CN109636451B - Automatic old age maintenance mode recommendation method and device and terminal equipment - Google Patents

Automatic old age maintenance mode recommendation method and device and terminal equipment Download PDF

Info

Publication number
CN109636451B
CN109636451B CN201811457321.9A CN201811457321A CN109636451B CN 109636451 B CN109636451 B CN 109636451B CN 201811457321 A CN201811457321 A CN 201811457321A CN 109636451 B CN109636451 B CN 109636451B
Authority
CN
China
Prior art keywords
mode
endowment
questionnaire
care
automatic
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201811457321.9A
Other languages
Chinese (zh)
Other versions
CN109636451A (en
Inventor
夏林中
罗德安
张春晓
管明祥
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Institute of Information Technology
Original Assignee
Shenzhen Institute of Information Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Institute of Information Technology filed Critical Shenzhen Institute of Information Technology
Priority to CN201811457321.9A priority Critical patent/CN109636451B/en
Publication of CN109636451A publication Critical patent/CN109636451A/en
Application granted granted Critical
Publication of CN109636451B publication Critical patent/CN109636451B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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)
  • Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • General Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention is suitable for the technical field of deep learning, and provides an automatic old-age mode recommendation method, an automatic old-age mode recommendation device and terminal equipment, wherein the automatic old-age mode recommendation method comprises the following steps: acquiring a training data set; the training data set comprises questionnaire answers and a manually labeled endowment mode, the questionnaire answers are used as input features, the manually labeled endowment mode is used as output features, a back propagation feedforward neural network model is created, the back propagation feedforward neural network model is trained according to the training data set to obtain an endowment mode automatic recommendation model, characteristic values of the questionnaire are obtained, the characteristic values are input into the endowment mode automatic recommendation model, and an automatic recommendation result of the endowment mode is obtained. According to the invention, the back propagation feedforward neural network model is created according to the training data set and is trained to obtain the automatic old-age mode recommending model so as to realize automatic old-age mode recommending, so that a large amount of manpower, material resources and financial resources are saved, and the applicability of the obtained result is improved.

Description

Automatic old age maintenance mode recommendation method and device and terminal equipment
Technical Field
The invention belongs to the technical field of deep learning, and particularly relates to an automatic old-age-care mode recommendation method, an automatic old-age-care mode recommendation device and terminal equipment.
Background
In the process of continuous development in China for recent decades, the problem of endowment becomes more and more prominent, and the problem of endowment is not only a social and civil problem which needs to be solved properly, but also is closely related to the development of social economy. Therefore, in the future development, it is important to think how to invest in the old-age care industry, which not only affects the return on investment, but also affects whether the old-age care industry can build the old-age care environment meeting the needs of different old people.
Due to the influences of various factors such as age, occupation, economic income, education degree, health condition, marital condition, regional difference and the like, different requirements of old people groups on the old-age care mode exist, and the single old-age care mode of the traditional family old-age care mode cannot meet the diversified and different old-age care requirements of the old people. Therefore, diversification of the endowment modes is a necessity of historical development, the endowment modes are selected like an equation, the old people in each era have to answer, and the answers in different generations are different.
In order to better invest in the industry for old people, meet diversified requirements for old people, and avoid unnecessary waste caused by blind investment and construction, a reference basis which is instructive to the development of the future industry for old people is needed. At present, in order to predict the development direction of the future endowment industry, the applied method is basically a questionnaire mode.
However, the method of using questionnaire to investigate the development direction of the future aging industry has the following disadvantages:
1. the method requires a large amount of manpower, material resources and financial resources.
2. The result obtained by the method is only suitable for specific regions and specific groups, and is difficult to be generalized to regions such as provinces or countries.
Disclosure of Invention
In view of this, embodiments of the present invention provide an automatic recommendation method and apparatus for an old-age care mode, and a terminal device, so as to solve the problems in the prior art.
The first aspect of the embodiment of the invention provides an automatic recommendation method for an old-age care mode, which comprises the following steps:
acquiring a training data set; wherein the training data set comprises questionnaire answers and a manually labeled endowment mode;
taking the answer of the questionnaire as an input feature, taking the artificially labeled endowment mode as an output feature, and creating a back propagation feedforward neural network model;
training the back propagation feedforward neural network model according to the training data set to obtain an automatic old-age mode recommendation model;
and acquiring characteristic values of questionnaires and inputting the automatic recommendation model of the endowment mode to acquire an automatic recommendation result of the endowment mode.
Optionally, before the step of creating a back propagation feedforward neural network model by using the answer to the questionnaire as an input feature and the artificially labeled endowment pattern as an output feature, the method includes:
normalizing the questionnaire answers to obtain normalized questionnaire answers;
normalizing the artificially labeled endowment mode to obtain the normalized artificially labeled endowment mode.
Optionally, the normalized formula includes:
Figure BDA0001888004790000021
wherein x isiValue, x, representing normalized dataminMinimum value, x, representing variation of normalized datamaxRepresents the maximum value of the variation of the normalized data,
Figure BDA0001888004790000022
representing the normalized data value.
Optionally, training a back propagation feedforward neural network model according to the training data set to obtain an automatic recommendation model for an elderly care mode, including:
and training a back propagation feedforward neural network model according to the training data set through an error back propagation algorithm to obtain an automatic old-age mode recommendation model.
Optionally, the acquiring the training data set includes:
acquiring the type of the endowment mode;
acquiring a problem corresponding to the type of the endowment mode;
designing an endowment mode questionnaire according to the endowment mode and the problems corresponding to the type of the endowment mode;
acquiring questionnaire answers aiming at the endowment mode questionnaire and an artificially labeled endowment mode corresponding to the questionnaire answers as the training data set;
optionally, designing an endowment mode questionnaire according to the endowment mode and the questions corresponding to the type of the endowment mode includes:
designing an endowment mode questionnaire according to the endowment mode and the questions corresponding to the type of the endowment mode;
obtaining the reliability and efficiency of the endowment mode questionnaire;
if the credibility is lower than a preset credibility threshold and/or the efficiency is lower than a preset efficiency threshold, designing an endowment mode questionnaire again according to the endowment mode and the questions corresponding to the type of the endowment mode until the credibility reaches the preset credibility threshold and the efficiency reaches the preset efficiency threshold.
A second aspect of an embodiment of the present invention provides an automatic recommendation device for an old-age care mode, including:
the first acquisition module is used for acquiring a training data set; wherein the training data set comprises questionnaire answers and a manually labeled endowment mode;
the creating module is used for taking the questionnaire answers as input features, taking the artificially labeled endowment modes as output features, and creating a back propagation feedforward neural network model;
the training module is used for training the back propagation feedforward neural network model according to the training data set so as to obtain an automatic old-age mode recommendation model;
and the second acquisition module is used for acquiring the characteristic value of the questionnaire and inputting the characteristic value into the endowment mode automatic recommendation model so as to acquire an automatic recommendation result of the endowment mode.
A third aspect of an embodiment of the present invention provides a terminal device, including: a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method as described above when executing the computer program.
A fourth aspect of embodiments of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method as described above.
According to the embodiment of the invention, the back propagation feedforward neural network model is created, and the back propagation feedforward neural network model is trained according to the training data set, so that the automatic old-age mode recommendation model is obtained to realize the automatic old-age mode recommendation, a large amount of manpower, material resources and financial resources are saved, and the applicability of the obtained result is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a flowchart illustrating an automatic recommendation method for an old-age mode according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating an automatic recommendation method for an old-age mode according to a second embodiment of the present invention;
fig. 3 is a flowchart illustrating an automatic recommendation method for an old-age mode according to a third embodiment of the present invention;
FIG. 4 is a schematic diagram of training a three-layer back propagation-based feedforward neural network model according to a third embodiment of the present invention;
FIG. 5 is a flowchart illustrating an automatic recommendation method for an old-age mode according to a fourth embodiment of the present invention
Fig. 6 is a schematic structural diagram of an automatic old-age mode recommending device according to a fifth embodiment of the present invention;
fig. 7 is a schematic diagram of a terminal device according to a sixth embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood by those skilled in the art, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "comprises" and "comprising," and any variations thereof, in the description and claims of this invention and the above-described drawings are intended to cover non-exclusive inclusions. For example, a process, method, or system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus. Furthermore, the terms "first," "second," and "third," etc. are used to distinguish between different objects and are not used to describe a particular order.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
Example one
As shown in fig. 1, the present embodiment provides an automatic recommendation method for an old-age care mode, which can be applied to terminal devices such as a mobile phone, a tablet computer, and a PC. The automatic recommendation method for the endowment mode provided by the embodiment comprises the following steps:
s101, acquiring a training data set; wherein the training data set comprises questionnaire answers and manually labeled endowment patterns.
In a particular application, a training data set is obtained, wherein the training data set includes questionnaire answers and manually labeled endowment patterns. The questionnaire answers refer to answers corresponding to all questions acquired through the questionnaire. Manually labeled endowment patterns refer to patterns that are manually evaluated by questionnaires and labeled questionnaires fill in the appropriate endowment patterns, including but not limited to: the system comprises an organization care, a home care, a community care, a sojourn care, a modern learning center, a house care, an intelligent care, a shared home care, a home care integration system and a medical care combined care.
And S102, taking the answer of the questionnaire as an input feature, taking the artificially labeled endowment mode as an output feature, and creating a back propagation feedforward neural network model.
In specific application, the answer of the questionnaire can be used as the input of the model and the artificially labeled endowment mode can be used as the output to create the back propagation feedforward neural network model through the questionnaire coding and statistical technology and the back propagation feedforward neural network learning technology.
S103, training the back propagation feedforward neural network model according to the training data set to obtain an automatic old-age mode recommendation model.
In specific application, the back propagation feedforward neural network model is trained according to a training data set to obtain various parameters of the endowment mode automatic recommendation model, so that the endowment mode automatic recommendation model is obtained. In a specific implementation process, the back propagation feedforward neural network model is trained and analyzed by a large amount of training data, and finally the optimal values of all parameters are determined as follows: the number of layers of the back propagation feedforward neural network model is three, namely an input layer (29 nodes), a hidden layer (40 nodes), an output layer (10 nodes) and a learning rate of 0.0006. The implementation method comprises the following steps: the parameters to be determined of the back propagation feedforward neural network model are respectively the number of network layers, the number of hidden layer nodes and the network learning rate, the values of the number of hidden layer nodes and the network learning rate can be assumed firstly, and the obtained training data set is used for training the back propagation feedforward neural network model so as to obtain the number of network layers when the system is optimal; assuming the value of the network learning rate, continuously training a back propagation feedforward neural network by using a training data set to obtain the number of hidden layer nodes when the system is optimal; and after the number of the network layers and the number of the hidden layer nodes are determined, training the back propagation feedforward neural network by using the training data set to obtain the optimal value of the network learning rate. And when the network layer number, the number of hidden layer nodes and the value of the network learning rate are determined, the automatic recommendation model of the endowment mode is established. As shown in table 1, a questionnaire table comprising 29 input levels of nodes is schematically shown.
Figure BDA0001888004790000061
Figure BDA0001888004790000071
Figure BDA0001888004790000081
Figure BDA0001888004790000091
And S104, acquiring characteristic values of questionnaires and inputting the automatic recommendation model of the endowment mode to acquire an automatic recommendation result of the endowment mode.
