DESC:FORM 2

THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003

COMPLETE SPECIFICATION

(See Section 10 and Rule 13)

Title of invention:
A PERSONALIZED ALERT GENERATION SYSTEM AND METHOD FOR PREVENTING EAR DAMAGE USING DIGITAL EAR TWIN

APPLICANT:
ASKIM TECHNOLOGIES PRIVATE LIMITED
An Indian Entity having address as:
74, Alamanda, Glendale Complex,
Vasant Vihar, Thane(W) - 400610,
Maharashtra, India.

The following specification describes the invention and the manner in which it is to be performed.
CROSS-REFERENCE TO RELATED APPLICATIONS AND PRIORITY
The present application claims priority from an Indian Patent Application having application number 202021033491, filed on February 05, 2021, incorporated herein by a reference.
TECHNICAL FIELD
The present subject matter described herein, in general, relates to the field of alert generation. More particularly, the present disclosure relates to a personalized alert generation system and method for preventing ear damage. More precisely, the present subject matter discloses a personalized alert generation system and method for preventing ear damage using digital ear twin.
BACKGROUND
The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.
Conventionally, fatigue is a term used to describe an overall feeling of tiredness or lack of energy. It is something that every human being has experienced at some point in their life. Fatigue can be simply described as a feeling of tiredness or exhaustion, but there is no gold-standard definition to explain it accurately. However, fatigue can cause negative effects on the body, especially ear fatigue. Ear fatigue is not a clinical term, but it has been used by many professionals to describe tiredness, discomfort, pain, and loss of sensitivity of the ear due to prolonged exposure to auditory stimulus.
Recently, due to the increased use of smartphones, the popularity of truly wireless earphones has grown exponentially. The global earphones and headphones market size was valued at USD 25.1 billion in 2019 and is continually growing at a compound annual growth rate (CAGR) of 20.3% (2020 – 2027). Rising consumer preference for enhanced audio experience and growing music industry, coupled with mobile technology and internet penetration, are some of the primary factors driving the earphone market.
There is no doubt that earphones/headphones are popular. They are used by people of all ages, be it young or old, for listening music, consumption of media or for audio/video calling. Due to the current pandemic (COVID-19) situation, working from home is the new normal and using earphones/headphones for calls and meetings has become very common. Several large organizations have provided work from home as a permanent option for their employees. Currently, there are monitoring software for the use of screens to protect the eyes, however there is no similar software to protect one’s ears. Prolonged use of earphones/headphones causes serious issues related to the overall health of ears. Using earphones/headphones for long periods of time in use cases such as long meetings, watching movies without breaks, listening music at high volumes for longer periods are known to cause ear fatigue as well as ear infections.
Such ear fatigue issues primarily arise due to the following factors:
• Prolonged use of earphones/headphones at high decibels damages the inner ear hair irreversibly.
• Continuous coverage of ear results in perspiration inside the ear canal which may become an ideal condition for pathogens and result in ear infections.
Thus, there is an urgent need of a nudging/alerting system which alerts the user periodically based on his/her own digital ear twin or a threshold after which permanent damage occurs to an individual’s hearing.
SUMMARY
This summary is provided to introduce the concepts related to the field of alert generation, and more precisely, to a personalized alert generation system and method for preventing ear damage using a digital ear twin. This summary is not intended to identify essential features of the claimed subject matter, nor it is intended to use in determining or limiting the scope of claimed subject matter.
In an embodiment, a personalized alert generation system for preventing ear damage comprises an input module, a user profile selection module, a fatigue assessment module, a personalized model generation module, a personalized ear fatigue module, and a personalized alert generation module. The input module is configured to provide a generalized model, a metadata and ambient conditions as inputs, in which the metadata comprises metadata about a user, music and a wearable audio device. Further, the user profile selection module is configured for selection of a user profile based on the metadata, and the fatigue assessment module assess the effects of the wearable audio device on the user using a scientifically designed questionnaire. The personalized model generation module further generates a personalized model for ear fatigue as the output and the personalized ear fatigue module defines the threshold levels for ear fatigue. Furthermore, the personalized alert generation module generates custom alerts using pre-defined threshold levels for ear fatigue by the personalized ear fatigue module.
In another embodiment, a personalized alert generation method for preventing ear damage comprises the steps of: receiving, via an input module, a generalized model, a metadata and ambient conditions as inputs, in which the metadata comprises metadata about a user, music and a wearable audio device; user profile selection for selection of a user profile based on the metadata; fatigue assessment for assessing the effects of the wearable audio device on the user using a scientifically designed questionnaire; personalized model generation for generating a personalized model for ear fatigue as the output; personalized ear fatigue calculation for defining the threshold levels for ear fatigue; and personalized alert generation (260) for generating custom alerts using the pre-defined threshold levels for ear fatigue in the step of personalized ear fatigue calculation.
BRIEF DESCRIPTION OF DRAWINGS
The detailed description is described with reference to the accompanying figures. In the Figures, the left-most digit(s) of a reference number identifies the Figure in which the reference number first appears. The same numbers are used throughout the drawings to refer like features and components.
Figure 1 illustrates a generalized model generation method 100 for preventing ear damage, in accordance with an embodiment of a present subject matter.
Figure 2 illustrates a personalized alert generation method 200 for preventing ear damage, in accordance with an embodiment of a present subject matter.
Figure 3 illustrates a multimodal design 300 for a mobile application for issuing the personalised alerts to the user, in accordance with an embodiment of a present subject matter.
Figure 4 illustrates a block-diagram 400 for the system-on-a-chip hardware device running on an operating system like Linux, in accordance with an embodiment of a present subject matter.
Figure 5 illustrates a personalized alert generation system 500 for preventing ear damage, in accordance with an embodiment of a present subject matter
DETAILED DESCRIPTION
Reference throughout the specification to “various embodiments,” “some embodiments,” “one embodiment,” or “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases “in various embodiments,” “in some embodiments,” “in one embodiment,” or “in an embodiment” in places throughout the specification are not necessarily all referring to the same embodiment. Further, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments. The word like “earphones” may be used interchangeably with the words “headphones”, “wearable audio device”, “air-pods”, “earpiece”, “headset”, “earbuds” or the like, in the present disclosure.
The present subject matter described herein, in general, relates to a personalized alert generation system and method for preventing ear damage using digital ear twin. The personalized alert generation system and method for preventing ear damage comprises an input module, an earphone identification module, a user data storage module, a machine learning module comprising a user profile selection module, a fatigue assessment module, a generalized model generation module, a personalized model generation module, a personalized ear fatigue module, and a personalized alert generation module, a control module and a smartphone sync module. The input module provides, in a receiving step, a generalized model generated from the generalized model generation module, a metadata and ambient conditions as inputs. Further, the user profile selection module selects a user profile based on the metadata, and the fatigue assessment module assess the effects of the wearable audio device on the user using a scientifically designed questionnaire. The personalized model generation module further generates a personalized model for ear fatigue as the output based on the received inputs and the generalized model. and the personalized ear fatigue module defines the threshold levels for ear fatigue. The personalized alert generation module generates custom alerts using pre-defined threshold levels for ear fatigue by the personalized ear fatigue module.
Hereinafter, a personalized alert generation system and a personalized alert generation method for preventing ear damage, according to an exemplary form of the present disclosure, will be described in detail with reference to the drawings.
In one embodiment, referring to Figure 1, a generalized model generation method 100 for preventing ear damage is illustrated. The generalized model generation method 100 comprises the steps of receiving 110 the inputs, testing 120 a wearable audio device, fatigue assessment 130, and generalized model generation 140. The receiving step 110, comprises receiving an audio input 111 and a metadata 112 as inputs, via an input module 560. The audio input 111 contains controlled audio inputs and the metadata 112 contains the metadata of music and the wearable audio device as the input for the fatigue assessment 130 as the next step. Further, the step of testing 120 is aimed at testing the wearable audio device using a number of people as a plurality of test volunteers, comprising the use of various makes and models of the earphones with different test volunteers with music of various genres at varying volumes as a test study. This test study may be conducted as a number of sessions with the plurality of test volunteers and at the end of each session, the test volunteers are asked to answer a scientifically designed questionnaire. These answers along with the earphone metadata is fed as an input 110 in the machine learning module 530 incorporating I/O capability and AI capability. Further, the step of fatigue assessment 130 assesses the effects of the wearable audio device (earphone) on the plurality of test volunteers using the scientifically designed questionnaire, and then the step of generalized model generation 140 generates a generalized model 211 for ear fatigue as the output by analyzing the answers to the scientifically designed questionnaire using the steps of fatigue assessment 130 and receiving 110 the inputs, and the generalized model generation method 100 for preventing ear damage ends at the step 150. Further, the scientifically designed questionnaire may be formed in consultation with an ENT specialist or the like. The generalized model 211 may interchangeably be termed as a generic ear fatigue model.
Further, the generalized model 211 may be generated using the following input methodology:
? Selecting the top five popular earphones as per the user perspective and the earphone market evaluation.
? Performing a trial of these earphones on the test volunteers for a pre-defined amount of time with specific content (content for calibration).
? Receiving feedback as answers to a fatigue based questionnaire (scientific questionnaire).
? A generic/generalized model creation for that specific earphone type.
The aforementioned methodology may be repeated for optimum understanding of the earphones and the user depending on the make and model and the test volunteers’ feedback.
In another embodiment, as illustrated in Figure 2, a personalized alert generation method 200 for preventing ear damage comprises the steps of: receiving 210 the inputs, user profile selection 220, fatigue assessment 230, personalized model generation 240, personalized ear fatigue calculation 250, and personalized alert generation 260. The step of receiving 210 the inputs includes receiving a generalized model 211, a metadata 212 and ambient conditions 213 as inputs, via an input module 560. The metadata 212 comprises metadata about a user, music and a wearable audio device, in which the metadata about the user includes user health conditions, user age, medical condition of the user’s ears, or the like. The ambient conditions may include an ambient temperature detected by an embedded temperature sensor, or a background noise detected by a sound sensor, or the like. Further, the step of user profile selection 220 may select a user profile based on the metadata 212, and in the next step of fatigue assessment 230, the effects of the wearable audio device on the user are assessed using a scientifically designed questionnaire. The scientifically designed questionnaire may be created in consultation with an ENT specialist or the like. The step of personalized model generation 240 generates a personalized model for ear fatigue as the output for the selected user profile and the personalized ear fatigue calculation 250 step defines the threshold levels for ear fatigue for the user. The personalized model may further be interchangeably termed as the “digital twin” of the user’s ears or the “digital ear twin”. Further, in the step of personalized alert generation 260, custom alerts 270 are generated using the pre-defined threshold levels for ear fatigue in the step of personalized ear fatigue calculation 250, for the user of the selected user profile. The custom alerts 270 may be in the form of an alert message or a nudge or a soothing music/tone or the like. The custom alert 270 may further contain a prompt/warning message alarming the user to stop listening the music or using the earphones for a calculated / pre-defined time interval based on the selected user profile for the user.
Now, referring to Figure 3, which illustrates a multimodal design 300 for a mobile application for issuing the personalised alerts to the user, in accordance with an embodiment of the present disclosure. This multimodal design 300 discloses the processing steps of receiving the user data on the user interface screen 310, creating a personalized model / digital ear twin on the user interface screen 320 stating a message – “Please wait while your Personalized "Digital Twin" is being generated…”, and a message “You will receive Alerts, if the detected music is causing ear fatigue” on the user interface screen 330 confirming the creation of the digital ear twin and threshold levels defined for the digital ear twin created. Further, the user interface screen 340 displays the custom alert 270 generated and displays a custom message for the selected user profile for the user. For example, the user Sam may input his data on the screen 310 comprising the type of audio device used, earphones, age, medical condition, or the like. The screen 310 may also display the automatically detected ambient temperature. Further, the screen 310 may also display the selected earphones by automatically detecting the make and model of the earphone. Further, Sam might receive the alert 270 displayed as on the screen 340 with a calculated break time interval of 10 mins based on the pre-defined threshold values while generating the digital twin of Sam’s ears, as – “Sam, your music is causing ear fatigue. Take a 10 minute break from listening.”.
In another embodiment, referring to Figure 4, a block-diagram 400 for the system-on-a-chip hardware device running on an operating system like Linux is illustrated. The system-on-a-chip hardware device may comprise application layer, system libraries, Linux kernel, information architecture module, other hardware. Further, the application layer may comprise system software, machine learning (ML) / artificial intelligence (AI) programs, smartphone/mobile sync module, user data storage module, or the like. The information architecture module may also further comprise memory/storage modules, connectivity modules like Bluetooth or Wi-Fi, display module like LCD screen, 3.5 mm audio i/o module or the like.
In an embodiment, referring to Figure 5, a personalized alert generation system 500 for preventing ear damage is illustrated in accordance with an embodiment of the present disclosure. The personalized alert generation system 500 comprises an earphone identification module 510, a user data storage module 520, a machine learning module 530, a control module 540, and a smartphone sync module 550. The machine learning module 530 further comprises a user profile selection module 531, a fatigue assessment module 532, a generalized model generation module 533, a personalized model generation module 534, a personalized ear fatigue module 535, and a personalized alert generation module 536. The earphone identification module 510 detects the wearable audio device / earphone with its make and model, and the user data storage module 520 is used for storing user profile information related to various users of the system 500 containing the user metadata and/or music metadata and/or the ambient conditions. The control module 540 may be used for controlling the functionalities of the machine learning module 530 and the smartphone sync module 550, and may further perform accuracy checks to make sure output is within the threshold levels. The smartphone sync module 550 may be used for data transfer between the system 500 and mobile application 300. The input module 560 provides the generalized model 211, a metadata 212 and ambient conditions 213 as inputs to a machine learning module 530, in which the metadata 212 further comprises metadata about a user, music and the wearable audio device. The user profile selection module 531 selects of a user profile based on the metadata 212, and the fatigue assessment module 532 assesses the effects of the wearable audio device on the user using a scientifically designed questionnaire. The scientifically designed questionnaire may be created in consultation with an ENT specialist or the like. The generalized model generation module 533 may be configured for generating a generalized/generic model 211 based on the metadata 212 and the ear fatigue assessment made by the fatigue assessment module 532, as an input for the personalized model generation module 534. Further, the personalized model generation module 534 is configured to generate a personalized model for ear fatigue as the output for the selected user profile of the user, and based on this personalized model, the personalized ear fatigue module 535 defines the threshold levels for ear fatigue. The personalized alert generation module 536 is then further configured to generate custom alerts 270 using the personalized ear fatigue module 535 defined threshold levels for ear fatigue for the selected user profile of the user. The custom alerts 270 may be in the form of an alert message or a nudge or a soothing music/tone or the like. The custom alert 270 may further contain a prompt/warning message alarming the user to stop listening the music or using the earphones for a calculated / pre-defined time interval based on the selected user profile for the user.
The embodiments illustrated above, especially related to the personalized alert generation system and the personalized alert generation method for preventing ear damage using digital ear twin provides following technical advancements:
• Reduction in the inner ear hair damage.
• Reduction in individual’s overall fatigue level.
• Seamless wireless connectivity with a user device like a smartphone via a mobile application.
• Improvement in individual’s ear health, and overall health.
Various modifications to the embodiment will be readily apparent to those skilled in the art and the generic principles herein may be applied to other embodiments. However, one of ordinary skill in the art will readily recognize that the present disclosure is not intended to be limited to the embodiments illustrated but is to be accorded the widest scope consistent with the principles and features described herein.
The foregoing description shall be interpreted as illustrative and not in any limiting sense. A person of ordinary skill in the art would understand that certain modifications could come within the scope of this disclosure.
The embodiments, examples and alternatives of the preceding paragraphs or the description and drawings, including any of their various aspects or respective individual feature(s), may be taken independently or in any combination. Features described in connection with one embodiment are applicable to all embodiments unless such features are incompatible.
,CLAIMS:WE CLAIM:
1. A personalized alert generation system (500) for preventing ear damage, the personalized alert generation system (500) comprises:
an earphone identification module (510) configured for detecting the wearable audio device;
a user data storage module (520) configured for storing user profile information;
a control module (540);
a smartphone sync module (550);
an input module (560) configured to provide a generalized model (211), a metadata (212) and ambient conditions (213) as inputs to a machine learning module (530), wherein the metadata (212) comprises metadata about a user, music and the wearable audio device; and
the machine learning module (530) comprising:
a user profile selection module (531) configured for selection of a user profile based on the metadata (212);
a fatigue assessment module (532) configured to assess the effects of the wearable audio device on the user using a scientifically designed questionnaire;
a personalized model generation module (534) configured to generate a personalized model for ear fatigue as the output;
a personalized ear fatigue module (535) configured to define the threshold levels for ear fatigue; and
a personalized alert generation module (536) configured to generate custom alerts (270) using the personalized ear fatigue module (535) defined threshold levels for ear fatigue.
2. The personalized alert generation system (500) as claimed in claim 1, wherein the personalized alert generation system (500) comprises a generalized model generation system for preventing ear damage, wherein the generalized model generation system comprises:
an input module (560) configured to provide an audio input (111) and a metadata (112) as inputs, wherein the audio input (111) comprises controlled audio inputs and the metadata (112) comprises metadata of music and the wearable audio device;
the machine learning module (530) configured for receiving the results of testing the wearable audio device using a plurality of test volunteers, via the input module (560);
the fatigue assessment module (532) configured to assess the effects of the wearable audio device on the plurality of test volunteers using a scientifically designed questionnaire; and
a generalized model generation module (533) configured to generate a generalized model (211) for ear fatigue as the output by analyzing the answers to the scientifically designed questionnaire using the fatigue assessment module (533) and the entered inputs via the input module (560).
3. The personalized alert generation system (500) as claimed in claim 1, wherein the ambient conditions (213) include an ambient temperature detected by an embedded temperature sensor in the system (500) and/or a background noise detected by an embedded sound sensor in the system (500), or the like.
4. The personalized alert generation system (500) as claimed in claim 1, wherein the metadata about a user include user’s age, medical condition of user’s ears, user’s health conditions or the like.
5. The personalized alert generation system (500) as claimed in claim 1, wherein the metadata of music include tempo, genre, frequencies, instruments used, and/or the like.
6. The personalized alert generation system (500) as claimed in claim 1, wherein the metadata about the wearable audio device include make and model of the earphone and/or the like.
7. The personalized alert generation system (500) as claimed in claim 1, wherein the custom alerts (270) are in the form of an alert message or prompt/warning message or a nudge or a soothing music/tone or the like.
8. The personalized alert generation system (500) as claimed in claim 7, wherein the prompt/warning message is configured for alarming the user to stop listening the music or using the earphones for a calculated or pre-defined time interval based on the selected user profile for the user.
9. The personalized alert generation system (500) as claimed in claim 1, wherein the scientifically designed questionnaire is developed in consultation with an ENT specialist or the like.
10. The personalized alert generation system (500) as claimed in claim 2, wherein the machine learning module (530) comprises machine learning and artificial intelligence capabilities for computation and generation of generalized model (211) and the personalized model for preventing ear damage.
11. The personalized alert generation system (500) as claimed in claim 2, wherein the generalized model is the generic model for preventing ear damage and the personalized model for preventing ear damage is the digital ear twin of the user’s ears.
12. The personalized alert generation system (500) as claimed in claim 2, wherein the personalized alert generation system (500) may run on an operating system like Linux or the like.
13. A personalized alert generation method (200) for preventing ear damage, the personalized alert generation method (200) comprises the steps of:
receiving (210), via an input module (560), a generalized model (211), a metadata (212) and ambient conditions (213) as inputs, wherein the metadata (212) comprises metadata about a user, music and a wearable audio device;
user profile selection (220) for selection of a user profile based on the metadata (212);
fatigue assessment (230) for assessing the effects of the wearable audio device on the user using a scientifically designed questionnaire;
personalized model generation (240) for generating a personalized model for ear fatigue as the output;
personalized ear fatigue calculation (250) for defining the threshold levels for ear fatigue; and
personalized alert generation (260) for generating custom alerts (270) using the pre-defined threshold levels for ear fatigue in the step of personalized ear fatigue calculation (250).
14. The personalized alert generation method (200) as claimed in claim 13, the personalized alert generation method (200) comprises a generalized model generation method (100) for preventing ear damage, wherein the generalized model generation method (100) comprises the steps of:
receiving (110), via an input module (560), an audio input (111) and a metadata (112) as inputs, wherein the audio input (111) comprises controlled audio inputs and the metadata (112) comprises metadata of music and the wearable audio device;
testing (120) for testing the wearable audio device using a plurality of test volunteers;
fatigue assessment (130) for assessing the effects of the wearable audio device on the plurality of test volunteers using a scientifically designed questionnaire; and
generalized model generation (140) for generating a generalized model (211) for ear fatigue as the output by analyzing the answers to the scientifically designed questionnaire using the steps of fatigue assessment (130) and receiving (110) the inputs.
15. The personalized alert generation method (200) as claimed in claim 13, wherein the ambient conditions (213) include an ambient temperature detected by an embedded temperature sensor and/or a background noise detected by an embedded sound sensor, or the like, as per the method (200).
16. The personalized alert generation method (200) as claimed in claim 13, wherein the metadata about a user include user’s age, medical condition of user’s ears, user’s health conditions or the like.
17. The personalized alert generation method (200) as claimed in claim 13, wherein the metadata of music include tempo, genre, frequencies, instruments used, and/or the like.
18. The personalized alert generation method (200) as claimed in claim 13, wherein the metadata about the wearable audio device include make and model of the earphone and/or the like.
19. The personalized alert generation method (200) as claimed in claim 13, wherein the custom alerts (270) are in the form of an alert message or prompt/warning message or a nudge or a soothing music/tone or the like.
20. The personalized alert generation method (200) as claimed in claim 19, wherein the prompt/warning message is configured for alarming the user to stop listening the music or using the earphones for a calculated or pre-defined time interval based on the selected user profile for the user.
21. The personalized alert generation method (200) as claimed in claim 13, wherein the scientifically designed questionnaire is developed in consultation with an ENT specialist or the like.
22. The personalized alert generation method (200) as claimed in claim 14, wherein the computation and generation of generalized model (211) and the personalized model for preventing ear damage is executed via the machine learning module (530) comprises machine learnig and artificial intelligence capabilities.
23. The personalized alert generation method (200) as claimed in claim 14, wherein the generalized model is the generic model for preventing ear damage and the personalized model for preventing ear damage is the digital ear twin of the user’s ears.
24. The personalized alert generation method (200) as claimed in claim 14, wherein the personalized alert generation method (200) is a computer-readable program that may be stored on a memory and may run on an operating system like Linux or the like.

Dated this 05th day of February 2021