CN117373204B - Early warning method and system for aged people in digital village - Google Patents
Early warning method and system for aged people in digital village Download PDFInfo
- Publication number
- CN117373204B CN117373204B CN202311351764.0A CN202311351764A CN117373204B CN 117373204 B CN117373204 B CN 117373204B CN 202311351764 A CN202311351764 A CN 202311351764A CN 117373204 B CN117373204 B CN 117373204B
- Authority
- CN
- China
- Prior art keywords
- duration
- early warning
- probability
- old
- people
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000006870 function Effects 0.000 claims abstract description 30
- 238000012216 screening Methods 0.000 claims abstract description 9
- 238000012544 monitoring process Methods 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 20
- 201000010099 disease Diseases 0.000 claims description 11
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 9
- 239000003814 drug Substances 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 abstract description 2
- 230000007547 defect Effects 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 230000004308 accommodation Effects 0.000 description 3
- XOFYZVNMUHMLCC-ZPOLXVRWSA-N prednisone Chemical compound O=C1C=C[C@]2(C)[C@H]3C(=O)C[C@](C)([C@@](CC4)(O)C(=O)CO)[C@@H]4[C@@H]3CCC2=C1 XOFYZVNMUHMLCC-ZPOLXVRWSA-N 0.000 description 3
- 230000001960 triggered effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Algebra (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Evolutionary Biology (AREA)
- Development Economics (AREA)
- Emergency Management (AREA)
- Operations Research (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Gerontology & Geriatric Medicine (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a method and a system for early warning of aged people in a digital village, wherein the method comprises the following steps: collecting historical data of the aged in the rural area, which is continuously resided in the daytime, forming a first data set, and constructing the resident duration of the aged as b 0 Probability density functions of (2); screening out data which are continuously motionless due to falling from the first data set to form a second data set, wherein the residence duration is b under the condition that the old people are accidentally fallen under the root construction 0 Probability density functions of (2); counting the accidental falling probability of different old people; constructing early warning duration error conditions of the old people by combining a Bayesian formula, and calculating the minimum duration meeting the early warning duration error conditions as an optimal early warning threshold; and carrying out accidental fall pre-warning on the old people based on the optimal pre-warning threshold value. According to the invention, the optimal early warning threshold value is calculated based on the Bayesian formula, so that targeted safety early warning can be carried out on different aged people in time, and the defect of aged warning in the digital village is overcome.
Description
Technical Field
The invention belongs to the technical field of digital villages, and particularly relates to an early warning method and system for aged people in a digital village.
Background
In rural areas, aging is increasingly severe, but medical conditions and infrastructure are relatively weak, and the level of care for the aged is relatively lagged. Many elderly people are scattered and solitary in individual rural families, some of which are even engaged in agricultural production activities. With the development of digital rural technology, in order to monitor the health condition of the elderly and find problems in real time, the village commission generally adopts an intelligent bracelet to monitor information such as heartbeat and heart rate of the elderly, or monitors action tracks and personal safety through other intelligent monitoring devices which need to be carried around.
For example, the invention patent publication number CN 108093122A discloses an automatic alarm method for the safety monitoring of the elderly, which monitors the safety of the elderly by using an intelligent mobile terminal provided with an acceleration sensor, a displacement sensor and a GPS positioning part, and sounds an alarm in the event of an abnormality. However, the old often lacks health consciousness, and the old may not wear these equipment in the removal process, perhaps forget to charge, if take place the old condition such as falling down by accident at this moment, if can not send early warning in time, then can send serious safety problem. Therefore, under the condition that the old does not carry specific intelligent safety monitoring equipment with him, timely safety precaution for the old is also an important direction of digital rural development.
In general, if the elderly cannot move due to accidental falls, the device is characterized by being continuously resident in a certain fixed place. Based on this feature, it is possible to infer whether an unexpected fall has occurred by judging the residence time of the elderly. It is easily conceivable to use a method of setting an empirically constant value, and if the empirically constant value is exceeded and no other person is present around, the old person is considered to have fallen unexpectedly. However, this method is not accurate enough, because the time period for which the pre-warning occurs continuously varies for objective reasons such as age, sex, basic disease, etc. of each elderly person.
Therefore, a new pension early warning mode is needed to perform targeted safety early warning on pension personnel with different physical conditions in time.
Disclosure of Invention
In view of the above, the invention provides a method and a system for early warning of the aged in a digital country, which are used for solving the problem that the aged in the digital country cannot be subjected to targeted safety early warning on aged people with different physical conditions in time.
The invention discloses a method for early warning of aged people in a digital village, which comprises the following steps:
collecting historical data of the aged in the rural area, which is continuously resided in the daytime, forming a first data set, and constructing the aged resident duration of b according to the first data set 0 Probability density functions of (2);
screening data which is continuously motionless due to tumbling from the first data set to form a second data set, and constructing the elderly people according to the second data setIn the condition of unexpected fall, the residence duration is b 0 Probability density functions of (2);
determining influence factors influencing the probability of accidental falls of the old people, inquiring a historical database according to the influence factors, and counting the probability of accidental falls of different old people;
based on the old people resident duration of b 0 The residence duration is b under the condition that the elderly fall accidentally 0 The probability density function of the early warning time length error condition of each old person is constructed by combining a Bayesian formula and the probability of accidental falling of different old persons, and the minimum duration time meeting the early warning time length error condition is calculated;
and taking the minimum duration meeting the error condition of the early warning duration as the corresponding optimal early warning threshold value of the old people, and carrying out accidental fall early warning on the old people.
On the basis of the technical scheme, the data content of the first data set comprises the identity of the elderly, the reason for continuous immobility and the duration of continuous immobility.
On the basis of the technical proposal, the residence duration time of the old people constructed according to the first data set is b 0 Specifically, the probability density function of (1) includes:
assuming event B represents an elderly person residing in a certain area for a time greater than a preset time period, calculating the expected μ of the first dataset 2 Sum of variances sigma 2 Constructing the residence duration of the old person as b 0 Probability density function of (c):
wherein x represents a time period, P (B<b 0 ) Indicating that the old people stay for a duration of time b 0 Is a probability of (2).
On the basis of the technical proposal, the residence duration is b under the condition that the elderly people fall accidentally according to the second data set 0 Specifically, the probability density function of (1) includes:
assume event A representsCalculating the expected mu of the second data set under the condition that the elderly fall accidentally 1 Sum of variances sigma 1 The residence duration is b under the condition that the elderly fall accidentally 0 The probability density function of (2) is:
where x represents the duration, P ((B)<b 0 ) I A) indicates that the residence duration is b under the condition that the elderly fall accidentally 0 Is a probability of (2).
On the basis of the technical scheme, the early warning duration error conditions are as follows:
|P(A)P((B<b 0 )|A)-P 0 P(B<b 0 )|≤△E
wherein ΔE is a pre-configured error threshold, P 0 And P (A) is the corresponding probability of accidental falling of the old people for the preset early warning probability.
On the basis of the technical scheme, the calculating of the minimum duration meeting the early warning duration error condition specifically comprises the following steps:
setting initial time length of starting circulation, maximum time length of finishing circulation and increment time length dt of every circulation, and making b 0 ＝b 0 +dt, cyclically judging current duration b 0 Whether the early warning duration error condition is met, and once the early warning duration error condition is met, b is the moment 0 The minimum duration meeting the error condition of the early warning duration is obtained.
On the basis of the technical scheme, if the minimum duration meeting the error condition of the early warning duration is not calculated until the cycle is ended, searching the duration closest to the early warning probability as the optimal early warning threshold value within the time range from the initial duration of the cycle to the maximum duration of the cycle.
In a second aspect of the present invention, a pension warning system in a digital country is disclosed, the system comprising:
a first calculation module: elderly people for collecting rural areas during daytimeContinuously resident historical data to form a first data set, and constructing the resident duration of the old according to the first data set as b 0 Probability density functions of (2);
a second calculation module: the method comprises the steps of screening data which are continuously motionless due to falling from a first data set, forming a second data set, and constructing the residence duration of b under the condition that the old people fall accidentally according to the second data set 0 Probability density functions of (2);
probability statistics module: the method comprises the steps of determining influence factors which influence the probability of accidental falls of old people, inquiring a historical database according to the influence factors, and counting the probability of accidental falls of different old people;
a threshold calculating module: for a residence duration of b based on elderly people 0 The residence duration is b under the condition that the elderly fall accidentally 0 The probability density function of the early warning time length error condition of each old person is constructed by combining a Bayesian formula and the probability of accidental falling of different old persons, and the minimum duration time meeting the early warning time length error condition is calculated;
fall early warning module: the early warning method is used for carrying out accidental fall early warning on the old people by taking the minimum duration meeting the early warning duration error condition as the corresponding optimal early warning threshold value of the old people.
In a third aspect of the present invention, an electronic device is disclosed, comprising: at least one processor, at least one memory, a communication interface, and a bus;
the processor, the memory and the communication interface complete communication with each other through the bus;
the memory stores program instructions executable by the processor which the processor invokes to implement the method according to the first aspect of the invention.
In a fourth aspect of the invention, a computer-readable storage medium is disclosed, storing computer instructions that cause a computer to implement the method according to the first aspect of the invention.
Compared with the prior art, the invention has the following beneficial effects:
1) The invention collects the historical data of the aged in the rural area, which is continuously resident in the daytime, and calculates the resident duration of the aged as b 0 In the presence of a probability of accidental falls, the duration of residence is b 0 And the probability of accidental falls of different aged people is counted, probability estimation is carried out based on a Bayesian formula, an optimal early warning threshold is calculated, accidental falls of the aged are rapidly early warned based on the optimal early warning threshold, and even under the condition that the aged does not carry intelligent monitoring equipment with the intelligent monitoring equipment, targeted safety early warning can be carried out on different aged-maintenance personnel in time, the early warning difficulty is reduced, and the defect of early warning of the aged in a digital village is overcome.
2) According to the invention, the early warning time length error conditions are constructed for each old person based on the conditional probability model, the minimum time length meeting the early warning time length error conditions is calculated through iterative operation, the minimum time length meeting the early warning time length error conditions is used as the corresponding optimal early warning threshold value of the old person, the early warning can be fast performed without complex data processing, and the early warning response speed is improved.
3) According to the invention, the difference of the probability of falling events of the old people with different physical conditions is fully considered, the optimal early warning threshold value is calculated for each old people according to the individual difference of the different old people, the accidental falling situation of the old people is more accurately predicted, and the early warning emergency rescue efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method for early warning of endowment in a digital country according to the present invention;
fig. 2 is a flowchart of an embodiment of the method for early warning of aged people in digital village according to the present invention;
FIG. 3 is a flow chart of the early warning threshold calculation of the present invention.
Detailed Description
The following description of the embodiments of the present invention will clearly and fully describe the technical aspects of the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, are intended to fall within the scope of the present invention.
Although the old people do not carry specific intelligent safety monitoring equipment such as an intelligent bracelet, the intelligent mobile phone is generally used, so that the position information of the old people can be collected in real time by utilizing the GPS positioning function of the intelligent mobile phone to form a moving track. The general living area of the elderly includes private and non-private areas. Private areas generally refer to home areas and their contractual land, non-private areas including public areas and other personal areas; but the elderly are often on a private scale with accidents that are not found. Therefore, the duration of the continuous residence in the private range can be monitored by analyzing the moving track, and if the continuous residence time of the monitoring object of the old is found to exceed the early warning threshold value and no other people exist around, the early warning prompt is triggered to allow the village committee to dispatch personnel to check.
However, the method of setting a constant time value as an early warning threshold is not accurate enough and needs to be calculated for different old people. According to the invention, the conditional probability is calculated based on historical data, and the optimal early warning threshold value is calculated for each old person based on a Bayesian formula, so that the old person accidental fall early warning is carried out.
The principle of calculating the optimal early warning threshold value is as follows:
assuming that event a represents an accidental fall of the elderly, P (a) represents the probability of an accidental fall of the elderly. Event B indicates that the elderly person is resident in an area (such as a home or farmland) for more than a preset period of time, and B indicates that the elderly person is residentThe duration is left. P (B)<b) Indicating the probability of the elderly residing for a duration of time b. P (A| (B)<b 0 ) Indicating a residence duration of b in elderly people 0 The probability of an accidental fall occurs. If the early warning probability is set as P 0 Then P (A| (B)<b 0 ))≥P 0 In the time, the old is likely to fall down, and early warning needs to be sent out. However, the old resides for a duration of time b 0 Unknown, therefore, the minimum residence duration can be calculated according to the conditional probability model to serve as an optimal early warning threshold value, and if the minimum residence duration exceeds the optimal early warning threshold value, the old is considered to fall accidentally, and early warning is sent out.
Based on a Bayesian formula, the early warning needs to be sent out:
namely:
P(A)P((B<b 0 )|A)-P 0 P(B<b 0 )＝0
wherein P ((B)<b 0 ) I A) means that the old people stay for a period of time b under the condition that the old people fall accidentally 0 Is a probability of (2).
Therefore, the invention discloses a method for early warning for aged people in digital villages, which carries out early warning for accidental falls of the aged people by calculating the optimal early warning threshold, and mainly comprises the following steps as shown in figure 1:
s1, collecting historical data of the aged in the rural area, wherein the historical data comprise the identity, the continuous motionless reason and the continuous motionless time length of the aged, forming a first data set, and calculating the expected mu of the first data set 2 Sum of variances sigma 2 Suppose P ((B)<b 0 ) Normal distribution is obeyed, and the residence duration of the old is constructed to be b 0 Probability density function P (B)<b 0 )：
Where x represents the duration.
S2, screening data which are continuously motionless due to tumbling from the first data set to form a second data set, and calculating expected mu of the second data set 1 Sum of variances sigma 1 Suppose P ((B)<b 0 ) According to the normal distribution, the residence duration is b under the condition that the elderly fall accidentally 0 Probability density function P ((B)<b 0 )|A)：
S3, determining influence factors influencing the probability of accidental falls of the old people, inquiring a historical database of a medicine or an insurance company according to the influence factors, and counting the probability P (A) of accidental falls of different old people.
S4, constructing early warning duration error conditions of the old people based on the probabilities and combining a Bayesian formula:
|P(A)P((B<b 0 )|A)-P 0 P(B<b 0 )|≤△E
wherein ΔE is a pre-configured error threshold, P 0 The early warning probability is preset.
And calculating the minimum duration meeting the error condition of the early warning duration as the optimal early warning threshold of the corresponding old people.
S5, performing accidental fall pre-warning on the old people based on the optimal pre-warning threshold.
The implementation of the invention is based on data such as rural population, accommodation, land contractual land, etc. All adults need to carry mobile equipment through which personal information is bound with latitude and longitude range information of the land they are contracting on. Whether a person is within a certain privacy range is judged through longitude and latitude of the mobile device. After the positioning information of the equipment is collected each time, the residence time of a person in a certain place can be calculated, and whether the early warning needs to be triggered or not is judged according to the residence time.
Referring to fig. 2, the invention provides a method for early warning of aged people in digital villages, which comprises the following specific implementation processes:
step one, setting a resident standard: i.e. when a person does not move beyond a certain threshold, typically 3-5 meters, it is considered that the person resides, this threshold distance being called the residence criterion.
This criterion will be used to subsequently determine when the other person enters the residence range of the other person. And (3) entering a step two after the completion.
Step two, calculating an early warning threshold value: and calculating early warning thresholds of all the people in various active areas in the village.
In a country, the active area is divided into private areas, not private areas. Wherein other people exist in the non-private range, and the corresponding early warning threshold is lower; the private area includes the covered land and the residential area, and different early warning thresholds need to be determined according to the conditions of the day and the night. If the early warning threshold is not calculated in one area, the early warning condition is not required to be considered in the range. The early warning threshold value of the person in various active areas can be calculated for the specific person. Some early warning thresholds may need to be associated with a specific time period, for example, the old generally has a high possibility of accidents such as falling during the daytime, and the rest time at night is generally not active, so if the early warning threshold of the daytime activity is calculated, the start-stop time period of the early warning needs to be set.
As shown in fig. 3, which is a flowchart of early warning threshold calculation, the second step specifically includes the following sub-steps:
step 1, configuration parameters: in order to calculate the early warning threshold value of a certain elderly person, some parameters need to be configured. Because the invention calculates the time length of the optimal early warning threshold value in a circulating mode, the configured parameters comprise early warning probability P 0 An initial duration of the start of the cycle, a maximum duration of the end of the cycle, and an incremental duration at each cycle. Wherein, early warning probability P 0 Typically set to 0.7 or 0.8. The initial duration of the cycle start is typically 30 minutes; the maximum duration of the end of the cycle is typically 12 hours, and the incremental duration of the self-increment per cycle is typically 1 minute. In addition, an error Δe needs to be specified, and is generally set to 0.01 or 0.005. After the parameter configuration is completed, the method can enter step 2 to start calculating the old peopleAnd (5) early warning a threshold value.
Step 2, collecting data: the method comprises the steps of collecting senile data of a country, wherein the data generally comprise data over 60 years old, and the data content comprises the identity, the duration of immobility and the duration of immobility of the elderly, so that a first data set is formed, and the data in the first data set is at least 1000 pieces. After completion, step 3 is entered.
Step 3, construction of P (B)<b 0 ): the first data set conforms to the front distribution, and the expected mu is calculated through a formula of probability theory 2 Sum of variances sigma 2 And construct P (B)<b 0 ) Probability density function of (c):
after completion, step 4 is entered.
Step 4, screening data: and screening the data which is continuously motionless due to tumbling from the first data set to form a second data set. The second data set also conforms to the positive-going distribution. After completion, step 5 is entered.
Step 5, build P ((B)<b 0 ) |a): calculating the mean and variance mu of the second data set from the data screened in the step 4 by using a probability formula 1 ，σ 1 And P ((B)<b 0 ) Probability density function of i a):
after completion, step 6 is entered.
Step 6, selecting an old person: and selecting an old person with age exceeding a certain time limit for calculating the duration of the early warning threshold. After completion, step 7 is entered.
Step 7, acquiring a falling probability P (A): determining influencing factors influencing the probability of accidental falls of the old, and acquiring the probability of falling of the old through inquiring a historical database of a medicine or insurance company.
Taking two influencing factors of age and sex as an example, the probability of falling P (a) is shown in table 1, and is the probability of accidental falling between 60 and 75 years old, and a female old man is assumed, and the probability of falling is 0.46 for her 68 years old. The embodiment only lists two influencing factors of age and gender, and in fact, other influencing factors can be considered according to requirements, for example, if the old has other diseases, the falling probability is higher. The probability of fall P (a) can also be obtained as long as there is fall statistics for elderly people with certain diseases. After the parameter query is completed, the method proceeds to step 8, and the subsequent operation is continued.
Table 1: probability of accidental fall between 60 and 75 years old
Step 8, setting b 0 Is set to the initial value of (1): this variable represents the duration for the loop calculation P (A) P ((B)<b 0 ) I A) and P 0 P(B<b 0 ) If the difference satisfies the condition b 0 The early warning threshold time of the old is achieved. The initial value is set to an initial duration. After the completion of the setting, the process proceeds to step 9.
Step 9, temp_d=1, temp_b=maximum duration: if all the time periods cannot reach the range of the error delta E in the circulation range, the early warning threshold value of the old cannot be calculated. Thus, the duration of the minimum difference is used to represent its early warning threshold. In order to find the minimum difference, two variables temp_d, temp_b are introduced, wherein temp_d is used to record the minimum difference and temp_b is used to record the early warning threshold time in the case of the minimum difference. At the start of the cycle, temp_d is set to 1 and temp_b is set to the maximum duration. After the above steps are completed, the process proceeds to step 10, and the subsequent operations are continued.
Step 10, judging b 0 Whether greater than the longest duration: this step determines whether all time periods have been traversed, if soAnd (3) indicating that the most suitable early warning duration is not found all the time, and entering step 17. Otherwise, it indicates that further loop calculation is required, and step 11 is entered.
Step 11, calculate error d= |p (a) P ((B)<b 0 )|A)-P 0 P(B<b 0 ) I (L): b under the current cycle 0 Is a determined value, and the value of the error d is calculated by the probabilities obtained in steps 3, 6 and 7. After completion, the process proceeds to step 12.
Step 12, judging whether d is larger than temp_d: comparing the d value with the size of Temp_d, if d is greater than Temp_d, it means that d must be greater than ΔE, at which time b 0 If the threshold value is not the early warning threshold value, the step 15 is entered; otherwise, step 13 is entered.
Step 13, temp_d=d, temp_b=b 0 : sum the current d value and b 0 The temporary 2 variables are respectively assigned, and the value recorded by temp_d is the minimum value of d so far, and temp_b is the duration corresponding to the minimum value. After completion step 14 is entered.
Step 14, judging whether d is less than or equal to delta E: judging whether the d value is smaller than or equal to delta E, if so, indicating that the early warning threshold condition of the old is met, and entering a step 16; if not, this means that further cycles are required, proceeding to step 15.
Step 15, b 0 ＝b 0 +dt: this step indicates that the current cycle has ended and that the optimal pre-warning duration is not found for that duration. Therefore, on the basis of the current duration, it is necessary to increase the preset incremental duration dt and then start a new cycle. After completion, step 10 is entered.
Step 16, the early warning threshold value of the old is b 0 : at this time b 0 The early warning threshold value of the old is shown that when the early warning time length of the old is b 0 And when the old people fall down, the probability is early warning probability.
Step 17, the early warning threshold of the elderly is temp_b: in the range from the initial duration to the longest duration of the cycle, the elderly does not find the optimal early warning duration. However, although the exact warning duration is not found, there is a value of temp_b, which is the duration closest to the warning probability, in this time range. The value of Temp_b is taken as the optimal early warning threshold.
And step three is carried out after the calculation of the optimal early warning threshold is completed.
Step three, monitoring object configuration: specific populations are selected for monitoring, which are typically poor physical conditions in the country, especially elderly individuals living alone. The number of monitoring objects can be increased or decreased in real time according to the processing capacity of the actual calculation force. And step four is carried out after the completion.
Step four, monitoring object selection: the next flow will describe how to calculate its duration and how to determine whether or not an early warning is required, by selecting one monitoring object from all monitoring objects as an example. In actual operation, all the monitoring objects must be monitored at the same time, but the monitoring method of each object is the same. And step five is carried out after the completion.
Step five, collecting the current position of the monitored object: the point location information of the monitored objects is collected at a certain frequency, which information is provided by their mobile devices. In general, the GPS service on the mobile device to be monitored is used to obtain the location information at a certain frequency and send the location information to the monitoring server. Typically, the location information is collected once per minute. If the collection frequency is increased, more data will be generated, and stronger processing power is required for early warning calculation. The collection frequency is set according to the accuracy requirement of the early warning threshold. The collected information mainly comprises acquisition time, personnel identity and longitude and latitude. And step six is carried out after the completion.
Step six, judging whether one person: it is determined whether there are other people around. The judging method is to acquire the longitude and latitude of other people in the current time by utilizing GPS positioning, and calculate the distance between the person and the other people through the longitude and latitude. And taking the minimum value of the distances, and judging whether the minimum distance is larger than the residence standard. If the judgment result is that only one person is considered to be one person, further analysis is needed, and the step seven is entered. If the judgment is not yes, the fact that other people exist around the person is indicated, even if the person is unexpected, the person can quickly find out, therefore, early warning is not needed for the situation, and the step eight is entered.
Step seven, determining the position of the monitoring object: the private range is firstly determined, the latitude and longitude range information, the land contract information and the land block information of the contract are associated from all the contract information through the identity information of the monitoring object, the latitude and longitude range information of the contract is associated, the range information is the latitude and longitude representation of the boundary vertex, and the private range of the monitoring object is determined through the latitude and longitude range information. Then, whether the current position of the monitored object is in the accommodation area or the area of the covered land in the private area is judged by using a ray method. If the monitoring object is not in the range, the monitoring object is in a non-private range. Through this step, it is clear that the monitoring object is in one of the contractual land range, accommodation range, and other range. Step ten is entered after completion.
Step eight, setting the record not to participate in the calculation of the later residence time length: this step is to make an identification for the current record, which indicates that the record should be filtered out at a later time when the residence time length calculation is performed. After completion, step nine is entered.
Step nine, storing records: storing a point location record of a current acquisition, the record comprising: and acquiring the time, the personnel identity, the longitude and latitude and the identification of whether to participate in residence time calculation. And step five is carried out after the completion, and the position of the current monitoring object is continuously collected.
Step ten, obtaining a record group capable of calculating residence time length: and firstly, sorting all point position records of the monitoring object according to the time reverse order, and ensuring that the most recent records are arranged in the front and the most distant records are arranged in the back. Then, a set of point records is selected one by one in a sequential order until a record is presented that identifies that the record is not involved in the calculation of the residence time period and that the record is not in the set of records. After completion, step eleven is entered.
Step eleven, whether the total number of records is 0: if the total number of records is 0, indicating that the residence time can not be calculated, entering a step nine, and continuously collecting point location information; otherwise, the duration can be calculated, and step twelve is entered.
Step twelve, determining the earliest point location record which does not meet the residence condition: and sequentially calculating the distance between each record and the current point position according to the record group. If the distance is smaller than the residence standard, selecting the next record to calculate, and continuing to judge the distance. And continuing until the record with the appearance distance being greater than or equal to the residence standard is formed, wherein the record is the earliest point location record. If the distances between all records in the record group and the current point position are smaller than the residence standard, the last record is judged to be the earliest point position record which does not meet the residence condition. Step thirteenth is entered after completion.
Thirteenth, recording whether the earliest record and the current position are in the same time period: and (3) obtaining position range information from the step seven, obtaining a start-stop time period of early warning set by the monitoring object in early warning threshold calculation through the range information, judging whether the 2 records are in the start-stop time period, if so, entering the step fourteen, otherwise, entering the step fifteen.
Step fourteen, duration = current time-earliest recorded time: in the same time period class, the duration obtained by calculating the difference value from 2 time points is the duration of the monitored object until the present time. After completion, step sixteen is entered.
Fifteen steps: duration = current time-current time period start time: in order to avoid false early warning, when the phenomenon of crossing time periods is processed, the difference value between the starting time and the current time of the expiration time period is adopted as the duration of the monitored object in the new time period. For example, if the monitored subject is at rest at home from 20 pm 8 month 15 to 9 pm 8 month 16, the duration of residence calculated previously is 13 hours, but in practice according to the new method the person resides only 1 hour today. By adopting the method, false early warning conditions caused by the previous method can be effectively avoided, so that early warning accuracy is ensured. After completion, step sixteen is entered.
Sixthly, judging whether the duration is greater than an early warning threshold value: and comparing the calculated duration with an early warning threshold corresponding to the current range of the monitored object. If the duration is longer than the threshold, executing the step 17 to perform early warning processing; otherwise, the duration is smaller, the early warning is not required to be triggered, the current record is still required to be stored, and the step nine is carried out for subsequent processing.
Seventeenth step, early warning notification: if the duration is longer than the early warning threshold, an early warning event is formed and early warning information is notified to the responsible party of the village. The village principal can search the nearest gridding member or village people according to the position information of the monitored object, and request the village principal to go to the current monitored position for checking and assisting so as to ensure the effective transmission of the early warning information and take corresponding actions. After the completion, step eight is entered, the current record is marked as an identification which does not participate in the calculation of the subsequent residence time length, and the next calculation of the continuous residence time length is waited.
Corresponding to the embodiment of the method, the invention also provides an early warning system for the aged in the digital village, which comprises the following steps:
a first calculation module: a historical data for collecting the old person in rural area continuously stay in daytime, form first dataset, construct old person's stay duration according to first dataset and be b 0 Probability density functions of (2);
a second calculation module: the method comprises the steps of screening data which are continuously motionless due to falling from a first data set, forming a second data set, and constructing the residence duration of b under the condition that the old people fall accidentally according to the second data set 0 Probability density functions of (2);
probability statistics module: the method comprises the steps of determining influence factors which influence the probability of accidental falls of old people, inquiring a historical database according to the influence factors, and counting the probability of accidental falls of different old people;
a threshold calculating module: for a residence duration of b based on elderly people 0 The residence duration is b under the condition that the elderly fall accidentally 0 The probability density function of (2) and the probability of accidental falling of different aged people are combined with Bayesian formulas to construct early warning time length error conditions of the aged people, the minimum duration time meeting the early warning time length error conditions is calculated, and the minimum duration time is taken as the counterThe optimal early warning threshold value of the old people;
fall early warning module: the method is used for carrying out accidental fall pre-warning on the old people based on the optimal pre-warning threshold value.
The system embodiments and the method embodiments are in one-to-one correspondence, and the brief description of the system embodiments is just to refer to the method embodiments.
The invention also discloses an electronic device, comprising: at least one processor, at least one memory, a communication interface, and a bus; the processor, the memory and the communication interface complete communication with each other through the bus; the memory stores program instructions executable by the processor that the processor invokes to implement the aforementioned methods of the present invention.
The invention also discloses a computer readable storage medium storing computer instructions for causing a computer to implement all or part of the steps of the methods of the embodiments of the invention. The storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, i.e., may be distributed over a plurality of network elements. One of ordinary skill in the art may select some or all of the modules according to actual needs without performing any inventive effort to achieve the objectives of the present embodiment.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (10)
1. A method for early warning of endowment in a digital country, the method comprising:
collecting historical data of the aged in the rural area, which is continuously resided in the daytime, forming a first data set, and constructing the aged resident duration of b according to the first data set 0 Probability density functions of (2);
screening data which are continuously motionless due to falling from the first data set to form a second data set, and constructing the residence duration of b under the condition that the elderly fall accidentally according to the second data set 0 Probability density functions of (2);
determining influence factors influencing the probability of accidental falls of the old people, inquiring a historical database according to the influence factors, and counting the probability of accidental falls of different old people; the influencing factors include sex, age and/or disease; the historical database is a historical database of a medicine or insurance company, and the historical database stores the fall statistical data of the old with different sexes, ages and/or diseases; according to influence factor inquiry history database, the probability of different old people unexpected falls down specifically includes: inquiring a historical database of a medicine or insurance company according to the gender, age and/or disease information to obtain the probability P (A) of accidental falls of the old people with different sexes, ages and/or diseases;
based on the old people resident duration of b 0 The residence duration is b under the condition that the elderly fall accidentally 0 The probability density function of the early warning time length error condition of each old person is constructed by combining a Bayesian formula, the minimum duration time length meeting the early warning time length error condition is calculated, and the minimum duration time length is taken as the optimal early warning threshold value of the corresponding old person;
and analyzing the moving track of the old people, monitoring the duration of continuous residence in each area, and carrying out accidental fall pre-warning on the old people based on the optimal pre-warning threshold.
2. The method of claim 1, wherein the content of the history data includes an elderly person identity, a duration of immobility reason, and a duration of immobility.
3. The method of claim 2, wherein the constructing the old people resident duration from the first data set is b 0 Specifically, the probability density function of (1) includes:
assuming event B represents an elderly person residing in a certain area for a time greater than a preset time period, calculating the expected μ of the first dataset 2 Sum of variances sigma 2 Constructing the residence duration of the old person as b 0 Probability density function of (c):
wherein x represents a time period, P (B<b 0 ) Indicating that the old people stay for a duration of time b 0 Is a probability of (2).
4. The method for early warning of aged people in digital village according to claim 3, wherein the residence duration is b under the condition that the aged people fall accidentally according to the second data set 0 Specifically, the probability density function of (1) includes:
assuming event A represents an accidental fall of the elderly, the expected μ for the second data set is calculated 1 Sum of variances sigma 1 The residence duration is b under the condition that the elderly fall accidentally 0 The probability density function of (2) is:
where x represents the duration, P ((B)<b 0 ) I A) indicates that the residence duration is b under the condition that the elderly fall accidentally 0 Is a probability of (2).
5. The method for early warning of endowment in a digital country according to claim 4, wherein the early warning duration error condition is:
|P(A)P((B<b 0 )|A)-P 0 P(B<b 0 )|≤△E
wherein ΔE is a pre-configured error threshold, P 0 And P (A) is the corresponding probability of accidental falling of the old people for the preset early warning probability.
6. The method for early warning of aged people in digital village according to claim 1, wherein said calculating the minimum duration that satisfies the early warning duration error condition specifically comprises:
setting initial time length of starting circulation, maximum time length of finishing circulation and increment time length dt of every circulation, and making b 0 ＝b 0 +dt, cyclically judging current duration b 0 Whether the early warning duration error condition is met, and once the early warning duration error condition is met, b is the moment 0 The minimum duration meeting the error condition of the early warning duration is obtained.
7. The method for early warning of aged people in digital village according to claim 6, wherein if the minimum duration satisfying the error condition of the early warning duration is not calculated until the end of the cycle, searching the duration closest to the early warning probability as the optimal early warning threshold in the time range from the initial duration of the start of the cycle to the maximum duration of the end of the cycle.
8. An aged-giving pre-warning system in a digital country, the system comprising:
a first calculation module: a historical data for collecting the old person in rural area continuously stay in daytime, form first dataset, construct old person's stay duration according to first dataset and be b 0 Probability density functions of (2);
a second calculation module: the method comprises the steps of screening data which are continuously motionless due to falling from a first data set, forming a second data set, and constructing the residence duration of b under the condition that the old people fall accidentally according to the second data set 0 Probability density functions of (2);
probability statistics module: the method comprises the steps of determining influence factors which influence the probability of accidental falls of old people, inquiring a historical database according to the influence factors, and counting the probability of accidental falls of different old people; the influencing factors include sex, age and/or disease; the historical database is a historical database of a medicine or insurance company, and the historical database stores the fall statistical data of the old with different sexes, ages and/or diseases; according to influence factor inquiry history database, the probability of different old people unexpected falls down specifically includes: inquiring a historical database of a medicine or insurance company according to the gender, age and/or disease information to obtain the probability P (A) of accidental falls of the old people with different sexes, ages and/or diseases; a threshold calculating module: for a residence duration of b based on elderly people 0 The residence duration is b under the condition that the elderly fall accidentally 0 The probability density function of the early warning time length error condition of each old person is constructed by combining a Bayesian formula, the minimum duration time length meeting the early warning time length error condition is calculated, and the minimum duration time length is taken as the optimal early warning threshold value of the corresponding old person;
fall early warning module: the method is used for carrying out accidental fall pre-warning on the old people based on the optimal pre-warning threshold value.
9. An electronic device, comprising: at least one processor, at least one memory, a communication interface, and a bus;
the processor, the memory and the communication interface complete communication with each other through the bus;
the memory stores program instructions executable by the processor, the processor invoking the program instructions to implement the method of any of claims 1-7.
10. A computer readable storage medium storing computer instructions for causing a computer to implement the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311351764.0A CN117373204B (en) | 2023-10-17 | 2023-10-17 | Early warning method and system for aged people in digital village |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311351764.0A CN117373204B (en) | 2023-10-17 | 2023-10-17 | Early warning method and system for aged people in digital village |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117373204A CN117373204A (en) | 2024-01-09 |
| CN117373204B true CN117373204B (en) | 2024-03-22 |
Family
ID=89397863
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311351764.0A Active CN117373204B (en) | 2023-10-17 | 2023-10-17 | Early warning method and system for aged people in digital village |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117373204B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107145878A (en) * | 2017-06-01 | 2017-09-08 | 重庆邮电大学 | Old man's anomaly detection method based on deep learning |
| CN113096792A (en) * | 2021-04-01 | 2021-07-09 | 宁波伟吉电力科技有限公司 | Intelligent health monitoring and early warning method and system based on machine learning |
| CN116095602A (en) * | 2022-12-22 | 2023-05-09 | 中电信数智科技有限公司 | Old man safety caring method based on telecommunication position data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10319209B2 (en) * | 2016-06-03 | 2019-06-11 | John Carlton-Foss | Method and system for motion analysis and fall prevention |
-
2023
- 2023-10-17 CN CN202311351764.0A patent/CN117373204B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107145878A (en) * | 2017-06-01 | 2017-09-08 | 重庆邮电大学 | Old man's anomaly detection method based on deep learning |
| CN113096792A (en) * | 2021-04-01 | 2021-07-09 | 宁波伟吉电力科技有限公司 | Intelligent health monitoring and early warning method and system based on machine learning |
| CN116095602A (en) * | 2022-12-22 | 2023-05-09 | 中电信数智科技有限公司 | Old man safety caring method based on telecommunication position data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117373204A (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110349372B (en) | Method and device for early warning abnormal activities of family aged care personnel | |
| CN106777954A (en) | The intelligent guarding system and method for a kind of Empty nest elderly health | |
| CN105662384B (en) | Method and device for monitoring whether human heart rate is normal | |
| CN105125221A (en) | System and method for cloud service real-time falling-down detection | |
| CN104462744A (en) | Data quality control method suitable for cardiovascular remote monitoring system | |
| CN113555136B (en) | Five-in-one comprehensive medical and nutritional system based on medical and industrial fusion technology | |
| CN108460957A (en) | A kind of the elder's health group monitoring warning system and method | |
| CN116831523A (en) | Alarm method, device, equipment and storage medium based on health monitoring | |
| CN114694842A (en) | Pet health monitoring method and device, computer equipment and readable storage medium | |
| CN115662631A (en) | AI intelligence discrimination-based nursing home management system | |
| CN115343684A (en) | Fall detection method and system based on millimeter wave radar | |
| CN112102957A (en) | Epidemic disease early warning method and early warning system thereof | |
| CN114098655A (en) | Intelligent sleep risk monitoring method and system | |
| CN117877734A (en) | Mental disorder patient risk level judging system | |
| CN106559486B (en) | A kind of endowment nurse method and system based on big data | |
| CN109119172A (en) | A kind of human body behavioral value method based on ant colony algorithm | |
| CN117373204B (en) | Early warning method and system for aged people in digital village | |
| CN106606348A (en) | System for monitoring life safety, health and living safety of the elderly based on mobile communication | |
| CN113241199A (en) | Smart home old-age-care health management system | |
| CN116976834B (en) | Intelligent endowment service platform based on SaaS cloud service | |
| CN116269266B (en) | AI-based old people health monitoring method and system | |
| CN110852520A (en) | Block chain based nursing method and device | |
| CN211827514U (en) | Fall alarm device and system | |
| CN113671489A (en) | State reminding method and device, electronic equipment and computer readable storage medium | |
| CN114334109A (en) | Monitoring method, device, equipment and storage medium for emergency green area |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |