CN115101202A - Health detection data management system based on big data - Google Patents
Health detection data management system based on big data Download PDFInfo
- Publication number
- CN115101202A CN115101202A CN202210659543.9A CN202210659543A CN115101202A CN 115101202 A CN115101202 A CN 115101202A CN 202210659543 A CN202210659543 A CN 202210659543A CN 115101202 A CN115101202 A CN 115101202A
- Authority
- CN
- China
- Prior art keywords
- data
- detection
- health
- detector
- value
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 186
- 230000036541 health Effects 0.000 title claims abstract description 130
- 238000013523 data management Methods 0.000 title claims abstract description 62
- 238000012549 training Methods 0.000 claims abstract description 27
- 238000012216 screening Methods 0.000 claims abstract description 24
- 238000004891 communication Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 50
- 230000010354 integration Effects 0.000 claims description 19
- 230000035790 physiological processes and functions Effects 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 11
- 238000002372 labelling Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 230000000877 morphologic effect Effects 0.000 claims description 7
- 230000014759 maintenance of location Effects 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 230000006798 recombination Effects 0.000 claims description 3
- 238000005215 recombination Methods 0.000 claims description 3
- 101000878595 Arabidopsis thaliana Squalene synthase 1 Proteins 0.000 claims description 2
- 101000713575 Homo sapiens Tubulin beta-3 chain Proteins 0.000 claims description 2
- 101000713585 Homo sapiens Tubulin beta-4A chain Proteins 0.000 claims description 2
- 102100036790 Tubulin beta-3 chain Human genes 0.000 claims description 2
- 102100036788 Tubulin beta-4A chain Human genes 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims 3
- 230000004931 aggregating effect Effects 0.000 claims 1
- 238000007726 management method Methods 0.000 abstract description 13
- 238000011161 development Methods 0.000 abstract description 8
- 239000003814 drug Substances 0.000 abstract description 7
- 238000000605 extraction Methods 0.000 abstract description 7
- 238000012544 monitoring process Methods 0.000 abstract description 7
- 201000010099 disease Diseases 0.000 description 8
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 8
- 230000033228 biological regulation Effects 0.000 description 2
- 238000010835 comparative analysis Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 210000000577 adipose tissue Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006806 disease prevention Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of health detection, and aims to solve the problems that the existing health detection data archiving management mode is relatively general, so that the data redundancy of a data management platform is overlarge, and the extraction of effective health data can be reduced by massive health detection data, so that the intention of health detection data archiving management is violated, and the development of health monitoring medicine is hindered, in particular to a health detection data management system based on big data, which comprises a health data management platform, wherein a server is arranged in the health data management platform, and is in communication connection with a data acquisition unit, a guide sorting unit, a sample screening unit, a training judgment unit, an early warning analysis unit and a display terminal; the invention simplifies the health detection data by a data deduplication mode, reduces the data redundancy of a data management platform, improves the extraction of effective health data, follows the idea of health detection data archiving management, and promotes the development of health monitoring medicine.
Description
Technical Field
The invention relates to the technical field of health detection, in particular to a health detection data management system based on big data.
Background
The health detection is physical examination, which is the detection and measurement of human morphological structure and physiological function development level, and the health detection gradually becomes an effective means for guaranteeing human health, which can change passive diagnosis into active detection, negative disease treatment into active disease prevention, and the detection data of each item obtained by the health detection in the years are filed and stored, and become the most important reference data for preventing health diseases and diagnosing diseases;
however, the existing archive management of health detection data mostly carries out general archive management on detection data of a detector year after month without carrying out any practical processing on the detection data, and the archive management mode of the health detection data has great defects, so that the problem of overlarge data redundancy is caused for a data management platform, and the extraction of effective health data is reduced by mass health detection data, so that the essence of the archive management of the health detection data is violated, the important meaning of taking the health detection data as reference data for preventing and diagnosing health diseases is lost, and the development of health monitoring medicine is hindered;
in order to solve the above-mentioned defects, a technical solution is provided.
Disclosure of Invention
The invention aims to solve the problems that the existing health detection data archiving management mode is more general, the data redundancy of a data management platform is overlarge, the extraction of effective health data is reduced by massive health detection data, the intention of health detection data archiving management is violated, the important meaning of taking the health detection data as reference data for preventing and diagnosing health diseases is lost, and the development of health monitoring medicine is hindered, the invention removes data with larger similarity in the health detection data of each detector by utilizing the modes of mean value analysis, grouping integration, item-by-item comparison and information marking integration, simplifies the health data of each detector, simplifies the data of the health data management platform to remove redundancy, reduces the data redundancy of the data management platform, the method improves the extraction of effective health data, follows the idea of health detection data archiving management, really realizes the important significance of taking the health detection data as reference data for preventing and diagnosing health diseases, greatly promotes the development of health monitoring medicine, and provides a health detection data management system based on big data.
The purpose of the invention can be realized by the following technical scheme:
a health detection data management system based on big data comprises a health data management platform, wherein a server is arranged in the health data management platform, and the server is in communication connection with a data acquisition unit, a guide sorting unit, a sample screening unit, a training judgment unit, an early warning analysis unit and a display terminal;
the health data management platform is used for carrying out integration analysis on human health detection data, acquiring basic data information and health detection data information of all testers stored in the health data management platform through the data acquisition unit, sending the basic data information to the guide sorting unit and sending the health detection data information to the sample screening unit;
the guide sorting unit is used for carrying out operation guide judgment analysis processing on the received basic data information of all testers of the health data management platform, generating a data simplification operation instruction according to the operation guide judgment analysis processing, and sending the data simplification operation instruction to the sample screening unit, the sample screening unit is used for receiving the data simplification operation instruction, calling the health detection data information of all testers in the branch tester set according to the data simplification operation instruction, carrying out primary screening integration analysis processing, and generating all simplified detection sets Ay of all testers according to the primary screening integration analysis processing i* 、By i* And Cy i* And all of them are sent to a training decision unit for each of the received reduced detection sets Ay i* 、By i* And Cy i* Performing correlation training analysis processing, generating a positive redundancy removing signal and a negative redundancy removing signal according to the correlation training analysis processing, and sending the signals to an early warning analysis unit;
the early warning analysis unit is used for carrying out early warning analysis processing on the received positive redundancy removing signals and the negative redundancy removing signals, generating high-level early warning signals and low-level early warning signals according to the early warning analysis processing, and sending the high-level early warning signals and the low-level early warning signals to the display terminal in a text word description mode to display and explain the high-level early warning signals and the low-level early warning signals.
