Comprehensive old-age service platform system based on artificial intelligence

Abstract

The invention discloses a comprehensive old-age care service platform system based on artificial intelligence, and relates to the technical field of intelligent old-age care data processing. The method comprises the steps that firstly, feature data of all old people in a nursing home subordinate area and environment data in the nursing home subordinate area are obtained through monitoring equipment, and meanwhile the monitored data are optimized; and analyzing the optimized feature data of the old people in the nursing home membership area and the environment data to obtain feature response indexes of the old people in the nursing home membership area in the monitoring time periods. According to the feature response indexes of the old people in the subordinate area of the nursing home, monitoring of the platform on the safety condition of the old people and the subordinate area of the nursing home is effectively improved, and safety early warning can be provided in time.

Description

Technical Field

[0001] The present invention relates to the technical field of smart elderly care data processing, and in particular to a comprehensive elderly care service platform system based on artificial intelligence. Background Art

[0002] With the acceleration of aging and the development of information technology, elderly care service platforms have emerged. Elderly care services aim to meet the increasingly diverse needs of various elderly groups through the combination of technology and humanized services, provide personalized health services and life support for the elderly, and provide effective management and care tools for families and communities to promote the life and health management of the elderly. However, with the increasing needs of various elderly groups, the problem of insufficient coverage of the elderly care service platform's service functions has gradually become prominent. Therefore, it is particularly important for the elderly care service platform to provide more complete functions.

[0003] For example, the invention patent with announcement number CN116342344B is a smart elderly care service management system based on the Internet of Things, which belongs to the field of smart elderly care management. It solves the problem of how to monitor the current happiness of the elderly and provide timely help without disclosing their personal privacy; the health analysis module can judge the physical condition of the elderly, supervise the physical examination of the elderly, and discover health problems in time; the environment analysis module can judge whether the elderly are satisfied with the current living environment, and at the same time, if abnormal environmental information occurs, it can be quickly processed; the heart rate analysis module can judge the mood of the elderly, and timely relieve the elderly in a bad mood; when an abnormality occurs, it can promptly alarm and help the elderly out of life danger; the comprehensive evaluation module can regularly and promptly comfort the elderly with low happiness in nursing homes, help the elderly improve their sense of happiness, and also improve the work efficiency of smart elderly care services.

[0004] For example, the invention patent with the announcement number CN113095982B is a smart elderly care service system. It includes an elderly care service platform, which includes a service inquiry unit, a service selection unit, an off-site interaction unit and a storage unit. By sensing the heat signal generated by the inquiry module, information is exchanged, and different expression information corresponds to a time interval of heat output. The information is output by changing the length of the time interval to achieve the purpose of information transmission, which solves the problem of communicating with the elderly who cannot speak, see or read. In addition, the action recognition module selects the action recognition of the elderly, which solves the problem of communicating with the elderly who cannot speak.

[0005] Combined with the above findings, there are problems in the current elderly care service platform system, such as incomplete data acquisition and limited data analysis capabilities, which may lead to the platform’s inability to effectively coordinate resources, resulting in a poor experience for the elderly when using the elderly care service platform and increasing the risk of accidents for the elderly. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a comprehensive elderly care service platform system based on artificial intelligence, which solves the problems designed in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a comprehensive elderly care service platform system based on artificial intelligence, characterized in that it includes: a platform data acquisition module, which is used to monitor and obtain the characteristic data of each elderly person in the nursing home area and the environmental data in the nursing home area and optimize them.

[0008] The characteristic data analysis module is used to analyze the characteristic data of each elderly person in the nursing home's affiliated area, and at the same time analyze the environmental data in the nursing home's affiliated area to obtain the characteristic response index of each elderly person in the nursing home's affiliated area in each monitoring time period.

[0009] The safety and alarm module is used to issue safety alarm prompts based on the characteristic response index of each elderly person in the nursing home's affiliated area during each monitoring time period.

[0010] Furthermore, the monitoring obtains characteristic data of each elderly person in the nursing home's affiliated area and environmental data in the nursing home's affiliated area and optimizes them. The specific process is:

[0011] The characteristic data of each elderly person in the nursing home's affiliated area and the environmental data in the nursing home's affiliated area are optimized.

[0012] The characteristic data of each elderly person in the nursing home's affiliated area include movement distance, number of emergency calls, duration of abnormal behavior types, average walking speed, total sleep time, and number of awakenings at night.

[0013] The environmental data in the area to which the nursing home belongs include temperature, humidity, and pollutant concentration.

[0014] Furthermore, the characteristic data of each elderly person in the nursing home's affiliated area is analyzed, and the specific analysis process is as follows:

[0015] A monitoring cycle is set, and several monitoring time periods are arranged in the monitoring cycle. In each monitoring time period, the moving distance, number of emergency calls and average walking speed of each elderly person in the nursing home area are counted, and the first characteristic evaluation index of each elderly person in the nursing home area in each monitoring time period is obtained after processing.

[0016] Several monitoring time points are set in the monitoring cycle, the location of each elderly person in the nursing home area is identified at each monitoring time point, and a human skeleton map of each elderly person is generated. The skeleton outline of each elderly person is extracted from the human skeleton map, and then overlapped and compared with the reference skeleton outline lines corresponding to various abnormal behavior types stored in the database to obtain the abnormal behavior type of each elderly person, and the duration of the abnormal behavior type of each elderly person is counted.

