CN109636451A - A kind of old-age provision model auto recommending method, device and terminal device - Google Patents
A kind of old-age provision model auto recommending method, device and terminal device Download PDFInfo
- Publication number
- CN109636451A CN109636451A CN201811457321.9A CN201811457321A CN109636451A CN 109636451 A CN109636451 A CN 109636451A CN 201811457321 A CN201811457321 A CN 201811457321A CN 109636451 A CN109636451 A CN 109636451A
- Authority
- CN
- China
- Prior art keywords
- old
- provision model
- age provision
- model
- age
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012549 training Methods 0.000 claims abstract description 63
- 238000013528 artificial neural network Methods 0.000 claims abstract description 40
- 238000010606 normalization Methods 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 20
- 238000013461 design Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 230000000644 propagated effect Effects 0.000 claims description 2
- 239000000463 material Substances 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 12
- 238000011835 investigation Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000011161 development Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 229940036051 sojourn Drugs 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention is suitable for depth learning technology field, provides a kind of old-age provision model auto recommending method, device and terminal device, comprising: obtains training dataset；Wherein, training dataset includes questionnaire answer and the old-age provision model that manually marks, using questionnaire answer as input feature vector, using the old-age provision model manually marked as output feature, BP Neural Networks model is created, BP Neural Networks model is trained according to training dataset, to obtain the automatic recommended models of old-age provision model, it obtains the characteristic value of questionnaire and inputs the automatic recommended models of old-age provision model, to obtain the automatic recommendation results of old-age provision model.The present invention according to training dataset and is trained the BP Neural Networks model by creating BP Neural Networks model, to obtain the automatic recommendation that the automatic recommended models of old-age provision model realize old-age provision model, a large amount of human and material resources and financial resources have been saved, and have improved the applicability of eligible result.
Description
Technical field
The invention belongs to depth learning technology field more particularly to a kind of old-age provision model auto recommending methods, device and end
End equipment.
Background technique
During Chinese recent decades continue to develop, endowment problem seems more and more prominent, and endowment problem is not only
One social livelihood issues urgently properly settled, at the same it is also closely bound up with socio-economic development.For this purpose, in following development
In, how thinking, which invests endowment industry, is just particularly important, it not only influences rate of return on investment, it is often more important that influences
To can build up meet different old men needed for endowment environment.
Due to age, occupation, income, education level, health status, marital status, regional disparity etc. it is a variety of because
The influence of element, there is different demands, this single endowments of traditional home tele-monitoring mode for Aged mode for old group
Mode has been unable to satisfy the endowment demand of old man's diversification, otherness.For this purpose, old-age provision model diversification be historical development must
So, old-age provision model selection is just as one of equation, and the old man in each epoch must make answer, and the answer of different times is
It is different.
In order to preferably invest endowment industry, meet the endowment demand of old man's diversification, while in order to avoid blind investment
Construction, causes unnecessary waste, and a emphasis to the following endowment industry development is needed to have the reference frame of directiveness.Mesh
Before, in order to predict the developing direction of the following endowment industry, method be substantially questionnaire by way of.
However, the method for investigating the following endowment industrial development direction by way of questionnaire has the disadvantage in that
1, this method needs to expend a large amount of human and material resources and financial resources.
2, the result that this method obtains will be only suitable for specific region and specific crowd, be difficult extensive to as province or country
Territorial scope.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of old-age provision model auto recommending method, device and terminal device, with
Solve problems of the prior art.
The first aspect of the embodiment of the present invention provides a kind of old-age provision model auto recommending method, comprising:
Obtain training dataset；Wherein, the training dataset includes questionnaire answer and the old-age provision model that manually marks；
Using the questionnaire answer as input feature vector, using the old-age provision model manually marked as output feature, creation
BP Neural Networks model；
The BP Neural Networks model is trained according to the training dataset, to obtain endowment mould
The automatic recommended models of formula；
Obtain questionnaire characteristic value simultaneously input the automatic recommended models of the old-age provision model, with obtain old-age provision model from
Dynamic recommendation results.
