CN116936097A - Training lamp user eye abnormal movement intelligent detection method - Google Patents
Training lamp user eye abnormal movement intelligent detection method Download PDFInfo
- Publication number
- CN116936097A CN116936097A CN202310910047.0A CN202310910047A CN116936097A CN 116936097 A CN116936097 A CN 116936097A CN 202310910047 A CN202310910047 A CN 202310910047A CN 116936097 A CN116936097 A CN 116936097A
- Authority
- CN
- China
- Prior art keywords
- eye
- target person
- training
- data
- movement
- 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
- 238000012549 training Methods 0.000 title claims abstract description 134
- 238000001514 detection method Methods 0.000 title claims abstract description 44
- 208000012661 Dyskinesia Diseases 0.000 title abstract description 5
- 210000001508 eye Anatomy 0.000 claims abstract description 311
- 230000003068 static effect Effects 0.000 claims abstract description 81
- 230000002159 abnormal effect Effects 0.000 claims abstract description 53
- 238000004458 analytical method Methods 0.000 claims abstract description 27
- 230000004424 eye movement Effects 0.000 claims abstract description 25
- 238000012216 screening Methods 0.000 claims abstract description 17
- 208000002111 Eye Abnormalities Diseases 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims description 52
- 230000005856 abnormality Effects 0.000 claims description 35
- 238000004364 calculation method Methods 0.000 claims description 34
- 210000005252 bulbus oculi Anatomy 0.000 claims description 31
- 230000008569 process Effects 0.000 claims description 30
- 208000030533 eye disease Diseases 0.000 claims description 28
- 238000010586 diagram Methods 0.000 claims description 22
- 238000012937 correction Methods 0.000 claims description 18
- 230000004598 abnormal eye movement Effects 0.000 claims description 14
- 238000012512 characterization method Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 7
- 208000022873 Ocular disease Diseases 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 10
- 230000036541 health Effects 0.000 abstract description 5
- 238000013075 data extraction Methods 0.000 abstract 2
- 238000000605 extraction Methods 0.000 abstract 1
- 230000009471 action Effects 0.000 description 3
- 230000003449 preventive effect Effects 0.000 description 2
- 208000007101 Muscle Cramp Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004141 dimensional analysis Methods 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H5/00—Exercisers for the eyes
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- 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
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
Landscapes
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- Ophthalmology & Optometry (AREA)
- Pathology (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Pain & Pain Management (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Heart & Thoracic Surgery (AREA)
- Physical Education & Sports Medicine (AREA)
- Rehabilitation Therapy (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses an intelligent detection method for eye abnormal movement of a training lamp user, which relates to the technical field of eye abnormal detection and comprises basic information extraction and analysis, reference comparison data screening, training lamp mode data statistics, eye static mode data extraction and analysis, eye dynamic mode data extraction and analysis and eye abnormal dynamic feedback prompt. According to the invention, the basic condition of the target personnel is analyzed, so that the accuracy of data analysis is improved, and a more scientific and reasonable support basis can be provided for the dynamic intelligent detection of the eye abnormalities of the user. The abnormal indexes of the eye movement and static mode data of the target personnel are analyzed and calculated, so that the dimensionality of data analysis is diversified, more accurate data support is provided for judging the abnormal state of the eyes of the user, the potential abnormal risk of the eyes of the user can be timely found, and the eye health rationality screening level of the user is improved.
Description
Technical Field
The invention relates to the technical field of eye anomaly detection, in particular to an intelligent detection method for eye anomaly movement of a training lamp user.
Background
With the popularity of mobile devices and electronic screens, users have become a common phenomenon in daily life using electronic products for a long time. However, prolonged exposure of electronic screens can present a potential risk to human eye health. Eye abnormalities such as fatigue, dryness, eye muscle cramps, etc. are becoming a common eye health problem. To provide better eye care and health management, training a light user's eye abnormal movement intelligent detection method has been developed.
At present, the prior art has some limitations in the intelligent detection of eye abnormal movement of a training lamp user, and the specific implementation of the prior art is as follows: 1. firstly, the eye anomaly detection of the user of the training lamp at present lacks the analysis of eye data according to the characteristics of target personnel, different personnel have the difference in the requirements for eye screening data due to the difference of physical characteristics, if the analysis is carried out according to the basic conditions of corresponding target personnel, the accuracy of the data analysis is poor, the high-efficiency safety guarantee can not be provided for the eye anomaly dynamic intelligent detection of the user, the cost of the eye anomaly dynamic intelligent detection of the user is increased to a certain extent, and the problem of inaccurate detection exists.
2. Secondly, at present, in the intelligent detection process of the abnormal eye movement of the training lamp user, monitoring analysis is not carried out on eye movement data of a person in each mode of the training lamp, the eye movement data can reflect the abnormal eye condition of the person more accurately, consideration of the aspect is lacking, multi-dimensional analysis cannot be carried out on the eye movement change of the target person, accuracy of a detection result can be affected, and timely screening and reflection of the abnormal eye condition of the person are not facilitated.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an intelligent detection method for abnormal eye movement of a training lamp user, which solves the problems related to the background art.
In order to achieve the above purpose, the invention is realized by the following technical scheme: the intelligent detection method for the abnormal eye movement of the training lamp user comprises the following steps of firstly, extracting and pre-analyzing basic information: extracting basic information of a target person, and analyzing to obtain an eye state representation value of the target person; second step, screening reference comparison data: according to the eye state representation value of the target person, screening to obtain reference comparison data of the target person; thirdly, training the data statistics of the lamp modes: counting eye data of a target person in a static mode and a dynamic mode of the training lamp, and marking the eye data of the target person in the static mode and the dynamic mode of the training lamp as eye static mode data and eye dynamic mode data in sequence; fourth, extracting and analyzing static pattern data of eyes: extracting eye static mode data of a target person, and analyzing and calculating an abnormality index of the eye static mode data of the target person according to the eye static mode data; fifthly, extracting and analyzing the dynamic model data of the eyes: extracting eye dynamic mode data of a target person, and analyzing and calculating an abnormality index of the eye dynamic mode data of the target person according to the eye dynamic mode data; step six, dynamically feeding back and prompting abnormal eyes: according to the abnormal index of the eye static mode data of the target personnel and the abnormal index of the eye dynamic mode data, the eye abnormal coefficient of the target personnel is comprehensively calculated, and then the detection result of the target personnel is screened and feedback prompt is carried out.
Further, the analysis obtains an eye state representation value of the target person, and the specific process is as follows: according to basic information of a target person, wherein the basic information comprises age, binocular vision difference, binocular average vision and eye history illness information, the eye history illness information comprises: name and duration of each history ocular disease; according to the ages of the target personnel, further comparing the binocular reference allowable vision difference, the binocular reference healthy average vision and the characterization factors of the unit duration corresponding to various eye diseases stored in the database, obtaining the binocular reference allowable vision difference, the binocular reference healthy average vision and the characterization factors of the unit duration corresponding to various historical eye diseases corresponding to the target personnel, and calculating to obtain the eye state characterization value of the target personnel, wherein the calculation formula is as follows:wherein->Representing an eye state representation value of the target person, < +.>、/>Andrespectively representing binocular vision difference, binocular average vision and the duration of the c-th historical eye disease of the target person,、/>and->The characterization factors of the unit duration corresponding to the eyes reference allowable vision difference, eyes reference healthy average vision and the c-th historical eye disease of the target person are respectively represented, c represents the number of each historical eye disease name,k is the total number of historic eye diseases, +.>And->The set binocular vision difference and the set binocular average vision corresponding weight factors are respectively represented, and e represents a natural constant.
Further, the screening is performed to obtain reference comparison data of target personnel, and the specific process is as follows: according to the age and eye state representation values of the target person, further matching with reference eye data corresponding to the eye state representation value ranges of the persons in each age interval stored in the database, and further obtaining reference eye data of the target person, wherein the reference eye data comprises eye static mode reference data and eye movement mode reference data.
Further, the specific process of the eye data of the statistics target personnel in the static mode and the dynamic mode of the training lamp comprises the following steps: (1) The eye data of the target personnel in the static mode of the training lamp are counted, and the method specifically comprises the following steps: the training light is controlled in a static mode by setting training brightness, eye data of a target person in the static mode of the training light are monitored and counted, and accordingly the eye data of the target person in the static mode of the training light are marked as eye static mode data, wherein the eye static mode data comprise: blink frequency, eye opening duration, initial training positions corresponding to pupil center points of eyes and eye movement positions of eyes;
(2) The eye data of the target personnel under the training lamp movement mode is counted, and the method specifically comprises the following steps: and controlling the movement mode of the training lamp according to the set training brightness, acquiring training time length corresponding to the movement mode of the training lamp, and dividing the training time length into various training monitoring time points according to the set number, so as to monitor and count the pupil center point positions of various eyes of a target person in various training monitoring time points, constructing a pupil center point movement track line diagram of various eyes of the target person in the movement mode of the training lamp, taking the pupil center point movement track line diagram as eye data of the target person in the movement mode of the training lamp, and marking the eye movement track line diagram as eye movement mode data of the target person.
Further, the analysis calculates an abnormality index of the eye static mode data of the target person, and the specific analysis process is as follows: extracting blink frequency and eye opening duration of a target person in a training lamp static mode, and further according to eye static mode reference data of the target person, wherein the eye static mode reference data comprise reference blink frequency and eye opening duration, so that an eye basic training fitting index of the target person is analyzed and calculated, and a calculation formula is as follows:wherein->An eye basic training fitting index representing the target person, < ->、Respectively represent target personnelReference blink frequency and reference eye-open duration, +.>And->Respectively indicating blink frequency and eye opening duration of the target person in the training light static mode, +.>And->Correction factors respectively representing the set blink frequency and the eye opening duration; according to the initial training position and each eye movement position corresponding to the pupil center point of each eye of the target person, further extracting and obtaining each pupil center point offset of each eye of the target person, and calculating the eyeball position offset index of the target person, wherein the calculation formula is as follows: />Wherein->Index indicating the eye position shift of the target person, +.>Represents the jth pupil center point offset of the r eye of the target person, r=a or B, where a and B represent the left and right eyes, respectively, of the target person, and->For the deviation evaluation factor corresponding to the unit deviation amount of the pupil center point of the set eyeball, j represents the number of the deviation of the pupil center point of each time, g represents the total number of the deviation of the pupil center point and +.>A correction factor indicating the eyeball position deviation index of the set target person.
Further, the analysis calculates the eyes of the target personThe specific calculation process of the abnormality index to which the part static mode data belongs is as follows: according to the eye basic training attachment index and the eyeball position deviation index of the target person, further calculating to obtain an eye static training abnormal index of the target person, wherein the calculation formula is as follows:wherein->Eye static training abnormality index indicating target person, < ->And->The weight factors of the eye basic training attachment index and the eyeball position deviation index of the set target person are respectively represented.
Further, the analysis calculates an abnormality index of the eye dynamic mode data of the target person, and the specific analysis process is as follows: extracting eye movement pattern reference data of a target person, wherein the eye movement pattern reference data is a pupil center point movement track reference line diagram of each eye, and extracting the length of the pupil center point movement track reference line diagram of each eye of the target person, and recording asThe method comprises the steps of carrying out a first treatment on the surface of the Extracting pupil center point movement track line diagrams of eyes of a target person in a training light movement mode, respectively carrying out overlapping comparison with pupil center point movement track reference line diagrams of the eyes of the target person, extracting line lengths of overlapping pupil center point movement tracks of the eyes, and marking as +.>Further, calculating an eye dynamic track superposition index of the target person, wherein the calculation formula is as follows: />Wherein->Eye dynamic trajectory coincidence index of target person, < ->The correction coefficient is the line length of the set eye dynamic track line graph superposition; positioning the target person to the positions of all track points from a pupil center point movement track line diagram of each eye of the target person in a training light movement mode, further recording a line segment of an interval between two adjacent movement track points as a movement track segment, counting the distance of each movement track segment of each eye of the target person, extracting the interval duration between the two adjacent movement track points, further extracting the movement speed of each movement track segment of each eye of the target person, and recording the movement speed as->And comparing with standard eyeball training speed in a database, thereby calculating eyeball dynamic training coincidence indexes of target personnel, wherein the calculation formula is as follows:wherein->Eye dynamic training compliance index for the target person, < +.>Represents the standard eye training speed, b represents the number of each motion trail segment, < >>M is the number of motion track segments,the correction factor corresponding to the set eyeball movement speed is indicated.
Further, the analysis and calculation of the abnormality index of the eye dynamic mode data of the target person comprises the following specific calculation processes: according to the purposeThe eye dynamic track coincidence index of the target person and the eyeball dynamic training coincidence index of the target person are analyzed and calculated, and the abnormal index of the eye dynamic mode data of the target person is calculated according to the calculation formula:wherein->Abnormality index indicating the eye dynamic pattern data of the target person, +.>Andand respectively representing the set eye dynamic trajectory coincidence indexes of the target personnel and the correction factors corresponding to the eyeball dynamic training coincidence indexes of the target personnel.
Further, the comprehensive calculation of the ocular abnormality coefficient of the target person comprises the following specific processes: according to the abnormality index of the eye static mode data of the target person and the abnormality index of the eye dynamic mode data of the target person, further comprehensively calculating the eye abnormality coefficient of the target person, wherein the calculation formula is as follows:wherein->Eye abnormality coefficient representing target person, +.>And->And the correction factors respectively represent the abnormality indexes of the set eye static mode data and the abnormality indexes of the eye dynamic mode data.
Further, the detection result of the screening target personnel is fed back for prompting, and the specific process is as follows: and comparing the eye abnormal coefficient of the target person with a set eye abnormal coefficient threshold value, and when the eye abnormal coefficient of the target person is higher than the set eye abnormal coefficient threshold value, carrying out feedback prompt on the detection result of the target person.
The invention has the following beneficial effects:
(1) According to the invention, the eye state representation value of the target person is obtained through analysis, the eye data can be analyzed according to the characteristics of the target person, the accuracy of data analysis is improved, a more scientific and reasonable support basis can be provided for the dynamic intelligent detection of the eye abnormality of the user, the cost of the dynamic intelligent detection of the eye abnormality of the user is reduced to a certain extent, and the accuracy of the detection result is increased.
(2) According to the method, the abnormal indexes of the eye dynamic mode data of the target person are analyzed and calculated, so that the eye abnormal conditions of the person can be reflected more accurately, the detailed analysis is carried out, the dimensionality of the data analysis is more diversified, more accurate data support basis can be provided for judging the abnormal state of the eyes of the user, the potential abnormal risk of the eyes of the user can be found timely, and further efficient and safe guarantee is provided for the eye abnormal dynamic intelligent detection result of the user.
(3) According to the method, the ocular abnormality coefficient of the target personnel is analyzed, the ocular abnormality condition of the target personnel can be timely monitored and reminded, and reasonable feedback adjustment suggestion is carried out, so that the target personnel can more effectively take preventive measures, and the ocular health of the target personnel is greatly ensured.
Of course, it is not necessary for any one product to practice the invention to achieve all of the advantages set forth above at the same time.
Drawings
FIG. 1 is a flow chart of the method steps of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be understood that the terms "open," "upper," "lower," "thickness," "top," "middle," "length," "inner," "peripheral," and the like indicate orientation or positional relationships, merely for convenience in describing the present invention and to simplify the description, and do not indicate or imply that the components or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the present invention.
