scale smart elderly care community in the embodiment of the present application will generate a corresponding potential abnormal scene information template based on the significant weakness information of the marked elderly, and then continuously monitor the real-time scene information of the elderly, including location, time, activity content, number of people and gender of participants, etc., and match the real-time scene information with the preset potential abnormal scene information. If the matching degree exceeds the preset threshold, the abnormal situation management method applied to a large-scale smart elderly care community in the embodiment of the present application will trigger further monitoring measures, such as continuously obtaining the physiological information of the elderly through wearable smart devices. This intelligent triggering mechanism based on detailed scene information can not only detect potential risks in a timely manner, but also avoid unnecessary excessive monitoring, thereby achieving a balance between protecting the safety of the elderly and respecting the privacy of the elderly.

[0076] In some preferred embodiments, step S2 includes the following sub-steps: The potential abnormal scene information is extracted from a pre-constructed mapping table associated with the significant weakness information and the potential abnormal scene information based on the significant weakness information.

[0077] Specifically, the abnormal situation management method applied to large-scale smart elderly care communities in the embodiment of the present application realizes the rapid correspondence between significant weakness information and potential abnormal scene information by pre-constructing a mapping table that associates significant weakness information and potential abnormal scene information. It can quickly and accurately generate corresponding potential abnormal scene information based on the acquired significant weakness information of marked elderly people, which provides an important basis for subsequent monitoring and early warning work, helps to timely discover and prevent possible dangerous situations, and improves the safety management level of smart elderly care communities.

[0078] More specifically, the mapping table can be a combination of multiple significant weakness information corresponding to one potential abnormal scene information, or a combination of multiple significant weakness information corresponding to a set of multiple potential abnormal scene information, or one significant weakness information corresponding to one potential abnormal scene information, or one significant weakness information corresponding to a set of multiple potential abnormal scene information.

[0079] More specifically, the mapping table can be constructed based on expert experience, historical data analysis, and machine learning algorithms. The mapping table can continuously optimize and update the mapping relationship by analyzing historical abnormal events that have occurred to marked elderly people in different scenarios.

[0080] In some preferred embodiments, the step of judging or predicting whether the elderly user is experiencing discomfort based on the physiological information and the preset first warning value information includes the following sub-steps: S41. Continuously compare the physiological information with the preset first warning value information. If the physiological information is greater than the first warning value information, it is considered that the elderly user has or is about to have discomfort.

[0081] Specifically, the abnormal situation management method applied to large-scale smart elderly care communities in the embodiment of the present application judges or predicts whether the elderly users are experiencing discomfort by continuously comparing physiological information and preset first warning value information. This method utilizes measurable physiological indicators, especially heart rate information, to objectively evaluate the health (including psychological and physiological) status of the elderly users; among them, the preset first warning value is used as a reference standard, which can be personalized according to the individual differences of different elderly users to improve the accuracy of judgment.

[0082] More specifically, physiological information can be obtained in a variety of ways. For example, wearable devices such as smart bracelets or smart watches can be used to monitor elderly users' heart rate, blood pressure, body temperature and other physiological indicators in real time. These devices can upload data through wireless communication technologies such as Bluetooth or Wi-Fi.

[0083] More specifically, the process of continuously comparing physiological information with the preset first warning value information can be carried out in real-time monitoring or interval monitoring; if it is found that the physiological information exceeds the first warning value information, the abnormal situation management method applied to large-scale smart elderly care communities in the embodiment of the present application can immediately generate event processing information. In order to avoid false alarms, a short observation period can also be set. For example, event processing information will only be generated if three consecutive measurements exceed the warning value.

[0084] More specifically, this real-time monitoring and early warning mechanism based on physiological information has significant advantages over traditional regular physical examinations or manual observation methods. It can monitor the health status of elderly users 24 hours a day, greatly improving the speed of discovering and handling abnormal situations. At the same time, since objective physiological indicators are used as the basis for judgment, the errors that may be caused by subjective judgment are reduced, the accuracy of early warning is improved, and the workload of caregivers is reduced, allowing them to allocate their time and energy more efficiently.

[0085] In some other implementations, the step of judging or predicting whether the elderly user is experiencing discomfort based on the physiological information and the preset first warning value information includes the following sub-steps: S41', obtaining the fluctuation mean of the physiological information exceeding the preset first warning value information, if the fluctuation mean is greater than the fluctuation mean of other marked elderly people under the same potential abnormal scene information, it is considered that the elderly user has or is about to feel unwell.

[0086] Specifically, in this embodiment, obtaining the fluctuation mean of physiological information exceeding the warning value can reflect the abnormal degree of the elderly user's physiological state. Compared with simply comparing the physiological information with the warning value, the fluctuation mean can more comprehensively reflect the changing trend of the physiological state; secondly, comparing with the data of other marked elderly people in the same scene can eliminate the general influence of environmental factors on physiological indicators and more accurately identify individual abnormalities; this embodiment improves the accuracy of judgment by introducing group reference data, and not only considers the absolute value of individual physiological indicators, but also considers the changes relative to the group, so as to more accurately identify abnormal conditions that really need attention, and can effectively reduce misjudgments to increase sensitivity to potential risks.

[0087] More specifically, the process of obtaining the fluctuation mean of the physiological information exceeding the preset first warning value information can be achieved in the following manner: More specifically, the magnitude of each time the physiological information exceeds the warning value is recorded; then, the average of these exceeding values ​​is calculated within a certain time window (such as 30 seconds or 1 minute) to obtain the fluctuation mean. This method not only considers the degree to which the physiological indicators exceed the warning value, but also considers the persistence and frequency of the exceeding, thereby more comprehensively reflecting the abnormal degree of the physiological state.

[0088] More specifically, if the fluctuation mean is greater than the fluctuation mean of other marked elderly people under the same potential abnormal scene information, it means that the marked elderly person may have or is about to experience discomfort. If the fluctuation mean is significantly greater than the fluctuation mean of other marked elderly people under the same potential abnormal scene information (for example, more than 20%), it means that the marked elderly person has already experienced discomfort. This processing method takes into account the general impact of environmental factors on physiological indicators and can more accurately identify true individual abnormalities.

[0089] In some preferred embodiments, the event processing information includes a trigger signal, and the step of generating the event processing information includes the following sub-steps: S42: Generate a trigger signal for triggering the start of a scene monitoring component in the scene where the marked elderly person is located, so that the scene monitoring component collects and packages event information, and pushes the packaged event information to a target user.

[0090] Specifically, the target user may be one or more of a manager, a caregiver, and a relative.

[0091] More specifically, the trigger signal will activate the monitoring component that marks the scene where the elderly person is located to monitor the elderly person's condition and the condition of the place where he is located in real time; after the scene monitoring component is activated, it will collect all information related to the current event and integrate and package this information. The packaged event information will be pushed to the target user to ensure that relevant personnel can understand the situation in a timely manner and take necessary actions.

[0092] More specifically, the collected and packaged event information can include data in multiple dimensions, such as video surveillance data, audio data, environmental sensor data, etc. These data can be synchronized through timestamps to ensure the integrity and consistency of the information. Information push can be delivered in a variety of ways, such as SMS, application notifications, phone calls, etc., and the appropriate push method can be selected according to the urgency and preferences of the target users.

[0093] More specifically, compared with traditional retirement community management methods, the abnormal situation management method applied to large-scale smart retirement communities in the embodiments of the present application has significant advantages in early detection and rapid response to abnormal situations. It greatly improves the efficiency of detection and handling of abnormal situations through intelligent monitoring and automated information processing.

[0094] In some preferred implementations, the step of generating event processing information further includes the following sub-steps: S43: Generate an alarm signal.

[0095] In some preferred embodiments, the step S3 and the step S4 further include the following steps: S5. Determine whether the marked elderly person has ever felt uncomfortable in similar potential abnormal scene information. If so, generate an invitation message to invite the target user to be monitored through the scene monitoring component.

[0096] Specifically, step S5 is executed after monitoring the scene information of the elderly and obtaining physiological information, and before judging and predicting discomfort. It forms a multi-level and more comprehensive monitoring system through historical data analysis, early warning, manual monitoring intervention and improving monitoring efficiency.

