Data real-time analysis method and system applied to large-scale smart old-age care community

Abstract

The invention relates to the technical field of smart old-age care communities, and particularly discloses a data real-time analysis method and system applied to a large smart old-age care community, and the method comprises the steps: obtaining user tag information and current position information; obtaining load information, project type information and difference information of each function place of the same function type; acquiring preference information of the user according to the user tag information, and acquiring distance information of the user about each functional place according to the current position information; generating recommendation information according to the preference information, the project type information, the difference information, the distance information and the load information; according to the method, customized suggestions are provided in combination with the state of each functional place and the specific condition of the user, the problems of dynamic optimal allocation and personalized service of resources in a large smart old-age care community are effectively solved, the life experience of the user is improved, and the quality improvement of the old-age care service is promoted.

Description

Technical Field

[0001] The present application relates to the technical field of smart elderly care communities, and more specifically, to a real-time data analysis method and system for use in large-scale smart elderly care communities. Background Art

[0002] With the advancement of science and technology, the concept of smart elderly care communities has emerged, aiming to improve the quality of life and management efficiency of the elderly through intelligent means. Such communities use advanced Internet of Things technology and data analysis systems to monitor and analyze key data within the campus (specifically the elderly care community environment) in real time, including but not limited to the occupancy of chess and card rooms, reading activity in the library, the number of people eating in the cafeteria, and the frequency of visits to the infirmary. These data are integrated on the campus data visualization screen to provide community managers with an intuitive and comprehensive management view, which helps to respond to various needs in a timely manner and optimize resource allocation.

[0003] However, although these management methods have greatly enhanced the operational efficiency of the community, they often focus on macro-level management and monitoring, while ignoring direct interaction and service connections with individual elderly care users. As the core objects of community services, the personalized needs, health conditions, and daily activity preferences of elderly care users have not been fully integrated into the existing data management and service system, resulting in a certain degree of disconnection between service provision and actual user needs.

[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 real-time data analysis method and system applied to large-scale smart elderly care communities, to solve the problems of dynamic optimization allocation of resources and personalized services in large-scale smart elderly care communities, so that service provision is interconnected with actual user needs.

[0006] In a first aspect, the present application provides a real-time data analysis method applied to a large-scale smart elderly care community, which is used to analyze the status of various functional places in the community, and the method comprises the following steps: S1. Obtain user tag information and current location information; S2. Obtaining load information, project type information and difference information of each functional place of the same functional type; S3, obtaining the user's preference information according to the user tag information, and obtaining the user's distance information to each functional place according to the current location information; S4. Generate recommendation information based on the preference information, the item type information, the difference information, the distance information and the load information.

[0007] The real-time data analysis method applied to large-scale smart elderly care communities in the present application conducts a multi-dimensional analysis based on key factors such as user preference information and project type information, difference information, distance information, and load information of functional places, and generates personalized recommendation information to provide customized suggestions based on the status of each functional place and the specific situation of the user. It effectively solves the problems of dynamic optimization allocation of resources and personalized services in large-scale smart elderly care communities, enhances the intelligent management level of elderly care communities, improves resource utilization efficiency, improves users' life experience, and promotes the quality of elderly care services.

[0008] The real-time data analysis method applied to a large-scale smart elderly care community, wherein the functional type of the functional place is one of a dining hall, a library, an entertainment room, a sports room, a physical therapy room, and a medical room.

[0009] In this example, these functional places cover the elderly's daily needs for eating, reading, entertainment, exercise, health care, and medical treatment, providing a basis for solving the problem of diverse types of functional places.

[0010] The real-time data analysis method applied to a large-scale smart elderly care community, wherein the user tag information includes: one or more of household registration information, gender information, personality information, age information, health information, asset information and consumption habit information.

[0011] In this example, the real-time data analysis method applied to a large-scale smart elderly care community in the embodiment of the present application collects multi-dimensional user tag information, builds user portraits, and provides personalized and precise service support for the smart elderly care community. This method can comprehensively and dynamically capture user characteristics, help improve the accuracy and pertinence of elderly care services, and achieve refined matching of user needs.

[0012] The real-time data analysis method applied to a large-scale smart elderly care community, wherein the difference information includes: one or more of consumption level difference information, environmental quality difference information, equipment quality information, and service quality difference information.

[0013] In the real-time data analysis method applied to a large-scale smart elderly care community, the step of obtaining load information of each functional place of the same functional type includes: Acquire status information of various function venues of the same function type, the status information including venue capacity, number of people who have entered, number of people who have left, and number of people participating in activities; The load information of each functional venue is generated according to the venue capacity, the number of people who have entered, the number of people who have left, and the number of people who have participated in the activity.

