A method and device for providing automatic prediction of changes in the fatigue state of a person performing visual tasks.

Abstract

This computer-implemented method for providing an automated prediction of a change in fatigue state of a subject performing a visual task involving any type of visual content includes providing a plurality of input data about the subject to a fatigue state change prediction model, the plurality of input data including at least one subjective measure about the subject, and / or at least one objective measure about the subject, and / or at least one other subject-related data; and obtaining, by a processor implementing the model, a value representing a level of change in the subject's fatigue state.

Description

Technical Field

[0001] The present disclosure relates to a method and a device for automatically predicting changes in the fatigue state of a subject performing a visual task.

[0002] The present disclosure also relates to a related ophthalmoscope, a computer program product, and a mobile terminal, as well as a corresponding method for providing an individual prescription of anti-fatigue optical articles to a subject.

Background Art

[0003] Visual fatigue and the terms "computer vision syndrome" and "digital eye strain" are often used interchangeably to describe complex eye and vision-related problems resulting from prolonged near-vision tasks on digital devices such as computers, tablets, mobile phones, e-book readers, etc.

[0004] More generally, prolonged visual tasks can also lead to other types of fatigue as follows: - Cognitive fatigue, i.e., brain fatigue manifested, for example, by changes in attention level or reading speed, - General fatigue, such as drowsiness and a general feeling of fatigue, - Muscle fatigue, such as neck pain from maintaining the same posture for a long time, - Driver fatigue, etc.

[0005] Due to modern lifestyles, the use of digital devices and the spread of such types of fatigue have increased very significantly and dramatically over the past 20 years.

[0006] Regarding visual fatigue, two official definitions are presented below. - The World Health Organization defines visual fatigue as a subjective visual impairment (ICD-10, H53.1), typically manifested by a high level of visual discomfort that occurs after prolonged visual activity and is characterized by fatigue, pain around the eyes, blurred vision, and headache. The American Optometry Association defines visual fatigue as the aforementioned Computer Vision Syndrome, which describes a group of eye and vision-related problems resulting from prolonged use of computers, tablets, e-readers, and mobile phones.

[0007] The symptoms, assessment methods, and management strategies for visual fatigue are attracting significant attention in the research and medical communities. Symptoms can be caused by insufficient lighting, glare from digital screens, inappropriate viewing distance, prolonged work, warning levels, reduced light spectrum, decreased contrast, small fonts, and uncorrected visual impairment.

[0008] Methods for evaluating visual fatigue can be classified as subjective or objective.

[0009] For subjective assessment, questionnaires can be used. Most commonly used questionnaires are symptom-based, such as the Visual Discomfort Scale (Conlon, Lovegrove, Chekaluk & Pattison, 1999, available at https: / / www.tandfonline.com / doi / abs / 10.1080 / 135062899394885), the 10-item Visual Fatigue Questionnaire (Hayes, Sheedy, Stelmack & Heaney, 2007, available at https: / / www.researchgate.net / publication / 6140024_Computer_Use_Symptoms_and_Quality_of_Life), and the Convergence-and-Symptom Survey (CISS) (available at https: / / wowvision.net / wp-content / uploads / 2014 / 08 / CI-Screening-and-symptom-survey.pdf).

[0010] For objective evaluation, minute fluctuations in accommodation may be monitored because they can sometimes be found to increase after prolonged visual work. Several studies have evaluated accommodative response or accommodative delay after inducing visual discomfort, but no consistent changes were observed in these parameters after prolonged visual work. Convergence dynamics, associated strabismus, and convergence near point were found to change after close-range computer work. Blinking patterns were found to show a decrease in blink rate, an increase in blink duration, and an increase in incomplete blinks. Changes in pupil diameter, increased pupillary minute fluctuations, and increased pupillary reflexes were also identified as potential indicators of visual fatigue. Critical flicker fusion frequency (CFFF) was found to decrease with workload.

[0011] However, CFFF is influenced by various factors (age, refractive errors, activity level, fasting, circadian rhythm, etc.) and varies depending on the type of display, work, lighting, and working distance. Therefore, CFFF cannot be treated as an absolute indicator of visual fatigue.

[0012] In addition, many of the above parameters are also affected by general fatigue and / or cognitive fatigue.

[0013] Therefore, not only is it difficult to objectively and accurately measure and evaluate visual fatigue itself, but there are also no generally accepted, reliable, objective measurement criteria or indicators for visual fatigue in this field.

[0014] Furthermore, it takes a long time, for example more than an hour, to cause visual fatigue.

[0015] Therefore, it is not appropriate to build tools to induce and measure visual fatigue in "real-world" scenarios such as inside a store.

[0016] Furthermore, the most well-known methods for calculating and predicting visual fatigue levels relate to viewing stereoscopic images, videos, or virtual reality content, but these are limited to specific types of visual content and are not suitable for all types of visual work. Other known methods are simply based on images of the eyes (open or closed). These methods do not take other input data into consideration.

[0017] Chinese Patent No. 107468206A discloses a method for predicting visual fatigue from viewing stereoscopic content based on pupil diameter. Two models are described: one that predicts subjective visual fatigue levels, and another that predicts objective visual fatigue based solely on pupil diameter (i.e., predicting pupil diameter) after viewing stereoscopic content. Both models use a multiple regression algorithm. Factors include maximum disparity, refresh rate, ambient brightness, viewing angle, and observer's age. The output of the subjective model is the result of a visual fatigue questionnaire. The output of the objective model is pupil diameter.

[0018] Such solutions are limited to viewing three-dimensional content. Furthermore, the input data includes content and environmental parameters, as well as the subject's age, but does not consider objective parameters such as pupil size. Pupil diameter is used as an output, but not as input to the objective model. Moreover, the solution becomes complex because objective and subjective predictions reside in separate models.

[0019] Furthermore, conventional solutions merely focus on predicting and / or evaluating visual syndromes. They do not enable the prediction of changes in visual fatigue, such as its increase.

[0020] Therefore, the need for a tool that can quickly and easily predict changes, such as an increase in the level of visual fatigue, for all types of visual tasks without causing visual fatigue itself remains unmet. [Overview of the project]

Problems to be Solved by the Invention

[0021] An object of the present disclosure is to overcome at least some of the above limitations of the prior art and to meet the above needs.

Means for Solving the Problems

[0022] For that purpose, the present disclosure provides a computer-implemented method that provides an automatic prediction of changes in the fatigue state of a subject who performs a visual task related to any type of visual content, providing a plurality of input data related to the subject to a fatigue state change prediction model, wherein the plurality of input data includes at least one subjective measurement value related to the subject, and / or at least one objective measurement value related to the subject, and / or at least one other subject-related data, obtaining a value representing the level of change in the fatigue state of the subject by a processor implementing the model, including.

[0023] Thus, various types of data, probably including both subjective and objective measurements, are considered, and the change in the visual fatigue level is predicted, whether it is a typical digital near-work or any other visual task.

[0024] In addition, this method is simple and fast, and for example, it may not take even 5 minutes to obtain a value representing the level of change in the fatigue state of the target individual.

[0025] The method according to the present disclosure not only saves time, improves the accuracy of prediction, simplifies the process, but also enables many types of prevention and mitigation functions.

[0026] Furthermore, the proposed model makes it possible to predict how likely a person is to get tired without having to perform a long-term task to actually induce visual fatigue.

[0027] The model input data consists of measurements that can be taken in-store and can be completed in a very short time, such as 1-2 minutes.

[0028] In addition, the system instantly generates output from a model representing the level of change in the individual's fatigue state, allowing people to be classified into various levels of "fatigue." This enables the system to recommend that individuals purchase anti-fatigue products that are appropriate for them.

[0029] In other words, for the same purpose, this disclosure also proposes a method for providing individuals with anti-fatigue optical articles, and this method is To obtain an automated prediction of changes in fatigue levels of subjects performing visual tasks involving any type of visual content, Providing multiple input data about a subject to a fatigue state change prediction model, wherein the multiple input data includes at least one subjective measurement about the subject, and / or at least one objective measurement about the subject, and / or at least one other subject-related data. The processor implementing the model obtains a value representing the level of change in the subject's fatigue state, To provide subjects with anti-fatigue optical articles that implement a formulation suited to a value representing the level of change in the subject's fatigue state, Includes.

[0030] For the same purpose, the disclosure also provides a device for providing an automatic prediction of changes in fatigue levels of an object performing visual tasks involving any type of visual content, A measurement unit adapted to provide measurement input data including at least one subjective measurement and / or at least one objective measurement of a subject, A processing unit adapted to implement a fatigue state change prediction model using measured value input data and / or at least one other subject-related data to obtain a value representing the level of change in the subject's fatigue state, A data input unit adapted to acquire measurement input data from a measurement unit and / or to acquire at least one other subject-related data, wherein the data input unit is adapted to input the measurement input data and / or at least one other subject-related data to a processing unit to allow the processing unit to implement a model. A data output unit adapted to output a value representing the level of change in the subject's fatigue state, We provide a device that includes the following features.

[0031] For the same purpose, the Disclosure further provides an optometrist comprising at least one device for providing an automated prediction of changes in fatigue levels of an subject performing visual tasks involving any type of visual content, the at least one device being A measurement unit adapted to provide measurement input data including at least one subjective measurement and / or at least one objective measurement of a subject, A processing unit adapted to implement a fatigue state change prediction model using measured value input data and / or at least one other subject-related data to obtain a value representing the level of change in the subject's fatigue state, A data input unit adapted to acquire measurement input data from a measurement unit and / or to acquire at least one other subject-related data, wherein the data input unit is adapted to input the measurement input data and / or at least one other subject-related data to a processing unit to allow the processing unit to implement a model. A data output unit adapted to output a value representing the level of change in the subject's fatigue state, It is equipped with.

