KR20240081674A - Apparatus and method for providing text reading services - Google Patents

Abstract

An apparatus and method for providing a text reading service are disclosed. The method of providing a text reading service includes the steps of collecting reading content including videos and scripts, receiving a request for reading participation from the user, and selecting content for the user to read from among the reading content collected according to the reading participation request. A step of selecting and presenting, a step of acquiring the user's voice data for the presented content, a step of determining whether the presented content matches the acquired voice data, determination result, if the presented content and the acquired voice data match, the user It includes providing a reward to the user and storing the acquired voice data in a database as the presented content matches the acquired voice data.

Description

Apparatus and method for providing text reading services}

The present invention relates to an apparatus and method for providing text reading services.

Recently, with the development and high interest in artificial intelligence (AI) technology, artificial intelligence is being applied or studied in many fields. Artificial intelligence is a subfield of computer science that seeks to implement computer systems to perform tasks that generally require human learning, reasoning, and perception abilities. Additionally, artificial intelligence is a computer system with intelligent functions, and human intelligence is artificially implemented in machines, etc.

In order to implement such artificial intelligence, artificial intelligence must be allowed to learn. For artificial intelligence learning, a huge amount of learning data is required, and collecting the learning data costs a lot of money.

Therefore, a method to efficiently collect learning data for artificial intelligence is required.

Republic of Korea Patent No. 10-2446970 (2022.09.20)

The present invention is intended to provide an apparatus and method for providing a text reading service that collects reading content from one user, induces other users to read the collected reading content using reward provision, and obtains voice data.

According to one aspect of the present invention, a method for providing a text reading service performed by a text reading service providing device that cooperates with a user terminal is disclosed.

A method of providing a text reading service according to an embodiment of the present invention includes the steps of collecting reading content including a video and a script, receiving a reading participation request from a user, and reading the collected reading according to the reading participation request. Selecting and presenting content to be read by the user from content for use, obtaining voice data of the user for the presented content, determining whether the presented content matches the acquired voice data, and a result of the determination , providing a reward to the user when the presented content and the acquired voice data match, and storing the acquired voice data in a database as the presented content and the acquired voice data match. do.

In the step of acquiring the user's voice data for the presented content, the voice data is received from the user terminal that has acquired the voice data by receiving the user's reading sound for the presented content through a built-in microphone.

The step of determining whether the presented content matches the acquired voice data includes converting the acquired voice data into text using STT (Speech To Text) technology, and converting the acquired voice data into text. An editing step, calculating the similarity between the presented content and the edited text using the Levenshtein algorithm (Levenshtein Distance), and converting the calculated similarity into a percentage to obtain a matching rate between the presented content and the acquired voice data. Includes calculating steps.

In the step of determining whether the presented content matches the acquired voice data, if the coincidence rate between the presented content and the acquired voice data is more than a preset threshold, the presented content and the acquired voice data are considered to match. and, if the coincidence rate between the presented content and the acquired voice data is less than a preset threshold, determining that the presented content and the acquired voice data do not match.

The text reading service providing method further includes discarding the acquired voice data when the presented content and the acquired voice data do not match.

According to another aspect of the present invention, an apparatus for providing a text reading service that operates in conjunction with a user terminal is disclosed.

An apparatus for providing a text reading service according to an embodiment of the present invention includes a memory for storing instructions and a processor for executing the instructions, wherein the instructions include collecting reading content including images and scripts. , receiving a reading participation request from a user, selecting and presenting content to be read by the user from among the collected reading content according to the reading participation request, and obtaining the user's voice data for the presented content. , determining whether the presented content matches the acquired voice data; as a result of the determination, if the presented content and the acquired voice data match, providing a reward to the user; and providing a reward to the user. A method of providing a text reading service is performed, including the step of storing the obtained voice data in a database as the obtained voice data matches.

An apparatus and method for providing a text reading service according to an embodiment of the present invention collects reading content from one user, uses reward provision to induce other users to read the collected reading content, and obtains voice data, In addition to providing advertising agency services to users, voice data for various words can be collected.

1 is a flowchart showing a text reading service providing method performed by a text reading service providing device according to an embodiment of the present invention.
Figure 2 is a flowchart showing detailed steps of step S150 in Figure 1.
Figure 3 is a diagram showing an example of a screen output by a user terminal interoperating with a text reading service providing device according to an embodiment of the present invention.
Figure 4 is a diagram schematically illustrating the configuration of a text reading service providing device according to an embodiment of the present invention.

As used herein, singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as “consists of” or “comprises” should not be construed as necessarily including all of the various components or steps described in the specification, and some of the components or steps may be included in the specification. It may not be included, or it should be interpreted as including additional components or steps. In addition, terms such as "... unit" and "module" used in the specification refer to a unit that processes at least one function or operation, which may be implemented as hardware or software, or as a combination of hardware and software. .

Hereinafter, various embodiments of the present invention will be described in detail with reference to the attached drawings.

FIG. 1 is a flowchart showing a text reading service providing method performed by a text reading service providing device according to an embodiment of the present invention, FIG. 2 is a flowchart showing detailed steps of step S150 of FIG. 1, and FIG. 3 is a flowchart of the present invention. This is a diagram showing an example of a screen output by a user terminal that interacts with a text reading service providing device according to an embodiment.

The text reading service providing device according to an embodiment of the present invention may be implemented through a server capable of connecting to a network. For example, the server may perform a text reading service providing function and may be configured to include a text reading service providing device according to an embodiment of the present invention.

In this specification, a server is a computing device that performs a method for providing a text reading service according to an embodiment of the present invention, and may be one or two or more physical entities. When a server is divided into multiple physical entities and implemented, the management entity of each physical entity may be different. The server may include a DB, which refers to a functional and structural combination of software and hardware that stores information corresponding to each database. The DB may be implemented as at least one table, and the information stored in the database can be searched, stored, and It may also include a separate DBMS (Database Management System) for management. Additionally, it can be implemented in various ways, such as in the form of a linked-list, tree, or relational database, and includes all data storage media and data structures that can store information corresponding to the database.

Meanwhile, the text reading service providing device according to the embodiment of the present invention can link with the user terminal 300 to provide the text reading service according to the embodiment of the present invention to the user.

Hereinafter, a method for providing a text reading service according to an embodiment of the present invention will be described, focusing on FIG. 1, with reference to FIGS. 2 and 3.

In step S110, the text reading service providing device collects reading content. Here, reading content may include video and script.

For example, a text reading service providing device can upload advertising content for a small fee from a user who wants to advertise. Here, the user can purchase points through online payment or event participation, pay upload fees with the purchased points, and upload advertising content to a text reading service providing device.

In step S120, the text reading service providing device receives a reading participation request from the user.

In step S130, the text reading service providing device selects and presents content to be read by the user from among the reading content collected in response to the reading participation request.

For example, the text reading service providing device may randomly select content to be read from among the collected reading content, or select it in a preset order, such as sort order, most recent creation order, oldest creation order, etc.

In step S140, the text reading service providing device acquires the user's voice data for the presented content.

For example, referring to FIG. 3, the user terminal 300 outputs a product advertisement screen indicating that rewards (points) can be provided by participating in viewing the advertisement, and receives a reading participation request from the user through a participation button. It can be received and transmitted to a text reading service provider device. Subsequently, the text reading service providing device may transmit a content and voice data acquisition command including a script to be read to the user terminal 300 in response to a reading participation request. Subsequently, upon receiving the voice data acquisition command, the user terminal 300 may output a reading instruction message, a script to be read, and a microphone button on the screen, as shown in FIG. 3 . Accordingly, after checking the screen of the user terminal 300, the user can press the microphone button according to the reading instruction message and read the presented script aloud. At this time, the user terminal 300 acquires voice data by receiving the user's reading sound for the presented script using the built-in microphone, and as shown in FIG. 3, acquires voice data using STT (Speech To Text) technology. The voice data can be converted into text and output on the screen (my lines), and the acquired voice data can be transmitted to a text reading service provider.

In step S150, the text reading service providing device determines whether the presented content matches the acquired voice data.

Hereinafter, with reference to FIG. 2, detailed steps of step S150 will be described.

In step S151, the text reading service providing device converts the acquired voice data into text using STT (Speech To Text) technology.

In step S152, the text reading service providing device edits the text converted from the acquired voice data.

In other words, the text reading service providing device removes English letters (lowercase and uppercase letters), Korean letters, special characters other than numbers, spaces for spacing, etc. from the converted text.

For example, assuming the converted text is "Hello? Have you eaten?!", it can be edited to "Hello, have you eaten?"

In step S153, the text reading service providing device calculates the similarity between the presented content and the edited text using the Levenshtein algorithm (Levenshtein Distance).

In step S154, the text reading service providing device converts the calculated similarity into a percentage to calculate the matching rate between the presented content and the acquired voice data.

According to another embodiment, the text reading service providing device may process one sentence as 0 points if two or more words are different, and may process it as a full score if only special characters are excluded for one sentence.

For example, if the script of the presented content is [Let the East Sea and Mt. Baekdu dry and wear down], and the text converted from the voice data is [Let the seafood and Mt. Baekdu dry and grow] or [Until the companions and Mt. Baekdu dry and grow]. , Since two or more words are different, it can be treated as 0 points. Also, if the script of the presented content is [Father, "Have you eaten?"] and the text converted from voice data is [Father, have you eaten?], only special characters are excluded, so it can be processed as 50 points.

Referring again to FIG. 1, in step S160, if the match rate between the presented content and the acquired voice data is greater than or equal to a preset threshold as a result of the determination in step S150, the text reading service providing device determines that the presented content and the acquired voice data are It is considered a match, and a certain reward is provided to the user.

In step S170, the text reading service providing device stores the acquired voice data in the database as the presented content matches the acquired voice data.

In step S180, if, as a result of the determination in step S150, the match rate between the presented content and the acquired voice data is less than a preset threshold, the text reading service providing device considers the presented content and the acquired voice data to be inconsistent, and Discard voice data.

Figure 4 is a diagram schematically illustrating the configuration of a text reading service providing device according to an embodiment of the present invention.

Referring to FIG. 4, a text reading service providing device according to an embodiment of the present invention includes a processor 10, a memory 20, a communication unit 30, and an interface unit 40.

The processor 10 may be a CPU or a semiconductor device that executes processing instructions stored in the memory 20.

Memory 20 may include various types of volatile or non-volatile storage media. For example, memory 20 may include ROM, RAM, etc.

For example, the memory 20 may store instructions for performing a method for providing a text reading service according to an embodiment of the present invention.

The communication unit 30 is a means for transmitting and receiving data with other devices through a communication network.

The interface unit 40 may include a network interface and a user interface for accessing the network.

Meanwhile, the components of the above-described embodiment can be easily understood from a process perspective. In other words, each component can be understood as a separate process. Additionally, the processes of the above-described embodiments can be easily understood from the perspective of the components of the device.

Additionally, the technical contents described above may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiments or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -Includes optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. A hardware device may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

The above-described embodiments of the present invention have been disclosed for illustrative purposes, and those skilled in the art will be able to make various modifications, changes, and additions within the spirit and scope of the present invention, and such modifications, changes, and additions will be possible. should be regarded as falling within the scope of the patent claims below.

10: processor
20: memory
30: Department of Communications
40: interface part

Claims (6)

In a method of providing a text reading service performed by a text reading service providing device linked to a user terminal,
Collecting reading content including videos and scripts;
Receiving a reading participation request from a user;
selecting and presenting content to be read by the user from among the collected reading content in response to the reading participation request;
Obtaining the user's voice data for the presented content;
determining whether the presented content matches the acquired voice data;
As a result of the determination, if the presented content matches the acquired voice data, providing a reward to the user; and
A method of providing a text reading service, including the step of storing the acquired voice data in a database as the presented content matches the acquired voice data.
According to paragraph 1,
The step of acquiring the user's voice data for the presented content is,
A method of providing a text reading service, comprising receiving the user's reading sound for the presented content through a built-in microphone and receiving the voice data from the user terminal that has acquired the voice data.
According to paragraph 1,
The step of determining whether the presented content matches the acquired voice data includes:
Converting the obtained voice data into text using STT (Speech To Text) technology;
editing text converted from the acquired voice data;
calculating the similarity between the presented content and the edited text using the Levenshtein algorithm (Levenshtein Distance); and
A method for providing a text reading service, comprising converting the calculated similarity into a percentage to calculate a matching rate between the presented content and the acquired voice data.
According to paragraph 3,
The step of determining whether the presented content matches the acquired voice data includes:
If the matching rate between the presented content and the acquired voice data is greater than a preset threshold, considering the presented content and the acquired voice data to match; and
If the coincidence rate between the presented content and the acquired voice data is less than a preset threshold, determining that the presented content and the acquired voice data do not match is a method for providing a text reading service.
According to paragraph 1,
The method of providing the text reading service is,
If there is a discrepancy between the presented content and the acquired voice data, the method further includes discarding the acquired voice data.
In a text reading service providing device that interfaces with a user terminal,
Memory for storing instructions; and
Including a processor that executes the instructions,
The command is:
Collecting reading content including videos and scripts;
Receiving a reading participation request from a user;
selecting and presenting content to be read by the user from among the collected reading content in response to the reading participation request;
Obtaining the user's voice data for the presented content;
determining whether the presented content matches the acquired voice data;
As a result of the determination, if the presented content matches the acquired voice data, providing a reward to the user; and
A text reading service providing method comprising the step of storing the acquired voice data in a database as the presented content matches the acquired voice data.

Images