Optionally, special using the old-age provision model manually marked as output using the questionnaire answer as input feature vector
It levies, before creation BP Neural Networks model, comprising:
The questionnaire answer is normalized, to obtain the questionnaire answer after normalization；
The old-age provision model manually marked is normalized, to obtain the old-age provision model manually marked after normalization.
Optionally, the normalized formula includes:
Wherein, xiRepresent the value of normalization data, xminRepresent the minimum value of normalization data variation, xmaxRepresent normalizing
Change the maximum value of data variation,Data value after representing the normalization.
Optionally, BP Neural Networks model is trained according to the training dataset, is supported with obtaining
The old automatic recommended models of mode, comprising:
BP Neural Networks model is carried out according to the training dataset by error backpropagation algorithm
Training, to obtain the automatic recommended models of old-age provision model.
Optionally, the acquisition training dataset, comprising:
Obtain the type of old-age provision model；
Obtain the problem corresponding with the type of the old-age provision model；
According to the old-age provision model and the problem corresponding with the type of the old-age provision model, designs old-age provision model investigation and ask
Volume；
Obtain the questionnaire answer for the old-age provision model questionnaire and artificial mark corresponding with the questionnaire answer
Old-age provision model, as the training dataset；
Optionally, old-age provision model tune is designed according to the old-age provision model and the problem corresponding with the type of the old-age provision model
Interrogate volume, comprising:
Old-age provision model questionnaire is designed according to the old-age provision model and the problem corresponding with the type of the old-age provision model；
Obtain the confidence level and efficiency of the old-age provision model questionnaire；
If it is described it is with a low credibility be lower than default efficiency threshold in default believability threshold and/or the efficiency, root again
Old-age provision model questionnaire is designed according to the old-age provision model and the problem corresponding with the type of the old-age provision model, until described can
Reliability reaches default believability threshold and until the efficiency reaches default efficiency threshold.
The second aspect of the embodiment of the present invention provides a kind of automatic recommendation apparatus of old-age provision model, comprising:
First obtains module, for obtaining training dataset；Wherein, the training dataset includes questionnaire answer and artificial
The old-age provision model of mark；
Creation module, for using the questionnaire answer as input feature vector, using the old-age provision model manually marked as
Feature is exported, BP Neural Networks model is created；
Training module, for being instructed according to the training dataset to the BP Neural Networks model
Practice, to obtain the automatic recommended models of old-age provision model；
Second obtains module, for obtaining the characteristic value of questionnaire and inputting the automatic recommended models of the old-age provision model,
To obtain the automatic recommendation results of old-age provision model.
The third aspect of the embodiment of the present invention provides a kind of terminal device, comprising: memory, processor and is stored in
In the memory and the computer program that can run on the processor, when the processor executes the computer program
It realizes such as the step of the above method.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, realizes when the computer program is executed by processor such as the step of the above method.
The embodiment of the present invention is by creation BP Neural Networks model, according to training dataset and to described anti-
It is trained to BP network model is propagated, realizes pushing away automatically for old-age provision model to obtain the automatic recommended models of old-age provision model
It recommends, has saved a large amount of human and material resources and financial resources, and improve the applicability of eligible result.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the flow diagram for the old-age provision model auto recommending method that the embodiment of the present invention one provides；
Fig. 2 is the flow diagram of old-age provision model auto recommending method provided by Embodiment 2 of the present invention；
Fig. 3 is the flow diagram for the old-age provision model auto recommending method that the embodiment of the present invention three provides；
Fig. 4 is being trained to three layers based on BP Neural Networks model for the offer of the embodiment of the present invention three
Schematic diagram；
Fig. 5 is the flow diagram for the old-age provision model auto recommending method that the embodiment of the present invention four provides
Fig. 6 is the structural schematic diagram for the automatic recommendation apparatus of old-age provision model that the embodiment of the present invention five provides；
Fig. 7 is the schematic diagram for the terminal device that the embodiment of the present invention six provides.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical solution in the embodiment of the present invention are explicitly described, it is clear that described embodiment is the present invention one
The embodiment divided, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, should fall within the scope of the present invention.
