CN112992348A - Endowment mode prediction system, method, equipment and storage medium - Google Patents
Endowment mode prediction system, method, equipment and storage medium Download PDFInfo
- Publication number
- CN112992348A CN112992348A CN201911214705.2A CN201911214705A CN112992348A CN 112992348 A CN112992348 A CN 112992348A CN 201911214705 A CN201911214705 A CN 201911214705A CN 112992348 A CN112992348 A CN 112992348A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- data
- prediction model
- particle
- endowment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000011156 evaluation Methods 0.000 claims abstract description 126
- 230000000474 nursing effect Effects 0.000 claims abstract description 65
- 230000036541 health Effects 0.000 claims abstract description 63
- 238000013528 artificial neural network Methods 0.000 claims abstract description 37
- 230000032683 aging Effects 0.000 claims abstract description 33
- 238000012549 training Methods 0.000 claims description 101
- 239000002245 particle Substances 0.000 claims description 99
- 210000002569 neuron Anatomy 0.000 claims description 58
- 230000006870 function Effects 0.000 claims description 20
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 4
- 238000007726 management method Methods 0.000 claims description 4
- 238000013523 data management Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 10
- 238000003062 neural network model Methods 0.000 description 8
- 230000007246 mechanism Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000013439 planning Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000019771 cognition Effects 0.000 description 2
- 230000001149 cognitive effect Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000005111 flow chemistry technique Methods 0.000 description 2
- 230000008531 maintenance mechanism Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Public Health (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Epidemiology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Pathology (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a system, a method, equipment and a storage medium for predicting an aging mode, wherein the system comprises: the health evaluation module is used for providing a health evaluation interface and collecting evaluation data input by a user in the health evaluation interface; the endowment mode prediction module is used for integrating the evaluation data into evaluation features of a preset model input format, inputting the evaluation features into a trained endowment mode prediction model, and acquiring output endowment mode data, wherein the endowment mode prediction model is a model constructed based on a neural network, and the endowment mode data comprises time length data of each nursing grade; and the display module is used for pushing the endowment mode data to a user. By adopting the invention, based on the user evaluation data and the neural network, the user evaluation data is automatically acquired and the time length of the aged living at different nursing levels in the future is predicted, so that the efficiency and the accuracy of the aged-care mode prediction are improved, and the aged-care resources are favorably and reasonably distributed.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a system, a method, equipment and a storage medium for predicting an aging mode.
Background
With the increasing of the elderly population in China, the life of the people in China is continuously prolonged, and the problem of old age care is increasingly severe. Aiming at the social problems of active population mobility, heavy burden of endowment of the solitary child and the like, the endowment mode of the institution, community endowment and the like is derived from the traditional single family endowment. The institutional endowment is a mode of providing systematic and standardized endowment services for the elderly by endowment affair execution mechanisms such as an endowment hospital, a welfare institute, an elderly apartment and the like. Compared with home care, institutional care is a care model for living care service through a payment mode. However, as the resources of the senior citizen become more and more tense, how to reasonably arrange the various resources of the senior citizen becomes a problem of great concern.
At present, in order to provide better service for the old, the old care institution arranges the old to reside in different care areas according to the evaluation result of the old, and provides different care services. The allocated endowment resources for different care areas are different. At present, in order to estimate the time length of the old people entering the staying and old age care mechanism, the following two schemes are provided: firstly, the living years of different nursing levels are set according to self definition, the living years of the nursing levels are calculated according to a certain proportion in the other type, the two methods have large deviation in the calculation of the living cost of the old and the requirement of living resources, and the living resource planning has no great guiding value, so that the resources of the old maintenance mechanism cannot be reasonably distributed, and certain inconvenience is brought to the management of the old maintenance mechanism.
Disclosure of Invention
Aiming at the problems in the prior art, the invention aims to provide a system, a method, equipment and a storage medium for predicting an aging mode, which can automatically acquire user evaluation data, automatically predict the time length of the aged living in different nursing grades in the future based on the user evaluation data and a neural network, and push the time length to the user, and are beneficial to reasonably distributing aging resources.
The embodiment of the invention provides an old-age care mode prediction system, which comprises:
the health evaluation module is used for providing a health evaluation interface and collecting evaluation data input by a user in the health evaluation interface;
the endowment mode prediction module is used for integrating the evaluation data into evaluation features of a preset model input format, inputting the evaluation features into a trained endowment mode prediction model, and acquiring output endowment mode data, wherein the endowment mode prediction model is a model constructed based on a neural network, and the endowment mode data comprises time length data of each nursing grade;
and the display module is used for pushing the endowment mode data to a user.
Optionally, the health assessment interface provided by the health assessment module includes assessment questionnaires of a plurality of assessment categories, and the health assessment module collects assessment data input by the user in the health assessment interface, includes collecting response data input by the user in the health assessment interface, and calculates health assessment scores of the plurality of assessment categories of the user according to the response data;
the evaluation feature comprises a plurality of evaluation feature values, each of the evaluation feature values corresponding to a health evaluation score;
the endowment mode prediction module integrates the evaluation data into the evaluation characteristics of a preset model input format, and integrates the health evaluation scores according to the sequence of evaluation characteristic values in the preset model input format to obtain the evaluation characteristics.
Optionally, the system further includes a prediction model training module, configured to construct the endowment model prediction model by:
the prediction model training module builds an aging mode prediction model based on the adaptive radial basis function neural network;
the prediction model training module collects the evaluation characteristics of a plurality of users and the duration data of each user corresponding to each nursing grade and adds the evaluation characteristics and the duration data into a training set;
the prediction model training module takes the evaluation characteristics of each user and the duration data of each nursing grade as a training sample, and trains the aging mode prediction model by adopting the training set.
Optionally, the predicting model training module collects evaluation features of a plurality of users and duration data of each user corresponding to each care level, and includes:
the prediction model training module acquires historical user data from a historical data management system of the endowment institution;
the prediction model training module screens out historical data of users who have left the endowment institution from the historical user data, wherein the historical data comprises evaluation data of the users and duration data of the users corresponding to various care levels;
and the prediction model training module integrates the evaluation data of the user into the evaluation characteristics of a preset model input format.
Optionally, the prediction model training module constructs an aging-support mode prediction model based on an adaptive radial basis function neural network, including:
the prediction model training module determines the number of neurons in an input layer, a hidden layer and an output layer of the endowment mode prediction model, wherein the number of the neurons in the input layer is the number M of evaluation characteristic values in evaluation characteristics, the number of the neurons in the hidden layer is K, and the number of the neurons in the output layer is the number of care grades;
the prediction model training module adopts the following formula to construct the connection of neurons in an input layer, a hidden layer and an output layer in the endowment mode prediction model:
wherein t represents time, wk(t) represents the connection weight of the kth neuron in the hidden layer and the output layer, K ∈ (1, K), x (t) ═ x1(t)，x2(t)，x3(t)，…，xM(t)]Representing input numbers of input layersAccording to y (t), the actual output data of the endowment model is shown as phik(x (t)) is the output data of the k neuron of the hidden layer;
wherein, the output data phi of the kth neuron of the hidden layer is calculated by adopting the following formulak(x(t))：
Wherein, mukRepresenting the central value, σ, of the k-th neuron of the hidden layerkRepresenting the central width of the k-th neuron of the hidden layer.
Optionally, the prediction model training module trains the aging pattern prediction model with the training set, including training the aging pattern prediction model for each training sample x (t) in the training set in sequence with the following steps:
representing parameters of the radial basis function neural network as particles in the particle swarm, and initializing the position and the speed of each particle;
inputting the training sample x (t) into the endowment mode prediction model, and calculating a fitness value of each particle;
calculating the inertia weight and the global optimal position of each particle according to the fitness value of the particle;
updating the position and the speed of each particle according to the inertia weight of each particle, the global optimal position of the particle and the historical optimal position of the particle;
and finding out an optimal network structure according to the global optimal positions of the particles, and updating the number of the neural network hidden layer neurons corresponding to each particle according to the difference between the number of each particle neuron and the optimal number of the particle neurons.
Optionally, when the prediction model training module trains the endowment model prediction model, the position and the speed of each particle are initialized by using the following formula:
wherein, aiDenotes the position of the ith particle, i ∈ (1, s), s denotes the total number of particles, μi,k，σi,kAnd wi,kRespectively representing the central value, the central width and the connection weight value of the kth hidden layer neuron in the ith particle, KiNumber of hidden layer neurons, v, representing the ith particle representationiDenotes the velocity of the ith particle, DiRepresents the dimension of the ith particle;
for the input x (t) of the neural network, the fitness value of each particle is calculated using the following formula:
where T represents the number of training samples input by the neural network, yd(t) representing an expected output of the aging mode prediction model;
the prediction model training module calculates the inertia weight of each particle by adopting the following formula:
ωi(t)＝S(t)tAi(t)
wherein, S (t) and Ai(t) is calculated by the following formula:
S(t)＝fmin(a(t))/fmax(a(t))
Ai(t)＝f(g(t))/f(ai(t))
wherein f ismin(a(t))、fmax(a (t)) are the minimum fitness value and the maximum fitness value of the current moment respectively;
the prediction model training module calculates the historical optimal position p of the particle by adopting the following formulai(t)：
The prediction model training module calculates the global optimal position g (t) of the particle by adopting the following formula:
the prediction model training module updates the position and the speed of each particle by adopting the following formula:
vi(t+1)＝ωi(t)vi(t)+c1r1(pi(t)-ai(t))+c2r2(g(t)-ai(t))
ai(t)＝ai(t-1)+αvi(t)
wherein, c1And c2Respectively is a particle swarm acceleration constant, alpha is a particle swarm balance weight, r1And r2Respectively obtaining a particle historical optimal coefficient and a global optimal position coefficient;
the prediction model training module finds out an optimal network structure according to the global optimal position g (t), and the number of hidden layer neurons of the optimal neural network at the moment is KbestAnd updating the number of hidden layer neurons corresponding to each particle according to the difference between the number of each particle neuron and the optimal number of the particle neurons as follows:
optionally, the system further includes a cost prediction module, configured to obtain, from the cost management system, nursing costs in unit time corresponding to each nursing level, calculate, according to the predicted duration of each nursing level, the predicted nursing costs of the user in each nursing level, and count to obtain the total predicted nursing costs of the user;
the presentation module is further configured to push the total predicted care cost to a user.
The embodiment of the invention also provides a method for predicting the old-keeping mode, which comprises the following steps:
the health evaluation module provides a health evaluation interface and collects evaluation data input by a user in the health evaluation interface;
integrating the assessment data into assessment features of a preset model input format by an endowment mode prediction module, inputting the assessment features into a trained endowment mode prediction model, and acquiring output endowment mode data, wherein the endowment mode prediction model is a model constructed based on a neural network, and the endowment mode data comprises duration data of each nursing grade;
and the display module pushes the endowment mode data to the user.
An embodiment of the present invention further provides an old-age support mode prediction device, including:
a processor;
a memory having stored therein executable instructions of the processor;
wherein the processor is configured to perform the steps of the endowment mode prediction method via execution of the executable instructions.
An embodiment of the present invention further provides a computer-readable storage medium, which is used for storing a program, and when the program is executed, the method for predicting the endowment mode is implemented.
An embodiment of the present invention further provides an old-age support mode prediction device, including:
a processor;
a memory having stored therein executable instructions of the processor;
wherein the processor is configured to perform the steps of the endowment mode prediction method via execution of the executable instructions.
An embodiment of the present invention further provides a computer-readable storage medium, which is used for storing a program, and when the program is executed, the method for predicting the endowment mode is implemented.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
By adopting the method and the device, the user evaluation data is automatically collected, the time lengths of the old people living in different nursing grades in the future are predicted by adopting the trained neural network model, and the prediction result is pushed to the user, so that the problem that the time lengths of the old people living in different nursing grades in the future are difficult to predict is solved, and the planning of living resources and the planning of living in of different old people in the old people can be well assisted in the aged-care community; the input data of the neural network model are health assessment data of the old, so that the health level of the old can be comprehensively considered for intelligent prediction, and compared with a user-defined living age limit method and a proportion distribution method in the prior art, the time length of the old living in different nursing states can be predicted more accurately.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, with reference to the accompanying drawings.
FIG. 1 is a block diagram of an embodiment of a endowment model prediction system;
FIG. 2 is a schematic diagram of a endowment model prediction system according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for predicting endowment modes according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an old-age mode prediction device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
In order to provide more reasonable check-in service for the old, the old can carry out various health evaluations after check-in, such as functional family evaluation, fall history evaluation, standing walking timing evaluation, self-selected walking speed evaluation, audio-visual evaluation, psychological state evaluation, modified Papanicolaou index evaluation, Montreal cognition evaluation, concise cognition evaluation, comprehensive decline evaluation and the like, so as to comprehensively evaluate the health state of the old. In order to solve the technical problems in the prior art, an embodiment of the invention provides a method for predicting an old age care mode, wherein the predicted old age care mode is the residence time of the old in each nursing grade area.
As shown in fig. 1 and fig. 2, an embodiment of the present invention provides an aging mode prediction system, including:
the health evaluation module M100 is used for providing a health evaluation interface and collecting evaluation data input by a user in the health evaluation interface;
the endowment mode prediction module M200 is used for integrating the evaluation data into the evaluation features of a preset model input format, inputting the evaluation features into a trained endowment mode prediction model, and acquiring output endowment mode data, wherein the endowment mode prediction model is a model constructed based on a neural network, and the endowment mode data comprises duration data of each nursing grade;
the display module M300 is configured to push the endowment mode data to the user, where the pushing may be to provide an endowment mode data viewing interface for the user to directly click and view, or may be to send the endowment mode data viewing interface to the terminal of the user for the user to view.
For each user, the combination of the predicted time length corresponding to each care level is the predicted endowment mode of the user. The nursing grade can be obtained by dividing a preset nursing grade dividing method in the nursing institution, and the number of the nursing grades can be selected according to the requirement.
According to the invention, the health assessment module M100 automatically collects the assessment data of the user firstly, and the nursing grade duration prediction is carried out by combining the health assessment data of the user, so that the prediction accuracy is improved, furthermore, the aged people can predict the durations of the aged people living in different nursing grades in the future by adopting the trained neural network model through the aged people pattern prediction module M200, the problem that the durations of the aged people living in different nursing grades in the future are difficult to predict is solved, and the aged people pattern prediction efficiency is improved. For the endowment mechanism, can know in advance the regional old man's quantity of coming into different nursing levels in the future, not only can rationally arrange the bed resource, can help endowment mechanism go to rationally arrange the old man to go into moreover, improve endowment mechanism availability factor. According to the invention, the display module M300 is used for pushing the predicted endowment mode data to the user, so that the user can conveniently check the endowment mode data.
In this embodiment, the assessment data includes health assessment scores for a plurality of assessment categories for the user, the assessment features include a plurality of assessment feature values, each of the assessment feature values corresponding to one of the health assessment scores. The assessment categories may be selected from one or more of functional family assessment, fall history assessment, standing walking timing assessment, self-selected walking speed assessment, audio visual assessment, mental state assessment, modified pap index assessment, montreal cognitive assessment, concise cognitive assessment, comprehensive decline assessment, as desired. The corresponding relationship between the evaluation feature value and the health evaluation score may be that the health evaluation score is directly used as the evaluation feature value, or the health evaluation score is divided into a plurality of sections, each section corresponds to one evaluation feature value, for example, the evaluation feature value of one evaluation category is set to 0,1, and 2, for the health evaluation score of more than 90, the corresponding evaluation feature value is 0, for the health evaluation score of 60-90, the corresponding evaluation feature value is 1, for the health evaluation score of less than 60, the corresponding evaluation feature value is 2, which is more convenient for classifying and counting the users.
The health assessment interface provided by the health assessment module M100 includes assessment questionnaires of a plurality of assessment categories, and the health assessment module M100 collects assessment data input by the user in the health assessment interface, includes collecting response data input by the user in the health assessment interface, and calculates health assessment scores of the plurality of assessment categories of the user according to the response data.
The integration of the assessment data into the assessment features of the preset model input format by the endowment mode prediction module M200 includes: and integrating the health assessment scores according to the sequence of the assessment characteristic values in the preset model input format to obtain the assessment characteristics. For example, the preset model input format includes four evaluation categories: functional family evaluation, fall history evaluation, standing walking timing evaluation and self-selected walking speed evaluation, and then the evaluation characteristic values of the four evaluation categories are required to be arranged according to the sequencing sequence in the preset model input format to form a characteristic vector of the health evaluation score.
As shown in fig. 2, an embodiment of the present invention further provides a method for predicting an aging mode, where the method includes:
s100: the health evaluation module provides a health evaluation interface and collects evaluation data input by a user in the health evaluation interface;
s200: integrating the assessment data into assessment features of a preset model input format by an endowment mode prediction module, inputting the assessment features into a trained endowment mode prediction model, and acquiring output endowment mode data, wherein the endowment mode prediction model is a model constructed based on a neural network, and the endowment mode data comprises duration data of each nursing grade;
s300: and the display module pushes the endowment mode data to the user.
Each step in the endowment mode prediction method of the present invention may be implemented by using a function implementation manner of each module in the endowment mode prediction system, for example, step S100 may be implemented by using a function implementation manner of the health assessment module M100, step S200 may be implemented by using a function implementation manner of the endowment mode prediction module M200, and step S300 may be implemented by using a function implementation manner of the display module M300, that is, providing an endowment mode data display interface or pushing endowment mode data to a user terminal, which is not described herein again.
In this embodiment, the endowment mode prediction system further includes a prediction model training module, the prediction model training module is configured to perform an endowment mode prediction model training step, and the endowment mode prediction method further includes S400: the method comprises the following steps of training an endowment mode prediction model by a prediction model training module, specifically, the endowment mode prediction model training comprises the following steps:
s410: the prediction model training module builds an aging mode prediction model based on the adaptive radial basis function neural network;
the radial basis function neural network is a forward network with good performance, has the performances of optimal approximation, concise training, high learning convergence speed and overcoming the problem of local minimum, and has been proved at present to be capable of approximating any continuous function with any precision. It has been widely used in the fields of pattern recognition, nonlinear control, and image processing. The basic idea of the radial basis function neural network is to use a Radial Basis Function (RBF) as a 'basis' of a hidden unit to form a space of a hidden layer, wherein the hidden layer transforms an input vector and converts low-dimensional mode input data into a high-order space, so that linear inseparability in the low-dimensional space is converted into linear inseparability in the high-dimensional space. The method is suitable for different crowds and different age groups by adopting the self-adaptive radial basis function neural network model, and the applicability of the prediction model is greatly improved.
S420: the prediction model training module collects the evaluation characteristics of a plurality of users and the time length data of each user corresponding to each nursing grade and adds the evaluation characteristics of each user and the time length data of each nursing grade into a training set, and the evaluation characteristics of each user and the time length data of each nursing grade are used as a training sample;
s430: the prediction model training module trains the endowment model prediction model by adopting the training set.
In this embodiment, in step S420, the predicting model training module collects evaluation features of a plurality of users and duration data corresponding to each care level of each user, and includes the following steps:
s421: the prediction model training module acquires historical user data from a historical data management system of the endowment institution;
s422: the prediction model training module screens out historical data of users who have left the endowment institution from the historical user data, wherein the historical data comprises evaluation data of the users and duration data of the users corresponding to various care levels;
s423: and the prediction model training module integrates the evaluation data of the user into the evaluation characteristics of a preset model input format.
Therefore, when the endowment model prediction model is trained, the historical data of the user in the endowment institution can be analyzed, and the selection condition of the endowment model of the user in the endowment institution can be reflected more truly. If the amount of the historical user data stored in the current endowment institution is insufficient, further expansion can be performed on the basis, for example, one to two health assessment characteristic values in the historical data of a user are adjusted, the duration of each nursing grade in the endowment mode is correspondingly adjusted, and a new training sample is generated. Or, the data of the user living in the current endowment institution can be collected, the existing nursing grade duration and evaluation features of the user can be obtained, and the nursing grade duration lacking for the user can be filled to obtain a new training sample.
In this embodiment, the step S410: the prediction model training module builds an aging mode prediction model based on the adaptive radial basis function neural network, and comprises the following steps:
s411: the prediction model training module determines input and output variables of a neural network model: taking M groups of historical data as the input of the model, taking M +1 to M +6 as output variables, namely residence time of zero-level nursing, first-level nursing, second-level nursing, third-level nursing, fourth-level nursing and fifth-level nursing, and taking 10 evaluations as the input in the current practical application, namely 10 inputs and 6 outputs of the model. But the invention is not limited thereto.
S412: the prediction model training module determines the number of neurons in an input layer, a hidden layer and an output layer of the endowment mode prediction model and determines the connection mode of a neural network M-K-6, wherein the number of neurons in the input layer is the number M of evaluation characteristic values in evaluation characteristics, the number of neurons in the hidden layer is K, and the number of neurons in the output layer is the number of care grades, and in the embodiment, the number of neurons is 6;
s413: the prediction model training module assigns values to parameters of the neural network; let the total number of T training samples, and the input of the neural network at the T-th moment is x (T) ═ x1(t)，x2(t)，x3(t)，x4(t)，x5(t)，x6(t)，x7(t)，x8(t)，x9(t)，x10(t)]The desired output of the neural network is denoted as yd(t), the actual output is expressed as y (t), and the relation of the neurons in the input layer, the hidden layer and the output layer in the endowment mode prediction model is constructed by adopting the following formula:
wherein, wk(t) represents the connection weight of the kth neuron of the hidden layer and the output layer, K belongs to (1, K), phik(x (t)) is the output data of the k neuron of the hidden layer;
wherein, the output data phi of the kth neuron of the hidden layer is calculated by adopting the following formulak(x(t))：
Wherein, mukRepresenting the central value, σ, of the k-th neuron of the hidden layerkRepresenting the central width of the k-th neuron of the hidden layer.
In this embodiment, the step S430: training the aging pattern prediction model by adopting the training set, wherein the training of the aging pattern prediction model for each training sample x (t) in the training set comprises the following steps:
s431: the prediction model training module represents parameters of the radial basis function neural network as particles in the particle swarm, and initializes the position and the speed of each particle;
s432: the prediction model training module inputs the training sample x (t) into the endowment mode prediction model and calculates the fitness value of each particle;
s433: the prediction model training module calculates the inertia weight and the global optimal position of each particle according to the fitness value of the particle;
s434: the prediction model training module updates the position and the speed of each particle according to the inertia weight of each particle, the global optimal position of the particle and the historical optimal position of the particle;
s435: and the prediction model training module finds out an optimal network structure according to the global optimal positions of the particles, and updates the number of neural network hidden layer neurons corresponding to each particle according to the difference between the number of each particle neuron and the optimal number of the particle neurons.
Specifically, the step S431 includes: the prediction model training module initializes a particle swarm acceleration constant c1And c2，c1∈(0,1)，c2E (0, 1); setting a particle swarm balance weight alpha to be [0,1 ∈ ]]Expressing parameters of the radial basis function neural network as particles in the particle swarm, and initializing the position and the speed of each particle by adopting the following formula:
wherein, aiDenotes the position of the ith particle, i ∈ (1, s), s denotes the total number of particles, μi,k，σi,kAnd wi,kRespectively representing the central value, the central width and the connection weight value of the kth hidden layer neuron in the ith particle, KiRepresenting the number of hidden layer neurons, μ, of the ith particle representationi,k，σi,kAnd wi,kThe initial value of (1) is an arbitrary number of (0,1), KiIs an arbitrary positive integer, viDenotes the velocity of the ith particle, DiRepresents the dimension of the ith particle;
in step S432, for the input x (t) of the neural network, the prediction model training module calculates the fitness value of each particle by using the following formula:
where T represents the number of training samples input by the neural network, yd(t) representing an expected output of the aging mode prediction model;
in step S433, the predictive model training module calculates the inertia weight of each particle by using the following formula:
ωi(t)＝S(t)tAi(t) (6)
wherein, S (t) and Ai(t) is calculated by the following formula:
S(t)＝fmin(a(t))/fmax(a(t)) (7)
Ai(t)＝f(g(t))/f(ai(t)) (8)
wherein f ismin(a(t))、fmax(a (t)) are the minimum fitness value and the maximum fitness value of the current moment respectively;
the prediction model training module calculates the historical optimal position p of the particle by adopting the following formulai(t)：
The prediction model training module calculates the global optimal position g (t) of the particle by adopting the following formula:
in step S434, the prediction model training module updates the position and the velocity of each particle by using the following formula:
vi(t+1)＝ωi(t)vi(t)+c1r1(pi(t)-ai(t))+c2r2(g(t)-ai(t)) (11)
ai(t)＝ai(t-1)+αvi(t) (12)
wherein, c1And c2Respectively is a particle swarm acceleration constant, alpha is a particle swarm balance weight, r1And r2Respectively as the historical optimum coefficient and the global optimum position coefficient, r1And r2Take [0,1]Any number of (a);
the step S435 includes: the prediction model training module finds out an optimal network structure according to the global optimal position g (t), and the number of hidden layer neurons of the optimal neural network at the moment is KbestAnd updating the number of hidden layer neurons corresponding to each particle according to the difference between the number of each particle neuron and the optimal number of the particle neurons as follows:
after the process of the steps S431 to S435 is completed for one training sample x (t), the prediction model training module inputs the next training sample x (t +1) until all the training samples are input into the neural network model.
In this embodiment, the system further comprises a cost prediction module for predicting care costs by:
s510: acquiring nursing cost in unit time corresponding to each nursing grade from a cost management system;
s520: calculating the predicted nursing cost of the user in each nursing grade according to the predicted time length of each nursing grade;
s530: and counting to obtain the total predicted nursing cost of the user.
The display module M300 is further configured to push the total predicted nursing cost predicted by the cost prediction module to the user. The user can conveniently check the total predicted nursing cost of the user, and the decision of the user is facilitated.
Therefore, the method can not only estimate the length of time that the old people live in different nursing levels in advance, is very beneficial to a guiding mechanism to plan the bed resources of each nursing level in advance, but also can enable the old people to know the cost of live in advance, and has important significance for reasonably arranging live in. For the old man, not only can predict the length of time of the old man in different nursing business states, help the old man to know the situation of coming in advance, also can help the old man to calculate the expense condition better, promote user experience better.
The embodiment of the invention also provides old-age care mode prediction equipment, which comprises a processor; a memory having stored therein executable instructions of the processor; wherein the processor is configured to perform the steps of the endowment mode prediction method via execution of the executable instructions.
As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a method, system, or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
An electronic device 600 according to this embodiment of the invention is described below with reference to fig. 4. The electronic device 600 shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 4, the electronic device 600 is embodied in the form of a general purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 that connects the various system components (including the storage unit 620 and the processing unit 610), a display unit 640, and the like.
Wherein the storage unit stores program code executable by the processing unit 610 to cause the processing unit 610 to perform steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic prescription flow processing method section of the present specification. For example, the processing unit 610 may perform the steps as shown in fig. 3.
The storage unit 620 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)6201 and/or a cache memory unit 6202, and may further include a read-only memory unit (ROM) 6203.
The memory unit 620 may also include a program/utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including, but not limited to: a processing system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 600, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 600 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 650. Also, the electronic device 600 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via the bus 630. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
An embodiment of the present invention further provides a computer-readable storage medium, which is used for storing a program, and when the program is executed, the method for predicting the endowment mode is implemented. In some possible embodiments, aspects of the present invention may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic prescription flow processing method section of this specification, when the program product is run on the terminal device.
Referring to fig. 5, a program product 800 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out processes of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
The endowment mode prediction system, the endowment mode prediction method, the endowment mode prediction equipment and the storage medium have the following advantages:
by adopting the method, the trained neural network model is adopted to predict the time lengths of the old people living in different nursing grades in the future, so that the problem that the time lengths of the old people living in different nursing grades in the future are difficult to predict is solved, and the planning of living resources and the planning of living in of different old people in the aged-care community can be well assisted; the input data of the neural network model are health assessment data of the old, so that the health level of the old can be comprehensively considered for intelligent prediction, and compared with a user-defined living age limit method and a proportion distribution method in the prior art, the time length of the old living in different nursing states can be predicted more accurately.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, embodiments of the system, apparatus, and computer storage medium are described in relative terms as substantially similar to the method embodiments, where relevant, reference may be had to the description of the method embodiments.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (11)
1. An aging pattern prediction system, comprising:
the health evaluation module is used for providing a health evaluation interface and collecting evaluation data input by a user in the health evaluation interface;
the endowment mode prediction module is used for integrating the evaluation data into evaluation features of a preset model input format, inputting the evaluation features into a trained endowment mode prediction model, and acquiring output endowment mode data, wherein the endowment mode prediction model is a model constructed based on a neural network, and the endowment mode data comprises time length data of each nursing grade;
and the display module is used for pushing the endowment mode data to a user.
2. The aging model prediction system of claim 1, wherein the health assessment module provides a health assessment interface including assessment questionnaires of a plurality of assessment categories, and the health assessment module collects assessment data input by the user in the health assessment interface, including collecting response data input by the user in the health assessment interface, and calculates health assessment scores of the plurality of assessment categories of the user according to the response data;
the evaluation feature comprises a plurality of evaluation feature values, each of the evaluation feature values corresponding to a health evaluation score;
the endowment mode prediction module integrates the evaluation data into the evaluation characteristics of a preset model input format, and integrates the health evaluation scores according to the sequence of evaluation characteristic values in the preset model input format to obtain the evaluation characteristics.
3. The aging mode prediction system of claim 1, further comprising a prediction model training module for constructing the aging mode prediction model by:
the prediction model training module builds an aging mode prediction model based on the adaptive radial basis function neural network;
the prediction model training module collects the evaluation characteristics of a plurality of users and the duration data of each user corresponding to each nursing grade and adds the evaluation characteristics and the duration data into a training set;
the prediction model training module takes the evaluation characteristics of each user and the duration data of each nursing grade as a training sample, and trains the aging mode prediction model by adopting the training set.
4. The aging mode prediction method of claim 3, wherein the predictive model training module collects evaluation features of a plurality of users and time duration data corresponding to each care level of each user, comprising:
the prediction model training module acquires historical user data from a historical data management system of the endowment institution;
the prediction model training module screens out historical data of users who have left the endowment institution from the historical user data, wherein the historical data comprises evaluation data of the users and duration data of the users corresponding to various care levels;
and the prediction model training module integrates the evaluation data of the user into the evaluation characteristics of a preset model input format.
5. The aging mode prediction system of claim 3, wherein the prediction model training module builds an aging mode prediction model based on an adaptive radial basis function neural network, comprising:
the prediction model training module determines the number of neurons in an input layer, a hidden layer and an output layer of the endowment mode prediction model, wherein the number of the neurons in the input layer is the number M of evaluation characteristic values in evaluation characteristics, the number of the neurons in the hidden layer is K, and the number of the neurons in the output layer is the number of care grades;
the prediction model training module adopts the following formula to construct the connection of neurons in an input layer, a hidden layer and an output layer in the endowment mode prediction model:
wherein t represents time, wk(t) represents the connection weight of the kth neuron in the hidden layer and the output layer, K ∈ (1, K), x (t) ═ x1(t)，x2(t)，x3(t)，…，xM(t)]Input data representing an input layer, y (t) actual output data, phi, of said endowment-mode prediction modelk(x (t)) is the output data of the k neuron of the hidden layer;
wherein, the output data phi of the kth neuron of the hidden layer is calculated by adopting the following formulak(x(t))：
Wherein, mukRepresenting the central value, σ, of the k-th neuron of the hidden layerkRepresenting the central width of the k-th neuron of the hidden layer.
6. The aging pattern prediction system of claim 5, wherein the prediction model training module trains the aging pattern prediction model with the training set, including training the aging pattern prediction model for each training sample x (t) in the training set in turn with the steps of:
representing parameters of the radial basis function neural network as particles in the particle swarm, and initializing the position and the speed of each particle;
inputting the training sample x (t) into the endowment mode prediction model, and calculating a fitness value of each particle;
calculating the inertia weight and the global optimal position of each particle according to the fitness value of the particle;
updating the position and the speed of each particle according to the inertia weight of each particle, the global optimal position of the particle and the historical optimal position of the particle;
and finding out an optimal network structure according to the global optimal positions of the particles, and updating the number of the neural network hidden layer neurons corresponding to each particle according to the difference between the number of each particle neuron and the optimal number of the particle neurons.
7. The aging mode prediction system of claim 6, wherein when the prediction model training module trains the aging mode prediction model, the position and velocity of each particle is initialized by the following formula:
wherein, aiDenotes the position of the ith particle, i ∈ (1, s), s denotes the total number of particles, μi,k，σi,kAnd wi,kRespectively representing the central value, the central width and the connection weight value of the kth hidden layer neuron in the ith particle, KiNumber of hidden layer neurons, v, representing the ith particle representationiDenotes the velocity of the ith particle, DiRepresents the dimension of the ith particle;
for the input x (t) of the neural network, the fitness value of each particle is calculated using the following formula:
where T represents the number of training samples input by the neural network, yd(t) representing an expected output of the aging mode prediction model;
the prediction model training module calculates the inertia weight of each particle by adopting the following formula:
ωi(t)＝S(t)tAi(t)
wherein, S (t) and Ai(t) is calculated by the following formula:
S(t)＝fmin(a(t))/fmax(a(t))
Ai(t)＝f(g(t))/f(ai(t))
wherein f ismin(a(t))、fmax(a (t)) are the minimum fitness value and the maximum fitness value of the current moment respectively;
the prediction model training module calculates the historical optimal position p of the particle by adopting the following formulai(t)：
The prediction model training module calculates the global optimal position g (t) of the particle by adopting the following formula:
the prediction model training module updates the position and the speed of each particle by adopting the following formula:
vi(t+1)＝ωi(t)vi(t)+c1r1(pi(t)-ai(t))+c2r2(g(t)-ai(t))
ai(t)＝ai(t-1)+αvi(t)
wherein, c1And c2Respectively is a particle swarm acceleration constant, alpha is a particle swarm balance weight, r1And r2Respectively obtaining a particle historical optimal coefficient and a global optimal position coefficient;
the prediction model training module finds out an optimal network structure according to the global optimal position g (t), and the number of hidden layer neurons of the optimal neural network at the moment is KbestAnd updating the number of hidden layer neurons corresponding to each particle according to the difference between the number of each particle neuron and the optimal number of the particle neurons as follows:
8. the aging mode prediction system of claim 1, further comprising a cost prediction module, configured to obtain nursing costs in unit time corresponding to each nursing level from the cost management system, calculate predicted nursing costs of the user in each nursing level according to the predicted time length of each nursing level, and count to obtain the total predicted nursing costs of the user;
the presentation module is further configured to push the total predicted care cost to a user.
9. A method for predicting an aging mode is characterized by comprising the following steps:
the health evaluation module provides a health evaluation interface and collects evaluation data input by a user in the health evaluation interface;
integrating the assessment data into assessment features of a preset model input format by an endowment mode prediction module, inputting the assessment features into a trained endowment mode prediction model, and acquiring output endowment mode data, wherein the endowment mode prediction model is a model constructed based on a neural network, and the endowment mode data comprises duration data of each nursing grade;
and the display module pushes the endowment mode data to the user.
10. An old-age pattern prediction apparatus, comprising:
a processor;
a memory having stored therein executable instructions of the processor;
wherein the processor is configured to perform the steps of the endowment mode prediction method of claim 9 via execution of the executable instructions.
11. A computer-readable storage medium storing a program which, when executed, performs the steps of the endowment mode prediction method of claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911214705.2A CN112992348A (en) | 2019-12-02 | 2019-12-02 | Endowment mode prediction system, method, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911214705.2A CN112992348A (en) | 2019-12-02 | 2019-12-02 | Endowment mode prediction system, method, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112992348A true CN112992348A (en) | 2021-06-18 |
Family
ID=76331104
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911214705.2A Pending CN112992348A (en) | 2019-12-02 | 2019-12-02 | Endowment mode prediction system, method, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112992348A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113486255A (en) * | 2021-09-08 | 2021-10-08 | 南京麦豆健康管理有限公司 | Internet-based postpartum online consultation matching system and method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130197936A1 (en) * | 2012-02-01 | 2013-08-01 | Richard R. Willich | Predictive Healthcare Diagnosis Animation |
| CN106169167A (en) * | 2016-08-30 | 2016-11-30 | 南京索酷信息科技股份有限公司 | A kind of wisdom the endowment management method of service cloud platform, Apparatus and system |
| CN107863153A (en) * | 2017-11-24 | 2018-03-30 | 中南大学 | A kind of human health characteristic modeling measuring method and platform based on intelligent big data |
| WO2019007794A1 (en) * | 2017-07-05 | 2019-01-10 | Koninklijke Philips N.V. | System and method for providing prediction models for predicting a health determinant category contribution in savings generated by a clinical program |
| CN109726904A (en) * | 2018-12-19 | 2019-05-07 | 泰康保险集团股份有限公司 | Medical treatment and nursing assessment result generation method, equipment and storage medium |
| CN109767371A (en) * | 2017-11-09 | 2019-05-17 | 北京宏源丽家养老服务有限公司 | A kind of length based on Internet of Things shines old man's wisdom maintenance service system |
| CN110458440A (en) * | 2019-08-06 | 2019-11-15 | 南京信息工程大学 | A kind of ecology endowment suitability quantification overall analysis system |
-
2019
- 2019-12-02 CN CN201911214705.2A patent/CN112992348A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130197936A1 (en) * | 2012-02-01 | 2013-08-01 | Richard R. Willich | Predictive Healthcare Diagnosis Animation |
| CN106169167A (en) * | 2016-08-30 | 2016-11-30 | 南京索酷信息科技股份有限公司 | A kind of wisdom the endowment management method of service cloud platform, Apparatus and system |
| WO2019007794A1 (en) * | 2017-07-05 | 2019-01-10 | Koninklijke Philips N.V. | System and method for providing prediction models for predicting a health determinant category contribution in savings generated by a clinical program |
| CN109767371A (en) * | 2017-11-09 | 2019-05-17 | 北京宏源丽家养老服务有限公司 | A kind of length based on Internet of Things shines old man's wisdom maintenance service system |
| CN107863153A (en) * | 2017-11-24 | 2018-03-30 | 中南大学 | A kind of human health characteristic modeling measuring method and platform based on intelligent big data |
| CN109726904A (en) * | 2018-12-19 | 2019-05-07 | 泰康保险集团股份有限公司 | Medical treatment and nursing assessment result generation method, equipment and storage medium |
| CN110458440A (en) * | 2019-08-06 | 2019-11-15 | 南京信息工程大学 | A kind of ecology endowment suitability quantification overall analysis system |
Non-Patent Citations (2)
| Title |
|---|
| 李晓俞;张文光;席杨娟;王巧倩;韩雪;: "医养结合模式下老年人分级照护评估研究现状", 护理研究, no. 09, 21 May 2019 (2019-05-21) * |
| 李晓俞等: ""医养结合模式下老年人分级照护评估研究现状"", 《护理研究》, vol. 33, no. 9, 21 May 2019 (2019-05-21), pages 1545 - 1548 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113486255A (en) * | 2021-09-08 | 2021-10-08 | 南京麦豆健康管理有限公司 | Internet-based postpartum online consultation matching system and method |
| CN113486255B (en) * | 2021-09-08 | 2021-11-16 | 南京麦豆健康管理有限公司 | Internet-based postpartum online consultation matching system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fong et al. | Composite Monte Carlo decision making under high uncertainty of novel coronavirus epidemic using hybridized deep learning and fuzzy rule induction | |
| Yousefi et al. | Chaotic genetic algorithm and Adaboost ensemble metamodeling approach for optimum resource planning in emergency departments | |
| Datseris et al. | Agents. jl: a performant and feature-full agent-based modeling software of minimal code complexity | |
| WO2020107806A1 (en) | Recommendation method and device | |
| Shukla | Neuro-genetic prediction of software development effort | |
| CN103226566B (en) | For optimizing the system and method for group | |
| CN104572583B (en) | Method and system for data densification | |
| CN110890146B (en) | Bedside intelligent interaction system for intelligent ward | |
| Waller et al. | Using disability data to estimate design exclusion | |
| KR102088296B1 (en) | Method and apparatus of predicting disease correlation based on air quality data | |
| CN111696656B (en) | Doctor evaluation method and device of Internet medical platform | |
| Jung et al. | Self-attention-based deep learning network for regional influenza forecasting | |
| Hu et al. | A practice mining system for the delivery of sustainable retirement villages | |
| Tang et al. | Multi-feature based Question–Answerer Model Matching for predicting response time in CQA | |
| CN112992348A (en) | Endowment mode prediction system, method, equipment and storage medium | |
| CN111126629A (en) | Model generation method, system, device and medium for identifying brushing behavior | |
| Parimanam et al. | Hybrid optimization based learning technique for multi‐disease analytics from healthcare big data using optimal pre‐processing, clustering and classifier | |
| US20110231336A1 (en) | Forecasting product/service realization profiles | |
| Arunmozhi et al. | Managing the resource allocation for the COVID-19 pandemic in healthcare institutions: a pluralistic perspective | |
| CN114693461A (en) | Method for acquiring risk influence factors of urban general insurance based on machine learning | |
| CN112466401B (en) | Method and device for analyzing multiple types of data by utilizing artificial intelligence AI model group | |
| Fox et al. | Aicov: An integrative deep learning framework for covid-19 forecasting with population covariates | |
| CN113555120B (en) | Biological state analysis method and device, storage medium, and electronic device | |
| CN114068035A (en) | Infectious disease intervention action adjustment method and device, storage medium and electronic equipment | |
| CN111652433B (en) | Endowment expense measuring and calculating device |
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 |