CN106203813A - Life of elderly person self-care ability Quantitative Calculation Method - Google Patents
Life of elderly person self-care ability Quantitative Calculation Method Download PDFInfo
- Publication number
- CN106203813A CN106203813A CN201610522157.XA CN201610522157A CN106203813A CN 106203813 A CN106203813 A CN 106203813A CN 201610522157 A CN201610522157 A CN 201610522157A CN 106203813 A CN106203813 A CN 106203813A
- Authority
- CN
- China
- Prior art keywords
- care ability
- self
- quantized value
- self care
- attribute
- 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.)
- Pending
Links
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
Abstract
The present invention relates to a kind of life of elderly person self-care ability Quantitative Calculation Method, belong to field of biomedicine technology.First self care ability is divided into self care ability baseline quantized value and self care ability state quantized value by the present invention, select self care ability Fundamentals by list of references and calculate self care ability baseline quantized value, the application Boruta algorithm quantified property influence degree to self care ability, select self care ability key influence factor, use Logic Regression Models, the probability of taking care of oneself that prediction is individual, so obtain individual relative take care of oneself probability and percentage turns to state quantized value of taking care of oneself;The method COMPREHENSIVE CALCULATING self care ability quantized value of application Weighted Fusion.Realize the evaluation to individual self care ability and feed back with centesimal form, individual personalized feature can be embodied, reach the purpose of careful division crowd, providing instruction for individual personalized the intervention.
Description
Technical field
The present invention relates to a kind of life of elderly person self-care ability Quantitative Calculation Method.Say from the angle of application scenarios, belong to
Field of biomedicine technology;From the point of view of the angle that technology realizes, also belong to computer science and Bioinformatics technical field.
Background technology
Along with the increase of China's aging population quantity, China has been enter into aging society.Social pension problem also just becomes
The huge challenge faced for country.Self care ability is the most basic ability that old people ensures to live on one's own life.Once take care of oneself energy
Power is lost, and the life of old people needs exist for the intervention of external force.This brings burden can to undoubtedly family or even society.To this end, it is right
Self care ability is furtherd investigate, and weighs and describe the self care ability of old people, contributes to finding in advance and using
Reasonably means are avoided or delay the forfeiture of self care ability, are possible not only to improve old people's quality of life in old age, right
In country and society, also there is important medical economics meaning.
Self care ability is generally divided into daily life self-care ability and instrumental self care ability two kinds.Daily life
The ability that the daily basic livings such as self-care ability has been primarily referred to as having a meal, wears the clothes, goes to toilet, modifies, indoor activity are movable, it
Reflect the health level of the cognitive function of old people's somatic function and lowest level.It is that instrumental is raw in addition with an index
Self-care ability alive, it is emphasised that utilize or complete by instrument the ability of life activity in Sheng Huo, including doing housework, laundry clothes,
Manage money matters, do shopping, ride, take medicine, the activity such as make a phone call, the health level of the individual higher level cognitive function of its reflection.These are two years old
The measurement planting self care ability the most all occurs with the form of scale, and scale is a kind of special questionnaire, in questionnaire
Project can distribute different weight, same project can distribute again different score option, comprehensive after obtain final energy of taking care of oneself
Power describes.
Basic daily life active ability was proposed by Katz in 1963, comprised 6 basic functions: have a bath, wear the clothes, on
Lavatory, indoor activity, possessiveness, have a meal.Primarily to the description mankind are by the primary ability gradually obtained childhood, to recognizing
Know that Capability Requirement is the highest.Along with the proposition of basic living self-care ability, the multiple scale about basic living self-care ability is the most just
Appearance as emerging rapidly in large numbersBamboo shoots after a spring rain.
The purpose that these scales build can be divided into 3 classes: describes, it was predicted that and assessment.Descriptive scale primarily to
Presenting the individual health at current time, its result is used for the contrast with other people.Common descriptive scale has ADL
Index, PULSES Profile, Barthel Index.These scales individuality can be divided into self care ability impaired and
The crowd that self care ability is intact, can provide the order of severity that self care ability is impaired simultaneously.Predictability scale be for
Setting a baseline criteria to individuality, essence is exactly to predict following possible state.The most representational scale is exactly
Klein-Bell ADLs, it can predict that crowd is to be placed in community or health medical treatment mechanism accurately.Law& simultaneously
Usher applies the research in department of pediatrics to demonstrate its effectiveness about Klein-Bell scale.Assessment property scale is to supervise at any time
Survey individual state and evaluate corresponding individual change in terms of self care ability.Common assessment scale has ADL
Index, Barthel Index, Donaldson ADL assesses scale, and Kenny takes care of oneself and assesses scale, and LORS-II assesses scale
(Revised Level of Rehabilitation Scale)。
Basic living self-care ability is that old people can take care of oneself the movable condition of basic living, if but live on one's own life, need
Activity that will be more complicated, such as cooks, managerial finance etc..Therefore to the ability that research old people lives on one's own life, instrumental
Self care ability (IADL) rises also with the development of ADL.
Lawton IADL in common instrumental self care ability scale, IDDD, Bristol ADL, DAD, B-ADL,
ADLQ, ADCS-ADL etc. belong to assessment property scale, and Blessed DS, CSADL, ADL-IS, ADCS-ADL-Sev etc. belong to description
Property scale, ADL-PI scale belongs to predictability scale.For comparing ADL, the research of IADL is more absorbed in and focuses mostly on
(58.4%) in assessment property scale, for evaluating the situation of change of individuality;Scale about predictability is the most relatively fewer
(8.3%);Descriptive scale then rather moderate (33.3%).
To sum up analyze, the form of equal employing activity scales in numerous researchs of self care ability, by observing or adjusting
The performance looking into experimenter's specific activities gives corresponding quantized value.No matter scale project is how many for this mode, each project
Dividing how many ranks, analysis result is that classification is discrete eventually, also arises that the individuality of different situations obtains identical amount
Change value, crowd is divided by its essence the most qualitatively;Simultaneously in reality is tested, great majority can preferably complete per capita
All activities.Crowd's result can be caused excessively to concentrate based on above 2, cause self care ability analysis result coarse size, difficult
To embody individual individualized feature, it is unfavorable for individuality is carried out and intervenes targetedly or physical therapy measures, it is difficult to reach to delay
The purpose declining or maintaining existing self care ability of individual self care ability.
Summary of the invention
It is an object of the invention to: be difficult to carry for individual character for current life of elderly person self-care ability analysis result coarse size
For the problem of service, a kind of life of elderly person self-care ability quantitative analysis method is proposed.Reach multi-layer, comment targetedly
Determine the purpose of the individual self care ability of old people.
The design principle of the present invention is: analyze current research obtain self care ability research field generally acknowledge basic because of
Element, calculates self care ability baseline quantized value.Use a kind of self care ability based on boruta algorithm based on this
Key influence factor extracting method, selects self care ability key influence factor.Based on crucial effect influence factor, structure is patrolled
Volume regression model, it was predicted that individuality is taken care of oneself probability, so calculate normalization self-care probability and build acquisition continuous print life from
Reason state quantized value;Finally apply the method comprehensive self care ability baseline quantized value of Weighted Fusion and quantity of state of taking care of oneself
Change value obtains continuous print self care ability quantized value.The present invention can provide a centesimal quantization for individual state
Value, fully demonstrates the individualized feature of individuality, reaches the purpose that refinement crowd divides.
The technical scheme is that and be achieved by the steps of:
Step 1, analyzes and screens self care ability Fundamentals, and after obtaining cleaning, data to be analyzed constitute data set,
Calculating self care ability baseline quantized value, and demarcate state of taking care of oneself, concrete methods of realizing is:
Step 1.1, the achievement in research more admitted in comprehensive analysis self care ability research field is to energy of taking care of oneself
The description attribute of power, selects its common factor attribute as the Fundamentals of self care ability.
Step 1.2, after obtaining cleaning, data to be analyzed constitute data set, and wherein every data comprises m dimension and takes care of oneself energy
Power Fundamentals, and M-m dimension self care ability influence factor, with influence factor as column vector, the attribute that different samples are corresponding
Value is row vector, builds data set S and is labeled as [SNM]。
Step 1.3, m based on data tie up self care ability Fundamentals, calculate self care ability baseline quantized value,
Computing formula is:
Wherein, sbiIt is i-th sample self care ability baseline quantized value,Represent the dimension life of i-th sample jth
Self-care ability Fundamentals.
Step 1.4, state of taking care of oneself based on self care ability baseline quantized value nominal data, self care ability
Quantized value full marks represent m kind basic activity ability the most intact (being labeled as 1), under other quantized values then illustrate that mobility is
Fall (being demarcated as 0), it is thus achieved that data Sl after demarcation.
Step 2, obtains data set Sl to step 1, applies boruta algorithm, and calculating often dimension affects attribute to energy of taking care of oneself
The influence degree of power, combines attribute acquisition difficulty based on this quantization effect degree and expertise selects self care ability crucial
Influence factor, concrete methods of realizing is:
Step 2.1, setup parameter, for data set Sl, clone random p group attribute as copy attribute, and it is carried out
Reset, to eliminate the dependency of itself and corresponding attribute.Recombination data collection Sl '.
Step 2.2, based on data set Sl ', builds random forest training, and according to setup parameter, training builds a classification
Regression tree, calculates the mean square sesidual obtaining out of band data corresponding to each tree, is designated as: MSEn, wherein n ∈ 1,2 ... num, thus
Original out of band data mean square sesidual vector [MSE can be obtained for n tree1, MSE2... MSEnum]。
Step 2.3, the residual error [MSE obtained based on step 2.21, MSE2... MSEnum] corresponding with corresponding property calculation
Z value, determines the copy attribute that Z value is maximum, the attribute that labelling is bigger than its value simultaneously, and as important attribute, and correspondence is less than its Z value
Attribute be then labeled as insignificant attribute and from data set delete.Finally delete all copy attributes.
Step 2.4, repeats above step 2.1 to step 2.3, until it reaches the end condition of setting.
Step 2.5, based on the attribute that Importance of Attributes sequence is forward, and deletes redundant attributes with reference to expertise, it is considered to
Attribute acquisition difficulty deletes part attribute, it is thus achieved that self care ability key influence factor.
Step 3, based on self care ability key influence factor, construction logic regression model, calculates individuality and takes care of oneself
Probability, calculates normalization self-care probability and builds self care ability state quantized value, and concrete methods of realizing is:
Step 3.1, is standardized the property value of self care ability key influence factor, and computational methods are:WhereinIt is that i-th sample l ties up key influence factor original value,It it is i-th sample l dimension
The standardized value of key influence factor, mean (xl) and sd (xl) then be respectively sample l dimension key influence factor average and
Standard deviation.
Step 3.2, construction logic regression model, the Logic Regression Models obtained based on training, with individual normalized data,
Calculate individuality to take care of oneself probability Pi。
Step 3.3, based on individual self-care probability, calculates self care ability state quantized value, and computational methods are:
Wherein, StiIt is state quantized value of taking care of oneself, min (P) and max (P) and is then respectively the minima of self-care probability
And maximum.
Step 4, the method for application Weighted Fusion, comprehensive self care ability baseline quantized value and state of taking care of oneself quantify
Value, calculates and obtains self care ability quantized value, and concrete methods of realizing is:
Step 4.1, calculates mean square with self care ability baseline quantized value sb and the state quantized value st that takes care of oneself respectively
Difference, computational methods:
The wherein the most corresponding self care ability baseline quantized value of mean (Sb) and mean (St) and self care ability shape
The average of state quantized value, N is sample size.
Step 4.2, the mean square deviation obtained based on step 4.1, calculate self care ability baseline quantized value and take care of oneself
Relative entropy λ of capability state1, λ2, computational methods are:
Step 4.3, based on relative entropy, as self care ability baseline quantized value and self care ability quantity of state
The weight of change value, Weighted Fusion obtains self care ability quantized value Sf, and percentage computational methods are:
Sf=λ1*Sb+λ2*St
Beneficial effect
Compared to ADL isodose chart methods of marking, the present invention propose based on boruta algorithm and the life of logistic regression algorithm
Self-care ability Quantitative Calculation Method alive, calculates continuous print self care ability by logistic regression according to personal feature and quantifies
Value, can embody individual individualized feature, and the crowd reaching more careful divides effect, instructs for individual personalized intervention and arranges
Execute and provide instruction.
Compared to IADL isodose chart method, the method that this patent proposes, boruta algorithm algorithm is used to quantify attribute pair
The influence degree of self care ability, based on this and combine expertise and attribute acquisition difficulty, is extracted self care ability
Key influence factor, is effectively reduced the attribute that self care ability is analyzed, reduces time and the cost consumption of assessment, tool
There are wider array of use scene, great use value.
Accompanying drawing explanation
Fig. 1 is that the self care ability key influence factor that the present invention proposes extracts schematic diagram;
Fig. 2 is the life of elderly person self-care ability Quantitative Calculation Method schematic diagram that the present invention proposes;
Fig. 3 is in detailed description of the invention, the attribute attribute to first 10 of self care ability importance degree ranking;
Fig. 4 is in detailed description of the invention, final self care ability quantized value scattergram.
Detailed description of the invention
In order to better illustrate objects and advantages of the present invention, below in conjunction with the accompanying drawings with the embodiment reality to the inventive method
The mode of executing is described in further details.
The most all tests all complete on same computer, and concrete configuration is: Intel double-core CPU (dominant frequency
2.53G), 4G internal memory, Windows 7 operating system.
Test uses Data Source in combining 13 hospital's investigation numbers of national 7 provinces and cities in 2011~2012 Nian Jian Beijing Hospitals
According to, questionnaire is kept healthy by ministry of Health of China sector fund the elder's health comprehensive assessment seminar and Chinese Aged and disease is prevented
Control alliance's co-design, including individual's essential information, Body health assessment, somatic function assessment, life-form structure and social function
Assessment, cognitive function, medical conditions, mental health, the assessment of anergy grade, auxiliary examination, gather data totally 482 dimension, comprise
9503 data.
First link
This link uses data source original data source.Describe self care ability baseline quantized value in detail and calculate process.Tool
It is as follows that body implements step:
Step 1.1, selects the self care ability analysis and research Berthel Index scale more admitted of field and the world
Function classification (being called for short ICF), as reference, selects the common factor analyzing attribute of self care ability in the two scale, it is thus achieved that raw
Self-care ability 5 of living ties up Fundamentals: has a meal, wear the clothes, go to toilet, modify, have a bath.
Step 1.2, carries out vacancy value deletion and attribute primary election to initial data, final select to comprise individual essential information,
Body health assessment, somatic function assessment, mental health, cognitive function, 78 dimension attributes of 6 big classes of anergy grade assessment table,
4837 data.
Step 1.3, the data obtained based on step 1.2, the 5 dimension Fundamentals obtained with step 1.1 calculate the life of data
Live self-care ability baseline quantized value Sb.
Step 1.4, based on self care ability baseline quantized value, according to rule shown in table 1, marks individual data items
Fixed.
Table 1 data scaling rule
Second link
This link uses data source to be the data source that a upper link obtains.Describe in detail self care ability crucial effect because of
Element extraction process.It is embodied as step as follows:
Step 2.1, replicates the data of 5 groups of variablees, builds 5 copy attributes, and resets copy attribute, with original
Data sets obtains growth data collection.
Step 2.2, based on growth data collection, builds random forest grader, and according to setup parameter, training builds one point
Class regression tree, calculates the mean square sesidual obtaining out of band data corresponding to each tree, is designated as: MSEn, wherein n ∈ 1,2 ... num, by
This can obtain original out of band data mean square sesidual vector [MSE for m tree1, MSE2... MSEnum]。
Step 2.3, the residual error [MSE obtained based on step 2.21, MSE2... MSEnum] corresponding with corresponding property calculation
Z value, determines the copy attribute that Z value is maximum, the attribute that labelling is bigger than its value simultaneously, and as important attribute, and correspondence is less than its Z value
Attribute be then labeled as insignificant attribute and from data set delete.Finally delete all copy attributes.
Step 2.4, repeats step 2.1 to 2.3 until end condition, it is contemplated that the collection difficulty of attribute, in conjunction with expert's warp
Test, delete and gather the attribute that the big part Attribute Significance of difficulty is big, add simultaneously expert clinical experience think the most important and
The attribute that Attribute Significance is relatively low.
By experiment, before Attribute Significance ranking, the attribute of 10 is as shown in table 2 below.The final existing residence, the most residual of selecting
Barrier, leg speed, job specification, age, sex 7 dimension attribute.
Table 2 Attribute Significance ranking results
Three link model
This link uses data source to be the data source that a upper link obtains.Detailed description take care of oneself state quantized value calculate
Process.It is embodied as step as follows:
Step 3.1, is standardized the self care ability key influence factor in data.
Step 3.2, with standardization self care ability key influence factor as independent variable, state of taking care of oneself calibration result
For dependent variable, self care ability key influence factor is independent variable, construction logic regression model.Calculate and the life of recording individual
Self-care probability P aliveik。
Step 3.5, is calculated and is obtained individuality by the take care of oneself percentageization of probability of normalization and take care of oneself state quantized value
St。
4th link
This link uses data source to be the data source that a upper link obtains.Detailed description quantized value of taking care of oneself calculated
Journey.It is embodied as step as follows:
Step 4.1, based on self care ability baseline quantized value Sb and the state quantized value St that takes care of oneself, calculates mean square deviation
Var (Sb)=1.06, Var (St)=9.67.
Step 4.2, calculates relative entropy λ1=0.094, λ2=0.906.
Step 4.3, calculates self care ability quantized value by weighted sum, and final self care ability quantized value is distributed
As shown in Figure 4.
5th link
This link, by contrasting self care ability quantum chemical method result and the tradition ADL of the present invention, stresses
The inventive method can be careful crowd is divided.
Use same data to be respectively adopted ADL method and the inventive method is analyzed.Use division rate as evaluation
Two kinds of methods are contrasted by index, and comparing result is as shown in table 3.
Table 3 self care ability quantum chemical method Comparative result
It can be seen that crowd can only be divided into 11 groups by ADL score in table 3, especially self care ability is in the best state
Classification group have 4595 people, here it is no matter how the point of contact of ADL score divides, these people can be divided into same class people.
And context of methods corresponding this group crowd can be divided into 4374 category division rates be 95.19, in other words, closed by selection
The point of contact of suitable self care ability quantized value, can necessarily be divided into ADL score same category of people and be divided into the most not
More than 4374 class groups.And in other people ADL classification crowd, the self care ability quantized value that context of methods obtains can be by
ADL must be divided into congener group and carry out the division of 100%.Comprehensive above analysis, ADL can be difficult to divide by context of methods
Crowd carry out more careful division.
The present invention is directed to current life of elderly person self-care ability analysis result coarse size be difficult to provide service for individual character
Problem, it is proposed that a kind of life of elderly person self-care ability Quantitative Calculation Method.By self care ability quantum chemical method experiment card
Bright, individual self care ability can be given by the method with centesimal form, can divide crowd meticulously, be provided simultaneously with
Less analysis attribute and less attribute acquisition difficulty, for the popularization and application letter of life of elderly person self-care ability quantum chemical method
Single, great use value.The method can be as theoretical research simultaneously, as the skill of other old people's chronic disease quantum chemical method
Art and method basis.
Claims (4)
1. a life of elderly person self-care ability Quantitative Calculation Method, it is characterised in that said method comprising the steps of:
Step 1, analyzes and screens self care ability Fundamentals, and after obtaining cleaning, data to be analyzed constitute data set, calculate
Self care ability baseline quantized value, and demarcate state of taking care of oneself;
Step 2, obtains data set Sl to step 1, applies boruta algorithm, and calculating often dimension affects attribute to self care ability
Influence degree, combines attribute acquisition difficulty based on this quantization effect degree and expertise selects self care ability crucial effect
Factor;
Step 3, based on self care ability key influence factor, construction logic regression model, calculate individuality and take care of oneself probability,
Calculate normalization self-care probability and build self care ability state quantized value;
Step 4, the method for application Weighted Fusion, comprehensive self care ability baseline quantized value and state quantized value of taking care of oneself,
Calculate and obtain self care ability quantized value.
Method the most according to claim 1, it is characterised in that the step that described self care ability key influence factor extracts
Suddenly specifically include:
Step 2.1, step 2.1, setup parameter, for data set Sl, clone random p group attribute as copy attribute, and to it
Reset, to eliminate the dependency of itself and corresponding attribute.Recombination data collection Sl ';
Step 2.2, based on data set Sl ', builds random forest training, and according to setup parameter, training builds a classification and returns
Tree, calculates the mean square sesidual obtaining out of band data corresponding to each tree, is designated as: MSEn, wherein n ∈ 1,2 ... num is the most right
Original out of band data mean square sesidual vector [MSE can be obtained in n tree1, MSE2... MSEnum]:
Step 2.3, the residual error [MSE obtained based on step 2.21, MSE2... MSEnum] with the corresponding corresponding Z of property calculation
Value, determines the copy attribute that Z value is maximum, the attribute that labelling is bigger than its value simultaneously, and as important attribute, and correspondence is less than its Z value
Attribute be then labeled as insignificant attribute and from data set delete.Finally delete all copy attributes;
Step 2.4, repeats above step 2.1 to step 2.3, until it reaches the end condition of setting;
Step 2.5, based on the attribute that Importance of Attributes sequence is forward, deletes redundant attributes with reference to expertise, it is considered to attribute is adopted
Collection difficulty deletes part attribute, it is thus achieved that self care ability key influence factor.
Method the most according to claim 1, it is characterised in that the step that described self care ability state quantized value calculates
Specifically include:
Step 3.1, is standardized the property value of self care ability key influence factor, and computational methods are:WhereinIt is that i-th sample l ties up key influence factor original value,It it is i-th sample l dimension
The standardized value of key influence factor, mean (xl) and sd (xl) then be respectively sample l dimension key influence factor average and
Standard deviation;
Step 3.2, construction logic regression model, the Logic Regression Models obtained based on training, with individual normalized data, calculate
Individuality is taken care of oneself probability Pi;
Step 3.3, based on individual self-care probability, calculates self care ability state quantized value, and computational methods are:
Wherein, StiIt is state quantized value of taking care of oneself, min (P) and max (P) and is then respectively the minima and of self-care probability
Big value.
Method the most according to claim 1, it is characterised in that the step of described self care ability quantized value COMPREHENSIVE CALCULATING
Specifically include:
Step 4.1, calculates mean square deviation respectively with self care ability baseline quantized value Sb and the state quantized value St that takes care of oneself, meter
Calculation method:
The wherein the most corresponding self care ability baseline quantized value of mean (Sb) and mean (St) and self care ability quantity of state
The average of change value, N is sample size;
Step 4.2, the mean square deviation obtained based on step 4.1, calculate self care ability baseline quantized value and self care ability
Relative entropy λ of state1, λ2, computational methods are:
Step 4.3, based on relative entropy, as self care ability baseline quantized value and self care ability state quantized value
Weight, Weighted Fusion obtain self care ability quantized value Sf, percentage computational methods are:
Sf=λ1*Sb+λ2*St。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610522157.XA CN106203813A (en) | 2016-07-05 | 2016-07-05 | Life of elderly person self-care ability Quantitative Calculation Method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610522157.XA CN106203813A (en) | 2016-07-05 | 2016-07-05 | Life of elderly person self-care ability Quantitative Calculation Method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106203813A true CN106203813A (en) | 2016-12-07 |
Family
ID=57465231
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610522157.XA Pending CN106203813A (en) | 2016-07-05 | 2016-07-05 | Life of elderly person self-care ability Quantitative Calculation Method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106203813A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107049251A (en) * | 2017-03-28 | 2017-08-18 | 浙江大学台州研究院 | Upper extremity exercise control ability assessment system |
CN107169284A (en) * | 2017-05-12 | 2017-09-15 | 北京理工大学 | A kind of biomedical determinant attribute system of selection |
CN108172298A (en) * | 2018-01-30 | 2018-06-15 | 成都信息工程大学 | A kind of data preprocessing method of mental scale |
CN108629436A (en) * | 2017-03-15 | 2018-10-09 | 阿里巴巴集团控股有限公司 | A kind of method and electronic equipment of estimation warehouse picking ability |
CN108922621A (en) * | 2018-06-26 | 2018-11-30 | 泰康保险集团股份有限公司 | A kind of appraisal procedure and device of the grade that disables |
CN109598354A (en) * | 2018-09-11 | 2019-04-09 | 李涛 | A kind of ship pressure gauge buret reason classification method |
CN109801710A (en) * | 2018-12-14 | 2019-05-24 | 平安科技(深圳)有限公司 | Capacity determination method and device, terminal and computer readable storage medium |
CN113205887A (en) * | 2021-05-28 | 2021-08-03 | 武汉玖燊科技有限公司 | Big data and artificial intelligence based intelligent aged-care user full-period tracking analysis method, system and storage medium |
-
2016
- 2016-07-05 CN CN201610522157.XA patent/CN106203813A/en active Pending
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108629436A (en) * | 2017-03-15 | 2018-10-09 | 阿里巴巴集团控股有限公司 | A kind of method and electronic equipment of estimation warehouse picking ability |
CN108629436B (en) * | 2017-03-15 | 2022-04-12 | 阿里巴巴集团控股有限公司 | Method and electronic equipment for estimating warehouse goods picking capacity |
CN107049251A (en) * | 2017-03-28 | 2017-08-18 | 浙江大学台州研究院 | Upper extremity exercise control ability assessment system |
CN107169284A (en) * | 2017-05-12 | 2017-09-15 | 北京理工大学 | A kind of biomedical determinant attribute system of selection |
CN108172298A (en) * | 2018-01-30 | 2018-06-15 | 成都信息工程大学 | A kind of data preprocessing method of mental scale |
CN108922621A (en) * | 2018-06-26 | 2018-11-30 | 泰康保险集团股份有限公司 | A kind of appraisal procedure and device of the grade that disables |
CN109598354A (en) * | 2018-09-11 | 2019-04-09 | 李涛 | A kind of ship pressure gauge buret reason classification method |
CN109801710A (en) * | 2018-12-14 | 2019-05-24 | 平安科技(深圳)有限公司 | Capacity determination method and device, terminal and computer readable storage medium |
CN113205887A (en) * | 2021-05-28 | 2021-08-03 | 武汉玖燊科技有限公司 | Big data and artificial intelligence based intelligent aged-care user full-period tracking analysis method, system and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106203813A (en) | Life of elderly person self-care ability Quantitative Calculation Method | |
CN101916334B (en) | A kind of skin Forecasting Methodology and prognoses system thereof | |
Dlouhy et al. | Optimal matching analysis in career research: A review and some best-practice recommendations | |
Carmichael et al. | Unpaid caregiving and paid work over life-courses: Different pathways, diverging outcomes | |
CN107516110A (en) | A kind of medical question and answer Semantic Clustering method based on integrated convolutional encoding | |
Ali et al. | Big-sized trees and forest functioning: Current knowledge and future perspectives | |
Papadimitriou et al. | Is road safety management linked to road safety performance? | |
CN108197425B (en) | A kind of smart grid data resolving method based on Non-negative Matrix Factorization | |
CN105975912A (en) | Hyperspectral image nonlinearity solution blending method based on neural network | |
CN107346556A (en) | A kind of PET image reconstruction method based on block dictionary learning and sparse expression | |
CN107016260B (en) | A kind of gene regulatory network method for reconstructing based on cross-platform gene expression data | |
Mathers et al. | Structural and functional responses of macroinvertebrate assemblages to long‐term flow variability at perennial and nonperennial sites | |
Binder et al. | Design-and model-based inference for model parameters | |
CN107085661A (en) | A kind of the elderly's physical function Quantitative Calculation Method | |
Barber et al. | Reliability and predictive validity of a consensus-based risk assessment tool | |
Zhang et al. | Analyzing 2000–2010 childhood age-adjusted cancer rates in Florida: A spatial clustering approach | |
CN106407706A (en) | Boruta algorithm-based multi-level old people physical state quantization level calculation method | |
Viroli | Using factor mixture analysis to model heterogeneity, cognitive structure, and determinants of dementia: an application to the Aging, Demographics, and Memory Study | |
CN105138835A (en) | Human body composition prediction method based on physiological information entropy | |
Caputi et al. | Analyzing grids: New and traditional approaches | |
Wu et al. | An empirical study on the employment monitoring and early warning mechanism of medical graduates in universities with big data and complex computing system | |
Marbac et al. | Finite mixture model of conditional dependencies modes to cluster categorical data | |
Spoto | Formal psychological assessment theoretical and mathematical foundations | |
KR20200133505A (en) | Method and apparatus for evaluating seismic safety of structure | |
Yang et al. | Tensor-based Complex-valued Graph Neural Network for Dynamic Coupling Multimodal brain Networks |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20161207 |