CN112365107B - Myopia risk assessment method, device and system based on artificial intelligence - Google Patents
Myopia risk assessment method, device and system based on artificial intelligence Download PDFInfo
- Publication number
- CN112365107B CN112365107B CN202011482956.1A CN202011482956A CN112365107B CN 112365107 B CN112365107 B CN 112365107B CN 202011482956 A CN202011482956 A CN 202011482956A CN 112365107 B CN112365107 B CN 112365107B
- Authority
- CN
- China
- Prior art keywords
- data
- myopia
- myopia risk
- index
- target object
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000004379 myopia Effects 0.000 title claims abstract description 150
- 208000001491 myopia Diseases 0.000 title claims abstract description 150
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000012502 risk assessment Methods 0.000 title claims abstract description 57
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 41
- 238000011156 evaluation Methods 0.000 claims abstract description 58
- 238000004364 calculation method Methods 0.000 claims abstract description 44
- 238000004140 cleaning Methods 0.000 claims abstract description 20
- 230000009471 action Effects 0.000 claims abstract description 10
- 210000003128 head Anatomy 0.000 claims description 21
- 230000015654 memory Effects 0.000 claims description 19
- 230000006399 behavior Effects 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 17
- 238000012937 correction Methods 0.000 claims description 11
- 230000003542 behavioural effect Effects 0.000 claims description 10
- 230000004397 blinking Effects 0.000 claims description 8
- 238000013210 evaluation model Methods 0.000 claims description 6
- 210000004709 eyebrow Anatomy 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000013500 data storage Methods 0.000 claims description 3
- 238000004898 kneading Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 206010041250 Social phobia Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000004630 mental health Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 201000009487 Amblyopia Diseases 0.000 description 1
- 201000004569 Blindness Diseases 0.000 description 1
- 206010038848 Retinal detachment Diseases 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000010234 longitudinal analysis Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 210000001747 pupil Anatomy 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000004264 retinal detachment Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a myopia risk assessment method, device and system based on artificial intelligence, wherein the method comprises the following steps: sensing the state of a target object in a preset area in real time, wherein the method comprises the following steps: the video data are collected and stored in real time; performing sequence modeling on the video, and performing identity recognition, eye state recognition and action feature recognition on a target object in the video through a video structuring algorithm to generate structured data and unstructured data; the method for collecting, cleaning and managing various information data comprises the following steps: according to the structured data, the unstructured data, and personal data and basic data of the target object, converging, cleaning and managing are carried out; based on the structured data and the unstructured data, analyzing and evaluating the myopia risk of the target object in a preset scene, wherein the method comprises the following steps: based on the real-time calculation data and the historical calculation data, a myopia risk evaluation index model is constructed, and based on the model, the myopia risk of the target object in a preset scene is analyzed and evaluated.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a myopia risk assessment method, device and system based on artificial intelligence.
Background
With the development of society, people's life is improved increasingly, more and more electronic products enter people's daily life, bring convenience and also cause certain harm to people's physical and mental health, myopia is one of the common diseases, and is mainly manifested by vision decline, fine targets or reduced identification ability of distant objects, and retinal detachment, amblyopia and even blindness can be caused when serious. Myopia has become a significant public health problem in china, especially in young children. The screening myopia rates of pupils, junior middle school students and senior high school students in 2018 are 36.0%,71.6% and 81.0% respectively. The trend of increasing and decreasing the prevalence of myopia year by year has seriously affected the physical and mental health of teenagers in children in China, resulting in an increase in the socioeconomic burden.
In the prior art, the invention has more prevention and treatment on myopia of related people, but has less prediction technology on myopia of related people, and a scheme for predicting myopia of children by using classroom learning scene data has not been realized in a better way at present.
Disclosure of Invention
In view of the above, the embodiment of the invention provides a myopia risk assessment method, device and system based on artificial intelligence, so as to solve the problems that the prediction technology of myopia of related people is less, and the scheme for predicting myopia of children by using classroom learning scene data has no better implementation mode at present.
According to a first aspect, an embodiment of the present invention provides a myopia risk assessment method based on artificial intelligence, including: sensing the state of a target object in a preset area in real time, wherein the method comprises the following steps: the video data are collected and stored in real time; performing sequence modeling on the video, and performing identity recognition, eye state recognition and action feature recognition on a target object in the video through a video structuring algorithm to generate structured data and unstructured data; the method for collecting, cleaning and managing various information data comprises the following steps: according to the structured data, the unstructured data, and personal data and basic data of the target object, converging, cleaning and managing are carried out; based on the structured data and the unstructured data, analyzing and evaluating the myopia risk of the target object in a preset scene, wherein the method comprises the following steps: based on real-time calculation data and historical calculation data, a myopia risk evaluation index model is constructed, and based on the myopia risk evaluation index model, the myopia risk of the target object in a preset scene is analyzed and evaluated.
Optionally, the myopia risk assessment method based on artificial intelligence further comprises: and respectively generating a structured data file containing time information for each target object in the preset area based on the identity recognition result.
Optionally, the myopia risk assessment method based on artificial intelligence further comprises: and synchronously storing the structured data and the unstructured data.
Optionally, the myopia risk evaluation index model includes: a myopia risk calculation model based on real-time data, and a myopia risk evaluation model based on full-scale data.
Optionally, the myopia risk assessment method based on artificial intelligence further comprises:
and periodically sending analysis and evaluation results based on the myopia risk evaluation index model to a user terminal for display.
According to a second aspect, an embodiment of the present invention provides an artificial intelligence based myopia risk assessment device, including: the state sensing module is used for sensing the state of the target object in the preset area in real time, and comprises the following steps: the video data are collected and stored in real time; performing sequence modeling on the video, and performing identity recognition, eye state recognition and action feature recognition on a target object in the video through a video structuring algorithm to generate structured data and unstructured data; the data analysis module is used for converging, cleaning and managing various information data, and comprises the following components: according to the structured data, the unstructured data, and personal data and basic data of the target object, converging, cleaning and managing are carried out; the analysis and evaluation module is used for analyzing and evaluating the myopia risk of the target object in a preset scene based on the structured data and the unstructured data, and comprises the following steps: based on real-time calculation data and historical calculation data, a myopia risk evaluation index model is constructed, and based on the myopia risk evaluation index model, the myopia risk of the target object in a preset scene is analyzed and evaluated.
Optionally, the artificial intelligence based myopia risk assessment device further comprises: and the structured data file generation module is used for respectively generating structured data files containing time information for each target object in the preset area based on the identification result.
Optionally, the artificial intelligence based myopia risk assessment device further comprises: and the data storage module is used for synchronously storing the structured data and the unstructured data.
Optionally, the myopia risk evaluation index model includes: a myopia risk calculation model based on real-time data, and a myopia risk evaluation model based on full-scale data.
Optionally, the myopia risk assessment device based on artificial intelligence further comprises: and the result display module is used for periodically sending the analysis and evaluation results based on the myopia risk evaluation index model to a user terminal for display.
According to a third aspect, embodiments of the present invention provide an artificial intelligence based myopia risk assessment system, comprising: the system comprises a computing platform, an information platform, a myopia risk assessment module and a result feedback module, wherein the computing platform is used for sensing the state of a target object in a preset area in real time and comprises the following components: the video data are collected and stored in real time; performing sequence modeling on the video, and performing identity recognition, eye state recognition and action feature recognition on a target object in the video through a video structuring algorithm to generate structured data and unstructured data; the information platform is used for converging, cleaning and managing various information data, and comprises: according to the structured data, the unstructured data, and personal data and basic data of the target object, converging, cleaning and managing are carried out; the myopia risk assessment module is used for analyzing and evaluating the myopia risk of a target object in a preset scene based on the structured data and the unstructured data, and comprises the following steps: based on real-time calculation data and historical calculation data, a myopia risk evaluation index model is constructed, and based on the myopia risk evaluation index model, the myopia risk of a target object under a preset scene is analyzed and evaluated; and the result feedback module is used for periodically sending analysis and evaluation results based on the myopia risk evaluation index model to a user terminal for display.
According to a fourth aspect, an embodiment of the present invention provides a computer apparatus, comprising: the system comprises a memory and a processor, wherein the memory and the processor are in communication connection, the memory stores computer instructions, and the processor executes the computer instructions, so as to execute the myopia risk assessment method based on artificial intelligence according to the first aspect or any implementation mode of the first aspect.
According to a fifth aspect, an embodiment of the present invention provides a computer readable storage medium storing computer instructions for causing the computer to perform the artificial intelligence based myopia risk assessment method according to the first aspect or any implementation manner of the first aspect.
The technical scheme of the invention has the following advantages:
according to the myopia risk assessment method based on the artificial intelligence, the video image and the like, educational process data is used as a main basis, related data is aided to be structured, the possibility that a child suffers from myopia risk is assessed and quantified, so that teachers and parents can be helped to find problems in time, intervention treatment can be carried out early, and healthy growth of the child can be helped.
