CN117116455B - Intelligent control method and system for Internet of things - Google Patents
Intelligent control method and system for Internet of things Download PDFInfo
- Publication number
- CN117116455B CN117116455B CN202311379679.5A CN202311379679A CN117116455B CN 117116455 B CN117116455 B CN 117116455B CN 202311379679 A CN202311379679 A CN 202311379679A CN 117116455 B CN117116455 B CN 117116455B
- Authority
- CN
- China
- Prior art keywords
- patients
- data information
- treatment data
- information
- recovery
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000011084 recovery Methods 0.000 claims description 125
- 230000007613 environmental effect Effects 0.000 claims description 81
- 238000004364 calculation method Methods 0.000 claims description 73
- 238000004458 analytical method Methods 0.000 claims description 42
- 238000012545 processing Methods 0.000 claims description 36
- 239000002245 particle Substances 0.000 claims description 34
- 238000003066 decision tree Methods 0.000 claims description 29
- 238000004422 calculation algorithm Methods 0.000 claims description 28
- 239000011159 matrix material Substances 0.000 claims description 25
- 238000005457 optimization Methods 0.000 claims description 22
- 230000008859 change Effects 0.000 claims description 19
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 238000003062 neural network model Methods 0.000 claims description 11
- 238000000611 regression analysis Methods 0.000 claims description 9
- 238000012098 association analyses Methods 0.000 claims description 6
- 238000007621 cluster analysis Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000013138 pruning Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 2
- 238000010219 correlation analysis Methods 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 230000001225 therapeutic effect Effects 0.000 claims description 2
- 230000006855 networking Effects 0.000 claims 1
- 230000008569 process Effects 0.000 description 13
- 230000000694 effects Effects 0.000 description 11
- 206010052428 Wound Diseases 0.000 description 6
- 208000027418 Wounds and injury Diseases 0.000 description 6
- 238000005286 illumination Methods 0.000 description 6
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 5
- 229910052760 oxygen Inorganic materials 0.000 description 5
- 239000001301 oxygen Substances 0.000 description 5
- 238000004378 air conditioning Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000001802 infusion Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 208000031636 Body Temperature Changes Diseases 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000029663 wound healing Effects 0.000 description 1
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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/40—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/60—Healthcare; Welfare
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/10—Detection; Monitoring
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioethics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides an Internet of things intelligent control method and system, and relates to the technical field of Internet of things.
Description
Technical Field
The invention relates to the technical field of the Internet of things, in particular to an Internet of things intelligent control method and system.
Background
At present, a plurality of links and factors are required to be coordinated in the hospital management and patient treatment process, in the patient recovery process, the hospital environment and the patient recovery condition are often required to be monitored, the time is further adjusted for the hospital environment, and the patient recovery efficiency is guaranteed, but the traditional management mode is usually manual adjustment, the problems of misoperation, inefficiency, low precision and the like are easy to occur, and the condition that the patient recovery condition is not ideal is further caused. In addition, because manual management is difficult to cope with the situation of large data volume, an intelligent control method of the internet of things is needed to solve the problems.
Disclosure of Invention
The present invention is directed to an intelligent control method and system for internet of things, so as to improve the above-mentioned problems. In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
in one aspect, the application provides an intelligent control method for an internet of things, which comprises the following steps:
acquiring environmental information of each area of a hospital and treatment data information of all patients based on the Internet of things, wherein the environmental information of each area of the hospital comprises temperature information, humidity information, oxygen concentration information and illumination information of each area of the hospital, and the treatment data information of the patients comprises wound recovery information of the patients and body index change information of the patients;
performing hierarchical analysis on the treatment data information of all the patients based on a hierarchical analysis method to obtain treatment data information of the patients with at least two recovery levels, wherein the recovery levels are levels of the patients corresponding to the recovery levels in the hierarchical structure model;
performing association analysis on the treatment data information of the patients of all recovery levels and the environmental information of all areas of the hospital, and determining an association degree value between the treatment data information of the patients of each recovery level and the environmental information of each area of the hospital;
Formulating control schemes of environmental information of each area of at least two hospitals based on the association degree values, and sending all the control schemes to a trained neural network model to predict the recovery condition of the patient, so as to obtain a prediction result of a recovery level of the patient;
determining an optimal control scheme corresponding to a prediction result of a patient recovery level based on a particle swarm optimization algorithm, and generating a device control command according to the optimal control scheme;
and controlling the intelligent equipment in the hospital area according to the equipment control command.
On the other hand, the application also provides an Internet of things intelligent control system, which comprises:
an acquisition unit configured to acquire environmental information of each area of a hospital including temperature information, humidity information, oxygen concentration information, and illumination information of each area of the hospital and treatment data information of all patients including wound recovery information of the patient and body index change information of the patient based on the internet of things;
the first analysis unit is used for carrying out hierarchical analysis on the treatment data information of all the patients based on a hierarchical analysis method to obtain treatment data information of the patients with at least two recovery levels, wherein the recovery levels are levels of the patients corresponding to the levels in the hierarchical structure model;
A second analysis unit for performing association analysis on the treatment data information of the patients of all the recovery levels and the environmental information of all the areas of the hospital, and determining an association degree value between the treatment data information of the patients of each recovery level and the environmental information of each area of the hospital;
the first processing unit is used for formulating control schemes of environmental information of each area of at least two hospitals based on the association degree value, and sending all the control schemes to the trained neural network model to predict the recovery condition of the patient so as to obtain a prediction result of a recovery level of the patient;
the second processing unit is used for determining an optimal control scheme corresponding to a prediction result of the patient recovery level based on a particle swarm optimization algorithm and generating a device control command according to the optimal control scheme;
and the control unit is used for receiving the equipment control command and controlling intelligent equipment in the hospital area according to the equipment control command.
The beneficial effects of the invention are as follows:
the invention can carry out intelligent analysis and control on the hospital environment and the patient treatment data, and realizes the intellectualization and individuation of hospital management and patient treatment process. Specifically, by analyzing the association degree of the treatment data information of the patient and the hospital environment information, the treatment requirement and the disease condition of the patient are considered when the environment control scheme is prepared, and the accuracy and the effect of the control scheme are improved. In addition, the recovery state of the patient is predicted by a plurality of optimization methods such as analytic hierarchy process, particle swarm optimization algorithm and the like, personalized treatment and health monitoring of the patient are realized, and the effects of quick response and automatic processing are realized by the control of intelligent equipment.
Meanwhile, the method comprises data layering based on an analytic hierarchy process and control scheme optimization based on a particle swarm optimization algorithm, and the method has a certain unique effect. The data layering based on the analytic hierarchy process enables treatment data to be built into a hierarchical structure from top to bottom according to importance, so that data analysis is finer, and analysis results are objective and scientific. The control scheme optimization based on the particle swarm optimization algorithm is beneficial to finding the optimal solution, and overcomes the defect that the traditional control scheme is difficult to find the global optimal solution. The methods cooperate with each other, so that the control effect of the intelligent Internet of things can be improved to the greatest extent, the hospital cost can be reduced, the efficiency of the hospital environment control equipment can be improved, and the recovery speed of patients in the hospital can be ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an intelligent control method for an Internet of things according to an embodiment of the invention;
fig. 2 is a schematic structural diagram of the intelligent control system for internet of things according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1
The embodiment provides an Internet of things intelligent control method, namely an equipment control method based on the Internet of things.
Referring to fig. 1, the method is shown to include steps S1, S2, S3, S4, S5 and S6.
Step S1, acquiring environmental information of each area of a hospital and treatment data information of all patients based on the Internet of things, wherein the environmental information of each area of the hospital comprises temperature information, humidity information, oxygen concentration information and illumination information of each area of the hospital, and the treatment data information of the patients comprises wound recovery information of the patients and body index change information of the patients;
temperature information, humidity information, oxygen concentration information and illumination information in the step are all obtained through the sensor, and then data of the sensor and central control equipment are obtained through the Internet of things to control all equipment, and then environmental information of a hospital is changed, complexity of manual control is reduced, and control efficiency is improved, wherein wound recovery information of a patient and body index change information of the patient can be quantized into data in a numerical form, and the data are uploaded through manual operation and equipment record, and data processing and storage are carried out through the Internet of things as well, wherein wound recovery information of the patient can specifically refer to information such as wound healing speed of the patient, and body index change information of the patient can specifically refer to information such as body temperature change of the patient.
Step S2, performing hierarchical analysis on the treatment data information of all the patients based on a hierarchical analysis method to obtain treatment data information of the patients with at least two recovery levels, wherein the recovery levels are levels of the patients corresponding to the levels in the hierarchical structure model;
therefore, treatment data information of all patients is subjected to layering treatment based on an analytic hierarchy process, and the data can be analyzed and treated more finely after layering, so that when the hospital environment and the treatment process of the patients are controlled, the user requirements and the control strategies are divided more accurately, and the control effect and the control precision are improved.
Further, step S2 includes step S21, step S22, and step S23.
Step S21, carrying out hierarchical analysis on the treatment data information of all the patients, wherein the hierarchical structure model of at least two layers formed from top to bottom is obtained by carrying out cluster analysis on each data in the treatment data information of all the patients;
in this step, all data are classified by the clustering analysis, and then the hierarchical structure model of at least two levels is obtained by layering the data of different score levels, specifically, step S21 includes step S211, step S212, step S213, step S214 and step S215.
Step S211, scoring the historical treatment data information of all preset patients based on a scoring threshold value of the treatment data information of the preset patients to obtain scoring values of the historical treatment data information of all patients;
step S212, constructing a CART decision tree based on a CART algorithm and scoring values of historical treatment data information of all patients, performing random pruning treatment on the CART decision tree, and determining constants of the CART decision tree to obtain at least one untrained sub decision tree;
step S213, obtaining an optimal sub-decision tree based on the untrained sub-decision tree and a base index calculation method, and obtaining a body index change scoring model based on the optimal sub-decision tree;
step S214, sending the treatment data information of all patients to a body index change scoring model for scoring, and carrying out clustering calculation on the corresponding scores of the treatment data information of all patients based on a K-means algorithm to obtain at least two clustering clusters;
step S215, calculating to obtain a threshold range corresponding to each cluster based on all clusters and the Laida criterion, and layering treatment data information of all patients based on the threshold ranges to obtain treatment data information of patients with two levels.
And scoring, clustering and layering treatment data information of all patients through a CART algorithm and a K-means algorithm, so that personalized control and refined service of the treatment process of the patients are realized. Through the calculation of the grading value and the construction of the decision tree, the historical treatment data of the patient can be analyzed and predicted, and then the body index change grading model is obtained and used for evaluating the treatment effect of the patient.
Meanwhile, the treatment data information is sent to a body index change scoring model for scoring, and the scoring is subjected to clustering calculation based on a K-means algorithm, so that patients can be divided into different clustering clusters, and personalized management and optimal control of the patients are realized. Finally, calculating the threshold range of each cluster based on the Laida criterion, layering treatment data information to obtain two-level treatment data information of patients, and further performing hospital management and patient treatment process control based on the treatment data information, so as to realize finer and personalized equipment control effect based on the Internet of things.
S22, based on the hierarchical structure model, performing importance comparison on all treatment data in the hierarchical structure model of each recovery level, and performing normalization processing and constructing a discrimination matrix based on the data obtained by the comparison;
The construction formula of the discrimination matrix is as follows: :
wherein: a is a discrimination matrix;the importance ratio of the data i and the data j of the current level to the previous level is scaled; i and j are respectively different kinds of data; n is the dimension of the hierarchical model.
And S23, calculating the eigenvectors and the maximum eigenvalues of the matrix based on the discrimination matrix, and carrying out consistency test on the discrimination matrix based on the calculation result, and if the consistency test is the same as a preset result, sequencing the recovery levels of each level based on the calculation result to obtain the recovery levels of the treatment data information of all patients.
Wherein the calculation formula of the index of the consistency is as followsThe illustration is:
wherein: r is a consistency index;the maximum eigenvalue of the matrix is judged; n is the order of the discrimination matrix; e is an average random uniformity index.
And carrying out layering treatment on the treatment data information of all the patients based on a layering analysis method, and carrying out refining treatment on the data through methods such as cluster analysis, importance comparison and the like so as to form a hierarchical structure model with at least two layers formed from top to bottom sequentially. On the basis, the importance of the data in the hierarchical structure is evaluated and checked by constructing a discrimination matrix and consistency check, and the recovery levels of each level are ordered on the basis, so that the intelligent control and optimization of the hospital management and patient treatment process are realized, and the method has the advantages of high accuracy, high reliability, high processing speed and the like.
Step S3, carrying out association analysis on the treatment data information of the patients of all recovery levels and the environmental information of all areas of the hospital, and determining an association degree value between the treatment data information of the patients of each recovery level and the environmental information of each area of the hospital;
and determining the connection between the environmental information of the patient recovery data hospital through the association analysis, further providing basis for the subsequent environmental change control, and further comprising the step S31, the step S32 and the step S33 in the step S3.
Step S31, carrying out dimensionless treatment on treatment data information of patients at all recovery levels and environment information of all areas of a hospital, and calculating the dimensionless treatment data information and the environment information of all areas of the dimensionless hospital based on a mean conversion method to obtain the dimensionless treatment data information of the patients and the environment information of all areas of the dimensionless hospital;
in this embodiment, the treatment data after dimensionless treatment is converted based on the mean value conversion methodThe information and the environment information of all areas of the hospital after dimensionless treatment are calculated, the dimensionality difference between different data is eliminated, and a mean conversion method calculation formula is shown as follows:
Wherein:the parameter is a parameter after dimensionless treatment, x is a sample of certain treatment data information or environmental data information, and mu is a sample mean value of certain treatment data information or environmental data information; sigma is the sample standard deviation of certain treatment data information or environmental data information.
Step S32, obtaining a relation coefficient based on a preset relation coefficient calculation formula for treatment data information of a patient after dimensionless treatment and environment information of all areas of a hospital after dimensionless treatment;
the calculation formula of the relation coefficient is as follows:
wherein:a relationship coefficient of the environmental data information f relative to the therapeutic data information k; f is environmental data information; k is treatment data information; y (k) is corresponding time information when the environmental data information is collected; x is x f (k) Corresponding time information when the treatment data information is acquired; ρ is the resolution factor, taking 0-1.
And step S33, performing association degree calculation based on an association degree calculation formula and the relation coefficient to obtain association degree values between treatment data information of patients of each recovery level and environment information of each region of the hospital.
The calculation formula of the association degree is as follows:
wherein: epsilon is a correlation value between the treatment data information of the patient of each recovery hierarchy and the environmental information of each area of the hospital; k is treatment data information; n is the total number of data samples in the treatment data information; f is environmental data information; γ f (k) Is a coefficient of relationship of the environmental data information f to the treatment data information k.
Therefore, the method and the device can extract, quantitatively evaluate and analyze the association degree between the treatment data information of the patient at the recovery level and the environmental information of all areas of the hospital by collecting and analyzing the data, so that more accurate and comprehensive data support is provided for the hospital. And secondly, when data analysis is carried out, dimensionless processing, relation coefficient calculation and other methods are adopted, so that the dimensionality difference among different data can be effectively eliminated, and the accuracy and precision of data processing, analysis and display are improved. Finally, through calculation of a calculation formula and a relation coefficient based on the association degree, more comprehensive, accurate and intelligent support can be provided for hospital management and patient treatment process, quantitative evaluation and optimization of the patient treatment process and hospital management are realized, and therefore the hospital service level and the recovery effect of patients are improved.
Step S4, formulating control schemes of environmental information of each area of at least two hospitals based on the association degree value, and sending all the control schemes to a trained neural network model to predict the recovery condition of the patient, so as to obtain a prediction result of a recovery level of the patient;
Therefore, the control scheme of the environmental information of each area of at least two hospitals can be formulated based on the association value and the regression analysis mode, and the recovery effect prediction is performed based on each control scheme, so that the control scheme is rapidly selected, and further, the step S4 comprises the steps S41, S42, S43, S44 and S45.
S41, carrying out regression analysis on the relevance value, the environmental information of each area of the hospital and the treatment data information of all patients, determining an influence coefficient between the environmental information of each area of the hospital and the treatment data information of all patients, and formulating at least one control scheme of the environmental information based on the influence coefficient;
wherein, the calculation formula of the influence coefficient is as follows:
wherein k is treatment data information of a patient, f is environmental information of each area of a hospital, lambda is a preset weight coefficient of a relevance value, epsilon is a relevance value, a and b are regression coefficients, the influence degree and basic recovery capacity of the treatment data information k of the patient on the environmental information f are represented, an optimal solution is calculated by using a bias derivative method, and the influence coefficient between the environmental information of each area of the hospital and the treatment data information of all patients is determined.
In the step, the influence coefficient between each piece of environment information and the treatment data information of all patients is calculated by substituting the regression analysis result into a calculation formula, and then an environment information control scheme is formulated according to the influence coefficient so as to improve the treatment effect and recovery speed of the patients.
Step S42, preset historical environment information of a hospital and preset historical treatment data information of a patient are sent to an input layer of an LSTM neural network for input, and an influence coefficient between the treatment data information of the patient of each recovery level and the environment information of each area of the hospital is used as a weight to carry out weighting and activation function calculation, so that recovery level prediction results of the patient corresponding to all the historical environment information are obtained;
step S43, calculating a matching degree value of the prediction result and the actual recovery layer level of the preset patient based on a preset matching degree calculation formula;
the matching degree value calculation formula is as follows:
wherein A is the matching degree value of the prediction result and the actual recovery layer level of the preset patient,x i indicating the i-th prediction information in the prediction result,y i representing the ith actual recovery level in the actual recovery levels of the preset patient, and n represents the total number of predicted results.
Step S44, adjusting parameters of the LSTM neural network based on the matching degree value, and repeatedly carrying out prediction and matching degree value calculation until the matching degree value is larger than a preset threshold value to obtain a trained neural network;
and step S45, the control scheme is sent to the trained neural network model to predict the recovery condition of the patient, and the recovery level of the patient corresponding to the control scheme is obtained.
Therefore, the intelligent degree of hospital management and patient treatment process can be improved through regression analysis, LSTM neural network, matching degree calculation and other methods. Specifically, the regression analysis can analyze the influence coefficient between the treatment data information of the patient and the environmental information of the hospital, and then make an environmental information control scheme to improve the treatment effect and recovery speed of the patient. The prediction of the recovery condition of the patient and the calculation of the matching degree can be realized through the LSTM neural network, the matching degree calculation and other methods, so that the personalized requirements of the patient can be better met, wherein the influence of the environmental information on the treatment data information of the patient can be accurately analyzed through regression analysis and the matching degree calculation, and a more scientific and reliable control scheme is made.
And step S5, determining an optimal control scheme corresponding to a prediction result of the patient recovery level based on a particle swarm optimization algorithm, and generating a device control command according to the optimal control scheme to reduce the control cost of the hospital, wherein the step S5 comprises a step S51 and a step S52.
Step S51, taking the recovery levels of all patients corresponding to the control scheme and the control cost of all intelligent devices as input parameters and particle swarm parameters, and calculating the fitness of particles in the particle swarm based on a fitness function to obtain the individual optimal position and the global optimal position of the particles;
step S52, dynamically tracking the individual optimal position and the global optimal position based on the particle swarm optimization algorithm to continuously update the speeds and positions of all particles until the particle swarm optimization algorithm reaches the maximum iteration times, obtaining an optimal control scheme corresponding to the recovery level of the patient, and generating a device control command according to the optimal control scheme.
Therefore, the optimal control scheme corresponding to the recovery level of the patient can be effectively searched through the particle swarm optimization algorithm, so that the efficiency and quality of hospital management and patient treatment process are improved, and the control cost of the hospital is saved.
Furthermore, the control scheme and the control cost of the intelligent equipment are used as input parameters, the fitness of each particle in the particle swarm can be evaluated and analyzed by combining fitness function calculation, and then the individual optimal position and the global optimal position are found out to form an optimal control scheme. The particle swarm optimization algorithm can well combine the control cost of the control scheme and the control cost of the intelligent equipment to form an optimal control scheme, and the optimal solution of the control scheme is continuously searched and updated through multiple iterations.
And S6, controlling each intelligent device in the hospital area according to the device control command.
The intelligent equipment in this step includes equipment such as medical equipment, intelligent lighting system, fan and air conditioning system, wherein fan and air conditioning system are used for controlling the temperature and the humidity of each regional in hospital, with ensure patient's comfort level and equipment normal operating, ensure indoor air quality and accord with the standard, intelligent lighting system is used for monitoring the illumination level in room, can be used to automatic dimming system, with the improvement efficiency and satisfy patient's demand, medical equipment includes equipment such as breathing machine, infusion pump, be used for adjusting the output parameter of equipment such as breathing machine and infusion pump, optimize patient's recovery process and improve the efficiency and the quality of hospital environment.
Example 2
As shown in fig. 2, the present embodiment provides an internet of things intelligent control system, which includes an acquisition unit 701, a first analysis unit 702, a second analysis unit 703, a first processing unit 704, a second processing unit 705, and a control unit 706.
An acquiring unit 701, configured to acquire environmental information of each area of a hospital and treatment data information of all patients based on the internet of things, where the environmental information of each area of the hospital includes temperature information, humidity information, oxygen concentration information, and illumination information of each area of the hospital, and the treatment data information of the patients includes wound recovery information of the patients and body index change information of the patients;
a first analysis unit 702, configured to perform a hierarchical analysis on the treatment data information of all the patients based on a hierarchical analysis method, so as to obtain treatment data information of patients with at least two recovery levels, where the recovery levels are levels of the patients corresponding to the levels located in the hierarchical structure model;
the first analysis unit 702 includes a first analysis subunit 7021, a first processing subunit 7022, and a first calculation subunit 7023.
A first analysis subunit 7021, configured to perform hierarchical analysis on treatment data information of all the patients, where a hierarchical structure model of at least two levels formed sequentially from top to bottom is obtained by performing cluster analysis on each data in the treatment data information of all the patients;
The first analysis subunit 7021 includes a second processing subunit 70211, a third processing subunit 70212, a second computing subunit 70213, a third computing subunit 70214, and a fourth computing subunit 70215.
A second processing subunit 70211, configured to score, based on a scoring threshold of the preset treatment data information of the patient, preset historical treatment data information of all patients, so as to obtain scoring values of the historical treatment data information of all patients;
the third processing subunit 70212 is configured to construct a CART decision tree based on a CART algorithm and score values of historical treatment data information of all patients, perform random pruning processing on the CART decision tree, and determine constants of the CART decision tree to obtain at least one untrained sub decision tree;
a second calculating subunit 70213, configured to obtain an optimal sub-decision tree based on the untrained sub-decision tree and a keni index calculation method, and obtain a body index change scoring model based on the optimal sub-decision tree;
the third calculation subunit 70214 is configured to send treatment data information of all patients to a body index change scoring model for scoring, and perform cluster calculation on corresponding scores of the treatment data information of all patients based on a K-means algorithm to obtain at least two clusters;
The fourth calculating subunit 70215 is configured to calculate, based on all the clusters and the rada criterion, a threshold range corresponding to each cluster, and layer treatment data information of all patients based on the threshold ranges, so as to obtain treatment data information of patients with two levels.
A first processing subunit 7022, configured to perform importance comparison on all the treatment data in the hierarchical structure model of each recovery level based on the hierarchical structure model, and normalize and construct a discrimination matrix based on the data obtained by the comparison;
the first calculating subunit 7023 is configured to calculate a feature vector and a maximum feature value of a matrix based on the discrimination matrix, perform a consistency check on the discrimination matrix based on a calculation result, and rank recovery levels of each level based on the calculation result if the consistency check is the same as a preset result, so as to obtain recovery levels of treatment data information of all patients.
A second analysis unit 703 for performing a correlation analysis of the treatment data information of the patients of all the recovery levels and the environmental information of all the areas of the hospital, and determining a correlation value between the treatment data information of the patients of each recovery level and the environmental information of each area of the hospital;
The second analysis unit 703 includes a fourth processing subunit 7031, a fifth calculation subunit 7032, and a sixth calculation subunit 7033.
A fourth processing subunit 7031, configured to perform dimensionless treatment on the treatment data information of the patients at all recovery levels and the environmental information of all areas of the hospital, and calculate the dimensionless treatment data information and the environmental information of all areas of the dimensionless hospital based on a mean conversion method, so as to obtain the dimensionless treatment data information of the patients and the environmental information of all areas of the dimensionless hospital;
a fifth calculating subunit 7032, configured to obtain a relationship coefficient for the treatment data information of the patient after dimensionless treatment and the environmental information of all areas of the hospital after dimensionless treatment based on a preset relationship coefficient calculation formula;
a sixth calculating subunit 7033 is configured to perform association calculation based on the association calculation formula and the relationship coefficient, so as to obtain an association value between the treatment data information of the patient of each recovery level and the environmental information of each region of the hospital.
The first processing unit 704 is configured to formulate a control scheme of environmental information of each area of at least two hospitals based on the association degree value, and send all the control schemes to the trained neural network model to predict the recovery condition of the patient, so as to obtain a prediction result of the recovery level of the patient;
Wherein the first processing unit 704 includes a second analysis subunit 7041, a seventh calculation subunit 7042, an eighth calculation subunit 7043, a ninth calculation subunit 7044, and a fifth processing subunit 7045.
A second analysis subunit 7041, configured to perform regression analysis on the relevance value, the environmental information of each area of the hospital, and the treatment data information of all patients, determine an influence coefficient between the environmental information of each area of the hospital and the treatment data information of all patients, and formulate at least one control scheme of the environmental information based on the influence coefficient;
a seventh calculating subunit 7042, configured to send preset historical environmental information of a hospital and preset historical treatment data information of a patient to an input layer of the LSTM neural network for input, and perform weighted and activated function calculation with an influence coefficient between the treatment data information of the patient at each recovery level and the environmental information of each area of the hospital as a weight, so as to obtain recovery level prediction results of the patient corresponding to all the historical environmental information;
an eighth calculating subunit 7043, configured to calculate a matching degree value between the prediction result and an actual recovery level of the preset patient based on a preset matching degree calculation formula;
A ninth calculating subunit 7044, configured to adjust parameters of the LSTM neural network based on the matching degree value, and repeat prediction and calculation of the matching degree value until the matching degree value is greater than a preset threshold value, so as to obtain a trained neural network;
and a fifth processing subunit 7045, configured to send the control scheme to the trained neural network model for predicting a patient recovery condition, so as to obtain a recovery hierarchy of the patient corresponding to the control scheme.
The second processing unit 705 is configured to determine an optimal control scheme corresponding to a prediction result of the patient recovery hierarchy based on a particle swarm optimization algorithm, and generate an equipment control command according to the optimal control scheme;
the second processing unit 705 includes a tenth computing sub-unit 7051 and a sixth processing sub-unit 7052.
A tenth calculation subunit 7051, configured to use the recovery levels of all patients corresponding to the control schemes and the control costs of all intelligent devices as input parameters and particle swarm parameters, and calculate the fitness of the particles in the particle swarm based on a fitness function, so as to obtain an individual optimal position and a global optimal position of the particles;
and a sixth processing subunit 7052, configured to dynamically track the individual optimal position and the global optimal position based on the particle swarm optimization algorithm to continuously update the speeds and positions of all the particles until the particle swarm optimization algorithm reaches the maximum iteration number, thereby obtaining an optimal control scheme corresponding to the recovery level of the patient.
And the control unit 706 is configured to receive the device control command, and control the intelligent devices in the hospital area according to the device control command.
It should be noted that, regarding the system in the above embodiment, the specific manner in which the respective modules perform the operations has been described in detail in the embodiment regarding the method, and will not be described in detail herein.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (7)
1. An intelligent control method for an internet of things is characterized by comprising the following steps:
Acquiring environmental information of each area of a hospital and treatment data information of all patients based on the Internet of things, wherein the treatment data information of the patients comprises wound recovery information of the patients and body index change information of the patients;
performing hierarchical analysis on the treatment data information of all the patients based on a hierarchical analysis method to obtain treatment data information of the patients with at least two recovery levels, wherein the recovery levels are levels of the patients corresponding to the recovery levels in the hierarchical structure model;
performing association analysis on the treatment data information of the patients of all recovery levels and the environmental information of all areas of the hospital, and determining an association degree value between the treatment data information of the patients of each recovery level and the environmental information of each area of the hospital;
formulating control schemes of environmental information of each area of at least two hospitals based on the association degree values, and sending all the control schemes to a trained neural network model to predict the recovery condition of the patient, so as to obtain a prediction result of a recovery level of the patient;
determining an optimal control scheme corresponding to a prediction result of a patient recovery level, and generating a device control command according to the optimal control scheme;
Controlling intelligent equipment in the hospital area according to the equipment control command;
wherein the hierarchical analysis of the treatment data information of all the patients based on the hierarchical analysis method comprises the following steps:
performing hierarchical analysis on the treatment data information of all the patients, wherein the hierarchical structure model of at least two layers formed from top to bottom sequentially is obtained by performing cluster analysis on each data in the treatment data information of all the patients;
based on the hierarchical structure model, carrying out importance comparison on all treatment data in the hierarchical structure model of each recovery level, and carrying out normalization processing and constructing a discrimination matrix based on the data obtained by comparison;
calculating a feature vector and a maximum feature value of a matrix based on the discrimination matrix, and carrying out consistency check on the discrimination matrix based on a calculation result, and if the consistency check is the same as a preset result, sequencing the recovery levels of each level based on the calculation result to obtain recovery levels of treatment data information of all patients;
wherein the hierarchical structure model divided into at least two levels formed in the order from top to bottom by performing cluster analysis on each data in the treatment data information of all patients comprises:
Scoring the historical treatment data information of all the preset patients based on a scoring threshold value of the treatment data information of the preset patients to obtain scoring values of the historical treatment data information of all the patients;
constructing a CART decision tree based on a CART algorithm and scoring values of historical treatment data information of all patients, performing random pruning treatment on the CART decision tree, and determining constants of the CART decision tree to obtain at least one untrained sub decision tree;
obtaining an optimal sub-decision tree based on the untrained sub-decision tree and a base index calculation method, and obtaining a body index change scoring model based on the optimal sub-decision tree;
transmitting the treatment data information of all patients to a body index change scoring model for scoring, and carrying out clustering calculation on the corresponding scores of the treatment data information of all patients based on a K-means algorithm to obtain at least two clusters;
calculating a threshold range corresponding to each cluster based on all clusters and Laida criteria, and layering treatment data information of all patients based on the threshold ranges to obtain treatment data information of patients with two levels;
the method for predicting the recovery condition of the patient comprises the steps of formulating a control scheme of environmental information of each area of at least two hospitals based on the relevance value, and sending all the control schemes to a trained neural network model to predict the recovery condition of the patient, wherein the method comprises the following steps:
Performing regression analysis on the association value, the environmental information of each area of the hospital and the treatment data information of all patients, determining an influence coefficient between the environmental information of each area of the hospital and the treatment data information of all patients, and formulating at least one control scheme of the environmental information based on the influence coefficient;
the method comprises the steps of sending preset historical environment information of a hospital and preset historical treatment data information of a patient to an input layer of an LSTM neural network for input, and taking an influence coefficient between treatment data information of the patient of each recovery level and environment information of each area of the hospital as a weight to perform weighting and activation function calculation to obtain recovery level prediction results of the patient corresponding to all the historical environment information;
calculating a matching degree value of the prediction result and an actual recovery layer level of a preset patient based on a preset matching degree calculation formula;
adjusting parameters of the LSTM neural network based on the matching degree value, and repeatedly carrying out prediction and matching degree value calculation until the matching degree value is larger than a preset threshold value to obtain a trained neural network;
and sending the control scheme to the trained neural network model for predicting the recovery condition of the patient, and obtaining the recovery level of the patient corresponding to the control scheme.
2. The intelligent control method for the internet of things according to claim 1, wherein the construction formula of the discrimination matrix is as follows:
;
wherein: a is a discrimination matrix;the importance ratio of the data i and the data j of the current level to the previous level is scaled; i and j are respectively different kinds of data; n is the dimension of the hierarchical structure model;
the calculation formula of the index of the consistency is as follows:
;
wherein: r is a consistency index;the maximum eigenvalue of the matrix is judged; n is the order of the discrimination matrix; e is an average random uniformity index.
3. The thing networking intelligent control method according to claim 1, wherein the correlation analysis of the treatment data information of the patients of all recovery levels and the environmental information of all areas of the hospital comprises:
performing dimensionless treatment on the treatment data information of the patients at all recovery levels and the environmental information of all areas of the hospital, and calculating the dimensionless treatment data information and the environmental information of all areas of the dimensionless hospital based on a mean value conversion method to obtain the treatment data information of the dimensionless patients and the environmental information of all areas of the dimensionless hospital;
Obtaining a relationship coefficient for treatment data information of a patient after dimensionless treatment and environmental information of all areas of a hospital after dimensionless treatment based on a preset relationship coefficient calculation formula;
performing association degree calculation based on the calculation formula of the association degree and the relation coefficient to obtain an association degree value between treatment data information of patients of each recovery level and environment information of each region of the hospital;
wherein, the calculation formula of the relation coefficient is as follows:
;
wherein:a relationship coefficient of the environmental data information f relative to the therapeutic data information k; f is environmental data information; k is treatment data information; y (k) is corresponding time information when the environmental data information is collected; x is x f (k) Corresponding time information when the treatment data information is acquired; ρ is the resolution factor, taking 0-1.
4. The intelligent control method for the internet of things according to claim 1, wherein the calculation formula of the influence coefficient is as follows:
wherein, the calculation formula of the influence coefficient is as follows:
;
where k is treatment data information of the patient, f is environmental information of each area of the hospital, λ is a preset weight coefficient of the association value, ε is the association value, a and b are regression coefficients, and represent the extent of influence and basic recovery capability of the treatment data information k of the patient on the environmental information f.
5. The intelligent control method for the internet of things according to claim 1, wherein the preset matching degree calculation formula is as follows:
the preset matching degree calculation formula is as follows:
;
wherein A is the matching degree value of the prediction result and the actual recovery layer level of the preset patient,x i indicating the i-th prediction information in the prediction result,y i representing the ith actual recovery level in the actual recovery levels of the preset patient, and n represents the total number of predicted results.
6. The internet of things intelligent control method according to claim 1, wherein determining an optimal control scheme corresponding to a predicted result of a patient recovery level based on a particle swarm optimization algorithm comprises:
taking the recovery levels of all patients corresponding to the control scheme and the control cost of all intelligent devices as input parameters and particle swarm parameters, and calculating the fitness of particles in the particle swarm based on a fitness function to obtain the individual optimal position and the global optimal position of the particles;
and dynamically tracking the individual optimal position and the global optimal position based on the particle swarm optimization algorithm to continuously update the speeds and positions of all particles until the particle swarm optimization algorithm reaches the maximum iteration times, so as to obtain an optimal control scheme corresponding to the recovery level of the patient.
7. An internet of things intelligent control system for implementing the internet of things intelligent control method of claim 1, comprising:
an acquisition unit for acquiring environmental information of each area of a hospital and treatment data information of all patients based on the internet of things, wherein the treatment data information of the patients comprises wound recovery information of the patients and body index change information of the patients;
the first analysis unit is used for carrying out hierarchical analysis on the treatment data information of all the patients based on a hierarchical analysis method to obtain treatment data information of the patients with at least two recovery levels, wherein the recovery levels are levels of the patients corresponding to the levels in the hierarchical structure model;
a second analysis unit for performing association analysis on the treatment data information of the patients of all the recovery levels and the environmental information of all the areas of the hospital, and determining an association degree value between the treatment data information of the patients of each recovery level and the environmental information of each area of the hospital;
the first processing unit is used for formulating control schemes of environmental information of each area of at least two hospitals based on the association degree value, and sending all the control schemes to the trained neural network model to predict the recovery condition of the patient so as to obtain a prediction result of a recovery level of the patient;
The second processing unit is used for determining an optimal control scheme corresponding to a prediction result of the patient recovery level based on a particle swarm optimization algorithm and generating a device control command according to the optimal control scheme;
the control unit is used for receiving the equipment control command and controlling intelligent equipment in the hospital area according to the equipment control command;
wherein the first analysis unit includes:
the first analysis subunit is used for carrying out hierarchical analysis on the treatment data information of all the patients, wherein the hierarchical structure model of at least two levels formed from top to bottom is obtained by carrying out cluster analysis on each data in the treatment data information of all the patients;
the first processing subunit is used for comparing the importance of all treatment data in the hierarchical structure model of each recovery level based on the hierarchical structure model, and normalizing and constructing a discrimination matrix based on the data obtained by comparison;
the first calculating subunit is used for calculating the eigenvectors and the maximum eigenvalues of the matrix based on the judging matrix, carrying out consistency check on the judging matrix based on the calculation result, and sequencing the recovery levels of each level based on the calculation result if the consistency check is the same as the preset result so as to obtain the recovery levels of the treatment data information of all patients;
Wherein the first analysis subunit comprises:
the second processing subunit is used for scoring the preset historical treatment data information of all patients based on the scoring threshold value of the preset treatment data information of the patients to obtain scoring values of the historical treatment data information of all patients;
the third processing subunit is used for constructing a CART decision tree based on a CART algorithm and scoring values of historical treatment data information of all patients, carrying out random pruning processing on the CART decision tree, and determining constants of the CART decision tree to obtain at least one untrained sub decision tree;
the second calculation subunit is used for obtaining an optimal sub-decision tree based on the untrained sub-decision tree and a base index calculation method and obtaining a body index change scoring model based on the optimal sub-decision tree;
the third calculation subunit is used for sending the treatment data information of all patients to the body index change scoring model for scoring, and carrying out clustering calculation on the corresponding scores of the treatment data information of all patients based on a K-means algorithm to obtain at least two clusters;
a fourth calculation subunit, configured to calculate, based on all the clusters and the rada criterion, a threshold range corresponding to each cluster, and layer treatment data information of all patients based on the threshold ranges, so as to obtain treatment data information of patients with two levels;
Wherein the first processing unit includes:
the second analysis subunit is used for carrying out regression analysis on the relevance value, the environmental information of each area of the hospital and the treatment data information of all patients, determining an influence coefficient between the environmental information of each area of the hospital and the treatment data information of all patients, and formulating at least one control scheme of the environmental information based on the influence coefficient;
a seventh calculation subunit, configured to send preset historical environmental information of a hospital and preset historical treatment data information of a patient to an input layer of the LSTM neural network for input, and perform weighted and activated function calculation with an influence coefficient between the treatment data information of the patient at each recovery level and the environmental information of each area of the hospital as a weight, so as to obtain recovery level prediction results of the patient corresponding to all the historical environmental information;
an eighth calculation subunit, configured to calculate a matching degree value between the prediction result and an actual recovery level of the preset patient based on a preset matching degree calculation formula;
a ninth calculating subunit, configured to adjust parameters of the LSTM neural network based on the matching degree value, and repeatedly perform prediction and matching degree value calculation until the matching degree value is greater than a preset threshold value, so as to obtain a trained neural network;
And the fifth processing subunit is used for sending the control scheme to the trained neural network model to predict the recovery condition of the patient, and obtaining the recovery level of the patient corresponding to the control scheme.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311379679.5A CN117116455B (en) | 2023-10-24 | 2023-10-24 | Intelligent control method and system for Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311379679.5A CN117116455B (en) | 2023-10-24 | 2023-10-24 | Intelligent control method and system for Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117116455A CN117116455A (en) | 2023-11-24 |
| CN117116455B true CN117116455B (en) | 2024-01-23 |
Family
ID=88798773
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311379679.5A Active CN117116455B (en) | 2023-10-24 | 2023-10-24 | Intelligent control method and system for Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117116455B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006018532A (en) * | 2004-06-30 | 2006-01-19 | Toshiba Corp | System and method for analyzing hospital management information, computer readable storage medium and computer program |
| AU2012397204A1 (en) * | 2012-12-20 | 2015-07-23 | Schneider Electric Buildings, Llc | System and method for managing patient environment |
| CN108289643A (en) * | 2015-11-23 | 2018-07-17 | 皇家飞利浦有限公司 | Pulse oximetry and environmental control |
| CN112316264A (en) * | 2020-11-24 | 2021-02-05 | 方梁 | Automatic device for breathing oxygen on wall of hospital |
| CN113031457A (en) * | 2021-03-11 | 2021-06-25 | 山东润一智能科技有限公司 | Intelligent ward control system and method |
| CN114036813A (en) * | 2021-11-11 | 2022-02-11 | 华南农业大学 | Greenhouse temperature and humidity method controlled by particle swarm BP neural network PID |
| CN114610748A (en) * | 2022-03-16 | 2022-06-10 | 云南升玥信息技术有限公司 | Safe, rapid, accurate and effective medical disease data management system based on artificial intelligence and application |
| CN115665184A (en) * | 2022-09-07 | 2023-01-31 | 苏州德品医疗科技股份有限公司 | Intelligent extension system of bedside for intelligent hospital based on Internet of things technology |
| CN115662591A (en) * | 2022-11-02 | 2023-01-31 | 浙江大学 | Ward integrated management platform and server |
| CN116013495A (en) * | 2022-12-08 | 2023-04-25 | 广州视声健康科技有限公司 | Data monitoring method and device based on intelligent ward |
| DE202023101305U1 (en) * | 2023-03-16 | 2023-05-23 | Lulwah Mohammed Alkwai | An intelligent health and fitness data management system using artificial intelligence with IoT devices |
| CN116147112A (en) * | 2023-04-21 | 2023-05-23 | 安徽逸天科技有限公司 | Hospital environment health data communication control processing system based on artificial intelligence |
| CN116364295A (en) * | 2022-12-28 | 2023-06-30 | 北京谊安医疗系统股份有限公司 | Medical data processing method and system |
| CN116684454A (en) * | 2023-06-02 | 2023-09-01 | 成都瑞华康源科技有限公司 | Automatic control system, method and storage medium for operating room environment |
| CN116825314A (en) * | 2023-08-28 | 2023-09-29 | 四川互慧软件有限公司 | Dynamic optimal distribution system and method for medical rescue resources based on operation research |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105431851B (en) * | 2013-07-31 | 2019-12-31 | 皇家飞利浦有限公司 | Healthcare decision support system and method and patient care system |
| US20180017947A1 (en) * | 2016-07-13 | 2018-01-18 | Siemens Industry, Inc. | System and method for optimizing building system control of patient rooms to enhance patient outcomes |
| US11166862B2 (en) * | 2018-12-06 | 2021-11-09 | General Electric Company | System and method for a thermoregulated environment |
| US20230011521A1 (en) * | 2021-07-06 | 2023-01-12 | Koninklijke Philips N.V. | System and method for adjusting hospital unit capacity based on patient-specific variables |
-
2023
- 2023-10-24 CN CN202311379679.5A patent/CN117116455B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006018532A (en) * | 2004-06-30 | 2006-01-19 | Toshiba Corp | System and method for analyzing hospital management information, computer readable storage medium and computer program |
| AU2012397204A1 (en) * | 2012-12-20 | 2015-07-23 | Schneider Electric Buildings, Llc | System and method for managing patient environment |
| CN108289643A (en) * | 2015-11-23 | 2018-07-17 | 皇家飞利浦有限公司 | Pulse oximetry and environmental control |
| CN112316264A (en) * | 2020-11-24 | 2021-02-05 | 方梁 | Automatic device for breathing oxygen on wall of hospital |
| CN113031457A (en) * | 2021-03-11 | 2021-06-25 | 山东润一智能科技有限公司 | Intelligent ward control system and method |
| CN114036813A (en) * | 2021-11-11 | 2022-02-11 | 华南农业大学 | Greenhouse temperature and humidity method controlled by particle swarm BP neural network PID |
| CN114610748A (en) * | 2022-03-16 | 2022-06-10 | 云南升玥信息技术有限公司 | Safe, rapid, accurate and effective medical disease data management system based on artificial intelligence and application |
| CN115665184A (en) * | 2022-09-07 | 2023-01-31 | 苏州德品医疗科技股份有限公司 | Intelligent extension system of bedside for intelligent hospital based on Internet of things technology |
| CN115662591A (en) * | 2022-11-02 | 2023-01-31 | 浙江大学 | Ward integrated management platform and server |
| CN116013495A (en) * | 2022-12-08 | 2023-04-25 | 广州视声健康科技有限公司 | Data monitoring method and device based on intelligent ward |
| CN116364295A (en) * | 2022-12-28 | 2023-06-30 | 北京谊安医疗系统股份有限公司 | Medical data processing method and system |
| DE202023101305U1 (en) * | 2023-03-16 | 2023-05-23 | Lulwah Mohammed Alkwai | An intelligent health and fitness data management system using artificial intelligence with IoT devices |
| CN116147112A (en) * | 2023-04-21 | 2023-05-23 | 安徽逸天科技有限公司 | Hospital environment health data communication control processing system based on artificial intelligence |
| CN116684454A (en) * | 2023-06-02 | 2023-09-01 | 成都瑞华康源科技有限公司 | Automatic control system, method and storage medium for operating room environment |
| CN116825314A (en) * | 2023-08-28 | 2023-09-29 | 四川互慧软件有限公司 | Dynamic optimal distribution system and method for medical rescue resources based on operation research |
Non-Patent Citations (6)
| Title |
|---|
| Hospital environment and patient recovery – a review;A. Lourenço et al.;European Psychiatry;753-754 * |
| The effects of environmental factors on the patient outcomes in hospital environments: A review of literature;Saman Jamshidi et al.;Frontiers of Architectural Research;249-263 * |
| 优化病区环境对提高康复质量的临床研究;唐海英;廖静;黎旭英;;首都食品与医药(24);107 * |
| 医院公共空间环境对病人心理的影响分析;巴志强;林晓萍;郭启勇;郭锡斌;;医学与哲学(人文社会医学版)(04);52-54 * |
| 基于AHP-FCE的医院陪护病床设计与评价;侯士江;刘甲财;孙可;;包装工程(24);186-190 * |
| 浅谈影响患者病情的环境因素;刘超琼;何正昌;;大家健康(学术版)(16);41 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117116455A (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111105860B (en) | Accurate motion big data intelligent prediction, analysis and optimization system for chronic disease rehabilitation | |
| Kangra et al. | Comparative analysis of predictive machine learning algorithms for diabetes mellitus | |
| CN116680637B (en) | Construction method and device of sensing data analysis model of community-built elderly people | |
| CN110880369A (en) | Gas marker detection method based on radial basis function neural network and application | |
| Wang et al. | Diabetes Risk Analysis Based on Machine Learning LASSO Regression Model | |
| CN117854739A (en) | Intelligent internal medicine nursing monitoring system | |
| CN107480721A (en) | A kind of ox only ill data analysing method and device | |
| CN117116455B (en) | Intelligent control method and system for Internet of things | |
| CN112382382B (en) | Cost-sensitive integrated learning classification method and system | |
| CN116665843A (en) | Dietary energy intake optimization method for tumor patients | |
| CN114613465B (en) | Cerebral apoplexy risk prediction and personalized treatment recommendation method and system | |
| CN109801711B (en) | Juvenile body composition prediction method based on PSO algorithm | |
| CN111709440B (en) | Feature selection method based on FSA-choket fuzzy integral | |
| CN118471540B (en) | Cardiovascular case data processing method and system | |
| Zhao et al. | Genetic Algorithm-Based Optimization of Arrhythmia Classification Model | |
| CN117476183B (en) | Construction system of autism children rehabilitation effect AI evaluation model | |
| CN117883076B (en) | Human movement energy consumption monitoring system and method based on big data | |
| Farabe et al. | A supervised learning approach by machine learning and deep learning algorithms to predict type II DM risk | |
| US20240185056A1 (en) | An apparatus for enhancing longevity and method for its use | |
| CN115545507A (en) | Indoor space thermal comfort evaluation method, device and system | |
| Chen et al. | A Classification Model for Drug Addicts Based on Improved Random Forests Algorithm | |
| CN118522473A (en) | Method, system, electronic device and medium for predicting postoperative pulmonary complications | |
| CN118446652A (en) | LED track lamp production control method and system based on Internet of things | |
| WO2024091292A1 (en) | Cancer progression assessment method and system thereof | |
| CN118711822A (en) | Cardiovascular and cerebrovascular disease risk prediction method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |