Intelligent old-age care service management system based on big data

Abstract

The invention relates to the technical field of pension service management, and discloses a smart pension service management system based on big data, which comprises an intelligent equipment data acquisition module, an intelligent equipment use analysis module, an old people psychological state analysis module and an intelligent equipment compliance analysis module, and the intelligent equipment use analysis module comprises an intelligent equipment use analysis unit, a habit fluctuation evaluation unit, a cloud fluctuation analysis unit and a first early warning unit. According to the system, the living habit fluctuation condition of the elderly living alone and the use condition of each intelligent device in the home environment are comprehensively analyzed, and the duration of the intelligent device used by the current elderly is compared with the use duration of other people; according to the invention, whether the elderly is disordered in work and rest or the device is not turned off after being turned on is quickly reflected, the state of the elderly is analyzed in time, and when the elderly is abnormal, guardians can be informed in time.

Description

Technical Field

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

[0002] Smart elderly care is a model of elderly care that utilizes advanced information technology and intelligent equipment to meet the health, living, and safety needs of the elderly, providing a variety of services including health monitoring, smart home, social interaction, and security. By applying smart elderly care technology in elderly care centers, it is possible to monitor the health status of the elderly, intelligently manage their home life, and facilitate social activities, thereby improving the quality of life of the elderly and extending their ability to live independently and participate in society. Although comprehensive and unified smart management services can be provided to more elderly people through nursing homes, some elderly people living alone are not adapted to this collective living environment. Therefore, there are unique care services for elderly people living alone. Since the smart elderly care technologies used in existing nursing homes are not all used for elderly people living alone, it is not possible to provide feedback and management on the living conditions of elderly people living alone. Summary of the Invention

[0003] In response to the shortcomings of the existing technology, the present invention provides a smart elderly care service management system based on big data, which has the advantages of providing feedback management based on the living conditions of elderly people living alone, and solves the above technical problems.

[0004] To achieve the above objectives, the present invention provides the following technical solutions: a smart elderly care service management system based on big data, comprising: The smart device data collection module is used to collect the usage data of smart devices in the elderly’s home, build a smart device database, and upload it to the cloud database simultaneously; The smart device usage analysis module analyzes the current home appliance usage habits of the elderly based on the smart device database and constructs a habit fluctuation coefficient Then, we build an average fluctuation threshold based on the appliance usage habits of other elderly people in the cloud database. , when the habit fluctuation coefficient Exceeding the average volatility threshold The first warning signal is issued and the first warning strategy is implemented; The elderly psychological state analysis module is called after the first warning signal is issued. It analyzes the current psychological state of the elderly based on the smart device database and constructs a psychological state evaluation coefficient , and at the same time determine whether to issue an early warning. If an early warning is required, a second early warning signal is issued and a second early warning strategy is executed; The smart device compliance analysis module is called after the first warning signal is issued. It analyzes the compliance status of the smart devices currently used by the elderly based on the smart device database and constructs the i-th smart device compliance coefficient , and preset smart device compliance thresholds , when the smart device compliance coefficient Exceeding smart device compliance threshold The third warning signal is issued and the third warning strategy is implemented at the same time.

[0005] As a preferred technical solution of the present invention, the smart device usage analysis module includes a smart device usage analysis unit, a habit fluctuation assessment unit, a cloud fluctuation analysis unit and a first early warning unit; The smart device usage analysis unit analyzes the current home appliance usage habits of the elderly based on the smart device database, and constructs the living habit fluctuation coefficient in turn. and the current fluctuation coefficient of comprehensive use of home appliances by the elderly , the specific steps are as follows: Step A1: Read the electricity, gas and water consumption of the elderly in a sampling period t stored in the smart device database, and construct the living habit fluctuation coefficient , the specific expression is as follows: ; in, Indicates the historical average of the current electricity consumption of the elderly, obtained through the cloud database, represents the average power consumption within a sampling period t, Indicates the historical average of the current gas usage of the elderly, obtained through the cloud database, represents the average gas usage within a sampling period t, Indicates the historical average of the current water consumption of the elderly, obtained through the cloud database, represents the mean water consumption within a sampling period t, Indicates absolute value; Step A2: Construct the current fluctuation system of comprehensive use of home appliances for the elderly , the specific steps are as follows: Step A2.1: Read the usage time and time points of the i-th smart device by other elderly people in the cloud database, and match them to the 0-24 hour time axis to obtain several different coverage areas; Step A2.2: Based on the smart device database, read the usage duration and usage time of the i-th smart device in the current elderly home environment, and construct the usage fluctuation coefficient of the i-th smart device in the current elderly home environment , the specific expression is as follows: ; in, Indicates the usage time of the i-th smart device in the current elderly’s home environment, represents the average usage time of the i-th smart device, Indicates the total number of smart devices connected to the cloud database, Indicates the number of overlaps between the usage time point and usage duration of the i-th smart device in the elderly’s current home environment and the remaining coverage areas on the 0-24H time axis. represents the correction constant, and ; Step A2.3: Traverse the fluctuation coefficient of home appliance usage of each elderly person that has been uploaded to the cloud database, and construct the comprehensive fluctuation coefficient of home appliance usage of the elderly person. , the specific expression is as follows: ; in, Indicates the total number of home appliances that the elderly have uploaded to the cloud database. Indicates summation.

[0006] As a preferred technical solution of the present invention, the habit fluctuation evaluation unit is based on the living habit fluctuation coefficient and the current fluctuation coefficient of comprehensive use of home appliances by the elderly , comprehensively construct the habit fluctuation coefficient , the specific expression is as follows: ; in, represents the habit fluctuation coefficient.

[0007] As a preferred technical solution of the present invention, the cloud fluctuation analysis unit constructs an average fluctuation threshold based on the appliance usage habits of other elderly people in the cloud database. , the specific steps are as follows: Step B1: Read the habit fluctuation coefficient of the jth elderly person who received user intervention from the cloud database , and construct the remaining elderly fluctuation sets ; Step B2: Based on the remaining elderly fluctuation sets Get the mean of the habit fluctuation coefficient of the elderly who receive user intervention , the specific expression is as follows: ; in, Indicates the total number of elderly people who received user intervention, , Indicates summation, Represents the fluctuation set from the rest of the elderly The set after removing the maximum and minimum values; Step B3: Based on the remaining elderly fluctuation sets Eliminate the maximum and minimum values and Comprehensively construct the average fluctuation threshold , the specific expression is as follows: ; in, and Represent two different weight coefficients respectively, and their specific expressions are as follows: ; in, Represents the fluctuation set from the rest of the elderly The maximum value to be eliminated, Represents the fluctuation set from the rest of the elderly The minimum value to be eliminated, It represents the mean of the habit fluctuation coefficients of the remaining elderly people when they receive user intervention.

[0008] As the preferred technical solution of the present invention, the first early warning unit is used to the fluctuation coefficient Exceeding the average volatility threshold The first warning signal is issued when the first warning strategy specifically includes notifying the current elderly guardian, and the guardian chooses to upload whether the current elderly status is abnormal. If it is in an abnormal state, the current elderly habit fluctuation coefficient Set up a separate storage area and delete it when the abnormal state ends. At the same time, the current elderly person’s usage time and usage time of the i-th smart device will not be uploaded to the cloud database.

[0009] As a preferred technical solution of the present invention, the elderly psychological state analysis module includes a social state analysis unit, an emotion analysis unit, a psychological state assessment unit and a second early warning unit; The social status analysis unit is used to read the total call duration of the current elderly person in the smart device database and the call duration of the call association concentration set by the current elderly person's guardian, and construct the social influence fluctuation coefficient within the tth sampling period , the specific steps are: Read the total duration of the elderly person’s current call in the tth sampling period from the smart device database , and read the total length of calls between the current elderly person and the call-related personnel set by the current elderly person's guardian in the tth sampling period , and construct the social influence coefficient of the tth sampling period based on the ratio of the two , the social influence fluctuation coefficient is constructed by the following expression : ; in, Indicates the The social influence coefficient of the sampling period; The emotion analysis unit is based on the current elderly face image set obtained by the camera in the smart device database, and The emotion recognition model is used to obtain the corresponding duration of each facial emotion in the t-th sampling period, and to construct an emotion set. The emotion set includes four emotions: happy, sad, normal, and angry. Based on the emotion set, the emotion fluctuation coefficient of the t-th sampling period is constructed. , the specific steps are as follows: Step C1: Get the duration of each facial emotion in the emotion set, and sum it up to get the total duration of emotion sampling in the tth sampling period ; Step C2: Extract sadness and anger duration from the emotion set and compare them with the total emotion sampling duration in the t-th sampling period Calculate the sentiment ratio of the tth sampling period : ; in, Indicates the duration of sadness extracted from the emotion set in the t-th sampling period, Indicates the anger duration extracted from the emotion set in the t-th sampling period; Step C3: Based on the sentiment ratio of the tth sampling period Calculate the emotional fluctuation coefficient of the tth sampling period , the specific expression is as follows: ; in, Indicates the The sentiment ratio of each sampling period.