Drawings
The features and advantages of the present invention will be more clearly understood by reference to the accompanying drawings, which are illustrative and should not be construed as limiting the invention in any way, in which:
FIG. 1 illustrates a flowchart of one specific example of an artificial intelligence based myopia risk assessment method in an embodiment of the present invention;
FIG. 2 illustrates one specific example diagram of an artificial intelligence based myopia risk assessment method in an embodiment of the present invention;
FIG. 3 illustrates a specific example schematic block diagram of an artificial intelligence based myopia risk assessment device in an embodiment of the present invention;
FIG. 4 illustrates a specific example schematic block diagram of an artificial intelligence based myopia risk assessment system in an embodiment of the present invention;
fig. 5 shows a schematic block diagram of a specific example of a computer device in an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
The embodiment of the invention provides a myopia risk assessment method based on artificial intelligence, which is shown in fig. 1 and comprises the following steps:
step S1: sensing the state of a target object in a preset area in real time, wherein the method comprises the following steps: the video data are collected and stored in real time; performing sequence modeling on the video, and performing identity recognition, eye state recognition and action feature recognition on a target object in the video through a video structuring algorithm to generate structured data and unstructured data;
step S2: the method for collecting, cleaning and managing various information data comprises the following steps: according to the structured data, the unstructured data, and personal data and basic data of the target object, converging, cleaning and managing are carried out;
step S3: based on the structured data and the unstructured data, analyzing and evaluating the myopia risk of the target object in a preset scene, wherein the method comprises the following steps: based on real-time calculation data and historical calculation data, a myopia risk evaluation index model is constructed, and based on the myopia risk evaluation index model, the myopia risk of the target object in a preset scene is analyzed and evaluated.
Optionally, in some embodiments of the present invention, the myopia risk assessment method mainly includes the following:
(1) Index system establishment
As shown in fig. 2, first, it is clear that the study object is all students in the classroom, and the objective is to predict the myopia risk presented by the students in the situations of looking to blackboard, writing, reading, etc.; secondly, various criteria affecting target realization are used as criterion layer elements below a target layer, wherein the criteria comprise three criteria including behavior characteristics, eye characteristics and other characteristics; thirdly, an index layer contains a certain index under each index layer to reflect the corresponding index property, wherein the behavior characteristics are reflected by 3 indexes of eye kneading, head tilting and head lowering, the eye characteristics are reflected by 3 indexes of eyebrow tattooing, squinting, blinking and the like, and other characteristics are reflected according to 1 index of the reading distance between students and books when reading books; and finally, outputting an evaluation result to obtain the risk score of the possible myopia of the student. The specific analysis of the determination of the evaluation index is shown in table 1 below.
TABLE 1
(2) Myopia risk assessment calculation method
y represents the myopia risk score, χ of student A in certain lesson on i Scores representing behavioral, ocular and other characteristics, alpha i Is the corresponding weight coefficient;
quantitative calculation of characteristic indexes:
(1) behavioral characteristics, a 1 ，a 2 ，a 3 The calculation formulas of the index features are as follows:
a 1 ＝n exp(t)；wherein n is the number of times each behavior feature occurs, alpha is the head-skew and low head angle, and t is the time. The integral calculation formula is L 2 Norms: />
(2) Eye features, b 1 ，b 2 ，b 3 The calculation formulas of the index features are as follows:
b 1 ＝n exp(t)；b 2 ＝n exp(t)；b 3 =n-15×45; wherein n is the number of times each behavior feature occurs, t is time, and the overall calculation formula is L 2 Norms:
(3) other features, c 1 The characteristic of reading distance is expressed, and the calculation formula is c 1 = |χ -33|exp (t), where χ is reading distance in cm and t is time.
(3) Determination of model weights
The model adopts an AHP entropy weight method to determine the weight, combines the subjective and objective, and enables the weighted result to be as close to the actual result as possible.
(1) AHP assay: establishing a judgment matrix, comparing all qualitative indexes under the same criterion layer and indexes of each criterion layer in pairs, and determining the relative importance of each index. The expert is asked to fill out a scoring table, a 1-9 scale method is adopted to judge the relative importance, and a scoring result is used for listing a comparison matrix A= { a lk (l, =1, 2,3, n.), wherein a lk The relative importance of the index l to the index k is shown, and there are:calculating eigenvalue and eigenvector, determining weight a= (a) 1 ，a 2 ，...，a n )。
(2) Entropy weight method: the entropy weight method utilizes entropy values of various indexes to determine index weights, and the larger the information entropy is, the higher the disorder degree of the information is, and the smaller the utility value of the information is; conversely, the smaller the information entropy, the smaller the disorder of the information and the larger the utility value of the information. The calculation of the weight is based on the original data, the result is real and reliable, and the influence of subjective factors can be eliminated. First, each index value subjected to normalization processing is recorded asConverting into specific gravity form>∑P i =1; next, the entropy of each evaluation index, h= { -k Σp, is determined i ln p i }，/>H∈[0，1]The method comprises the steps of carrying out a first treatment on the surface of the Finally, determining the weight according to the variation degree of each index value,
(3) AHP-entropy weighting method and comprehensive weighting
3. Model weight correction
An index weight correction system is established, and specifically comprises an expert weight module and an index system module. The system is used for collecting and inputting physical examination results through a periodic physical examination state in the test operation process of the approximate risk assessment feedback platform, and analyzing the deviation degree of the calculation results and the real conditions through iterative calculation of the original data. And adjusting and modifying the weight coefficient and the model index according to the analysis data.
4. Providing a myopia risk analysis report
According to the calculated and comprehensively evaluated student social anxiety disorder scores and class social anxiety disorder scores, social anxiety disorder evaluation reports can be generated weekly, monthly, and every school year to every school year, and specifically the method comprises the following steps:
(1) Periodic student myopia risk assessment report
Based on evaluating the myopia risk of the student individual in the period, the probability of suffering from myopia is known in time.
(2) Analysis of myopia risk degree of students in different periods
Through mutual comparison of evaluation results among different evaluation periods, longitudinal analysis is performed to analyze whether the myopia risk of an evaluation object is an ascending trend, a descending trend or a cliff-like falling suddenly appears in a representation before a certain time period is compared, and a threshold is set for early warning, so that parents can correct and intervene timely.
By implementing the invention, based on methods such as artificial intelligence, video images and the like, education process data is used as a main basis, related data is aided to be structured, and the possibility of the child suffering from myopia risks is estimated and quantified, so that teachers and parents can be helped to find problems in time, intervene and treat early, and healthy growth of the child is helped.
Optionally, in some embodiments of the invention, the method further comprises: and respectively generating a structured data file containing time information for each target object in the preset area based on the identity recognition result.
Optionally, in some embodiments of the invention, the method further comprises: and synchronously storing the structured data and the unstructured data.
Optionally, in some embodiments of the invention, the myopia risk assessment index model used by the method includes: a myopia risk calculation model based on real-time data, and a myopia risk evaluation model based on full-scale data.
Optionally, in some embodiments of the invention, the method further comprises: and periodically sending analysis and evaluation results based on the myopia risk evaluation index model to a user terminal for display.
The embodiment of the invention provides a myopia risk assessment device based on artificial intelligence, as shown in fig. 3, comprising:
the state sensing module 1 is configured to sense, in real time, a state of a target object in a preset area, and includes: the video data are collected and stored in real time; performing sequence modeling on the video, and performing identity recognition, eye state recognition and action feature recognition on a target object in the video through a video structuring algorithm to generate structured data and unstructured data; the details are referred to the corresponding parts of the method in the above embodiment, and will not be described herein.
The data analysis module 2 is configured to perform aggregation, cleaning and management of various information data, and includes: according to the structured data, the unstructured data, and personal data and basic data of the target object, converging, cleaning and managing are carried out; the details are referred to the corresponding parts of the method in the above embodiment, and will not be described herein.
The analysis and evaluation module 3 is configured to analyze and evaluate a myopia risk of the target object in a preset scene based on the structured data and the unstructured data, and includes: based on real-time calculation data and historical calculation data, a myopia risk evaluation index model is constructed, and based on the myopia risk evaluation index model, the myopia risk of the target object in a preset scene is analyzed and evaluated. The details are referred to the corresponding parts of the method in the above embodiment, and will not be described herein.
Optionally, in some embodiments of the present invention, the apparatus further comprises:
and the structured data file generation module is used for respectively generating structured data files containing time information for each target object in the preset area based on the identification result. The details are referred to the corresponding parts of the method in the above embodiment, and will not be described herein.
Optionally, in some embodiments of the present invention, the apparatus further comprises:
and the data storage module is used for synchronously storing the structured data and the unstructured data. The details are referred to the corresponding parts of the method in the above embodiment, and will not be described herein.
Optionally, in some embodiments of the present invention, the myopia risk assessment index model used by the apparatus includes: a myopia risk calculation model based on real-time data, and a myopia risk evaluation model based on full-scale data. The details are referred to the corresponding parts of the method in the above embodiment, and will not be described herein.
Optionally, in some embodiments of the present invention, the apparatus further comprises:
and the result display module is used for periodically sending the analysis and evaluation results based on the myopia risk evaluation index model to a user terminal for display. The details are referred to the corresponding parts of the method in the above embodiment, and will not be described herein.
The embodiment of the invention also provides a myopia risk assessment system based on artificial intelligence, as shown in fig. 4, which comprises: the system comprises a computing platform, an information platform, a myopia risk assessment module and a result feedback module.
The computing platform is used for sensing the state of a target object in a preset area in real time, and comprises the following steps: the video data are collected and stored in real time; performing sequence modeling on the video, and performing identity recognition, eye state recognition and action feature recognition on a target object in the video through a video structuring algorithm to generate structured data and unstructured data;
the information platform is used for converging, cleaning and managing various information data, and comprises: according to the structured data, the unstructured data, and personal data and basic data of the target object, converging, cleaning and managing are carried out;
the myopia risk assessment module is used for analyzing and evaluating the myopia risk of a target object in a preset scene based on the structured data and the unstructured data, and comprises the following steps: based on real-time calculation data and historical calculation data, a myopia risk evaluation index model is constructed, and based on the myopia risk evaluation index model, the myopia risk of a target object under a preset scene is analyzed and evaluated;
and the result feedback module is used for periodically sending analysis and evaluation results based on the myopia risk evaluation index model to a user terminal for display.
Embodiments of the present application also provide a computer device, as shown in fig. 5, a processor 310 and a memory 320, where the processor 310 and the memory 320 may be connected by a bus or other means.
The processor 310 may be a central processing unit (Central Processing Unit, CPU). The processor 310 may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSPs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), field programmable gate arrays (Field-Programmable Gate Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above.
The memory 320 is used as a non-transitory computer readable storage medium for storing non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the artificial intelligence based myopia risk assessment method according to the embodiments of the present invention. The processor executes various functional applications of the processor and data processing by running non-transitory software programs, instructions, and modules stored in memory.
Memory 320 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store data created by the processor, etc. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 320 may optionally include memory located remotely from the processor, which may be connected to the processor via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 320, which when executed by the processor 310, perform the artificial intelligence based myopia risk assessment method in the embodiments shown in fig. 1-3.
The details of the electronic device may be understood in response to the corresponding relevant descriptions and effects of the embodiments shown in fig. 1-3, which are not repeated herein.
The present embodiment also provides a computer storage medium storing computer executable instructions that are capable of performing the artificial intelligence based myopia risk assessment method of any of the above method embodiments. Wherein the storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a Flash Memory (Flash Memory), a Hard Disk (HDD), or a Solid State Drive (SSD); the storage medium may also comprise a combination of memories of the kind described above.
Although embodiments of the present invention have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the invention, and such modifications and variations are within the scope of the invention as defined by the appended claims.
Claims (13)
1. An artificial intelligence based myopia risk assessment method, comprising:
sensing the state of a target object in a preset area in real time, wherein the method comprises the following steps: the video data are collected and stored in real time; performing sequence modeling on the video, and performing identity recognition, eye state recognition and action feature recognition on a target object in the video through a video structuring algorithm to generate structured data and unstructured data;
the method for collecting, cleaning and managing various information data comprises the following steps: according to the structured data, the unstructured data, and personal data and basic data of the target object, converging, cleaning and managing are carried out;
based on the structured data and the unstructured data, analyzing and evaluating the myopia risk of the target object in a preset scene, wherein the method comprises the following steps: based on real-time calculation data and historical calculation data, a myopia risk evaluation index model is constructed, and based on the myopia risk evaluation index model, the myopia risk of a target object under a preset scene is analyzed and evaluated;
the index system of the myopia risk evaluation index model comprises: the study object is a whole student in the teaching room, and aims to predict myopia risks presented by the student in the situations of looking to a blackboard, writing and reading in class; various criteria affecting target realization are taken as criterion layer elements below a target layer, wherein the criteria comprise three criteria including behavior characteristics, eye characteristics and other characteristics; under each criterion layer, preset indexes are contained to reflect the corresponding criterion properties specifically, wherein the behavior characteristics are reflected by three indexes of eye rubbing, head tilting and head lowering, the eye characteristics are reflected by three indexes of eyebrow wrinkling, eye squinting and eye blinking, and other characteristics are reflected according to the index of reading distance between students and books when reading books, and the evaluation result is the risk score of myopia of the students; the myopia risk evaluation index model adopts an AHP entropy weight method to determine weight, and an index weight correction system is established to adjust and modify the weight coefficient and the model index;
the risk score of student myopia is calculated by the following formula:
y represents the risk score of myopia of students, χ 1 、χ 2 And χ (x) 3 Scores, k, representing behavioral, ocular and other characteristics, respectively 1 、k 2 And k 3 Corresponding weight coefficients for behavioral features, ocular features and other features;
behavioral characteristics utilization L 2 The norm is calculated using the following formula:
wherein,score X representing behavioral characteristics 1 ，a 1 ，a 2 ，a 3 The calculation formulas for the behavior characteristics of eye kneading, head tilting and head lowering are as follows:
wherein n is 1 、n 2 、n 3 To knead the times of occurrence of eyes, head distortion and low head behavior, alpha 1 、α 2 The head is inclined and has a low head angle, and t is time;
the ocular feature is calculated using the L2 norm using the following formula:
wherein,score, χ, representing ocular characteristics 2 ，b 1 ，b 2 ，b 3 The calculation formulas respectively represent the characteristics of eyebrow tattooing, squinting and blinking behavior, and the characteristics are as follows:
wherein n is 4 、n 5 、n 6 The times of occurrence of behavior characteristics of frowning, squinting and blinking are shown as t is time;
other features are calculated using the following formula:
wherein c 1 Score X representing other features 3 χ is reading distance, t is time;
the method for adjusting and modifying the weight coefficient and the model index by establishing the index weight correction system comprises the following steps: and establishing an index weight correction system which comprises an expert weight module and an index system module, wherein the index weight correction system is used for approximating a physical examination state of a risk assessment feedback platform in a test operation process, collecting and inputting physical examination results, analyzing the deviation degree of the calculation results and the real situation through iterative calculation of original data, and adjusting and modifying weight coefficients and model indexes according to analysis data.
2. The artificial intelligence based myopia risk assessment method according to claim 1, further comprising:
and respectively generating a structured data file containing time information for each target object in the preset area based on the identity recognition result.
3. The artificial intelligence based myopia risk assessment method according to claim 1, further comprising:
and synchronously storing the structured data and the unstructured data.
4. The artificial intelligence based myopia risk assessment method according to claim 1, wherein the myopia risk assessment index model comprises: a myopia risk calculation model based on real-time data, and a myopia risk evaluation model based on full-scale data.
5. The artificial intelligence based myopia risk assessment method according to claim 1, further comprising:
and periodically sending analysis and evaluation results based on the myopia risk evaluation index model to a user terminal for display.
6. An artificial intelligence based myopia risk assessment device, comprising:
the state sensing module is used for sensing the state of the target object in the preset area in real time, and comprises the following steps: the video data are collected and stored in real time; performing sequence modeling on the video, and performing identity recognition, eye state recognition and action feature recognition on a target object in the video through a video structuring algorithm to generate structured data and unstructured data;
the data analysis module is used for converging, cleaning and managing various information data, and comprises the following components: according to the structured data, the unstructured data, and personal data and basic data of the target object, converging, cleaning and managing are carried out;
the analysis and evaluation module is used for analyzing and evaluating the myopia risk of the target object in a preset scene based on the structured data and the unstructured data, and comprises the following steps: based on real-time calculation data and historical calculation data, a myopia risk evaluation index model is constructed, and based on the myopia risk evaluation index model, the myopia risk of a target object under a preset scene is analyzed and evaluated;
the index system of the myopia risk evaluation index model comprises: the study object is a whole student in the teaching room, and aims to predict myopia risks presented by the student in the situations of looking to a blackboard, writing and reading in class; various criteria affecting target realization are taken as criterion layer elements below a target layer, wherein the criteria comprise three criteria including behavior characteristics, eye characteristics and other characteristics; under each criterion layer, preset indexes are contained to reflect the corresponding criterion properties specifically, wherein the behavior characteristics are reflected by three indexes of eye rubbing, head tilting and head lowering, the eye characteristics are reflected by three indexes of eyebrow wrinkling, eye squinting and eye blinking, and other characteristics are reflected according to the index of reading distance between students and books when reading books, and the evaluation result is the risk score of myopia of the students; the myopia risk evaluation index model adopts an AHP entropy weight method to determine weight, and an index weight correction system is established to adjust and modify the weight coefficient and the model index;
the risk score of student myopia is calculated by the following formula:
y represents the risk score of myopia of students, χ 1 、χ 2 And χ (x) 3 Scores, k, representing behavioral, ocular and other characteristics, respectively 1 、k 2 And k 3 Corresponding weight coefficients for behavioral features, ocular features and other features;
behavioral characteristics utilization L 2 The norm is calculated using the following formula:
wherein,score X representing behavioral characteristics 1 ，a 1 ，a 2 ，a 3 The calculation formulas for the behavior characteristics of eye kneading, head tilting and head lowering are as follows:
wherein n is 1 、n 2 、n 3 To knead the times of occurrence of eyes, head distortion and low head behavior, alpha 1 、α 2 The head is inclined and has a low head angle, and t is time;
the ocular feature is calculated using the L2 norm using the following formula:
wherein,score, χ, representing ocular characteristics 2 ，b 1 ，b 2 ，b 3 The calculation formulas respectively represent the characteristics of eyebrow tattooing, squinting and blinking behavior, and the characteristics are as follows:
wherein n is 4 、n 5 、n 6 The times of occurrence of behavior characteristics of frowning, squinting and blinking are shown as t is time;
other features are calculated using the following formula:
wherein c 1 Score X representing other features 3 χ is reading distance, t is time;
the method for adjusting and modifying the weight coefficient and the model index by establishing the index weight correction system comprises the following steps: and establishing an index weight correction system which comprises an expert weight module and an index system module, wherein the index weight correction system is used for approximating a physical examination state of a risk assessment feedback platform in a test operation process, collecting and inputting physical examination results, analyzing the deviation degree of the calculation results and the real situation through iterative calculation of original data, and adjusting and modifying weight coefficients and model indexes according to analysis data.
7. The artificial intelligence based myopia risk assessment device according to claim 6, further comprising:
and the structured data file generation module is used for respectively generating structured data files containing time information for each target object in the preset area based on the identification result.
8. The artificial intelligence based myopia risk assessment device according to claim 6, further comprising:
and the data storage module is used for synchronously storing the structured data and the unstructured data.