In a specific application, a characteristic value input by a survey user in a survey questionnaire (the characteristic value refers to an answer of the survey user to each question in the survey questionnaire) is obtained and input to an endowment mode automatic recommendation model, and the endowment mode automatic recommendation model automatically predicts an endowment mode which the survey user may select. Namely, any survey user only needs to complete questionnaire investigation on line, and the automatic endowment mode recommendation model based on the back propagation feedforward neural network can automatically recommend a proper endowment mode to the survey user.
According to the embodiment, the back propagation feedforward neural network model is created and trained according to the training data set to obtain the automatic old-age mode recommending model to realize automatic old-age mode recommending, so that a large amount of manpower, material resources and financial resources are saved, and the applicability of the obtained result is improved.
Example two
As shown in fig. 2, this embodiment is a further description of the method steps in the first embodiment. In this embodiment, before the step S102, the method further includes:
and S105, normalizing the questionnaire answers to obtain the normalized questionnaire answers.
In a specific application, the questions of the questionnaire and the answers to the questionnaire relate to input data with different physical meanings or dimensions, and the answers to the questionnaire can be given the same weight (i.e., the same important status) by normalization. Thus, the answer value of the questionnaire can be normalized to be between [0, 1], and the transformation used is:
Figure BDA0001888004790000092
in the above formula, xiRepresents the value of an independent variable, xminMinimum value, x, representing variation of datamaxRepresents the maximum value of the data and,
Figure BDA0001888004790000093
represents the value of the normalized independent variable.
S106, normalizing the artificially labeled endowment mode to obtain the normalized artificially labeled endowment mode.
In a specific application, because the output value corresponding to the value of the artificially labeled endowment mode can only take the value of 1 or 0, the artificially labeled endowment mode needs to be normalized. The user can set that when 1 is taken, the user indicates that the corresponding endowment mode is selected, and when 0 is taken, the user indicates that the corresponding endowment mode is not selected.
In one embodiment, the normalized formula includes:
Figure BDA0001888004790000101
wherein x isiValue, x, representing normalized dataminMinimum value, x, representing variation of normalized datamaxRepresents the maximum value of the variation of the normalized data,
Figure BDA0001888004790000102
representing the normalized data value.
In a specific application, the normalized formula includes:
Figure BDA0001888004790000103
wherein x isiThe value representing the normalized data (namely the value of the questionnaire answers and the value of the manually labeled endowment mode), xminRepresents the minimum value of the normalized data change (i.e., the minimum value of the questionnaire answers and the manually labeled aging mode change), xmaxRepresents the maximum value of the normalized data change (i.e. the maximum value of the questionnaire answers and the manually labeled aging mode change),
Figure BDA0001888004790000104
representing the normalized data values (i.e., the value of the normalized questionnaire answers and the value of the manually labeled endowment pattern).
According to the embodiment, the credibility of the data is improved through the normalization of the data with different types and different meanings, and the credibility of the automatic recommendation model of the endowment mode is further improved.
EXAMPLE III
As shown in fig. 3, this embodiment is a further description of the method steps in the first embodiment. In this embodiment, step S103 includes:
and S1031, training the back propagation feedforward neural network model according to the training data set through an error back propagation algorithm to obtain an automatic old-age mode recommendation model.
In specific application, a back propagation feedforward neural network model is trained through an error Back Propagation (BP) algorithm according to a training data set to obtain an automatic recommendation model of an endowment mode. As shown in fig. 4, a schematic diagram of a back propagation feedforward neural network model-based training of three layers (input layer (29 nodes), hidden layer (40 nodes), output layer (10 nodes), respectively) by an error back propagation algorithm is provided.
According to the embodiment, the automatic old-age mode recommendation model achieves the optimal state through the error back propagation algorithm, and the applicability of the automatic old-age mode recommendation result is further improved.
Example four
As shown in fig. 5, this embodiment is a further description of the method steps in the first embodiment. In this embodiment, step S101 includes:
s1011, acquiring the type of the endowment mode.