[0097] More specifically, in the specific implementation, the abnormal situation management method applied to a large-scale smart elderly care community in the embodiment of the present application needs to establish a historical database of marked elderly people to record the discomfort of each marked elderly person in different scenarios. This database can contain the following information: marked elderly person ID, potential abnormal scene type, discomfort occurrence time, discomfort symptom description, treatment method, etc. When the system detects that the marked elderly person enters a potential abnormal scene, it will immediately query the database.

[0098] More specifically, the generation of invitation information can be set with different priorities according to different urgency levels. For example, if historical data shows that the elderly have experienced severe discomfort in this scenario, the system will generate a high-priority invitation message and notify multiple target users simultaneously through SMS, phone calls, or smart bracelets. If it is a minor discomfort, only a single target user may be notified through App push.

[0099] More specifically, the above steps fully consider the historical circumstances of the marked elderly and introduce manual supervision when necessary, forming a more comprehensive supervision system. By combining historical data analysis and manual supervision, the system can detect potential problems earlier, improve the level of protection for marked elderly people, and reduce the possibility of discomfort or injury.

[0100] Second, please refer to Figure 3 Some embodiments of the present application also provide an abnormal situation management system applied to a large-scale smart elderly care community, which is used to monitor abnormal situations of elderly users. The system includes: The server side 201 is used to obtain significant weakness information of the marked elderly, mark the elderly as the marked elderly user, and generate potential abnormal scene information according to the significant weakness information; The scene monitoring component 202 is connected to the server 201 for monitoring the scene information where the marked elderly person is located; A wearable smart device 203 is connected to the server 201 and is worn by an elderly user to collect physiological information; The server 201 is also used to determine whether the scene information matches the potential abnormal scene information, and if they match, obtain physiological information through the wearable smart device; The server end 201 is also used to judge or predict whether the elderly user is experiencing discomfort based on the physiological information and the preset first warning value information, and generate event processing information if so.

[0101] The system realizes the management of abnormal situations in large-scale smart elderly care communities through the collaborative work of multiple technical features. The server side 201, as the core processing unit, is responsible for obtaining the information of the marked elderly, generating potential abnormal scene information, judging the scene matching degree, analyzing physiological data and generating early warnings. This enables the system to carry out personalized monitoring for the weaknesses of specific elderly users. The scene monitoring component 202 monitors the environment of the marked elderly in real time, provides scene information to the server side 201, and enables the system to identify potential dangerous situations in a timely manner. The wearable smart device 203 collects the physiological information of the elderly user and provides real-time health data to the server side 201, so that the system can detect the physical abnormalities of the elderly user in a timely manner. The server side 201 compares the actual scene with the preset potential abnormal scene, triggers the physiological information collection when matching, realizes targeted monitoring, and improves the efficiency of the system. Finally, the server side 201 makes judgments based on the collected physiological information and the preset early warning value, generates event processing information in a timely manner, and realizes a rapid response to abnormal situations of elderly users.

[0102] It should be noted that, in some implementations, the wearable smart device 203 may be included in the scene monitoring component 202 . For example, when the wearable smart device 203 has a positioning function, the server 201 may obtain the wearable smart device 203 in the scene information through the wearable smart device 203 .

[0103] The abnormal situation management system applied to a large-scale smart elderly care community in the embodiment of the present application realizes all-round and intelligent monitoring of the elderly by integrating the server side 201, the scene monitoring component 202 and the wearable smart device 203, and can generate personalized potential abnormal scene information according to the specific situation of each elderly person, which greatly improves the pertinence and effectiveness of monitoring. Secondly, the use of intelligent judgment and automatic early warning functions greatly reduces the pressure of manual monitoring and improves the management efficiency of the elderly care community.

[0104] In some preferred embodiments, the abnormal situation management method applied to a large-scale smart elderly care community provided in the first aspect of the present application is preferably applied in the abnormal situation management system applied to a large-scale smart elderly care community provided in the second aspect.

[0105] In the embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. The system embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some communication interface, device or unit, which can be electrical, mechanical or other forms.

[0106] In addition, the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0107] Furthermore, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0108] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0109] The above description is only an embodiment of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for managing abnormal situations in a large-scale smart elderly care community, used to monitor abnormal situations of elderly users, characterized in that: The method comprises the following steps: S1. Obtaining significant weakness information of the marked elderly, and marking the elderly as the marked elderly user; S2. Generate potential abnormal scenario information based on significant weakness information; S3, monitoring the scene information where the marked elderly person is located, and when the scene information matches the potential abnormal scene information, continuously acquiring physiological information based on the wearable smart device on the marked elderly person; S4. Determine or predict whether the elderly user is experiencing discomfort based on the physiological information and the preset first warning value information, and generate event processing information if so.

2. The abnormal situation management method applied to a large-scale smart elderly care community according to claim 1 is characterized in that: Step S1 includes the following sub-steps: S11, obtaining characteristic information of different elderly users, where the characteristic information includes one or more of body shape information, health information, personality information, asset information, and family relationship information; S12, extracting the weakness features of each elderly user according to the feature information and a preset feature range; S13. Determine whether each elderly user is a marked elderly person by comprehensively considering the weakness features, and extract the significant weakness features of the marked elderly people as significant weakness information.

3. The abnormal situation management method applied to a large-scale smart elderly care community according to claim 2 is characterized in that: Step S13 includes the following sub-steps: S131, calculating a potential abnormality score for each elderly user according to the weak feature and the corresponding feature weight, and defining the elderly user as a marked elderly user when the potential abnormality score is greater than a preset score; S132. Extract the weak feature corresponding to the weighted feature value of the marked elderly person that is greater than a preset weighted value as significant weak feature information, wherein the weighted feature value is the product of the weak feature and the corresponding feature weight.

4. The abnormal situation management method applied to a large-scale smart elderly care community according to claim 2 is characterized in that: Step S13 includes the following sub-steps: S131', obtain the types of various abnormal events that have occurred in the smart elderly care community; S132', screening elderly users according to the weak features associated with the types of various abnormal events that have occurred, and defining elderly users who have at least one weak feature associated with the type of abnormal event that has occurred as marked elderly people; S133', extracting and marking all the weak features of the elderly that are associated with the types of abnormal events that have occurred as significant weak information.

5. The abnormal situation management method applied to a large-scale smart elderly care community according to claim 1 is characterized in that: The potential abnormal scene information includes: one or more of location information, time information, activity content information, number of people information, and gender information of participants.

6. The abnormal situation management method applied to a large-scale smart elderly care community according to claim 1 is characterized in that: Step S2 includes the following sub-steps: The potential abnormal scene information is extracted from a pre-constructed mapping table associated with the significant weakness information and the potential abnormal scene information based on the significant weakness information.

7. The abnormal situation management method applied to a large-scale smart elderly care community according to claim 1 is characterized in that: The step of judging or predicting whether the elderly user is experiencing discomfort based on the physiological information and the preset first warning value information comprises the following sub-steps: S41. Continuously compare the physiological information with the preset first warning value information. If the physiological information is greater than the first warning value information, it is considered that the elderly user has or is about to have discomfort.

8. The abnormal situation management method applied to a large-scale smart elderly care community according to claim 1 is characterized in that: The event processing information includes a trigger signal, and the step of generating the event processing information includes the following sub-steps: S42: Generate a trigger signal for triggering the scene monitoring component in the scene where the marked elderly person is located to start, so that the scene monitoring component collects and packages event information, and pushes the packaged event information to the target user.

9. The abnormal situation management method applied to a large-scale smart elderly care community according to claim 1 is characterized in that: The steps between step S3 and step S4 include: S5. Determine whether the marked elderly person has ever felt uncomfortable in similar potential abnormal scene information. If yes, generate invitation information to invite the target user to be monitored through the scene monitoring component.

10. An abnormal situation management system applied to a large-scale smart elderly care community, used to monitor abnormal situations of elderly users, characterized in that: The system comprises: The server side is used to obtain the significant weakness information of the marked elderly, mark the elderly as the marked elderly user, and generate potential abnormal scene information according to the significant weakness information; A scene monitoring component, connected to the server end for monitoring scene information where the marked elderly person is located; A wearable smart device is connected to the server end for communication and is worn on the elderly user to collect physiological information; The server is also used to determine whether the scene information matches the potential abnormal scene information, and if they match, obtain the physiological information through the wearable smart device; The server is also used to judge or predict whether the elderly user is experiencing discomfort based on the physiological information and the preset first warning value information, and generate event processing information if so.

Images