Intelligent old-age nursing supervision system based on big data processing

Abstract

The invention belongs to the technical field of nursing supervision, and particularly relates to an intelligent old-age nursing supervision system based on big data processing, which comprises an intelligent monitoring acquisition module, a personnel state evaluation analysis module, an old-age nursing space influence analysis module, a nursing scheduling optimization evaluation module and an old-age nursing supervision terminal. Old-age nursing comprehensive monitoring is carried out through the intelligent monitoring and collecting module, and analysis is carried out through the personnel state evaluation and analysis module to judge whether the corresponding old people have health hidden dangers or not and early warning is carried out in time. The old-age nursing space influence analysis module analyzes the environment quality conditions of all the old-age nursing living spaces and conducts cleaning and environment regulation and control on the interiors of the corresponding old-age nursing living spaces in time, the public praise of the old-age nursing service is remarkably improved, and healthy old-age nursing is achieved. And when a nursing scheduling optimization bad signal is generated, scheduling supervision on nursing personnel is enhanced, so that the nursing risk of the aged is reduced, and the nursing service quality is ensured.

Description

Technical Field

[0001] The present invention relates to the field of nursing supervision technology, and in particular to a smart elderly care supervision system based on big data processing. Background Art

[0002] As the global aging problem intensifies, the traditional elderly care service model can no longer meet the growing elderly care needs. The Chinese invention patent with the publication number CN117151950A discloses a smart elderly care service information platform. Through the coordinated use of the elderly information entry module, the relative information entry module, the nursing level selection module and the bed selection module, the elderly information is recorded in more detail, which is convenient for future management and communication with relatives.

[0003] However, in actual application, the above-mentioned technical solution is difficult to conduct comprehensive monitoring and analysis of the elderly's status and the elderly living space they are in and timely warning, and it is also impossible to reasonably analyze and accurately evaluate the scheduling of elderly care staff and the quality of nursing services, which is not conducive to ensuring the healthy elderly care of the elderly and improving the reputation of elderly care services.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent elderly care supervision system based on big data processing, which solves the problem that the existing technology is difficult to comprehensively monitor and analyze the status of the elderly and the elderly living space they are in and to provide timely warnings, and is unable to reasonably analyze and accurately evaluate the scheduling status of elderly care personnel and the quality of nursing services, which is not conducive to ensuring the healthy care of the elderly and cannot significantly improve the reputation of elderly care services.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The smart elderly care supervision system based on big data processing includes a smart monitoring and collection module, a personnel status evaluation and analysis module, an elderly care space impact analysis module, a nursing scheduling optimization evaluation module and an elderly care supervision terminal; the smart monitoring and collection module collects various physiological data and behavioral data of the elderly in real time through smart Internet of Things devices, and monitors all elderly living spaces to collect various environmental data of the elderly living environment, and sends various physiological data and behavioral data of the elderly to the personnel status evaluation and analysis module, and sends various environmental data of all elderly living spaces to the elderly space impact analysis module;

[0008] The personnel status assessment and analysis module receives various physiological data and behavioral data of the corresponding elderly. If there is physiological data or behavioral data that does not meet the corresponding preset requirements, it is judged that the corresponding elderly has health risks and generates a status alarm signal, and the status alarm signal is sent to the elderly care supervision end;

[0009] The elderly care space impact analysis module analyzes the environmental quality status of all elderly care living spaces, and determines whether to generate a space warning signal and send it to the elderly care supervision end; when the elderly care supervision end receives a status alarm signal or a space warning signal, it notifies the nursing staff to take corresponding improvement measures; the nursing scheduling optimization evaluation module determines the nursing scheduling optimization performance through analysis, and generates a nursing scheduling optimization qualified signal or a nursing scheduling optimization poor signal based on this, and sends the nursing scheduling optimization qualified signal or the nursing scheduling optimization poor signal to the elderly care supervision end.

[0010] Furthermore, the specific analysis process of the elderly care space impact analysis module is: obtaining the garbage and dirt distribution value in the corresponding elderly care living space, and based on the air quality detection analysis to obtain the air quality detection value, the garbage and dirt distribution value and the air quality detection value are numerically compared with the preset garbage and dirt distribution threshold and the preset air quality detection threshold respectively; if the garbage and dirt distribution value or the air quality detection value exceeds the corresponding preset threshold, a space warning signal for the corresponding elderly care living space is generated.