In specific application, the type of the endowment mode can be obtained through various modes such as field industry research, literature research, various electronic media research, government-related work reports, personal interview and the like.
And S1012, acquiring a problem corresponding to the type of the endowment mode.
In a specific application, a problem (with high correlation degree) corresponding to the type of the endowment mode is determined according to the type of the endowment mode.
And S1013, designing an endowment mode questionnaire according to the endowment mode and the questions corresponding to the endowment mode type.
In specific application, a reasonable endowment mode questionnaire is designed according to an endowment mode and problems corresponding to the type of the endowment mode. Specifically, a large amount of research data can be collected through actual research to serve as research materials, and a plurality of senior care specialists are organized to manually label the care modes in the research data.
S1014, acquiring questionnaire answers aiming at the endowment mode questionnaire and an artificially labeled endowment mode corresponding to the questionnaire answers as the training data set.
In the specific application, questionnaire answers aiming at the questionnaire of the endowment mode survey and an artificially labeled endowment mode corresponding to the questionnaire answers are obtained and used as a training set of an endowment mode automatic recommendation model for creating the endowment mode automatic recommendation model.
In one embodiment, S1013 includes:
designing an endowment mode questionnaire according to the endowment mode and the questions corresponding to the type of the endowment mode;
obtaining the reliability and efficiency of the endowment mode questionnaire;
if the credibility is lower than a preset credibility threshold and/or the efficiency is lower than a preset efficiency threshold, designing an endowment mode questionnaire again according to the endowment mode and the questions corresponding to the type of the endowment mode until the credibility reaches the preset credibility threshold and the efficiency reaches the preset efficiency threshold.
In specific application, the endowment mode questionnaire is designed according to the endowment mode and the problems corresponding to the type of the endowment mode, SPSS software can be used for analyzing and acquiring the reliability and efficiency of the designed endowment mode questionnaire, if the reliability is lower than a preset reliability threshold and/or the efficiency is lower than a preset efficiency threshold, the endowment mode questionnaire is designed again according to the endowment mode and the problems corresponding to the type of the endowment mode until the reliability reaches the preset reliability threshold and the efficiency reaches the preset efficiency threshold.
According to the embodiment, a reasonable questionnaire is designed through a large amount of data research, the automatic recommendation model of the endowment mode is created and trained based on the data of the questionnaire, the selection preference of a survey object on the endowment mode and the key direction of future development of the endowment industry can be automatically predicted, and the development rate of the endowment industry is improved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
EXAMPLE five
As shown in fig. 6, the present embodiment provides an automatic recommendation apparatus 100 for an old-age care mode, which is used for executing the method steps in the first embodiment. The automatic recommendation device 100 for an old-age mode provided by the embodiment comprises:
a first obtaining module 101, configured to obtain a training data set; wherein the training data set comprises questionnaire answers and a manually labeled endowment mode;
a creating module 102, configured to use the questionnaire answers as input features, use the artificially labeled endowment mode as output features, and create a back propagation feedforward neural network model;
the training module 103 is configured to train the back propagation feedforward neural network model according to the training data set to obtain an automatic old-age-care-mode recommendation model;
and the second obtaining module 104 is configured to obtain a feature value of the questionnaire and input the feature value into the endowment mode automatic recommendation model to obtain an automatic recommendation result of the endowment mode.
In one embodiment, the apparatus 100 further comprises:
a third obtaining module 105, configured to normalize the questionnaire answers, so as to obtain normalized questionnaire answers;
a fourth obtaining module 106, configured to normalize the artificially labeled endowment mode, so as to obtain a normalized artificially labeled endowment mode.
In one embodiment, the normalized formula includes:
Figure BDA0001888004790000131
wherein x isiValue, x, representing normalized dataminMinimum value, x, representing variation of normalized datamaxRepresents the maximum value of the variation of the normalized data,
Figure BDA0001888004790000132
representing the normalized data value.
