An intelligent old-age service management system based on big data

Abstract

The application relates to the technical field of old-age service management, and discloses a smart old-age service management system based on big data, which comprises an intelligent device data acquisition module, an intelligent device use analysis module, an old person psychological state analysis module and an intelligent device compliance analysis module; the intelligent device use analysis module comprises an intelligent device use analysis unit, a habit fluctuation evaluation unit, a cloud fluctuation analysis unit and a first early warning unit. The system comprehensively analyzes the habit fluctuation of the old person living alone and the use of various intelligent devices in the home environment, compares the use time of the intelligent device used by the old person with the use time of the intelligent device used by other people, quickly reflects whether the old person has work and rest disorder or has not turned off the device after turning it on, analyzes the state of the old person in a timely manner, and timely informs the guardian when the old person has an abnormality.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pension service management, in particular to a smart pension service management system based on big data. BACKGROUND

[0002] Smart pension is a pension mode that uses advanced information technology and intelligent equipment to meet the health, life and safety needs of the elderly as the core, and provides services including health monitoring, smart home, social interaction, safety protection and other aspects. Through the application of smart pension technology in the pension center, the health status of the elderly can be monitored, the intelligent management of home life can be realized, and social activities can be conveniently carried out, so as to improve the quality of life of the elderly and prolong their self-care ability and social participation.

[0003] Although the comprehensive and unified smart management service of many old people can be realized through the pension center, some solitary old people are not suitable for such a collective living environment, so there is a unique care service for solitary old people. Since the existing smart pension technology applied in the pension center is not used on all solitary old people, it cannot feedback and manage the living conditions of solitary old people. SUMMARY

[0004] In view of the defects of the prior art, the present application provides a smart pension service management system based on big data, which has the advantages of feedback management for the living conditions of solitary old people, and solves the above technical problems.

[0005] To achieve the above purpose, the present application provides the following technical scheme: a smart pension service management system based on big data, comprising:

[0006] An intelligent device data acquisition module is used to acquire the use data of the intelligent devices in the current old people's home, and to build an intelligent device database, and to synchronize uploading to the cloud database;

[0007] An intelligent device use analysis module is used to analyze the use habits of the current old people's home appliances based on the intelligent device database, and to build a habit fluctuation coefficient , and then to build an average fluctuation threshold based on the use habits of the rest of the old people in the cloud database When the habit fluctuation coefficient exceeds the average fluctuation threshold , a first warning signal is sent out, and a first warning strategy is executed;

[0008] An old people's psychological state analysis module is called after the first warning signal is sent out, and is used to analyze the psychological state of the current old people based on the intelligent device database, and to build a psychological state evaluation coefficientMeanwhile, it is judged whether to give a warning, if a warning is needed, a second warning signal is sent, and a second warning strategy is executed;

[0009] The intelligent device compliance analysis module is called after the first warning signal is sent, the compliance state of the intelligent device used by the current old person is analyzed based on the intelligent device database, and the i-th intelligent device compliance coefficient is constructed Meanwhile, an intelligent device compliance threshold is preset When the intelligent device compliance coefficient Exceeds the intelligent device compliance threshold , a third warning signal is sent, and a third warning strategy is executed.

[0010] As a preferred technical solution of the present application, the intelligent device use analysis module comprises an intelligent device use analysis unit, a habit fluctuation evaluation unit, a cloud fluctuation analysis unit and a first warning unit;

[0011] The intelligent device use analysis unit analyzes the use habits of the current old person's home appliances based on the intelligent device database, and sequentially constructs a living habit fluctuation coefficient And a current old person's home appliance comprehensive use fluctuation coefficient The specific steps are as follows:

[0012] Step A1: read the current old person's electricity consumption, gas consumption and water consumption in a sampling period t stored in the intelligent device database, and construct a living habit fluctuation coefficient The specific expression is as follows: ;

[0013] Among them, Indicates the current old person's electricity consumption history average, which is obtained through the cloud database, Indicates the average electricity consumption in a sampling period t, Indicates the current old person's gas consumption history average, which is obtained through the cloud database, Indicates the average gas consumption in a sampling period t, Indicates the current old person's water consumption history average, which is obtained through the cloud database, Indicates the average water consumption in a sampling period t, Indicates the absolute value;

[0014] Step A2: construct a current old person's home appliance comprehensive use fluctuation coefficient The specific steps are as follows:

[0015] Step A2.1: read the use time and use time point of the i-th intelligent device by the rest of the old people in the cloud database, and match to the 0~24H time axis to obtain several different coverage areas;

[0016] Step A2.2: Based on the smart device database, read the use duration and use time point of the i-th smart device in the current old person's home environment, and construct the use fluctuation coefficient of the i-th smart device in the current old person's home environment , the specific expression is as follows: ;