[0017] During the monitoring period, the total sleep time and the number of times the elderly people woke up at night in the nursing home area were counted, and the duration of each elderly person's abnormal behavior type was extracted. After processing, the second characteristic evaluation index of each elderly person in the nursing home area in each monitoring time period was obtained.

[0018] Furthermore, the environmental data in the area to which the nursing home belongs is analyzed, and the specific analysis process is as follows:

[0019] The average temperature, average humidity and average concentration of pollutants in the nursing home area are extracted in each monitoring time period, and the environmental safety index of the nursing home area in each monitoring time period is obtained after processing.

[0020] Furthermore, the environmental safety index of the area to which the nursing home belongs in each monitoring time period is the numerical result of analyzing the environmental data in the area to which the nursing home belongs, and is used to quantitatively evaluate the overall condition of the environment in the area to which the nursing home belongs in each monitoring time period.

[0021] Furthermore, the characteristic response index of each elderly person in the nursing home affiliated area in each monitoring time period is obtained, and the specific process is as follows:

[0022] According to the first characteristic evaluation index of each elderly person in the nursing home's area in each monitoring time period, the second characteristic evaluation index of each elderly person in the nursing home's area in each monitoring time period and the environmental safety index of the nursing home's area in each monitoring time period, the characteristic response index of each elderly person in the nursing home's area in each monitoring time period is obtained after processing.

[0023] The characteristic response index of each elderly person in the nursing home's affiliated area is a numerical result obtained by analyzing the characteristic data of each elderly person in the nursing home's affiliated area, and is used to quantitatively evaluate the behavioral safety status of each elderly person in the nursing home's affiliated area in each monitoring time period.

[0024] Furthermore, the safety alarm is prompted according to the characteristic response index of each elderly person in the nursing home's affiliated area in each monitoring time period. The specific analysis process is as follows:

[0025] The characteristic response index of each elderly person in the nursing home area in each monitoring time period is extracted and compared with the set characteristic response index threshold of the elderly. If the characteristic response index of an elderly person in the nursing home area in a certain monitoring time period is higher than the characteristic response index threshold of the elderly, then the monitoring time period is recorded as an abnormal monitoring time period. In this way, each abnormal monitoring time period is traversed and an early warning prompt is issued through text messages.

[0026] Furthermore, the first characteristic evaluation index of each elderly person in the nursing home affiliated area in each monitoring time period is specifically analyzed under the following conditions:

[0027]

[0028] Among them, δ k→a A is the first characteristic evaluation index of the ath elderly person in the nursing home area during the kth monitoring period, k→a represents the moving distance of the ath elderly person in the kth monitoring period, ΔA is the set moving distance of the elderly person, and B k→a represents the number of emergency calls made by the ath elderly person in the kth monitoring period, C k→a represents the average walking speed of the ath elderly person in the kth monitoring period, ΔB is the number of emergency calls made by the elderly, and α 1 is the correction factor corresponding to the set moving distance, α 2 is the correction factor corresponding to the set number of emergency calls, α 3 is the correction factor corresponding to the set walking speed, k represents the number of each monitoring time period, k=2, 3, ..., m, m represents the total number of monitoring time periods, a represents the number of the a-th elderly person, a=2, 3, ..., b, b represents the total number of elderly people.

[0029] Furthermore, the characteristic response index of each elderly person in the nursing home affiliated area in each monitoring time period is specifically analyzed under the following conditions:

[0030]

[0031] in, is the characteristic response index of the ath elderly person in the nursing home area during the kth monitoring period, δ k→a is the first characteristic evaluation index of the ath elderly person in the nursing home area during the kth monitoring period, τ k→a is the second characteristic evaluation index of the ath elderly person in the nursing home area during the kth monitoring period, ρ kis the environmental safety index of the nursing home area in the kth monitoring period, k represents the number of each monitoring period, k = 2, 3, ..., m, m represents the total number of monitoring periods, a represents the number of the ath elderly person, a = 2, 3, ..., b, b represents the total number of elderly people, β 1 It represents the weight factor corresponding to the first characteristic evaluation index of the elderly, β 2 It represents the weight factor corresponding to the second characteristic evaluation index of the elderly, β 3 It represents the weight factor corresponding to the set environmental safety index, and e is a natural constant.

[0032] Furthermore, the security alarm is issued based on the characteristic response index of each elderly person in the nursing home's affiliated area during each monitoring time period, and also includes obtaining the safety index of each elderly person by processing the characteristic response index of each elderly person in the nursing home's affiliated area during each monitoring time period through the platform, and performing early warning processing.

[0033] The present invention has the following beneficial effects:

[0034] (1) The present invention discloses a comprehensive elderly care service platform system based on artificial intelligence, which relates to the field of smart elderly care data processing technology. First, through monitoring equipment, the characteristic data of each elderly person in the nursing home's affiliated area and the environmental data of the nursing home's affiliated area are obtained, and the monitored data are optimized at the same time. The optimized characteristic data and environmental data of each elderly person in the nursing home's affiliated area are analyzed to obtain the characteristic response index of each elderly person in the nursing home's affiliated area in each monitoring time period. Through the characteristic response index of each elderly person in the nursing home's affiliated area, the platform's monitoring of the safety of the elderly and the nursing home's affiliated area is effectively improved, and safety warnings can be provided in a timely manner.