[0032] For the same purpose, the Disclosure further provides a computer program product that, when executed by a processor, causes the processor to obtain a value representing a level of change in the fatigue state of a subject performing visual work involving any type of visual content, based on at least one subjective measurement of the subject and / or at least one objective measurement of the subject and / or at least one other subject-related data provided as input data to the model, by using a fatigue state change prediction model.

[0033] For the same purpose, the Disclosure further provides a mobile terminal comprising a processor and a data storage unit, the data storage unit including instructions, when executed by the processor, causing the processor to obtain a value representing a level of change in the fatigue state of a subject performing visual work involving any kind of visual content, based on at least one subjective measurement of a subject and / or at least one objective measurement of a subject and / or at least one other subject-related data provided as input data to the model, by using a fatigue state change prediction model.

[0034] According to the methods, devices, machines, computer program products, or mobile terminals described above, and the specific possible functions that can be used in any combination or individually, At least one subjective measurement may include data representing at least one response from the subject to at least one question related to the subject's visual acuity. The state of fatigue may also be a state of visual fatigue. At least one objective measurement may include at least one pupil and / or gaze measurement performed on the subject. Each of the multiple input data, which are measurement value input data, may include at least one subjective and / or objective ophthalmoscopic measurement value related to the subject. The model may be stored in the cloud, and the step of obtaining a value representing the level of change in the subject's fatigue state by the processor implementing the model may also be performed in the cloud. The processor may be located in the cloud. Predictive models may use machine learning. The predictive model may use a classification algorithm, and / or the values ​​representing the level of change in fatigue status may be discrete values. The predictive model may use a regression algorithm, and / or the values ​​representing the level of change in fatigue status may be continuous values. The predictive model may be a machine learning-based predictive model.

[0035] As a method for providing individualized prescriptions of anti-fatigue optical articles to subjects, and as a device for providing automatic prediction of changes in the subject's fatigue state, the optometry machine, computer program product, and mobile terminal briefly described above have the same advantages as the method for providing automatic prediction of changes in the subject's fatigue, but those advantages will not be repeated here.

[0036] To better understand the descriptions and advantages provided herein, refer here to the following brief descriptions in relation to the accompanying drawings and detailed descriptions, where similar reference numbers represent similar parts. [Brief explanation of the drawing]

[0037] [Figure 1] This flowchart illustrates the steps of the method according to this disclosure, which provides automatic prediction of changes in the fatigue state of a subject performing a visual task in a specific embodiment. [Figure 2] This is a schematic diagram of a device according to the present disclosure for providing automatic prediction of changes in the fatigue state of a subject performing visual tasks in a specific embodiment. [Figure 3] This is a schematic diagram of an eye examination machine according to the present invention in a specific embodiment. [Figure 4] This is a schematic diagram of a mobile application implementing the method according to this disclosure in a specific embodiment. [Figure 5] This is a simplified flowchart of the method according to the present disclosure, which provides an individualized formulation of an anti-fatigue optical article to a subject in a particular embodiment. [Modes for carrying out the invention]

[0038] In the following description, the drawings are not necessarily to scale, and certain features may be shown in a generalized or schematic form for clarity and conciseness or for informational purposes. In addition, while the creation and use of various embodiments are discussed in detail below, it should be understood that many inventive concepts are provided that can be embodied in a variety of situations as described herein. The embodiments discussed herein are merely representative and do not limit the scope of this disclosure. It will also be apparent to those skilled in the art that all technical features defined in relation to a process can be replaced individually or in combination with those of a device, and conversely, all technical features related to a device can be replaced individually or in combination with those of a process, and that technical features of different embodiments can be interchanged or combined with those of other embodiments.

[0039] The terms “comprise” (and any of its grammatical variations such as “comprises” and “comprising”), “have” (and any of its grammatical variations such as “has” and “having”), “contain” (and any of its grammatical variations such as “contains” and “containing”), and “include” (and any of its grammatical variations such as “includes” and “including”) are open-ended linking verbs. They are used to specify the existence of a feature, integer, process or component, or a group thereof, but do not preclude the existence or addition of one or more other features, integers, processes or components, or groups thereof. As a result, a method or a process in a method that "comprises," "has," "contains," or "includes" one or more steps or elements has, but is not limited to having only, one or more of those steps or elements.

[0040] The optical articles of this disclosure comprise at least one ophthalmic lens or optical filter or optical glass or optical material suitable for human vision, for example, at least one ophthalmic lens or optical filter or optical film or patch intended to be fixed onto a substrate or optical glass or optical material intended for use in ophthalmic instruments for determining the visual acuity and / or refraction of an object, or any type of safety device, such as safety lenses or masks or shields, including safety glass or safety walls intended to face an individual's eye.

[0041] Optical articles can be implemented as eyewear devices having a frame that at least partially surrounds one or more ophthalmic lenses. In non-limiting examples, optical articles may be eyeglasses, sunglasses, safety goggles, sports goggles, contact lenses, intraocular implants, and active lenses having amplitude modulation such as polarizing lenses or phase modulation such as autofocus lenses.

[0042] At least one ophthalmic lens, optical glass, or optical material suitable for human vision can provide optical function to the user, i.e., the wearer of the lens.

[0043] These could be, for example, corrective lenses for treating nearsightedness, farsightedness, astigmatism, and / or presbyopia, i.e., spherical, cylindrical, and / or add-type refractive power lenses for users with refractive errors. Since the lenses may have a constant refractive power, they may provide refractive power in the same way as monofocal lenses, or they may be progressive lenses with variable refractive power.

[0044] In this disclosure, the term “visual fatigue” means any change in the level of visual fatigue that may occur in a person referred to in this disclosure as “Subject,” “Individual,” “User,” or “Wearer,” when he uses a digital device, or more generally, when he performs any type of visual work.

[0045] Figure 1 shows three main components of both the method and the functional device according to the present invention for providing automatic prediction of changes in the fatigue state of an object performing visual tasks in a particular embodiment.

[0046] As a non-limiting example, the fatigue state may be visual fatigue. Nevertheless, instead, as described above, it may be another type of fatigue (cognitive, general, muscular, driver fatigue, etc.).

[0047] Visual work can involve any type of visual content, such as visual content displayed on a screen, visual content available on paper, or visual content available in other ways in the environment in which the target audience views it.

[0048] As shown in Figure 1, this method includes step 10 of providing multiple input data 12 to a fatigue state change prediction model 14.

[0049] Input data 12 pertains to the subject, i.e., the person for whom automatic prediction of changes in fatigue status is desired. The input data may include the following: -One or more subjective measurements related to the subject16, and / or, -One or more objective measurements related to the subject18, and / or - One or more other data points about the subject.20

[0050] Subjective measurement values ​​16 differ from objective measurement values ​​18 depending on the measurement method.

[0051] Therefore, parameters of the same type (such as convergence near point, accommodation near point, and prism fusion range) can be subjective or objective depending on the acquisition method.

[0052] The subjective measurement 16 is an arbitrary result that depends at least in part on the subject's response and can be measured, for example, by a machine or an ophthalmologist.

[0053] Therefore, subjective measurements 16 may include data representing one or more responses made by the subject to one or more questions about the subject's vision. In non-limiting examples, questions may concern the subject's perception of visual fatigue, current and general levels of visual fatigue, etc. The CISS described above can be used as a general visual fatigue questionnaire. Any appropriate current visual fatigue questionnaire can be used.

[0054] Objective measurements 18 are arbitrary results obtained by a machine or ophthalmologist, for example, without using the subject's responses to questions asked by the machine or ophthalmologist.

[0055] Therefore, the objective measurement 18 may include one or more pupillary measurements or any other ophthalmic measurements performed on the subject by any appropriate means known in itself.

[0056] Pupil data includes, for example, pupil size, minute variations in pupil size, and changes in these.

[0057] Ophthalmic measurements are common measurements that can be performed by an optometrist in a clinic and include, in non-exclusive examples, visual acuity, spherical equivalence, near convergence point, near accommodation point, prism fusion range, and accommodative convergence / accommodative ratio.

[0058] Objective measurements 18 may include gaze measurements taken on a subject by any suitable means known in itself. For example, gaze measurements may include gaze stability and fixation drift, as well as blink-related measurements. They can be obtained in minutes and calculated using any eye-tracking device known in itself.

[0059] Gaze measurements can be used in place of or in addition to pupillary measurements.

[0060] Subjective and objective measurements can be taken simultaneously or separately. When they are taken simultaneously, this method is faster than when they are taken separately.

[0061] Other data about the subjects 20 include subject-related data other than measurement values, such as demographic data, gender, age, and ethnic data.

[0062] Multiple input data 12 may include one or more subjective optometric measurements related to the subject, such as subjective refraction, subjective methods for measuring accommodative near point, subjective convergence near point, prism fusion range, etc. More generally, measurements involved in the measurement process in which the subject is asked to report whether something is clearly visible are considered subjective optometric measurements.

[0063] Multiple input data 12 may include one or more objective optometric measurements related to the subject.

[0064] Any combination of any objective measurement values, any combination of any subjective measurement values, or any combination of any objective measurement value and any subjective measurement value is possible.

[0065] To improve model performance and expand the scenarios in which this method can be used, other types of data such as test time, content display, or posture can be added.

[0066] In addition, during step 10, which provides multiple input data 12, one or more subjective measurements 16 and one or more objective measurements 18 can be obtained simultaneously or separately.

[0067] Using all of the above types of measurements and subject-related data yields a more accurate and robust predictive model 14. However, it is not mandatory to use all of these measurements and data types. In fact, it may be possible to use fewer data types, which may be more practical but will result in lower performance. For example, even for users who do not have access to pupil measurement tools, changes in visual fatigue levels can be predicted using only subjective and ophthalmic data. The reliability and performance of the predictive model 14 will be lower than that of a complete model using all possible input data, but will remain higher than the chance level.

[0068] As a non-limiting example, the input data related to step 10 could be collected as follows: The above questionnaire is administered on a computer screen, and eye-tracking measurements are obtained simultaneously. Such questions can be completed in a short time, for example, within 3 minutes.

[0069] From eye-tracking data, pupillary parameters are calculated, including blink rate, minute variations in pupil size, minute variations in fixation shift, and fixation stability. In the next step of the analysis, gradients representing changes in each of these parameters during the questionnaire are calculated. Along with the questionnaire results and initial ophthalmic measurements, a predictive model14 is constructed to predict changes in the current subjective visual fatigue level as measured by the questionnaire results.

[0070] Step 10, which provides input data to the prediction model 14, is followed by step 11, in which a processor implementing the prediction model 14 obtains a value V representing the level of change in the subject's fatigue state.

[0071] The processor may use machine learning to implement the predictive model 14, but it is not required to do so.

[0072] The prediction model 14 can use a classification algorithm, and / or the value V can be a discrete value within a range from a given minimum value to a given maximum value.

[0073] As a variation, the predictive model 14 can use a regression algorithm, and / or the value V can be a continuous value. For example, multiple regression can be used.

[0074] The value V allows any user to be classified into a predetermined number of categories, for example, 3 to 5 categories, ranging from low to high visual fatigue.

[0075] In the above modification using a regression algorithm, the value V allows for classifying any user according to different levels of visual fatigue, for example, by comparing the value V with a value stored in a database.

[0076] In the above embodiments using the classification algorithm, the classification of users by different levels of visual fatigue is obtained directly as a result of the algorithm. Therefore, the method according to this disclosure can directly provide categories of visual fatigue levels.

[0077] In embodiments where machine learning is not used, the predictive model 14 can use, for example, a simple linear regression.

[0078] By applying appropriate weights (in the case of regression machine learning-based algorithms) or other types of coefficients favorably to each significant factor, the best set of parameters can be obtained that represents the largest portion of the total variability of the data.

[0079] Predictive models 14 may also be based on decision trees, random forests, support vector machines, neural networks, or the well-known open-source software library XGBoost. As a non-restrictive example, an XGBoost classifier was used to classify changes in visual fatigue into high and low, and the overall accuracy achieved, defined as the ratio of the number of correct predictions to the total number of input samples, was 73.91%.

[0080] In one embodiment, a method for providing automatic prediction of changes in fatigue status may further include the steps of storing a prediction model 14 in the cloud and performing a step 11 in the cloud to obtain a value representing the level of change in the fatigue status of the subject.

[0081] The method described herein may take several minutes, for example, about three minutes.

[0082] This predicts changes in the level of visual fatigue without actually inducing or causing visual fatigue or an increase in it.

[0083] Figure 2 shows a specific embodiment of the device 21 according to this disclosure for providing automatic prediction of changes in the fatigue state of a subject performing visual tasks.

[0084] As in the method described above, as a non-limiting example, the fatigue state considered by device 21 may be a state of visual fatigue. Nevertheless, instead, as described above, it may be another type of fatigue (cognitive, general, muscular, driver fatigue, etc.).

[0085] Similar to the method described above, the visual work considered by device 21 can involve any type of visual content, which may be, for example, visual content displayed on a screen, visual content available on paper, or visual content available in other ways in the environment in which the subject views.

[0086] As shown in Figure 2, the device 21 includes a measuring unit 22 adapted to provide measurement input data.

[0087] The measurement input data includes subjective measurement values ​​16 and / or objective measurement values ​​18 related to the subject.

[0088] Device 21 further includes a processing unit 26.

[0089] The processing unit 26 is adapted to implement a fatigue state change prediction model 14 using measurement input data and / or other data (single / multiple) 20 related to the subject, in order to obtain a value V representing the level of change in the subject's fatigue state. The processing unit 26 is also adapted to provide this value to the data output unit 28, which will be described later.

[0090] As described above: - The subjective measurements 16 provided by the measurement unit 22 may include data representing one or more responses made by the subject to one or more questions about the subject's vision. -The objective measurement values ​​18 provided by the measurement unit 22 may include one or more pupil measurement values ​​that are known in themselves and have been taken on the subject by any suitable means included in the measurement unit 22. -The objective measurement values ​​18 provided by the measurement unit 22 may include gaze measurements that are known in themselves and are taken on a subject by any appropriate means included in the measurement unit 22. - The gaze measurement can be used in place of, or in addition to, the pupil measurement. - The measurement input data 12 may include one or more subjective optometric measurement values ​​for the subject. - The measurement input data 12 may include one or more objective optometric measurement values ​​related to the subject. - Any combination of any objective measurement values, any combination of any subjective measurement values, or any combination of any objective measurement value and any subjective measurement value is possible. - The processing unit 26 may use machine learning to implement the predictive model 14, but it is not required to do so. - Predictive model 14 can use a classification algorithm, and / or the value V can be a discrete value. -As a variation, the predictive model 14 can use a regression algorithm, and / or the value V can be a continuous value.

[0091] Device 21 further comprises a data input unit 24.

[0092] The data input unit 24 is adapted to acquire measurement input data from the measurement unit 22 and / or to acquire other data (single / multiple) 20 about the subject. The data input unit 24 is also adapted to input multiple input data 12, namely measurement input data 16, 18 and / or other data (single / multiple) 20 about the subject, to the processing unit 26 to implement the fatigue state change prediction model 14.

[0093] The device 21 further comprises the aforementioned data output unit 28, which is adapted to output a value V representing the level of change in the subject's fatigue state.

[0094] In one embodiment, the processing unit 26 can be located in the cloud, and therefore the predictive model 14 is implemented in the cloud.

[0095] In such an embodiment, the device 21 further comprises a communication unit (not shown in Figure 2) adapted to communicate with the cloud. For example, the above value V is received from the cloud via the communication unit.

[0096] Each method or device according to the present invention may be integrated and implemented in a multifunctional ophthalmometer comprising at least one of the above-described devices.

[0097] Figure 3 shows an embodiment of such an eye examination device according to the present disclosure.

[0098] In a specific embodiment shown in Figure 3, the predictive model 14 is implemented in the multi-functional ophthalmic machine 30.

[0099] Machine 30 measures three types of input data, including questionnaire responses, pupil data from a built-in eye tracker, and other ophthalmic parameters.

[0100] Machine 30 includes the following: - A display unit 32, for example, a digital screen, for displaying a visual fatigue questionnaire and presenting test results. - A data entry unit 34 that records user responses to questionnaires and general information. - An eye-tracking unit 36 ​​that measures the user's pupil size and gaze parameters. -Data storage unit 38. - A central processing unit (CPU) 40 that calculates visual fatigue using a predictive model 14 preloaded onto machine 30 and manages all functions. - An optional data communication / transmission unit 42 that uploads data to the cloud and receives results regarding visual fatigue from the cloud. - A set of 44 units for collecting other optometric parameters.

[0101] Non-limiting exemplary scenarios for the practical use of the optometry machine 30 are as follows:

[0102] A customer enters an optician's shop. If, while waiting for the next available optometrist or salesperson to serve them, or during conversation, the customer expresses concerns, complaints, or interest regarding eye strain, or if their profile fits the description of a "heavy digital user / worker," the customer may be guided to undergo an eye strain test using the optometrist 30.

[0103] This test typically takes less than three minutes and collects data on responses to a subjective visual fatigue questionnaire, as well as pupil measurement using a built-in eye tracker. Machine 30 is also used to perform other ophthalmic measurements.

[0104] Next, the CPU 40 uses the prediction model 14 to perform calculations locally, or performs calculations remotely after the communication unit 42 uploads the data to the cloud, and receives the calculation results from the cloud.

[0105] The results of the visual fatigue test are displayed on the display unit 32 almost instantly.

[0106] As a non-limiting example, the results indicate that the customer has low, moderate, high, or very high levels of fatigue. Depending on the level of fatigue, an anti-fatigue product is recommended.

[0107] Thus, visual fatigue testing provides both customers and practitioners with knowledge about how susceptible customers are to visual fatigue when performing close-up digital tasks, and whether customers require anti-fatigue products or other preventative measures to mitigate the situation.

[0108] As another non-exclusive illustrative scenario (not shown), a standalone visual fatigue toolbox implementing the predictive model 14 can be provided.

[0109] It may include the same units as described above for machine 30, except for set 44 of units.

[0110] In such cases, the practitioner needs to perform ophthalmic measurements using a separate machine and routine before entering the data into the toolbox's data entry unit 34. In such cases, the practitioner can, for example, enter the ophthalmic measurements into the system before or after the test.

[0111] The method described herein can be incorporated into a mobile application installed on a mobile device.

[0112] In such embodiments, -Measurements can be obtained using a mobile device. -Data entry can be performed using the interface of a mobile device, such as a keyboard, screen, or other input or display means. - The processing can be performed by the central processing unit (CPU) of the mobile device, which performs the calculations and predictions. - The display means on the mobile device can be used to show results and recommendations to the user.

[0113] The prediction model 14 can be pre-loaded on the mobile device or stored in the cloud. Accordingly, calculations can be performed locally on the mobile device or remotely in the cloud.

[0114] Figure 4 illustrates yet another non-limiting example in which the method according to this disclosure for providing automatic prediction of changes in the fatigue state of an object performing a visual task may be implemented in a mobile application and run on a digital device that implements the prediction model 14.

[0115] A functional unit or flow in a mobile application includes the following: -Block 46: Present a visual fatigue questionnaire on the device screen. -Block 48: Simultaneously, the device's camera records the pupil and provides a pupil / eye image 49. -Block 50: Present general information and questions regarding optometric measurements. This can be done from the beginning. -Block 52: Answer / input using the device's keyboard or touchscreen. -Block 54: Using the device's CPU, calculations including pupillary parameters and visual fatigue predictions are performed using the predictive model 14 preloaded into the mobile application, or, as a variation, data is uploaded to the cloud and the mobile device's communication unit is used to receive the results regarding visual fatigue from the cloud. -Block 56: Display the predicted value V on the device screen.

[0116] Practitioners can use a mobile application on their mobile device to input general information and optometrial data into the application.

[0117] As yet another example of using the methods described herein, for example, a simplified version of predictive model 14 could be used to make a website about visual fatigue accessible to users, allowing them to easily answer a visual fatigue questionnaire and input general information and optometric data.

[0118] This is a downgraded version of the previous example device or mobile application, intended for practitioners who may not necessarily have access to an eye-tracking optometrist or device, or the camera on their own mobile device, but who may use those mobile devices for pupil measurement.

[0119] This website retrieves data entered by the user, performs a simplified calculation of the visual fatigue level, and displays the results regarding the visual fatigue level and recommendations, similar to the previous example.

[0120] As yet another example, a simplified visual fatigue model could be used to make a website targeting visual fatigue accessible to users. In this model, users can answer a visual fatigue questionnaire and input general information as well as basic optometric data such as visual acuity and spherical equivalence.

[0121] This is a downgraded version of a previous example device or mobile application, intended for general consumers or the general public who do not have access to an eye-tracking machine or device, or the camera on their mobile device, and yet it can still be used for pupil measurement.

[0122] In this final example, the website retrieves data entered by the user, performs calculations using a more simplified version of the visual fatigue model, and displays the results regarding the visual fatigue level and recommendations, similar to the previous example.

[0123] Therefore, the methods described herein may be used in consumers' daily lives to monitor their general level of visual fatigue, send warnings about recent increases in visual fatigue, and recommend anti-fatigue practices and products.

[0124] By adding a pupil measurement monitoring function, it's possible to warn users about increased visual fatigue before it actually starts, prompting them to take a break.

[0125] Furthermore, it can help ophthalmologists identify patients with high levels of visual fatigue and prescribe treatment and products to improve their condition.

[0126] Furthermore, it can be used among children and teenagers during times when their nearsightedness is progressing to warn them about eye strain and excessive use of digital devices / close work, and to help control their nearsightedness.

[0127] Furthermore, by using a modified version of the model with the driver, fatigue from driving can be reduced and traffic safety improved by predicting and warning the driver before the increase in fatigue levels actually begins. Such a modified version may include, for example, a method of continuously, or at least regularly and frequently, monitoring the driver's pupils and gaze behavior.

[0128] Similarly, the methods described herein can be used in factory or other work environments where safety requirements are particularly high and fatigue levels are relevant.

[0129] In addition, the methods described herein can be used as a tool for filtering subjects for scientific or consumer research, to select or exclude specific subjects exhibiting high levels of visual fatigue, and to improve the quality of studies on populations in accordance with specific research objectives.

[0130] As shown in Figure 5, the method according to the present disclosure for providing a subject with an individualized formulation of an anti-fatigue optical article includes step 58 of obtaining an automatic prediction of changes in the fatigue state of a subject performing visual work involving any type of visual content, by performing the above steps of the method according to the present disclosure for providing an automatic prediction of changes in the subject's fatigue state, and step 60 of providing the subject with an anti-fatigue optical article that implements a formulation conforming to value V.

[0131] For example, fitting a prescription to a value V may involve relating the value V to the level of near-add power of the anti-fatigue lens, such that a higher value V corresponds to a higher near-add power.

[0132] As a non-limiting example, anti-fatigue products may be eyeglasses and / or contact lenses and / or eye drops and / or behavioral therapy and / or orthopedic sessions and / or any other suitable form.

[0133] The computer program product provided herein, when executed by a processor capable of operating as described above, includes instructions that cause the processor to obtain a value V by using the predictive model 14 based on at least one subjective measurement related to the subject and / or at least one objective measurement related to the subject and / or at least one other subject-related data provided as input data to the predictive model 14.

[0134] The mobile terminal according to this disclosure comprises a processor capable of operating as described above and a data storage unit. The data storage unit includes instructions that, when executed by the processor, cause the processor to obtain a value V by using the predictive model 14 based on at least one subjective measurement related to the subject and / or at least one objective measurement related to the subject and / or at least one other subject-related data provided as input data to the predictive model 14.

[0135] While typical methods and devices are described in detail herein, those skilled in the art will recognize that various substitutions and modifications may be made without departing from the scope described and defined by the appended claims.

Claims

1. A computer implementation method that provides automatic prediction of changes in the fatigue state of a subject performing visual tasks involving any type of visual content, Providing a fatigue state change prediction model with multiple input data relating to the subject, wherein the multiple input data includes at least one subjective measurement value relating to the subject, and / or at least one objective measurement value relating to the subject, and / or at least one other subject-related data, and the at least one subjective measurement value includes data representing at least one response by the subject to at least one question relating to the subject's vision. The processor implementing the aforementioned model obtains a value representing the level of change in the subject's fatigue state, Computer implementation methods, including those mentioned above.

2. The method according to claim 1, wherein the fatigue state is a visual fatigue state.

3. The method according to claim 1 or 2, wherein the at least one objective measurement includes at least one pupil and / or gaze measurement performed on the subject.

4. The method according to any one of claims 1 to 3, wherein the plurality of input data includes at least one subjective and / or objective optometric measurement value related to the subject.

5. The method according to any one of claims 1 to 4, further comprising storing the model in the cloud and performing the retrieval in the cloud.

6. A computer implementation method for determining the recommendation of an individual prescription for an anti-fatigue optical article according to the fatigue state of the subject, To obtain an automatic prediction of changes in the fatigue state of the subject performing visual tasks involving any type of visual content, Providing a fatigue state change prediction model with multiple input data relating to the subject, wherein the multiple input data includes at least one subjective measurement value relating to the subject, and / or at least one objective measurement value relating to the subject, and / or at least one other subject-related data, and the at least one subjective measurement value includes data representing at least one response by the subject to at least one question relating to the subject's vision. The processor implementing the aforementioned model obtains a value representing the level of change in the subject's fatigue state, The processor determines the recommendation for an anti-fatigue optical article that implements a formulation suitable for the value representing the level of change in the subject's fatigue state, Computer implementation methods, including those mentioned above.

7. A device for providing automatic prediction of changes in fatigue levels of a subject performing visual tasks involving any type of visual content, A measurement unit adapted to provide measurement input data including at least one subjective measurement and / or at least one objective measurement relating to the subject, wherein the at least one subjective measurement includes data representing at least one response by the subject to at least one question relating to the subject's vision, A processing unit adapted to implement a fatigue state change prediction model using the aforementioned measurement input data and / or at least one other subject-related data, and to obtain a value representing the level of change in the subject's fatigue state, A data input unit adapted to acquire the measurement input data from the measurement unit and / or to acquire the at least one other subject-related data, wherein the data input unit is adapted to input the measurement input data and / or the at least one other subject-related data to the processing unit to cause the processing unit to implement the model, A data output unit adapted to output a value representing the level of change in the fatigue state of the subject, A device equipped with the following features.

8. The device according to claim 7, wherein the fatigue state is a visual fatigue state.

9. The device according to claim 7, wherein the at least one objective measurement includes at least one pupil and / or gaze measurement performed on the subject.

10. The device according to any one of claims 7 to 9, wherein the measurement input data includes at least one subjective and / or objective ophthalmic measurement value related to the subject.

11. An eye examination machine comprising at least one device for providing automatic prediction of changes in the fatigue state of a subject performing visual tasks involving any type of visual content, the at least one device is A measurement unit adapted to provide measurement input data including at least one subjective measurement and / or at least one objective measurement relating to the subject, wherein the at least one subjective measurement includes data representing at least one response by the subject to at least one question relating to the subject's vision, A processing unit adapted to implement a fatigue state change prediction model using the aforementioned measurement input data and / or at least one other subject-related data, and to obtain a value representing the level of change in the subject's fatigue state, A data input unit adapted to acquire the measurement input data from the measurement unit and / or to acquire the at least one other subject-related data, wherein the data input unit is adapted to input the measurement input data and / or the at least one other subject-related data to the processing unit to cause the processing unit to implement the model, A data output unit adapted to output a value representing the level of change in the fatigue state of the subject, An eye examination machine equipped with the following features.

12. A computer program, when executed by a processor, includes instructions causing the processor to obtain a value representing a level of change in the fatigue state of a subject performing visual work involving any type of visual content, based on at least one subjective measurement of the subject and / or at least one objective measurement of the subject and / or at least one other subject-related data provided as input data to the model, wherein the at least one subjective measurement includes data representing at least one answer by the subject to at least one question concerning the subject's vision.

13. A mobile terminal comprising a processor and a data storage unit, wherein the data storage unit, when executed by the processor, includes an instruction causing the processor to obtain a value representing a level of change in the fatigue state of a subject performing visual work involving any type of visual content, based on at least one subjective measurement of a subject and / or at least one objective measurement of the subject and / or at least one other subject-related data provided as input data to the model, wherein the at least one subjective measurement includes data representing at least one answer by the subject to at least one question concerning the subject's vision.

Images