[0011] Furthermore, the specific analysis process of the air quality detection and analysis is as follows: obtaining the environmental parameters that need to be monitored in the corresponding elderly living space, and if the data of all environmental parameters that need to be monitored meet the corresponding requirements, the value of the air quality detection value is set to zero;

[0012] If there are environmental parameter data that do not meet the corresponding requirements, the corresponding environmental parameters will be marked as alarm parameters, and the deviation values ​​of the corresponding alarm parameter data compared to the corresponding requirements will be marked as alarm level values; each environmental parameter is set in advance to correspond to a set of preset weight values ​​greater than zero, and the product of the alarm level value of the corresponding alarm parameter and the corresponding preset weight value is marked as the alarm analysis value, and the sum of the alarm analysis values ​​of all alarm parameters is marked as the air quality detection value of the corresponding elderly living space.

[0013] Furthermore, the specific analysis process of the nursing scheduling optimization evaluation module is as follows: setting a nursing cycle, collecting the number of times the state alarm signals of all elderly people are generated during the nursing cycle and summing them up to obtain the total frequency value of the state alarm, and collecting the number of times the space warning signals of all elderly living spaces are generated during the nursing cycle and summing them up to obtain the total frequency value of the space warning;

[0014] The average number of elderly people who need care during the care cycle is collected and marked as the caregiver inspection value, and the corresponding preset proportional coefficients are assigned to the state alarm total frequency value, the space warning total frequency value and the caregiver inspection value, respectively, and the state alarm total frequency value, the space warning total frequency value and the caregiver inspection value are multiplied by the corresponding preset proportional coefficients, and the sum of the three sets of product results is marked as the elderly care supervision coefficient;

[0015] The real-time number of nursing staff on duty is collected and marked as nursing detection values. The mean of all nursing detection values ​​within the detection period is calculated to obtain the nursing scheduling value. The target threshold is obtained through nursing matching analysis. The nursing scheduling value is numerically compared with the target threshold. If the nursing scheduling value exceeds the target threshold, a qualified nursing scheduling optimization signal is generated; if the nursing scheduling value does not exceed the target threshold, a poor nursing scheduling optimization signal is generated.

[0016] Furthermore, the specific analysis process of the nursing matching analysis is: setting several groups of preset elderly care supervision coefficient ranges in advance, and each group of preset elderly care supervision coefficient ranges corresponds to a group of preset nursing scheduling thresholds; comparing the elderly care supervision coefficient with all preset elderly care supervision coefficient ranges one by one, and marking the preset elderly care supervision coefficient range containing the corresponding elderly care supervision coefficient as the preferred range, and marking the preset nursing scheduling threshold corresponding to the preferred range as the target threshold.

[0017] Furthermore, the nursing scheduling optimization and evaluation module is communicatively connected to the nursing service tracing module. The nursing scheduling optimization and evaluation module sends the nursing scheduling optimization qualified signal to the nursing service tracing module. When the nursing service tracing module receives the nursing scheduling optimization qualified signal, it performs a nursing service tracing decision analysis, generates a nursing service non-optimal signal or a nursing service qualified signal through analysis, and sends the nursing service non-optimal signal or the nursing service qualified signal to the elderly care supervision end. When the elderly care supervision end receives the nursing service non-optimal signal, it issues a corresponding warning.

[0018] Furthermore, the specific analysis process of the nursing service traceability decision analysis is as follows: the number of complaints about nursing services during the detection period is collected and marked as the nursing complaint value, and the proportion of nursing staff who have received complaints about nursing services during the detection period is marked as the complaint matching value, and the nursing complaint value and the complaint matching value are numerically compared with the preset nursing complaint threshold and the preset complaint matching threshold respectively. If the nursing complaint value or the complaint matching value exceeds the corresponding preset threshold, a non-optimal nursing service signal is generated.

[0019] Furthermore, if the nursing complaint value and the complaint matching value do not exceed the corresponding preset threshold value, the monitoring images of all nursing staff performing nursing in the detection period are collected, and the poor nursing behaviors of all nursing staff are identified based on the monitoring images. The number of occurrences and the total duration of the poor nursing behaviors of the corresponding nursing staff are marked as nursing abnormal frequency values ​​and nursing abnormal time values, respectively. The nursing abnormal frequency values ​​and nursing abnormal time values ​​are numerically compared with the preset nursing abnormal frequency threshold value and the preset nursing abnormal time threshold value, respectively. If the nursing abnormal frequency value or the nursing abnormal time value exceeds the corresponding preset threshold value, the corresponding nursing staff is marked as an optimization object;

[0020] The proportion of the number of optimized objects in the detection period is obtained and marked as the optimization proportion value, and the optimization proportion value is numerically compared with the preset optimization proportion threshold. If the optimization proportion value exceeds the preset optimization proportion threshold, a non-optimal nursing service signal is generated.

[0021] Furthermore, if the optimized table occupancy value does not exceed the preset optimized table occupancy threshold, the nursing frequency values ​​of all nursing staff in the detection period are averaged to obtain the nursing frequency value, and the nursing time values ​​of all nursing staff in the detection period are averaged to obtain the nursing time value;

[0022] When a status alarm signal or a space warning signal is generated, the time when the corresponding signal is generated is marked as the first time, and the time when the nursing staff starts to take treatment measures is marked as the second time, and the interval between the first time and the second time is marked as the nursing delay time;

[0023] All nursing delay times within the detection period are collected and their mean is calculated to obtain the nursing effectiveness inspection value, and the nursing service abnormal inspection coefficient is calculated by weighted summation of the nursing complaint value, complaint matching value, optimization table value, nursing frequency value, nursing time value and nursing effectiveness inspection value. The nursing service abnormal inspection coefficient is numerically compared with the preset nursing service abnormal inspection coefficient threshold. If the nursing service abnormal inspection coefficient exceeds the preset nursing service abnormal inspection coefficient threshold, a nursing service non-optimal signal is generated; if the nursing service abnormal inspection coefficient does not exceed the preset nursing service abnormal inspection coefficient threshold, a nursing service qualified signal is generated.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] 1. In the present invention, the intelligent monitoring and collection module is used to conduct comprehensive monitoring of elderly care, the personnel status assessment and analysis module is used to analyze whether the corresponding elderly have health risks and timely warn, and the elderly care space impact analysis module is used to analyze the environmental quality of all elderly care living spaces, thereby reducing the difficulty of elderly care supervision, significantly improving the reputation of elderly care services and facilitating the realization of healthy elderly care, and the nursing scheduling optimization evaluation module is used to analyze the nursing scheduling optimization performance, strengthen the scheduling supervision of nursing staff when a bad nursing scheduling optimization signal is generated, reduce the risk of elderly care and ensure the quality of nursing services;

[0026] 2. In the present invention, the nursing scheduling optimization qualified signal is sent to the nursing service tracing module through the nursing scheduling optimization evaluation module. When the nursing service tracing module receives the nursing scheduling optimization qualified signal, it performs nursing service tracing decision analysis, and strengthens the supervision and training of nursing staff when a non-optimal nursing service signal is generated, so as to ensure the subsequent nursing service quality and reputation, and has a high degree of intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0028] Figure 1 This is a system block diagram of Embodiment 1 of the present invention;

[0029] Figure 2 This is a system block diagram of Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0030] 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.

[0031] Embodiment 1: Figure 1 As shown, the smart elderly care supervision system based on big data processing proposed by the present invention includes a smart monitoring and acquisition module, a personnel status evaluation and analysis module, an elderly care space impact analysis module, a nursing scheduling optimization evaluation module and an elderly care supervision terminal;

[0032] The smart monitoring and acquisition module collects various physiological data (such as heart rate, blood pressure, blood sugar, etc.) and behavioral data (such as activity trajectory, sleep quality, etc.) of the elderly in real time through smart IoT devices (including smart bracelets, smart mattresses, cameras, etc.), and monitors all elderly living spaces to collect various environmental data of the elderly’s living environment (including temperature, humidity, dust concentration, oxygen concentration, etc.), to achieve comprehensive monitoring of elderly care to ensure the safety and comfort of the elderly, and send the elderly’s various physiological and behavioral data to the personnel status assessment and analysis module, and send various environmental data of all elderly living spaces to the elderly space impact analysis module.

[0033] The personnel status assessment and analysis module receives various physiological data and behavioral data of the corresponding elderly people. If there are physiological data or behavioral data that do not meet the corresponding preset requirements, it is judged that the corresponding elderly people have health risks and a status alarm signal is generated, and the status alarm signal is sent to the elderly care supervision end. When the elderly care supervision end receives the status alarm signal, it notifies the nursing staff to take corresponding improvement measures. By real-time monitoring and early warning of potential health risks and timely taking reasonable measures, the risk of sudden illness in the elderly is reduced, which is conducive to providing precise nursing services according to the health status and needs of the elderly, and significantly improving the reputation of elderly care services.

[0034] The elderly care space impact analysis module analyzes the environmental quality of all elderly care living spaces, and determines whether to generate a space warning signal and send it to the elderly care supervision end. When the elderly care supervision end receives the space warning signal, it notifies the nursing staff to take corresponding improvement measures, mainly to clean and regulate the environment in the corresponding elderly care living space, ensure the cleanliness and comfort of the elderly care living space, further improve the reputation of elderly care services, and help achieve healthy elderly care; the specific analysis process of the elderly care space impact analysis module is as follows:

[0035] Obtaining the garbage and dirt distribution value in the corresponding elderly living space, wherein the garbage and dirt distribution value is a data quantity value indicating the ratio of the space volume occupied by garbage and dirt in the corresponding elderly living space to the total volume of the elderly living space, and the larger the value of the garbage and dirt distribution value is, the dirtier and more unfavorable the corresponding elderly living space is, and the less conducive it is for the elderly to live;

[0036] And based on the air quality detection analysis to obtain the air quality detection value, specifically: obtain the environmental parameters that need to be monitored in the corresponding elderly living space, compare the data of all environmental parameters with the corresponding preset requirements, if the data of all environmental parameters that need to be monitored meet the corresponding requirements, indicating that the air quality in the corresponding elderly living space at the corresponding moment is very good, then the air quality detection value is set to zero;

[0037] If there are environmental parameter data that do not meet the corresponding requirements, the corresponding environmental parameter is marked as an alarm parameter, and the deviation value of the corresponding alarm parameter data compared to the corresponding requirement is marked as an alarm level value; each environmental parameter is set in advance to correspond to a set of preset weight values ​​greater than zero, and the more important the corresponding environmental parameter is, the greater the value of the preset weight value matching it is;

[0038] The product of the alarm level value of the corresponding alarm parameter and the corresponding preset weight value is marked as the alarm analysis value, and the sum of the alarm analysis values ​​of all alarm parameters is marked as the air quality detection value of the corresponding elderly living space; it should be noted that the larger the value of the air quality detection value, the worse the air quality condition in the corresponding elderly living space at the corresponding moment;

[0039] The garbage and dirt distribution value and the air quality detection value are numerically compared with the preset garbage and dirt distribution threshold and the preset air quality detection threshold respectively. If the garbage and dirt distribution value or the air quality detection value exceeds the corresponding preset threshold, it indicates that the environmental conditions in the corresponding elderly living space at the corresponding moment are poor, which is more unfavorable to ensuring the living comfort of the elderly, and a spatial warning signal for the corresponding elderly living space is generated.

[0040] The nursing scheduling optimization evaluation module judges the nursing scheduling optimization performance through analysis, and generates a nursing scheduling optimization qualified signal or a nursing scheduling optimization poor signal based on it, and sends the nursing scheduling optimization qualified signal or the nursing scheduling optimization poor signal to the elderly care supervision end. When the elderly care supervision end receives the nursing scheduling optimization poor signal, it issues an early warning and promptly strengthens the scheduling supervision of nursing staff, reduces the risk of elderly care and ensures the quality of nursing services, with a high degree of intelligence; the specific analysis process of the nursing scheduling optimization evaluation module is as follows:

[0041] A nursing cycle is set, preferably, the nursing cycle is twenty days; the number of times the state alarm signals of all elderly people are generated during the nursing cycle is collected and summed up to obtain the total frequency value of the state alarm (obtained from the personnel state assessment and analysis module), and the number of times the space warning signals of all elderly living spaces are generated during the nursing cycle is collected and summed up to obtain the total frequency value of the space warning (obtained from the elderly space impact analysis module);

[0042] The average number of elderly people who need care during the care cycle is collected and marked as the caregiver inspection value, and the corresponding preset proportional coefficients are respectively assigned to the state alarm total frequency value, the space warning total frequency value and the caregiver inspection value (and the values ​​of the assigned preset proportional coefficients are all positive numbers), and the state alarm total frequency value, the space warning total frequency value and the caregiver inspection value are respectively multiplied by the corresponding preset proportional coefficients, and the sum of the three sets of product results is marked as the elderly care supervision coefficient;

[0043] The target threshold is obtained through nursing matching analysis, specifically: several groups of preset elderly care supervision coefficient ranges are set in advance, and each group of preset elderly care supervision coefficient ranges corresponds to a group of preset nursing scheduling thresholds; it should be noted that the larger the value of the preset elderly care supervision coefficient range, the larger the value of the preset nursing scheduling threshold matched therewith;

[0044] Compare the elderly care supervision coefficient with all preset elderly care supervision coefficient ranges one by one, mark the preset elderly care supervision coefficient range containing the corresponding elderly care supervision coefficient as the preferred range, and mark the preset nursing scheduling threshold corresponding to the preferred range as the target threshold;

[0045] The real-time number of nursing staff on duty is collected and marked as nursing detection values, and the nursing scheduling value is obtained by averaging all nursing detection values ​​within the detection period. The nursing scheduling value is numerically compared with the target threshold. If the nursing scheduling value exceeds the target threshold, it indicates that the scheduling arrangement for nursing staff within the detection period is good, and a qualified nursing scheduling optimization signal is generated; if the nursing scheduling value does not exceed the target threshold, it indicates that the scheduling arrangement for nursing staff within the detection period is not good, and the nursing care risk brought about is relatively large, and a poor nursing scheduling optimization signal is generated.

[0046] Embodiment 2: Figure 2 As shown, the difference between this embodiment and the first embodiment is that the nursing scheduling optimization evaluation module is connected to the nursing service tracing module in communication, the nursing scheduling optimization evaluation module sends the nursing scheduling optimization qualified signal to the nursing service tracing module, and the nursing service tracing module performs nursing service tracing decision analysis when receiving the nursing scheduling optimization qualified signal, and generates a nursing service non-optimal signal or a nursing service qualified signal through analysis;

[0047] The non-optimal nursing service signal or the qualified nursing service signal is sent to the elderly care supervision end. When the elderly care supervision end receives the non-optimal nursing service signal, it issues a corresponding warning, which can comprehensively analyze and reasonably evaluate the quality of elderly care services during the detection period, and promptly remind the back-end supervisors to strengthen the supervision and training of nursing staff to ensure the subsequent nursing service quality and reputation; the specific analysis process of nursing service traceability decision analysis is as follows:

[0048] The number of complaints about nursing services during the detection period is collected and marked as the nursing complaint value, and the proportion of nursing staff who received complaints about nursing services during the detection period is marked as the complaint matching value (i.e., the ratio of the number of nursing staff who received complaints to the total number of nursing staff). The nursing complaint value and the complaint matching value are numerically compared with the preset nursing complaint threshold and the preset complaint matching threshold, respectively. If the nursing complaint value or the complaint matching value exceeds the corresponding preset threshold, it indicates that the nursing service performance during the detection period is poor, and a non-optimal nursing service signal is generated;

[0049] If the nursing complaint value and the complaint matching value do not exceed the corresponding preset threshold, the monitoring images of all nursing staff performing nursing during the detection period are collected, and the bad nursing behaviors (including insults, beatings, etc.) of all nursing staff are identified based on the monitoring images. The number of occurrences and the total duration of the bad nursing behaviors of the corresponding nursing staff during the detection period are marked as the nursing abnormal frequency value and the nursing abnormal time value respectively;

[0050] The nursing frequency difference value and the nursing time difference value are numerically compared with the preset nursing frequency difference threshold value and the preset nursing time difference threshold value, respectively. If the nursing frequency difference value or the nursing time difference value exceeds the corresponding preset threshold value, indicating that the service status of the corresponding nursing staff during the detection period is poor, the corresponding nursing staff is marked as an optimization object;

[0051] The proportion of the number of optimized objects in the detection period is obtained and marked as the optimization proportion value, and the optimization proportion value is numerically compared with the preset optimization proportion threshold. If the optimization proportion value exceeds the preset optimization proportion threshold, it indicates that the nursing service performance in the detection period is poor, and a non-optimal nursing service signal is generated.

[0052] Furthermore, if the optimized table occupancy value does not exceed the preset optimized table occupancy threshold, the nursing frequency values ​​of all nursing staff in the detection period are averaged to obtain the nursing frequency value, and the nursing time values ​​of all nursing staff in the detection period are averaged to obtain the nursing time value;

[0053] When a status alarm signal or a space warning signal is generated, the corresponding signal generation time is marked as the first time, and the time when the nursing staff starts to take treatment measures is marked as the second time, and the interval between the first time and the second time is marked as the nursing delay time; wherein, the larger the value of the nursing delay time is, the lower the emergency treatment efficiency for the corresponding warning is;

[0054] All nursing delays in the detection period are collected and their average is calculated to obtain the nursing effectiveness inspection value. The nursing complaint value W, complaint matching value B, optimization table value L, nursing frequency value S, nursing time value N and nursing effectiveness inspection value X are weighted and summed to obtain the nursing service abnormal inspection coefficient FAq through the formula FAq=c×W+t×B+n×L+e×S+a×N+h×X; among them, c, t, n, e, a, h are preset proportional coefficients with values ​​greater than zero, and the larger the value of the nursing service abnormal inspection coefficient FAq, the worse the overall nursing performance of the elderly care in the detection period is.

[0055] It should be noted that the above formula is a dimensionless numerical calculation, and the formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formula are set by technicians in this field according to actual conditions;

[0056] The nursing service anomaly detection coefficient FAq is numerically compared with the preset nursing service anomaly detection coefficient threshold. If the nursing service anomaly detection coefficient FAq exceeds the preset nursing service anomaly detection coefficient threshold, it indicates that the elderly care performance during the detection period is generally poor, and a non-optimal nursing service signal is generated; if the nursing service anomaly detection coefficient FAq does not exceed the preset nursing service anomaly detection coefficient threshold, it indicates that the elderly care performance during the detection period is generally good, and a qualified nursing service signal is generated.

[0057] The working principle of the present invention is as follows: when in use, the intelligent monitoring and acquisition module collects various physiological data, behavioral data of the elderly and various environmental data of all elderly living spaces in real time. The personnel status assessment and analysis module determines whether the corresponding elderly have health risks based on the various physiological data and behavioral data of the corresponding elderly and issues timely warnings to reduce the risk of sudden illness in the elderly. The elderly care space impact analysis module analyzes the environmental quality conditions of all elderly care living spaces to determine whether to generate a space warning signal and timely clean and regulate the environment of the corresponding elderly care living space to ensure cleanliness and comfort in the elderly care living space, significantly improve the reputation of elderly care services and facilitate the realization of healthy elderly care. The nursing scheduling optimization evaluation module determines the nursing scheduling optimization performance through analysis, and strengthens the scheduling supervision of nursing staff when a poor nursing scheduling optimization signal is generated, thereby reducing the risk of elderly care and ensuring the quality of nursing services. The intelligent level is high.

[0058] The preferred embodiments of the present invention disclosed above are used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. 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. The intelligent elderly care supervision system based on big data processing is characterized by: It includes intelligent monitoring and acquisition module, personnel status assessment and analysis module, elderly care space impact analysis module, nursing scheduling optimization assessment module and elderly care supervision terminal; the intelligent monitoring and acquisition module sends various physiological data and behavioral data of the elderly to the personnel status assessment and analysis module, and sends various environmental data of all elderly living spaces to the elderly care space impact analysis module; The personnel status assessment and analysis module receives various physiological data and behavioral data of the corresponding elderly. If there is physiological data or behavioral data that does not meet the corresponding preset requirements, it is judged that the corresponding elderly has health risks and generates a status alarm signal, and the status alarm signal is sent to the elderly care supervision end; The elderly care space impact analysis module analyzes the environmental quality of all elderly care living spaces, and determines whether to generate a space warning signal and send it to the elderly care supervision end; The nursing scheduling optimization evaluation module determines the nursing scheduling optimization performance through analysis, and sends the nursing scheduling optimization qualified signal or the nursing scheduling optimization poor signal to the elderly care supervision end.

2. The smart elderly care supervision system based on big data processing according to claim 1 is characterized in that: The specific analysis process of the elderly care space impact analysis module is as follows: obtaining the garbage and dirt distribution value in the corresponding elderly care living space, and obtaining the air quality detection value based on air quality detection analysis. If the garbage and dirt distribution value or the air quality detection value exceeds the corresponding preset threshold, a space warning signal for the corresponding elderly care living space is generated.

3. The smart elderly care supervision system based on big data processing according to claim 2 is characterized in that: The specific analysis process of air quality detection and analysis is as follows: obtain the environmental parameters that need to be monitored in the corresponding elderly living space. If the data of all environmental parameters that need to be monitored meet the corresponding requirements, the air quality detection value is set to zero; if there are environmental parameter data that do not meet the corresponding requirements, the corresponding environmental parameter is marked as an alarm parameter, and the deviation value of the corresponding alarm parameter data compared to the corresponding requirement is marked as an alarm level value; the product of the alarm level value of the corresponding alarm parameter and the corresponding preset weight value is marked as an alarm analysis value, and the sum of the alarm analysis values ​​of all alarm parameters is marked as the air quality detection value of the corresponding elderly living space.

4. The smart elderly care supervision system based on big data processing according to claim 1 is characterized in that: The specific analysis process of the nursing scheduling optimization evaluation module is as follows: assign corresponding preset proportional coefficients to the total frequency value of state alarms, the total frequency value of space warnings and the value of nursing personnel inspection, respectively, and multiply the total frequency value of state alarms, the total frequency value of space warnings and the value of nursing personnel inspection by the corresponding preset proportional coefficients to obtain the elderly care supervision coefficient; The real-time number of nursing staff on duty is collected and marked as nursing detection values. The mean of all nursing detection values ​​within the detection period is calculated to obtain the nursing scheduling value. The target threshold is obtained through nursing matching analysis. If the nursing scheduling value exceeds the target threshold, a nursing scheduling optimization qualified signal is generated; if the nursing scheduling value does not exceed the target threshold, a nursing scheduling optimization poor signal is generated.

5. The smart elderly care supervision system based on big data processing according to claim 4 is characterized in that: The specific analysis process of nursing matching analysis is: set several groups of preset elderly care supervision coefficient ranges in advance, and each group of preset elderly care supervision coefficient ranges corresponds to a group of preset nursing scheduling thresholds; mark the preset elderly care supervision coefficient ranges containing corresponding elderly care supervision coefficients as preferred ranges, and mark the preset nursing scheduling thresholds corresponding to the preferred ranges as target thresholds.

6. The smart elderly care supervision system based on big data processing according to claim 4 is characterized in that: The nursing scheduling optimization and evaluation module is communicatively connected to the nursing service tracing module. The nursing scheduling optimization and evaluation module sends the nursing scheduling optimization qualified signal to the nursing service tracing module. When the nursing service tracing module receives the nursing scheduling optimization qualified signal, it performs a nursing service tracing decision analysis, generates a nursing service non-optimal signal or a nursing service qualified signal through analysis, and sends the nursing service non-optimal signal or the nursing service qualified signal to the elderly care supervision end.

7. The smart elderly care supervision system based on big data processing according to claim 6 is characterized in that: The specific analysis process of nursing service traceability decision analysis is as follows: the number of complaints about nursing services during the detection period is collected and marked as the nursing complaint value, and the proportion of nursing staff who received complaints about nursing services during the detection period is marked as the complaint matching value. If the nursing complaint value or the complaint matching value exceeds the corresponding preset threshold, a non-optimal nursing service signal is generated.

8. The smart elderly care supervision system based on big data processing according to claim 7 is characterized in that: If the nursing complaint value and the complaint matching value do not exceed the corresponding preset threshold, the proportion of the number of optimization objects during the detection period is obtained and marked as the optimization proportion value. If the optimization proportion value exceeds the preset optimization proportion threshold, a non-optimal nursing service signal is generated.

9. The smart elderly care supervision system based on big data processing according to claim 8 is characterized in that: If the optimization share value does not exceed the preset optimization share threshold, the nursing service abnormality coefficient is calculated by weighted summing up the nursing complaint value, complaint matching value, optimization share value, nursing frequency value, nursing time value and nursing effectiveness inspection value. If the nursing service abnormality coefficient exceeds the preset nursing service abnormality coefficient threshold, a nursing service non-optimal signal is generated; if the nursing service abnormality coefficient does not exceed the preset nursing service abnormality coefficient threshold, a nursing service qualified signal is generated.

Images