Referring to fig. 1, the embodiment of the invention provides a technical scheme: the intelligent detection method for the abnormal eye movement of the training lamp user comprises the following steps of firstly, extracting and pre-analyzing basic information: basic information of the target personnel is extracted, and the eye state representation value of the target personnel is obtained through analysis.
Second step, screening reference comparison data: and obtaining reference comparison data of the target personnel through screening according to the eye state representation value of the target personnel.
Thirdly, training the data statistics of the lamp modes: and counting eye data of the target person in the static mode and the dynamic mode of the training lamp, and marking the eye data of the target person in the static mode and the dynamic mode of the training lamp as eye static mode data and eye dynamic mode data in sequence.
Fourth, extracting and analyzing static pattern data of eyes: and extracting eye static mode data of the target person, and analyzing and calculating an abnormality index of the eye static mode data of the target person according to the eye static mode data.
Fifthly, extracting and analyzing the dynamic model data of the eyes: and extracting eye dynamic mode data of the target personnel, and analyzing and calculating an abnormality index of the eye dynamic mode data of the target personnel according to the eye dynamic mode data.
Step six, dynamically feeding back and prompting abnormal eyes: according to the abnormal index of the eye static mode data of the target personnel and the abnormal index of the eye dynamic mode data, the eye abnormal coefficient of the target personnel is comprehensively calculated, and then the detection result of the target personnel is screened and feedback prompt is carried out.
Specifically, the eye state representation value of the target person is obtained through analysis, and the specific process is as follows: according to basic information of a target person, wherein the basic information comprises age, binocular vision difference, binocular average vision and eye history illness information, the eye history illness information comprises: name and duration of each history of ocular disease.
According to the ages of the target personnel, further comparing the binocular reference allowable vision difference, the binocular reference healthy average vision and the characterization factors of the unit duration corresponding to various eye diseases stored in the database, obtaining the binocular reference allowable vision difference, the binocular reference healthy average vision and the characterization factors of the unit duration corresponding to various historical eye diseases corresponding to the target personnel, and calculating to obtain the eye state characterization value of the target personnel, wherein the calculation formula is as follows:wherein->Represents the eye state representation value of the target person,、/>and->Respectively representing binocular vision difference, binocular average vision and c time duration of historical eye disease of target person,/->、/>And->Characterization factors respectively representing binocular reference allowable vision difference, binocular reference healthy average vision and unit duration corresponding to the c-th historical eye disease of target personnel, c represents the number of each historical eye disease name, and +.>K is the total number of historic eye diseases, +.>And->The set binocular vision difference and the set binocular average vision corresponding weight factors are respectively represented, and e represents a natural constant.
In this embodiment, through carrying out the analysis of eye data according to target personnel's characteristic, the requirement of physical characteristic and eye screening data to different personnel has been analyzed, has increased the accuracy of data analysis, can provide scientific and reasonable support basis more for the unusual dynamic intelligent detection of user's eye.
Specifically, screening to obtain reference comparison data of target personnel, wherein the specific process is as follows: according to the age and eye state representation values of the target person, further matching with reference eye data corresponding to the eye state representation value ranges of the persons in each age interval stored in the database, and further obtaining reference eye data of the target person, wherein the reference eye data comprises eye static mode reference data and eye movement mode reference data.
Specifically, the eye data of the target person in the static mode and the dynamic mode of the training lamp are counted, and the specific process comprises the following steps: (1) The eye data of the target personnel in the static mode of the training lamp are counted, and the method specifically comprises the following steps: the training light is controlled in a static mode by setting training brightness, eye data of a target person in the static mode of the training light are monitored and counted, and accordingly the eye data of the target person in the static mode of the training light are marked as eye static mode data, wherein the eye static mode data comprise: blink frequency, eye opening duration, initial training positions corresponding to pupil center points of the eyes, and eye movement positions of the eyes.
(2) The eye data of the target personnel under the training lamp movement mode is counted, and the method specifically comprises the following steps: and controlling the movement mode of the training lamp according to the set training brightness, acquiring training time length corresponding to the movement mode of the training lamp, and dividing the training time length into various training monitoring time points according to the set number, so as to monitor and count the pupil center point positions of various eyes of a target person in various training monitoring time points, constructing a pupil center point movement track line diagram of various eyes of the target person in the movement mode of the training lamp, taking the pupil center point movement track line diagram as eye data of the target person in the movement mode of the training lamp, and marking the eye movement track line diagram as eye movement mode data of the target person.
In this embodiment, an eye tracker is used to acquire blink frequency, eye opening duration, and pupil center point of each eye.
Specifically, the abnormality index of the eye static mode data of the target person is analyzed and calculated, and the specific analysis process is as follows: extracting blink frequency and eye opening duration of a target person in a training lamp static mode, and further according to eye static mode reference data of the target person, wherein the eye static mode reference data comprise reference blink frequency and eye opening duration, so that an eye basic training fitting index of the target person is analyzed and calculated, and a calculation formula is as follows:wherein->An eye basic training fitting index representing the target person, < ->、/>Respectively indicating a reference blink frequency and a reference eye-opening duration of the target person, < >>And->Respectively indicating blink frequency and eye opening duration of the target person in the training light static mode, +.>And->Correction factors indicating the set blink frequency and the eye-open duration, respectively.
According to the initial training position and each eye movement position corresponding to the pupil center point of each eye of the target person, further extracting and obtaining each pupil center point offset of each eye of the target person, and calculating the eyeball position offset index of the target person, wherein the calculation formula is as follows:wherein->Index indicating the eye position shift of the target person, +.>Represents the jth pupil center point offset of the r eye of the target person, r=a or B, where a and B represent the left and right eyes, respectively, of the target person, and->For the deviation evaluation factor corresponding to the unit deviation amount of the pupil center point of the set eyeball, j represents the number of the deviation of the pupil center point of each time, g represents the total number of the deviation of the pupil center point and +.>A correction factor indicating the eyeball position deviation index of the set target person.
In the embodiment, the analysis is performed according to the basic conditions of the corresponding target personnel, so that the accuracy of data analysis is improved, efficient and safe guarantee can be provided for the dynamic intelligent detection of the eye abnormality of the user, and the cost of the dynamic intelligent detection of the eye abnormality of the user is reduced to a certain extent.
Specifically, the abnormality index of the eye static mode data of the target person is analyzed and calculated, and the specific calculation process is as follows: according to the eye basic training attachment index and the eyeball position deviation index of the target person, further calculating to obtain an eye static training abnormal index of the target person, wherein the calculation formula is as follows:wherein->Eye static training abnormality index indicating target person, < ->And->The weight factors of the eye basic training attachment index and the eyeball position deviation index of the set target person are respectively represented.
Specifically, the abnormal index of the eye dynamic mode data of the target person is analyzed and calculated, and the specific analysis process is as follows: extracting eye movement pattern reference data of a target person, wherein the eye movement pattern reference data is a pupil center point movement track reference line diagram of each eye, and extracting the length of the pupil center point movement track reference line diagram of each eye of the target person, and recording as。
Extracting a pupil center point movement track line diagram of each eye of a target person in a training light movement mode, respectively carrying out overlapping comparison with a pupil center point movement track reference line diagram of each eye of the target person, extracting the length of a line with the overlapping pupil center point movement track of each eye, and recording asFurther calculating the eye dynamic track superposition index of the target person, and calculating the formulaThe method comprises the following steps: />Wherein->Eye dynamic trajectory coincidence index of target person, < ->And the correction coefficient is the line length of the set eye dynamic track line graph superposition.
Positioning the target person to the positions of all track points from a pupil center point movement track line diagram of each eye of the target person in a training light movement mode, further recording line segments of intervals between two adjacent movement track points as movement track segments, counting the distance of each movement track segment of each eye of the target person, extracting the interval duration between the two adjacent movement track points, further extracting the movement speed of each movement track segment of each eye of the target person, and recording the movement speed as movement track segmentsAnd comparing with standard eyeball training speed in a database, thereby calculating eyeball dynamic training coincidence indexes of target personnel, wherein the calculation formula is as follows: />Wherein->Eye dynamic training compliance index for the target person, < +.>Represents the standard eye training speed, b represents the number of each motion trail segment, < >>M is the number of motion trail segments, +.>Representing the settingsAnd a correction factor corresponding to the eyeball movement speed.
In this embodiment, according to the formula, according to the distance between each motion track segment to which the pupil center point of each eye of the target person belongs and the duration of the interval between two adjacent motion track points: the "velocity is equal to the distance divided by the time" to calculate the motion velocity of each motion trajectory segment to which the pupil center point of each eye of the target person belongs.
Specifically, the abnormal index of the eye dynamic mode data of the target person is analyzed and calculated, and the specific calculation process is as follows: according to the eye dynamic track coincidence index of the target person and the eyeball dynamic training coincidence index of the target person, further analyzing and calculating an abnormal index of eye dynamic mode data of the target person, wherein the calculation formula is as follows:wherein->Abnormality index indicating the eye dynamic pattern data of the target person, +.>And->And respectively representing the set eye dynamic trajectory coincidence indexes of the target personnel and the correction factors corresponding to the eyeball dynamic training coincidence indexes of the target personnel.
Specifically, the eye anomaly coefficient of the target person is comprehensively calculated, and the specific process is as follows: according to the abnormality index of the eye static mode data of the target person and the abnormality index of the eye dynamic mode data of the target person, further comprehensively calculating the eye abnormality coefficient of the target person, wherein the calculation formula is as follows:wherein->Eye abnormality coefficient representing target person, +.>And->And the correction factors respectively represent the abnormality indexes of the set eye static mode data and the abnormality indexes of the eye dynamic mode data.
In this embodiment, by analyzing and calculating the abnormality index of the eye static mode data of the target person and the abnormality index of the eye dynamic mode data of the target person, the eye abnormal condition of the person can be reflected more accurately to perform detailed and in-place analysis, so that the dimensionality of data analysis is more diversified, and a more accurate data support basis is provided for judging the eye abnormal state of the user.
Specifically, screening the detection result of the target personnel and carrying out feedback prompt, wherein the specific process is as follows: and comparing the eye abnormal coefficient of the target person with a set eye abnormal coefficient threshold value, and when the eye abnormal coefficient of the target person exceeds the set eye abnormal coefficient threshold value, carrying out feedback prompt on the detection result of the target person.
In the embodiment, the abnormal condition of the target person is judged through the eye abnormal coefficient of the target person, and the eye abnormal condition is monitored and reminded in real time and reasonably fed back to adjust the advice, so that the target person can more effectively take preventive measures, and the eye health of the target person is greatly ensured
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not exhaustive or to limit the invention to the precise form 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 understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (10)
1. An intelligent detection method for abnormal eye movement of a training lamp user is characterized by comprising the following steps:
firstly, extracting and pre-analyzing basic information: extracting basic information of a target person, and analyzing to obtain an eye state representation value of the target person;
second step, screening reference comparison data: according to the eye state representation value of the target person, screening to obtain reference comparison data of the target person;
thirdly, training the data statistics of the lamp modes: counting eye data of a target person in a static mode and a dynamic mode of the training lamp, and marking the eye data of the target person in the static mode and the dynamic mode of the training lamp as eye static mode data and eye dynamic mode data in sequence;
fourth, extracting and analyzing static pattern data of eyes: extracting eye static mode data of a target person, and analyzing and calculating an abnormality index of the eye static mode data of the target person according to the eye static mode data;
fifthly, extracting and analyzing the dynamic model data of the eyes: extracting eye dynamic mode data of a target person, and analyzing and calculating an abnormality index of the eye dynamic mode data of the target person according to the eye dynamic mode data;
step six, dynamically feeding back and prompting abnormal eyes: according to the abnormal index of the eye static mode data of the target personnel and the abnormal index of the eye dynamic mode data, the eye abnormal coefficient of the target personnel is comprehensively calculated, and then the detection result of the target personnel is screened and feedback prompt is carried out.
2. The intelligent detection method for abnormal eye movement of a training light user according to claim 1, wherein the method comprises the following steps of: the eye state representation value of the target person is obtained through analysis, and the specific process is as follows:
according to basic information of a target person, wherein the basic information comprises age, binocular vision difference, binocular average vision and eye history illness information, the eye history illness information comprises: name and duration of each history ocular disease;
according to the ages of the target personnel, further comparing the binocular reference allowable vision difference, the binocular reference healthy average vision and the characterization factors of the unit duration corresponding to various eye diseases stored in the database, obtaining the binocular reference allowable vision difference, the binocular reference healthy average vision and the characterization factors of the unit duration corresponding to various historical eye diseases corresponding to the target personnel, and calculating to obtain the eye state characterization value of the target personnel, wherein the calculation formula is as follows:wherein->Representing an eye state representation value of the target person, < +.>、And->Respectively representing binocular vision difference, binocular average vision and c time duration of historical eye disease of target person,/->、/>And->Characterization factors respectively representing binocular reference allowable vision difference, binocular reference healthy average vision and unit duration corresponding to the c-th historical eye disease of target personnel, c represents the number of each historical eye disease name, and +.>K is the total number of historic eye diseases, +.>And->The set binocular vision difference and the set binocular average vision corresponding weight factors are respectively represented, and e represents a natural constant.
3. The intelligent detection method for abnormal eye movement of a training light user according to claim 1, wherein the method comprises the following steps of: the screening is carried out to obtain reference comparison data of target personnel, and the specific process is as follows:
according to the age and eye state representation values of the target person, further matching with reference eye data corresponding to the eye state representation value ranges of the persons in each age interval stored in the database, and further obtaining reference eye data of the target person, wherein the reference eye data comprises eye static mode reference data and eye movement mode reference data.
4. The intelligent detection method for abnormal eye movement of a training light user according to claim 1, wherein the method comprises the following steps of: the eye data of the statistics target personnel in the static mode and the dynamic mode of the training lamp comprises the following specific processes:
(1) The eye data of the target personnel in the static mode of the training lamp are counted, and the method specifically comprises the following steps: the training light is controlled in a static mode by setting training brightness, eye data of a target person in the static mode of the training light are monitored and counted, and accordingly the eye data of the target person in the static mode of the training light are marked as eye static mode data, wherein the eye static mode data comprise: blink frequency, eye opening duration, initial training positions corresponding to pupil center points of eyes and eye movement positions of eyes;
(2) The eye data of the target personnel under the training lamp movement mode is counted, and the method specifically comprises the following steps: and controlling the movement mode of the training lamp according to the set training brightness, acquiring training time length corresponding to the movement mode of the training lamp, and dividing the training time length into various training monitoring time points according to the set number, so as to monitor and count the pupil center point positions of various eyes of a target person in various training monitoring time points, constructing a pupil center point movement track line diagram of various eyes of the target person in the movement mode of the training lamp, taking the pupil center point movement track line diagram as eye data of the target person in the movement mode of the training lamp, and marking the eye movement track line diagram as eye movement mode data of the target person.
5. The intelligent detection method for abnormal eye movement of a training light user according to claim 1, wherein the method comprises the following steps of: the analysis and calculation target personnel's eye static mode data belong to abnormal index, its concrete analysis process is:
extracting blink frequency and eye opening duration of a target person in a training lamp static mode, and further according to eye static mode reference data of the target person, wherein the eye static mode reference data comprise reference blink frequency and eye opening duration, so that an eye basic training fitting index of the target person is analyzed and calculated, and a calculation formula is as follows:wherein->An eye basic training fitting index representing the target person, < ->、/>Respectively indicating a reference blink frequency and a reference eye-opening duration of the target person, < >>And->Respectively indicating blink frequency and eye opening duration of the target person in the training light static mode, +.>And->Correction factors respectively representing the set blink frequency and the eye opening duration;
according to the initial training position and each eye movement position corresponding to the pupil center point of each eye of the target person, further extracting and obtaining each pupil center point offset of each eye of the target person, and calculating the eyeball position offset index of the target person, wherein the calculation formula is as follows:wherein->An eyeball position deviation index representing a target person,represents the jth pupil center point offset of the r eye of the target person, r=a or B, where a and B represent the left and right eyes, respectively, of the target person, and->To be set upThe deviation evaluation factor corresponding to the unit deviation amount of the pupil center point of the eyeball, j represents the number of the deviation of the pupil center point of each time, g represents the total number of the deviation of the pupil center point and +.>A correction factor indicating the eyeball position deviation index of the set target person.
6. The intelligent detection method for abnormal eye movement of a training light user according to claim 5, wherein the method comprises the following steps: the analysis and calculation target personnel eye static mode data belong to abnormal indexes, and the specific calculation process comprises the following steps:
according to the eye basic training attachment index and the eyeball position deviation index of the target person, further calculating to obtain an eye static training abnormal index of the target person, wherein the calculation formula is as follows:wherein->Eye static training abnormality index indicating target person, < ->And->The weight factors of the eye basic training attachment index and the eyeball position deviation index of the set target person are respectively represented.
7. The intelligent detection method for abnormal eye movement of a training light user according to claim 1, wherein the method comprises the following steps of: the analysis and calculation target personnel eye dynamic mode data belong to abnormal indexes, and the specific analysis process comprises the following steps:
extracting eye movement pattern reference data of a target person, wherein the eye movement pattern reference data is pupil center point movement track parameters of each eyeTaking the line graph, extracting the movement track of the pupil center point of each eye of the target person, referring to the length of the line graph, and marking as；
Extracting pupil center point movement track line diagrams of eyes of a target person in a training light movement mode, respectively carrying out overlapping comparison with pupil center point movement track reference line diagrams of the eyes of the target person, extracting line lengths of overlapping pupil center point movement tracks of the eyes, and recording asFurther, calculating an eye dynamic track superposition index of the target person, wherein the calculation formula is as follows: />Wherein->Eye dynamic trajectory coincidence index of target person, < ->The correction coefficient is the line length of the set eye dynamic track line graph superposition;
positioning the target person to the positions of all track points from a pupil center point movement track line diagram of each eye of the target person in a training light movement mode, further recording line segments of intervals between two adjacent movement track points as movement track segments, counting the distance of each movement track segment of each eye of the target person, extracting the interval duration between the two adjacent movement track points, further extracting the movement speed of each movement track segment of each eye of the target person, and recording the movement speed as movement track segmentsComparing with standard eyeball training speed in a database, thereby calculating eyeball dynamic training coincidence finger of target personnelThe number is calculated by the following formula: />Wherein->Eye dynamic training compliance index for the target person, < +.>Represents the standard eye training speed, b represents the number of each motion trail segment, < >>M is the number of motion trail segments, +.>The correction factor corresponding to the set eyeball movement speed is indicated.
8. The intelligent detection method for abnormal eye movement of a training light user according to claim 7, wherein the method comprises the following steps: the analysis and calculation target personnel eye dynamic mode data belong to abnormal indexes, and the specific calculation process comprises the following steps:
according to the eye dynamic track coincidence index of the target person and the eyeball dynamic training coincidence index of the target person, further analyzing and calculating an abnormal index of eye dynamic mode data of the target person, wherein the calculation formula is as follows:wherein->Abnormality index indicating the eye dynamic pattern data of the target person, +.>And->And respectively representing the set eye dynamic trajectory coincidence indexes of the target personnel and the correction factors corresponding to the eyeball dynamic training coincidence indexes of the target personnel.
9. The intelligent detection method for abnormal eye movement of a training light user according to claim 8, wherein the method comprises the following steps: the eye anomaly coefficient of the target person is comprehensively calculated, and the specific process is as follows:
according to the abnormality index of the eye static mode data of the target person and the abnormality index of the eye dynamic mode data of the target person, further comprehensively calculating the eye abnormality coefficient of the target person, wherein the calculation formula is as follows:wherein->Eye abnormality coefficient representing target person, +.>And->And the correction factors respectively represent the abnormality indexes of the set eye static mode data and the abnormality indexes of the eye dynamic mode data.
10. The intelligent detection method for abnormal eye movement of a training light user according to claim 9, wherein the method comprises the following steps: the detection result of the screening target personnel is fed back for prompting, and the specific process is as follows:
and comparing the eye abnormal coefficient of the target person with a set eye abnormal coefficient threshold value, and when the eye abnormal coefficient of the target person is higher than the set eye abnormal coefficient threshold value, carrying out feedback prompt on the detection result of the target person.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310910047.0A CN116936097A (en) | 2023-07-24 | 2023-07-24 | Training lamp user eye abnormal movement intelligent detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310910047.0A CN116936097A (en) | 2023-07-24 | 2023-07-24 | Training lamp user eye abnormal movement intelligent detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116936097A true CN116936097A (en) | 2023-10-24 |
Family
ID=88376927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310910047.0A Pending CN116936097A (en) | 2023-07-24 | 2023-07-24 | Training lamp user eye abnormal movement intelligent detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116936097A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5684562A (en) * | 1994-12-12 | 1997-11-04 | Nidek Company, Ltd. | Ophthalmic apparatus |
| CN107680683A (en) * | 2017-10-09 | 2018-02-09 | 上海睦清视觉科技有限公司 | A kind of AI eye healths appraisal procedure |
| US20190238581A1 (en) * | 2017-07-06 | 2019-08-01 | Zhongan Information Technology Service Co., Ltd. | Method, apparatus and system for detecting abnormal behavior of user |
| CN112907635A (en) * | 2021-03-22 | 2021-06-04 | 东南大学 | Method for extracting eye abnormal motion characteristics based on geometric analysis |
| CN113181016A (en) * | 2021-05-13 | 2021-07-30 | 云南白药集团无锡药业有限公司 | Eye adjustment training lamp with dynamically-changed illumination |
| CN113208884A (en) * | 2021-01-08 | 2021-08-06 | 上海青研科技有限公司 | Visual detection and visual training equipment |
-
2023
- 2023-07-24 CN CN202310910047.0A patent/CN116936097A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5684562A (en) * | 1994-12-12 | 1997-11-04 | Nidek Company, Ltd. | Ophthalmic apparatus |
| US20190238581A1 (en) * | 2017-07-06 | 2019-08-01 | Zhongan Information Technology Service Co., Ltd. | Method, apparatus and system for detecting abnormal behavior of user |
| CN107680683A (en) * | 2017-10-09 | 2018-02-09 | 上海睦清视觉科技有限公司 | A kind of AI eye healths appraisal procedure |
| CN113208884A (en) * | 2021-01-08 | 2021-08-06 | 上海青研科技有限公司 | Visual detection and visual training equipment |
| CN112907635A (en) * | 2021-03-22 | 2021-06-04 | 东南大学 | Method for extracting eye abnormal motion characteristics based on geometric analysis |
| CN113181016A (en) * | 2021-05-13 | 2021-07-30 | 云南白药集团无锡药业有限公司 | Eye adjustment training lamp with dynamically-changed illumination |
Non-Patent Citations (1)
| Title |
|---|
| ZHIWEI ZHU等: "Real-Time Eye Detection and Tracking under Various Light Conditions", 《DATA SCIENCE JOURNAL》, no. 6, 30 September 2007 (2007-09-30), pages 1 - 6 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102056541B (en) | Detection of hypokinetic and/or hyperkinetic states | |
| EP3783619A1 (en) | Human body health assessment method and system based on sleep big data | |
| WO2018127506A1 (en) | Apparatus and method for triggering a fall risk alert to a person | |
| CN111345823B (en) | Remote exercise rehabilitation method, device and computer readable storage medium | |
| CN111528842A (en) | Quantitative assessment method for Parkinson disease symptoms based on physiological and behavioral indexes | |
| CN111281361A (en) | Student health monitoring system based on big data | |
| CN114068042A (en) | Health management platform and management method based on wearable intelligent terminal | |
| CN114334158B (en) | Monitoring management method and system based on Internet of things | |
| CN104586402A (en) | Feature extracting method for body activities | |
| CN111931568A (en) | Human body falling detection method and system based on enhanced learning | |
| CN111916179A (en) | Method for carrying out 'customized' diet nourishing model based on artificial intelligence self-adaption individual physical sign | |
| CN109300546A (en) | A kind of individual sub-health state appraisal procedure based on big data and artificial intelligence | |
| CN116936097A (en) | Training lamp user eye abnormal movement intelligent detection method | |
| CN112741943B (en) | Sleep-aiding system with sleep stability decision principle database | |
| CA2912162C (en) | Method and apparatus for characteristic monitoring in conjunction with a mode of continuously measured blood glucose values and computer program product | |
| CN109620263B (en) | Physical sign safety analysis method for post workers in enterprises and public institutions | |
| EP3425637B1 (en) | Electronic system and method for classifying a physiological state | |
| CN116403670A (en) | Intelligent monitoring management method and system for postoperative care training | |
| CN114470719B (en) | Full-automatic posture correction training method and system | |
| CN115067934A (en) | Hand motion function analysis system based on machine intelligence | |
| CN115547449A (en) | Method for improving visual function performance of adult amblyopia patient based on visual training | |
| CN113080945A (en) | Parkinson patient disease monitoring method and system | |
| CN115223232A (en) | Eye health comprehensive management system | |
| CN114202772A (en) | Reference information generation system and method based on artificial intelligence and intelligent medical treatment | |
| CN106725364B (en) | Controller fatigue detection method and system based on probability statistical 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 |