[0014] The real-time data analysis method applied to a large-scale smart elderly care community, wherein the steps between step S3 and step S4 further include: SA,generates predicted arrival time information based on distance information; SB. Predict and compensate the load information based on the predicted arrival time information.

[0015] The real-time data analysis method applied to a large-scale smart elderly care community, wherein the preference information includes: preference information and preference weight; Step S4 includes: S41, selecting a suitable functional place according to the matching degree between the preference information and the project category information; S42, generating a score value for each filtered functional place according to the preference weight, the difference information, the distance information and the load information; S43: Generate the recommendation information based on the rating value.

[0016] The real-time data analysis method applied to a large-scale smart elderly care community, wherein the step between step S42 and step S43 further includes the following steps: S4A. Compensate and adjust the score value of each filtered functional venue based on the user's historical participation information.

[0017] The real-time data analysis method applied to a large-scale smart elderly care community, wherein the user historical participation information includes historical evaluation information and / or historical effective activity duration information.

[0018] In the second aspect, the present application also provides a real-time data analysis system applied to a large-scale smart elderly care community, which is used to analyze the status of various functional places in the community. The system includes: The client is used to collect and obtain user tag information and current location information, and upload it to the server; The site data collection terminal is used to collect and obtain the load information, project type information and difference information of each functional site of the same functional type, and upload it to the server; The server side is used to obtain the user's preference information according to the user tag information, and obtain the user's distance information to each functional place according to the current location information; The server is further configured to generate recommendation information according to the preference information, the item type information, the difference information, the distance information and the load information, and send the recommendation information to the client.

[0019] The real-time data analysis system applied to large-scale smart elderly care communities in the embodiment of the present application provides customized suggestions based on the status of each functional venue and the specific circumstances of the user, effectively solving the problems of dynamic optimization allocation of resources and personalized services in large-scale smart elderly care communities.

[0020] From the above, it can be seen that the present application provides a real-time data analysis method and system applied to large-scale smart elderly care communities, wherein the real-time data analysis method applied to large-scale smart elderly care communities comprehensively analyzes key factors such as user preference information and project type information, difference information, distance information and load information of functional places, and generates personalized recommendation information to provide customized suggestions based on the status of each functional place and the specific situation of the user, effectively solving the problems of dynamic optimization allocation of resources and personalized services in large-scale smart elderly care communities, enhancing the intelligent management level of elderly care communities, improving resource utilization efficiency, improving users' life experience, and promoting the quality of elderly care services. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flowchart of a real-time data analysis method applied to a large-scale smart elderly care community provided in some embodiments of the present application.

[0022] Figure 2 A flowchart of a real-time data analysis 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 a real-time data analysis system for a large-scale smart elderly care community provided in an embodiment of the present application.

[0024] Figure numerals: 201, client; 202, location data collection terminal; 203, server terminal. 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] First, please refer to Figure 1 and Figure 2 Some embodiments of the present application provide a real-time data analysis method applied to a large-scale smart elderly care community, which is used to analyze the status of various functional places in the community. The method includes the following steps: S1. Obtain user tag information and current location information; S2. Obtaining load information, project type information and difference information of each functional place of the same functional type; S3. Obtaining the user's preference information according to the user tag information, and obtaining the user's distance information to each functional place according to the current location information; S4. Generate recommendation information based on the preference information, project type information, difference information, distance information and load information.

[0028] Specifically, the real-time data analysis method applied to a large-scale smart elderly care community in an embodiment of the present application aims to analyze the status of each functional place in real time and provide personalized recommendations for users. It mainly generates recommendation information based on a certain type of functional place that the user needs to go to. For example, if the user needs to go to the canteen for dinner, step S2 obtains the relevant parameters of each canteen in the smart elderly care community, and then generates personalized recommendation information suitable for the user for the user's reference and selection.

[0029] More specifically, user tag information refers to attribute information that describes the user characteristics of the corresponding user, and current location information is used to describe the user's location, which can be determined by a device with positioning function carried by the user.

[0030] More specifically, in order to fully understand the real-time status of each functional place, the real-time data analysis method applied to a large-scale smart elderly care community in the embodiment of the present application proposes a means of obtaining load information, project type information and difference information of each functional place of the same functional type, wherein the load information reflects the real-time usage of the corresponding functional place, the project type information indicates the type of service provided by the corresponding functional place, and the difference information reflects the characteristics and advantages and disadvantages between different corresponding functional places.

[0031] More specifically, step S3 performs analysis based on user tag information and current location information to obtain user preferences and distance information, which are related to the user's preferences for different project types or different conditions of functional places. Then step S4 combines key factors such as preference information, project type information, difference information, distance information and load information for multi-dimensional analysis to generate personalized recommendation information. This processing method can not only reflect the status of each functional place in real time, but also provide customized suggestions based on the specific situation of each user, effectively solving the problems of dynamic optimization allocation of resources and personalized services in large-scale smart elderly care communities, enhancing the intelligent management level of elderly care communities, improving resource utilization efficiency, improving users' life experience, and promoting the quality of elderly care services.

