A smart elderly care service supervision system and method for elderly care

Abstract

The invention discloses a smart elderly care service supervision system and method for elderly care, which belongs to the field of intelligent supervision technology. A community elderly care database is constructed, which includes community data and community elderly data; an activity area set and a community elderly set are constructed; the activity area is marked, and the weight of the activity area in the same time period is calculated; the community elderly rescue data in the activity area is extracted, the safety factor of the activity area is calculated, and the number of caregivers in the activity area is pre-allocated; after user authorization, the course of illness log of the community elderly is extracted, a disease assessment model is constructed, and the disease condition of the community elderly is assessed; the risk probability of the community elderly waiting for rescue is calculated; the predicted value of the risk probability of all community elderly waiting for rescue in the activity area is calculated, and the risk monitoring sequence in the activity area is generated, and the risk monitoring sequence in the activity area is sent to the caregiver; thereby improving the quality of elderly care services.

Description

Technical Field

[0001] The present invention relates to the field of intelligent supervision technology, and specifically to a smart elderly care service supervision system and method for elderly care. Background Art

[0002] As an emerging model of elderly care, smart senior care provides the elderly with intelligent, real-time, safe, convenient and humanized professional services through new-generation information technology products such as the Internet of Things and cloud computing, so that they can enjoy high-quality care such as medical care and life care at home, and continue to promote the development of the smart health care industry to meet the life needs of the elderly.

[0003] The National Working Committee on Aging has proposed the informatization of elderly care services and promoted the construction of Internet-based virtual nursing homes. How to ensure that elderly users can enjoy high-quality smart elderly care services, promote the combination of traditional elderly care services with intelligent and digital technologies, and provide the elderly with convenient, efficient, and safe care in their later years has become an issue we need to study. Summary of the invention

[0004] The purpose of the present invention is to provide a smart elderly care service supervision system and method for elderly care to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A method for supervising smart elderly care services for elderly care, the method comprising the following steps:

[0007] Step S1: construct a community elderly care database, which includes community data and community elderly data; based on the activity scope of community elderly care, construct an activity area set and a community elderly set;

[0008] Step S2: Mark the activity areas and calculate the weights of the activity areas in the same time period;

[0009] Step S3: extracting community elderly rescue data in the activity area, calculating the safety factor of the activity area, and pre-allocating the number of caregivers in the activity area;

[0010] Step S4: With user authorization, extract the medical history log of the elderly in the community, build a disease assessment model, and assess the medical condition of the elderly in the community; calculate the risk probability of the elderly in the community waiting for assistance, build a coordinate axis to generate a broken line to obtain a function; calculate the predicted value of the risk probability of all elderly people in the community waiting for assistance in the activity area, generate a risk monitoring sequence in the activity area, and send the risk monitoring sequence in the activity area to the caregiver.

[0011] Furthermore, the specific implementation process of step S1 includes:

[0012] Step S1.1: construct a community elderly care database, the community elderly care database is used to store community data and community elderly data; the community data includes the activity scope of community elderly care and community elderly rescue data; the community elderly data includes the location information of the community elderly and the disease course log of the community elderly, the disease course log of the community elderly records the physical monitoring data of the community elderly; locate the location information of the community elderly through wearable devices, and use the wearable devices to obtain the physical monitoring data of the community elderly, the physical monitoring data includes blood sugar data, blood pressure data and heart rate data;

[0013] Step S1.2: Based on the activity range of community elderly care, construct an activity area set B = (B i |i∈[1,I]}, where B i represents the ith activity area, I represents the total number of activity areas; construct the community elderly set A = {A j |j∈[1,J]}, where A j Represents the jth elderly person in the community within the jurisdiction of the community.

[0014] Furthermore, the specific implementation process of step S2 includes:

[0015] Step S2.1: Divide the time range within a day into time periods, and record the xth time period as T x , for the active area B i Mark it as B i |T x ; Statistical time period T x Activity Area B i Total number of elderly people in the community;

[0016] Step S2.2: Based on the community activity area data, pre-process the community activity area data to extract the activity area B in the same time period within the first preset time. i The total number of elderly people in the community, calculate the same time period T x Activity Area B i Weight Wherein, M represents the total number of days after preprocessing within the first preset time, count(B i |x) m represents the mth day time period T x Enter activity area B i The total number of elderly people in the community.

[0017] The purpose of preprocessing the community activity area data is to remove outliers in the community activity area data and improve the data quality. Outliers in the community activity area data may lead to misleading results. For example, holding community activities will cause community elderly people to gather to participate in the activities. The total number of community elderly people in the activity area where community activities are held will increase, while the total number of community elderly people in other activity areas where no community activities are held will decrease.

