KR102347807B1 - Voice reading method and apparatus thereof - Google Patents

Abstract

A voice reading method and apparatus are disclosed. A voice reading method according to an embodiment includes the steps of collecting data related to a user's terminal usage pattern and analyzing the user's preference, and visual information from data displayed on a screen of the user terminal or data obtained from outside. It includes the steps of recognizing, extracting necessary information from the visual information according to user preference and importance identified in advance, and converting the extracted necessary information into the form of auditory information for reading.

Description

Voice reading method and apparatus thereof

The present invention relates to a vision assistance technology for reading by converting visual information into auditory information.

Recently, many smart devices provide a function to read text characters in the name of voice reading. However, in the case of voice reading, it reads from beginning to end, so there is no problem in the case of having to grasp the contents sequentially like a book, but in the case of a web-like format, especially a shopping web, it takes a considerable amount of time to be bored until the user hears the desired content. It takes time, and it is not easy to even connect the product and the content.

KR10-2044555 (Registered on 2019.11.07.)

According to one embodiment, a voice reading method and apparatus for reading only necessary information by a user are proposed.

The voice reading method according to an embodiment collects data related to a user's terminal usage pattern, and from the user's usage pattern data, according to a preset analysis standard, at least one of a web page visit history of the user terminal, a product of interest, and a search keyword Recognizing user preference by analyzing It includes the steps of extracting and converting the extracted necessary information into the form of auditory information for reading.

delete

The step of recognizing the visual information includes the steps of recognizing an object constituting a web page displayed on the terminal screen, determining the type of product the user wants to purchase from the recognized object, and purchasing the determined product It may include a step of receiving confirmation, and a step of recognizing text in a web page if there is a purchase intention.

The step of extracting the necessary information includes the steps of extracting, as necessary information, a key word presented in the text in the recognized visual information according to a preset importance level, and extracting information preferred by the user from among the extracted key words as necessary information. may include

In the step of identifying user preference, if the user belongs to a group, common information commonly used by a plurality of users in the group is identified, and in the step of extracting necessary information, in the visual information currently displayed on the terminal screen, The necessary information can be extracted. The voice reading method may further include, when common information within a group and individual user information are different, providing the common information first, then personalizing the different individual information to provide the personalized information together.

In the voice reading method, if the recognized visual information is treatment reservation information, it is checked whether the patient information included in the treatment reservation information is a user. may include more.

In the step of identifying the user preference, the interval at which the user purchases a predetermined product is identified, and the voice reading method may further include the step of notifying the user in the form of auditory information when the user intends to purchase the predetermined product in advance of the identified purchase interval. can

The voice reading method may further include converting user preference information and recommendation information generated based on the user preference information into auditory information and outputting the converted information.

The voice reading device according to another embodiment collects data related to the user's terminal usage pattern, and from the user's usage pattern data according to a preset analysis criterion, at least one of a web page visit history of the user terminal, a product of interest, and a search keyword A data analysis unit for recognizing user preference by analyzing It includes a data extraction unit for extracting necessary information from the inside, a data conversion unit for converting the extracted necessary information into the form of auditory information, and an output unit for outputting and reading the converted auditory information.

The user terminal may include a vision assisting device mounted on a main body worn on the user's body to capture an external image to obtain a captured image.

The data recognition unit recognizes the objects constituting the web page displayed on the terminal screen, determines the type of product the user wants to purchase from the recognized object, and after receiving confirmation of the purchase intention for the determined product, Recognizing the text, the data extraction unit may extract, as necessary information, a key word presented in the recognized text according to a preset importance level, and extract information preferred by the user from among the extracted key words as necessary information.

The voice reading method and the apparatus according to an embodiment provide a function of reading only necessary information to the user, so that the user can quickly and comfortably obtain the desired information, and can easily purchase the desired product in the purchase mode.

Furthermore, after collecting data related to the user's terminal usage pattern and analyzing the user's preference, it is possible to provide a user-customized reading function as the user reads only necessary information in consideration of the user's preference. For example, if a user prefers a specific brand, efficiency and user satisfaction can be increased by extracting a product of the preferred brand first and reading it.