[0010] As a preferred technical solution of the present invention, the psychological state assessment unit is based on the social influence fluctuation coefficient obtained in t sampling periods. and the mood swing coefficient Constructing psychological state assessment coefficient , the specific expression is as follows: ; in, Represents two and The weight coefficient of .

[0011] As a preferred technical solution of the present invention, the second early warning unit receives the psychological state assessment coefficient Then make a judgment. The specific steps are: If the current mental state evaluation coefficient of the elderly The average value of the mental state assessment of the remaining elderly people from the cloud database within the t sampling period , then a second warning signal is issued, indicating that the mental state of the elderly person is not good in the t sampling period, and the second warning strategy is implemented, specifically: the current elderly person is marked. If the current elderly person is marked in n consecutive sampling periods, the corresponding guardian or community manager is notified; If the current mental state evaluation coefficient of the elderly Does not exceed the mean value of the psychological status assessment of the remaining elderly people from the cloud database during the t-th sampling period , the second warning signal will not be issued.

[0012] As a preferred technical solution of the present invention, the smart device compliance analysis module includes a smart device compliance evaluation unit and a third early warning unit; The smart device compliance evaluation unit analyzes the compliance status of the smart devices currently used by the elderly based on the smart device database and constructs the i-th smart device compliance coefficient , the body comprises the following steps: Step D1: Construct the device update compliance coefficient of the i-th smart device in the smart device database , the specific expression is as follows: ; in, Indicates the number of errors reported after the i-th smart device is updated. The update count of the i-th smart device is obtained from the update log of the i-th smart device in the smart device database; Step D2: Construct the maintenance compliance coefficient of the i-th smart device in the smart device database , the specific expression is as follows: ; in, Indicates the number of service interruptions of the i-th smart device, represents the number of times the i-th smart device has been repaired, Respectively represent and The weight coefficient of Step D3: Construct the compliance coefficient of the i-th smart device , the specific expression is as follows: ; in, represents the correction constant, and .

[0013] As a preferred technical solution of the present invention, the third warning unit is Exceeding smart device compliance threshold The third warning signal is issued and the third warning strategy is implemented at the same time, including: Get the usage percentage of the i-th smart device from the smart device database , when the usage ratio of the i-th smart device Match the set usage ratio and execute the corresponding strategy.

[0014] Compared with the existing technology, the present invention provides a smart elderly care service management system based on big data, which has the following beneficial effects: The present invention conducts a comprehensive analysis of the fluctuations in the living habits of elderly people living alone and the usage of various smart devices in the home environment. By comparing the duration of time the elderly person currently uses the smart device with the duration of use by other people, it can quickly reflect whether the elderly person currently has a disordered work and rest schedule or does not turn off the device after turning it on, thereby being able to timely analyze the elderly person's condition and promptly inform the guardian when the elderly person shows any abnormality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0017] See also Figure 1 , a smart elderly care service management system based on big data, including: The smart device data collection module is used to collect the usage data of smart devices in the elderly’s home, build a smart device database, and upload it to the cloud database simultaneously; The smart device usage analysis module analyzes the current home appliance usage habits of the elderly based on the smart device database and constructs a habit fluctuation coefficient Then, we build an average fluctuation threshold based on the appliance usage habits of other elderly people in the cloud database. , when the habit fluctuation coefficient Exceeding the average volatility threshold The first warning signal is issued and the first warning strategy is implemented; The smart device usage analysis module includes a smart device usage analysis unit, a habit fluctuation assessment unit, a cloud fluctuation analysis unit, and a first warning unit; The smart device usage analysis unit analyzes the current home appliance usage habits of the elderly based on the smart device database, and constructs the lifestyle fluctuation coefficient in turn. and the current fluctuation coefficient of comprehensive use of home appliances by the elderly , the specific steps are as follows: Step A1: Read the electricity, gas and water consumption of the elderly in a sampling period t stored in the smart device database, and construct the living habit fluctuation coefficient , the specific expression is as follows: ; in, Indicates the historical average of the current electricity consumption of the elderly, obtained through the cloud database, represents the average power consumption within a sampling period t, Indicates the historical average of the current gas usage of the elderly, obtained through the cloud database, represents the average gas usage within a sampling period t, Indicates the historical average of the current water consumption of the elderly, obtained through the cloud database, represents the mean water consumption within a sampling period t, Indicates the absolute value. By calculating and analyzing the current usage of the parameters necessary for the elderly's life, the current living conditions of the elderly can be reflected more quickly. When the indicator fluctuates greatly, it will affect the overall habit fluctuation coefficient. Produce an impact, thereby reaching the triggering warning conditions; Step A2: Construct the current fluctuation coefficient of comprehensive use of home appliances for the elderly , the specific steps are as follows: Step A2.1: Read the usage time and time points of the i-th smart device by other elderly people in the cloud database, and match them to the 0-24 hour time axis to obtain several different coverage areas; For example, the i-th smart device is a smart TV, and its usage time coverage is as shown in Table 1 below: Table 1 Smart TV usage time coverage

[0018] The data recorded in this table is authorized by the user and only the usage time is stored; Step A2.2: Based on the smart device database, read the usage duration and usage time of the i-th smart device in the current elderly home environment, and construct the usage fluctuation coefficient of the i-th smart device in the current elderly home environment , the specific expression is as follows: ; in, Indicates the usage time (hours) of i smart devices in the elderly’s current home environment. represents the average usage time of the i-th smart device, Indicates the total number of smart devices connected to the cloud database, Indicates the number of overlaps between the usage time point and usage duration of the i-th smart device in the elderly’s current home environment and the remaining coverage areas on the 0-24H time axis. represents the correction constant, and By comparing the duration of time the elderly currently use their smart devices with that of other people, it is possible to quickly determine whether the elderly currently have irregular work and rest schedules or do not turn off the devices after turning them on, thereby enabling timely analysis of the elderly’s status. If the elderly’s current usage habits are more consistent with those of other elderly people, it will lead to The lower the value of If the elderly only use the smart device briefly, The item can reduce the impact of this short-term use; Step A2.3: Traverse the fluctuation coefficient of home appliance usage of each elderly person that has been uploaded to the cloud database, and construct the comprehensive fluctuation coefficient of home appliance usage of the elderly person. , the specific expression is as follows: ; in, Indicates the total number of home appliances that the elderly have uploaded to the cloud database. It represents the sum. By analyzing the usage of all smart appliances, we can clearly see the changes in the overall life of the elderly, rather than focusing on a certain situation. When the overall abnormality occurs, it will be reflected in the habit fluctuation coefficient. .

[0019] Habit Fluctuation Assessment Unit is based on the Life Habit Fluctuation Coefficient and the current fluctuation coefficient of comprehensive use of home appliances by the elderly , comprehensively construct the habit fluctuation coefficient , the specific expression is as follows: ; in, It represents the habit fluctuation coefficient. By comprehensively considering the fluctuations in living habits and electrical usage, it can reflect the fluctuations in the elderly's work and rest in the short term. When the fluctuations in the elderly's work and rest are large, an early warning will be issued to remind guardians or managers to visit.

[0020] The cloud fluctuation analysis unit constructs an average fluctuation threshold based on the appliance usage habits of other elderly people in the cloud database. , the specific steps are as follows: Step B1: Read the habit fluctuation coefficient of the jth elderly person who received user intervention from the cloud database , and construct the remaining elderly fluctuation sets ; Step B2: Based on the remaining elderly fluctuation sets Get the mean of the habit fluctuation coefficient of the elderly who receive user intervention , the specific expression is as follows: ; in, Indicates the total number of elderly people who received user intervention, , Indicates summation, Represents the fluctuation set from the rest of the elderly The set after removing the maximum and minimum values can effectively reflect the current average situation by removing the maximum and minimum values in the fluctuation set. The user intervention here refers to the active reporting of the elderly by the guardian or manager when he or she actively detects the abnormal state of the elderly. ; Step B3: Based on the remaining elderly fluctuation sets Eliminate the maximum and minimum values and Comprehensively construct the average fluctuation threshold , combining the maximum and minimum values and their corresponding weights, the final average fluctuation threshold can be coupled more accurately , the specific expression is as follows: ; in, and Represent two different weight coefficients respectively, and their specific expressions are as follows: ; in, Represents the fluctuation set from the rest of the elderly The maximum value to be eliminated, Represents the fluctuation set from the rest of the elderly The minimum value to be eliminated, It represents the mean of the habit fluctuation coefficients of the remaining elderly people when they receive user intervention.

[0021] The first warning unit is in the habit of fluctuation coefficient Exceeding the average volatility threshold The first warning signal is issued when the first warning strategy specifically includes notifying the current elderly guardian, and the guardian chooses to upload whether the current elderly status is abnormal. If it is in an abnormal state, the current elderly habit fluctuation coefficient A separate storage area is set up and deleted when the abnormal state ends. At the same time, the current elderly person's usage time and usage time of the i-th smart device are not uploaded to the cloud database. The abnormal states include: illness, forgetting to turn off the smart device after turning it on, etc.

[0022] The elderly psychological state analysis module is called after the first warning signal is issued. It analyzes the current psychological state of the elderly based on the smart device database and constructs a psychological state evaluation coefficient , and at the same time determine whether to issue an early warning. If an early warning is required, a second early warning signal is issued and a second early warning strategy is executed; The elderly psychological state analysis module includes a social state analysis unit, an emotion analysis unit, a psychological state assessment unit, and a second early warning unit; The social status analysis unit is used to read the total call duration of the current elderly person and the call association concentration call duration set by the current elderly person's guardian in the smart device database, and construct the social influence fluctuation coefficient within the t-th sampling period , the specific steps are: Read the total duration of the elderly person’s current call in the tth sampling period from the smart device database , and read the total length of calls between the current elderly person and the call-related personnel set by the current elderly person's guardian in the tth sampling period , and construct the social influence coefficient of the tth sampling period based on the ratio of the two , the social influence fluctuation coefficient is constructed by the following expression : ; in, Indicates the The social influence coefficient of each sampling period. Since the social circle of elderly people who live alone and need care is relatively small, dividing and extracting the call duration of the elderly’s common contacts can effectively reflect the current social situation of the elderly in a sampling period. The call association set stores each contact name and the corresponding phone number, and performs matching when reading the call records, such as the following Table 2: Table 2 Contact call association table

[0023] The duration of the call at this time , ; The emotion analysis unit is based on the current elderly face image set obtained by the camera in the smart device database, and The emotion recognition model (this model is an existing model, and those skilled in the art should know how to build it, so I will not elaborate on it here) is used to obtain the corresponding duration of each facial emotion in the t-th sampling period, and to construct an emotion set. The emotion set includes four emotions: happy, sad, normal, and angry. Based on the emotion set, the emotion fluctuation coefficient of the t-th sampling period is constructed. , the specific steps are as follows: Step C1: Get the duration of each facial emotion in the emotion set, and sum it up to get the total duration of emotion sampling in the tth sampling period ; Step C2: Extract sadness and anger duration from the emotion set and compare them with the total emotion sampling duration in the t-th sampling period Calculate the sentiment ratio of the tth sampling period : ; in, Indicates the duration of sadness extracted from the emotion set in the t-th sampling period, Indicates the anger duration extracted from the emotion set in the t-th sampling period; Step C3: Based on the sentiment ratio of the tth sampling period Calculate the emotional fluctuation coefficient of the tth sampling period , the specific expression is as follows: ; in, Indicates the The sentiment ratio of each sampling period.

[0024] The social influence fluctuation coefficient obtained by the psychological state assessment unit based on the t-th sampling period and the mood swing coefficient Constructing psychological state assessment coefficient , the specific expression is as follows: ; in, Represents two and The weight coefficient of .

[0025] The second warning unit receives the psychological state assessment coefficient Then make a judgment. The specific steps are: If the current mental state evaluation coefficient of the elderly The average value of the mental state assessment of the remaining elderly people from the cloud database within the t sampling period , then a second warning signal is issued, indicating that the mental state of the elderly person in the tth sampling period is not good, and the second warning strategy is implemented, specifically: the current elderly person is marked. If the current elderly person is marked within n consecutive sampling periods, the corresponding guardian or community manager is notified; If the current mental state evaluation coefficient of the elderly Does not exceed the mean value of the psychological status assessment of the remaining elderly people from the cloud database during the t-th sampling period , the second warning signal will not be issued.

[0026] The smart device compliance analysis module is called after the first warning signal is issued. It analyzes the compliance status of the smart devices currently used by the elderly based on the smart device database and constructs the i-th smart device compliance coefficient , and preset smart device compliance thresholds , when the smart device compliance coefficient Exceeding smart device compliance threshold The third warning signal is issued and the third warning strategy is implemented at the same time.

[0027] The smart device compliance analysis module includes a smart device compliance assessment unit and a third early warning unit; The smart device compliance evaluation unit analyzes the compliance status of the smart devices currently used by the elderly based on the smart device database and constructs the i-th smart device compliance coefficient , specifically including the following steps: Step D1: Construct the device update compliance coefficient of the i-th smart device in the smart device database , the specific expression is as follows: ; in, Shows the number of errors reported after the i-th smart device is updated, Indicates the update times of the i-th smart device. No calculation is performed before the update. , are obtained from the update log of the i-th smart device in the smart device database. Since it is difficult for elderly people living alone to repair smart devices, the more errors a device reports after updating, the more problems it has with the current device and the more it needs to remind the guardian. Step D2: Construct the maintenance compliance coefficient of the i-th smart device in the smart device database , the specific expression is as follows: ; in, Indicates the number of service interruptions of the i-th smart device. The number of service interruptions can reflect the maintenance needs of the current device. represents the number of maintenance times of the i-th smart device, Respectively represent and The weight coefficient of Step D3: Construct the compliance coefficient of the i-th smart device , the specific expression is as follows: ; in, represents the correction constant, and .

[0028] The third warning unit is when the compliance coefficient of the i-th smart device Exceeding smart device compliance threshold The third warning signal is issued and the third warning strategy is implemented at the same time, including: Get the usage percentage of the i-th smart device from the smart device database , the usage ratio of the i-th smart device Match the set usage percentage and execute the corresponding strategy; Among them, the usage ratio of the i-th smart device is The specific expression is: , Indicates the total number of times the smart device is used. Indicates the usage frequency of the i-th smart device. When the third warning signal is issued, the usage ratio set is read, see Table 3 below: Table 3 Warning strategy table for the usage ratio of smart devices

[0029] Example: In this embodiment, the specific data of the current elderly home appliance usage habits within a sampling period t is recorded in Table 4 below: Table 4 Current usage habits of home appliances by the elderly

[0030] ,From this we can see that there are some differences between the living habits of the elderly in the current sampling period t and the historical average usage habits; Construct the current fluctuation coefficient of comprehensive use of home appliances for the elderly See Table 5 below: Table 5 Current fluctuations in the use of home appliances by the elderly

[0031] At this time, the calculation ; The remaining elderly fluctuation sets in the cloud fluctuation analysis unit See Table 6 below: Table 6 Fluctuations of other elderly people in the cloud fluctuation analysis unit

[0032] ; Now calculate , Exceeding the average volatility threshold Notify the current elderly guardian. When the guardian confirms that the elderly is in an abnormal state, the current elderly habit fluctuation coefficient Set up a separate storage area and delete it when the supervisor confirms that the abnormal state has ended; The data involved in the social status analysis unit are shown in Table 7 below: Table 7 Data involved in social status analysis unit

[0033] , then we can calculate At this time, the current elderly Secondary marking: if the current elderly person is marked within n consecutive sampling periods, the corresponding guardian or community management personnel will be notified; The data involved in the smart device compliance analysis module is shown in Table 8 below: Table 8 Data involved in the smart device compliance analysis module

[0034] at this time, Exceeding smart device compliance threshold , no third warning signal is issued; The above embodiments only provide one or more feasible solutions, which do not represent the optimal solutions. The amount and size of data recorded in the embodiments are only for the convenience of technical personnel in this field to understand the technical solutions, and do not mean that this solution only uses the data recorded in the above embodiments in actual applications. The setting of the threshold value is for the convenience of comparison. The size of the threshold value depends on the amount of sample data and the number of bases set by technical personnel in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameters and the quantized values, and the size of the weight can be determined by technical personnel in this field based on each sample data and multiple rounds of experimental processes, the above formulas are all calculated by removing the dimensions and taking their numerical values.

[0035] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A smart elderly care service management system based on big data, characterized by: include: The smart device data collection module is used to collect the usage data of smart devices in the elderly’s home, build a smart device database, and upload it to the cloud database simultaneously; The smart device usage analysis module analyzes the current home appliance usage habits of the elderly based on the smart device database and constructs a habit fluctuation coefficient Then, we build an average fluctuation threshold based on the appliance usage habits of other elderly people in the cloud database. , when the habit fluctuation coefficient Exceeding the average volatility threshold The first warning signal is issued and the first warning strategy is implemented; The elderly psychological state analysis module is called after the first warning signal is issued. It analyzes the current psychological state of the elderly based on the smart device database and constructs a psychological state evaluation coefficient , and at the same time determine whether to issue an early warning. If an early warning is required, a second early warning signal is issued and a second early warning strategy is executed; The smart device compliance analysis module is called after the first warning signal is issued. It analyzes the compliance status of the smart devices currently used by the elderly based on the smart device database and constructs the i-th smart device compliance coefficient , and preset smart device compliance thresholds , when the smart device compliance coefficient Exceeding smart device compliance threshold The third warning signal is issued and the third warning strategy is implemented at the same time.

2. The big data-based smart elderly care service management system according to claim 1 is characterized by: The smart device usage analysis module includes a smart device usage analysis unit, a habit fluctuation assessment unit, a cloud fluctuation analysis unit and a first early warning unit; The smart device usage analysis unit analyzes the current home appliance usage habits of the elderly based on the smart device database, and constructs the living habit fluctuation coefficient in turn. and the current fluctuation coefficient of comprehensive use of home appliances by the elderly , the specific steps are as follows: Step A1: Read the electricity, gas and water consumption of the elderly in a sampling period t stored in the smart device database, and construct the living habit fluctuation coefficient , the specific expression is as follows: ; in, Indicates the historical average of the current electricity consumption of the elderly, obtained through the cloud database, represents the average power consumption within a sampling period t, Indicates the historical average of the current gas usage of the elderly, obtained through the cloud database, represents the average gas usage within a sampling period t, Indicates the historical average of the current water consumption of the elderly, obtained through the cloud database, represents the mean water consumption within a sampling period t, Indicates absolute value; Step A2: Construct the current fluctuation coefficient of comprehensive use of home appliances for the elderly , the specific steps are as follows: Step A2.1: Read the usage time and time points of the i-th smart device by other elderly people in the cloud database, and match them to the 0-24 hour time axis to obtain several different coverage areas; Step A2.2: Based on the smart device database, read the usage duration and usage time of the i-th smart device in the current elderly home environment, and construct the usage fluctuation coefficient of the i-th smart device in the current elderly home environment , the specific expression is as follows: ; in, Indicates the usage time of the i-th smart device in the current elderly’s home environment, represents the average usage time of the i-th smart device, Indicates the total number of smart devices connected to the cloud database, Indicates the number of overlaps between the usage time point and usage duration of the i-th smart device in the elderly’s current home environment and the remaining coverage areas on the 0-24H time axis. represents the correction constant, and ; Step A2.3: Traverse the fluctuation coefficient of home appliance usage of each elderly person that has been uploaded to the cloud database, and construct the comprehensive fluctuation coefficient of home appliance usage of the elderly person. , the specific expression is as follows: ; in, Indicates the total number of home appliances that the elderly have uploaded to the cloud database. Indicates summation.

3. The big data-based smart elderly care service management system according to claim 2 is characterized by: The habit fluctuation evaluation unit is based on the life habit fluctuation coefficient and the current fluctuation coefficient of comprehensive use of home appliances by the elderly , comprehensively construct the habit fluctuation coefficient , the specific expression is as follows: ; in, represents the habit fluctuation coefficient.

4. The big data-based smart elderly care service management system according to claim 2, characterized in that: The cloud fluctuation analysis unit constructs an average fluctuation threshold based on the appliance usage habits of other elderly people in the cloud database. , the specific steps are as follows: Step B1: Read the habit fluctuation coefficient of the jth elderly person who received user intervention from the cloud database , and construct the remaining elderly fluctuation sets ; Step B2: Based on the remaining elderly fluctuation sets Get the mean of the habit fluctuation coefficient of the elderly who receive user intervention , the specific expression is as follows: ; in, Indicates the total number of elderly people who received user intervention, , Indicates summation, Represents the fluctuation set from the rest of the elderly The set after removing the maximum and minimum values; Step B3: Based on the remaining elderly fluctuation sets Eliminate the maximum and minimum values and Comprehensively construct the average fluctuation threshold , the specific expression is as follows: ; in, and Represent two different weight coefficients respectively, and their specific expressions are as follows: ; in, Represents the fluctuation set from the rest of the elderly The maximum value to be eliminated, Represents the fluctuation set from the rest of the elderly The minimum value to be eliminated, It represents the mean of the habit fluctuation coefficients of the remaining elderly people when they receive user intervention.

5. The big data-based smart elderly care service management system according to claim 2 is characterized by: The first early warning unit is used to the fluctuation coefficient Exceeding the average volatility threshold The first warning signal is issued when the first warning strategy specifically includes notifying the current elderly guardian, and the guardian chooses to upload whether the current elderly status is abnormal. If it is in an abnormal state, the current elderly habit fluctuation coefficient Set up a separate storage area and delete it when the abnormal state ends. At the same time, the current elderly person’s usage time and usage time of the i-th smart device will not be uploaded to the cloud database.

6. The big data-based smart elderly care service management system according to claim 1, characterized in that: The elderly psychological state analysis module includes a social state analysis unit, an emotion analysis unit, a psychological state assessment unit and a second early warning unit; The social status analysis unit is used to read the total call duration of the current elderly person in the smart device database and the call duration of the call association concentration set by the current elderly person's guardian, and construct the social influence fluctuation coefficient within the tth sampling period , the specific steps are: Read the total duration of the elderly person’s current call in the tth sampling period from the smart device database , and read the total length of calls between the current elderly person and the call-related personnel set by the current elderly person's guardian in the tth sampling period , and construct the social influence coefficient of the tth sampling period based on the ratio of the two , the social influence fluctuation coefficient is constructed by the following expression : ; ; in, Indicates the The social influence coefficient of the sampling period; The emotion analysis unit is based on the current elderly face image set obtained by the camera in the smart device database, and The emotion recognition model is used to obtain the corresponding duration of each facial emotion in the t-th sampling period, and to construct an emotion set. The emotion set includes four emotions: happy, sad, normal, and angry. Based on the emotion set, the emotion fluctuation coefficient of the t-th sampling period is constructed. , the specific steps are as follows: Step C1: Get the duration of each facial emotion in the emotion set, and sum it up to get the total duration of emotion sampling in the tth sampling period ; Step C2: Extract sadness and anger duration from the emotion set and compare them with the The total duration of emotion sampling in each sampling period Calculate the sentiment ratio of the tth sampling period : ; in, Indicates the duration of sadness extracted from the emotion set in the t-th sampling period, Indicates the anger duration extracted from the emotion set in the t-th sampling period; Step C3: Based on the sentiment ratio of the tth sampling period Calculate the emotional fluctuation coefficient of the tth sampling period , the specific expression is as follows: ; in, Indicates the The sentiment ratio of each sampling period.

7. The big data-based smart elderly care service management system according to claim 6, characterized in that: The psychological state evaluation unit is based on the social influence fluctuation coefficient obtained in the t-th sampling period and the mood swing coefficient Constructing psychological state assessment coefficient , the specific expression is as follows: ; in, They represent two weight coefficients whose sum is 1.

8. The big data-based smart elderly care service management system according to claim 7 is characterized by: The second early warning unit receives the psychological state assessment coefficient Then make a judgment. The specific steps are: If the current mental state evaluation coefficient of the elderly The average value of the mental state assessment of the remaining elderly people from the cloud database within the t sampling period , then a second warning signal is issued, indicating that the mental state of the elderly person in the tth sampling period is not good, and the second warning strategy is implemented, specifically: the current elderly person is marked. If the current elderly person is marked within n consecutive sampling periods, the corresponding guardian or community management personnel is notified; If the current mental state evaluation coefficient of the elderly Does not exceed the mean value of the mental state assessment of the remaining elderly people from the cloud database during the t sampling period , then no second warning signal will be issued.

9. The big data-based smart elderly care service management system according to claim 1, characterized in that: The smart device compliance analysis module includes a smart device compliance evaluation unit and a third early warning unit; The smart device compliance evaluation unit analyzes the compliance status of the smart devices currently used by the elderly based on the smart device database and constructs the i-th smart device compliance coefficient , specifically including the following steps: Step D1: Construct the device update compliance coefficient of the i-th smart device in the smart device database , the specific expression is as follows: ; in, Indicates the number of errors reported after the i-th smart device is updated. The update count of the i-th smart device is obtained from the update log of the i-th smart device in the smart device database; Step D2: Construct the maintenance compliance coefficient of the i-th smart device in the smart device database , the specific expression is as follows: ; in, Indicates the number of service interruptions of the i-th smart device, represents the number of maintenance times of the i-th smart device, They represent weight coefficients that sum to 1 respectively; Step D3: Construct the compliance coefficient of the i-th smart device , the specific expression is as follows: ; in, represents the correction constant, and .

10. The big data-based smart elderly care service management system according to claim 9, characterized in that: The third early warning unit is when the compliance coefficient of the i-th smart device Exceeding smart device compliance threshold The third warning signal is issued and the third warning strategy is implemented at the same time, including: Get the usage percentage of the i-th smart device from the smart device database , when the usage ratio of the i-th smart device Match the set usage ratio and execute the corresponding strategy.

Images