[0017] Among them, represents the use duration of the i-th smart device in the current old person's home environment, represents the average use duration of the i-th smart device, represents the total number of the i-th smart device connected to the cloud database, represents the number of coincidences of the use time point of the i-th smart device in the current old person's home environment and the use duration of the i-th smart device with the rest of the covered area on the 0~24H time axis, represents a correction coefficient, and ;

[0018] Step A2.3: Traverse the use fluctuation coefficient of each home appliance of the current old person uploaded to the cloud database in turn, and construct the comprehensive use fluctuation coefficient of the current old person's home appliances , the specific expression is as follows: ;

[0019] Among them, represents the total number of home appliances of the current old person uploaded to the cloud database, represents the sum.

[0020] As a preferred technical solution of the present application, the habit fluctuation assessment unit is based on the life habit fluctuation coefficient and the comprehensive use fluctuation coefficient of the current old person's home appliances , and constructs the habit fluctuation coefficient , the specific expression is as follows: ;

[0021] Among them, represents the habit fluctuation coefficient.

[0022] As a preferred technical solution of the present application, the cloud fluctuation analysis unit constructs the average fluctuation threshold based on the use habits of the rest of the old people in the cloud database, and the specific steps are as follows:

[0023] Step B1: Read the habit fluctuation coefficient of the j-th old person receiving user intervention in the cloud database , and construct the rest of the old people fluctuation set ;

[0024] Step B2: based on the remaining old people fluctuation set Obtain the mean value of the habit fluctuation coefficient of the old people receiving user intervention , the specific expression is as follows: ;

[0025] Wherein, represents the total number of old people receiving user intervention, , represents the summation, represents the set after removing the maximum value and the minimum value from the remaining old people fluctuation set ;

[0026] Step B3: based on the remaining old people fluctuation set remove the maximum value and the minimum value and integrated to build an average fluctuation threshold , the specific expression is as follows: ;

[0027] Wherein, and respectively represent two different weight coefficients, and the specific expression is as follows: ;

[0028] Wherein, represents the maximum value removed from the remaining old people fluctuation set , represents the minimum value removed from the remaining old people fluctuation set , represents the mean value of the habit fluctuation coefficient of the remaining old people when receiving user intervention.

[0029] As a preferred technical solution of the present application, the first early warning unit issues a first early warning signal when the habit fluctuation coefficient exceeds the average fluctuation threshold , and the first early warning strategy specifically includes notifying the current old people guardian, and the guardian selects whether to upload the current old people state is abnormal, if it is in an abnormal state, the habit fluctuation coefficient of the current old people is set in a separate storage area, and is deleted when the abnormal state is terminated, and at the same time, the current old people's use time length and use time point of the i-th intelligent device are not uploaded to the cloud database.

[0030] As a preferred technical solution of the present application, the old people psychological state analysis module includes a social state analysis unit, an emotion analysis unit, a psychological state evaluation unit and a second early warning unit;

[0031] The social status analysis unit is used to read the total call duration of the current elderly person and the call duration of the call association set by the current caregiver in the smart device database, and to construct the social influence fluctuation coefficient within the t-th sampling period. The specific steps are as follows:

[0032] Retrieve the total call duration of the elderly person during the t-th sampling period from the smart device database. And read the total call duration of the current elderly person and the current elderly person's guardian set in the call association set during the t-th sampling period. And construct the social influence coefficient for the t-th sampling period based on the ratio of the two. The social impact fluctuation coefficient is constructed using the following expression. : ;

[0033] in, Indicates the first Social impact coefficient for each sampling period;

[0034] The emotion analysis unit is based on a set of current facial images of the elderly obtained from cameras in the smart device's database, and through... An emotion recognition model is used to obtain the duration of each facial emotion within the t-th sampling period, constructing an emotion set that includes four emotions: happiness, sadness, normal, and anger. Based on this emotion set, an emotion fluctuation coefficient for the t-th sampling period is constructed. The specific steps are as follows:

[0035] Step C1: Obtain the duration corresponding to each facial emotion in the emotion set, and sum them to obtain the total duration of emotion sampling in the t-th sampling period. ;

[0036] Step C2: Extract the durations of sadness and anger from the emotion set and combine them with the total duration of emotion sampling in the t-th sampling period. The percentage of emotions in the t-th sampling period is calculated. : ;

[0037] in, This indicates that the duration of sadness is extracted from the emotion set during the t-th sampling period. This indicates that the duration of anger is extracted from the emotion set during the t-th sampling period;

[0038] Step C3: Based on the sentiment percentage in the t-th sampling period The emotional fluctuation coefficient for the t-th sampling period was calculated. The specific expression is as follows: ;

[0039] in, indicates the emotion proportion of the t th sampling period.

[0040] As a preferred technical solution of the present application, the psychological state evaluation unit constructs a psychological state evaluation coefficient based on the social influence fluctuation coefficient and the emotion fluctuation coefficient obtained in the t sampling periods, and the specific expression is as follows: ;

[0041] wherein, respectively represent two weight coefficients whose sum is .

[0042] As a preferred technical solution of the present application, the second early warning unit judges after receiving the psychological state evaluation coefficient , and the specific steps are as follows:

[0043] If the psychological state evaluation coefficient of the current old person exceeds the mean value of the psychological state evaluation of the rest of the old people in the t sampling period from the cloud database , a second early warning signal is sent out, indicating that the psychological state of the current old person in the t sampling period is not good, and a second early warning strategy is executed, specifically: the current old person is marked, and if the current old person is marked in the continuous n sampling periods, the corresponding guardian or community manager is notified;

[0044] If the psychological state evaluation coefficient of the current old person does not exceed the mean value of the psychological state evaluation of the rest of the old people in the t sampling period from the cloud database , no second early warning signal is sent out.

[0045] As a preferred technical solution of the present application, the intelligent device compliance analysis module includes an intelligent device compliance evaluation unit and a third early warning unit.

[0046] The intelligent device compliance evaluation unit analyzes the compliance state of the intelligent device used by the current old person based on the intelligent device database, and constructs the i th intelligent device compliance coefficient , which includes the following steps:

[0047] Step D1: Constructing the device update compliance coefficient of the i th intelligent device in the intelligent device database, and the specific expression is as follows: ;

[0048] wherein, represents the number of times of updating the i-th intelligent device, and is obtained from the update log of the i-th intelligent device in the intelligent device database;

[0049] Step D2: constructing the maintenance compliance coefficient of the i-th intelligent device in the intelligent device database , and the specific expression is as follows: ;

[0050] wherein, represents the number of times of service interruption of the i-th intelligent device, represents the number of times of maintenance of the i-th intelligent device, respectively represent the weight coefficients of and .

[0051] Step D3: constructing the compliance coefficient of the i-th intelligent device , and the specific expression is as follows: ;

[0052] wherein, represents a correction number, and .

[0053] As a preferred technical scheme of the present application, when the compliance coefficient of the i-th intelligent device exceeds the intelligent device compliance threshold , the third warning signal is sent by the third warning unit, and the third warning strategy is executed, which specifically includes:

[0054] obtaining the use proportion of the i-th intelligent device from the intelligent device database , and when the use proportion of the i-th intelligent device matches the set use proportion set, the corresponding strategy is executed.

[0055] Compared with the prior art, the present application provides a smart pension service management system based on big data, which has the following beneficial effects:

[0056] The present application comprehensively analyzes the life habit fluctuation of the elderly living alone and the use of each intelligent device in the home environment, and compares the use time of the intelligent device by the current elderly with the use time of the rest of the personnel, which can quickly respond to whether the current elderly has irregular work and rest or has not turned off the device after turning it on, so as to analyze the state of the elderly in time, and inform the guardian in time when the elderly is abnormal. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 The present application is a system framework schematic diagram. DETAILED DESCRIPTION

[0058] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0059] Please refer to Figure 1 A big data-based smart pension service management system comprises:

[0060] An intelligent device data acquisition module is configured to acquire intelligent device usage data in a current old person's home, build an intelligent device database, and synchronously upload the intelligent device database to a cloud database.

[0061] An intelligent device usage analysis module is configured to analyze the current old person's home appliance usage habits based on the intelligent device database, and build a habit fluctuation coefficient , and then build an average fluctuation threshold based on the home appliance usage habits of the remaining old persons in the cloud database When the habit fluctuation coefficient exceeds the average fluctuation threshold , a first early warning signal is sent, and a first early warning strategy is executed.

[0062] The intelligent device usage analysis module comprises an intelligent device usage analysis unit, a habit fluctuation evaluation unit, a cloud fluctuation analysis unit, and a first early warning unit.

[0063] The intelligent device usage analysis unit is configured to analyze the current old person's home appliance usage habits based on the intelligent device database, and build a living habit fluctuation coefficient and a current old person's home appliance comprehensive usage fluctuation coefficient in sequence, and the specific steps are as follows:

[0064] Step A1: reading the current old person's power consumption, gas usage, and water consumption in a sampling period t stored in the intelligent device database, and building a living habit fluctuation coefficient , and the specific expression is as follows:

[0065] wherein represents the current old person's power consumption historical mean value, which is obtained through the cloud database, represents the power consumption mean value in a sampling period t, represents the current old person's gas usage historical mean value, which is obtained through the cloud database, represents the gas usage mean value in a sampling period t, represents the current old person's water consumption historical mean value, which is obtained through the cloud database,​ represents the average water consumption in a sampling period t, represents the absolute value, by calculating and analyzing the current old person's life essential parameter usage, the current old person's life state can be quickly reflected, when the index appears large fluctuation, it will affect the overall habit fluctuation coefficient , so as to trigger the early warning condition;

[0066] Step A2: construct the current old person's comprehensive use fluctuation coefficient of home appliances , the specific steps are as follows:

[0067] Step A2.1: read the use time and use time point of the rest of the old people on the i-th smart device in the cloud database, and match to the 0~24H time axis, get several different coverage areas;

[0068] For example: the i-th smart device is a smart TV, and the use time coverage is as shown in the following table 1:

[0069] Table 1: smart TV use time coverage table

[0070]

[0071] The data recorded in this table are authorized by the user, and only the use time is stored;

[0072] Step A2.2: based on the smart device database, read the use time and use time point of the i-th smart device in the current old person's home environment, construct the use fluctuation coefficient of the i-th smart device in the current old person's home environment , the specific expression is as follows: ;

[0073] Among them, represents the use time (hours) of the i-th smart device in the current old person's home environment, represents the average use time of the i-th smart device, represents the total number of the i-th smart device connected to the cloud database, represents the number of overlaps of the use time point of the i-th smart device in the current old person's home environment and the use time of the i-th smart device matched to the 0~24H time axis with the rest of the coverage areas, represents a correction constant, and By comparing the use time of the smart device used by the current old person with the use time of the rest of the people, it can quickly reflect whether the current old person has irregular work and rest or has not turned off the device after turning it on, so as to analyze the state of the old person in time, if the use habit of the current old person matches the rest of the old people more, the value of will be lower, thereby reducing If the current old person only uses the smart device temporarily, the impact of this temporary use can be reduced through the expression ;

[0074] Step A2.3: Traverse each home appliance usage fluctuation coefficient of the current old person uploaded to the cloud database in turn, and construct the comprehensive home appliance usage fluctuation coefficient of the current old person , the specific expression is as follows: ;

[0075] Among them, represents the total number of home appliances uploaded to the cloud database by the current old person, represents the sum, by analyzing the usage of all smart appliances, the changes of the current old person in the overall life related can be determined, and the habit fluctuation coefficient .

[0076] The habit fluctuation assessment unit is based on the life habit fluctuation coefficient and the comprehensive home appliance usage fluctuation coefficient of the current old person , and comprehensively constructs the habit fluctuation coefficient , the specific expression is as follows: ;

[0077] Among them, represents the habit fluctuation coefficient, by comprehensively considering the life habit fluctuation and the electrical appliance usage fluctuation, the rest-activity fluctuation of the old person in the short term can be reflected, when the rest-activity fluctuation of the old person is large, the warning is issued, reminding the guardian or the management personnel to visit.

[0078] The cloud fluctuation analysis unit constructs the average fluctuation threshold based on the electrical appliance usage habits of the remaining old people in the cloud database , the specific steps are as follows:

[0079] Step B1: Read the habit fluctuation coefficient of the jth old person receiving user intervention in the cloud database , and construct the remaining old person fluctuation set ;

[0080] Step B2: Based on the remaining old person fluctuation set , obtain the mean value of the habit fluctuation coefficient of the old person receiving user intervention , the specific expression is as follows: ;

[0081] Among them, represents the total number of old people receiving user intervention, , represents the sum, Indicates the fluctuation set of the remaining elderly The set after removing the maximum and minimum values ​​effectively reflects the current average situation by removing the maximum and minimum values ​​from the fluctuation set. User intervention here refers to the proactive reporting and recording by caregivers or managers when they notice abnormalities in the elderly person's condition. ;

[0082] Step B3: Based on the fluctuation set of the remaining elderly people Remove maximum and minimum values Comprehensive construction of average fluctuation threshold By combining the maximum and minimum values ​​with their corresponding weights, the final average fluctuation threshold can be coupled more accurately. The specific expression is as follows: ;

[0083] in, and These represent two different weighting coefficients, and their specific expressions are as follows: ;

[0084] in, Indicates the fluctuation set of the remaining elderly The maximum value to be removed Indicates the fluctuation set of the remaining elderly The minimum value to be removed. This represents the mean of the habit fluctuation coefficient of the remaining elderly people when user intervention is received.

[0085] The first early warning unit is based on the habitual fluctuation coefficient. Exceeding the average fluctuation threshold The system issues a first warning signal. The first warning strategy specifically includes notifying the current caregiver of the elderly person, who then selects whether to upload information indicating an abnormal state of the elderly person. If an abnormal state is detected, the caregiver's habit fluctuation coefficient is then recorded. Set up a separate storage area to be deleted when the abnormal state ends. At the same time, do not upload the current usage time and time of the elderly on the i-th smart device to the cloud database. Abnormal states include: being sick, forgetting to turn off the smart device after turning it on, etc.

[0086] The elderly psychological state analysis module is invoked 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 assessment coefficient. At the same time, it determines whether to issue an early warning. If an early warning is required, it issues a second early warning signal and executes the second early warning strategy.

[0087] 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;

[0088] The social status analysis unit is used to read the total call duration of the current elderly person and the call duration of the call association set by the current caregiver in the smart device database, and to construct the social influence fluctuation coefficient in the t-th sampling period. The specific steps are as follows:

[0089] Retrieve the total call duration of the elderly person during the t-th sampling period from the smart device database. And read the total call duration of the current elderly person and the current elderly person's guardian set in the call association set during the t-th sampling period. And construct the social influence coefficient for the t-th sampling period based on the ratio of the two. The social impact fluctuation coefficient is constructed using the following expression. : ;

[0090] in, Indicates the first The social influence coefficient for each sampling period can effectively reflect the social status of the elderly within a sampling period by dividing and extracting the call duration of the elderly's common contacts, since the social circle of elderly people living alone who need care is relatively small.

[0091] The call association database stores the name of each contact and their corresponding phone number, and matches them when reading call logs, as shown in Table 2 below:

[0092] Table 2 Contact Call Association Table

[0093]

[0094] Call duration at this time , ;

[0095] The emotion analysis unit is based on a set of current facial images of the elderly obtained from cameras in the smart device's database, and then... An emotion recognition model (this is an existing model, and those skilled in the art should know how to build it, so it will not be elaborated here) is used to obtain the duration of each facial emotion in the t-th sampling period, constructing an emotion set that includes four emotions: happy, sad, normal, and angry. Based on the emotion set, an emotion fluctuation coefficient for the t-th sampling period is constructed. The specific steps are as follows:

[0096] Step C1: Obtain the duration corresponding to each facial emotion in the emotion set, and sum them to obtain the total duration of emotion sampling in the t-th sampling period. ;

[0097] Step C2: Extract the length of sadness and anger from the emotion set and the total length of emotion samples in the tth sampling period Calculate the emotion proportion in the tth sampling period :

[0098] ;

[0099] wherein, represents the length of sadness extracted from the emotion set in the tth sampling period, represents the length of anger extracted from the emotion set in the tth sampling period;

[0100] Step C3: According to the emotion proportion in the tth sampling period Calculate the emotion fluctuation coefficient in the tth sampling period , the specific expression is as follows: ;

[0101] wherein, represents the emotion proportion in the tth sampling period.

[0102] The mental state assessment unit constructs the mental state assessment coefficient based on the social influence fluctuation coefficient and the emotion fluctuation coefficient in the tth sampling period, and the specific expression is as follows: ;

[0103] wherein, respectively represent two weight coefficients whose sum is .

[0104] The second early warning unit judges after receiving the mental state assessment coefficient , and the specific steps are as follows:

[0105] If the mental state assessment coefficient of the current old person exceeds the average of the mental state assessment of the rest of the old people in the tth sampling period from the cloud database , a second early warning signal is sent out, indicating that the mental state of the current old person in the tth sampling period is not good, and the second early warning strategy is executed, which is specifically: marking the current old person, if the current old person is marked in continuous n sampling periods, the corresponding guardian or community manager is notified;

[0106] If the mental state assessment coefficient of the current old person does not exceed the average of the mental state assessment of the rest of the old people in the tth sampling period from the cloud database , no second early warning signal is sent out.​

[0107] The intelligent device compliance analysis module is called after the first early warning signal is sent, analyzes the compliance state of the intelligent device currently used by the old person based on the intelligent device database, and constructs the i-th intelligent device compliance coefficient , and a preset intelligent device compliance threshold is set When the intelligent device compliance coefficient exceeds the intelligent device compliance threshold , a third early warning signal is sent, and a third early warning strategy is executed.

[0108] The intelligent device compliance analysis module includes an intelligent device compliance evaluation unit and a third early warning unit.

[0109] The intelligent device compliance evaluation unit analyzes the compliance state of the intelligent device currently used by the old person based on the intelligent device database, and constructs the i-th intelligent device compliance coefficient , specifically including the following steps:

[0110] Step D1: Constructing the device update compliance coefficient of the i-th intelligent device in the intelligent device database , the specific expression is as follows: ;

[0111] Wherein, indicates the number of error reports after the i-th intelligent device is updated, indicates the number of updates of the i-th intelligent device, and the default is not calculated before the update , are obtained from the update log of the i-th intelligent device in the intelligent device database. Since it is difficult for the elderly to maintain the intelligent device, the more error reports after the device is updated, the more it indicates that there is a problem with the current device, and the guardian needs to be reminded;

[0112] Step D2: Constructing the maintenance compliance coefficient of the i-th intelligent device in the intelligent device database , the specific expression is as follows: ;

[0113] Wherein, indicates the number of service interruptions of the i-th intelligent device, which can reflect the situation that the current device needs to be maintained, indicates the number of repairs of the i-th intelligent device, respectively indicate the weight coefficients of ;

[0114] Step D3: Constructing the i-th intelligent device compliance coefficient , the specific expression is as follows: ;

[0115] Wherein, represents a correction number, and .

[0116] The third early warning unit sends out a third early warning signal when the i-th smart device compliance coefficient exceeds the smart device compliance threshold , and executes a third early warning strategy, which specifically includes:

[0117] Obtains the use proportion of the i-th smart device from the smart device database , matches the use proportion of the i-th smart device with the set use proportion set, and executes the corresponding strategy;

[0118] The specific expression of the use proportion of the i-th smart device is: , represents the total use frequency of the smart device, represents the use frequency of the i-th smart device, and when the third early warning signal is sent out, the use proportion set is read, as shown in Table 3 below:

[0119] Table 3 Use Proportion Early Warning Strategy Table of Smart Device

[0120]

[0121] Embodiment:

[0122] In this embodiment, the specific data of the current old person's home appliance use habit in one sampling period t is recorded in Table 4 below:

[0123] Table 4 Current Old Person's Home Appliance Use Habit

[0124]

[0125] It can be seen that there is a part difference between the old person's living habit and the historical average use habit in the current sampling period t;

[0126] Construct a current old person's home appliance comprehensive use fluctuation coefficient , as shown in Table 5 below:

[0127] Table 5 Current Old Person's Home Appliance Use Fluctuation

[0128]

[0129] At this time, the ;

[0130] The rest of the old person fluctuation set in the cloud fluctuation analysis unit , as shown in Table 6 below:

[0131] Table 6 fluctuation of the rest of the old people in the cloud fluctuation analysis unit

[0132]

[0133] At this time, the habit fluctuation coefficient of the current old person is calculated exceeds the average fluctuation threshold inform the current old person's guardian, and when the guardian confirms that the old person is in an abnormal state, the habit fluctuation coefficient of the current old person is set to a separate storage area, and is deleted when the guardian confirms that the abnormal state has ended.

[0134] The data involved in the social state analysis unit is shown in Table 7 below:

[0135] Table 7 data involved in the social state analysis unit

[0136]

[0137] At this time, the habit fluctuation coefficient of the current old person is calculated At this time, the current old person is marked for the first time, and if the current old person is marked for n consecutive sampling periods, the corresponding guardian or community manager is notified. The data involved in the intelligent device compliance analysis module is shown in Table 8 below:

[0138] Table 8 data involved in the intelligent device compliance analysis module

[0139]

[0140]

[0141] At this time, exceeds the intelligent device compliance threshold , and no third warning signal is issued. The above embodiments only give one or more feasible schemes, and do not represent the optimal scheme, and the amount of data and the size of the data recorded in the embodiments are only for the understanding of the technical scheme by those skilled in the art, and do not represent that the scheme only uses the data recorded in the above embodiments in actual application. The size of the threshold is set for easy comparison. The size of the threshold depends on the amount of sample data and the number of base set by those skilled in the art for each group of sample data. As long as it does not affect the proportional relationship of the parameters and the quantized values, and the size of the weight can be determined by those skilled in the art according to each sample data and the process of multiple experiments. The above formulas are all dimensionless to calculate the numerical values.

[0142]

[0143] ​​While embodiments of the application have been shown and described, it is to be understood that the embodiments described are merely exemplary of the principles and application of the present application. Numerous modifications and adaptions can be effected without departing from the spirit and scope of the present application, which is not limited to the exact construction and arrangement described. It is intended, therefore, to cover all modifications and adaptions that fall within the scope of the claims and their equivalents.

Claims

1.A big data-based smart elderly care service management system, characterized in that: Comprise: The intelligent device data acquisition module is used for collecting the current old people's home intelligent device use data, and constructs the intelligent device database, and synchronously uploads to the cloud database; The intelligent device usage analysis module analyzes the current old person's home appliance usage habit based on the intelligent device database, and constructs a habit fluctuation coefficient , and then constructs an average fluctuation threshold based on the appliance usage habits of the remaining old people in the cloud database When the habit fluctuation coefficient exceeds the average fluctuation threshold , a first early warning signal is sent out, and a first early warning strategy is executed; The intelligent device use analysis module includes an intelligent device use analysis unit, a habit fluctuation evaluation unit, a cloud fluctuation analysis unit and a first warning unit; The intelligent device uses an analysis unit to analyze the current old person's home appliance use habit based on an intelligent device database, and sequentially constructs a living habit fluctuation coefficient and a current old person's home appliance comprehensive use fluctuation coefficient , and the specific steps are as follows: Step A1: read the current old person's electricity consumption, gas usage and water usage stored in the smart device database within a sampling period t, and construct the living habit fluctuation coefficient , the specific expression is as follows: ; wherein, represents the current old person's electricity consumption history mean value, which is obtained through a cloud database, represents the electricity consumption mean value in a sampling period t, represents the current old person's gas consumption history mean value, which is obtained through a cloud database, represents the gas consumption mean value in a sampling period t, represents the current old person's water consumption history mean value, which is obtained through a cloud database, represents the water consumption mean value in a sampling period t, represents an absolute value; Step A2: Constructing the current old people's home electrical appliances comprehensive use fluctuation coefficient The specific steps are as follows: Step A2.1: read the remaining old people's use time length and use time point of the i-th intelligent device in the cloud database, and match to the 0~24H time axis, obtain several different coverage areas; Step A2.2: Based on the smart device database, read the use duration and use time point of the i-th smart device in the current old person's home environment, and construct the use fluctuation coefficient of the i-th smart device in the current old person's home environment , the specific expression is as follows: ; wherein, represents the use time length of the i-th smart device in the current old people's home environment, represents the average use time length of the i-th smart device, represents the total number of the i-th smart device connecting to the cloud database, represents the number of overlaps of the use time point of the i-th smart device in the current old people's home environment and the use time length of the i-th smart device with the rest of the coverage area on the time axis of 0~24H, represents a correction number, and ; Step A2.3: Traverse each of the home appliance usage fluctuation coefficients of the current old person uploaded to the cloud database in turn, and construct the comprehensive usage fluctuation coefficient of the current old person's home appliances , the specific expression is as follows: ; wherein, represents the total number of home appliances currently synchronized by the old person to upload to the cloud database, represents summation; The old man psychological state analysis module is called after the first early warning signal is sent, analyzes the psychological state of the current old man based on the intelligent device database, and constructs a psychological state evaluation coefficient Meanwhile, it is judged whether to perform early warning, and if early warning is needed, a second early warning signal is sent, and a second early warning strategy is executed. The intelligent device compliance analysis module is called after the first early warning signal is sent, analyzes the compliance state of the intelligent device currently used by the old person based on the intelligent device database, and constructs the i-th intelligent device compliance coefficient , and a preset intelligent device compliance threshold is simultaneously set When the intelligent device compliance coefficient exceeds the intelligent device compliance threshold , a third early warning signal is sent, and a third early warning strategy is executed. 2.The big data-based smart aged care service management system according to claim 1, characterized in that: The habit fluctuation evaluation unit is based on a living habit fluctuation coefficient and a current old person home appliance comprehensive use fluctuation coefficient , a habit fluctuation coefficient is comprehensively constructed , and the specific expression is as follows: ; wherein represents the habituation volatility coefficient. 3.The big data-based smart aged care service management system according to claim 1, characterized in that: The cloud fluctuation analysis unit constructs an average fluctuation threshold value based on the electrical appliance use habits of the remaining old people in the cloud database The specific steps are as follows: Step B1 : read the habit fluctuation coefficient of the first elderly person who accepts user intervention from the cloud database and construct the fluctuation set of the remaining elderly people ; Step B2: Based on the remaining old person fluctuation set Obtain the mean value of the habit fluctuation coefficient of the old person receiving user intervention , the specific expression is as follows: ; wherein, represents the total number of old people who accept user intervention, , represents the summation, represents the set of fluctuations from the remaining old people the set after removing the maximum and minimum values; Step B3: Based on the remaining old person fluctuation set Cull max and min and Build average fluctuation threshold The specific expression is as follows: ; wherein, and represent two different weight coefficients, whose specific expressions are as follows: ; ; wherein, represents the maximum value of the remaining old person fluctuation set represents the maximum value of the remaining old person fluctuation set represents the minimum value of the remaining old person fluctuation set represents the minimum value of the remaining old person fluctuation set represents the mean value of the habit fluctuation coefficient of the remaining old person when accepting user intervention. 4.The big data-based smart aged care service management system according to claim 1, characterized in that: The first early warning unit sends a first early warning signal when the habit fluctuation coefficient exceeds the average fluctuation threshold The first early warning strategy specifically includes notifying the current elderly guardian, and the guardian selects whether to upload the current elderly state as abnormal. If the state is abnormal, the habit fluctuation coefficient of the current elderly The first early warning strategy specifically includes notifying the current elderly guardian, and the guardian selects whether to upload the current elderly state as abnormal. If the state is abnormal, the habit fluctuation coefficient of the current elderly 5.The big data-based smart aged care service management system according to claim 1, characterized in that: The old man's psychological state analysis module includes a social state analysis unit, an emotion analysis unit, a psychological state evaluation unit and a second warning unit; The social state analysis unit is configured to read the total call duration of the current old person in the intelligent device database and the call duration in the call association set set by the current old person's guardian, and construct a social influence fluctuation coefficient in the tth sampling period The specific steps are as follows: read from the smart device database the total current old person call duration in the tth sampling period , and read the total person call duration in the tth sampling period in the current old person and the current old person guardian set call association set , and construct the social influence coefficient of the tth sampling period according to the ratio of the two , construct the social influence fluctuation coefficient through the following expression : ; wherein, represents the social influence coefficient for the th sampling period; The emotion analysis unit obtains a current old person face image set acquired by a camera in the intelligent device database, and obtains a corresponding time length of each kind of face emotion in the tth sampling period through an emotion recognition model An emotion set is constructed, the emotion set including four emotions of happy, sad, normal and angry, and an emotion fluctuation coefficient of the tth sampling period is constructed according to the emotion set The specific steps are as follows: Step C1: obtain the time length corresponding to each facial emotion in the emotion set, and sum up to obtain the total time length of emotion sampling in the tth sampling period ; Step C2: Extract the duration of sadness and anger from the emotion set and total duration of emotion samples in the tth sampling period Calculate the emotion proportion in the tth sampling period : ; wherein, represents extracting the sadness duration from the set of emotions for the tth sampling period, represents extracting the anger duration from the set of emotions for the tth sampling period; Step C3: emotion proportion in the tth sampling period The emotion fluctuation coefficient in the tth sampling period is calculated , and the specific expression is as follows ; wherein, represents the sample period emotion proportion. 6.The system according to claim 5, wherein the system is a big data-based smart elderly care service management system. The mental state evaluation unit constructs a mental state evaluation coefficient based on the sociality number and the emotion fluctuation coefficient obtained in the tth sampling period and the emotion fluctuation coefficient The mental state evaluation coefficient is constructed The specific expression is as follows: ; wherein respectively denote two weight coefficients that sum to one. 7.The big data-based smart aged care service management system according to claim 6, characterized in that: The second early warning unit judges whether the psychological state of the user is abnormal after receiving the psychological state evaluation system The specific steps are as follows: If the current old man's psychological state evaluation coefficient exceeds the mean value of the psychological state evaluation of the rest of the old people in the cloud database in the t-th sampling period , a second warning signal is sent out, indicating that the current old man's psychological state is not good in the t-th sampling period, and a second warning strategy is executed, specifically: the current old man is marked, and if the current old man is marked in the next n sampling periods, the corresponding guardian or community manager is notified; If the current old man's psychological state evaluation coefficient If the current old man's psychological state evaluation coefficient then the second early warning signal is not sent out. 8.The big data-based smart aged care service management system according to claim 1, characterized in that: The intelligent device compliance analysis module includes an intelligent device compliance evaluation unit and a third warning unit; The smart device compliance evaluation unit analyzes the compliance state of the smart device currently used by the old person based on the smart device database, and constructs the i-th smart device compliance coefficient , and specifically includes the following steps: Step D1 : Constructing the device update adherence coefficient of the i-th smart device in the smart device database , the specific expression is as follows: ; wherein, represents the updated error reporting times of the i-th intelligent device, represents the update times of the i-th intelligent device, which are obtained from the update log of the i-th intelligent device in the intelligent device database; Step D2: constructing a maintenance adherence coefficient for the i-th smart device in the smart device database , and the specific expression is as follows: ; wherein, represents the number of interruptions of the i-th smart device service, represents the number of repairs of the i-th smart device, respectively represent weight coefficients that sum to 1; Step D3: Constructing the i-th smart device compliance coefficient , and the specific expression is as follows: ; wherein represents a correction number, and . 9.The big data-based smart aged care service management system according to claim 8, characterized in that: The third early warning unit when the i-th intelligent device adherence coefficient Exceeds the intelligent device adherence threshold The third early warning signal is sent out, and the third early warning strategy is executed, specifically including: Obtaining the use proportion of the i-th smart device from the smart device database When the use proportion of the i-th smart device Matches the set use proportion set, and executes the corresponding strategy.

Images