Description and claims of this specification and term " includes " and their any deformations in above-mentioned attached drawing, meaning
Figure, which is to cover, non-exclusive includes.Such as process, method or system comprising a series of steps or units, product or equipment do not have
It is defined in listed step or unit, but optionally further comprising the step of not listing or unit, or optionally also wrap
Include the other step or units intrinsic for these process, methods, product or equipment.In addition, term " first ", " second " and
" third " etc. is for distinguishing different objects, not for description particular order.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
Embodiment one
As shown in Figure 1, the present embodiment provides a kind of old-age provision model auto recommending method, this method be can be applied to such as hand
The terminal devices such as machine, tablet computer, PC.Old-age provision model auto recommending method provided by the present embodiment, comprising:
S101, training dataset is obtained；Wherein, the training dataset includes questionnaire answer and the endowment mould manually marked
Formula.
In a particular application, training dataset is obtained, wherein training dataset includes questionnaire answer and manually marks feeding
Old mode.Questionnaire answer refers to the corresponding answer of all problems that questionnaire is got by inquiry.The old-age provision model manually marked
Refer to by manually evaluating questionnaire, and the questionnaire marked fills in the suitable old-age provision model of people, including but not limited to: mechanism is supported
Always, family endowment, community endowment, sojourn in endowment, generation-inter- learning center, use house property as the living means for one's old age, intelligence endowment, shared family endowment, occupying
Family's endowment integrating system and doctor, which support, combines endowment.
S102, using the questionnaire answer as input feature vector, using the old-age provision model manually marked as output feature,
Create BP Neural Networks model.
In a particular application, can by the way that questionnaire is endowed and statistical technique and BP Neural Networks learning art,
Using questionnaire answer as the input of model, the old-age provision model manually to mark creates backpropagation Feedforward Neural Networks as output
Road model.
S103, the BP Neural Networks model is trained according to the training dataset, to obtain
The automatic recommended models of old-age provision model.
In a particular application, BP Neural Networks model is trained according to training dataset, to obtain
The parameters of the automatic recommended models of old-age provision model, to obtain the automatic recommended models of old-age provision model.In the specific implementation process,
BP Neural Networks model passes through the training and analysis of a large amount of training datas, the final optimal value for determining parameters
The number of plies for being respectively as follows: BP Neural Networks model is three layers, is input layer (29 nodes), hidden layer (40 respectively
A node), output layer (10 nodes), learning rate 0.0006.Implementation method: BP Neural Networks model needs
Determining parameter is respectively the network number of plies, node in hidden layer and e-learning rate, can first assume node in hidden layer and network
The value of learning rate makes system optimal with resulting training dataset training BP Neural Networks model to obtain
When the network number of plies；The value for again assuming that e-learning rate is continued to train BP Neural Networks with training dataset,
Make node in hidden layer when system optimal to obtain；After the network number of plies and node in hidden layer determine, then use training data
Collect training BP Neural Networks, obtains the value of optimal e-learning rate.When the network number of plies, node in hidden layer and
After the value of e-learning rate determines, that is, it is created that the automatic recommended models of old-age provision model.As shown in table 1, one is schematically illustrated
Kind includes the questionnaire table of 29 node input layers.
S104, the characteristic value for obtaining questionnaire simultaneously input the automatic recommended models of the old-age provision model, to obtain endowment mould
The automatic recommendation results of formula.
In a particular application, obtaining the characteristic value that investigation user inputs in questionnaire, (characteristic value refers to that investigation user is directed to
The answer of each single item problem in questionnaire), and the automatic recommended models of old-age provision model are input to, the automatic recommended models of old-age provision model
The old-age provision model that automatic Prediction investigation user may select.I.e. any investigation user need to only complete questionnaire investigation online, based on anti-
User can be investigated from trend to the automatic recommended models of old-age provision model for propagating feedforward neural network recommend suitable old-age provision model.
The present embodiment by creation BP Neural Networks model according to training dataset and to backpropagation before
Feedback neural network model is trained, and to obtain the automatic recommendation that the automatic recommended models of old-age provision model realize old-age provision model, is saved
A large amount of human and material resources and financial resources, and improve the applicability of eligible result.
Embodiment two
As shown in Fig. 2, the present embodiment is the further explanation to the method and step in embodiment one.In the present embodiment,
Before the step S102, further includes:
S105, the normalization questionnaire answer, to obtain the questionnaire answer after normalization.
In a particular application, the problem of questionnaire and its corresponding questionnaire answer relate separately to different physical significances or
The input data of dimension, can be to each questionnaire answer with identical weight (status i.e. of equal importance) by normalization.Cause
This, can normalize to questionnaire answer value between [0,1], the transform used are as follows:
In above formula, xiRepresent the value of independent variable, xminRepresent the minimum value of data variation, xmaxRepresent the maximum of data
Value,Represent the value of normalization independent variable.
S106, the normalization old-age provision model manually marked, to obtain the old-age provision model manually marked after normalization.
In a particular application, due to the corresponding output valve of the value of the old-age provision model manually marked can only value 1 or 0, because
This need to normalize the old-age provision model manually marked.Wherein, can set indicates that its corresponding old-age provision model is selected when taking 1, when
Indicate that its corresponding old-age provision model is not selected when taking 0.
In one embodiment, the normalized formula includes:
Wherein, xiRepresent the value of normalization data, xminRepresent the minimum value of normalization data variation, xmaxRepresent normalizing
Change the maximum value of data variation,Data value after representing the normalization.
In a particular application, normalized formula includes:
Wherein, xiRepresenting the value of normalization data, (i.e. the value of questionnaire answer and the old-age provision model manually marked takes
Value), xminRepresenting the minimum value that normalization data changes, (i.e. the value of questionnaire answer and the old-age provision model manually marked change
Minimum value), xmaxRepresent maximum value (the i.e. value of questionnaire answer and the old-age provision model manually marked change of normalization data variation
The maximum value of change),Data value after representing the normalization (value of the questionnaire answer after normalizing and manually marks feeding
The value of old mode).
The present embodiment improves the confidence level of data by the normalization of the data to different type and different meanings, into
One step improves the confidence level of the automatic recommended models of old-age provision model.
Embodiment three
As shown in figure 3, the present embodiment is the further explanation to the method and step in embodiment one.In the present embodiment,
Step S103, comprising:
S1031, pass through error backpropagation algorithm according to the training dataset to BP Neural Networks mould
Type is trained, to obtain the automatic recommended models of old-age provision model.
In a particular application, by error backpropagation algorithm (error BackPropagation, BP) according to training number
BP Neural Networks model is trained according to collection, to obtain the automatic recommended models of old-age provision model.As shown in figure 4,
Provide it is a kind of by error backpropagation algorithm to the number of plies be three layers (be input layer (29 nodes) respectively, hidden layer (40
Node), output layer (10 nodes)) the training based on BP Neural Networks model schematic diagram.
The present embodiment is optimal state by what error backpropagation algorithm made the automatic recommended models of old-age provision model, into one
Step improves the applicability of the automatic recommendation results of old-age provision model.
Example IV
As shown in figure 5, the present embodiment is the further explanation to the method and step in embodiment one.In the present embodiment,
Step S101, comprising:
S1011, the type for obtaining old-age provision model.
In a particular application, the investigation of industry on the spot, literature survey, the investigation of all kinds of electronic mediums, government's correlation work can be passed through
It gives a report, the various ways such as personal interview, obtains the type of old-age provision model.
S1012, the problem corresponding with the type of the old-age provision model is obtained.
In a particular application, (the degree of correlation corresponding with the type of old-age provision model is determined according to the type of above-mentioned old-age provision model
High) problem.
S1013, according to the old-age provision model and the problem corresponding with the type of the old-age provision model, design old-age provision model tune
Interrogate volume.
In a particular application, according to old-age provision model and the problem corresponding with the type of old-age provision model, design portion is more closed
The old-age provision model questionnaire of reason.Specifically, high-volume investigational data can be collected as research material by practical investigate, and group
The senior endowment expert of multidigit is knitted manually to mark the old-age provision model in this batch of investigational data.
S1014, the questionnaire answer for being directed to the old-age provision model questionnaire and people corresponding with the questionnaire answer are obtained
The old-age provision model of work mark, as the training dataset.
In a particular application, it obtains for the questionnaire answer of old-age provision model questionnaire and corresponding with questionnaire answer artificial
Old-age provision model after mark recommends mould for creating old-age provision model as the training set of the automatic recommended models of old-age provision model automatically
Type.
In one embodiment, S1013 includes:
Old-age provision model questionnaire is designed according to the old-age provision model and the problem corresponding with the type of the old-age provision model；
Obtain the confidence level and efficiency of the old-age provision model questionnaire；
If it is described it is with a low credibility be lower than default efficiency threshold in default believability threshold and/or the efficiency, root again
Old-age provision model questionnaire is designed according to the old-age provision model and the problem corresponding with the type of the old-age provision model, until described can
Reliability reaches default believability threshold and until the efficiency reaches default efficiency threshold.
In a particular application, according to old-age provision model and the problem design old-age provision model investigation corresponding with the type of old-age provision model
SPSS software can be used to carry out the analysis and acquisition of confidence level and efficiency to the old-age provision model questionnaire designed for questionnaire, if
It is with a low credibility to be lower than default efficiency threshold in default believability threshold and/or efficiency, then again according to old-age provision model and with endowment
Problem corresponding to the type of mode designs old-age provision model questionnaire, until reliability reaches default believability threshold and efficiency reaches
Until default efficiency threshold.
The present embodiment is investigated by a large amount of data, designs reasonable questionnaire, and the data based on questionnaire
Creation and the training automatic recommended models of old-age provision model, can automatic Prediction go out respondent for the selection preference and not of old-age provision model
Come the emphasis direction for industry development of supporting parents, the development rate of endowment industry is improved.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Embodiment five
As shown in fig. 6, the present embodiment provides a kind of automatic recommendation apparatus 100 of old-age provision model, for executing in embodiment one
Method and step.The automatic recommendation apparatus 100 of old-age provision model provided in this embodiment, comprising:
First obtains module 101, for obtaining training dataset；Wherein, the training dataset include questionnaire answer and
The old-age provision model manually marked；
Creation module 102, for using the questionnaire answer as input feature vector, the old-age provision model manually marked to be made
To export feature, BP Neural Networks model is created；
Training module 103, for being carried out according to the training dataset to the BP Neural Networks model
Training, to obtain the automatic recommended models of old-age provision model；
Second obtains module 104, recommends mould automatically for obtaining the characteristic value of questionnaire and inputting the old-age provision model
Type, to obtain the automatic recommendation results of old-age provision model.
In one embodiment, described device 100, further includes:
Third obtains module 105, for normalizing the questionnaire answer, to obtain the questionnaire answer after normalization；
4th obtains module 106, artificial after normalization to obtain for normalizing the old-age provision model manually marked
The old-age provision model of mark.
In one embodiment, the normalized formula includes:
Wherein, xiRepresent the value of normalization data, xminRepresent the minimum value of normalization data variation, xmaxRepresent normalizing
Change the maximum value of data variation,Data value after representing the normalization.
In one embodiment, the training module 103, comprising:
BP Neural Networks model is carried out according to the training dataset by error backpropagation algorithm
Training, to obtain the automatic recommended models of old-age provision model.
In one embodiment, described first module 101 is obtained, comprising:
First acquisition unit 1011, for obtaining the type of old-age provision model；
Second acquisition unit 1012, for obtaining the problem corresponding with the type of the old-age provision model；
Design cell 1013, for according to the old-age provision model and the problem corresponding with the type of the old-age provision model, if
Count old-age provision model questionnaire；
Third acquiring unit 1014, for obtaining for the questionnaire answer of the old-age provision model questionnaire and being asked with described
The corresponding old-age provision model manually marked of answer is rolled up, as the training dataset；
In one embodiment, the design cell 1013, comprising:
Subelement is designed, is supported for being designed according to the old-age provision model and the problem corresponding with the type of the old-age provision model
Old mode questionnaire；
Subelement is obtained, for obtaining the confidence level and efficiency of the old-age provision model questionnaire；
Judgment sub-unit, if with a low credibility being imitated in default believability threshold and/or the efficiency lower than default for described
Rate threshold value, then again according to the old-age provision model and the problem design old-age provision model investigation corresponding with the type of the old-age provision model
Questionnaire, until the confidence level reaches default believability threshold and the efficiency reaches default efficiency threshold.
The present embodiment by creation BP Neural Networks model according to training dataset and to backpropagation before
Feedback neural network model is trained, and to obtain the automatic recommendation that the automatic recommended models of old-age provision model realize old-age provision model, is saved
A large amount of human and material resources and financial resources, and improve the applicability of eligible result.
Embodiment six
Fig. 7 is the schematic diagram for the terminal device that the present embodiment six provides.As shown in fig. 7, the terminal device 7 of the embodiment wraps
It includes: processor 70, memory 71 and being stored in the computer that can be run in the memory 71 and on the processor 70
Program 72, such as the automatic recommended program of old-age provision model.The processor 70 is realized above-mentioned each when executing the computer program 72
Step in a old-age provision model auto recommending method embodiment, such as step S101 to S104 shown in FIG. 1.Alternatively, the place
Reason device 70 realizes the function of each module/unit in above-mentioned each Installation practice, such as Fig. 6 institute when executing the computer program 72
Show the function of module 101 to 104.
Illustratively, the computer program 72 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 71, and are executed by the processor 70, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 72 in the terminal device 7 is described.For example, the computer program 72 can be divided
It is cut into the first acquisition module, creation module, training module and second and obtains module, each module concrete function is as follows:
First obtains module, for obtaining training dataset；Wherein, the training dataset includes questionnaire answer and artificial
The old-age provision model of mark；
Creation module, for using the questionnaire answer as input feature vector, using the old-age provision model manually marked as
Feature is exported, BP Neural Networks model is created；
Training module, for being instructed according to the training dataset to the BP Neural Networks model
Practice, to obtain the automatic recommended models of old-age provision model；
Second obtains module, for obtaining the characteristic value of questionnaire and inputting the automatic recommended models of the old-age provision model,
To obtain the automatic recommendation results of old-age provision model.
The terminal device 7 can be the calculating such as desktop PC, notebook, palm PC and cloud server and set
It is standby.The terminal device may include, but be not limited only to, processor 70, memory 71.It will be understood by those skilled in the art that Fig. 7
The only example of terminal device 7 does not constitute the restriction to terminal device 7, may include than illustrating more or fewer portions
Part perhaps combines certain components or different components, such as the terminal device can also include input-output equipment, net
Network access device, bus etc..
Alleged processor 70 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 71 can be the internal storage unit of the terminal device 7, such as the hard disk or interior of terminal device 7
It deposits.The memory 71 is also possible to the External memory equipment of the terminal device 7, such as be equipped on the terminal device 7
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), safe digital card (Secure Digital, SD) dodge
Deposit card (Flash Card) etc..Further, the memory 71 can also both include the storage inside list of the terminal device 7
Member also includes External memory equipment.The memory 71 is for storing needed for the computer program and the terminal device
Other programs and data.The memory 71 can be also used for temporarily storing the data that has exported or will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device/terminal device and method, it can be with
It realizes by another way.For example, device described above/terminal device embodiment is only schematical, for example, institute
The division of module or unit is stated, only a kind of logical function partition, there may be another division manner in actual implementation, such as
Multiple units or components can be combined or can be integrated into another system, or some features can be ignored or not executed.Separately
A bit, shown or discussed mutual coupling or direct-coupling or communication connection can be through some interfaces, device
Or the INDIRECT COUPLING or communication connection of unit, it can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
It may include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic that can carry the computer program code
Dish, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to the requirement made laws in jurisdiction with patent practice
Subtract, such as does not include electric carrier signal and electricity according to legislation and patent practice, computer-readable medium in certain jurisdictions
Believe signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of old-age provision model auto recommending method characterized by comprising
Obtain training dataset；Wherein, the training dataset includes questionnaire answer and the old-age provision model that manually marks；
Using the questionnaire answer as input feature vector, using the old-age provision model manually marked as output feature, creation is reversed
Propagate BP network model；
The BP Neural Networks model is trained according to the training dataset, to obtain old-age provision model certainly
Dynamic recommended models；
It obtains the characteristic value of questionnaire and inputs the automatic recommended models of the old-age provision model, to obtain pushing away automatically for old-age provision model
Recommend result.
2. old-age provision model auto recommending method as described in claim 1, which is characterized in that using the questionnaire answer as input
Feature, using the old-age provision model manually marked as output feature, before creating BP Neural Networks model, packet
It includes:
The questionnaire answer is normalized, to obtain the questionnaire answer after normalization；
The old-age provision model manually marked is normalized, to obtain the old-age provision model manually marked after normalization.
3. old-age provision model auto recommending method as claimed in claim 2, which is characterized in that the normalized formula includes:
Wherein, xiRepresent the value of normalization data, xminRepresent the minimum value of normalization data variation, xmaxRepresent normalization number
According to the maximum value of variation,Data value after representing the normalization.
4. old-age provision model auto recommending method as described in claim 1, which is characterized in that according to the training dataset to anti-
It is trained to BP network model is propagated, to obtain the automatic recommended models of old-age provision model, comprising:
BP Neural Networks model is trained according to the training dataset by error backpropagation algorithm,
To obtain the automatic recommended models of old-age provision model.
5. old-age provision model auto recommending method as described in claim 1, which is characterized in that the acquisition training dataset, packet
It includes:
Obtain the type of old-age provision model；
Obtain the problem corresponding with the type of the old-age provision model；
According to the old-age provision model and the problem corresponding with the type of the old-age provision model, old-age provision model questionnaire is designed；
Obtain for the old-age provision model questionnaire questionnaire answer and it is corresponding with the questionnaire answer manually mark support
Old mode, as the training dataset.
6. old-age provision model auto recommending method as claimed in claim 5, which is characterized in that according to the old-age provision model and with institute
State problem design old-age provision model questionnaire corresponding to the type of old-age provision model, comprising:
Old-age provision model questionnaire is designed according to the old-age provision model and the problem corresponding with the type of the old-age provision model；
Obtain the confidence level and efficiency of the old-age provision model questionnaire；
If it is described it is with a low credibility be lower than default efficiency threshold in default believability threshold and/or the efficiency, again according to institute
Old-age provision model and the problem design old-age provision model questionnaire corresponding with the type of the old-age provision model are stated, until the confidence level
Reach default believability threshold and until the efficiency reaches default efficiency threshold.
7. a kind of automatic recommendation apparatus of old-age provision model characterized by comprising
First obtains module, for obtaining training dataset；Wherein, the training dataset includes questionnaire answer and artificial mark
Old-age provision model；
Creation module is used for using the questionnaire answer as input feature vector, using the old-age provision model manually marked as output
Feature creates BP Neural Networks model；
Training module, for being trained according to the training dataset to the BP Neural Networks model, with
Obtain the automatic recommended models of old-age provision model；
Second obtains module, for obtaining the characteristic value of questionnaire and inputting the automatic recommended models of the old-age provision model, to obtain
Take the automatic recommendation results of old-age provision model.
8. the automatic recommendation apparatus of old-age provision model as claimed in claim 7, which is characterized in that further include:
Third obtains module, for normalizing the questionnaire answer, to obtain the questionnaire answer after normalization；
4th obtains module, for normalizing the old-age provision model manually marked, to obtain manually marking after normalization
Old-age provision model.
9. a kind of terminal device, including memory, processor and storage are in the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 6 when executing the computer program
The step of any one the method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In when the computer program is executed by processor the step of any one of such as claim 1 to 6 of realization the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811457321.9A CN109636451B (en) | 2018-11-30 | 2018-11-30 | Automatic old age maintenance mode recommendation method and device and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811457321.9A CN109636451B (en) | 2018-11-30 | 2018-11-30 | Automatic old age maintenance mode recommendation method and device and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109636451A true CN109636451A (en) | 2019-04-16 |
| CN109636451B CN109636451B (en) | 2021-07-09 |
Family
ID=66070558
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811457321.9A Active CN109636451B (en) | 2018-11-30 | 2018-11-30 | Automatic old age maintenance mode recommendation method and device and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109636451B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915667A (en) * | 2015-05-27 | 2015-09-16 | 华中科技大学 | Mobile-terminal-based method and system for identification and analysis of answering card |
| CN105787639A (en) * | 2016-02-03 | 2016-07-20 | 北京云太科技有限公司 | Artificial-intelligence-based talent big data quantization precise matching method and apparatus |
| CN107066458A (en) * | 2016-08-26 | 2017-08-18 | 北京车网互联科技有限公司 | A kind of Spatial dimensionality user portrait analysis method based on car networking data |
| CN107169031A (en) * | 2017-04-17 | 2017-09-15 | 广东工业大学 | It is a kind of to recommend method based on the picture materials that depthmeter reaches |
| US20170323212A1 (en) * | 2016-05-06 | 2017-11-09 | Crowd Computing Systems, Inc. | Agent aptitude prediction |
| CN107885849A (en) * | 2017-11-13 | 2018-04-06 | 成都蓝景信息技术有限公司 | A kind of moos index analysis system based on text classification |
-
2018
- 2018-11-30 CN CN201811457321.9A patent/CN109636451B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915667A (en) * | 2015-05-27 | 2015-09-16 | 华中科技大学 | Mobile-terminal-based method and system for identification and analysis of answering card |
| CN105787639A (en) * | 2016-02-03 | 2016-07-20 | 北京云太科技有限公司 | Artificial-intelligence-based talent big data quantization precise matching method and apparatus |
| US20170323212A1 (en) * | 2016-05-06 | 2017-11-09 | Crowd Computing Systems, Inc. | Agent aptitude prediction |
| CN107066458A (en) * | 2016-08-26 | 2017-08-18 | 北京车网互联科技有限公司 | A kind of Spatial dimensionality user portrait analysis method based on car networking data |
| CN107169031A (en) * | 2017-04-17 | 2017-09-15 | 广东工业大学 | It is a kind of to recommend method based on the picture materials that depthmeter reaches |
| CN107885849A (en) * | 2017-11-13 | 2018-04-06 | 成都蓝景信息技术有限公司 | A kind of moos index analysis system based on text classification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109636451B (en) | 2021-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fienberg et al. | Categorical data analysis of single sociometric relations | |
| Le et al. | Land-Use Dynamic Simulator (LUDAS): A multi-agent system model for simulating spatio-temporal dynamics of coupled human–landscape system. I. Structure and theoretical specification | |
| CN104123684B (en) | Power distribution network economy reconstructing method considering network loss and reliability | |
| Castelli et al. | Urban intelligence: a modular, fully integrated, and evolving model for cities digital twinning | |
| CN109754068A (en) | Transfer learning method and terminal device based on deep learning pre-training model | |
| Augustine et al. | Cognitive map-based system modeling for identifying interaction failure modes | |
| CN109885452A (en) | Method for monitoring performance, device and terminal device | |
| CN106897404A (en) | A kind of recommendation method and system based on many GRU layers of neutral nets | |
| CN107992595A (en) | A kind of learning Content recommends method, apparatus and smart machine | |
| CN108764332A (en) | A kind of Channel Quality analysis method, computing device and storage medium | |
| CN108549276A (en) | A kind of method and system of intelligent interaction control water making device | |
| CN110163350A (en) | A kind of computing device and method | |
| CN110110226A (en) | A kind of proposed algorithm, recommender system and terminal device | |
| CN108664241A (en) | A method of SysML models are subjected to simulating, verifying | |
| Tiu et al. | An evaluation of various data pre-processing techniques with machine learning models for water level prediction | |
| Raju et al. | Multi-objective differential evolution application to irrigation planning | |
| CN109636451A (en) | A kind of old-age provision model auto recommending method, device and terminal device | |
| Parker et al. | Multi-Agent systems for the simulation of land-use and land-cover change: A review | |
| Ahmad | An intelligent expert system for decision analysis and support in multi-attribute layout optimization | |
| CN110215703A (en) | The selection method of game application, apparatus and system | |
| CN109657907A (en) | Method of quality control, device and the terminal device of geographical national conditions monitoring data | |
| Reddy et al. | A Beginner's Guide to Federated Learning | |
| Kryuchin et al. | The prediction of currency exchange rates using artificial neural networks | |
| CN109446400A (en) | A kind of learning management method, learning management device and electronic equipment | |
| CN114239387A (en) | Organic biochemical reaction strain putting guidance method and system |
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 |