Further, the basic data information includes the number of the detected items and the number of the detected items, and the health detection data information includes the magnitude of the morphological index, the magnitude of the physiological function, and the magnitude of the body composition.
Further, the specific operation steps of the operation-oriented judgment analysis processing are as follows:
acquiring the number of detection items and the number of detected items in the basic data information of all the detectors in the health data management platform, and marking the number of detected items as soc i Where i ═ {1, 2, 3 … … n }, and subjecting it to formula processing according to formula ptz i ＝3×soc i Obtaining the total data detection value ptz of each detector i And detecting the total value ptz of the data of each detector i Carrying out mean value analysis to obtain a platform data mean value Jptz;
taking the personnel base number as an abscissa and the total data detection value as an ordinate, establishing a rectangular coordinate system according to the coordinates, and detecting the total data detection value ptz of each detector i Drawing on a rectangular coordinate system in a point drawing mode, converting the platform data mean value ptz into a standard reference line and drawing on a two-dimensional coordinate system, namely drawing the standard reference line Y as ptz;
when the data detects the total value ptz i When the reference line Y is not less than ptz, redundant signals are generated, and when the total data detection value ptz is detected i Generating a shortage signal when the standard reference line Y is less than ptz;
and extracting each detector marked as a redundant signal and integrating and warping the detectors, so that a branch detector set i ═ {1, 2, 3 … … n }, is obtained, and i ∈ i is obtained, and the data reduction operation instruction is generated according to the branch detector set i ·.
Further, the specific operation steps of the primary screening integration analysis treatment are as follows:
s1: according to the data reduction operation instruction, the shape index detection value, the physiological function detection value and the body component detection value of each detector in the branch detector set are obtained and respectively marked as xtl i* 、sel i* And stl i* Wherein i ═ {1, 2, 3 … … n };
s2: according to step S1, a time threshold t is set j Where j ═ {1, 2, 3 … … m }, and captures the time threshold t j Shape index detection value and physiological function of each detected person within the rangeDetecting values of body composition and time threshold t j The health detection data information of each detector is normalized by a sample set, and a morphological index detection sample set A of each detector is obtained according to the normalized data information i* ＝{xtl t1 ，xtl t2 ，xtl t3 ……xtl tm And a physiological function detection sample set B of each detector i* ＝{sel t1 ，sel t2 ，sel t3 ……sel tm And a set of body composition measurement samples C of each subject i* ＝{stl t1 ，stl t2 ，stl t3 ……stl tm }；
S3: according to step S2, each detection sample set A for each detector i* 、B i* And C i* Respectively carrying out similar de-emphasis analysis processing to generate each simplified detection set Ay of each detector i* 、By i* And Cy i* 。
Further, the specific operation steps of the similar de-duplication analysis processing are as follows:
SS 1: obtaining each detection sample set A of each detector i* 、B i* And C i* And performing mean value analysis on each detection sample set of each detector, and calculating the first sample mean value coefficient Jxtl of each detector i* The second sample mean coefficient Jsel i* And a third sample mean coefficient Jstl i* ；
SS 2: grouping m detection elements in each detection sample set of each detector according to a group of 10 elements, dividing the m detection elements into k groups, wherein k is a positive integer greater than or equal to 1, and is a multiple of 10, and k is m ÷ 10, and performing item-by-item comparison analysis processing on the k grouped detection elements to generate a deduplication instruction and a retention instruction;
SS 3: according to the generated deduplication instruction and the reservation instruction, respectively carrying out signal labeling on each group, labeling the group generating the deduplication instruction as a minus sign, and labeling the group generating the reservation instruction as a plus sign;
SS 4: according to the symbol calibration type, the packet with the symbol of "" is detected from each detectionEliminating in each detection sample set of testee, retaining all grouped data whose grouped symbol is + so as to produce various detection sample sets Ad in grouped form i* 、Bd i* 、Cd i* ；
SS 5: according to the steps SS2-SS3, the grouped detection sample sets of each detector are grouped and sorted again, so that the simplified detection set Ay of each detector can be obtained i* 、By i* And Cy i* 。
Further, the specific operation steps of item-by-item comparison analysis processing are as follows:
obtaining a first sample mean value coefficient Jxtl of each detector i* The second sample mean coefficient Jsel i* And a third sample mean coefficient Jstl i* And regularizing the mean values to obtain an integrated mean coefficient Jun i*p Wherein, p ═ {1, 2, 3 };
randomly capturing any 5 detection elements in each of k groups, and respectively combining the detection elements with the integrated mean coefficient Jun i*p Performing difference analysis, and accordingly obtaining a sample de-weighting coefficient qcxop, o ∈ {1, 2 … … 5}, and o ∈ j of each detection sample of each detector;
setting a deduplication reference value Ca p And is multiplied by a sample de-weight coefficient qcx op Performing comparative analysis, if the sample weight removal coefficient is satisfied qcx op Not less than the de-emphasis reference value Ca p Then a dissimilar signal is generated and if the sample de-emphasis factor qcx is satisfied op < Deduplicated reference value Ca p Generating a similar signal;
and performing summation analysis on the number of the types of the generated signals, generating a deduplication instruction if the sum of the number of the generated similar signals is more than or equal to 3, and generating a retention instruction if the sum of the number of the generated similar signals is less than 3.
Further, the specific operation steps of the association training analysis processing are as follows:
obtaining each simplified detection set Ay of each detector of recombination i* 、By i* And Cy i* Retrieving the number soc of each examiner i The examined gradient reference thresholds Yu1, Yu2 and Yu3 are set, and the examined number of each examiner is countedsoc i Substituting into the reference threshold of the detected gradient to perform comparison analysis, and if the detected number soc i Within the examined gradient reference threshold value Yu1 or the examined number soc i When the detected gradient reference threshold value Yu2 is reached, redundant training signals are generated, and if the detected number soc is within the reference threshold value Yu2 i In the detected gradient reference threshold Yu3, an unnecessary training signal is generated;
retrieving simplified detection sets Ay of detectors labeled as redundant training signals i* 、By i* And Cy i* Acquiring the number of elements in each detection set, and summing and analyzing the number of elements to obtain the total simplified data ptz of each detector i* ；
Calling a platform data mean value Jptz and simplifying a data total value ptz of each detector i* Performing comparative analysis, and if the total value ptz of the simplified data is met i* When the average value Jptz of the platform data is more than or equal to the average value Jptz of the platform data, a negative redundancy removing signal is generated, and if the total value ptz of the simplified data is met i* If the average value Jptz of the platform data is less than the average value Jptz, a positive redundancy removing signal is generated.
Further, the specific operation steps of the early warning analysis processing are as follows:
when a positive redundancy removal signal is received, generating a high-grade early warning signal, and sending a text word to a display terminal for displaying, wherein the text word is used for carrying out data simplification operation on a health data management platform in need of manual intervention;
and when the negative redundancy removing signal is received, generating a low-level early warning signal, and sending a text word pattern of 'no need of carrying out data simplification operation on the health data management platform' to the display terminal for displaying.
Compared with the prior art, the invention has the beneficial effects that:
the health data storage of all testers in the platform is preliminarily judged through symbolic calibration, formulaic processing, coordinate model analysis and set regulation, all testers needing data simplification are obtained, and accurate calibration is carried out on the health detection data of all testers in the branch set through setting of a threshold value, construction of a sample set and a sample set regulation mode, so that a foundation is laid for redundancy removal of data redundancy of a health data management platform;
by means of mean value analysis, grouping integration, item-by-item comparison and letter labeling integration, data with high similarity in health detection data of each detector is removed, the health data of each detector is simplified, meanwhile, the data simplification and redundancy removal operation of a health data management platform is achieved, the data redundancy of the data management platform is reduced, the extraction of effective health data is improved, the intention of health detection data archiving management is followed, the important significance of enabling the health detection data to serve as reference data for preventing and diagnosing health diseases is truly achieved, and the development of health monitoring medicine is greatly promoted.
Drawings
In order to facilitate understanding for those skilled in the art, the present invention will be further described with reference to the accompanying drawings;
FIG. 1 is a general block diagram of the system of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be apparent that the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The first embodiment is as follows:
as shown in fig. 1, a health detection data management system based on big data comprises a health data management platform, a server is arranged in the health data management platform, and the server is in communication connection with a data acquisition unit, a guide sorting unit, a sample screening unit, a training determination unit, an early warning analysis unit and a display terminal;
the health data management platform is used for carrying out integration analysis on human health detection data, acquiring basic data information and health detection data information of all testers stored in the health data management platform through the data acquisition unit, sending the basic data information to the guide sorting unit and sending the health detection data information to the sample screening unit;
the basic data information is used for representing basic condition information of detection data of each detector in the health data management platform, the basic data information comprises detection item numbers and detected numbers, wherein the detection item numbers comprise form index detection items, physiological function detection items and body composition detection items, and the detected numbers are used for representing the number of detection data generated by each detection item of the detector;
the health detection data information is used for representing detection type data information of the body health state of a detector, and the health detection data information comprises a form index quantity value, a physiological function quantity value and a body component quantity value, wherein the form index quantity value refers to the data quantity value of the weight of the detector accounting for the percentage of the height, the physiological function quantity value refers to the comprehensive data quantity value of the sensory expression state and the vital capacity expression state of the detector, and the body component quantity value refers to the data quantity value of the skin fold thickness of the detector accounting for the percentage of the body fat;
the guide sorting unit is used for carrying out operation guide judgment analysis processing on the received basic data information of all testers of the health data management platform, generating a data simplification operation instruction according to the operation guide judgment analysis processing, and sending the data simplification operation instruction to the sample screening unit, the sample screening unit is used for receiving the data simplification operation instruction, calling the health detection data information of all testers in the branch tester set according to the data simplification operation instruction, carrying out primary screening integration analysis processing, and generating all simplified detection sets Ay of all testers according to the primary screening integration analysis processing i* 、By i* And Cy i* And all of them are sent to a training decision unit for each of the received reduced detection sets Ay i* 、By i* And Cy i* Performing correlation training analysis processing, generating a positive redundancy removing signal and a negative redundancy removing signal according to the correlation training analysis processing, and sending the signals to an early warning analysis unit;
the early warning analysis unit is used for carrying out early warning analysis processing on the received positive redundancy removing signals and the negative redundancy removing signals, generating high-level early warning signals and low-level early warning signals according to the early warning analysis processing, and sending the high-level early warning signals and the low-level early warning signals to the display terminal in a text word description mode to display and explain the high-level early warning signals and the low-level early warning signals.
Example two:
as shown in fig. 1, when the guidance sorting unit receives basic data information of all examiners of the health data management platform, and performs operation guidance determination analysis processing according to the basic data information, the specific operation process is as follows:
acquiring the number of detection items and the number of detected items in the basic data information of all the detectors in the health data management platform, and marking the number of detected items as soc i Wherein i is a positive integer greater than or equal to 1, and i ═ 1, 2, 3 … … n }, and is subjected to formula processing according to formula ptz i ＝3×soc i Obtaining the total data detection value ptz of each detector i And detecting the total value ptz of the data of each detector i The mean value analysis was performed according to the formula Jptz ═ ptz (ptz) 1 ＋ptz 2 ＋……＋ptz n ) N, solving a platform data mean value Jptz;
in addition, i represents each detector, and formula ptz i ＝3×soc i 3 in (2) is used for representing three items of a morphological index detection item, a physiological function detection item and a body composition detection item in the number of detection items;
taking the personnel base number as an abscissa and the total data detection value as an ordinate, establishing a rectangular coordinate system according to the coordinates, and detecting the total data detection value ptz of each detector i Drawing on a rectangular coordinate system in a point drawing mode, converting the platform data mean value ptz into a standard reference line, and drawing on a two-dimensional coordinate system, namely drawing the standard reference line Y (ptz);
when the data detects the total value ptz i When the reference line Y is not less than ptz, redundant signals are generated, and when the total data detection value ptz is detected i Generating a shortage signal when the standard reference line Y is less than ptz;
extracting each detector marked as a redundant signal, integrating and warping the detectors, so as to obtain a branch detector set i ═ {1, 2, 3 … … n }, wherein i ×, is a positive integer greater than or equal to 1, and i ∈ i, generating a data simplification operation instruction according to the branch detector set i, and sending the generated data simplification operation instruction to a sample screening unit;
in addition, i denotes each detector in the branch detector set;
when the sample screening unit receives the data simplification operation instruction, the health detection data information of each detector in the branch detector set is called according to the data simplification operation instruction, and primary screening, integration and analysis processing is performed according to the health detection data information, wherein the specific operation process is as follows:
according to the data reduction operation instruction, the form index detection value, the physiological function detection value and the body composition detection value in the health detection data information of each detector in the branch detector set are obtained and respectively marked as xtl i* 、sel i* And stl i* ；
Setting a time threshold t j Wherein j is a positive integer equal to or greater than 1, and {1, 2, 3 … … m }, and capturing a time threshold t j The shape index detection value, physiological function detection value and body component detection value of each detected person in the range are determined according to the time threshold t j The health detection data information of each detector is normalized by a sample set, and a morphological index detection sample set A of each detector is obtained according to the normalized data information i* ＝{xtl t1 ，xtl t2 ，xtl t3 ……xtl tm And a physiological function detection sample set B of each detector i* ＝{sel t1 ，sel t2 ，sel t3 ……sel tm And (5) a body composition detection sample set C of each detector i* ＝{stl t1 ，stl t2 ，stl t3 ……stl tm }；
In addition, j represents each time point of the time threshold;
respectively carrying out similar deduplication analysis processing on each detection sample set of each detector, wherein the specific operation process is as follows:
obtaining each detection sample set A of each detector i* 、B i* And C i* And performing mean value analysis on each detection sample set of each detector according to a formula Jxtl i* ＝（xtl t1 ＋xtl t2 ＋xtl tm ）÷m，Jsel i* ＝（sel t1 ＋sel t2 ＋sel tm ）÷m，Jstl i* ＝（stl t1 ＋stl t2 ＋stl tm ) Dividing m, and finding out the first sample average coefficient Jxtl of each detector i* The second sample mean coefficient Jsel i* And a third sample mean coefficient Jstl i* ；
Grouping m detection elements in each detection sample set of each detector according to a group of 10 elements, and dividing the m detection elements into k groups, wherein k is a positive integer greater than or equal to 1, and is a multiple of 10, and k is m/10;
it should be noted that each grouped detection sample set can be represented as follows: morphology index detection sample set A i* ＝{W i1 ，W i2 ……W ik And W is i1 ＝{xtl t1 ，xtl t2 ……xtl t10 }，W i2 ＝{xtl t11 ，xtl t12 ……xtl t20 And a physiological function detection sample set B i* ＝{V i1 ，V i2 ，V i3 ……V ik }，V i1 ＝{sel t1 ，sel t2 ……sel t10 }，V i2 ＝{sel t11 ，sel t12 ……sel t20 A body composition detection sample set C i* ＝{Z i1 ，Z i2 ，Z i3 ……Z ik }，Z i1 ＝{stl t1 ，stl t2 ……stl t10 }，Z i2 ＝{stl t11 ，stl t12 ……stl t20 }；
Performing item-by-item comparison analysis processing on the k grouped detection elements, wherein the specific operation process is as follows:
obtaining a first sample mean value coefficient Jxtl of each detector i* The second sample mean coefficient Jsel i* And a third sample mean coefficient Jstl i* And regularizing the mean values to obtain an integrated mean coefficient Jun i*p Where p is {1, 2, 3}, it should be noted that Jun is given when p is 1 i*1 ＝Jxtl i* When p is 2, Jun i*2 ＝Jsel i* When p is 3, Juni 3 Jstl i* ；
Randomly capturing any 5 detection elements in each of k groups, and respectively combining the detection elements with the integrated mean coefficient Jun i*p Performing difference analysis according to formula qcx op Jun | Jun i*p －D i*op Obtaining a sample de-weighting factor qcx for each sample of each detector op Where o ═ {1, 2 … … 5}, and o ∈ j;
when p is 1, D is i*o1 ＝xtl i*o (ii) a When p is 2, D i*o2 ＝sel i*o (ii) a When p is 3, D i*o2 ＝stl i*o Wherein, when o is 1, it indicates that the first arbitrary element of the 5 detection elements is arbitrarily captured in each group, when o is 2, it indicates that the second arbitrary element of the 5 detection elements is arbitrarily captured in each group, and so on, and when o is 5, it indicates that the fifth arbitrary element of the 5 detection elements is arbitrarily captured in each group;
setting a deduplication reference value Ca p And is summed with the sample de-weighting factor qcx op Performing comparison analysis, if the weight removal coefficient of the sample is satisfied qcx op Not less than the de-emphasis reference value Ca p Then a dissimilar signal is generated if the sample de-emphasis factor qcx is satisfied op < Deduplicated reference value Ca p If so, generating a similar signal;
performing summation analysis on the number of the types of the generated signals, if the sum of the number of the generated similar signals is more than or equal to 3, generating a duplicate removal instruction, and if the sum of the number of the generated similar signals is less than 3, generating a retention instruction;
according to the generated deduplication instruction and the reservation instruction, respectively carrying out signal labeling on each group, labeling the group generating the deduplication instruction as a "-" symbol, and labeling the group generating the reservation instruction as a "+" symbol;
and the grouping with the grouping symbol of negative is removed from each detection sample set of each detector, and each grouping data with the grouping symbol of positive is reserved, so as to generate each detection sample set Ad with the grouping form i* ＝{W i1 ，W i2 ……W ik1* }，Bd i* ＝{V i1 ，V i2 ，V i3 ……V ik2* }，Cd i* ＝{Z i1 ，Z i2 ，Z i3 ……Z ik3* K1, k2 and k3 are positive integers greater than or equal to 1, respectively, and k1 belongs to k, k2 belongs to k, k3 belongs to k;
the grouped detection sample sets of each detector are grouped and sorted again, so that the simplified detection set Ay of each detector can be obtained i* 、By i* And Cy i* Wherein Ay i* ＝{xtl t1 ，xtl t2 ，xtl t3 ……xtl tm1* }，By i* ＝{sel t1 ，sel t2 ，sel t3 ……sel tm2* }，Cy i* ＝{stl t1 ，stl t2 ，stl t3 ……stl tm3* J1 ═ {1, 2, 3 … … m1 }, j2 ═ 1, 2, 3 … … m2 }, j3 ═ 1, 2, 3 … … m 3}, j1 ∈ j, j2 ∈ j, j3 ∈ j, wherein j1 ∈, j2 ∈ and j3 are positive integers greater than or equal to 1;
it should be noted that grouping sorting is used to indicate that groups which originally use 10 elements as a group are removed, and sorting is performed again by the minimum element unit according to the time sequence;
it should be noted that the "-", "+" symbols are not mathematical symbols in the mathematical sense, but are merely notations provided for each group for the convenience of computer operations;
and generating simplified detection sets Ay of the detectors i* 、By i* And Cy i* All are sent to a training judgment unit;
when the training judgment unit receives each simplified detection set Ay i* 、By i* And Cy i* And then, performing correlation training analysis processing according to the data, wherein the specific operation process is as follows:
obtaining each simplified detection set Ay of each detector of recombination i* 、By i* And Cy i* Retrieving the number soc of each examiner i The examined gradient reference thresholds Yu1, Yu2 and Yu3 are set, and the examined number soc of each examiner is determined i Substituting the reference threshold value of the detected gradientPerforming comparison analysis internally, if the number soc is detected i Within the examined gradient reference threshold Yu1 or the examined number soc i When the detected gradient reference threshold value Yu2 is reached, redundant training signals are generated, and if the detected number soc is within the reference threshold value Yu2 i In the detected gradient reference threshold Yu3, an unnecessary training signal is generated;
it should be noted that the threshold size relationship among the detected gradient reference thresholds Yu1, Yu2, and Yu3 is Yu1 < Yu2 < Yu3, for example, if Yu1= [10, 20], Yu2= [20, 30], Yu3= [30, 40], and it should be noted that the specific value size of the detected gradient reference threshold is specifically set by a person skilled in the art according to the data condition of the specific health data management platform, and therefore, the detailed description is omitted;
retrieving simplified detection sets Ay of detectors labeled as redundant training signals i* 、By i* And Cy i* Acquiring the number of elements in each detection set, summing and analyzing the elements, and carrying out ptz analysis according to a formula i* (m 1 + m2 + m 3/3) to obtain the total value ptz of simplified data for each detector i* ；
Calling a platform data mean value Jptz and simplifying a data total value ptz of each detector i* Performing comparison analysis, if the total value ptz of the simplified data is satisfied i* When the average value Jptz of the platform data is more than or equal to the average value Jptz of the platform data, a negative redundancy removing signal is generated, and if the total value ptz of the simplified data is met i* If the platform data mean value Jptz is less than the platform data mean value Jptz, generating a positive redundancy removing signal, and sending the generated positive redundancy removing signal and the generated negative redundancy removing signal to an early warning analysis unit;
when the early warning analysis unit receives the positive redundancy removal signal and the negative redundancy removal signal, early warning analysis processing is carried out according to the positive redundancy removal signal and the negative redundancy removal signal, and the specific processing process is as follows:
when a positive redundancy removal signal is received, generating a high-grade early warning signal, and sending a text word to a display terminal for displaying, wherein the text word is used for carrying out data simplification operation on a health data management platform in need of manual intervention;
and when the negative redundancy removing signal is received, generating a low-level early warning signal, and sending a text word pattern of 'no need of carrying out data simplification operation on the health data management platform' to the display terminal for displaying.
The above formulas are obtained by collecting a large amount of data and performing software simulation, and the coefficients in the formulas are set by those skilled in the art according to actual conditions.
When the health data management platform is used, basic data information of all testers in the health data management platform is collected and subjected to guide judgment analysis processing, platform data conditions of all testers are subjected to preliminary guide judgment analysis through symbolic calibration, formulaic processing, coordinate model analysis and a set-normalization mode, and all testers needing data simplification are obtained, so that the data redundancy degree of all testers in the health data management platform is clearly analyzed, and a foundation is laid for integration of data redundancy removal of the health data management platform;
based on the guide judgment analysis processing, collecting health detection data information of each detector in the branch detector set, and respectively carrying out accurate calibration output on the health detection data of each detector in the branch set by setting a threshold value, constructing a sample set and arranging the sample set, thereby laying a foundation for redundancy removal of data redundancy of a health data management platform;
by means of mean analysis, grouping integration, item-by-item comparison and marking of integration credits, the health detection data information of each detector in a branch detector set in the health data management platform is subjected to de-duplication analysis, data with large similarity in the health detection data of each detector are removed, and data with large difference are reserved, so that the space of the health data management platform is expanded, and archive management of the health detection data is promoted;
the health data of each detector is simplified in a data duplication removing mode, and then the data simplification redundancy removing operation of the health data management platform is realized, so that the data redundancy of the data management platform is reduced, the extraction of effective health data is improved, the idea of health detection data archiving management is followed, the important significance of taking the health detection data as reference data for preventing and diagnosing health diseases is really realized, and the development of health monitoring medicine is greatly promoted.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not exhaustive and do not limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (8)
1. A health detection data management system based on big data comprises a health data management platform and is characterized in that a server is arranged inside the health data management platform, and the server is in communication connection with a data acquisition unit, a guide sorting unit, a sample screening unit, a training judgment unit, an early warning analysis unit and a display terminal;
the health data management platform is used for carrying out integration analysis on human health detection data, acquiring basic data information and health detection data information of all testers stored in the health data management platform through the data acquisition unit, sending the basic data information to the guide sorting unit, and sending the health detection data information to the sample screening unit;
the guide sorting unit is used for carrying out operation guide judgment analysis processing on the received basic data information of all testers of the health data management platform, generating a data simplification operation instruction according to the operation guide judgment analysis processing, and sending the data simplification operation instruction to the sample screening unit, the sample screening unit is used for receiving the data simplification operation instruction, calling the health detection data information of each tester in the branch tester set according to the data simplification operation instruction, carrying out primary screening integration analysis processing, and generating each simplified detection set Ay of each tester according to the primary screening integration analysis processing i* 、By i* And Cy i* And all of them are sent to a training decision unit for aggregating the received simplified detectionsPerforming line correlation training analysis processing, generating a positive redundancy removing signal and a negative redundancy removing signal according to the line correlation training analysis processing, and sending the signals to an early warning analysis unit;
the early warning analysis unit is used for carrying out early warning analysis processing on the received positive redundancy removing signal and the negative redundancy removing signal, generating a high-level early warning signal and a low-level early warning signal according to the early warning analysis processing, and sending the high-level early warning signal and the low-level early warning signal to the display terminal in a text word description mode for displaying and explaining.
2. The big-data based health-check data management system of claim 1, wherein the basic data information includes the number of items to be checked and the number of subjects to be checked, and the health check data information includes the values of morphological index, physiological function and body composition.
3. The big-data based health-testing data management system of claim 1, wherein the specific operation steps of the operation-oriented decision analysis process are as follows:
acquiring the number of detected items and the number of detected items of all the detectors in the health data management platform, and marking the number of detected items as soc i Where i ═ 1, 2, 3 … … n, and subjecting it to formula processing according to the formula ptz i ＝3×soc i Obtaining the total data detection value ptz of each detector i And detecting the total value ptz of the data of each detector i Carrying out mean value analysis to obtain a platform data mean value Jptz;
taking the personnel base number as an abscissa and the total data detection value as an ordinate, establishing a rectangular coordinate system according to the coordinates, and detecting the total data detection value ptz of each detector i Drawing on a rectangular coordinate system in a point drawing mode, converting the platform data mean value ptz into a standard reference line and drawing on a two-dimensional coordinate system, namely drawing the standard reference line Y as ptz;
when the data detects the total value ptz i When the reference line Y is not less than ptz, redundant signals are generated, and when the total data detection value ptz is detected i When the standard reference line Y is less than ptz, generating a shortage signal;
extracting each detector marked as a redundant signal and integrating and warping the detectors, so as to obtain a branch detector set i ═ {1, 2, 3 … … n }, wherein i ∈ i belongs to the branch detector set i, and generating a data simplification operation command according to the branch detector set i.
4. The big-data-based health-testing data management system of claim 1, wherein the specific operation steps of the primary screening integration analysis process are as follows:
s1: according to the data reduction operation instruction, the shape index detection value, the physiological function detection value and the body component detection value of each detector in the branch detector set are obtained and respectively marked as xtl i* 、sel i* And stl i* Wherein i ═ {1, 2, 3 … … n };
s2: according to step S1, a time threshold t is set j Where j ═ {1, 2, 3 … … m }, and captures the time threshold t j The shape index detection value, physiological function detection value and body component detection value of each detector in the range are determined according to the time threshold t j The health detection data information of each detector is normalized by a sample set, and a morphological index detection sample set A of each detector is obtained according to the normalized data information i* ＝{xtl t1 ，xtl t2 ，xtl t3 ……xtl tm And a physiological function detection sample set B of each detector i* ＝{sel t1 ，sel t2 ，sel t3 ……sel tm And a set of body composition measurement samples C of each subject i* ＝{stl t1 ，stl t2 ，stl t3 ……stl tm }；
S3: according to step S2, each detection sample set A for each detector i* 、B i* And C i* Respectively carrying out similar de-emphasis analysis processing to generate each simplified detection set Ay of each detector i* 、By i* And Cy i* 。
5. The big-data based health-detection data management system of claim 4, wherein the detailed operation steps of the similar deduplication analysis process are as follows:
SS 1: obtaining each detection sample set A of each detector i* 、B i* And C i* And performing mean value analysis on each detection sample set of each detector, and calculating the first sample mean value coefficient Jxtl of each detector i* The second sample mean coefficient Jsel i* And a third sample mean coefficient Jstl i* ；
SS 2: grouping m detection elements in each detection sample set of each detector according to a group of 10 elements, dividing the m detection elements into k groups, wherein k is a positive integer greater than or equal to 1, and is a multiple of 10, and k is m ÷ 10, and performing item-by-item comparison analysis processing on the k grouped detection elements to generate a deduplication instruction and a retention instruction;
SS 3: according to the generated deduplication instruction and the reservation instruction, respectively carrying out signal labeling on each group, labeling the group generating the deduplication instruction as a "-" symbol, and labeling the group generating the reservation instruction as a "+" symbol;
SS 4: according to the symbol calibration type, the packet with the packet symbol of "-" is removed from each detection sample set of each detector, and each packet data with the packet symbol of "+" is reserved, so that each detection sample set Ad with the packet form is generated according to the packet data i* 、Bd i* 、Cd i* ；
SS 5: according to the steps SS2-SS3, the grouped detection sample sets of each detector are grouped and sorted again, so that the simplified detection set Ay of each detector can be obtained i* 、By i* And Cy i* 。
6. The big-data-based health-detection data management system according to claim 5, wherein the specific operation steps of the item-by-item comparison analysis processing are as follows:
obtaining a first sample mean value coefficient Jxtl of each detector i* The second sample mean coefficient Jsel i* And a third sample mean coefficient Jstl i* And regularizing them so that they are integratedValue coefficient Jun i*p Wherein, p ═ {1, 2, 3 };
randomly capturing any 5 detection elements in each of k groups, and respectively combining the detection elements with the integrated mean coefficient Jun i*p The difference analysis is performed to determine qcx the sample weight removal coefficient of each test sample of each tester op O ═ {1, 2 … … 5}, and o ∈ j;
setting a deduplication reference value Ca p And is summed with the sample de-weighting factor qcx op Performing comparison analysis, if the weight removal coefficient of the sample is satisfied qcx op Not less than the de-emphasis reference value Ca p Then a dissimilar signal is generated if the sample de-emphasis factor qcx is satisfied op < Deduplicated reference value Ca p Generating a similar signal;
and performing summation analysis on the number of the types of the generated signals, generating a deduplication instruction if the sum of the number of the generated similar signals is more than or equal to 3, and generating a retention instruction if the sum of the number of the generated similar signals is less than 3.
7. The big-data-based health-detection data management system according to claim 6, wherein the specific operation steps of the association training analysis process are as follows:
obtaining each simplified detection set Ay of each detector of the recombination i* 、By i* And Cy i* Retrieving the number soc of each examiner i The detected gradient reference thresholds Yu1, Yu2 and Yu3 are set, and the detected number soc of each detector is determined i Substituting into the reference threshold of the detected gradient for comparison and analysis, and if the detected number soc i Within the examined gradient reference threshold value Yu1 or the examined number soc i When the detected gradient reference threshold value Yu2 is reached, redundant training signals are generated, and if the detected number soc is within the reference threshold value Yu2 i In the detected gradient reference threshold Yu3, an unnecessary training signal is generated;
retrieving simplified detection sets Ay of detectors labeled as redundant training signals i* 、By i* And Cy i* Acquiring the number of elements in each detection set, and summing and analyzing the number of elements to obtain the simplified data sum of each detectorValue ptz i* ；
Calling a platform data mean value Jptz and simplifying a data total value ptz of each detector i* Performing comparison analysis, if the total value ptz of the simplified data is satisfied i* When the average value Jptz of the platform data is more than or equal to Jptz, generating a negative redundancy removal signal, and if the total value ptz of the simplified data is met i* If the average value Jptz of the platform data is less than the average value Jptz, a positive redundancy removing signal is generated.
8. The big-data-based health detection data management system according to claim 1, wherein the early warning analysis processing comprises the following specific operation steps:
when a positive redundancy removal signal is received, generating a high-grade early warning signal, and sending a text word to a display terminal for displaying, wherein the text word is used for carrying out data simplification operation on a health data management platform in need of manual intervention;
and when the negative redundancy removing signal is received, generating a low-level early warning signal, and sending a text word pattern of 'no need of carrying out data simplification operation on the health data management platform' to the display terminal for displaying.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210659543.9A CN115101202A (en) | 2022-06-13 | 2022-06-13 | Health detection data management system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210659543.9A CN115101202A (en) | 2022-06-13 | 2022-06-13 | Health detection data management system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115101202A true CN115101202A (en) | 2022-09-23 |
Family
ID=83291248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210659543.9A Pending CN115101202A (en) | 2022-06-13 | 2022-06-13 | Health detection data management system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115101202A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117954036A (en) * | 2024-03-26 | 2024-04-30 | 青岛益生康健科技股份有限公司 | Health management method and system based on big data |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040103001A1 (en) * | 2002-11-26 | 2004-05-27 | Mazar Scott Thomas | System and method for automatic diagnosis of patient health |
| CN111370124A (en) * | 2020-03-05 | 2020-07-03 | 湖南城市学院 | Health analysis system and method based on facial recognition and big data |
| CN111973194A (en) * | 2020-08-28 | 2020-11-24 | 郑金燕 | Wearable terminal equipment health detection system based on big data |
| CN112002424A (en) * | 2020-09-01 | 2020-11-27 | 张婉婷 | Intelligent analysis management system for intelligent community endowment health based on big data |
| CN112927782A (en) * | 2021-03-29 | 2021-06-08 | 山东思正信息科技有限公司 | Mental and physical health state early warning system based on text emotion analysis |
| JP2021525411A (en) * | 2018-05-30 | 2021-09-24 | インターナショナル・ビジネス・マシーンズ・コーポレーションＩｎｔｅｒｎａｔｉｏｎａｌ Ｂｕｓｉｎｅｓｓ Ｍａｃｈｉｎｅｓ Ｃｏｒｐｏｒａｔｉｏｎ | Personalized device recommendations for proactive health monitoring and management |
| CN113990477A (en) * | 2021-10-20 | 2022-01-28 | 上海轻迅信息科技有限公司 | Big data intelligent health monitoring system based on cloud platform |
| CN114500615A (en) * | 2022-04-18 | 2022-05-13 | 深圳日晨物联科技有限公司 | Intelligent terminal based on thing allies oneself with sensing technology |
| CN114613128A (en) * | 2022-02-11 | 2022-06-10 | 河南中医药大学 | Subway epidemic prevention monitoring management system based on data analysis |
-
2022
- 2022-06-13 CN CN202210659543.9A patent/CN115101202A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040103001A1 (en) * | 2002-11-26 | 2004-05-27 | Mazar Scott Thomas | System and method for automatic diagnosis of patient health |
| JP2021525411A (en) * | 2018-05-30 | 2021-09-24 | インターナショナル・ビジネス・マシーンズ・コーポレーションＩｎｔｅｒｎａｔｉｏｎａｌ Ｂｕｓｉｎｅｓｓ Ｍａｃｈｉｎｅｓ Ｃｏｒｐｏｒａｔｉｏｎ | Personalized device recommendations for proactive health monitoring and management |
| CN111370124A (en) * | 2020-03-05 | 2020-07-03 | 湖南城市学院 | Health analysis system and method based on facial recognition and big data |
| CN111973194A (en) * | 2020-08-28 | 2020-11-24 | 郑金燕 | Wearable terminal equipment health detection system based on big data |
| CN112002424A (en) * | 2020-09-01 | 2020-11-27 | 张婉婷 | Intelligent analysis management system for intelligent community endowment health based on big data |
| CN112927782A (en) * | 2021-03-29 | 2021-06-08 | 山东思正信息科技有限公司 | Mental and physical health state early warning system based on text emotion analysis |
| CN113990477A (en) * | 2021-10-20 | 2022-01-28 | 上海轻迅信息科技有限公司 | Big data intelligent health monitoring system based on cloud platform |
| CN114613128A (en) * | 2022-02-11 | 2022-06-10 | 河南中医药大学 | Subway epidemic prevention monitoring management system based on data analysis |
| CN114500615A (en) * | 2022-04-18 | 2022-05-13 | 深圳日晨物联科技有限公司 | Intelligent terminal based on thing allies oneself with sensing technology |
Non-Patent Citations (3)
| Title |
|---|
| 李伟;王士泉;于楠;张麟;周丁华;: "区域健康医疗大数据平台解决方案策划与初步设计", 医疗卫生装备, no. 07, 15 July 2018 (2018-07-15) * |
| 渠林楠;韩雷;江艳;王淑霞;: "公立医院"互联网+健康管理"系统建设实践分析", 新疆医学, no. 07, 25 July 2020 (2020-07-25) * |
| 祁静;茅倬彦;: "健康干预对农村中老年人健康知识、态度和行为的影响", 人口学刊, no. 02, 1 March 2018 (2018-03-01) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117954036A (en) * | 2024-03-26 | 2024-04-30 | 青岛益生康健科技股份有限公司 | Health management method and system based on big data |
| CN117954036B (en) * | 2024-03-26 | 2024-06-07 | 青岛益生康健科技股份有限公司 | Health management method and system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106056595B (en) | Based on the pernicious assistant diagnosis system of depth convolutional neural networks automatic identification Benign Thyroid Nodules | |
| CN110731773B (en) | Abnormal electrocardiogram screening method based on fusion of global and local depth features of electrocardiogram | |
| CN109009102B (en) | Electroencephalogram deep learning-based auxiliary diagnosis method and system | |
| CN103646183A (en) | Intelligent alzheimer disease discriminant analysis method based on artificial neural network and multi-modal MRI (Magnetic Resonance Imaging) | |
| CN108710822A (en) | Personnel falling detection system based on infrared array sensor | |
| WO2021075826A1 (en) | Method for diagnosing disease by preprocessing biologically-extracted data and device therefor | |
| CN104462744A (en) | Data quality control method suitable for cardiovascular remote monitoring system | |
| CN115101202A (en) | Health detection data management system based on big data | |
| CN109087702B (en) | Four-diagnosis representation information fusion method for traditional Chinese medicine health state analysis | |
| Radha | Analysis of COVID-19 and pneumonia detection in chest X-ray images using deep learning | |
| CN105611872A (en) | An apparatus and method for evaluating multichannel ECG signals | |
| CN113823414B (en) | Main diagnosis and main operation matching detection method, device, computing equipment and storage medium | |
| CN110070013B (en) | Intelligent evaluation method for noise pollution degree and category of ECG signal | |
| CN109907751B (en) | Laboratory chest pain data inspection auxiliary identification method based on artificial intelligence supervised learning | |
| Taher et al. | Identification of lung cancer based on shape and color | |
| CN111081374A (en) | Autism auxiliary diagnosis device based on common attention paradigm | |
| CN115083616A (en) | Chronic nephropathy subtype mining system based on self-supervision graph clustering | |
| CN111028906A (en) | Method for rapidly detecting positive charge amount of tissue cells | |
| CN112382413A (en) | Method for detecting adverse reaction of combined medication | |
| CN113171105A (en) | Myocardial ischemia identification and classification method based on integrated CNN | |
| Kalita et al. | Detection of COVID-19 using a deep neural network with transfer learning approach | |
| Anuradha | Human blood type classification by ROI based pixel segmentation and neural network | |
| CN114595731B (en) | Semantic segmentation method of nonlinear medical sensor data based on continuous learning | |
| Agrawal et al. | Automated COVID-19 detection using Deep Convolutional Neural Network and Chest X-ray Images | |
| CN116259408A (en) | Physical testing data acquisition and detection system and method |
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 |