[0032] The real-time data analysis method applied to large-scale smart elderly care communities in the embodiment of the present application comprehensively analyzes key factors such as user preference information and project type information, difference information, distance information and load information of functional places, and generates personalized recommendation information to provide customized suggestions based on the status of each functional place and the specific situation of the user, effectively solving the problems of dynamic optimization allocation of resources and personalized services in large-scale smart elderly care communities, enhancing the intelligent management level of elderly care communities, improving resource utilization efficiency, improving users' life experience, and promoting the quality of elderly care services.

[0033] In some preferred embodiments, the functional type of the functional place is one of a dining room, a library, an entertainment room, a sports room, a physical therapy room, and a medical room.

[0034] Specifically, these functional places cover the elderly's daily needs for eating, reading, entertainment, exercise, health care and medical treatment, providing a basis for solving the problem of diversified types of functional places.

[0035] More specifically, the real-time data analysis method applied to a large-scale smart elderly care community in the embodiment of the present application can perform more accurate data analysis and service recommendations for different types of places by clarifying the types of functional places; it should be noted that since step S2 is aimed at obtaining the status information of each functional place of the same functional type, therefore, in actual use, the real-time data analysis method applied to a large-scale smart elderly care community in the embodiment of the present application provides recommendations for functional places of a functional type. After the user selects the functional place of the corresponding functional type through the client, the real-time data analysis method applied to a large-scale smart elderly care community in the embodiment of the present application can generate appropriate recommendation information. For example, for the canteen, the number of diners and dining preferences can be analyzed; for the library, reading preferences and borrowing frequency can be analyzed; for the recreation room and the exercise room, the activity participation and usage time can be analyzed; for the physiotherapy room and the medical room, the health needs and usage frequency can be analyzed. This classification method makes the data analysis more targeted and can better meet the needs of the elderly in different aspects.

[0036] More specifically, in addition, clarifying the functional types of functional places can provide a clear direction for subsequent data collection, analysis and recommendation. The real-time data analysis method applied to large-scale smart elderly care communities in the embodiment of the present application can set corresponding data collection points and analysis models according to functional places of different functional types, so as to more accurately obtain the load information, project type information and difference information of each place, which can be combined with the user's tag information and location information to generate more personalized and accurate recommendation information; in addition, the real-time data analysis method applied to large-scale smart elderly care communities in the embodiment of the present application can also set different presentation forms or styles for recommendation information according to functional places of different functional types, such as canteens can be recommended based on dishes, pictures, etc., and libraries can be recommended based on the catalog of borrowable books.

[0037] In general, clarifying the functional types of functional places can provide a comprehensive and targeted framework for real-time data analysis of large-scale smart elderly care communities, and can better solve the challenges of data analysis and service recommendation brought about by the diversity of functional place types.

[0038] In some preferred implementations, the user tag information includes: one or more of household registration information, gender information, personality information, age information, health information, asset information, and consumption habit information.

[0039] Specifically, the real-time data analysis method applied to large-scale smart elderly care communities in the embodiment of the present application collects multi-dimensional user tag information, builds user portraits, and provides personalized and precise service support for smart elderly care communities. This method can comprehensively and dynamically capture user characteristics, help improve the accuracy and pertinence of elderly care services, and achieve refined matching of user needs.

[0040] More specifically, household registration information can help understand the user's geographical background and cultural characteristics. For example, elderly people from different regions may have different eating habits or cultural preferences, and this information can be used to customize services. Gender information is used to identify the user's basic physiological characteristics. This is very important for providing gender-related health services or activity arrangements. Personality information is used to analyze the user's behavioral preferences and interaction methods. For example, extroverted elderly people may prefer to participate in group activities, while introverted elderly people may prefer a quiet environment. Age information is used to judge the user's physiological and psychological characteristics. Elderly people of different age groups may have different needs and interests. Health information is used to assess the user's physical condition and service needs. This is essential for developing personalized health management plans and providing appropriate medical services. Asset information is used to analyze the user's consumption ability and service acceptance. This helps recommend services and activities that are suitable for the user's economic conditions, which can include income and deposits. Consumption habit information is used to predict the user's interests and preferences. This can help the system more accurately recommend services and activities that meet the user's preferences.

[0041] More specifically, the real-time data analysis method applied to a large-scale smart elderly care community in the embodiment of the present application can construct a comprehensive user portrait by comprehensively analyzing these multi-dimensional user tag information, which can not only capture the static characteristics of the user, but also reflect the dynamic changes of the user. For example, changes in health information may affect the user's activity participation, and changes in consumption habits may reflect changes in user interests.

[0042] More specifically, the user tag information collection system can obtain data through multiple channels. For example, household registration information and gender information can be directly obtained when the user registers; personality information can be obtained through psychological testing or behavioral analysis; age information can be automatically updated based on ID card information; health information can be obtained through regular physical examinations or real-time monitoring by smart wearable devices; asset information can be obtained through financial data analysis authorized by the user; consumption habit information can be obtained by analyzing the user's consumption records and activity participation in the community; it should be noted that all this information is obtained without violating the relevant privacy agreement.

[0043] More specifically, traditional user tag information often only focuses on basic demographic information, such as age and gender, while ignoring the personalized needs and dynamic changes of the elderly. The real-time data analysis method applied to large-scale smart elderly care communities in the embodiments of the present application can not only fully understand the characteristics of each elderly person, but also capture their changes in needs in a timely manner through multi-dimensional user tag information collection. This refined user portrait can support more personalized and dynamic service recommendations, greatly improving the accuracy of the service and user satisfaction. At the same time, the method of the present application also provides community managers with more comprehensive and in-depth user insights, which helps to optimize resource allocation and service design and improve overall operational efficiency.

[0044] In some preferred implementations, the difference information includes: one or more of consumption level difference information, environmental quality difference information, equipment quality information, and service quality difference information.

[0045] Specifically, the difference information is used to describe the difference between different places of the same functional type, which includes multiple aspects: the consumption level difference information reflects the price level of different places, which helps to provide suitable choices for users with different economic abilities; the environmental quality difference information describes the environmental conditions and building conditions of the place, such as noise, light, temperature, etc., to meet the different needs of users for comfort; the equipment quality information reflects the degree of advancement and perfection of the facilities in the place, and adapts to the preferences of different users for equipment requirements; the service quality difference information reflects the service level of each place, including service attitude, professionalism, etc., to meet users' expectations for service quality. These difference information plays a key role in solving the problem of how to recommend the most suitable functional place for users. By comprehensively considering these differences, the real-time data analysis method applied to large-scale smart elderly care communities in the embodiment of the present application can more accurately match user needs and place characteristics, and improve the accuracy of recommendations and user satisfaction.

[0046] More specifically, each feature of the difference information can be implemented in a variety of ways. For example, consumption level difference information can be determined by analyzing the historical consumption records and price tags of the venue; environmental quality difference information can be achieved through sensors monitoring parameters such as noise, light, and temperature; equipment quality information can be obtained by checking the model of the equipment, maintenance records, etc.; service quality difference information can be evaluated through user feedback, service ratings and other data. The connection and interaction between each feature is that they jointly affect the user's choice of venue. By analyzing this information, the system can better recommend venues that meet user preferences.

[0047] More specifically, by analyzing the difference information of each place, the real-time data analysis method applied to a large-scale smart elderly care community in the embodiment of the present application can identify the unique advantages and disadvantages of each place, thereby providing users with more targeted recommendations. Compared with the solution that only considers the basic functions of the place, the method of the present application can better meet the personalized needs of users, improve user satisfaction and the utilization efficiency of community resources.

[0048] More specifically, by introducing difference information, the real-time data analysis method applied to large-scale smart elderly care communities in the embodiment of the present application can effectively solve the problem of inaccurate recommendations in the prior art, improve the accuracy of the recommendation system and user satisfaction, and refine the analysis of differences between functional venues. It can more comprehensively evaluate each functional venue and provide users with recommendations that are more in line with personal preferences and needs.

[0049] In some preferred implementations, the step of obtaining load information of each functional place of the same functional type includes: Obtain status information of each functional venue of the same functional type, including venue capacity, number of people who have entered, number of people who have left, and number of people participating in activities; Generate load information for each functional venue based on venue capacity, number of people entering, number of people leaving, and number of people participating in activities.

[0050] It should be noted that the number of people who have entered and left is the data of the corresponding functional venue on the day or the data of the current activity round.

[0051] Specifically, the above status information can be obtained through intelligent sensors, cameras or manual entry systems. The capacity of the venue can be a preset fixed value or dynamically adjusted according to actual conditions. The number of people who have entered can be counted in real time through the access control system or crowd counter at the entrance or the camera in front of the door, and the number of people leaving can also be recorded in real time through the access control system or crowd counter at the exit or the camera in front of the door. The number of people participating in the event can be obtained through the event registration system or the on-site check-in system, consumption system, or can be taken and counted through indoor cameras set up on site.

[0052] More specifically, the real-time data analysis method applied to a large-scale smart elderly care community in the embodiment of the present application can calculate the load information based on a simple load rate algorithm, such as load rate = (number of people entering - number of people leaving + number of people participating in the activity) / venue capacity * 100%. In this implementation, the number of people participating in the activity is equivalent to generating double load, or a more complex weighted algorithm can be used to consider the changing characteristics of the flow of people in different time periods; in addition, the real-time data analysis method applied to a large-scale smart elderly care community in the embodiment of the present application can also adjust the calculation method of the load information according to the characteristics of functional venues of different functional types. For example, for the canteen, the number of people queuing and the table occupancy rate can be considered more, and for the library, the seat occupancy rate can be considered more; for the exercise room, the equipment utilization rate may need to be considered; for the medical room, it may be necessary to combine the appointment situation and the need for emergency medical treatment.

[0053] More specifically, by obtaining the capacity of the venue, the number of people who have entered, the number of people who have left, and the number of people participating in the activity to calculate in real time the load information, the real-time data analysis method applied to the large-scale smart elderly care community in the embodiment of the present application can reflect the usage status of each functional venue in real time and accurately. This not only provides accurate data support for community managers, but also provides convenience for elderly users to choose suitable activity venues.

[0054] More specifically, in some other implementations, the load information may also be rated based on pre-classified load levels to ensure that the load information can be easily compared and analyzed.

[0055] In some preferred implementations, the load information includes one or more of: project occupancy rate information, project average duration information, and queue duration information.

[0056] Specifically, the technical solution of the present application can be implemented to obtain detailed load information in a variety of ways. For example, project occupancy information can be collected through a real-time monitoring system or a sensor network to record the real-time usage of each functional place. The average duration of the project can be calculated by analyzing the user entry and exit records or the activity participation time (such as the duration of user seat occupancy in the library). Queuing time information can be obtained through an intelligent queuing system or crowd monitoring equipment (which can be estimated based on the number of people in the queue).

[0057] More specifically, there is a close correlation and interaction between these detailed load information. The project occupancy rate information reflects the overall use of the venue, while the project average duration information provides the time dimension of the user's use behavior. The queue time information directly reflects the crowdedness and service efficiency of the venue. These three types of information complement each other and together constitute a comprehensive data analysis basis; the project occupancy rate information can reflect the crowdedness of the corresponding projects in each functional venue (such as the occupancy of the dining table), the project average duration information can reflect the user's stay time in each functional venue (such as the average dining time), and the queue time information directly reflects the number of participants in each functional venue. These data combined can directly reflect the use of each functional venue in the current and future period of time, which is conducive to the real-time data analysis method applied to large-scale smart elderly care communities in the embodiment of the present application to assist users in generating personalized recommendation information to meet user needs. For example, for some users who do not like to queue, they are more inclined to functional venues with smaller queue time information, and for some users who like lively places, they are more inclined to functional venues with large project occupancy rate information, and for some impatient users, they are more inclined to functional venues with small project average duration information and small queue time information.

[0058] More specifically, the real-time data analysis method applied to large-scale smart elderly care communities in the embodiment of the present application determines the load information by comprehensively considering the project occupancy rate, average duration and waiting time, and generates recommendation information accordingly, providing more comprehensive and detailed data support, making data analysis decisions more accurate and effective, which not only optimizes resource allocation but also improves user experience.

[0059] In some preferred embodiments, the method further includes the following steps between step S3 and step S4: SA,generates predicted arrival time information based on distance information; SB, predict the compensation load information based on the predicted arrival time information.

[0060] Specifically, the predicted arrival time information is the time node after the user moves to the corresponding functional place estimated based on the user's current location information, that is, step SA calculates and obtains the predicted arrival time information about each functional place of the same functional type.

[0061] More specifically, the practice of predicting and compensating load information in step SB actually takes into account the fact that it takes a certain amount of time for the user to reach the functional place from the current location, during which the load situation may change; the real-time data analysis method applied to large-scale smart elderly care communities in the embodiment of the present application predicts the user's arrival time and compensates for the load information based on this time, thereby providing more accurate and targeted recommendations.

[0062] More specifically, generating predicted arrival time information based on distance information can be achieved in a variety of ways. For example, the arrival time can be estimated by simply dividing the linear distance by the average walking speed, or a more accurate predicted time can be calculated by combining map data and a path planning algorithm. In addition, the predicted time can also be adjusted by considering factors such as the user's age and health status; in the embodiment of the present application, the predicted arrival time information is preferably predicted based on the user's recent historical average walking speed combined with map data and a path planning algorithm.

[0063] More specifically, the step of predicting the compensation load information based on the predicted arrival time information can use a variety of algorithms. For example, historical data can be used to analyze the load change trend, and the current load and the predicted arrival time can be combined to predict the future load through interpolation or extrapolation methods. Another method is to use a machine learning model, such as a time series prediction model, to consider multiple factors (such as time, date, weather, etc.) to predict the future load.

[0064] More specifically, there is a close relationship between these two steps. The predicted arrival time information provides a time dimension for load compensation, making the load forecast more accurate. At the same time, the compensated load information can in turn affect the decision of the recommendation system. For example, if it is predicted that the load will increase significantly when the user arrives, the method of this application may suggest that the user choose other times or other functional places. For another example, a certain functional place may require queuing, but the load information after compensation predicted by the predicted arrival time information may represent a state where queuing is not required. In this case, the functional place will be added to the recommendation for users who do not like queuing.

[0065] More specifically, compared with the prior art, the real-time data analysis method applied to a large-scale smart elderly care community in the embodiment of the present application significantly improves the accuracy and practicality of the recommendation by introducing the steps of predicting arrival time and load compensation. Traditional methods may only consider the current load conditions and ignore the situations that users may face when they actually arrive. The real-time data analysis method applied to a large-scale smart elderly care community in the embodiment of the present application provides users with more valuable information by predicting future loads, helping users make more informed decisions, thereby improving user satisfaction and the overall efficiency of the system.

[0066] In some preferred embodiments, the preference information includes: preference information and preference weight; Step S4 includes: S41, selecting a suitable functional venue according to the matching degree between the preference information and the project type information; S42, generating a score value for each screened functional place according to the preference weight, difference information, distance information and load information; S43: Generate recommendation information based on the rating value.

[0067] Specifically, the real-time data analysis method applied to large-scale smart elderly care communities in the embodiment of the present application introduces user preference information (including preference information and preference weights) as basic data, combined with project type information, difference information, distance information and load information of functional venues, to achieve a multi-step, multi-dimensional recommendation process.

[0068] More specifically, the preference information reflects the user's favorite types and / or interest levels in the item category information of the functional venues. For example, for a canteen, the item category information includes dishes of different cuisines, and the preference information includes the cuisines that the user likes. For another example, for a library, the item category information includes different types of books, and the preference information includes the types of books that the user likes. Therefore, step S41 preliminarily screens out potential suitable venues by matching the preference information and the item category information, thereby ensuring the basic relevance of the recommendation results to the user's interests. Then, step S42 uses more detailed information (such as preference weights, difference information, distance information, and load information) to score the screened venues, taking into account multiple factors such as the importance of user preferences, differences between venues, geographical convenience, and current usage, thereby obtaining a comprehensive and objective evaluation result. Finally, the final recommendation information is generated based on these scores to provide users with personalized and real-time venue recommendations.

[0069] More specifically, the preference weight reflects the degree of importance users place on the difference information, distance information and load information of functional places, and is used to configure different weights for the difference information, distance information and load information to calculate the score value. For example, if the user pays more attention to the round-trip distance, the corresponding configured preference weight has a larger weight for the distance information, so that the score value pays more attention to the distance information.

[0070] More specifically, step S42 can be to generate three basic scores based on the difference information, distance information and load information respectively, and then calculate the score of the functional place in combination with the preference weights of the three basic scores; through this multi-dimensional scoring mechanism, the real-time data analysis method applied to large-scale smart elderly care communities in the embodiment of the present application can generate a comprehensive score for each screened functional place. This score not only reflects the matching degree between the place and the user's preference, but also takes into account the convenience and comfort of actual use.

[0071] More specifically, the difference information may include the facility level of the venue, the comfort of the environment, etc., which will affect the actual experience of the user. Distance information takes into account the convenience of the geographical location and can be quantified by calculating the actual distance or estimated walking time from the user's current location to each venue. Load information reflects the current usage status of the venue and can avoid recommending venues that are already overcrowded. All of these data can be quantitatively analyzed based on preset standards or analysis models to convert them into basic scores; finally, based on these scoring values, the system generates the final recommendation information. This information can be a ranked list showing the highest-scoring venues, or it can be a more detailed information card containing the specific situation and recommendation reasons for each recommended venue. The possible form is as follows: "Dear Mr. Zhang, based on your preferences and current situation, we recommend the following activity venues for you: XX chess and card room (5 minutes walking distance): comfortable environment, moderate current usage rate, very suitable for you to enjoy a game of chess."

[0072] More specifically, in some embodiments, the recommendation information may include a list of functional venues and corresponding scores arranged in descending order based on the rating values, and may also include an introduction to one or more of project type information, difference information, distance information, and load information.

[0073] More specifically, this personalized recommendation method has significant advantages over traditional fixed recommendations or simple location-based recommendations. It fully considers multiple factors such as the user's personal preferences, the real-time status of the venue, and geographical convenience, and can more accurately meet the needs of users. For example, even if the preference weight of the chess and card room is higher, if it is already overcrowded, the method of the present application will appropriately lower its recommendation priority. This dynamic adjustment can effectively avoid resource congestion and improve the overall user experience. Secondly, the method of the present application is also very flexible and scalable, and can be easily adjusted and updated as the user's preferences change or new functional venues are added. This is of great significance to the long-term operation of large-scale smart elderly care communities and the continuous improvement of service quality.

[0074] In some preferred embodiments, the step between step S42 and step S43 further includes the following steps: S4A. Compensate and adjust the score value of each filtered functional venue based on the user's historical participation information.

[0075] Specifically, the real-time data analysis method applied to large-scale smart elderly care communities in the embodiment of the present application introduces user historical participation information as a compensatory adjustment factor to adjust the scoring values ​​of functional venues. By considering the user's historical participation, it can more comprehensively reflect the user's actual preferences and usage of each functional venue, thereby improving the accuracy and personalization of the scoring.

[0076] More specifically, the real-time data analysis method applied to a large-scale smart elderly care community in the embodiment of the present application effectively solves the problem of insufficient accuracy of the rating value by introducing the user's historical participation information to adjust the rating value in the process of generating recommendation information; specifically, after generating preliminary rating values ​​based on preference weights, difference information, distance information, and load information, the method of the present application will further consider the user's historical participation information to adjust these ratings. This adjustment mechanism can better reflect the user's actual needs and preferences, thereby improving the accuracy and personalization of recommendations. In this way, the method of the present application can provide users of large-scale smart elderly care communities with more accurate and personal recommendations for functional venues, thereby improving user experience and the utilization efficiency of community resources.

[0077] More specifically, the real-time data analysis method applied to a large-scale smart elderly care community in an embodiment of the present application can set different weights according to different types of historical participation information; for example, a higher weight can be given to the score value corresponding to the functional venue in which the user participated most in the past month, because this can better reflect the user's current preference.

[0078] More specifically, compared with the prior art, the technical solution of the present application has significant advantages. Traditional recommendation methods usually only consider the user's immediate needs and environmental factors, while ignoring the user's historical behavior and long-term preferences, which may lead to deviations between the recommendation results and the user's actual needs. The real-time data analysis method applied to a large-scale smart elderly care community in the embodiment of the present application can more comprehensively capture the user's preferences and behavior patterns by introducing the user's historical participation information, thereby generating more accurate and personalized recommendations, which not only improves the accuracy of the recommendation, but also enhances the user's trust in the recommended information, thereby improving the service quality and user satisfaction of the entire smart elderly care community.

[0079] In some preferred implementations, the user's historical participation information includes historical evaluation information and / or historical effective activity duration information.

[0080] Specifically, user historical participation information can include multiple forms. For example, it can include historical evaluation information, which reflects the user's satisfaction and preference for a specific functional venue. Another form is historical effective activity duration information, which indicates the time the user actually participated in the activity in each functional venue. Both types of information can provide valuable reference for rating adjustment.

[0081] More specifically, the historical evaluation information may be the user's score or comment on the functional venue, which reflects the user's subjective evaluation of the functional venue. By analyzing the user's score, comment and other data on the functional venue in different periods, the user's overall satisfaction with the functional venue can be obtained; if a user has given a higher evaluation to a functional venue in the past, then when generating a new recommendation, the score value of the functional venue may be appropriately increased; on the contrary, if the user's historical evaluation of a functional venue is low, then the score value of the functional venue may be reduced accordingly.

[0082] More specifically, the historical effective activity duration information records the actual length of time that users stay in a venue. These data reflect the actual usage of each functional venue by users and can objectively reflect the frequency of use and preference of users for functional venues. For example, if a user often stays in a library for a long time, even if he does not give a clear evaluation, the system can infer that the user has a high preference for this library, thereby appropriately increasing the rating of the library when generating recommendations.

[0083] More specifically, historical evaluation information can be in various forms, such as star ratings, text reviews, or satisfaction surveys. These evaluation data are standardized and converted into rating adjustment factors. Historical effective activity duration information can be obtained through the location system or card swiping records in the venue, and the effective activity duration is determined by setting a time threshold and converted into a duration weight factor.

[0084] More specifically, through the comprehensive use of historical evaluation information and historical effective activity duration information, the real-time data analysis method applied to large-scale smart elderly care communities in the embodiment of the present application realizes the precise adjustment of the scoring values ​​of functional places; in the adjustment process, the scoring adjustment factor is first calculated based on the historical evaluation information, and then the duration weight factor is generated in combination with the historical effective activity duration information, and finally these two factors are weightedly calculated with the original scoring value to obtain the final scoring value.

[0085] More specifically, the real-time data analysis method applied to a large-scale smart elderly care community in the embodiment of the present application introduces user historical participation information to establish a complete score adjustment mechanism. Compared with the prior art, it not only takes into account the user's subjective evaluation, but also combines objective usage data, so that the recommendation results are more in line with the user's actual needs and usage habits. This dual-dimensional score adjustment mechanism effectively improves the accuracy and personalization of the recommendation system.

[0086] Second, please refer to Figure 3 Some embodiments of the present application also provide a real-time data analysis system applied to a large-scale smart elderly care community, which is used to analyze the status of various functional places in the community. The system includes: The client 201 is used to collect and obtain user tag information and current location information, and upload them to the server 203; The site data collection terminal 202 is used to collect and obtain the load information, project type information and difference information of each functional site of the same functional type, and upload it to the server terminal 203; The server side 203 is used to obtain the user's preference information according to the user tag information, and obtain the user's distance information about each functional place according to the current location information; The server 203 is further configured to generate recommendation information according to the preference information, item type information, difference information, distance information, and load information, and send the recommendation information to the client 201 .

[0087] The real-time data analysis system applied to large-scale smart elderly care communities in the embodiment of the present application comprehensively analyzes key factors such as user preference information and project type information, difference information, distance information and load information of functional places, and generates personalized recommendation information to provide customized suggestions based on the status of each functional place and the specific situation of the user, effectively solving the problems of dynamic optimization allocation of resources and personalized services in large-scale smart elderly care communities, enhancing the intelligent management level of elderly care communities, improving resource utilization efficiency, improving users' life experience, and promoting the quality of elderly care services.

[0088] It should be noted that the client 201 can be installed in a smart terminal carried by the user, such as a mobile phone, a smart watch, etc.; the place data collection terminal 202 can include collection devices such as cameras, access control systems, etc. set in various functional places and capable of communicating with the server 203.

[0089] In some preferred implementations, the server side 203 is further configured to generate predicted arrival time information based on the distance information and predict the compensation load information according to the predicted arrival time information.

[0090] 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 only 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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 real-time data analysis method applied to a large-scale smart elderly care community, used to analyze the status of each functional place in the community, characterized in that: The method comprises the following steps: S1. Obtain user tag information and current location information; S2. Obtaining load information, project type information and difference information of each functional place of the same functional type; S3, obtaining the user's preference information according to the user tag information, and obtaining the user's distance information to each functional place according to the current location information; S4. Generate recommendation information based on the preference information, the item type information, the difference information, the distance information and the load information.

2. The real-time data analysis method applied to a large-scale smart elderly care community according to claim 1 is characterized in that: The functional type of the functional place is one of a dining room, a library, an entertainment room, a sports room, a physical therapy room, and a medical room.

3. The real-time data analysis method applied to a large-scale smart elderly care community according to claim 1 is characterized in that: The user tag information includes: one or more of household registration information, gender information, personality information, age information, health information, asset information and consumption habit information.

4. The real-time data analysis method applied to a large-scale smart elderly care community according to claim 1 is characterized in that: The difference information includes: one or more of consumption level difference information, environmental quality difference information, equipment quality information, and service quality difference information.

5. The real-time data analysis method applied to a large-scale smart elderly care community according to claim 1 is characterized in that: The steps for obtaining load information of each functional location of the same functional type include: Acquire status information of various function venues of the same function type, the status information including venue capacity, number of people who have entered, number of people who have left, and number of people participating in activities; The load information of each functional venue is generated according to the venue capacity, the number of people who have entered, the number of people who have left, and the number of people who have participated in the activity.

6. The real-time data analysis method applied to a large-scale smart elderly care community according to claim 1 is characterized in that: The method further includes the following steps between step S3 and step S4: SA,generates predicted arrival time information based on distance information; SB. Predict and compensate the load information based on the predicted arrival time information.

7. The real-time data analysis method applied to a large-scale smart elderly care community according to claim 1 is characterized in that: The preference information includes: preference information and preference weight; Step S4 includes: S41, selecting a suitable functional place according to the matching degree between the preference information and the project category information; S42, generating a score value for each filtered functional place according to the preference weight, the difference information, the distance information and the load information; S43: Generate the recommendation information based on the rating value.

8. The real-time data analysis method applied to a large-scale smart elderly care community according to claim 7 is characterized in that: The following steps are also included between step S42 and step S43: S4A. Compensate and adjust the score value of each filtered functional venue based on the user's historical participation information.

9. The real-time data analysis method applied to a large-scale smart elderly care community according to claim 8 is characterized in that: The user's historical participation information includes historical evaluation information and / or historical effective activity duration information.

10. A real-time data analysis system applied to a large-scale smart elderly care community, used to analyze the status of various functional places in the community, characterized in that: The system comprises: The client is used to collect and obtain user tag information and current location information, and upload it to the server; The site data collection terminal is used to collect and obtain the load information, project type information and difference information of each functional site of the same functional type, and upload it to the server; The server side is used to obtain the user's preference information according to the user tag information, and obtain the user's distance information about each functional place according to the current location information; The server is further configured to generate recommendation information according to the preference information, the item type information, the difference information, the distance information and the load information, and send the recommendation information to the client.

Images