[0035] (2) The present invention obtains characteristic data of each elderly person in the nursing home's affiliated area to monitor the elderly's behavioral safety and regularity, which helps to provide a reliable basis for subsequent analysis and processing of the elderly's behavioral status.

[0036] (3) The present invention obtains the environmental safety index in the nursing home's area during each monitoring period to evaluate the overall environmental status of the nursing home's area, which is conducive to timely discovery and resolution of potential environmental safety issues and provides safe and comfortable living conditions for the elderly.

[0037] (4) In the present invention, the average temperature, average humidity and average concentration of pollutants in the nursing home area are obtained and processed to obtain the environmental safety index. The parameters are closely related and influence each other, so the obtained environmental safety index is more accurate and helps to improve the overall safety and comfort of the nursing home.

[0038] (5) In the present invention, the total sleep time, number of awakenings at night, and duration of abnormal behavior types of each elderly person are obtained, and the first characteristic evaluation index of each elderly person is obtained. The moving distance, number of emergency calls, and average walking speed of each elderly person are obtained, and the second characteristic evaluation index of each elderly person is obtained. The first characteristic evaluation index and the second characteristic evaluation index of each elderly person are closely related and influence each other. Comprehensive analysis can quantitatively evaluate the behavioral safety status of each elderly person.

[0039] (6) In the present invention, the first characteristic evaluation index, the second characteristic evaluation index and the environmental safety index of the area where the nursing home is located are obtained, and the characteristic response index of the elderly is obtained, wherein the first characteristic evaluation index, the second characteristic evaluation index and the environmental safety index of the elderly influence each other and do not exist independently. By comprehensively analyzing these three parameters, the behavioral safety status and environmental safety status of the elderly are evaluated. This provides data support for nursing homes to improve their nursing levels.

[0040] (7) The present invention helps the platform provide personalized services to the elderly and provide reliable data support for the elderly to improve their quality of life by comprehensively analyzing the first characteristic evaluation index of each elderly person in the nursing home's affiliated area during each monitoring time period and the second characteristic evaluation index of each elderly person in the nursing home's affiliated area during each monitoring time period.

[0041] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic diagram of the method flow of the present invention.

[0043] Figure 2 It is a curve of the abnormal evaluation index of the first characteristic data of each elderly person in the nursing home affiliated area in each monitoring time period of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] In the description of the present invention, it should be understood that the terms "opening", "upper", "lower", "thickness", "top", "middle", "length", "inside", "all around" and the like indicating orientation or positional relationship are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0046] See also Figure 1 As shown, an embodiment of the present invention provides a technical solution: a comprehensive elderly care service platform system based on artificial intelligence, characterized in that it includes: a platform data acquisition module, which is used to monitor and obtain the characteristic data of each elderly person in the nursing home area and the environmental data in the nursing home area and optimize them.

[0047] The platform data acquisition module is used to monitor and obtain the characteristic data of each elderly person in the nursing home's affiliated area and the environmental data in the nursing home's affiliated area and optimize it.

[0048] The characteristic data analysis module is used to analyze the characteristic data of each elderly person in the nursing home's affiliated area, and at the same time analyze the environmental data in the nursing home's affiliated area to obtain the characteristic response index of each elderly person in the nursing home's affiliated area in each monitoring time period.

[0049] The safety and alarm module is used to issue safety alarm prompts based on the characteristic response index of each elderly person in the nursing home's affiliated area during each monitoring time period.

[0050] It should be noted that by analyzing the characteristic data of each elderly person in the monitored nursing home area and the environmental data in the nursing home area, the characteristic response index of each elderly person in the nursing home area in each monitoring time period is obtained. According to the characteristic response index of each elderly person in the nursing home area in each monitoring time period, the safety situation of the elderly is judged and an alarm is issued in time.

[0051] Specifically, the characteristic data of each elderly person in the nursing home's affiliated area and the environmental data in the nursing home's affiliated area are optimized.

[0052] The characteristic data of each elderly person in the nursing home's affiliated area include movement distance, number of emergency calls, duration of abnormal behavior types, average walking speed, total sleep time, and number of awakenings at night.

[0053] The environmental data in the area to which the nursing home belongs include temperature, humidity, and pollutant concentration.

[0054] It should be noted that the optimization of abnormal data includes the optimization of missing values. If there are too many missing values, consider deleting these records. For individual missing values, you can use the mean, median, and mode to fill in the missing data to ensure the integrity of the data. It also includes the optimization of mutation values. If the mutation data is determined to be abnormal data, you can consider deleting these records, or replace the mutation value with a reasonable value.

[0055] It should be noted that the moving distance can be measured by a pedometer to measure the walking distance and walking time; the number of emergency calls can be recorded by the platform's electronic recording system, which records all call events of the elderly.

[0056] It should be noted that the duration of abnormal behavior types is determined by monitoring the positions of key human body points such as the head, shoulders, elbows, hands, hips, buttocks, knees, and ankles, thereby capturing the positions of each elderly person and constructing a human skeleton map. The skeleton outlines extracted from the human skeleton map formed by the positions of the elderly monitored by the monitoring points are compared with the skeleton outlines of abnormal behaviors in the database to determine the degree of overlap between the two, and to determine whether the activity status of each elderly person at this time is abnormal, and to determine the duration of the abnormal behavior.

[0057] It should be noted that the average walking speed is calculated based on the walking distance and walking time measured by the pedometer.

[0058] It should be noted that the temperature is measured by a temperature sensor; the humidity is obtained by monitoring the changes in water vapor content in the environment through a humidity sensor; pollutants mainly refer to atmospheric pollutants such as carbon monoxide, carbon dioxide, and ozone. The concentration of specific gases in the air can be measured through a gas sensor to obtain the pollutant concentration.

[0059] It should be noted that the sleep time is the start time, end time and duration of different sleep stages monitored by smart mattresses or sleep monitoring instruments. The number of awakenings at night can be monitored by heart rate sensors. The heart rate may change greatly when waking up. Based on this, the sleep quality, including the number and duration of awakenings at night, can be analyzed through smart bracelets or smart watches based on heart rate, body movement, breathing and other data.

[0060] It should be noted that the number of times you wake up at night can be monitored by a heart rate sensor. Your heart rate may change significantly when you wake up. Based on this, you can use a smart bracelet or smart watch to analyze your sleep quality, including the number and duration of awakenings at night, based on heart rate, body movement, breathing and other data.

[0061] A monitoring cycle is set, and several monitoring time periods are arranged in the monitoring cycle. In each monitoring time period, the moving distance, number of emergency calls and average walking speed of each elderly person in the nursing home area are counted, and the first characteristic evaluation index of each elderly person in the nursing home area in each monitoring time period is obtained after processing.

[0062] Several monitoring time points are set in the monitoring cycle, the location of each elderly person in the nursing home area is identified at each monitoring time point, and a human skeleton map of each elderly person is generated. The skeleton outline of each elderly person is extracted from the human skeleton map, and then overlapped and compared with the reference skeleton outline lines corresponding to various abnormal behavior types stored in the database to obtain the abnormal behavior type of each elderly person, and the duration of the abnormal behavior type of each elderly person is counted.

[0063] During the monitoring period, the total sleep time and the number of times the elderly people woke up at night in the nursing home area were counted, and the duration of each elderly person's abnormal behavior type was extracted. After processing, the second characteristic evaluation index of each elderly person in the nursing home area in each monitoring time period was obtained.

[0064] It should be noted that the first characteristic evaluation index of each elderly person in the nursing home area during each monitoring time period is obtained by analyzing and counting the moving distance, number of emergency calls and average walking speed of each elderly person in the nursing home area.

[0065] It should be noted that the second characteristic evaluation index of each elderly person in the nursing home area in each monitoring period is calculated by counting the total sleep time and the number of times each elderly person wakes up at night in the nursing home area, and extracting the duration of each elderly person's abnormal behavior type. According to the second characteristic evaluation index of each elderly person in the nursing home area in each monitoring period, it helps the platform optimize care plans and service arrangements and discover potential safety issues in a timely manner.

[0066] Specifically, the average temperature, average humidity and average concentration of pollutants in the area to which the nursing home belongs in each monitoring time period are extracted, and the environmental safety index of the area to which the nursing home belongs in each monitoring time period is obtained after processing.

[0067] It should be noted that pollutants mainly include PM2.5, PM10, carbon monoxide, carbon dioxide and other atmospheric pollutants.

[0068] It should be noted that the specific analysis process of the environmental safety index of the nursing home’s area in each monitoring time period is as follows.

[0069]

[0070] In the formula, ρ k is the environmental safety index of the nursing home’s area during the kth monitoring period, Xk is the average temperature in the nursing home area during the kth monitoring period, ΔX is the average temperature in the nursing home area, and Y k is the average humidity in the nursing home area during the kth monitoring period, ΔY is the average humidity in the nursing home area, and Z k is the average concentration of pollutants in the nursing home area during the kth monitoring period, ΔZ is the average concentration of pollutants in the nursing home area, μ 1 Indicates the correction factor corresponding to the set average temperature, μ 2 Indicates the correction factor corresponding to the set average humidity, μ 3 It represents the correction factor corresponding to the set average concentration of pollutants, k represents the number of each monitoring time period, k=2, 3, ..., m, m represents the total number of monitoring time periods.

[0071] It should be added that the average temperature, average humidity and average pollutant concentration extracted from the nursing home area in each monitoring time period in this formula are correlated. An increase in humidity may lead to an increase in pollutant concentration. A comprehensive analysis of the average temperature, average humidity and average pollutant concentration in each nursing home area can then be used to obtain the environmental safety index of the nursing home area in each monitoring time period.

[0072] In a specific embodiment, the correction factor of the average temperature is between 0 and 1, and the correction factor corresponding to the average temperature is extracted from a database. Through the relationship between the average temperature and the second characteristic evaluation index in the historical data, a mapping set of the average temperature and its corresponding correction factor is established, and the real-time average temperature is input to obtain the correction factor corresponding to the average temperature from the mapping set.

[0073] In a specific embodiment, the correction factor corresponding to the average humidity is between 0 and 1, and the correction factor corresponding to the average humidity of each elderly person is extracted from a database. Through the relationship between the average humidity and the second characteristic evaluation index in the historical data, a mapping set of the average humidity and its corresponding correction factor is established, and the real-time average humidity is input to obtain the correction factor corresponding to the average humidity from the mapping set.

[0074] In a specific embodiment, the correction factor corresponding to the average pollutant concentration is between 0 and 1, and the correction factor corresponding to the average pollutant concentration is extracted from a database. Through the relationship between the average concentration of different pollutants in historical data and the second characteristic evaluation index, a mapping set of average pollutant concentrations and their corresponding correction factors is established, and the real-time average pollutant concentration is input to obtain the correction factor corresponding to the average pollutant concentration from the mapping set.

[0075] Specifically, the environmental safety index of the area to which the nursing home belongs in each monitoring time period is the numerical result of analyzing the environmental data in the area to which the nursing home belongs, and is used to quantitatively evaluate the overall condition of the environment in the area to which the nursing home belongs in each monitoring time period.

[0076] It should be noted that the environmental safety index of the nursing home's area in each monitoring time period is obtained by monitoring and analyzing the average temperature, average humidity, and average pollutant concentration in the nursing home's area. It is used to monitor the environmental safety index, which helps to improve the overall safety and comfort of the nursing home.

[0077] Specifically, according to the first characteristic evaluation index of each elderly person in the nursing home's affiliated area in each monitoring time period, the second characteristic evaluation index of each elderly person in the nursing home's affiliated area in each monitoring time period, and the environmental safety index of the nursing home's affiliated area in each monitoring time period, the characteristic response index of each elderly person in the nursing home's affiliated area in each monitoring time period is obtained after processing;

[0078] The characteristic response index of each elderly person in the nursing home's affiliated area is a numerical result obtained by analyzing the characteristic data of each elderly person in the nursing home's affiliated area, and is used to quantitatively evaluate the behavioral safety status of each elderly person in the nursing home's affiliated area in each monitoring time period.

[0079] It should be noted that the specific analysis method for the second characteristic assessment index of each elderly person in the nursing home’s affiliated area during each monitoring time period is as follows.

[0080]

[0081] In the formula, τ k→a is the second characteristic evaluation index of the ath elderly person in the nursing home area during the kth monitoring period, M k→a is the total sleep time of the ath elderly person in the nursing home area during the kth monitoring period, ΔM is the reference value of the total sleep time of the elderly, and N k→a is the number of times the ath elderly person wakes up at night, ΔN is the reference number of times the elderly person wakes up at night, O k→a is the duration of the abnormal behavior type of the ath elderly person in the nursing home area during the kth monitoring period, ΔO is the reference value of the duration of the abnormal behavior type, and θ 1 Indicates the correction factor corresponding to the set total sleep time, θ 2 Indicates the correction factor corresponding to the number of times the elderly wake up at night, θ 3 Indicates the correction factor corresponding to the duration of the set abnormal behavior type.

[0082] It should be added that the total sleep time, number of awakenings at night, and duration of abnormal behavior types of each elderly person in each monitoring time period in this formula are correlated. An increase in the number of times the elderly wake up at night may lead to a decrease in total sleep time and an increase in the duration of abnormal behavior types. A comprehensive analysis of the total sleep time, number of awakenings at night, and cumulative duration of abnormal behavior types of each elderly person can then yield the second characteristic assessment index of each elderly person.

[0083] In a specific embodiment, the correction factor corresponding to the total sleep time is between 0 and 1, and the correction factor corresponding to the total sleep time is extracted from a database. Through the relationship between the total sleep time and the second characteristic evaluation index in the historical data, a mapping set of the total sleep time and its corresponding correction factor is established, and the real-time total sleep time is input to obtain the correction factor corresponding to the total sleep time from the mapping set.

[0084] In a specific embodiment, the correction factor corresponding to the number of night awakenings is between 0 and 1, and the correction factor corresponding to the number of night awakenings of each elderly person is extracted from a database. Through the relationship between the number of night awakenings in historical data and the second characteristic evaluation index, a mapping set of the number of night awakenings and their corresponding correction factors is established, and the real-time number of night awakenings is input to obtain the correction factor corresponding to the number of night awakenings from the mapping set.

[0085] In a specific embodiment, the correction factor corresponding to the duration of the abnormal behavior type is between 0 and 1, and the correction factor corresponding to the duration of the abnormal behavior type is extracted from a database. Through the relationship between the duration of the abnormal behavior type in the historical data and the second feature evaluation index, a mapping set of the duration of the abnormal behavior type and its corresponding correction factor is established, and the real-time duration of the abnormal behavior type is input to obtain the correction factor corresponding to the duration of the abnormal behavior type from the mapping set.

[0086] Specifically, the characteristic response index of each elderly person in the nursing home area in each monitoring time period is extracted and compared with the set characteristic response index threshold of the elderly. If the characteristic response index of an elderly person in the nursing home area in a certain monitoring time period is higher than the characteristic response index threshold of the elderly, then the monitoring time period is recorded as an abnormal monitoring time period. In this way, each abnormal monitoring time period is traversed and an early warning prompt is issued through text messages.

[0087] The characteristic response index of each elderly person in the nursing home area during each monitoring time period is extracted and compared with the characteristic response index threshold of the elderly set in the database, and the monitoring time period with abnormal characteristic response index is screened out, and early warning is issued through text messages.

[0088] Specifically, the first characteristic evaluation index of each elderly person in the nursing home affiliated area in each monitoring time period, the specific analysis conditions are:

[0089]

[0090] Among them, δ k→a A is the first characteristic evaluation index of the ath elderly person in the nursing home area during the kth monitoring period, k→a represents the moving distance of the ath elderly person in the kth monitoring period, ΔA is the set moving distance of the elderly person, and B k→a represents the number of emergency calls made by the ath elderly person in the kth monitoring period, C k→a represents the average walking speed of the ath elderly person in the kth monitoring period, ΔB is the number of emergency calls made by the elderly, and α 1 is the correction factor corresponding to the set moving distance, α 2 is the correction factor corresponding to the set number of emergency calls, α 3 is the correction factor corresponding to the set walking speed, k represents the number of each monitoring time period, k=2, 3, ..., m, m represents the total number of monitoring time periods, a represents the number of the a-th elderly person, a=2, 3, ..., b, b represents the total number of elderly people.

[0091] It should be explained that the moving distance, number of emergency calls and average walking speed of each elderly person are related and do not exist independently. For example, if the average walking speed of the elderly increases, the moving distance will also increase. By comprehensively analyzing the moving distance, number of emergency calls and average walking speed of the elderly, we can accurately obtain the first characteristic evaluation index of each elderly person in the nursing home area during each monitoring period.

[0092] In a specific embodiment, the correction factor corresponding to the moving distance is between 0 and 1, and the correction factor corresponding to the moving distance is extracted from a database. Through the relationship between the moving distance in historical data and the first characteristic evaluation index of each elderly person in the nursing home affiliation area in each monitoring time period, a mapping set of moving distance and its corresponding correction factor is established, and the correction factor corresponding to the moving distance is obtained from the mapping set by inputting the moving distance.

[0093] In a specific embodiment, the correction factor corresponding to the number of emergency calls is between 0 and 1, and the correction factor corresponding to the number of emergency calls is extracted from a database. Through the relationship between the number of emergency calls in historical data and the first characteristic evaluation index of each elderly person in the nursing home area in each monitoring time period, a mapping set of the number of emergency calls and their corresponding correction factors is established, and the number of emergency calls is input to obtain the correction factor corresponding to the number of emergency calls from the mapping set.

[0094] In a specific embodiment, the correction factor corresponding to the average walking speed is between 0 and 1, and the correction factor corresponding to the average walking speed is extracted from a database. Through the relationship between the average walking speed in historical data and the first characteristic evaluation index of each elderly person in the nursing home area in each monitoring time period, a mapping set of the average walking speed and its corresponding correction factor is established, and the average walking speed is input to obtain the correction factor corresponding to the average walking speed from the mapping set.

[0095] like Figure 2 As shown, Figure 2 The curve represents the first characteristic evaluation index of each elderly person in the nursing home affiliated area in each monitoring time period, wherein the x-axis represents the moving distance of the ath elderly person in the kth monitoring time period, in meters (m), and the y-axis represents the first characteristic evaluation index of the ath elderly person in the nursing home affiliated area in the kth monitoring time period. Three different sets of example parameters are defined in the figure, corresponding to different situations of the three curves, represented by solid lines, dashed lines and dotted lines, respectively, and the corresponding curve labels are a, b, and c, respectively. When the number of emergency calls of the elderly is 0, the schematic diagram of the relationship between the moving distance of the elderly and the first characteristic evaluation index of each elderly person in the nursing home affiliated area in each monitoring time period is shown in curve a, when the number of emergency calls of the elderly is 1, the schematic diagram of the relationship between the moving distance of the elderly and the first characteristic evaluation index of each elderly person in the nursing home affiliated area in each monitoring time period is shown in curve b, when the number of emergency calls of the elderly is 3, the schematic diagram of the relationship between the moving distance of the elderly and the first characteristic evaluation index of each elderly person in the nursing home affiliated area in each monitoring time period is shown in curve c. When the moving distance of the ath elderly person in the kth monitoring time period is closer to the set moving distance of the elderly, the first characteristic evaluation index of each elderly person in the nursing home area in each monitoring time period will increase accordingly, which reflects the influence of the moving distance of each elderly person on the first characteristic evaluation index of each elderly person in the nursing home area in each monitoring time period.

[0096] As shown in Table 1, Table 1 is example data of the first characteristic evaluation index of each elderly person in the nursing home area in each monitoring time period, which lists the first characteristic evaluation index of each elderly person in the nursing home area in each monitoring time period and the moving distance of the elderly.

[0097] Table 1 Example data of the first characteristic evaluation index of each elderly person in the nursing home area during each monitoring period

[0098]

[0099] As shown in Table 1, in a specific embodiment, assuming that the moving distance of the elderly is set to ΔA = 50 (meters), the number of emergency calls made by the a-th elderly person in the k-th monitoring time period is B k→a= 0 (times), the number of emergency calls by the elderly is set to ΔB = 1 (times), the walking speed value of the ath elderly person in the k monitoring time period is C k→a =0.8 (m / s), average walking speed The set moving distance of the elderly is ΔA = 20 (times / minute), and the correction factor corresponding to the moving distance of the elderly is α 1 =0.8, the correction factor corresponding to the number of emergency calls by the elderly is α 2 =0.9, the correction factor corresponding to the walking speed of the elderly is α 3 =0.95. The first characteristic evaluation index of each elderly person in the nursing home area in each monitoring time period is determined by the moving distance, number of emergency calls, and average walking speed of each monitored elderly person. When the moving distance value deviates from the set moving distance of the elderly, the first characteristic evaluation index of each elderly person in the nursing home area in each monitoring time period will decrease accordingly.

[0100] Specifically, the characteristic response index of each elderly person in the nursing home area during each monitoring period, the specific analysis conditions are:

[0101]

[0102] in, is the characteristic response index of the ath elderly person in the nursing home area during the kth monitoring period, δ k→a is the first characteristic evaluation index of the ath elderly person in the nursing home area during the kth monitoring period, τ k→a is the second characteristic evaluation index of the ath elderly person in the nursing home area during the kth monitoring period, ρ k is the environmental safety index of the nursing home area in the kth monitoring period, k represents the number of each monitoring period, k = 2, 3, ..., m, m represents the total number of monitoring periods, a represents the number of the ath elderly person, a = 2, 3, ..., b, b represents the total number of elderly people, β 1 It represents the weight factor corresponding to the first characteristic evaluation index of the elderly, β 2 It represents the weight factor corresponding to the second characteristic evaluation index of the elderly, β 3 It represents the weight factor corresponding to the set environmental safety index, and e is a natural constant.

[0103] In a specific embodiment, by extracting historical data from a database, a fitting curve is obtained by fitting the relationship between the first characteristic evaluation index of each elderly person, the second characteristic evaluation index, the environmental safety index, and the characteristic response index. The weight factor corresponding to the first characteristic evaluation index, the second characteristic evaluation index of the elderly person, and the weight factor corresponding to the environmental safety index are determined based on the fitting curve.

[0104] It should be noted that there is a correlation between the first characteristic assessment index and the second characteristic assessment index of each elderly person and the environmental safety index. When the first characteristic assessment index of each elderly person decreases, the second characteristic assessment index may also decrease. When the environmental safety index increases, the first characteristic assessment index and the second characteristic assessment index of the elderly may also increase. The characteristic response index of the elderly is obtained by comprehensively analyzing the first characteristic assessment index, the second characteristic assessment index and the environmental safety index of each elderly person. Therefore, these three parameters work together to jointly participate in the assessment of the behavioral safety status and environmental safety status of the elderly, and the characteristic response index of the elderly is obtained, which provides an important basis for improving the overall care of nursing homes.

[0105] According to the first characteristic evaluation index, the second characteristic evaluation index of each elderly person and the environmental safety index of the nursing home's area, the characteristic response index of each elderly person is obtained by integration.

[0106] Specifically, safety alarm prompts are issued based on the characteristic response index of each elderly person in the nursing home's affiliated area during each monitoring time period. It also includes obtaining the safety index of each elderly person by processing the characteristic response index of each elderly person in the nursing home's affiliated area during each monitoring time period through the platform, and performing early warning processing.

[0107] It should be noted that the comprehensive elderly care service platform uses artificial intelligence technology to calculate and generate a safety index for each elderly person based on the characteristic response index of the elderly in the nursing home’s area during each monitoring period, and performs early warning processing, further providing scientific and precise support for the health management and prevention of each elderly person.

[0108] It should be noted that the comprehensive elderly care service platform system based on artificial intelligence also includes a database, which is an important tool for storing and managing the health status data of each elderly person in the nursing home area during each monitoring time period, the second characteristic data of each elderly person and related data. In this embodiment, the database is used to store the set moving distance of the elderly, the set number of emergency calls of the elderly, the correction factor corresponding to the set moving distance, the correction factor corresponding to the set number of emergency calls, the correction factor corresponding to the set walking speed, the weight factor corresponding to the set first characteristic evaluation index of the elderly, the weight factor corresponding to the set second characteristic evaluation index of the elderly, the set average temperature in the nursing home area, the set average humidity in the nursing home area, the set average concentration of pollutants in the nursing home area, the correction factor corresponding to the set average temperature, the correction factor corresponding to the set average humidity, and the correction factor corresponding to the set average concentration of pollutants.

[0109] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0110] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A comprehensive elderly care service platform system based on artificial intelligence, characterized in that: include: The platform data acquisition module is used to monitor and obtain the characteristic data of each elderly person in the nursing home's affiliated area and the environmental data in the nursing home's affiliated area and optimize them; The characteristic data analysis module is used to analyze the characteristic data of each elderly person in the nursing home's affiliated area, and analyze the environmental data in the nursing home's affiliated area at the same time, to obtain the characteristic response index of each elderly person in the nursing home's affiliated area in each monitoring time period; The safety and alarm module is used to issue safety alarm prompts based on the characteristic response index of each elderly person in the nursing home's affiliated area during each monitoring time period.

2. According to claim 1, a comprehensive elderly care service platform system based on artificial intelligence is characterized by: The monitoring obtains characteristic data of each elderly person in the nursing home's area and environmental data in the nursing home's area and optimizes the data. The specific process is as follows: Optimize the characteristic data of each elderly person in the nursing home's affiliated area and the environmental data in the nursing home's affiliated area; The characteristic data of each elderly person in the nursing home’s affiliated area include the distance moved, the number of emergency calls, the duration of abnormal behavior types, the average walking speed, the total sleep time, and the number of awakenings at night; The environmental data in the area to which the nursing home belongs include temperature, humidity, and pollutant concentration.

3. The comprehensive elderly care service platform system based on artificial intelligence according to claim 1 is characterized by: The characteristic data of each elderly person in the nursing home's affiliated area is analyzed, and the specific analysis process is as follows: A monitoring cycle is set, and several monitoring time periods are arranged in the monitoring cycle. In each monitoring time period, the moving distance, number of emergency calls and average walking speed of each elderly person in the nursing home area are counted, and the first characteristic evaluation index of each elderly person in the nursing home area in each monitoring time period is obtained after processing; Several monitoring time points are set in the monitoring cycle, and the location of each elderly person in the nursing home area is identified at each monitoring time point, and a human skeleton diagram of each elderly person is generated. The skeleton outline of each elderly person is extracted from the human skeleton diagram of each elderly person, and then the skeleton outline is overlapped and compared with the reference skeleton outline corresponding to various abnormal behavior types stored in the database to obtain the abnormal behavior type of each elderly person, and the duration of the abnormal behavior type of each elderly person is counted; During the monitoring period, the total sleep time and the number of times the elderly people woke up at night in the nursing home area were counted, and the duration of each elderly person's abnormal behavior type was extracted. After processing, the second characteristic evaluation index of each elderly person in the nursing home area in each monitoring time period was obtained.

4. The comprehensive elderly care service platform system based on artificial intelligence according to claim 1 is characterized by: The environmental data in the area to which the nursing home belongs is analyzed, and the specific analysis process is as follows: The average temperature, average humidity and average concentration of pollutants in the nursing home area are extracted in each monitoring time period, and the environmental safety index of the nursing home area in each monitoring time period is obtained after processing.

5. The comprehensive elderly care service platform system based on artificial intelligence according to claim 4 is characterized by: The environmental safety index of the nursing home's area in each monitoring time period is the numerical result of analyzing the environmental data in the nursing home's area, and is used to quantitatively evaluate the overall condition of the environment in the nursing home's area in each monitoring time period.

6. The comprehensive elderly care service platform system based on artificial intelligence according to claim 1 is characterized by: The specific process of obtaining the characteristic response index of each elderly person in the nursing home area in each monitoring time period is as follows: According to the first characteristic evaluation index of each elderly person in the nursing home's affiliated area in each monitoring time period, the second characteristic evaluation index of each elderly person in the nursing home's affiliated area in each monitoring time period, and the environmental safety index of the nursing home's affiliated area in each monitoring time period, the characteristic response index of each elderly person in the nursing home's affiliated area in each monitoring time period is obtained after processing; The characteristic response index of each elderly person in the nursing home's affiliated area is a numerical result obtained by analyzing the characteristic data of each elderly person in the nursing home's affiliated area, and is used to quantitatively evaluate the behavioral safety status of each elderly person in the nursing home's affiliated area in each monitoring time period.

7. The comprehensive elderly care service platform system based on artificial intelligence according to claim 1 is characterized by: The safety alarm is given according to the characteristic response index of each elderly person in the nursing home area in each monitoring time period. The specific analysis process is as follows: The characteristic response index of each elderly person in the nursing home area in each monitoring time period is extracted and compared with the set characteristic response index threshold of the elderly. If the characteristic response index of an elderly person in the nursing home area in a certain monitoring time period is higher than the characteristic response index threshold of the elderly, then the monitoring time period is recorded as an abnormal monitoring time period. In this way, each abnormal monitoring time period is traversed and an early warning prompt is issued through text messages.

8. The comprehensive elderly care service platform system based on artificial intelligence according to claim 4 is characterized by: The specific analysis conditions for the first characteristic evaluation index of each elderly person in the nursing home's affiliated area during each monitoring period are: Among them, δ k→a A is the first characteristic evaluation index of the ath elderly person in the nursing home area during the kth monitoring period, k→a represents the moving distance of the ath elderly person in the kth monitoring period, ΔA is the set moving distance of the elderly person, and B k→a represents the number of emergency calls made by the ath elderly person in the kth monitoring period, C k→a represents the average walking speed of the ath elderly person in the kth monitoring time period, ΔB is the set number of emergency calls made by the elderly, α1 is the correction factor corresponding to the set moving distance, α2 is the correction factor corresponding to the set number of emergency calls, α3 is the correction factor corresponding to the set walking speed, k represents the number of each monitoring time period, k=2,3,...,m, m represents the total number of monitoring time periods, a represents the number of the ath elderly person, a=2,3,...,b, b represents the total number of elderly people.

9. The comprehensive elderly care service platform system based on artificial intelligence according to claim 7 is characterized by: The characteristic response index of each elderly person in the nursing home area during each monitoring period, the specific analysis conditions are: in, is the characteristic response index of the ath elderly person in the nursing home area during the kth monitoring period, δ k→a is the first characteristic evaluation index of the ath elderly person in the nursing home area during the kth monitoring period, τ k→a is the second characteristic evaluation index of the ath elderly person in the nursing home area during the kth monitoring period, ρ k is the environmental safety index of the nursing home’s affiliated area in the kth monitoring time period, k represents the number of each monitoring time period, k=2, 3, ..., m, m represents the total number of monitoring time periods, a represents the number of the ath elderly person, a=2, 3, ..., b, b represents the total number of elderly people, β1 represents the weight factor corresponding to the set first characteristic evaluation index of the elderly, β2 represents the weight factor corresponding to the set second characteristic evaluation index of the elderly, β3 represents the weight factor corresponding to the set environmental safety index, and e is a natural constant.

10. The comprehensive elderly care service platform system based on artificial intelligence according to claim 1 is characterized by: The method of issuing a safety alarm based on the characteristic response index of each elderly person in the nursing home's affiliated area during each monitoring time period also includes processing the characteristic response index of each elderly person in the nursing home's affiliated area during each monitoring time period through the platform to obtain the safety index of each elderly person and perform early warning processing.

Images