In one embodiment, the training module 103 includes:
and training a back propagation feedforward neural network model according to the training data set through an error back propagation algorithm to obtain an automatic old-age mode recommendation model.
In one embodiment, the first obtaining module 101 includes:
a first acquiring unit 1011 for acquiring a type of the endowment mode;
a second acquiring unit 1012 for acquiring a question corresponding to the type of the endowment mode;
a design unit 1013 for designing an endowment mode questionnaire according to the endowment mode and a question corresponding to the type of the endowment mode;
a third obtaining unit 1014, configured to obtain questionnaire answers to the endowment pattern questionnaire and a manually labeled endowment pattern corresponding to the questionnaire answers as the training data set;
in one embodiment, the design unit 1013 comprises:
a design subunit, configured to design an endowment mode questionnaire according to the endowment mode and a question corresponding to the type of the endowment mode;
the obtaining subunit is used for obtaining the reliability and the efficiency of the endowment mode questionnaire;
and the judging subunit is used for designing an endowment mode questionnaire again according to the endowment mode and the problems corresponding to the type of the endowment mode if the credibility is lower than a preset credibility threshold and/or the efficiency is lower than a preset efficiency threshold until the credibility reaches the preset credibility threshold and the efficiency reaches the preset efficiency threshold.
According to the embodiment, the back propagation feedforward neural network model is created and trained according to the training data set to obtain the automatic old-age mode recommending model to realize automatic old-age mode recommending, so that a large amount of manpower, material resources and financial resources are saved, and the applicability of the obtained result is improved.
EXAMPLE six
Fig. 7 is a schematic diagram of a terminal device provided in the sixth embodiment. As shown in fig. 7, the terminal device 7 of this embodiment includes: a processor 70, a memory 71 and a computer program 72, such as an endowment mode automatic recommendation program, stored in said memory 71 and operable on said processor 70. The processor 70, when executing the computer program 72, implements the steps in the above-mentioned embodiments of the automatic old-age mode recommendation method, such as the steps S101 to S104 shown in fig. 1. Alternatively, the processor 70, when executing the computer program 72, implements the functions of each module/unit in the above-described device embodiments, for example, the functions of the modules 101 to 104 shown in fig. 6.
Illustratively, the computer program 72 may be partitioned into one or more modules/units that are stored in the memory 71 and executed by the processor 70 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 72 in the terminal device 7. For example, the computer program 72 may be divided into a first acquisition module, a creation module, a training module, and a second acquisition module, each of which functions specifically as follows:
the first acquisition module is used for acquiring a training data set; wherein the training data set comprises questionnaire answers and a manually labeled endowment mode;
the creating module is used for taking the questionnaire answers as input features, taking the artificially labeled endowment modes as output features, and creating a back propagation feedforward neural network model;
the training module is used for training the back propagation feedforward neural network model according to the training data set so as to obtain an automatic old-age mode recommendation model;
and the second acquisition module is used for acquiring the characteristic value of the questionnaire and inputting the characteristic value into the endowment mode automatic recommendation model so as to acquire an automatic recommendation result of the endowment mode.
The terminal device 7 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal device may include, but is not limited to, a processor 70, a memory 71. It will be appreciated by those skilled in the art that fig. 7 is merely an example of a terminal device 7 and does not constitute a limitation of the terminal device 7 and may comprise more or less components than shown, or some components may be combined, or different components, for example the terminal device may further comprise input output devices, network access devices, buses, etc.
The Processor 70 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 71 may be an internal storage unit of the terminal device 7, such as a hard disk or a memory of the terminal device 7. The memory 71 may also be an external storage device of the terminal device 7, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital Card (SD), a Flash memory Card (Flash Card), and the like, which are provided on the terminal device 7. Further, the memory 71 may also include both an internal storage unit and an external storage device of the terminal device 7. The memory 71 is used for storing the computer program and other programs and data required by the terminal device. The memory 71 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.

Claims (8)

1. An automatic recommendation method for an old-age mode is characterized by comprising the following steps:
acquiring a training data set; wherein the training data set includes questionnaire answers and manually labeled endowment patterns including, but not limited to: the system comprises an organization care, a home care, a community care, a sojourn care, a modern learning center, a house care, an intelligent care, a shared home care, a home care integration system and a medical care combined care;
taking the answer of the questionnaire as an input feature, taking the artificially labeled endowment mode as an output feature, and creating a back propagation feedforward neural network model;
training the back propagation feedforward neural network model according to the training data set to obtain an automatic old-age mode recommendation model;
acquiring a characteristic value of a questionnaire and inputting the characteristic value into the endowment mode automatic recommendation model to acquire an automatic recommendation result of the endowment mode;
wherein the obtaining a training data set comprises: acquiring the type of the endowment mode;
acquiring a problem corresponding to the type of the endowment mode;
designing an endowment mode questionnaire according to the endowment mode and the problems corresponding to the type of the endowment mode;
acquiring questionnaire answers aiming at the endowment mode questionnaire and an artificially labeled endowment mode corresponding to the questionnaire answers as the training data set;
the designing of an endowment mode questionnaire according to the endowment mode and questions corresponding to the type of the endowment mode comprises the following steps: designing an endowment mode questionnaire according to the endowment mode and the questions corresponding to the type of the endowment mode;
obtaining the reliability and efficiency of the endowment mode questionnaire;
if the credibility is lower than a preset credibility threshold and/or the efficiency is lower than a preset efficiency threshold, designing an endowment mode questionnaire again according to the endowment mode and the questions corresponding to the type of the endowment mode until the credibility reaches the preset credibility threshold and the efficiency reaches the preset efficiency threshold.
2. The automatic recommendation method for endowment model according to claim 1, wherein before creating a back propagation feedforward neural network model, using the questionnaire answers as input features and the artificially labeled endowment model as output features, the method comprises:
normalizing the questionnaire answers to obtain normalized questionnaire answers;
normalizing the artificially labeled endowment mode to obtain the normalized artificially labeled endowment mode.
3. The automatic old fashioned recommendation method of claim 2, wherein said normalized formula comprises:
Figure FDA0002943878910000021
wherein x isiValue, x, representing normalized dataminMinimum value, x, representing variation of normalized datamaxRepresents the maximum value of the variation of the normalized data,
Figure FDA0002943878910000022
representing the normalized data value.
4. The method of claim 1, wherein training a back propagation feedforward neural network model according to the training data set to obtain an aging mode automatic recommendation model comprises:
and training a back propagation feedforward neural network model according to the training data set through an error back propagation algorithm to obtain an automatic old-age mode recommendation model.
5. An automatic recommendation device for old age care mode, comprising:
the first acquisition module is used for acquiring a training data set; wherein the training data set includes questionnaire answers and manually labeled endowment patterns including, but not limited to: the system comprises an organization care, a home care, a community care, a sojourn care, a modern learning center, a house care, an intelligent care, a shared home care, a home care integration system and a medical care combined care;
the creating module is used for taking the questionnaire answers as input features, taking the artificially labeled endowment modes as output features, and creating a back propagation feedforward neural network model;
the training module is used for training the back propagation feedforward neural network model according to the training data set so as to obtain an automatic old-age mode recommendation model;
the second acquisition module is used for acquiring the characteristic value of the questionnaire and inputting the characteristic value into the endowment mode automatic recommendation model so as to acquire an automatic recommendation result of the endowment mode;
wherein the first obtaining module comprises:
the first acquisition unit is used for acquiring the type of the endowment mode;
a second acquisition unit configured to acquire a question corresponding to a type of the endowment mode;
the design unit is used for designing an endowment mode questionnaire according to the endowment mode and the problems corresponding to the type of the endowment mode;
a third obtaining unit, configured to obtain questionnaire answers to the endowment pattern questionnaire and an artificially labeled endowment pattern corresponding to the questionnaire answers as the training data set;
the design unit includes:
a design subunit, configured to design an endowment mode questionnaire according to the endowment mode and a question corresponding to the type of the endowment mode;
the obtaining subunit is used for obtaining the reliability and the efficiency of the endowment mode questionnaire;
and the judging subunit is used for designing an endowment mode questionnaire again according to the endowment mode and the problems corresponding to the type of the endowment mode if the credibility is lower than a preset credibility threshold and/or the efficiency is lower than a preset efficiency threshold until the credibility reaches the preset credibility threshold and the efficiency reaches the preset efficiency threshold.
6. The automatic old fashioned recommendation device of claim 5, further comprising:
the third acquisition module is used for normalizing the questionnaire answers to acquire the normalized questionnaire answers;
and the fourth acquisition module is used for normalizing the old-age mode of the artificial label so as to acquire the normalized old-age mode of the artificial label.
7. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 4 when executing the computer program.
8. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 4.
CN201811457321.9A 2018-11-30 2018-11-30 Automatic old age maintenance mode recommendation method and device and terminal equipment Active CN109636451B (en)

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 CN109636451A (en) 2019-04-16
CN109636451B true 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)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112801223A (en) * 2020-12-21 2021-05-14 深圳市音润科技有限公司 Three-axis acceleration training data labeling method for step counting and readable storage medium

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104915667B (en) * 2015-05-27 2018-04-24 华中科技大学 A kind of answering card identifying and analyzing method and system based on mobile terminal
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
US11080608B2 (en) * 2016-05-06 2021-08-03 Workfusion, 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
CN107169031B (en) * 2017-04-17 2020-05-19 广东工业大学 Picture material recommendation method based on depth expression
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
CN109636451A (en) 2019-04-16

Similar Documents

Publication Publication Date Title
Saurwein et al. Governance of algorithms: options and limitations
US20150095267A1 (en) Techniques to dynamically generate real time frequently asked questions from forum data
CN112508118B (en) Target object behavior prediction method aiming at data offset and related equipment thereof
CN110135942A (en) Products Show method, apparatus and computer readable storage medium
WO2021035975A1 (en) Method and apparatus for predicting hot-topic subject on basis of multiple evaluation dimensions, terminal, and medium
CN106097043A (en) The processing method of a kind of credit data and server
WO2020151170A1 (en) Position describing method, position describing apparatus, and terminal device
CN109241437A (en) A kind of generation method, advertisement recognition method and the system of advertisement identification model
CN113657547B (en) Public opinion monitoring method based on natural language processing model and related equipment thereof
CN111563810A (en) Credit wind control model generation method, credit evaluation system, machine-readable medium and device
CN114118192A (en) Training method, prediction method, device and storage medium of user prediction model
CN109213554A (en) A kind of icon layout method, computer readable storage medium and terminal device
CN109522858A (en) Plant disease detection method, device and terminal device
CN109636451B (en) Automatic old age maintenance mode recommendation method and device and terminal equipment
CN110533396A (en) Material binding method, material binding device and terminal device
CN111382336B (en) Data acquisition method and system
Lai et al. QFD optimization using linear physical programming
Huang et al. Economic inequality, distributive unfairness, and regime support in East Asia
CN110215703A (en) The selection method of game application, apparatus and system
CN107528969A (en) Management method, managing device and the terminal device of telephone call time
CN107071553A (en) Method, device and computer readable storage medium for modifying video and voice
Sahoo et al. Computation of Probabilistic linear programming problems involving normal and log-normal random variables with a joint constraint
CN110163279A (en) A kind of energy client segmentation method, apparatus and calculate equipment
CN113902576A (en) Deep learning-based information pushing method and device, electronic equipment and medium
CN107463416A (en) Application program management method, application program management device and intelligent terminal

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