9. The artificial intelligence based myopia risk assessment device according to claim 6, wherein the myopia risk assessment indicator model comprises: a myopia risk calculation model based on real-time data, and a myopia risk evaluation model based on full-scale data.
10. The artificial intelligence based myopia risk assessment device according to claim 6, further comprising:
and the result display module is used for periodically sending the analysis and evaluation results based on the myopia risk evaluation index model to a user terminal for display.
11. An artificial intelligence based myopia risk assessment system, comprising: the device comprises a computing platform, an information platform, a myopia risk assessment module and a result feedback module, wherein,
the computing platform is used for sensing the state of a target object in a preset area in real time, and comprises the following steps: the video data are collected and stored in real time; performing sequence modeling on the video, and performing identity recognition, eye state recognition and action feature recognition on a target object in the video through a video structuring algorithm to generate structured data and unstructured data;
the information platform is used for converging, cleaning and managing various information data, and comprises: according to the structured data, the unstructured data, and personal data and basic data of the target object, converging, cleaning and managing are carried out;
the myopia risk assessment module is used for analyzing and evaluating the myopia risk of a target object in a preset scene based on the structured data and the unstructured data, and comprises the following steps: based on real-time calculation data and historical calculation data, a myopia risk evaluation index model is constructed, and based on the myopia risk evaluation index model, the myopia risk of a target object under a preset scene is analyzed and evaluated; the index system of the myopia risk evaluation index model comprises: the study object is a whole student in the teaching room, and aims to predict myopia risks presented by the student in the situations of looking to a blackboard, writing and reading in class; various criteria affecting target realization are taken as criterion layer elements below a target layer, wherein the criteria comprise three criteria including behavior characteristics, eye characteristics and other characteristics; under each criterion layer, preset indexes are contained to reflect the corresponding criterion properties specifically, wherein the behavior characteristics are reflected by three indexes of eye rubbing, head tilting and head lowering, the eye characteristics are reflected by three indexes of eyebrow wrinkling, eye squinting and eye blinking, and other characteristics are reflected according to the index of reading distance between students and books when reading books, and the evaluation result is the risk score of myopia of the students; the myopia risk evaluation index model adopts an AHP entropy weight method to determine weight, and an index weight correction system is established to adjust and modify the weight coefficient and the model index;
and the result feedback module is used for periodically sending analysis and evaluation results based on the myopia risk evaluation index model to a user terminal for display.
12. A computer device, comprising:
a memory and a processor in communication with each other, the memory having stored therein computer instructions that, upon execution, perform the artificial intelligence based myopia risk assessment method according to any of claims 1-5.
13. A computer-readable storage medium storing computer instructions for causing the computer to perform the artificial intelligence based myopia risk assessment method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011482956.1A CN112365107B (en) | 2020-12-16 | 2020-12-16 | Myopia risk assessment method, device and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011482956.1A CN112365107B (en) | 2020-12-16 | 2020-12-16 | Myopia risk assessment method, device and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112365107A CN112365107A (en) | 2021-02-12 |
| CN112365107B true CN112365107B (en) | 2024-01-23 |
Family
ID=74534519
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011482956.1A Active CN112365107B (en) | 2020-12-16 | 2020-12-16 | Myopia risk assessment method, device and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112365107B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113378975A (en) * | 2021-06-30 | 2021-09-10 | 哈尔滨理工大学 | Method for evaluating difference of risk perception capability of electrician operating personnel |
| CN114937307B (en) * | 2022-07-19 | 2023-04-18 | 北京鹰瞳科技发展股份有限公司 | Method for myopia prediction and related products |
| CN115132364B (en) * | 2022-08-25 | 2022-12-09 | 首都医科大学附属北京同仁医院 | Myopia risk determination method and device, storage medium and wearable device |
| CN115547497B (en) * | 2022-10-09 | 2023-09-08 | 湖南火眼医疗科技有限公司 | Myopia prevention and control system and method based on multi-source data |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8016416B1 (en) * | 2005-01-15 | 2011-09-13 | Sandy Helene Straus | Automatic system and methods for measuring and evaluating at least one of mass vision, cognition, knowledge, operation skills, and the like |
| CN110069988A (en) * | 2019-01-31 | 2019-07-30 | 中国平安财产保险股份有限公司 | AI based on multidimensional data drives risk analysis method, server and storage medium |
| CN209301108U (en) * | 2018-02-06 | 2019-08-27 | 腾阅健康科技（深圳）有限公司 | A kind of human eye vision monitoring system |
| CN110269587A (en) * | 2019-06-28 | 2019-09-24 | 中山大学中山眼科中心 | Infant's motion analysis system and infant eyesight analysis system based on movement |
| CN110288266A (en) * | 2019-07-03 | 2019-09-27 | 爱尔眼科医院集团股份有限公司 | A kind of risks of myopia appraisal procedure and system |
| WO2020083382A1 (en) * | 2018-10-26 | 2020-04-30 | Ai Technologies Inc. | Accurate prediction and treatment of myopic progression by artificial intelligence |
| CN111160380A (en) * | 2018-11-07 | 2020-05-15 | 华为技术有限公司 | Method for generating video analysis model and video analysis system |
| CN111159249A (en) * | 2019-12-13 | 2020-05-15 | 深圳市唯特视科技有限公司 | Target identification method, device and system based on knowledge graph and storage medium |
| CN112085392A (en) * | 2020-09-10 | 2020-12-15 | 北京易华录信息技术股份有限公司 | Learning participation degree determining method and device and computer equipment |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140354949A1 (en) * | 2013-05-31 | 2014-12-04 | Sherwyne R. Bakar | Interactive platform for health assessment |
| US11051689B2 (en) * | 2018-11-02 | 2021-07-06 | International Business Machines Corporation | Real-time passive monitoring and assessment of pediatric eye health |
-
2020
- 2020-12-16 CN CN202011482956.1A patent/CN112365107B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8016416B1 (en) * | 2005-01-15 | 2011-09-13 | Sandy Helene Straus | Automatic system and methods for measuring and evaluating at least one of mass vision, cognition, knowledge, operation skills, and the like |
| CN209301108U (en) * | 2018-02-06 | 2019-08-27 | 腾阅健康科技（深圳）有限公司 | A kind of human eye vision monitoring system |
| WO2020083382A1 (en) * | 2018-10-26 | 2020-04-30 | Ai Technologies Inc. | Accurate prediction and treatment of myopic progression by artificial intelligence |
| CN111160380A (en) * | 2018-11-07 | 2020-05-15 | 华为技术有限公司 | Method for generating video analysis model and video analysis system |
| CN110069988A (en) * | 2019-01-31 | 2019-07-30 | 中国平安财产保险股份有限公司 | AI based on multidimensional data drives risk analysis method, server and storage medium |
| CN110269587A (en) * | 2019-06-28 | 2019-09-24 | 中山大学中山眼科中心 | Infant's motion analysis system and infant eyesight analysis system based on movement |
| CN110288266A (en) * | 2019-07-03 | 2019-09-27 | 爱尔眼科医院集团股份有限公司 | A kind of risks of myopia appraisal procedure and system |
| CN111159249A (en) * | 2019-12-13 | 2020-05-15 | 深圳市唯特视科技有限公司 | Target identification method, device and system based on knowledge graph and storage medium |
| CN112085392A (en) * | 2020-09-10 | 2020-12-15 | 北京易华录信息技术股份有限公司 | Learning participation degree determining method and device and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112365107A (en) | 2021-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112365107B (en) | Myopia risk assessment method, device and system based on artificial intelligence | |
| US7438418B2 (en) | Mental alertness and mental proficiency level determination | |
| JP2020509498A5 (en) | ||
| Chango et al. | A review on data fusion in multimodal learning analytics and educational data mining | |
| Vandekerckhove et al. | A crossed random effects diffusion model for speeded semantic categorization decisions | |
| JP7311637B2 (en) | Systems and methods for cognitive training and monitoring | |
| Endo et al. | A convolutional neural network for estimating synaptic connectivity from spike trains | |
| CN112528890B (en) | Attention assessment method and device and electronic equipment | |
| Herasymova et al. | Development of Intelligent Information Technology of Computer Processing of Pedagogical Tests Open Tasks Based on Machine Learning Approach. | |
| CN112115908A (en) | Social ability evaluation method and device | |
| Devkar et al. | Monkeys and humans take local uncertainty into account when localizing a change | |
| US20230127335A1 (en) | Intelligent and adaptive measurement system for remote education | |
| Cuong et al. | Eye Strain Detection During Online Learning. | |
| Uragun et al. | Developing an appropriate data normalization method | |
| Devi et al. | GA-CNN: Analyzing student’s cognitive skills with EEG data using a hybrid deep learning approach | |
| CN113842113A (en) | Developing reading disorder intelligent identification method, system, equipment and storage medium | |
| Maddu et al. | Online learners’ engagement detection via facial emotion recognition in online learning context using hybrid classification model | |
| Patel | A Machine Learning based Eye Tracking Framework to detect Zoom Fatigue | |
| Zhao et al. | [Retracted] Computational Technologies in Internet of Things and Big Data Technology for Physical Exercise Rehabilitation System | |
| Piesse et al. | Causal inference using semi-parametric imputation | |
| US11847127B2 (en) | Device and method for discovering causal patterns | |
| WO2023284067A1 (en) | Facial nerve function evaluation method and apparatus, and computer device and storage medium | |
| Kavya et al. | Student Personality Analysis In Blended Mode Using Big Five | |
| Endo et al. | CoNNECT: Convolutional Neural Network for Estimating synaptic Connectivity from spike Trains | |
| Liu et al. | Gaze based behavior analysis of online learners |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |