CN117423459A - Infant physical health detection platform and method based on artificial intelligence - Google Patents
Infant physical health detection platform and method based on artificial intelligence Download PDFInfo
- Publication number
- CN117423459A CN117423459A CN202311488785.7A CN202311488785A CN117423459A CN 117423459 A CN117423459 A CN 117423459A CN 202311488785 A CN202311488785 A CN 202311488785A CN 117423459 A CN117423459 A CN 117423459A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- report
- sub
- health
- 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
- 230000036541 health Effects 0.000 title claims abstract description 125
- 238000001514 detection method Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 25
- 238000003745 diagnosis Methods 0.000 claims abstract description 88
- 238000005516 engineering process Methods 0.000 claims abstract description 57
- 230000002159 abnormal effect Effects 0.000 claims abstract description 45
- 238000012544 monitoring process Methods 0.000 claims abstract description 19
- 238000003058 natural language processing Methods 0.000 claims abstract description 12
- 230000005856 abnormality Effects 0.000 claims description 48
- 230000005540 biological transmission Effects 0.000 claims description 34
- 238000012545 processing Methods 0.000 claims description 34
- 238000004458 analytical method Methods 0.000 claims description 31
- 230000003902 lesion Effects 0.000 claims description 25
- 230000006399 behavior Effects 0.000 claims description 24
- 208000024891 symptom Diseases 0.000 claims description 22
- 238000005457 optimization Methods 0.000 claims description 20
- 238000003909 pattern recognition Methods 0.000 claims description 18
- 238000013135 deep learning Methods 0.000 claims description 17
- 201000010099 disease Diseases 0.000 claims description 13
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 13
- 238000013527 convolutional neural network Methods 0.000 claims description 11
- 238000007619 statistical method Methods 0.000 claims description 11
- 230000007246 mechanism Effects 0.000 claims description 10
- 238000007405 data analysis Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 9
- 238000013480 data collection Methods 0.000 claims description 8
- 238000013500 data storage Methods 0.000 claims description 8
- 230000003993 interaction Effects 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000036760 body temperature Effects 0.000 claims description 6
- 238000010223 real-time analysis Methods 0.000 claims description 6
- 238000007418 data mining Methods 0.000 claims description 5
- 230000002452 interceptive effect Effects 0.000 claims description 5
- 230000036387 respiratory rate Effects 0.000 claims description 5
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000012800 visualization Methods 0.000 claims description 4
- 238000012300 Sequence Analysis Methods 0.000 claims description 3
- 238000011217 control strategy Methods 0.000 claims description 3
- 238000011221 initial treatment Methods 0.000 claims description 3
- 230000001133 acceleration Effects 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims 1
- 230000005802 health problem Effects 0.000 abstract description 4
- 238000013461 design Methods 0.000 abstract description 2
- 238000007726 management method Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003862 health status Effects 0.000 description 2
- 230000001965 increasing effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003449 preventive effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000011282 treatment Methods 0.000 description 2
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 235000006694 eating habits Nutrition 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000008103 glucose Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000000007 visual effect 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
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- 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
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- 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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Epidemiology (AREA)
- Biophysics (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Animal Behavior & Ethology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to the technical field of medical health, in particular to an artificial intelligence-based infant physical health detection platform and a method thereof. According to the invention, the real-time monitoring of the physiological parameters of the infants is realized by combining the wearable equipment technology, timely and accurate physiological data are provided, potential health risks can be timely found and early warned through the design of the abnormal early warning module, the personalized health recommendation module combines the historical health data of the infants, a health scheme is customized for the infants, the virtual doctor assistant module utilizes the natural language processing and the knowledge graph technology to help parents obtain medical advice in the primary stage, and the image diagnosis auxiliary module enables doctors to diagnose potential health problems more accurately.
Description
Technical Field
The invention relates to the technical field of medical health, in particular to an artificial intelligence-based infant physical health detection platform and a method thereof.
Background
The technical field of medical health refers to research and application in the aspects of monitoring, diagnosing, treating, preventing and the like of human health by utilizing modern information technology means. This field relates to a number of disciplines, such as computer science, biomedical engineering, medical imaging, and the like.
The infant physical health detection platform and the infant physical health detection method based on the artificial intelligence are used for detecting infant physical health by means of an artificial intelligence technology. The platform evaluates and predicts the physical health condition of the infant by collecting physiological data (such as heart rate, respiration, body temperature and the like) of the infant and combining big data analysis and a machine learning algorithm. The method aims at helping parents to know the physical condition of infants in time, preventing diseases, providing reference basis for doctors, and making personalized treatment schemes better. To achieve this, the platform typically employs a variety of sensors and devices to collect physiological data of the child and upload the data to the cloud for processing. Then, the data are analyzed and mined through a machine learning algorithm, and an evaluation result of the physical health condition of the infants is obtained. Finally, the results are visually presented to parents and doctors for their reference and decision making.
Most of the existing infant physical health detection systems lack real-time and intelligentization, and cannot effectively monitor physiological parameters of infants continuously. Thus, once a child has a health abnormality, a delayed discovery may occur, increasing the risk. In addition, many existing systems do not have personalized health recommendation functions, and unified standards are often adopted to provide the same advice for all infants, so that unique requirements of different infants are difficult to meet. In terms of image diagnosis, however, the old system may rely on only conventional medical image analysis techniques, and lack support of modern AI image recognition techniques, which may result in insufficient sensitivity and accuracy in detection of diseases.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides an artificial intelligence-based infant physical health detection platform and a method thereof.
In order to achieve the above purpose, the present invention adopts the following technical scheme: the infant physical health detection platform based on artificial intelligence comprises a physiological parameter monitoring module, an abnormality early warning module, a personalized health recommendation module, a virtual doctor assistant module, a data security protection module and an image diagnosis auxiliary module;
The physiological parameter monitoring module is used for collecting data based on the wearable equipment, adopting a data preprocessing technology to clean and format the data, and performing real-time monitoring to generate real-time physiological parameter data;
the abnormality early warning module is used for carrying out data analysis and abnormality pattern recognition by adopting a sequence abnormality detection algorithm based on the real-time physiological parameter data to generate an abnormality early warning report;
the personalized health recommendation module adopts a data mining technology to analyze user behaviors based on the user files and the historical health data, and makes personalized health schemes to generate personalized health schemes;
the virtual doctor assistant module performs preliminary diagnosis by adopting natural language processing and a knowledge graph based on symptoms and abnormal early warning reports input by a user, performs professional consultation scheme pairing, and generates a diagnosis consultation report;
the data security protection module adopts a block chain encryption technology to encrypt and control access to data, and performs data transmission to generate data privacy protection measures;
the image diagnosis auxiliary module is used for carrying out feature extraction and positioning of a lesion area by adopting an image recognition algorithm based on the acquired medical image data to generate an image diagnosis report;
The real-time physiological parameter data comprises a numerical set of heart rate, respiratory rate and body temperature indexes, the abnormal early warning report comprises abnormal events, duration and recommended schemes, the diagnosis consultation report comprises potential disease information and primary treatment comments, the data privacy protection is particularly used for encrypting stored user personal information and data privacy in transmission, and the image diagnosis report comprises image abnormal areas, disease probability and diagnosis comments of auxiliary doctors.
As a further scheme of the invention, the physiological parameter monitoring module comprises a data acquisition sub-module, a data transmission sub-module and a data storage sub-module;
the abnormality early warning module comprises an abnormality identification sub-module, a threshold setting sub-module and an early warning notification sub-module;
the personalized health recommendation module comprises a data collection sub-module, an algorithm analysis sub-module and a scheme generation sub-module;
the virtual doctor assistant module comprises a knowledge base establishment sub-module, a language processing sub-module and a diagnosis support sub-module;
the data security protection module comprises a data encryption sub-module, a data anonymization sub-module and a user authority setting sub-module;
the image diagnosis auxiliary module comprises an image processing sub-module, a pattern recognition sub-module and a doctor interaction sub-module.
As a further scheme of the invention, the data acquisition sub-module is based on wearable equipment, adopts a real-time signal processing technology to acquire physiological parameters in real time, and generates an original physiological data set through a data encoding technology;
the data transmission submodule utilizes a safe encryption transmission technology to carry out real-time transmission of data and generates a transmitted physiological data set through network protocol optimization;
the data storage submodule adopts a storage engine to store the transmitted physiological data set, and generates real-time physiological parameter data through database index optimization.
As a further scheme of the invention, the abnormality recognition submodule adopts a sequence abnormality detection algorithm to analyze an abnormality mode in real time based on real-time physiological parameter data, and generates a preliminary abnormality mode report through a mode recognition technology;
the threshold setting submodule is combined with a statistical analysis method to set an individualized physiological parameter threshold, and a parameter threshold standard is generated through a threshold adjustment mechanism;
and the early warning notification submodule judges whether to trigger early warning according to the preliminary abnormal mode report and the parameter threshold standard, and generates an abnormal early warning report through the intelligent notification system.
As a further scheme of the invention, the data collection sub-module collects the archives and the historical health data of the user and generates a historical health data set of the user through a personal health data analysis technology;
the algorithm analysis submodule adopts a deep learning algorithm to carry out deep analysis of user behaviors based on a user history health data set, and generates a user behavior analysis report through behavior pattern recognition;
the scheme generating submodule formulates a personalized health scheme according to the user behavior analysis report, and generates the personalized health scheme through a recommendation system algorithm.
As a further scheme of the invention, the knowledge base building submodule adopts deep learning and natural language processing methods to extract and sort knowledge based on medical literature data so as to generate a medical knowledge graph;
the language processing sub-module adopts a BERT model to analyze and understand symptom semantics based on user input and medical knowledge graph, and generates a user symptom semantics understanding report;
the diagnosis support submodule performs preliminary diagnosis and professional consultation scheme pairing by adopting a fuzzy logic and medical reasoning algorithm based on the user symptom semantic understanding report and the abnormality early warning report to generate a diagnosis consultation report.
As a further scheme of the invention, the data encryption sub-module adopts an asymmetric encryption algorithm to carry out data encryption protection based on the diagnosis consultation report, and generates an encrypted diagnosis consultation report;
the data anonymization submodule performs data anonymization processing by adopting a k-anonymization algorithm based on the encrypted diagnosis consultation report to generate an anonymization diagnosis consultation report;
and the user permission setting submodule is used for setting user permission based on the anonymized diagnosis consultation report by adopting an access control strategy based on roles, and generating data privacy protection measures.
As a further scheme of the invention, the image processing sub-module performs image preprocessing by adopting a gaussian filtering and image enhancement algorithm based on medical image data to generate preprocessed medical image data;
the pattern recognition submodule carries out lesion feature recognition by adopting a convolutional neural network based on the preprocessed medical image data to generate lesion feature data;
and the doctor interaction sub-module is used for positioning the lesion area by adopting an interactive visualization technology based on the lesion characteristic data and generating an image diagnosis report.
The infant physical health detection method based on the artificial intelligence is executed based on the infant physical health detection platform based on the artificial intelligence, and comprises the following steps of:
S1: based on wearable equipment, adopting a real-time signal processing technology to collect physiological parameters in real time, and performing data coding to generate an original physiological data set;
s2: based on the original physiological data set, adopting a secure encryption transmission technology to encrypt data, and optimizing a network protocol to generate a transmitted physiological data set;
s3: based on the transmitted physiological data set, a storage engine technology is adopted to store data, database index optimization is carried out, and real-time physiological parameter data are generated;
s4: based on the real-time physiological parameter data, adopting a sequence anomaly detection algorithm to perform real-time analysis of an anomaly mode, and performing mode recognition to generate a preliminary anomaly mode report;
s5: based on the preliminary abnormal mode report, setting an individualized physiological parameter threshold value by combining a statistical analysis method, and carrying out a threshold value adjustment mechanism to generate a parameter threshold value standard;
s6: based on the parameter threshold standard and the preliminary abnormal mode report, judging whether to trigger early warning or not, and carrying out early warning notification through an intelligent notification system to generate an abnormal early warning report;
s7: based on the abnormal early warning report, performing deep analysis of the personalized health scheme by adopting a deep learning algorithm, and performing a recommendation system algorithm to generate a personalized health scheme report.
As a further scheme of the invention, the real-time signal processing technology specifically refers to frequency domain analysis of signals through fourier transformation, the data encoding specifically refers to digitizing of the signals, the secure encryption transmission technology specifically refers to AES encryption algorithm, the network protocol optimization specifically refers to optimization of transmission rate and security by adopting a qic protocol, the storage engine technology specifically refers to InnoDB storage engine, the database index optimization specifically refers to accelerating retrieval speed by using a b+ tree index, the sequence anomaly detection algorithm specifically refers to time sequence analysis through a long and short memory network, the pattern recognition specifically refers to judging whether the signals are in an anomaly mode through a support vector machine, the statistical analysis method specifically refers to a Z-score method, the threshold adjustment mechanism comprises self-adaptive adjustment of threshold values according to historical data, the deep learning algorithm specifically refers to feature extraction of health data through a convolutional neural network, and the recommendation system algorithm specifically refers to generating a health scheme for users through a collaborative filtering algorithm.
Compared with the prior art, the invention has the advantages and positive effects that:
according to the invention, by combining with the wearable equipment technology, the real-time monitoring of the physiological parameters of the infants is realized, and timely and accurate physiological data are provided. Through the design of the abnormal early warning module, the platform can timely discover and early warn potential health risks, so that the infant can be intervened earlier. The personalized health recommendation module combines the historical health data of the infants and customizes health schemes for the infants. The virtual doctor assistant module utilizes natural language processing and knowledge graph technology to help parents obtain medical advice in the primary stage. The presence of the imaging diagnosis assistance module enables the physician to more accurately analyze and diagnose potential health problems.
Drawings
FIG. 1 is a platform flow diagram of the present invention;
FIG. 2 is a schematic view of a platform frame according to the present invention;
FIG. 3 is a flow chart of a physiological parameter monitoring module according to the present invention;
FIG. 4 is a flowchart of an anomaly early warning module according to the present invention;
FIG. 5 is a flowchart of a personalized health recommendation module of the present invention;
FIG. 6 is a flow chart of a virtual doctor helper module of the present invention;
FIG. 7 is a flow chart of a data security protection module of the present invention;
FIG. 8 is a flowchart of an image diagnosis assisting module according to the present invention;
FIG. 9 is a schematic diagram of the method steps of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Example 1
Referring to fig. 1, the present invention provides a technical solution: the infant physical health detection platform based on artificial intelligence comprises a physiological parameter monitoring module, an abnormality early warning module, a personalized health recommendation module, a virtual doctor assistant module, a data security protection module and an image diagnosis auxiliary module;
the physiological parameter monitoring module is used for collecting data based on the wearable equipment, adopting a data preprocessing technology to clean and format the data, and carrying out real-time monitoring to generate real-time physiological parameter data;
the abnormality early warning module is used for carrying out data analysis and abnormality pattern recognition by adopting a sequence abnormality detection algorithm based on the real-time physiological parameter data to generate an abnormality early warning report;
the personalized health recommendation module is used for analyzing user behaviors based on the user files and the historical health data by adopting a data mining technology, making personalized health schemes and generating personalized health schemes;
the virtual doctor assistant module performs preliminary diagnosis by adopting natural language processing and a knowledge graph based on the symptom and abnormality early warning report input by the user, and performs professional consultation scheme pairing to generate a diagnosis consultation report;
the data security protection module adopts a block chain encryption technology to encrypt and control access to data, and performs data transmission to generate data privacy protection measures;
The image diagnosis auxiliary module is used for carrying out feature extraction and positioning of a lesion area by adopting an image recognition algorithm based on the acquired medical image data to generate an image diagnosis report;
the real-time physiological parameter data comprises a numerical set of heart rate, respiratory rate and body temperature indexes, the abnormal early warning report comprises abnormal events, duration and proposal schemes, the diagnosis consultation report comprises potential disease information and primary treatment comments, the data privacy protection is specifically encryption stored user personal information and data privacy in transmission, and the image diagnosis report comprises image abnormal areas, disease probability and diagnosis comments of auxiliary doctors.
Firstly, a physiological parameter monitoring module monitors physiological data of infants in real time through wearable equipment, and generates real-time physiological parameter data through data cleaning and formatting. The health status of the infants is monitored in real time, key physiological information is ensured to be obtained in time, and a solid foundation is provided for early disease diagnosis and health management.
The abnormality early warning module analyzes the real-time physiological parameter data by adopting a sequence abnormality detection algorithm, identifies an abnormality mode and generates an abnormality early warning report. This helps to alert in time when an abnormal situation occurs, provides early diagnosis and preventive measures, helps to reduce the risk of disease, and improves the quality of life for infants.
The personalized health recommendation module establishes a personalized health scheme for each infant by utilizing a data mining technology based on the user file and the historical health data. The personalized method can meet the unique requirements of each infant, provides more accurate health advice and promotes positive management of health.
The virtual doctor assistant module provides a preliminary diagnosis and professional consultation scheme for the user through natural language processing and a knowledge graph. The assistant for virtual doctor can provide consultation for parents at any time, help them to better know the health condition of infants and take proper measures. The data security protection module adopts a block chain encryption technology to ensure the security and privacy of user data. This increases user trust, making them more willing to share data, facilitating sustainable use of the platform. The image diagnosis auxiliary module can help doctors to locate lesion areas through an image recognition algorithm, provides more accurate image diagnosis reports and provides important support for medical decision.
Referring to fig. 2, the physiological parameter monitoring module includes a data acquisition sub-module, a data transmission sub-module, and a data storage sub-module;
the abnormality early warning module comprises an abnormality identification sub-module, a threshold setting sub-module and an early warning notification sub-module;
The personalized health recommendation module comprises a data collection sub-module, an algorithm analysis sub-module and a scheme generation sub-module;
the virtual doctor assistant module comprises a knowledge base building sub-module, a language processing sub-module and a diagnosis support sub-module;
the data security protection module comprises a data encryption sub-module, a data anonymization sub-module and a user authority setting sub-module;
the image diagnosis auxiliary module comprises an image processing sub-module, a pattern recognition sub-module and a doctor interaction sub-module.
In the physiological parameter monitoring module, a data acquisition sub-module acquires a numerical set of heart rate, respiratory rate and body temperature indexes through wearable equipment; the data transmission sub-module transmits the real-time physiological parameter data; the data storage sub-module cleans and formats the acquired data and monitors the data in real time.
In the abnormality early warning module, an abnormality recognition submodule adopts a sequence abnormality detection algorithm to analyze data based on real-time physiological parameter data; the threshold setting submodule sets a threshold value of the abnormal event according to the analysis result; the early warning notification sub-module generates an abnormal early warning report including an abnormal event, a duration, and a suggested proposal.
In the personalized health recommendation module, a data collection submodule performs data mining according to the user file and the historical health data; the algorithm analysis sub-module analyzes the user behavior; the scheme generation submodule formulates a personalized health scheme.
In the virtual doctor assistant module, a knowledge base building sub-module builds a medical knowledge map; the language processing sub-module carries out natural language processing on symptoms input by a user; the diagnosis support sub-module performs preliminary diagnosis according to the symptom and abnormality early warning report and provides professional consultation scheme pairing.
In the data security protection module, a data encryption submodule encrypts data by adopting a blockchain encryption technology; the data anonymization submodule anonymizes the personal information of the user; the user authority setting sub-module controls the access authority of the data.
In the image diagnosis auxiliary module, an image processing sub-module acquires medical image data and performs feature extraction; the pattern recognition sub-module is used for positioning a lesion area; the doctor interaction sub-module provides an image diagnosis report including an image abnormal region, a disease probability and diagnosis comments of an auxiliary doctor.
Referring to fig. 3, the data acquisition sub-module performs real-time acquisition of physiological parameters by adopting a real-time signal processing technology based on the wearable device, and generates an original physiological data set by adopting a data encoding technology;
the data transmission submodule utilizes a safe encryption transmission technology to carry out real-time transmission of data, and generates a transmitted physiological data set through network protocol optimization;
The data storage sub-module adopts a storage engine to store the transmitted physiological data set, and generates real-time physiological parameter data through database index optimization.
The data acquisition sub-module is based on wearable equipment and adopts a real-time signal processing technology to acquire physiological parameters in real time. First, the wearable device is worn on a child, ensuring that the device is in close contact with the body. Then, physiological parameters such as heart rate, respiratory rate and body temperature are monitored through sensors built in the equipment, and monitored data are collected in real time.
The data transmission submodule utilizes a safe encryption transmission technology to transmit the acquired physiological data in real time. In order to ensure the security of the data, a secure transmission protocol, such as HTTPS or VPN, is used to encrypt the data. Meanwhile, in order to improve the transmission efficiency, a network protocol optimization technology such as a compression algorithm, a multi-line Cheng Chuanshu and the like can be adopted to optimize the data.
The data storage sub-module adopts a storage engine to store the transmitted physiological data set. Firstly, selecting a proper storage engine, such as a relational database or a NoSQL database, and the like, and selecting according to actual requirements. The transmitted physiological data set is then stored in a database and a corresponding index is established for subsequent query and analysis operations.
Referring to fig. 4, the anomaly identification sub-module performs real-time analysis of an anomaly mode by using a sequential anomaly detection algorithm based on real-time physiological parameter data, and generates a preliminary anomaly mode report by a mode identification technique;
the threshold setting submodule is combined with a statistical analysis method to set an individualized physiological parameter threshold, and a parameter threshold standard is generated through a threshold adjustment mechanism;
the early warning notification sub-module judges whether to trigger early warning according to the preliminary abnormal mode report and the parameter threshold standard, and generates an abnormal early warning report through the intelligent notification system.
The abnormality recognition submodule adopts a sequence abnormality detection algorithm to conduct real-time analysis of an abnormality mode based on the real-time physiological parameter data. Firstly, preprocessing is performed on physiological parameter data acquired in real time, such as noise removal, smoothing and the like. And then, inputting the preprocessed data into a sequence anomaly detection algorithm, and judging whether an anomaly mode exists by comparing the similarity of the current data and the historical data.
The threshold setting submodule is combined with a statistical analysis method to set an individualized physiological parameter threshold. First, a large amount of normal physiological parameter data is collected as a reference according to factors such as age, sex, physical condition, etc. of the infant. These data are then analyzed using statistical methods to calculate the mean and standard deviation of each physiological parameter. Finally, according to the statistical results, combining clinical experience and expert opinion, setting reasonable physiological parameter threshold values.
And the early warning notification sub-module judges whether to trigger early warning according to the preliminary abnormal mode report and the parameter threshold standard, and generates an abnormal early warning report through the intelligent notification system. Firstly, comparing the preliminary abnormal mode report with a parameter threshold standard, and judging whether the current data exceeds a set threshold or an abnormal mode appears. And if the early warning condition is met, triggering an early warning mechanism. And then, sending an abnormal early warning report to related personnel through an intelligent notification system, wherein the abnormal early warning report comprises information such as description, duration, proposal scheme and the like of an abnormal event.
Referring to fig. 5, the data collection sub-module collects the user's profile and historical health data, and generates a user historical health data set through a personal health data analysis technique;
the algorithm analysis submodule adopts a deep learning algorithm to carry out deep analysis of user behaviors based on a user history health data set, and generates a user behavior analysis report through behavior pattern recognition;
the scheme generation submodule formulates a personalized health scheme according to the user behavior analysis report, and generates the personalized health scheme through a recommendation system algorithm.
The data collection sub-module collects the user's profile and historical health data and generates a user historical health data set through personal health data analysis techniques. First, user profile information including basic information, medical history, medication records, etc. is obtained from an associated medical system or health management platform. Historical health data of the user, such as physical examination reports, blood pressure, blood glucose and other physiological parameter measurement results, are then collected. Next, the collected data is processed and analyzed using personal health data analysis techniques to extract features and patterns related to the user's health condition. And finally, integrating the processed data into a user history health data set.
The algorithm analysis submodule adopts a deep learning algorithm to conduct deep analysis of user behaviors based on the user history health data set, and generates a user behavior analysis report through behavior pattern recognition. First, a user historical health dataset is input into a deep learning algorithm, such as a Recurrent Neural Network (RNN) or Convolutional Neural Network (CNN), to learn a user's behavioral pattern. Different behavior patterns, such as exercise habits, eating habits, etc., are then identified and categorized by training the model. Next, a user behavior analysis report is generated according to the identified behavior pattern, including information such as health status assessment, potential risk prompt, etc. of the user.
The proposal generating submodule formulates a personalized health proposal according to the user behavior analysis report, and generates the personalized health proposal through a recommendation system algorithm. Firstly, according to health state assessment and potential risk prompt provided in a user behavior analysis report, corresponding health improvement targets and measures are formulated by combining clinical experience and expert opinion. And then, personalized adjustment and optimization are carried out on the formulated health scheme by using a recommendation system algorithm so as to meet the specific requirements and preferences of the user. Finally, a personalized wellness programme is generated and detailed instructions and advice are provided to the user.
Referring to fig. 6, the knowledge base building submodule performs knowledge extraction and arrangement by adopting a deep learning and natural language processing method based on medical literature data to generate a medical knowledge map;
the language processing sub-module is used for analyzing and understanding symptom semantics based on user input and medical knowledge graph by adopting a BERT model, and generating a user symptom semantics understanding report;
the diagnosis support submodule adopts fuzzy logic and medical reasoning algorithm to pair the preliminary diagnosis and the professional consultation scheme based on the user symptom semantic understanding report and the abnormality early warning report, and generates a diagnosis consultation report.
The knowledge base building submodule adopts deep learning and natural language processing methods to extract and sort knowledge based on medical literature data, and generates medical knowledge maps. First, relevant medical literature data including clinical guidelines, research papers, and the like are collected. Then, a deep learning algorithm is used for carrying out text mining and entity recognition on the literature data, and important medical concepts and relations are extracted. Next, these entities are classified and generalized using natural language processing methods, creating structures and associations of medical knowledge maps.
The language processing sub-module adopts the BERT model to analyze and understand symptom semantics based on user input and medical knowledge graph, and generates a user symptom semantics understanding report. First, the input sentence of the user is subjected to word segmentation and encoding processing for subsequent processing. And then, carrying out semantic analysis and understanding on the encoded sentences by using the pre-trained BERT model, and extracting key symptom information. Next, possible diseases or health problems are further analyzed and inferred from the associations in the medical knowledge graph. Finally, a user symptom semantic understanding report is generated, including information such as symptom descriptions, possible etiologies, and the like.
The diagnosis support submodule carries out preliminary diagnosis and professional consultation scheme pairing by adopting a fuzzy logic and medical reasoning algorithm based on the user symptom semantic understanding report and the abnormality early warning report to generate a diagnosis consultation report. Firstly, comprehensively analyzing information in a symptom semantic understanding report and an abnormality early warning report of a user. And then modeling and reasoning the association between the symptoms and the diseases by using a fuzzy logic algorithm to obtain a preliminary diagnosis result. And then, matching corresponding professional consultation schemes from the medical knowledge graph according to the preliminary diagnosis result and the personal condition of the user. Finally, generating a diagnosis consultation report, including information such as the preliminary diagnosis result, the suggested treatment scheme and the like.
Referring to fig. 7, the data encryption sub-module performs data encryption protection by adopting an asymmetric encryption algorithm based on the diagnosis consultation report, and generates an encrypted diagnosis consultation report;
the data anonymization submodule performs data anonymization processing by adopting a k-anonymization algorithm based on the encrypted diagnosis consultation report to generate an anonymization diagnosis consultation report;
the user permission setting submodule adopts a role-based access control strategy to set user permission based on the anonymized diagnosis consultation report, and generates data privacy protection measures.
The data encryption sub-module obtains the original data of the diagnosis consultation report. An asymmetric encryption algorithm, such as RSA or ECC, is then selected for cryptographically protecting the data. Next, a pair of keys is generated, including a public key and a private key. The public key is used to encrypt data and the private key is used to decrypt data. And then, encrypting the original data of the diagnosis consultation report by using the public key to generate an encrypted diagnosis consultation report. Finally, the encrypted diagnostic advisory report is stored in a secure storage medium, ensuring that only authorized users can access.
The data anonymization submodule loads the encrypted diagnostic advisory report. Then, a k-anonymization algorithm is selected for anonymizing the data. And then, sensitive information in the encrypted diagnosis consultation report is processed according to the requirement of the k-anonymization algorithm so as to protect the privacy of the user. And then generating an anonymized diagnosis consultation report which contains anonymized data. Finally, the anonymized diagnostic advisory report is stored in a secure storage medium, ensuring that only authorized users can access.
The user authority setting submodule loads an anonymized diagnosis consultation report. Then, the roles and users in the system are determined, and corresponding rights are assigned to each role. Then, based on the access control policy of the role, setting the access authority of the user to the anonymized diagnosis consultation report. And then, controlling operations such as reading, modifying and deleting the anonymized diagnosis consultation report by the user according to the role and the authority of the user. The user's rights settings information is then recorded for subsequent auditing and tracking. And finally, ensuring that only users with corresponding rights can access the anonymized diagnosis consultation report, and realizing data privacy protection measures.
Referring to fig. 8, the image processing sub-module performs image preprocessing by using gaussian filtering and an image enhancement algorithm based on medical image data to generate preprocessed medical image data;
the pattern recognition submodule carries out lesion feature recognition by adopting a convolutional neural network based on the preprocessed medical image data to generate lesion feature data;
based on the lesion characteristic data, the doctor interaction sub-module adopts an interactive visualization technology to locate a lesion area and generate an image diagnosis report.
The image processing sub-module acquires medical image data including X-ray film, CT scan or MRI. Then, the medical image data is subjected to a gaussian filter process to reduce noise and smooth an image. Next, image enhancement algorithms, such as histogram equalization, contrast enhancement, etc., are applied to enhance the visual effect of the image. Finally, the preprocessed medical image data is generated and prepared for subsequent pattern recognition.
The mode identification submodule loads the preprocessed medical image data. Then, a convolutional neural network model is constructed, which comprises an input layer, a convolutional layer, a pooling layer, a full connection layer and the like. Next, the convolutional neural network is trained using the training set to learn the recognition pattern of the lesion feature. And then, inputting the preprocessed medical image data into a trained convolutional neural network to identify lesion features. And finally, generating lesion characteristic data comprising information such as the position, shape, size and the like of the lesion.
The doctor interaction sub-module loads lesion feature data. And then, using an interactive visualization technology to visually display the lesion feature data on the medical image. Next, the physician may locate and mark the lesion area through the interactive interface. Then, according to the doctor's mark, an image diagnosis report is generated, including information such as description, position, type, etc. of the lesion. Finally, doctors can modify and perfect the image diagnosis report to meet clinical requirements.
Referring to fig. 9, an artificial intelligence-based infant physical health detection method is performed based on the above-mentioned artificial intelligence-based infant physical health detection platform, and includes the following steps:
s1: based on wearable equipment, adopting a real-time signal processing technology to collect physiological parameters in real time, and performing data coding to generate an original physiological data set;
s2: based on the original physiological data set, adopting a secure encryption transmission technology to encrypt data, and optimizing a network protocol to generate a transmitted physiological data set;
s3: based on the transmitted physiological data set, adopting a storage engine technology to store data, and performing database index optimization to generate real-time physiological parameter data;
S4: based on the real-time physiological parameter data, adopting a sequence anomaly detection algorithm to perform real-time analysis of an anomaly mode, and performing mode recognition to generate a preliminary anomaly mode report;
s5: based on the preliminary abnormal mode report, setting an individualized physiological parameter threshold value by combining a statistical analysis method, and carrying out a threshold value adjustment mechanism to generate a parameter threshold value standard;
s6: based on the parameter threshold standard and the preliminary abnormal mode report, judging whether to trigger early warning or not, and carrying out early warning notification through an intelligent notification system to generate an abnormal early warning report;
s7: based on the abnormal early warning report, the deep learning algorithm is adopted to carry out the deep analysis of the personalized health scheme, and the recommendation system algorithm is carried out to generate the personalized health scheme report.
The real-time signal processing technology is characterized in that the signal is subjected to frequency domain analysis through Fourier transformation, the signal is digitized, the secure encryption transmission technology is an AES encryption algorithm, the network protocol optimization is the transmission rate and security optimization through a QUIC protocol, the storage engine technology is an InnoDB storage engine, the database index optimization is the retrieval speed acceleration through a B+ tree index, the sequence anomaly detection algorithm is a time sequence analysis through a long-short-time storage network, the pattern recognition is a mode judgment through a support vector machine, the statistical analysis method is a Z-score method, the threshold adjustment mechanism comprises the self-adaptive adjustment of a threshold according to historical data, the deep learning algorithm is the feature extraction of healthy data through a convolutional neural network, and the recommendation system algorithm is the generation of a health scheme for users through a collaborative filtering algorithm.
Through the real-time signal processing technology of Fourier transformation, the physiological parameters of the infants, such as heart rate, blood pressure and the like, can be efficiently and accurately monitored in real time, and timeliness and accuracy of monitoring data are ensured. This is critical for early detection of physiological abnormalities in infants and timely taking medical action, especially when dealing with sudden health problems.
And secondly, the application of the AES encryption algorithm and the QUIC protocol ensures the safe transmission of physiological data, thus protecting personal privacy and improving the speed and the safety of data transmission. This is particularly important in the current digital and networked era background, and effectively avoids the risk of malicious interception or tampering of data.
Furthermore, by the InnoDB storage engine and the application of the B+ tree index, the storage efficiency of a large amount of health data is improved, the data retrieval speed is also increased, and the management of the health data is more efficient and stable. This is particularly important for processing large-scale health data, enhancing the overall performance of the system.
In addition, the application of the long-short-term memory network and the support vector machine in the aspects of abnormal mode detection and recognition enables the system to effectively recognize and analyze abnormal health modes and timely discover potential health risks. The method provides powerful data support for parents and medical institutions, and is helpful for improving the preventive and targeted health management of infants. The personalized health scheme recommendation combining the deep learning and collaborative filtering algorithm not only provides health suggestions for individuals, but also improves the adaptability and practicability of the scheme. The personalized health management mode can better meet the specific requirements of different infants, and promote the comprehensive development of the health of the infants.
The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.
Claims (10)
1. Infant physical health testing platform based on artificial intelligence, its characterized in that: the infant physical health detection platform based on the artificial intelligence comprises a physiological parameter monitoring module, an abnormality early warning module, a personalized health recommendation module, a virtual doctor assistant module, a data security protection module and an image diagnosis auxiliary module;
the physiological parameter monitoring module is used for collecting data based on the wearable equipment, adopting a data preprocessing technology to clean and format the data, and performing real-time monitoring to generate real-time physiological parameter data;
the abnormality early warning module is used for carrying out data analysis and abnormality pattern recognition by adopting a sequence abnormality detection algorithm based on the real-time physiological parameter data to generate an abnormality early warning report;
The personalized health recommendation module adopts a data mining technology to analyze user behaviors based on the user files and the historical health data, and makes personalized health schemes to generate personalized health schemes;
the virtual doctor assistant module performs preliminary diagnosis by adopting natural language processing and a knowledge graph based on symptoms and abnormal early warning reports input by a user, performs professional consultation scheme pairing, and generates a diagnosis consultation report;
the data security protection module adopts a block chain encryption technology to encrypt and control access to data, and performs data transmission to generate data privacy protection measures;
the image diagnosis auxiliary module is used for carrying out feature extraction and positioning of a lesion area by adopting an image recognition algorithm based on the acquired medical image data to generate an image diagnosis report;
the real-time physiological parameter data comprises a numerical set of heart rate, respiratory rate and body temperature indexes, the abnormal early warning report comprises abnormal events, duration and recommended schemes, the diagnosis consultation report comprises potential disease information and primary treatment comments, the data privacy protection is particularly used for encrypting stored user personal information and data privacy in transmission, and the image diagnosis report comprises image abnormal areas, disease probability and diagnosis comments of auxiliary doctors.
2. The artificial intelligence based infant physical health detection platform according to claim 1, wherein: the physiological parameter monitoring module comprises a data acquisition sub-module, a data transmission sub-module and a data storage sub-module;
the abnormality early warning module comprises an abnormality identification sub-module, a threshold setting sub-module and an early warning notification sub-module;
the personalized health recommendation module comprises a data collection sub-module, an algorithm analysis sub-module and a scheme generation sub-module;
the virtual doctor assistant module comprises a knowledge base establishment sub-module, a language processing sub-module and a diagnosis support sub-module;
the data security protection module comprises a data encryption sub-module, a data anonymization sub-module and a user authority setting sub-module;
the image diagnosis auxiliary module comprises an image processing sub-module, a pattern recognition sub-module and a doctor interaction sub-module.
3. The artificial intelligence-based infant physical health detection platform according to claim 2, wherein: the data acquisition sub-module is based on wearable equipment, adopts a real-time signal processing technology to acquire physiological parameters in real time, and generates an original physiological data set through a data encoding technology;
The data transmission submodule utilizes a safe encryption transmission technology to carry out real-time transmission of data and generates a transmitted physiological data set through network protocol optimization;
the data storage submodule adopts a storage engine to store the transmitted physiological data set, and generates real-time physiological parameter data through database index optimization.
4. The artificial intelligence-based infant physical health detection platform according to claim 2, wherein: the abnormality recognition submodule carries out real-time analysis of an abnormality mode by adopting a sequence abnormality detection algorithm based on real-time physiological parameter data and generates a preliminary abnormality mode report by a mode recognition technology;
the threshold setting submodule is combined with a statistical analysis method to set an individualized physiological parameter threshold, and a parameter threshold standard is generated through a threshold adjustment mechanism;
and the early warning notification submodule judges whether to trigger early warning according to the preliminary abnormal mode report and the parameter threshold standard, and generates an abnormal early warning report through the intelligent notification system.
5. The artificial intelligence-based infant physical health detection platform according to claim 2, wherein: the data collection submodule collects files and historical health data of the user and generates a historical health data set of the user through a personal health data analysis technology;
The algorithm analysis submodule adopts a deep learning algorithm to carry out deep analysis of user behaviors based on a user history health data set, and generates a user behavior analysis report through behavior pattern recognition;
the scheme generating submodule formulates a personalized health scheme according to the user behavior analysis report, and generates the personalized health scheme through a recommendation system algorithm.
6. The artificial intelligence-based infant physical health detection platform according to claim 2, wherein: the knowledge base building submodule is used for carrying out knowledge extraction and arrangement by adopting a deep learning and natural language processing method based on medical literature data to generate a medical knowledge map;
the language processing sub-module adopts a BERT model to analyze and understand symptom semantics based on user input and medical knowledge graph, and generates a user symptom semantics understanding report;
the diagnosis support submodule performs preliminary diagnosis and professional consultation scheme pairing by adopting a fuzzy logic and medical reasoning algorithm based on the user symptom semantic understanding report and the abnormality early warning report to generate a diagnosis consultation report.
7. The artificial intelligence-based infant physical health detection platform according to claim 2, wherein: the data encryption sub-module adopts an asymmetric encryption algorithm to carry out data encryption protection based on the diagnosis consultation report, and generates an encrypted diagnosis consultation report;
The data anonymization submodule performs data anonymization processing by adopting a k-anonymization algorithm based on the encrypted diagnosis consultation report to generate an anonymization diagnosis consultation report;
and the user permission setting submodule is used for setting user permission based on the anonymized diagnosis consultation report by adopting an access control strategy based on roles, and generating data privacy protection measures.
8. The artificial intelligence-based infant physical health detection platform according to claim 2, wherein: the image processing sub-module performs image preprocessing by adopting a Gaussian filtering and image enhancement algorithm based on the medical image data to generate preprocessed medical image data;
the pattern recognition submodule carries out lesion feature recognition by adopting a convolutional neural network based on the preprocessed medical image data to generate lesion feature data;
and the doctor interaction sub-module is used for positioning the lesion area by adopting an interactive visualization technology based on the lesion characteristic data and generating an image diagnosis report.
9. An artificial intelligence based infant physical health detection method, characterized in that the artificial intelligence based infant physical health detection platform according to any one of claims 1-8 is executed, comprising the following steps:
Based on wearable equipment, adopting a real-time signal processing technology to collect physiological parameters in real time, and performing data coding to generate an original physiological data set;
based on the original physiological data set, adopting a secure encryption transmission technology to encrypt data, and optimizing a network protocol to generate a transmitted physiological data set;
based on the transmitted physiological data set, a storage engine technology is adopted to store data, database index optimization is carried out, and real-time physiological parameter data are generated;
based on the real-time physiological parameter data, adopting a sequence anomaly detection algorithm to perform real-time analysis of an anomaly mode, and performing mode recognition to generate a preliminary anomaly mode report;
based on the preliminary abnormal mode report, setting an individualized physiological parameter threshold value by combining a statistical analysis method, and carrying out a threshold value adjustment mechanism to generate a parameter threshold value standard;
based on the parameter threshold standard and the preliminary abnormal mode report, judging whether to trigger early warning or not, and carrying out early warning notification through an intelligent notification system to generate an abnormal early warning report;
based on the abnormal early warning report, performing deep analysis of the personalized health scheme by adopting a deep learning algorithm, and performing a recommendation system algorithm to generate a personalized health scheme report.
10. The artificial intelligence based infant physical health detection method according to claim 9, wherein: the real-time signal processing technology specifically refers to frequency domain analysis of signals through Fourier transformation, the data coding specifically refers to digitizing of the signals, the secure encryption transmission technology specifically refers to AES encryption algorithm, the network protocol optimization specifically refers to optimization of transmission rate and security by adopting QUIC protocol, the storage engine technology specifically refers to InnoDB storage engine, the database index optimization specifically refers to acceleration of retrieval speed by using B+ tree index, the sequence anomaly detection algorithm specifically refers to time sequence analysis through a long and short time memory network, the pattern recognition specifically refers to judging whether the mode is an anomaly mode through a support vector machine, the statistical analysis method specifically refers to Z-score method, the threshold adjustment mechanism comprises self-adaptive adjustment of threshold according to historical data, the deep learning algorithm specifically refers to feature extraction of healthy data through a convolutional neural network, and the recommendation system algorithm specifically refers to generation of a health scheme for users through a collaborative filtering algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311488785.7A CN117423459A (en) | 2023-11-09 | 2023-11-09 | Infant physical health detection platform and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311488785.7A CN117423459A (en) | 2023-11-09 | 2023-11-09 | Infant physical health detection platform and method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117423459A true CN117423459A (en) | 2024-01-19 |
Family
ID=89530042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311488785.7A Pending CN117423459A (en) | 2023-11-09 | 2023-11-09 | Infant physical health detection platform and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117423459A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118280578A (en) * | 2024-05-31 | 2024-07-02 | 江苏盖睿健康科技有限公司 | Health consulting room information management method and system based on visual images |
| CN118315083A (en) * | 2024-02-26 | 2024-07-09 | 徐州嘉凯医疗科技有限公司 | Remote medical diagnosis system and method based on Internet of things |
-
2023
- 2023-11-09 CN CN202311488785.7A patent/CN117423459A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118315083A (en) * | 2024-02-26 | 2024-07-09 | 徐州嘉凯医疗科技有限公司 | Remote medical diagnosis system and method based on Internet of things |
| CN118280578A (en) * | 2024-05-31 | 2024-07-02 | 江苏盖睿健康科技有限公司 | Health consulting room information management method and system based on visual images |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Medical image analysis using deep learning algorithms | |
| CN117423459A (en) | Infant physical health detection platform and method based on artificial intelligence | |
| US20220005565A1 (en) | System with retroactive discrepancy flagging and methods for use therewith | |
| CN117711578B (en) | Medical image data analysis management system | |
| CN118197615B (en) | Postoperative risk prediction method and system based on big data and artificial intelligence | |
| CN116844733B (en) | Medical data integrity analysis method based on artificial intelligence | |
| CN110580951A (en) | diagnosis and monitoring comprehensive medical system with encrypted communication and encryption method thereof | |
| CN113488161A (en) | Temporomandibular joint disorder treatment regimen recommendation apparatus, device and storage medium | |
| Devi et al. | Framework for detecting the patients affected by COVID-19 at early stages using Internet of Things along with Machine Learning approaches with improved Accuracy | |
| Asuquo et al. | Febrile disease modeling and diagnosis system for optimizing medical decisions in resource-scarce settings | |
| Fatima et al. | Analyzing Breast Cancer Detection Using Machine Learning & Deep Learning Techniques | |
| Singh et al. | Smart device for effective communication in the healthcare system | |
| CN117558465A (en) | Intelligent follow-up visit system based on cloud computing and follow-up visit business operation method thereof | |
| Kwaśniewska et al. | Big data significance in remote medical diagnostics based on deep learning techniques | |
| Bhuvana et al. | AI Innovations in IoT and Machine Learning for Health Prediction Systems | |
| Sahapudeen et al. | Deep Learning Approaches for IoMT | |
| Nagarajaiah | EVALUATING THE EFFICIENCY OF MACHINE LEARNING (ML) METHODS FOR IDENTIFYING THE HEALTH OF INDIVIDUALS IN REMOTE AREAS | |
| CN116682544B (en) | Artificial intelligence medical automation test integrated system | |
| Priya et al. | Machine and Deep Learning Classifications for IoT-Enabled Healthcare Devices | |
| Rao et al. | A Multimodal Approach Utilizing the IOMT to Address both the Pandemic and its Aftermath | |
| Lakshmi et al. | IoT based Illness Prediction System using Machine Learning | |
| Samaraweera et al. | Poster: Embedded-Based Differentiated Communication for Remote ECG Monitoring with a Multi-Level Blockchain System | |
| Sharma et al. | Impact of AI, IoT and Big Data Analytics in Diseases Diagnosis and Prediction | |
| Nandan et al. | Early Detection of Dementia Disease using Machine Learning | |
| Kumar | AI & Mental Health |
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 |