[0018] Furthermore, the specific implementation process of step S3 includes:

[0019] Step S3.1: Extract community elderly rescue data from each activity area, activity area B i The number of elderly people rescued in the community D|B i , calculate the active area B i Safety factor

[0020] Step S3.2: Calculate the activity area B based on the safety factor of the activity area i Actual weight of caregivers:

[0021] Step S3.3: Pre-allocate the number of caregivers in the activity area: G(B i |T x )=G×f(B i |T x ), where G(B i |T x ) indicates that in the time period T x Pre-allocated to activity area B i The total number of caregivers, G represents the total number of caregivers on duty that day.

[0022] The environment of different activity areas is different. For example, some community activity areas have badminton and table tennis facilities indoors with air-conditioning equipment; some activity areas have pavilions for community elderly people to rest in the cool breeze; some activity areas have sports facilities that community elderly people like and can exercise for community elderly people; some activity areas can provide community elderly people with sunbathing, etc.; the preferences of the elderly in different communities are different, and the degree of gathering is also different. Therefore, for the safety of the elderly in the community and to prevent caregivers from being unable to provide timely emergency treatment when accidents occur, the total number of caregivers in different activity areas needs to be reasonably allocated; at the same time, due to different light intensities and different time periods, the degree of gathering of the elderly in the community is also different, so the caregivers need to be reasonably allocated in different time periods.

[0023] Furthermore, the specific implementation process of step S4 includes:

[0024] Step S4.1: With the authorization of the user, extract the medical history log of the elderly in the community and build a disease assessment model. Among them, U represents the preset maximum community elderly condition assessment value, w1, w2, w3 represent the number of abnormalities of blood sugar, blood pressure and heart rate in the preset period, α1, α2, α3 represent the preset health assessment coefficients, and uo represents the community elderly condition assessment value;

[0025] Step S4.2: Calculate the risk probability of community elderly people waiting for assistance: DEF(uo)=D(uo) / D, where DEF(uo) represents the risk probability of community elderly people waiting for assistance when the medical condition assessment value of the community elderly is greater than uo, D(uo) represents the number of historical elderly assistance data whose medical condition assessment value of the community elderly is greater than uo, and D represents the total number of historical elderly rescue data;

[0026] Construct a coordinate system with the assessment value of the condition of the elderly in the community as the horizontal axis and the risk probability of the elderly in the community waiting for assistance as the vertical axis, map the data point (uo, DEF (uo)) on the coordinate system to obtain the coordinate point, connect the adjacent coordinate points in the order of the horizontal axis coordinate value from small to large to generate a broken line, and obtain the function corresponding to the broken line;

[0027] Step S4.3: Extract time period T x Activity Area B i Real-time body monitoring data of wearable devices of the elderly in the community, for time period T x Activity Area B i The condition of the elderly in the community is evaluated and the time period T is obtained. x Activity Area B i Assessment value of the medical condition of the elderly in the community;

[0028] Set the time period T x Activity Area B i Substitute the assessment value of the condition of the elderly in the community into the function to calculate the activity area B i The predicted value of the risk probability of all elderly people in the community waiting for assistance in the activity area B i Community Elderly A j The predicted value of the probability of waiting for rescue risk is added with the label of the elderly in the community, denoted as DEF(uo)|A j ; Generate activity area B according to the predicted value of the risk probability of the elderly in the community waiting for assistance from large to small i Within the risk monitoring sequence, the activity area B i The internal risk monitoring sequence is sent to time period T x Activity Area B i Caregivers within.

[0029] By digitally processing the medical conditions of the elderly in the community, that is, the activity area risk monitoring sequence, caregivers know which elderly in the community are the focus of attention. The earlier the element in the sequence, the more attention the elderly in the community corresponding to the element needs, thereby achieving immediate handling of sudden medical conditions of the elderly in the community, increasing the safety of the elderly in the community and improving the quality of elderly care services.

[0030] A smart elderly care service supervision system for elderly care, the system comprising: a data acquisition module, a data processing module, a distribution module and a monitoring module;

[0031] The data acquisition module includes a data storage unit and a collection unit, which are used to construct a community elderly care database, an activity area collection and a community elderly collection;

[0032] The data processing module includes a marking unit and a weighting unit, which calculates the weights of the activity areas in the same time period by marking the activity areas;

[0033] The allocation module includes a safety factor unit and a pre-allocation unit, which extracts community elderly rescue data in the activity area, calculates the safety factor of the activity area, and pre-allocates the number of caregivers in the activity area;

[0034] The monitoring module includes an evaluation unit, a risk unit and a sequence unit. The condition of the elderly in the community is evaluated by constructing a condition evaluation model; the risk probability of the elderly in the community waiting for assistance is calculated, and a function is obtained by constructing a coordinate axis to generate a broken line; the predicted value of the risk probability of all elderly people in the community waiting for assistance in the activity area is calculated, a risk monitoring sequence in the activity area is generated, and the risk monitoring sequence in the activity area is sent to the caregiver.