It is also possible to check the frequency of purchasing a specific product, so that it is possible to check whether a product is purchased again without knowing it is in stock, providing convenience for planned purchases.

In the case of hospitals, if the patient reads the reserved information such as the future treatment date, it can check whether the patient is a user and provide a function that automatically registers the patient in the scheduler by recognizing that he/she has made a reservation for the treatment date. After that, you can use a reminder to notify you so you don't forget it.

In the case of a group, common information commonly used by multiple users is extracted and shared, and based on this, product purchase/information sharing is provided. can do.

1 and 2 are views showing the configuration of a voice reading apparatus according to various embodiments of the present invention;
3 is a diagram showing the structure of a user terminal according to an embodiment of the present invention;
4 is a view showing the configuration of a voice reading apparatus according to an embodiment of the present invention;
5 is a diagram illustrating an example of extracting and reading necessary information according to an embodiment of the present invention;
6 is a diagram illustrating an example in which the voice reading apparatus stores user preference information in a DB according to an embodiment of the present invention;
7 is a diagram illustrating a flow of a voice reading method according to an embodiment of the present invention.

Advantages and features of the present invention, and a method for achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments allow the disclosure of the present invention to be complete, and common knowledge in the technical field to which the present invention belongs It is provided to fully inform the possessor of the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout.

In describing the embodiments of the present invention, if it is determined that a detailed description of a well-known function or configuration may unnecessarily obscure the gist of the present invention, the detailed description will be omitted, and the terms to be described later are used in the embodiment of the present invention. As terms defined in consideration of the function of Therefore, the definition should be made based on the content throughout this specification.

Each block in the accompanying block diagram and combinations of steps in the flowchart may be executed by computer program instructions (execution engine), which may be executed by a processor of a general-purpose computer, special-purpose computer, or other programmable data processing equipment. It may be mounted so that the instructions, which are executed by the processor of a computer or other programmable data processing equipment, create means for performing the functions described in each block of the block diagram or in each step of the flowchart.

These computer program instructions may also be stored in a computer usable or computer readable memory which may direct a computer or other programmable data processing equipment to implement a function in a particular manner, and thus the computer usable or computer readable memory. It is also possible to produce an article of manufacture containing instruction means for performing the functions described in each block of the block diagram or each step of the flowchart, the instructions stored in the block diagram.

And since the computer program instructions may be mounted on a computer or other programmable data processing equipment, a series of operational steps is performed on the computer or other programmable data processing equipment to create a computer-executable process to create a computer or other programmable data processing equipment. It is also possible that the instructions for performing the data processing equipment provide steps for carrying out the functions described in each block of the block diagram and each step of the flowchart.

In addition, each block or step may represent a module, segment, or portion of code comprising one or more executable instructions for executing specified logical functions, and in some alternative embodiments the blocks or steps referred to in some alternative embodiments. It should be noted that it is also possible for functions to occur out of sequence. For example, it is possible that two blocks or steps shown one after another may be performed substantially simultaneously, and also the blocks or steps may be performed in the reverse order of the corresponding functions, if necessary.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the embodiments of the present invention illustrated below may be modified in various other forms, and the scope of the present invention is not limited to the embodiments described below. The embodiments of the present invention are provided to more completely explain the present invention to those of ordinary skill in the art to which the present invention pertains.

1 and 2 are diagrams illustrating a configuration of a voice reading apparatus according to various embodiments of the present disclosure.

The voice reading device 1 may have a structure provided in the user terminal 2 as shown in FIG. 1 , and as shown in FIG. 2 , functions are provided in the user terminal 2 and the management server 3 in the network ( 4) may be a distributed structure. For example, the DB may be located in the management server (3).

The voice reading device 1 recognizes visual information including objects, texts, images, etc. from data displayed on the screen of the user terminal 2 or acquired from the outside, and then converts it into auditory information and reads it. it is a device In this case, the recognized visual information is not read from the beginning to the end, but only necessary information (necessary information, hereinafter referred to as 'necessary information') is extracted and read from the visual information.

When the site visited by the user through the user terminal 2 is in a web-like form, particularly a shopping web site, it takes a considerable amount of time to be tedious until the user hears the desired content if he/she reads it from beginning to end, and even products and contents It is not easy to connect. However, after recognizing the object on the screen through the intelligent voice reading device 1 equipped with artificial intelligence and voice reading function, identifying the type of product to be purchased, and taking into account the recognized user preference pattern, only the necessary information is displayed on the screen. By extracting, processing, and reading it as a sound, it can provide a high-efficiency function. For example, if the web page is a page for selling products, the voice reading device 1 recognizes objects constituting the web page and preferentially reads necessary information corresponding to an important part. If a user wants to purchase a TV, the service is provided in the form of asking if the user wants to read the TV first after extracting the number of inches, the price, and the preferred brand. When a user wants to purchase milk, the necessary information corresponding to the important parts, such as normal or low fat, the expiration date, and the price, is extracted and read first. At this time, if the user prefers a specific brand, such a singularity can also be identified and suggested through a plurality of previous selection forms previously selected by the user.

It is possible to check the interval at which a user purchases a specific product, etc., so that it is possible to check whether there is stock but the user does not know and buy it, thereby providing convenience for planned purchases. As another example, in the case of a hospital, if the contents of a reservation such as a future treatment date are extracted, the function of automatically registering in the scheduler is provided by checking whether the patient is a user in the treatment reservation contents and recognizing that the treatment date has been reserved. After that, the user can be notified so as not to forget through a reminder before the treatment day.

The user may be a visually impaired class or a general public. Vulnerable groups include those whose eyesight is different from that of those with normal eyesight, including those who have rapidly developed presbyopia, hyperopia, myopia, and astigmatism due to the use of smartphones, as well as the existing hyperopia, myopia, astigmatism, the elderly, and the visually impaired. Concept. For the visually impaired, auditory information can be output through a speaker using a vision aid. A user may be an individual or a group. In the case of groups, for example, clubs, etc.

The service may be applied differently depending on whether the user is an individual or a group. For example, in the case of a group such as a club, it is possible to extract and share common information commonly used by a large number of users, and guide them to purchase a product based on this. When a new user is added to a group, based on common information, the group members can recommend or guide them to purchase the same necessary products.

Various technologies such as artificial intelligence (AI) technology, augmented reality (AR), and text to speech (TTS) technology are applied to the voice reading device 1 . Remote control is also possible. Artificial intelligence technology includes technology that automatically recognizes visual information such as objects, texts, and distances from images through machine learning. Augmented reality technology is a technology that combines the virtual world and the real world, such as recognizing the image of the object pointed by the user and notifying it by voice even if an object distant from the user is pointed out. Here, a technique for recognizing a user's gesture as an augmented reality pointer and recognizing a position indicated by the recognized augmented reality pointer is included. The speech conversion technology includes a technology for converting recognized visual information, for example, a text image, into text information, and converting it into auditory information that a user can hear and outputting a voice. The remote control includes a technique in which the user terminal 2 is supported by remote control from the management server 3 connected through the network 4 and the management server 3 monitors the user terminal 2 .

The network 4 is a wired/wireless network capable of transmitting and receiving data between the user terminal 2 and the management server 3 . The network 4 may use various types of communication networks, for example, Wi-Fi, Wireless LAN (WLAN), Wibro, Wimax, High Speed Downlink Packet Access (HSDPA), Bluetooth, DSL, LTE, PCS, Wireless communication methods such as 2G, 3G, 4G, 5G, LAN, CDMA, TDMA, GSM, WDM, or Ethernet (Ethernet), xDSL (ADSL, VDSL), HFC (Hybrid Fiber Coax), FTTC (Fiber to The Curb), A wired communication method such as Fiber To The Home (FTTH) may be used. The network is not limited to the above-described communication method, and may include all types of communication methods that are well-known or to be developed in the future in addition to the above-described communication method.

3 is a diagram illustrating the structure of a user terminal according to an embodiment of the present invention.

As shown in (a) of FIG. 3 , the user terminal 2 may be divided into an eyesight assisting device 20 and a control device 22 . The vision assisting device 20 may be a wearable device that is detachably attached to the leg of the user's glasses. The connection unit 26 connects the vision assisting device 20 and the control device 22 . The connection unit 26 may connect the vision assisting device 20 and the control device 22 by wire. It can be connected using a wireless method or can be used in parallel with a wireless method. A photographing unit capable of capturing an external image may be mounted on the vision assisting device 20 , and a battery may be mounted on the control device 22 .

The vision assisting device 20 is a wearable device that a user can easily wear and possess. As an example of the wearable device, there is a type of attaching and detaching to a frame or a bridge of glasses worn by a user. A photographing unit is mounted on the front or side, so that an image can be captured in real time through the photographing unit. Such a wearable device can be attached to and detached from conventional glasses, and minimized weight to make it convenient to wear.

As shown in (b) of FIG. 3 , the user terminal 2 may have a form in which the vision assisting device 20 is interlocked with the smart device 24 . The smart device 24 may be a smart phone or the like. The connection unit 26 connects the vision assisting device 20 and the smart device 24 . The connection unit 26 may connect the vision assisting device 20 and the smart device 24 by wire. It can be connected using a wireless method or can be used in parallel with a wireless method. A photographing unit capable of photographing an external image is mounted on the vision assisting device 20 , and a battery of the smart device 24 may be used. The smart device 24 may recognize the visual information displayed on the screen.

As shown in (c) of FIG. 3 , the user terminal 2 may be a smart device 24 without a vision assisting device. For example, the functions described above may be performed using only the smart device 24 without wearing the vision assisting device 20 . In this case, an external image may be photographed using a photographing unit mounted on the smart device 24 itself, and the photographed image or display screen may be recognized.

4 is a diagram illustrating a configuration of a voice reading apparatus according to an embodiment of the present invention.

Referring to FIG. 4 , the voice reading apparatus 1 includes a data analysis unit 10 , a data recognition unit 12 , a data extraction unit 14 , a data conversion unit 16 , and an output unit 18 .

The data analysis unit 10 , the data recognition unit 12 , the data extraction unit 14 , and the data conversion unit 16 perform corresponding functions in the processor, and instructions for performing the functions may be stored in a memory.

The data analysis unit 10 collects data related to the user's terminal usage pattern in advance and identifies the user's preference through analysis. The user preference may be, for example, a brand preferred by the user. User preference can be identified through analysis of web page visit history information, purchase information, and search information related to the user's usage pattern within the web page constituting the user visit site.

When purchasing an advertisement target product on a web page accessed through a user terminal, purchase information may include a product purchase order number, product code, product name, purchase price, product thumbnail web address, purchase quantity, and user terminal type. .

The data analysis unit 10 may set a preset time period and collect the above-mentioned information within the time period to perform analysis. A weight may be further assigned to a recent time interval. As the frequency is counted by checking the purchase history for each time section, if the user does not know that there is stock or wants to buy, the user is notified in advance, thereby increasing efficiency. The data analysis unit 10 may provide the analysis result including user preference to the data extraction unit 14 , and may provide the analysis result or recommendation information generated based on the analysis result to the data conversion unit 16 .

The data analysis unit 10 analyzes the user's terminal usage pattern data according to the analysis criteria set in advance, and analyzes the web page visit history and interest products of individual user terminals to determine the preferences of individual users, and the data extraction unit 14 can extract an individual recommended product list according to the identified preferences. The data analysis unit 10 analyzes the user's terminal usage pattern data according to the pre-set analysis criteria, including the web page visit history of the user terminals constituting the group and the products of interest, so that the user's preference of the entire group can be grasped, The data extraction unit 14 may extract a list of related products according to the identified preferences of the entire group.

The data analysis unit 10 analyzes the user's terminal usage pattern data according to the analysis criteria set in advance, and the search keyword of the individual user terminal, and the data extraction unit 14 is a list of recommended keywords according to the search history of the individual user terminal. can be extracted. The data analysis unit 10 analyzes the user's terminal usage pattern data including search keywords of the user terminals constituting the entire group according to the analysis criteria set in advance, and the data extraction unit 14 analyzes the search history of the entire user terminal It is possible to extract a list of related keywords according to

The data recognition unit 12 recognizes visual information from data displayed on the user terminal screen or acquired from the outside. The data displayed on the screen of the user terminal may be a screen of a web page displayed on the screen. The data obtained from the outside may be an external image captured by the user in real time through the user terminal. For example, it may be an image of product information of a product to be purchased, such as milk. The visual information may be an object, text, image, or the like. The web page screen may include a product detail page, a product purchase page, and a product search result page constituting the online shopping mall.

The data recognition unit 12 may distinguish objects such as people, animals, and things through artificial intelligence-based machine learning. Due to the nature of machine learning, the more users there are, the higher the accuracy.

The data recognition unit 12 may recognize an object constituting a web page displayed on the screen of the user terminal and determine the type of product the user wants to purchase from the recognized object. For example, it is determined that the user's interest product is milk from the milk image. Subsequently, the data recognition unit 12 may ask the user to confirm the purchase intention for the determined product. If there is a purchase intention, the data recognition unit 12 recognizes text in the web page.

The data extraction unit 14 extracts necessary information from the visual information according to user preference and importance identified in advance. The importance level is set in advance and can be modified by the user. For example, in the case of a TV, size and price correspond to important information, and in the case of milk, whether it is regular or low-fat, expiration date, price, etc. correspond to important information.

The data extraction unit 14 may extract a key word as necessary information according to importance among words presented in the text recognized by the data recognition unit 12 . Keywords are keywords that can identify product information among the characters in the text. Product code, product name, selling price, consumer price, product thumbnail web address, product image web address, mobile product image web address, product category, brand name, etc. information that includes For example, in the case of milk, whether it is normal or low-fat, expiration date, price, etc. are extracted as key words. If there is a key word preferred by the user in the recognized text, for example, a specific brand, it is determined as the user's preferred information and it can be extracted as necessary information.

When the user belongs to a group, the data analysis unit 10 may identify common information commonly used by a plurality of users in the group. A group can be a club or the like. At this time, the data extraction unit 14 extracts necessary information corresponding to common information from the visual information currently displayed on the terminal screen. For example, a swimsuit brand purchased as a group uniform in an aqua walking club may be common information. When the common information and the individual user information are different, the common information is preferentially extracted, and the individualized information can be extracted by personalizing the different individual information. For example, when a group wants to purchase a swimsuit as a group, size information may be different. After processing, different individual information can be personalized and processed.

The data conversion unit 16 converts the necessary information extracted by the data extraction unit 14 into auditory information. The output unit 18 outputs and reads the auditory information converted by the data conversion unit 16 . The data conversion unit 16 may receive the user preference information and the recommendation information generated based on the user preference information from the data analysis unit 10 , convert it into auditory information, and output it through the output unit 18 . When a new user is added to a group, the data conversion unit 16 may convert common information or recommendation information based on common information into auditory information, and then output it through the output unit 18 .

When the visual information recognized by the data recognition unit 12 is treatment reservation information, the data extraction unit 14 checks whether the patient information included in the treatment reservation information is a user, and if it is a user, after registering the treatment reservation date in the scheduler It can be informed in advance in the form of auditory information through the output unit 18 . The auditory information is a voice signal, a warning sound, and the like. For example, the output unit 18 reads necessary information from among the printed characters and provides a sound.

When the data analysis unit 10 identifies the user's preference, the interval at which the user purchases the predetermined product is identified, and when the user intends to purchase the predetermined product in advance of the identified purchase interval, it is transmitted in the form of auditory information through the output unit 18 can tell you

5 is a diagram illustrating an example of extracting and reading necessary information according to an embodiment of the present invention.

Referring to FIG. 5 , the voice reading apparatus does not read from beginning to end, but extracts and reads only necessary information corresponding to important information and user preference information from text. For example, as shown in FIG. 5, only Seoul milk, sterilized milk, 1L, 100% domestic raw milk, and cholesterol 10mg are extracted and read. Accordingly, the user can obtain only necessary information, thereby increasing the convenience of use. After reading the extracted necessary information, the voice reading device may additionally read other information by asking the user whether to read more and then requesting to read more.

6 is a diagram illustrating an example in which the voice reading apparatus stores user preference information in a DB according to an embodiment of the present invention.

Referring to FIG. 6 , the voice reading device 1 includes data related to the user's terminal usage pattern, for example, web page visit history information related to the user's usage pattern in the web page constituting the user visit site, purchase information, and search After collecting information and analyzing user preferences, the identified user preference information is stored in the DB.

For example, as shown in FIG. 6 , in the case of user A, storage items: 20 items, category 10: daily necessities, food 10.11 milk, brand> Seoul milk, raw/sterilized> sterilization, domestic or not> domestic, cholesterol> 10 mg The following are stored. At this time, items such as category, food name, brand, raw/sterilization, domestic availability, cholesterol, etc. correspond to important information, and the details correspond to user preference information.

Applications can be divided into individuals and groups. For example, as shown in FIG. 6 , in the case of group A (aqua walking group), storage items: 10 pieces, category 100: essential, clothes 70.11 swimsuit, brand> speedo, women/men> women, color> navy, size > 100, etc. are stored. In this case, when the user's body type is recognized in advance, the common information and the different individual information 600 may be processed by processing the common information of group A first and then personalizing the information. In the case of a group, common information commonly used by multiple users is extracted and shared, and product purchase/information sharing is provided based on this, and when a new user is added to the group, the same necessary product is recommended based on this. and guides.

7 is a diagram illustrating a flow of a voice reading method according to an embodiment of the present invention.

Referring to FIG. 7 , the voice reading apparatus collects data related to the user's terminal usage pattern and analyzes the data to determine user preference ( 710 ). In the user preference identification step 710, the voice reading device collects web page visit history information, purchase information, and search information related to the user's usage pattern within the web page constituting the user visit site, and can identify the user preference through analysis. have.

Next, the voice reading apparatus recognizes visual information from data displayed on the screen of the user terminal or data obtained from the outside ( S720 ). In the visual information recognition step 720 , the voice reading apparatus may recognize an object constituting a web page displayed on the terminal screen, and determine the type of product the user wants to purchase from the recognized object. In addition, after receiving confirmation of purchase intention for the determined product, if there is a purchase intention, the text in the web page may be recognized.

Next, the voice reading apparatus extracts necessary information from the visual information according to the user's preference and importance identified in advance (S730). In the necessary information extraction step 730, the voice reading device extracts, as necessary information, a key word presented in the text in the recognized visual information according to a preset importance level, and extracts information preferred by the user from among the extracted key words as necessary information can do. In the user preference identification step 710 , if the user belongs to a group, if common information commonly used by a plurality of users in the group is identified, common information is extracted from the visual information currently displayed on the terminal screen in the necessary information extraction step 730 . It is possible to extract necessary information corresponding to

Next, the voice reading apparatus converts the extracted necessary information into the form of auditory information and reads it ( 740 ). Furthermore, when the common information within the group and the user's individual information are different, the voice reading device may provide the common information first, then personalize the different individual information to provide the personalized information together.

As another example, if the visual information recognized in the visual information recognition step 720 is treatment reservation information, the voice reading device checks whether the patient information included in the treatment reservation information is a user, and if it is a user, registers the treatment reservation date in the scheduler and This can be informed in advance in the form of auditory information.

As another example, the voice reading device determines the interval at which the user purchases the predetermined product in the user preference identification step 710, and then informs the user in the form of auditory information when the user intends to purchase the predetermined product in advance of the identified purchase interval. have. The voice reading apparatus may convert user preference information and recommendation information generated based on the user preference information into auditory information and output the converted information.

So far, the present invention has been focused on the embodiments thereof. Those of ordinary skill in the art to which the present invention pertains will understand that the present invention can be implemented in modified forms without departing from the essential characteristics of the present invention. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is indicated in the claims rather than the foregoing description, and all differences within the scope equivalent thereto should be construed as being included in the present invention.

Claims (12)

In the voice reading method using the voice reading device, the voice reading device
identifying user preference by collecting data related to the user's terminal usage pattern and analyzing at least one of a web page visit history of the user terminal, a product of interest, and a search keyword from the user's usage pattern data according to a preset analysis standard;
Recognizing visual information from data displayed on a screen of a user terminal or data acquired from outside;
extracting necessary information from the visual information according to user preference and importance identified in advance; and
converting the extracted necessary information into a form of auditory information and reading; includes,
Recognizing visual information
Recognizing an object constituting a web page displayed on the terminal screen;
determining the type of product the user wants to purchase from the recognized object;
receiving confirmation of purchase intention for the determined product; and
recognizing text in a web page if there is a purchase intention; A voice reading method comprising a. delete delete According to claim 1, wherein the step of extracting the necessary information
extracting, as necessary information, a key word presented in the text in the recognized visual information according to a preset importance level; and
extracting information preferred by the user from among the extracted key words as necessary information;
A voice reading method comprising a. The method of claim 1, wherein the step of determining user preference comprises:
If a user belongs to a group, identify common information commonly used by multiple users in the group,
Steps to extract the necessary information
A voice reading method comprising extracting necessary information corresponding to common information from the visual information currently displayed on the terminal screen. The method of claim 5, wherein the voice reading method
If the common information within the group and the individual user information are different, providing the common information first, then personalizing the different individual information to provide the personalized information together;
Voice reading method, characterized in that it further comprises. In the voice reading method using the voice reading device, the voice reading device
identifying user preference by collecting data related to the user's terminal usage pattern and analyzing at least one of a web page visit history of the user terminal, a product of interest, and a search keyword from the user's usage pattern data according to a preset analysis standard;
Recognizing visual information from data displayed on a screen of a user terminal or data acquired from outside;
extracting necessary information from the visual information according to user preference and importance identified in advance; and
converting the extracted necessary information into a form of auditory information and reading; and
If the recognized visual information is treatment reservation information, confirming whether the patient information included in the treatment reservation information is a user, and if the user, registering the treatment reservation date in the scheduler and notifying it in advance in the form of auditory information;
A voice reading method comprising a. In the voice reading method using the voice reading device, the voice reading device
identifying user preference by collecting data related to the user's terminal usage pattern and analyzing at least one of a web page visit history of the user terminal, a product of interest, and a search keyword from the user's usage pattern data according to a preset analysis standard;
Recognizing visual information from data displayed on a screen of a user terminal or data acquired from outside; and
extracting necessary information from the visual information according to user preference and importance identified in advance; and
converting the extracted necessary information into a form of auditory information and reading; includes,
Steps to understand user preferences
Identify the interval at which users purchase a given product,
How to lead a voice
notifying the user in the form of auditory information when the user intends to purchase a predetermined product in advance of the identified purchase interval;
Voice reading method, characterized in that it further comprises. The method of claim 1, wherein the voice reading method
converting the user preference information and recommendation information generated based on the user preference information into auditory information and outputting the converted information;
Voice reading method, characterized in that it further comprises. Data analysis to identify user preferences by collecting data related to the user's terminal usage pattern and analyzing at least one of the user terminal's web page visit history, products of interest, and search keywords from the user's usage pattern data according to a preset analysis standard wealth;
a data recognition unit for recognizing visual information from data displayed on the screen of the user terminal or data obtained from the outside;
a data extraction unit for extracting necessary information from the visual information according to user preference and importance identified in advance;
a data conversion unit for converting the extracted necessary information into a form of auditory information; and
an output unit for outputting and reading the converted auditory information; includes,
data recognition unit
It recognizes the objects constituting the web page displayed on the terminal screen, determines the type of product the user wants to purchase from the recognized object, and after receiving confirmation of the purchase intention for the determined product, recognizes the text in the web page if there is a purchase intention A voice reading device, characterized in that. 11. The method of claim 10, wherein the user terminal is
and a vision assisting device mounted on a main body worn on the user's body to acquire an external image by photographing the external image. 11. The method of claim 10, wherein the data extraction unit
A voice reading device, characterized in that extracting a key word presented in the recognized text according to a preset importance as necessary information, and extracting information preferred by a user from among the extracted key words as necessary information.

Images