Method for generating subtitles to protect eyesight through AI digital intelligent identification

Abstract

The invention discloses a method for generating subtitles to protect eyesight through AI digital intelligent recognition. The method comprises the following steps of a, information acquisition, b, AI recognition, c, subtitle generation and d, subtitle display. According to the invention, the principles of mechanics, psychology, brain science and human body structure kinematics are combined to form an APP ecological mode for comprehensively preventing myopia caused by local fatigue eye use, so that people grow in learning, the eyes are protected in growth, and comprehensive development of the Dwisdom body is promoted.

Description

Technical Field

[0001] The present invention relates to the field of vision protection software, and in particular to a method for protecting vision by generating subtitles through AI digital intelligent recognition. Background Art

[0002] Myopia in my country seriously harms the healthy growth of young people and affects the selection of high-quality talents. With the development of society, informatization has become the cornerstone of promoting the progress of the times, and electronic equipment products are essential for spreading information, deeply understanding the world, learning and living. There are 5 billion Internet users in the world, and 800 million Chinese people are inseparable from their mobile phones. Mobile phones have become an extended organ of the human body and a window of mass consumption emotions. The diversity of short videos allows countless people to consume their hobbies in different fields. Whether it is consuming sympathetic tears or dopamine for laughing, high dependence on mobile phones seriously disrupts the ecology of the central nervous system of the brain. In severe cases, people are irritable and even vomit. The human brain spends more than 50% of its time dealing with eye problems. High dependence leads to less and less deep sleep, which seriously affects visual health. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art.

[0004] To this end, the technical solution adopted by the present invention to solve the technical problem is: a method for protecting eyesight by generating subtitles through AI digital intelligent recognition, the method comprising the following steps:

[0005] a. Information acquisition step: acquiring voice audio information in a video with voice, and acquiring music audio information in a video without voice;

[0006] b. AI recognition step: speech recognition text of the acquired speech audio information, and syllable recognition text of the acquired music audio information;

[0007] c. Subtitle generation step: generating corresponding subtitles for the speech recognition text and generating corresponding musical note symbols for the syllable recognition text;

[0008] d. Subtitle display step: split the screen display area into a number of circular invisible tracks or areas with invisible edges and place subtitles or musical note symbols on the tracks or areas, and the subtitles or musical note symbols run clockwise or counterclockwise along the tracks or areas.

[0009] Preferably, the speech recognition text and syllable recognition text in step b also contain emoticons that match the text content.

[0010] Preferably, the subtitles and musical note symbols in step c also contain emoticons.

[0011] Preferably, each word or musical note in the subtitles or musical note symbols is displayed in a gradual transition from blurry to clear.

[0012] Preferably, the more words or notes there are in the subtitles or musical note symbols, the more tracks or areas there are, and the number of tracks or areas ranges from 1 to 11 at most.

[0013] Preferably, the more words or notes there are in the subtitles or musical note symbols, the slower the running speed on the track or area, and the running speed ranges from 1 second to 10 seconds to go around the track or area.

[0014] Preferably, the speech recognition text generates corresponding Chinese and English subtitles.

[0015] Preferably, the syllable recognition text generates corresponding musical note symbols and the size of the musical note symbols is displayed according to the musical scale, and the higher the scale, the larger the musical note symbols.

[0016] The beneficial effects of the present invention are as follows: through video voice recognition technology, the voice in the video is processed by technology and converted into Chinese or English for presentation. According to the input of intelligence of different age groups, intelligent adjustment is made, and the mechanical principle is applied. The effect of red blood cells and nerve cells on the optic nerve generated by the physical movement of the eyeball is used to promote static blood circulation. The subtitles are long or short to perform on-track aerobic exercise, which solves the scleral hypoxia caused by long-term use of the eyes and improves various visual fatigue problems such as eye soreness and eye swelling; the intelligent big data technology algorithm and processing are used to effectively prevent the near-sightedness from causing scleral hypoxia by reducing choroidal blood flow, which eventually leads to the occurrence of myopia; the high and low rhythms of video music are used, and the notes appear with the music like playing the piano. The high or low rhythm forms a rhythm chain to drive the eyeballs to move on the track, activate the eye muscles, and enhance the elasticity of the eye axis; various expressions are designed in the background, pushed through the audio voice recognition conversion method, and online thinking plots are expressed. The brain mind map is used for passive adjustment to prevent lactic acid production, so as to achieve the purpose of preventing myopia. DETAILED DESCRIPTION

[0017] The present invention will be further described below in conjunction with the embodiments, but is not limited to the contents of the description.

[0018] Embodiment 1: A method for protecting eyesight by generating subtitles through AI digital intelligent recognition, the method comprising the following steps:

[0019] a. Information acquisition step: acquiring voice audio information in a video with voice, and acquiring music audio information in a video without voice;

[0020] b. AI recognition step: speech recognition text of the acquired speech audio information, and syllable recognition text of the acquired music audio information;

[0021] c. Subtitle generation step: generating corresponding subtitles for the speech recognition text and generating corresponding musical note symbols for the syllable recognition text;

[0022] d. Subtitle display step: split the screen display area into a number of circular invisible tracks or areas with invisible edges and place subtitles or musical note symbols on the tracks or areas, and the subtitles or musical note symbols run clockwise or counterclockwise along the tracks or areas.

[0023] The speech recognition text and syllable recognition text in step b also contain emoticons that match the text content.

[0024] The subtitles and musical note symbols in step c also contain emoticons.

[0025] Each single word or musical note in the subtitles or musical note symbols is displayed gradually from blurry to clear.

[0026] The more words or notes there are in the subtitles or musical note symbols, the more tracks or areas there are, and the number of tracks or areas ranges from 1 to 11.

[0027] The more words or notes there are in the subtitles or musical note symbols, the slower the running speed on the track or area, and the running speed ranges from 1 second to 10 seconds to circle the track or area.

[0028] The speech recognition text generates corresponding Chinese and English subtitles.

[0029] The syllable recognition text generates corresponding musical note symbols and displays the size of the musical note symbols according to the musical scale. The higher the scale, the larger the musical note symbols.

[0030] The above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the embodiments here. Any obvious changes or modifications derived from the technical solution of the present invention are still within the scope of protection of the present invention.

Claims

1. A method for protecting eyesight by generating subtitles through AI digital intelligent recognition, characterized in that: The method comprises the following steps: a. Information acquisition step: acquiring voice audio information in a video with voice, and acquiring music audio information in a video without voice; b. AI recognition step: speech recognition text of the acquired speech audio information, and syllable recognition text of the acquired music audio information; c. Subtitle generation step: generating corresponding subtitles for the speech recognition text and generating corresponding musical note symbols for the syllable recognition text; d. Subtitle display step: split the screen display area into a number of circular invisible tracks or areas with invisible edges and place subtitles or musical note symbols on the tracks or areas, and the subtitles or musical note symbols run clockwise or counterclockwise along the tracks or areas.

2. The method for protecting eyesight by generating subtitles through AI digital intelligent recognition according to claim 1, characterized in that: The speech recognition text and syllable recognition text in step b also contain emoticons that match the text content.

3. The method for protecting eyesight by generating subtitles through AI digital intelligent recognition according to claim 2, characterized in that: The subtitles and musical note symbols in step c also contain emoticons.

4. The method for protecting eyesight by generating subtitles through AI digital intelligent recognition according to claim 1, characterized in that: Each single word or musical note in the subtitles or musical note symbols is displayed gradually from blurry to clear.

5. The method for protecting eyesight by generating subtitles through AI digital intelligent recognition according to claim 4, characterized in that: The more words or notes there are in the subtitles or musical note symbols, the more tracks or areas there are, and the number of tracks or areas ranges from 1 to 11 at most.

6. The method for protecting eyesight by generating subtitles through AI digital intelligent recognition according to claim 4, characterized in that: The more words or notes there are in the subtitles or musical note symbols, the slower the running speed on the track or area, and the running speed ranges from 1 second to 10 seconds to go around the track or area.

7. The method for protecting eyesight by generating subtitles through AI digital intelligent recognition according to claim 1, characterized in that: The speech recognition text generates corresponding Chinese and English subtitles.

8. The method for protecting eyesight by generating subtitles through AI digital intelligent recognition according to claim 1, characterized in that: The syllable recognition text generates corresponding musical note symbols and displays the size of the musical note symbols according to the musical scale. The higher the scale, the larger the musical note symbols.