[0035] Further, the data acquisition module includes a data storage unit and a collection unit;

[0036] The data storage unit is used to construct a community elderly care database, and the community elderly care database is used to store community data and community elderly data; the community data includes the activity scope of community elderly care and community elderly rescue data; the community elderly data includes the location information of the community elderly and the disease course log of the community elderly, and the disease course log of the community elderly records the physical monitoring data of the community elderly; the location information of the community elderly is located by a wearable device, and the physical monitoring data of the community elderly is obtained by using the wearable device, and the physical monitoring data includes blood sugar data, blood pressure data and heart rate data;

[0037] The set unit constructs an activity area set B based on the activity range of community elderly care = (B i |i∈[1,I]}, where B irepresents the ith activity area, I represents the total number of activity areas; construct the community elderly set A = {A j |j∈[1,J]}, where A j Represents the jth elderly person in the community within the jurisdiction of the community.

[0038] Further, the data processing module includes a marking unit and a weighting unit;

[0039] The marking unit divides the time range within a day into time periods and records the xth time period as T x , for the active area B i Mark it as B i |T x ; Statistical time period T x Activity Area B i Total number of elderly people in the community;

[0040] The weighting unit pre-processes the community activity area data based on the community activity area data to extract the activity area B in the same time period within the first preset time. i The total number of elderly people in the community, calculate the same time period T x Activity Area B i Weight Wherein, M represents the total number of days after preprocessing within the first preset time, count(B i |x) m represents the mth day time period T x Enter activity area B i The total number of elderly people in the community.

[0041] Further, the allocation module includes a safety factor unit and a pre-allocation unit;

[0042] The safety factor unit extracts the community elderly rescue data of each activity area, and the activity area B i The number of elderly people rescued in the community D|B i , calculate the active area B i Safety factor

[0043] The pre-allocation unit calculates the activity area B based on the safety factor of the activity area. i Actual weight of caregivers: Pre-allocate the number of caregivers in the activity area: G(B i |T x )=G×f(B i |T x ), where G(B i |T x ) indicates that in the time period T xPre-allocated to activity area B i The total number of caregivers, G represents the total number of caregivers on duty that day.

[0044] Further, the monitoring module includes an assessment unit, a risk unit and a sequence unit;

[0045] The evaluation unit, with the authorization of the user, extracts the medical history log of the elderly in the community and constructs a disease evaluation model. Among them, U represents the preset maximum community elderly condition assessment value, w1, w2, w3 represent the number of abnormalities of blood sugar, blood pressure and heart rate in the preset period, α1, α2, α3 represent the preset health assessment coefficients, and uo represents the community elderly condition assessment value;

[0046] The risk unit calculates the risk probability of the elderly in the community waiting for assistance: DEF(uo)=D(uo) / D, wherein DEF(uo) represents the risk probability of the elderly in the community waiting for assistance when the medical condition assessment value of the elderly in the community is greater than uo, D(uo) represents the number of historical elderly assistance data whose medical condition assessment value of the elderly in the community is greater than uo, and D represents the total number of historical elderly rescue data; constructs a coordinate system with the medical condition assessment value of the elderly in the community as the horizontal axis and the risk probability of the elderly in the community waiting for assistance as the vertical axis, maps the data point (uo, DEF(uo)) on the coordinate system to obtain a coordinate point, connects adjacent coordinate points in order from small to large in the horizontal axis coordinate value to generate a broken line, and obtains a function corresponding to the broken line;

[0047] The sequence unit extracts the time period T x Activity Area B i Real-time body monitoring data of wearable devices of the elderly in the community, for time period T x Activity Area B i The condition of the elderly in the community is evaluated and the time period T is obtained. x Activity Area B i The assessment value of the condition of the elderly in the community; the time period T x Activity Area B i Substitute the assessment value of the condition of the elderly in the community into the function to calculate the activity area B i The predicted value of the risk probability of all elderly people in the community waiting for assistance in the activity area B i Community Elderly A j The predicted value of the probability of waiting for rescue risk is added with the label of the elderly in the community, denoted as DEF(uo)|A j ; Generate activity area B according to the predicted value of the risk probability of the elderly in the community waiting for assistance from large to small i Within the risk monitoring sequence, the activity area B i The internal risk monitoring sequence is sent to time period T x Activity Area Bi Caregivers within.

[0048] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in a smart elderly care service supervision system and method for elderly care provided by the present invention, a community elderly care database is constructed, which includes community data and community elderly data; an activity area set and a community elderly care set are constructed; the activity areas are marked, and the weights of the activity areas in the same time period are calculated; the rescue data of the community elderly in the activity areas are extracted, the safety factor of the activity areas is calculated, and the number of caregivers in the activity areas is pre-allocated; with the authorization of the user, the medical history logs of the community elderly are extracted, a disease assessment model is constructed, and the disease condition of the community elderly is assessed; the risk probability of the community elderly waiting for rescue is calculated; the predicted value of the risk probability of all community elderly people waiting for rescue in the activity area is calculated, a risk monitoring sequence in the activity area is generated, and the risk monitoring sequence in the activity area is sent to the caregiver; thereby improving the quality of elderly care services. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0050] Figure 1 It is a structural schematic diagram of a smart elderly care service supervision system for elderly care of the present invention;

[0051] Figure 2 It is a schematic diagram of the steps of a smart elderly care service supervision method for elderly care of the present invention. DETAILED DESCRIPTION

[0052] 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.

[0053] See also Figure 1-Figure 2 , the present invention provides a technical solution:

[0054] A method for supervising smart elderly care services for elderly care, the method comprising the following steps:

[0055] Step S1: construct a community elderly care database, which includes community data and community elderly data; based on the activity scope of community elderly care, construct an activity area set and a community elderly set;

[0056] Step S2: Mark the activity areas and calculate the weights of the activity areas in the same time period;

[0057] Step S3: extracting community elderly rescue data in the activity area, calculating the safety factor of the activity area, and pre-allocating the number of caregivers in the activity area;

[0058] Step S4: With user authorization, extract the medical history log of the elderly in the community, build a disease assessment model, and assess the medical condition of the elderly in the community; calculate the risk probability of the elderly in the community waiting for assistance, build a coordinate axis to generate a broken line to obtain a function; calculate the predicted value of the risk probability of all elderly people in the community waiting for assistance in the activity area, generate a risk monitoring sequence in the activity area, and send the risk monitoring sequence in the activity area to the caregiver.

[0059] Preferably, the specific implementation process of step S1 includes:

[0060] Step S1.1: construct a community elderly care database, which is used to store community data and community elderly data; the community data includes the scope of community elderly care activities and community elderly rescue data; the community elderly data includes the location information of the community elderly and the medical history log of the community elderly, and the medical history log of the community elderly records the physical monitoring data of the community elderly; the location information of the community elderly is located by wearable devices, and the physical monitoring data of the community elderly is obtained by using the wearable devices, and the physical monitoring data includes blood sugar data, blood pressure data and heart rate data;

[0061] Step S1.2: Based on the activity range of community elderly care, construct an activity area set B = {B i |i∈[1,I]}, where B i represents the ith activity area, I represents the total number of activity areas; construct the community elderly set A = {A j |j∈[1,J]}, where A j Represents the jth elderly person in the community within the jurisdiction of the community.

[0062] Preferably, the specific implementation process of step S2 includes:

[0063] Step S2.1: Divide the time range within a day into time periods, and record the xth time period as T x , for the active area B i Mark it as B i |T x ; Statistical time period T x Activity Area B i Total number of elderly people in the community;

[0064] Step S2.2: Based on the community activity area data, pre-process the community activity area data to extract the activity area B in the same time period within a preset time.i The total number of elderly people in the community, calculate the same time period T x Activity Area B i Weight Where M represents the total number of days after preprocessing within the preset time, count(B i |x) m represents the mth day time period T x Enter activity area B i The total number of elderly people in the community.

[0065] For example: the preset time is 3 days, and the total number of community elderly people in activity areas B1~B5 in the third time period T3 within three days is {6, 3, 2, 8, 6}, {6, 3, 3, 8, 6} and {9, 3, 1, 8, 6}, then a(B1|T3)=0.3, a(B2|T3)=0.1, a(B3|T3)=0.1, a(B4|T3)=0.3, a(B5|T3)=0.2.

[0066] Preferably, the specific implementation process of step S3 includes:

[0067] Step S3.1: Extract community elderly rescue data from each activity area, activity area B i The number of elderly people rescued in the community D|B i , calculate the active area B i Safety factor

[0068] Step S3.2: Calculate the activity area B based on the safety factor of the activity area i Actual weight of caregivers:

[0069] Step S3.3: Pre-allocate the number of caregivers in the activity area: G(B i |T x )=G×f(B i |T x ), where G(B i |T x ) indicates that in the time period T x Pre-allocated to activity area B i The total number of caregivers, G represents the total number of caregivers on duty that day.

[0070] For example: the number of community elderly rescuers in activity areas B1~B5 is {4, 2, 8, 2, 4}, respectively. The safety factors of activity areas B1~B5 are {0.2, 0.1, 0.4, 0.1, 0.2}, respectively; the actual weights of caregivers in activity areas B1~B5 are {0.33, 0.06, 0.22, 0.17, 0.22}, respectively. It is known that the total number of caregivers on duty that day is G=100, then the pre-allocated number of people in activity areas B1~B5 is {33, 6, 22, 17, 22}, respectively.

[0071] Preferably, the specific implementation process of step S4 includes:

[0072] Step S4.1: With the authorization of the user, extract the medical history log of the elderly in the community and build a disease assessment model. Among them, U represents the preset maximum community elderly condition assessment value, w1, w2, w3 represent the number of abnormalities of blood sugar, blood pressure and heart rate in the preset period, α1, α2, α3 represent the preset health assessment coefficients, and uo represents the community elderly condition assessment value;

[0073] Step S4.2: Calculate the risk probability of community elderly people waiting for assistance: DEF(uo)=D(uo) / D, where DEF(uo) represents the risk probability of community elderly people waiting for assistance when the medical condition assessment value of the community elderly is greater than uo, D(uo) represents the number of historical elderly assistance data whose medical condition assessment value of the community elderly is greater than uo, and D represents the total number of historical elderly rescue data;

[0074] Construct a coordinate system with the assessment value of the condition of the elderly in the community as the horizontal axis and the risk probability of the elderly in the community waiting for assistance as the vertical axis, map the data point (uo, DEF (uo)) on the coordinate system to obtain the coordinate point, connect the adjacent coordinate points in the order of the horizontal axis coordinate value from small to large to generate a broken line, and obtain the function corresponding to the broken line;

[0075] Step S4.3: Extract time period T x Activity Area B i Real-time body monitoring data of wearable devices of the elderly in the community, for time period T x Activity Area B i The condition of the elderly in the community is evaluated and the time period T is obtained. x Activity Area B i Assessment value of the medical condition of the elderly in the community;

[0076] Set the time period T x Activity Area B i Substitute the assessment value of the condition of the elderly in the community into the function to calculate the activity area B i The predicted value of the risk probability of all elderly people in the community waiting for assistance in the activity area B iCommunity Elderly A j The predicted value of the probability of waiting for rescue risk is added with the label of the elderly in the community, denoted as DEF(uo)|A j ; Generate activity area B according to the predicted value of the risk probability of the elderly in the community waiting for assistance from large to small i Within the risk monitoring sequence, the activity area B i The internal risk monitoring sequence is sent to time period T x Activity Area B i Caregivers within.

[0077] A smart elderly care service supervision system for elderly care, the system includes: a data acquisition module, a data processing module, a distribution module and a monitoring module;

[0078] The data collection module includes a data storage unit and a collection unit, which are used to construct a community elderly care database, an activity area collection, and a community elderly collection;

[0079] The data processing module includes a marking unit and a weighting unit, which calculates the weights of the activity areas in the same time period by marking the activity areas;

[0080] The allocation module includes a safety factor unit and a pre-allocation unit, which extracts the community elderly rescue data in the activity area, calculates the safety factor of the activity area, and pre-allocates the number of caregivers in the activity area;

[0081] The monitoring module includes an assessment unit, a risk unit and a sequence unit. It evaluates the condition of the elderly in the community by constructing a disease assessment model; calculates the risk probability of the elderly in the community waiting for help, constructs a coordinate axis to generate a broken line to obtain a function; calculates the predicted value of the risk probability of all elderly people in the community waiting for help in the activity area, generates a risk monitoring sequence in the activity area, and sends the risk monitoring sequence in the activity area to the caregivers.

[0082] Specifically, the data acquisition module includes a data storage unit and a collection unit;

[0083] The data storage unit is used to construct a community elderly care database, which is used to store community data and community elderly data; the community data includes the scope of community elderly care activities and community elderly rescue data; the community elderly data includes the location information of the community elderly and the medical history log of the community elderly, and the medical history log of the community elderly records the physical monitoring data of the community elderly; the location information of the community elderly is located by wearable devices, and the physical monitoring data of the community elderly is obtained by using the wearable devices, and the physical monitoring data includes blood sugar data, blood pressure data and heart rate data;

[0084] The collection unit, based on the activity range of community elderly care, constructs the activity area collection B = (B i |i∈[1,I]}, where Bi represents the ith activity area, I represents the total number of activity areas; construct the community elderly set A = {A j |j∈[1,J]}, where A j Represents the jth elderly person in the community within the jurisdiction of the community.

[0085] Specifically, the data processing module includes a marking unit and a weighting unit;

[0086] Marking unit, by dividing the time range within a day into time periods, the xth time period is recorded as T x , for the active area B i Mark it as B i |T x ; Statistical time period T x Activity Area B i Total number of elderly people in the community;

[0087] The weighting unit pre-processes the community activity area data based on the community activity area data, extracts the activity area B in the same time period within the first preset time period i The total number of elderly people in the community, calculate the same time period T x Activity Area B i Weight Wherein, M represents the total number of days after preprocessing within the first preset time, count(B i |x) m represents the mth day time period T x Enter activity area B i The total number of elderly people in the community.

[0088] Specifically, the allocation module includes a safety factor unit and a pre-allocation unit;

[0089] Safety factor unit, by extracting community elderly rescue data from each activity area, activity area B i The number of elderly people rescued in the community D|B i , calculate the active area B i Safety factor

[0090] Pre-allocate the unit, calculate the activity area B based on the safety factor of the activity area i Actual weight of caregivers: Pre-allocate the number of caregivers in the activity area: G(B i |T x )=G×f(B i |T x ), where G(B i |T x ) indicates that in the time period T xPre-allocated to activity area B i The total number of caregivers, G represents the total number of caregivers on duty that day.

[0091] Specifically, the monitoring module includes an assessment unit, a risk unit, and a sequence unit;

[0092] The evaluation unit, with user authorization, extracts the medical history logs of the elderly in the community and builds a disease assessment model. Among them, U represents the preset maximum community elderly condition assessment value, w1, w2, w3 represent the number of abnormalities of blood sugar, blood pressure and heart rate in the preset period, α1, α2, α3 represent the preset health assessment coefficients, and uo represents the community elderly condition assessment value;

[0093] The risk unit calculates the risk probability of the elderly in the community waiting for assistance: DEF(uo)=D(uo) / D, wherein DEF(uo) represents the risk probability of the elderly in the community waiting for assistance when the medical condition assessment value of the elderly in the community is greater than uo, D(uo) represents the number of historical elderly assistance data whose medical condition assessment value of the elderly in the community is greater than uo, and D represents the total number of historical elderly rescue data; a coordinate system is constructed with the medical condition assessment value of the elderly in the community as the horizontal axis and the risk probability of the elderly in the community waiting for assistance as the vertical axis, the data point (uo, DEF(uo)) is mapped on the coordinate system to obtain a coordinate point, and adjacent coordinate points are connected in order from small to large in the horizontal axis coordinate value to generate a broken line, and the function corresponding to the broken line is obtained;

[0094] Sequence unit, by extracting time period T x Activity Area B i Real-time body monitoring data of wearable devices of the elderly in the community, for time period T x Activity Area B i The condition of the elderly in the community is evaluated and the time period T is obtained. x Activity Area B i The assessment value of the condition of the elderly in the community; the time period T x Activity Area B i Substitute the assessment value of the condition of the elderly in the community into the function to calculate the activity area B i The predicted value of the risk probability of all elderly people in the community waiting for assistance in the activity area B i Community Elderly A j The predicted value of the probability of waiting for rescue risk is added with the label of the elderly in the community, denoted as DEF(uo)|A j ; Generate activity area B according to the predicted value of the risk probability of the elderly in the community waiting for assistance from large to small i Within the risk monitoring sequence, the activity area B i The internal risk monitoring sequence is sent to time period T x Activity Area B iCaregivers within.

[0095] 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.

[0096] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A smart elderly care service supervision method for elderly care, characterized in that: The method comprises the following steps: Step S1: construct a community elderly care database, which includes community data and community elderly data; based on the activity scope of community elderly care, construct an activity area set and a community elderly set; Step S2: Mark the activity areas and calculate the weights of the activity areas in the same time period; Step S3: extracting community elderly rescue data in the activity area, calculating the safety factor of the activity area, and pre-allocating the number of caregivers in the activity area; Step S4: With the authorization of the user, extract the medical history log of the elderly in the community, build a disease assessment model, and assess the medical condition of the elderly in the community; calculate the risk probability of the elderly in the community waiting for assistance, build a coordinate axis to generate a broken line to obtain a function; calculate the predicted value of the risk probability of all elderly people in the community waiting for assistance in the activity area, generate a risk monitoring sequence in the activity area, and send the risk monitoring sequence in the activity area to the caregiver; The specific implementation process of step S1 includes: Step S1.1: construct a community elderly care database, the community elderly care database is used to store community data and community elderly data; the community data includes the activity scope of community elderly care and community elderly rescue data; the community elderly data includes the location information of the community elderly and the disease course log of the community elderly, the disease course log of the community elderly records the physical monitoring data of the community elderly; locate the location information of the community elderly through wearable devices, and use the wearable devices to obtain the physical monitoring data of the community elderly, the physical monitoring data includes blood sugar data, blood pressure data and heart rate data; Step S1.2: Based on the activity range of community elderly care, construct an activity area set B = {B i |i∈[1,I]}, where B i represents the ith activity area, I represents the total number of activity areas; construct the community elderly set A = {A j |j∈[1,J]}, where A j represents the jth elderly person in the community within the jurisdiction of the community; The specific implementation process of step S2 includes: Step S2.1: Divide the time range within a day into time periods, and record the xth time period as T x , for the active area B i Mark it as B i |T x ; Statistical time period T x Activity Area B i Total number of elderly people in the community; Step S2.2: Based on the community activity area data, pre-process the community activity area data to extract the x Activity Area B i The total number of elderly people in the community, calculate the same time period T x Activity Area B i Weight Where M represents the total number of days after preprocessing within the first preset time, count(B i |T x ) m represents the mth day time period T x Enter activity area B i Total number of elderly people in the community; The specific implementation process of step S3 includes: Step S3.1: Extract community elderly rescue data from each activity area, activity area B i The number of elderly people rescued in the community D|B i , calculate the active area B i Safety factor Step S3.2: Calculate the activity area B based on the safety factor of the activity area i Actual weight of caregivers: Step S3.3: Pre-allocate the number of caregivers in the activity area: G(B i |T x )=G×f(B i |T x ), where G(B i |T x ) indicates that in the time period T x Pre-allocated to activity area B i The total number of caregivers, G represents the total number of caregivers on duty that day.

2. A smart elderly care service supervision method for elderly care according to claim 1, characterized in that: The specific implementation process of step S4 includes: Step S4.1: With the authorization of the user, extract the medical history log of the elderly in the community and build a disease assessment model. Among them, U represents the preset maximum community elderly condition assessment value, w1, w2, w3 represent the number of abnormalities of blood sugar, blood pressure and heart rate in the preset period, α1, α2, α3 represent the preset health assessment coefficients, and uo represents the community elderly condition assessment value; Step S4.2: Calculate the risk probability of community elderly people waiting for assistance: DEF(uo)=D(uo) / D, where DEF(uo) represents the risk probability of community elderly people waiting for assistance when the medical condition assessment value of the community elderly is greater than uo, D(uo) represents the number of historical elderly assistance data whose medical condition assessment value of the community elderly is greater than uo, and D represents the total number of historical elderly rescue data; Construct a coordinate system with the assessment value of the condition of the elderly in the community as the horizontal axis and the risk probability of the elderly in the community waiting for assistance as the vertical axis, map the data point (uo, DEF (uo)) on the coordinate system to obtain the coordinate point, connect the adjacent coordinate points in the order of the horizontal axis coordinate value from small to large to generate a broken line, and obtain the function corresponding to the broken line; Step S4.3: Extract time period T x Activity Area B i Real-time body monitoring data of wearable devices of the elderly in the community, for time period T x Activity Area B i The condition of the elderly in the community is evaluated and the time period T is obtained. x Activity Area B i Assessment value of the medical condition of the elderly in the community; Set the time period T x Activity Area B i Substitute the assessment value of the condition of the elderly in the community into the function to calculate the activity area B i The predicted value of the risk probability of all elderly people in the community waiting for assistance in the activity area B i Community Elderly A j The predicted value of the probability of waiting for rescue risk is added with the label of the elderly in the community, denoted as DEF(uo)|A j ; Generate activity area B according to the predicted value of the risk probability of the elderly in the community waiting for assistance from large to small i Within the risk monitoring sequence, the activity area B i The internal risk monitoring sequence is sent to time period T x Activity Area B i Caregivers within.

3. A smart elderly care service supervision system for elderly care, characterized in that: The system includes: a data acquisition module, a data processing module, a distribution module and a monitoring module; The data acquisition module includes a data storage unit and a collection unit, which are used to construct a community elderly care database, an activity area collection and a community elderly collection; The data processing module includes a marking unit and a weighting unit, which calculates the weights of the activity areas in the same time period by marking the activity areas; The allocation module includes a safety factor unit and a pre-allocation unit, which extracts community elderly rescue data in the activity area, calculates the safety factor of the activity area, and pre-allocates the number of caregivers in the activity area; The monitoring module includes an evaluation unit, a risk unit and a sequence unit. The condition of the elderly in the community is evaluated by constructing a condition evaluation model; the risk probability of the elderly in the community waiting for assistance is calculated, and a function is obtained by constructing a coordinate axis to generate a broken line; the predicted value of the risk probability of all elderly people in the community waiting for assistance in the activity area is calculated, and a risk monitoring sequence in the activity area is generated, and the risk monitoring sequence in the activity area is sent to the caregiver; The data acquisition module includes a data storage unit and a collection unit; The data storage unit is used to construct a community elderly care database, and the community elderly care database is used to store community data and community elderly data; the community data includes the activity scope of community elderly care and community elderly rescue data; the community elderly data includes the location information of the community elderly and the disease course log of the community elderly, and the disease course log of the community elderly records the physical monitoring data of the community elderly; the location information of the community elderly is located by a wearable device, and the physical monitoring data of the community elderly is obtained by using the wearable device, and the physical monitoring data includes blood sugar data, blood pressure data and heart rate data; The set unit constructs an activity area set B={B i |i∈[1,I]}, where B i represents the ith activity area, I represents the total number of activity areas; construct the community elderly set A = {A j |j∈[1,J]}, where A j represents the jth elderly person in the community within the jurisdiction of the community; The data processing module includes a marking unit and a weighting unit; The marking unit divides the time range within a day into time periods and records the xth time period as T x , for the active area B i Mark it as B i |T x ; Statistical time period T x Activity Area B i Total number of elderly people in the community; The weighting unit pre-processes the community activity area data based on the community activity area data to extract the activity area B in the same time period within the first preset time. i The total number of elderly people in the community, calculate the same time period T x Activity Area B i Weight Where M represents the total number of days after preprocessing within the first preset time, count(B i |x) m represents the mth day time period T x Enter activity area B i Total number of elderly people in the community; The allocation module includes a safety factor unit and a pre-allocation unit; The safety factor unit extracts the community elderly rescue data of each activity area, and the activity area B i The number of elderly people rescued in the community D|B i , calculate the active area B i Safety factor The pre-allocation unit calculates the activity area B based on the safety factor of the activity area. i Actual weight of caregivers: Pre-allocate the number of caregivers in the activity area: G(B i |T x )=G×f(B i |T x ), where G(B i |T x ) indicates that in the time period T x Pre-allocated to activity area B i The total number of caregivers, G represents the total number of caregivers on duty that day.

4. According to claim 3, a smart elderly care service supervision system for elderly care is characterized by: The monitoring module includes an assessment unit, a risk unit and a sequence unit; The evaluation unit, with the authorization of the user, extracts the medical history log of the elderly in the community and constructs a disease evaluation model. Among them, U represents the preset maximum community elderly condition assessment value, w1, w2, w3 represent the number of abnormalities of blood sugar, blood pressure and heart rate in the preset period, α1, α2, α3 represent the preset health assessment coefficients, and uo represents the community elderly condition assessment value; The risk unit calculates the risk probability of the elderly in the community waiting for assistance: DEF(uo)=D(uo) / D, wherein DEF(uo) represents the risk probability of the elderly in the community waiting for assistance when the medical condition assessment value of the elderly in the community is greater than uo, D(uo) represents the number of historical elderly assistance data whose medical condition assessment value of the elderly in the community is greater than uo, and D represents the total number of historical elderly rescue data; constructs a coordinate system with the medical condition assessment value of the elderly in the community as the horizontal axis and the risk probability of the elderly in the community waiting for assistance as the vertical axis, maps the data point (uo, DEF(uo)) on the coordinate system to obtain a coordinate point, connects adjacent coordinate points in order from small to large in the horizontal axis coordinate value to generate a broken line, and obtains a function corresponding to the broken line; The sequence unit extracts the time period T x Activity Area B i Real-time body monitoring data of wearable devices of the elderly in the community, for time period T x Activity Area B i The condition of the elderly in the community is evaluated and the time period T is obtained. x Activity Area B i The assessment value of the condition of the elderly in the community; the time period T x Activity Area B i Substitute the assessment value of the condition of the elderly in the community into the function to calculate the activity area B i The predicted value of the risk probability of all elderly people in the community waiting for assistance in the activity area B i Community Elderly A j The predicted value of the probability of waiting for rescue risk is added with the label of the elderly in the community, denoted as DEF(uo)|A j ; Generate activity area B according to the predicted value of the risk probability of the elderly in the community waiting for assistance from large to small i Within the risk monitoring sequence, the activity area B i The internal risk monitoring sequence is sent to time period T x Activity Area B i Caregivers within.

Images