KR102244447B1 - Method and server for providing image tlanslation service - Google Patents

Abstract

In one embodiment of the present invention, disclosed is a method for generating an arcade image by performing conversion on text existing in an image file performed by one or more processors of a computing device. The method comprises the steps of: recognizing one or more character images included in the image file to obtain original text information; determining the adequacy of the original text information by performing a quality check on the obtained original text information; determining to transmit a translation interface including the original text information to a user terminal based on the adequacy determination result; receiving translation text information corresponding to the one or more character images from the user terminal through the translation interface; and generating a translated text image based on the one or more character images and the received translated text information, and displaying the generated translated text image as an upper layer of the one or more character images to generate an arcade image file.

Description

Method and server for providing image translation service {METHOD AND SERVER FOR PROVIDING IMAGE TLANSLATION SERVICE}

The present disclosure relates to image translation technology, and more specifically, to generate an image related to translation by translating a text image existing in an image file, and to translate an image related to the generated translation in a region corresponding to the text image. This is to provide an image file.

Today, as Internet use becomes more common, users can obtain a variety of information through Internet search. Specifically, after accessing an Internet search site through a terminal capable of accessing the Internet, users may search for various contents related to news, knowledge, games, and communities, and obtain information on web pages or files.

On the other hand, as the living environment is diversifying today, employment or entry into the country as well as overseas is active, and the need for communication between users of various nationalities is increasing due to platforms such as sns. In this environment, acquisition of various contents through overseas sites is being activated. However, if the text included in the corresponding content is a foreign language that the user does not use, it may be difficult to obtain desired information. In order to increase the utilization of Internet search by these users and to obtain desired information from numerous contents, operators of many web sites provide web translation services. Korean Patent Application Publication No. 2000-0072108 discloses a method of supporting multiple languages on the Internet using a language translator.

Meanwhile, a web page provided to a user may include an image, and the image may include one or more characters or symbols. However, a typical web translation service is performed only on texts included in the corresponding content.

That is, when an image, video, text, etc. are included in the corresponding content, translation is performed and provided only for a portion corresponding to the text. In other words, if the content desired to be translated is in the form of an image or a video, it may not be translated by the web translation service. For example, when the main information that the user wants to acquire is displayed in the form of an image or a video, the main information may not be translated, but only the surrounding text may be translated.

In order to solve such a problem, translation services through various languages may be provided through character reading technology such as OCR (Optical Character Recognition). However, for services such as reading character symbols from images or translating text on images, an expensive device such as a character reading device or a translation device must be provided. There is a risk of causing.

Therefore, in the industry, there is a demand for a server that provides a translation service corresponding to the characters included in the image by inducing the voluntary participation of a large number of users who can use various languages and connecting with users who want to receive the image translation service. Can exist.

The problem to be solved by the present disclosure is to solve the above-described problem, and generate an image related to translation by translating a character image existing in an image file, and an image related to the translation generated in a region corresponding to the corresponding character image. It is to provide an image file that has been reflected and translated.

Problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems that are not mentioned will be clearly understood by those skilled in the art from the following description.

Disclosed is a method for generating an arcade image by performing conversion on text existing in an image file performed by one or more processors of a computing device according to various embodiments of the present disclosure for solving the above-described problem. The method includes the steps of acquiring original text information by recognizing one or more text images included in an image file, determining appropriateness for the original text information by performing a quality check on the obtained original text information, the Determining to transmit a translation interface including the original text information to a user terminal based on the appropriateness determination result, receiving translated text information corresponding to the one or more character images from the user terminal through the translation interface, and Generating a translated text image based on the at least one character image and the received translated text information, and displaying the generated translated text image as an upper layer of the at least one character image to generate an arcade image file. I can.

In an alternative embodiment, the step of acquiring original text information by recognizing one or more text images included in the image file includes one or more text images included in the image file through a text recognition model including one or more network functions. It may include at least one of acquiring the original text information corresponding to or acquiring the original text information from the user terminal through an original text interface.

In an alternative embodiment, the step of obtaining the original text information from the user terminal through the original text interface comprises generating an original text interface including some of one or more text images included in the image file and transmitting the text to the user terminal. And receiving the original text information based on a user input of the user terminal through the original text interface.

In an alternative embodiment, the step of detecting a typing input of the user terminal for the original text interface, and when a typing input of more than a predetermined threshold number of times is detected based on a predetermined unit time, the typing input of the user terminal is converted to an error input. It may further include determining and determining not to expose the one or more text images for a predetermined time to the user terminal in which the error input is detected.

In an alternative embodiment, the step of determining adequacy of the original text information by performing a quality check on the original text information includes the number of other user terminals to perform the quality check based on the history information of the user terminal. Determining, in response to the determined number of other user terminals, transmitting an evaluation information input window including the one or more character images and the original text information to one or more other user terminals, the one or more other users Determining adequacy of the original text information based on quality evaluation information received from each terminal through the evaluation information input window, and giving a reward to the user terminal based on the adequacy determination result. And the history information may include at least one of information on the number of input participation and cumulative quality evaluation information of the user terminal.

In an alternative embodiment, the step of identifying a user terminal matching the original text information included in the translation interface among a plurality of user terminals, and determining the identified user terminal as a user terminal to which the translation interface is to be transmitted. Can include.

In an alternative embodiment, determining to generate and transmit an evaluation interface including the original text information and the translated text information to one or more other user terminals, and translation evaluation information of each of one or more other user terminals through the evaluation interface It may further include the step of determining the appropriateness of the translated text information based on.

In an alternative embodiment, the evaluation interface may include a review information input area allowing a review input of the translated text information and one or more evaluation graphic objects for calculating an evaluation score for the translated text information.

In an alternative embodiment, generating a translated text image based on the at least one character image and the translated text information, and generating an arcade image by displaying the translated text image as an upper layer of the at least one character image, Identifying text image information including coordinate information, color information, and font information of the one or more text images, generating a translated text background image based on an average color value of an area corresponding to the coordinate information, shopping mall translation Generating the translated text image by reflecting the translated text information on a text background image based on the font information, and generating the arcade image file by displaying the translated text image as a higher layer in an area corresponding to the coordinate information It may include the step of.

According to another embodiment of the present disclosure, a computing device for generating an arcade image file by performing conversion on text existing in an image file is disclosed. The computing device includes a processor including one or more cores, a memory storing program codes executable in the processor, and a network unit for transmitting and receiving data to and from one or more user terminals, and the processor includes one or more characters included in an image file. Recognizing an image to obtain original text information, performing a quality check on the obtained original text information to determine adequacy of the original text information, and translation including the original text information based on the adequacy determination result Determine to transmit an interface to a user terminal, receive translation text information corresponding to the one or more text images from the user terminal through the translation interface, and translate based on the one or more text images and the received translation text information An arcade image file may be generated by generating a text image and displaying the generated translated text image as an upper layer of the one or more text images.

According to various embodiments of the present disclosure, an image related to translation is generated by translating a character image existing in an image file, and a translated image file is provided by reflecting the generated translation-related image in a region corresponding to the corresponding character image. By doing so, it is possible to provide convenience in obtaining information from images including texts related to various languages.

In addition, by inducing the voluntary participation of multiple users who can use various languages, it is possible to contribute to the creation of added value, such as providing learning or entertainment elements, and at the same time improving the accuracy of translation.

The effects of the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned will be clearly understood by those skilled in the art from the following description.

Various aspects are now described with reference to the drawings, wherein like reference numbers are used collectively to refer to like elements. In the examples that follow, for illustrative purposes, a number of specific details are presented to provide a comprehensive understanding of one or more aspects. However, it will be apparent that such aspect(s) may be practiced without these specific details.
1 is a conceptual diagram illustrating a system in which various aspects of a computing device for generating an arcade image by performing conversion on text existing in an image file according to an embodiment of the present disclosure may be implemented.
2 is a block diagram of a computing device for generating an arcade image by performing conversion on text existing in an image file according to an embodiment of the present disclosure.
3 is an exemplary diagram illustrating an original text interface and a translation interface related to an embodiment of the present disclosure.
4 is an exemplary diagram illustrating a translation interface related to an embodiment of the present disclosure.
5 is an exemplary diagram illustrating an evaluation interface and an arcade image related to an exemplary embodiment of the present disclosure.
6 is a flowchart illustrating steps for performing a method for generating an arcade image by performing conversion on text existing in an image file according to an exemplary embodiment of the present disclosure.
7 is a schematic diagram illustrating one or more network functions related to an embodiment of the present disclosure.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the present disclosure. However, it is clear that these embodiments may be implemented without this specific description.

As used herein, the terms "component", "module", "system" and the like refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or execution of software. For example, a component may be, but is not limited to, a process executed on a processor, a processor, an object, a thread of execution, a program, and/or a computer. For example, both an application running on a computing device and a computing device may be components. One or more components may reside within a processor and/or thread of execution. A component can be localized within a single computer. A component can be distributed between two or more computers. In addition, these components can execute from a variety of computer readable media having various data structures stored therein. Components can be, for example, through a signal with one or more data packets (e.g., data from one component interacting with another component in a local system, a distributed system, and/or a signal through another system and a network such as the Internet. Depending on the data being transmitted), it may communicate via local and/or remote processes.

In addition, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or”. That is, unless specified otherwise or is not clear from the context, "X employs A or B" is intended to mean one of the natural inclusive substitutions. That is, X uses A; X uses B; Or when X uses both A and B, "X uses A or B" can be applied to either of these cases. In addition, the term “and/or” as used herein should be understood to refer to and include all possible combinations of one or more of the listed related items.

In addition, the terms "comprises" and/or "comprising" should be understood to mean that the corresponding features and/or components are present. However, it is to be understood that the terms "comprising" and/or "comprising" do not exclude the presence or addition of one or more other features, elements, and/or groups thereof. In addition, unless otherwise specified or when the context is not clear to indicate a singular form, the singular in the specification and claims should be interpreted as meaning "one or more" in general.

Those of skill in the art would further describe the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein, including electronic hardware, computer software, or a combination of both. It should be recognized that it can be implemented as To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented in hardware or as software depends on the specific application and design restrictions imposed on the overall system. Skilled technicians can implement the described functionality in various ways for each particular application. However, such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

Description of the presented embodiments is provided so that a person of ordinary skill in the art of the present disclosure can use or implement the present disclosure. Various modifications to these embodiments will be apparent to those of ordinary skill in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure is not limited to the embodiments presented herein. This disclosure is to be accorded the widest scope consistent with the principles and novel features presented herein.

In the present specification, a computer means all kinds of hardware devices including at least one processor, and may be understood as encompassing a software configuration operating in the corresponding hardware device according to embodiments. For example, the computer may be understood as including all of a smartphone, a tablet PC, a desktop, a laptop, and a user client and application running on each device, and is not limited thereto.

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

Each of the steps described herein is described as being performed by a computer, but the subject of each step is not limited thereto, and at least some of the steps may be performed by different devices according to embodiments.

1 is a conceptual diagram illustrating a system in which various aspects of a computing device for generating an arcade image by performing conversion on text present in an image file according to an embodiment of the present disclosure may be implemented.

A system according to embodiments of the present disclosure may include a computing device 100, a user terminal 10, an external server 20, and a network. Components illustrated in FIG. 1 are exemplary, and additional components may be present or some of the components illustrated in FIG. 1 may be omitted. The computing device 100, the user terminal 10, and the external server 20 according to the embodiments of the present disclosure may mutually transmit and receive data for the system according to the exemplary embodiments of the present disclosure through a network.

Networks according to embodiments of the present disclosure include Public Switched Telephone Network (PSTN), x Digital Subscriber Line (xDSL), Rate Adaptive DSL (RADSL), Multi Rate DSL (MDSL), and Very High Speed DSL (VDSL). ), Universal Asymmetric DSL (UADSL), High Bit Rate DSL (HDSL), and local area network (LAN).

In addition, the networks presented here include Code Division Multi Access (CDMA), Time Division Multi Access (TDMA), Frequency Division Multi Access (FDMA), Orthogonal Frequency Division Multi Access (OFDMA), Single Carrier-FDMA (SC-FDMA), and Various wireless communication systems such as other systems can be used.

The network according to the embodiments of the present disclosure may be configured regardless of its communication mode, such as wired or wireless, and is composed of various communication networks such as a short-range communication network (PAN) and a local area network (WAN). Can be. In addition, the network may be a known World Wide Web (WWW), and a wireless transmission technology used for short-range communication such as infrared (IrDA) or Bluetooth may be used. The techniques described herein may be used not only in the networks mentioned above, but also in other networks.

According to an embodiment of the present disclosure, the user terminal 10 accesses the computing device 100 to receive information on one or more text images included in an image file, or translation test information corresponding to one or more text images. It may be a terminal related to a user for providing a. In FIG. 1, only one user terminal connected to the computing device 100 is illustrated as an example, but there may be a plurality of user terminals 10 connected to the computing device 100 in the present disclosure. For example, among a plurality of user terminals connected to the computing device 100, the first user terminal may be a terminal related to the first user to receive translated text information for one or more text images included in the image file. 2 The user terminal may be a terminal related to a second user for obtaining a reward by providing translated text information for one or more text images, and the third user terminal is used to determine whether the translated text information provided by the second user is appropriate. It may be a terminal related to a third user who performs a quality check on the device. The detailed description of each of the user terminals described above is only an example, and the present disclosure is not limited thereto. That is, in the present disclosure, a plurality of user terminals 10 may be provided corresponding to each of a plurality of users who are connected to the computing device 100 to receive various services.

The user terminal 10 may refer to any type of entity(s) in a system having a mechanism for communicating with the computing device 100. For example, the user terminal 10 includes a personal computer (PC), a notebook (note book), a mobile terminal, a smart phone, a tablet PC, and a wearable device. And the like, and may include all types of terminals capable of accessing a wired/wireless network. In addition, the user terminal 10 may include an arbitrary server implemented by at least one of an agent, an application programming interface (API), and a plug-in. In addition, the user terminal 10 may include an application source and/or a client application.

According to an embodiment of the present disclosure, the external server 20 may be a server that stores training data related to training of a character recognition model for generating original text information based on one or more character images included in an image file. . The character recognition model of the present disclosure may be a neural network model capable of OCR-based character recognition. Specifically, the character recognition model scans an image file to recognize one or more character images included in the image file, and classifies one or more character images into each character to recognize characters included in each of the at least one character image. have. In this case, the character recognition model may include one or more network functions, and one or more network functions may be learned through a deep learning algorithm. That is, the text recognition model may be a natural language processing model that recognizes one or more text images existing in an image file and generates original text information corresponding to the one or more text images.

Information stored in the external server 20 may be used as training data, verification data, and test data for training the neural network in the present disclosure. That is, the external server 20 may be a server that stores information on a data set for training the deep learning model of the present disclosure.

The computing device 100 of the present disclosure may construct a training data set based on video data of various categories and information on each video data from the external server 20, and perform one or more network functions through the training data set. By training the included neural network model, it is possible to generate a character recognition model that recognizes one or more character images from an image file to generate original text information. In addition, the computing device 100 of the present disclosure may perform augmentation on the learning data by transmitting the translated text information generated in response to the original text information to the external server 20.

The external server 20 is a digital device, such as a laptop computer, a notebook computer, a desktop computer, a web pad, and a mobile phone. The external server 20 may be a web server that processes a service. The types of servers described above are only examples, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the computing device 100 may obtain an image file. In this case, the image file may be an image file including one or more character images to be recognized. The text image may be an image including one text. For example, the text image may be an image including one letter'I'. The computing device 100 may receive and acquire an image file from the user terminal 10 through the network unit 110 or may acquire an image file through photographing through a camera unit (not shown).

According to an embodiment of the present disclosure, the computing device 100 may generate an arcade image file by performing conversion on one or more text images included in the image file, thereby providing translation information for the text image in the image file. have. In this case, the arcade image file may mean an image file in which one or more text images are replaced with translated text images translated into a specific language.

More specifically, the computing device 100 may acquire original text information by recognizing one or more text images included in the image file. The original text information may be information on characters corresponding to each of one or more character images. For example, the computing device 100 may acquire original text information corresponding to one or more text images using a text recognition model, or may acquire original text information from the user terminal 10 through an original text interface. The computing device 100 may determine the appropriateness of the acquired original text information, and when the appropriateness of the original text information is greater than or equal to a predetermined threshold, generate a translation interface including the original text information and transmit it to the user terminal. The translation interface is a user interface for receiving translated text information corresponding to one or more characters in an image file, and may include information on original text information. In other words, when the computing device 100 provides a translation interface to the user terminal 10, the translation interface is displayed on the user terminal 10 to communicate with the user for receiving translated text information corresponding to one or more character images. Interaction can be allowed. For example, the translation interface may include one or more input areas for allowing interaction with the user of the user terminal 10 in relation to the translated text information, or one or more graphic objects. That is, the user terminal 10 may receive and display a translation interface from the computing device 100, and the user responds to one or more text images based on the original text information included in the translation interface through the user terminal 10. You can enter the translated text information. Accordingly, the computing device 100 may receive translated text information corresponding to one or more text images from the user terminal 10 through the translation interface. In addition, the computing device 100 may generate a translated text image based on one or more text images and translated text information.

In detail, the computing device 100 may identify text image information corresponding to one or more text images in the image file. The character image information may include coordinate information, color information, and font information corresponding to one or more characters in the image file. For example, the text image information includes coordinate information indicating that the position of one or more text images is located at a first position in the image, color information indicating that the background color of one or more text images is yellow, the text color is black, and one or more text images. It is a font size of '11' and may include font information of the font'clear gothic'. The detailed description of coordinate information, color information, and font information included in the above-described text image information is only an example, and the present disclosure is not limited thereto. In addition, the computing device 100 may generate an arcade image by displaying the translated text image as an upper layer of the text image. That is, the arcade image generated by the computing device 100 may be an image file in which at least one character image displayed in the first language in the image file is changed to a translated image in the second language. In this case, the first language may be related to a starting language in which the user wants to perform translation, and the second language may be related to a destination language that the user wants to understand. For example, the first language may be a foreign language that is not frequently used by the user, and the second language may be a language related to the native language used by the user.

That is, the computing device 100 generates translated text information by performing translation on one or more text images written in a language (eg, a foreign language) that the user does not understand in the image file, and generates translated text information based on the generated translated text information. Arcade images can be created through conversion to image files. Accordingly, since the user may be provided with an arcade image generated through a language familiar to the user, information that the user does not understand in the image file can be easily obtained. In addition, the arcade image generated through the computing device 100 may include translated image information generated based on text image information of one or more existing text images. In other words, by including the translated image information generated based on the display area, color, font size, font, etc. of the character corresponding to the original text in the image before translation of the arcade image, It can provide a natural image.

In one embodiment, the computing device 100 may be a terminal or a server, and any type of device may be included. The computing device 100 is a digital device, and may be a digital device equipped with a processor, such as a laptop computer, a notebook computer, a desktop computer, a web pad, and a mobile phone, and equipped with a memory and a computing capability. The computing device 100 may be a web server that processes a service. The types of computing devices described above are only examples, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the computing device 100 may be a server providing a cloud computing service. More specifically, the computing device 100 may be a server that provides a cloud computing service that processes information with another computer connected to the Internet, not a user's computer, as a type of Internet basic computing. The cloud computing service may be a service that stores data on the Internet and can be used anytime, anywhere through an Internet connection without having to install data or programs required by a user on his or her computer. It can be easily shared and delivered with a click. In addition, the cloud computing service not only simply stores data on a server on the Internet, but also allows users to perform desired tasks using the functions of an application program provided on the web without installing a separate program. It may be a service that allows you to work while sharing. In addition, the cloud computing service may be implemented in at least one of an infrastructure as a service (IaaS), a platform as a service (PaaS), a software as a service (SaaS), a virtual machine-based cloud server, and a container-based cloud server. . That is, the computing device 100 of the present disclosure may be implemented in the form of at least one of the above-described cloud computing services. The detailed description of the cloud computing service described above is merely an example, and may include any platform for constructing the cloud computing environment of the present disclosure.

A detailed configuration of a method of generating an arcade image by performing conversion on text existing in an image file in the present disclosure and effects thereof will be described later with reference to FIG. 2.

2 is a block diagram of a computing device for generating an arcade image by performing conversion on text existing in an image file according to an embodiment of the present disclosure.

As shown in FIG. 2, the computing device 100 may include a network unit 110, a memory 120, and a processor 130. Components included in the above-described computing device 100 are exemplary, and the scope of the present disclosure is not limited to the above-described components. That is, additional components may be included or some of the above-described components may be omitted according to implementation aspects of the embodiments of the present disclosure.

According to an embodiment of the present disclosure, the computing device 100 may include a user terminal 10 and a network unit 110 that transmits and receives data to and from the external server 20. The network unit 110 converts text existing in an image file according to an embodiment of the present disclosure to perform a method for generating an arcade image and a training data set for training a neural network model Can be transmitted and received with other computing devices, servers, etc. That is, the network unit 110 may provide a communication function between the computing device 100 and the user terminal 10 and the external server 20. For example, the network unit 110 may receive original text information, translated text information, and evaluation information that is a criterion for determining the appropriateness of each text information from the user terminal 10. For another example, the network unit 110 may receive a training data set for training the character recognition model of the present disclosure from the external server 20. Additionally, the network unit 110 may allow information transfer between the computing device 100 and the user terminal 10 and the external server 20 by calling a procedure to the computing device 100.

The network unit 110 according to an embodiment of the present disclosure includes a public switched telephone network (PSTN), x Digital Subscriber Line (xDSL), Rate Adaptive DSL (RADSL), Multi Rate DSL (MDSL), and VDSL ( Various wired communication systems such as Very High Speed DSL), Universal Asymmetric DSL (UADSL), High Bit Rate DSL (HDSL), and local area network (LAN) can be used.

In addition, the network unit 110 presented in the present specification includes Code Division Multi Access (CDMA), Time Division Multi Access (TDMA), Frequency Division Multi Access (FDMA), Orthogonal Frequency Division Multi Access (OFDMA), and SC-FDMA ( Single Carrier-FDMA) and various wireless communication systems can be used.

In the present disclosure, the network unit 110 may be configured regardless of its communication mode, such as wired and wireless, and may be configured with various communication networks such as a short-range communication network (PAN) and a local area network (WAN). I can. In addition, the network may be a known World Wide Web (WWW), and a wireless transmission technology used for short-range communication such as infrared (IrDA) or Bluetooth may be used. The techniques described herein may be used not only in the networks mentioned above, but also in other networks.

According to an embodiment of the present disclosure, the memory 120 may store a computer program for performing a method for generating an arcade image by performing conversion on text existing in an image file according to an embodiment of the present disclosure. In addition, the stored computer program may be read and driven by the processor 130. In addition, the memory 120 may store information in any form generated or determined by the processor 130 and information in any form received by the network unit 110. Also, the memory 120 may store information related to single image data. For example, the memory 120 includes input/output data (eg, original text information corresponding to one or more character images, translation text information corresponding to one or more character images, and translation image corresponding to the translated text information). The arcade image, etc., which is generated as is reflected) can be temporarily or permanently stored.

According to an embodiment of the present disclosure, the memory 120 is a flash memory type, a hard disk type, a multimedia card micro type, and a card type memory (for example, SD or XD memory), RAM (Random Access Memory, RAM), SRAM (Static Random Access Memory), ROM (Read-Only Memory, ROM), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read) -Only Memory), magnetic memory, magnetic disk, and optical disk. The computing device 100 may operate in connection with a web storage that performs a storage function of the memory 120 on the Internet. The description of the above-described memory is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the processor 130 may be composed of one or more cores, and a central processing unit (CPU) of a server, a general purpose graphics processing unit (GPGPU), It may include a processor for data analysis and deep learning, such as a tensor processing unit (TPU).

The processor 130 may read a computer program stored in the memory 120 to process data for deep learning according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor 130 may perform an operation for learning a neural network. The processor 130 processes input data for learning in deep learning (DL), extracts features from the input data, calculates errors, and uses backpropagation to update the weights of the neural network. You can perform calculations.

In addition, the processor 130 may process learning of a network function by at least one of a CPU, a GPGPU, and a TPU. For example, the CPU and GPGPU can work together to learn network functions and classify data using network functions. In addition, in an embodiment of the present disclosure, learning of a network function and data classification using a network function may be processed by using processors of a plurality of computing devices together. In addition, the computer program executed in the computing device according to an embodiment of the present disclosure may be a CPU, a GPGPU, or a TPU executable program.

In the present specification, the network function may be used interchangeably with an artificial neural network or a neural network. In the present specification, the network function may include one or more neural networks, and in this case, the output of the network function may be an ensemble of outputs of one or more neural networks.

The processor 130 may provide a character recognition model according to an embodiment of the present disclosure by reading a computer program stored in the memory 120. According to an embodiment of the present disclosure, the processor 130 may perform calculation to obtain original text information from one or more character images. According to an embodiment of the present disclosure, the processor 130 may perform calculation for training a character recognition model.

According to an embodiment of the present disclosure, the processor 130 may typically process the overall operation of the computing device 100. The processor 130 may provide or process appropriate information or functions to the user terminal by processing signals, data, information, etc. that are input or output through the above-described components, or by running an application program stored in the memory 120. have.

According to an embodiment of the present disclosure, the processor 130 may obtain an image file. In this case, the image file may be obtained from the user terminal 10 through the network unit 110. The image file may be a file related to an image captured by the user terminal 10 or a file related to an image captured through a camera module provided in the user terminal 10. Also, the image file may be a file including one or more images of characters to be recognized. The character image may be an image including one or more characters written in various language texts. For example, the character image may be an image including one character of'I' (ie, a character written in Korean). In an additional embodiment, the computing device 100 may further include a separate camera unit (not shown), and may acquire an image file through photographing through the corresponding camera unit.

According to an embodiment of the present disclosure, the processor 130 may obtain original text information by recognizing one or more text images included in an image file. The original text information may be information on characters corresponding to each of one or more character images. For example, the processor 130 may recognize one or more text images included in the first image file to obtain original text information called'Odolbone'. For another example, the processor 130 may recognize one or more text images included in the second image file to obtain original text information such that'the head of both feathers is the first upper part of the cow and the light taste is excellent. The processor 130 may acquire original text information corresponding to one or more text images using a text recognition model, or acquire original text information from the user terminal 10 through an original text interface. The detailed description of the above-described original text information is only an example, and the present disclosure is not limited thereto.

In detail, the processor 130 may obtain original text information corresponding to one or more text images included in an image file through a text recognition model including one or more network functions. The processor 130 may recognize a character included in each of the one or more character images by classifying one or more character images included in the image file into each character through a character recognition model. The processor 130 responds to one or more text images by receiving training data for training a character recognition model through the external server 20, and learning about one or more network functions using the received training data Thus, it is possible to create a character recognition model that generates original text information. That is, the character recognition model may include one or more network functions, and one or more network functions may be learned through a deep learning algorithm. The processor 130 may perform character segmentation on an image file, and may perform segmentation on each character. That is, the processor 130 may recognize one or more text images included in the image file.

For example, the processor 130 may extract a feature of a character image through a character recognition model and extract a score for each of one or more classes. The class may be a character that a character image means. For example, each of the one or more classes may be a, a, a, a, a, etc. The processor 130 may classify the character image as a character based on the score value for each class of the character image. As a result of calculating the character image through the character recognition model, the processor 130 classifies the character image into a class having the highest score value, and determines a character included in each of the at least one character image. Original text information can be obtained. The detailed description of the class of the character image described above is only an example, and the present disclosure is not limited thereto.

Also, the processor 130 may obtain the original text information from the user terminal 10 through the original text interface. Specifically, the processor 130 may determine to generate the original text interface 200 including one or more text images included in the image file and transmit it to the user terminal 10. The original text interface 200 may be a user interface displayed on the user terminal 10 to obtain original text information corresponding to one or more text images from a user. The original text interface 200 may include one or more text images composed of text in a specific language.

The user terminal 10 to which the processor 130 provides the original text interface 200 is at least one of a plurality of user terminals that are connected to a server linked to the computing device 100 or subscribed to a server linked to the computing device. It may be one user terminal. In other words, the processor 130 obtains original text information corresponding to one or more text images from the user terminal by determining a user terminal to which the original text interface 200 is to be transmitted, among a plurality of user terminals linked to the computing device 100. can do. In this case, the user terminal for which the processor 130 determines (or selects) the terminal to which the original text interface 200 is to be transmitted (ie, user terminals for obtaining the original text information) can utilize a language related to one or more text images. It may be a terminal related to a user. For example, if the first user terminal is a terminal related to a user using English as a native language, the processor 130 may transmit the original text interface 200 including text images corresponding to English to the corresponding first user terminal. You can decide. For another example, when the second user terminal is a terminal related to a user who uses Korean as a native language, the processor 130 requests to transmit the original text interface 200 including text images corresponding to Korean to the corresponding second user terminal. You can decide. The detailed description of the language related to each user terminal described above is only an example, and the present disclosure is not limited thereto.

In a further embodiment, the processor 130 is based on the participation history information or language proficiency of each of the plurality of user terminals associated with the computing device 100, the extent to which the original text interface 200 is exposed to each of the plurality of user terminals (i.e. , The number of times the original text interface is provided) can be determined. For example, participation history information and language proficiency may be identified through activity information or personal information of each user terminal. Specifically, the processor 130 is one or more user terminals 10 for acquiring original text information through the original text interface 200 among a plurality of user terminals based on the existing participation history information or language proficiency level of each of the plurality of user terminals. Can be determined. For example, the participation history information of the first user terminal includes information that the number of existing participation (that is, the number of responses of the user terminal through the original text interface in the past) is 10, and the participation history information of the second user terminal is When the information that the existing number of participation is 20 is included, the processor 130 may increase the number of times the original text interface 200 is exposed to the first user terminal rather than the second user terminal or determine a shorter exposure time period. For another example, if the third user terminal has a higher language proficiency for'English', which is a specific language than the fourth user terminal, the processor 130 may have the original text interface 200 on the third user terminal rather than the fourth user terminal. You can increase the number of exposures or shorten the exposure time period. The detailed description of the participation history information or language proficiency level of each user terminal described above is only an example, and the present disclosure is not limited thereto.

In other words, the processor 130 may determine to expose the original text interface 200 to a user terminal having a large participation history (ie, a user terminal having a high participation rate) or a user terminal having a higher language proficiency level. That is, the probability of receiving the original text interface may increase as a user terminal with a large past participation history or a high language proficiency for a specific language increases. Accordingly, a response rate of receiving original text information corresponding to one or more character images may be improved.

More specifically, referring to FIG. 3, the original text interface 200 includes an original text guide information display area 210, a text image display area 220, an original text input area 230, and an image skipping graphic object 240. And a selective storage graphic object 250.

The original guide information display area 210 included in the original text interface 200 may be an area in which guide information related to a corresponding interface is displayed. For example, as shown in FIG. 3, text information composed of Korean may be displayed such as "Please read and write the same characters in the box". In this case, text information displayed on the original guide information display area 210 may be displayed in a language corresponding to one or more text images. For example, when one or more character images are related to Korean, text information displayed on the original guide information display area 210 may be text related to Korean corresponding to the corresponding character image, and at least one character image is related to Chinese. In this case, the text information displayed on the original guide information display area 210 may be text related to Chinese corresponding to the corresponding character image. In addition, the original text guide information display area 210 may include information on rewards generated in relation to a user's input related to the original text information. Here, the reward may be information on a reward provided to the user of the user terminal 10 according to an input related to the original text information through the original text interface 200. For example, information on a reward generated in relation to a user's input may be '10P' as shown in FIG. 3. These rewards may be calculated by the processor 130. Specifically, the processor 130 may calculate a reward based on the number of one or more character images. For example, when the number of one or more character images related to the acquisition of original text information is 5, the processor 130 may calculate a reward to be provided to the user terminal as '12P'. For another example, when the number of one or more character images related to the acquisition of original text information is 10, the processor 130 may calculate a reward to be provided to the user terminal as '20P'. That is, based on the number of one or more character images, when it is expected that there are fewer original texts to be input corresponding to the character images, the processor 130 calculates less rewards, and If more text is expected, more rewards can be calculated. That is, by allocating different rewards according to the level of the user's effort to input the original text, it is possible to induce voluntary participation of users and provide an element of entertainment interest.

In other words, a user of the user terminal may be provided with guide information regarding a method of inputting original text information through the original text interface 200 and a reward according to the text information displayed on the original text guide information display area 210.

The image display area 220 included in the original text interface 200 may be an area in which one or more text images are displayed. Here, the one or more text images displayed on the image display area 220 may be an image that serves as a reference for a user to input text into the original text input area 230. In addition, one or more text images may be related to an image file acquired through a camera module provided in the user terminal 10. For example, the user may capture a character written in a language that he or she does not understand through the user terminal 10 to obtain an image file including the character and transmit it to the processor 130. For a specific example, when a user who uses English wants to obtain information on text written in Korean, the text is captured through the camera module of the user terminal 10 to obtain an image file including one or more text images. Then, the obtained image file may be transmitted to the processor 130. When receiving an image file including one or more text images, the processor 130 may generate the original text interface 200 to display one or more text images included in the image file on the image display area 220. That is, the original text interface 200 received by the user terminal 10 may display one or more text images on the image display area 220. A user of the user terminal 10 may input information related to the original text in the original text input by referring to one or more text images displayed on the image display area 220. The image display area 220 may allow a user's adjustment input for adjustment of one or more text images. The user's adjustment input may be related to adjusting the size or direction of one or more text images. That is, the text image display area 220 may enlarge/reduce one or more text images in response to a user's adjustment input, or may be rotated in a clockwise/counterclockwise direction to be displayed. Accordingly, a user's readability of one or more text images may be improved.

The original text input area 230 included in the original text interface 200 may be an area for receiving a user input of the user terminal in relation to the original text information. That is, the user of the user terminal 10 may perform input related to the original text in the original text input area 230 by referring to one or more text images displayed on the image display area 220. For example, as shown in FIG. 3, the user may input'odentang' in the original text input area 230 by referring to one or more text images displayed on the image display area 220. In addition, when the user completes the input to the original text input area 230, the user may apply a selection input for the selective storage graphic object 250, and the processor 130 Text information input into the original text input area 230 in response to an input of may be obtained as original text information. That is, when a user inputs'odentang' in the original text input area 230 and then applies an input to the selectively stored graphic object 250, the processor 130 transfers'odentang' to one or more text image objects. It can be obtained as the corresponding original text information.

The image skipping graphic object 240 included in the original text interface 200 may be a graphic object that receives a user's input for converting a text image displayed on the image display area 220 into another text image. Specifically, when a user's input for the image skipping graphic object 240 is received, the processor 130 converts the image file currently displayed on the image display area 220 into another image file including another text image. I can.

For example, an image file including one or more text images may be displayed in the image display area 220, and a user inputs an input related to the original text information in the original text input area 230 by referring to the corresponding text image. I can make it. However, it may be difficult for a user to identify one or more text images displayed on the corresponding image display area 220. For example, as the user does not recognize a combination of one or more text images or is acquired through a low resolution of the text image, readability may be degraded. For another example, the user may wish to switch the image file displayed on the image display area 220 in order to obtain a high reward. In this case, the user may apply an input to the image skipping graphic object 240, and the processor 130 may generate an image file including one or more text images displayed on the image display area 220 in response to the input. You can switch to another image file containing different text images. That is, as the image file including different character images can be switched through the image skipping graphic object 240 included in the original text interface 200, the original text corresponding to various image files (or various character images) Convenience of obtaining information can be improved.

That is, as described above, the original text interface 200 provided by the processor 130 may be displayed on the user terminal 10. In addition, original text information may be obtained according to an interaction with a user through each display area included in the original text interface and a graphic object. This has the advantage of obtaining the original text information of improved quality than the obtaining of the original text information using a character recognition model. For example, a character recognition model that outputs original text information corresponding to one or more character images through training of a neural network is accurate when the training data is insufficient or when the legibility of the character images in the corresponding image file is insufficient. There is a risk of outputting the original text information lacking in However, in the present disclosure, the configuration of acquiring the original text information by using the original text interface is obtained in relation to the direct input of users of each of a plurality of user terminals, and thus relates to a text image that the machine cannot identify or read. Thus, it may be possible to obtain original text information with improved accuracy.

According to an embodiment of the present disclosure, the processor 130 may identify a typing input of the user terminal 10 for the original text interface 200. Specifically, the processor 130 may identify a typing input of the user terminal 10 for the original text input area 230 and the selectively stored graphic object 250 included in the original text interface 200. For example, in relation to the original text interface displayed on the first user terminal 10, the processor 130 may input a specific text in the original text input area 230 and the selection stored in the It is possible to identify the point of time to apply the input to the user.

In addition, when a typing input of more than a predetermined threshold number of times is identified based on a predetermined unit time, the processor 130 may determine the typing input of the user terminal 10 as an error input. For a specific example, the predetermined unit time is 5 seconds, the predetermined threshold number of times is 2, and the first user for the original text input area 230 and the selectively stored graphic object 250 displayed on the first user terminal. If the information indicating that the typing input has occurred 10 times within 10 seconds is included, the processor 130 may determine the typing input of the corresponding user terminal 10 as an error input. The timing input related to the error input may be discarded in the process of obtaining the original text information. That is, when the user's input related to the input of the original text information is abnormally fast, the processor 130 may determine an error input (eg, abusing) as a typing input related to the user terminal 10. Accordingly, it is possible to improve the accuracy of the original text information secured through the original text interface 200 by preventing indiscriminate input of information related to abnormal activities.

In addition, the processor 130 may determine not to expose one or more text images to the user terminal 10 related to the error input for a predetermined period of time. For example, when the typing input related to the second user terminal is determined as an error input by the processor 130, one or more text images may not be exposed to the second user terminal for a predetermined period of time (eg, 24 hours). That is, the processor 130 may induce a virtuous cycle in the system by identifying a user terminal related to an error input (ie, a negative input) and imposing a penalty for a predetermined period on the identified user terminal. In other words, it is possible to induce correct participation of user terminals by not exposing one or more text images so that the acquisition of the reward is restricted for a predetermined period of time with respect to the user terminal unfairly trying to obtain a reward. That is, the processor 130 may induce a virtuous cycle of user terminals in the system by imposing a penalty on the user terminal related to an illegal input, thereby causing the acquisition of the original text information of improved quality.

In an additional embodiment, the processor 130 may determine whether to use the original text interface based on the output accuracy of the character recognition model. Specifically, the processor 130 may determine whether to transmit the original text interface 200 to the user terminal based on the score regarding the output of the character recognition model. The processor 130 may output original text information corresponding to one or more text images by processing an image file including one or more text images as input to a text recognition model. In this case, the processor 130 may determine whether to transmit the original text interface 200 to the user terminal based on a score value related to the output of the original text information.

For a specific example, when the character recognition model outputs first text information by inputting the first image file, and the score value related to the output of the first text information is 80, and the predetermined threshold score value is 85, the processor 130 may determine to transmit the original text interface 200 to the user terminal. Accordingly, original text information may be obtained in response to an input of the user terminal to the original text interface 200.

For another example, if the character recognition model outputs second text information by inputting the second image file, and the score value related to the output of the second text information is 90, and the predetermined threshold score value is 85, the processor 130 may not transmit the original text interface 200 to the user terminal. That is, when the accuracy of the output of the character recognition model is greater than or equal to the threshold value, the processor 130 may obtain the original text information through the output of the corresponding character recognition model.

That is, when the score related to the output of the character recognition model is greater than or equal to the threshold value, the processor 130 may obtain the original text information through the corresponding output. In addition, if the score related to the output of the character recognition model is less than the threshold, the processor 130 determines that the accuracy of the model has not reached the threshold, and transmits the original text interface to the user terminal, thereby receiving the original text information. have. Accordingly, as it is determined whether to acquire the original text information through the user terminal according to the output accuracy of the character recognition model, the response speed of the process of obtaining the original text information can be improved.

According to an embodiment of the present disclosure, the processor 130 may determine the appropriateness of the original text information by performing a quality check on the original text information. Specifically, the processor 130 may determine the number of other user terminals to perform quality inspection based on the history information of the user terminal. The history information may include at least one of input participation number information of the user terminal or cumulative quality evaluation information. The input participation number information may be information on a participation history related to the number of times the user terminal 10 transmits the original text information to the processor 130 through the original text interface. The cumulative quality evaluation information may be related to quality evaluation information of other users with respect to the original text information transmitted from the user terminal 10 to the processor 130.

For a specific example, when the input participation number information of the first user terminal 10 includes information indicating that the original text information has been transmitted multiple times in the past, the processor 130 receives it from the first user terminal 10. The number of other user terminals to perform quality check on one original text information may be determined as '2'. For another example, when the input participation number information of the second user terminal 10 includes information that the original text information history does not exist at the past time, the processor 130 The number of other user terminals to perform quality check on the original text information may be determined as '5'. For another example, when the accumulated quality evaluation information of the third user terminal 10 is 3 points, and the accumulated quality evaluation information of the fourth user terminal 10 is 9 points, the processor 130 is the third user terminal ( 10) It is possible to determine the number of other user terminals to perform quality check on the original text information received from '6'. The number can be determined as '2'. The detailed description of the input participation count information, accumulated quality evaluation information, and the number of other user terminals described above are only examples, and the present disclosure is not limited thereto.

That is, the processor 130, when there is a number of past participation histories in the input participation count information of the user terminal that has transmitted the original text information, or when the past quality evaluation score of other users is high in the accumulated quality evaluation information, the corresponding It is possible to determine a small number of other user terminals for quality evaluation of original text information. In other words, the number of different user terminals for evaluation of the original text information obtained from each terminal can be determined differently based on the information of each user terminal that has transmitted the original text information (input participation count information and cumulative quality evaluation information). have. This may have an effect of maximizing response speed for evaluation by determining the number of other user terminals for evaluation in consideration of characteristics of each user terminal. In other words, the original text information of the user terminal that needs to be verified is evaluated through more other user terminals, and the original text information of the verified user terminal is evaluated through fewer other user terminals, thereby evaluating the quality of the original text information. Can lead to optimization of the response speed.

In addition, the processor 130 may determine to transmit an evaluation information input window including one or more character images and original text information to one or more other user terminals in response to the determined number of other user terminals. Specifically, the processor 130 may determine other user terminals related to the evaluation based on the past participation history information and the accumulated quality evaluation information of the user terminal 10, and provide an evaluation information input window to each of the determined You can decide what to send. In this case, the evaluation information input window may be an input window transmitted to each of the other user terminals for determining whether the original text information obtained through the user terminal 10 is appropriate.

For a specific example, the processor 130 transmits the second user terminal and the third user terminal to the first original text information transmitted from the first user terminal based on the past participation history information and the accumulated quality evaluation information to the first user terminal. It can be decided by another user terminal for evaluation. In this case, the processor 130 may determine to transmit an evaluation information input window including the first original text information to each of the second user terminal and the third user terminal. The evaluation information window may include one or more graphic objects for evaluation of original text information. For example, one or more graphic objects are composed of'bad','good','high','medium','low', or evaluation quality for the quality evaluation of other users related to the original text information. It may be configured through a plurality of numerical values related to, but is not limited thereto. That is, the processor 130 may determine to generate an evaluation information input window including the first original text information received from the first user terminal and transmit it to the second user terminal and the third user terminal.

In addition, the processor 130 may determine the appropriateness of the original text information based on the quality evaluation information received through the evaluation information input window from each of one or more other user terminals. Specifically, the processor 130 may acquire one or more quality evaluation information from each of the other user terminals through the evaluation information input window. In addition, the processor 130 may determine the appropriateness of the original text information based on one or more quality evaluation information received from each terminal and a predetermined evaluation criterion. For example, when the predetermined criterion is that the average quality evaluation information is 8 points or more, quality evaluation information of '8' and '9' is received from each of the second user terminal and the third user terminal through the evaluation information input window. , The processor 130 may determine that the average quality evaluation information of the terminals (ie, 8.5) satisfies a predetermined criterion and determine that the original text information is appropriate. For another example, the predetermined criterion is to receive 7 points or less of quality evaluation information from two or more users, and the evaluation information input window from each of the first user terminal, the second user terminal and the third user terminal is '6', When receiving quality evaluation information of '7' or '5', the processor 130 receives quality evaluation information of 6 points or less from at least two or more user terminals (ie, a first user terminal and a third user terminal). By identifying that, it can be determined that the original text information is not appropriate. Accordingly, the processor 130 may determine to discard the corresponding original text information. The detailed description of the above-described predetermined criteria and quality evaluation information received through each user terminal is only an example, and the present disclosure is not limited thereto.

In addition, the processor 130 may grant a reward to the user terminal 10 based on a result of determining the adequacy of the original text data information. In this case, the reward may be related to points given to the user terminal 10 in relation to the creation of original data information. Can be. For example, when it is determined that the first original text data received through the first user terminal 10 is appropriate, the processor 130 may give the first user terminal 10 a reward of '10P'. The detailed numerical description related to the above-described reward is merely an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the processor 130 may obtain translated text information from the user terminal 10 through a translation interface. Specifically, the processor 130 may determine to generate the translation interface 300 including the original text information based on a result of determining the adequacy of the original text information and transmit it to the user terminal 10. For example, when it is determined that the original text information is appropriate, the processor 130 may determine to generate and transmit the translation interface 300 including the original text information to the user terminal. The translation interface 300 may be a user interface provided to the user terminal 10 to obtain translated text information corresponding to the original text information from a user. As the original text information of the present disclosure is obtained in response to one or more text images, the translated text information generated in response to the original text information may be text information related to translation on one or more text images. The translation interface 300 may include one or more character images and original text information composed of text in a specific language.

In this case, the processor 130 may determine one or more other user terminals for transmitting the translation interface. Specifically, the processor 130 may identify a user terminal matching the original text information included in the translation interface among a plurality of user terminals. In addition, the processor 130 may determine the identified user terminal as a user terminal to which the translation interface is to be transmitted. For example, when the original text information is related to Korean, the processor 130 may determine a user terminal capable of utilizing the corresponding Korean as a user terminal to which the translation interface is to be transmitted.

Additionally, the user terminal 10 for which the processor 130 provides the translation interface 300 is connected to the server associated with the computing device 100, or a plurality of user terminals subscribed to the server associated with the computing device. It may be at least one of the user terminals. In other words, the processor 130 may obtain the translated text information corresponding to the original text from the user terminal by determining the user terminal that has transmitted the translation interface among the plurality of user terminals connected through the computing device 100 and the network. I can. In this case, the user terminal that the processor 130 determines as the terminal that has transmitted the translation interface (that is, the user terminal that wants to obtain the translated text information corresponding to the original text information) is the first language and the translated text related to the original text information. It may be a terminal related to a user capable of using a second language related to information. For example, if the original text information included in the translation interface 300 is text composed of Korean, and the translated text information to be acquired is text composed of English, the processor 130 is a first user who can utilize both Korean and English. The first user terminal related to may be determined as a user terminal to which the translation interface is to be transmitted. In this case, the available language of the first user terminal may be identified through user information input at the time of registration, for example. In an additional embodiment, the processor 130 may identify a subject corresponding to the original text information, and determine user terminals corresponding to the identified subject as user terminals to transmit the translation interface.

That is, the processor 130 may identify a user terminal more suitable for a translation job among a plurality of user terminals connected to the computing device 100 and determine the user terminal to which the translation interface is to be transmitted.

According to an exemplary embodiment of the present disclosure, the processor 130 may determine to generate a translation interface including the original text information and transmit it to the user terminal 10 based on a result of determining adequacy of the original text information.

For a specific example, as shown in FIG. 4, the translation interface 300 includes a translation guide information display area 310, an image display area 320, an original text display area 330, and a translation text input area 340. , A skip graphic object 350 and a selection storage graphic object 360.

The translation guide information display area 310 included in the translation interface 300 may be an area in which guide information related to a corresponding interface is displayed. For example, as shown in FIG. 4, text information written in Korean may be displayed such as "translate this sentence". In this case, text information displayed on the translation guide information display area 310 may be displayed in a language corresponding to the original text information. For example, if the original text information is related to English, the text information displayed in the translation guide information display area 310 may be text related to English corresponding to the original text information, and if the original text information is related to Japanese , The translation guide information display area 310 may be text related to Japanese corresponding to the original text information. Also, the translation guide information display area 310 may include information on rewards generated in relation to a user's input related to the translated text information. Here, the reward may be information about a reward provided to the user terminal 10 as an input related to translated text information is received through the translation interface 300. For example, information on a reward generated in relation to a user's input may be '10P' as shown in FIG. 4. These rewards may be calculated by the processor 130. Specifically, the processor 130 may calculate a reward based on the number of words included in the original text information. For example, when the number of words included in the original text information is 10, the processor 130 may calculate a reward to be provided to the user terminal as '20P'. For another example, when the number of words included in the original text information is 15, the processor 130 may calculate a reward to be provided to the user terminal as '30P'. That is, based on the number of one or more words included in the original text information, the processor 130 calculates less rewards to be generated when it is expected that there are fewer translated texts to be input corresponding to the original text, and the corresponding If it is expected that there will be more translated texts to be input corresponding to the original text information, more rewards can be calculated. That is, by giving different rewards according to the user's effort to input the translated text, it is possible to induce voluntary participation of users and provide an interesting element of entertainment.

In other words, the user of the user terminal may be provided with guide information regarding a method of inputting translated text information through the translation interface 300 and a reward according to the text information displayed on the translation guide information display area 310.

The image display area 320 included in the translation interface 300 may be an area in which one or more text images are displayed. Here, the one or more text images displayed on the image display area 320 may be images that serve as a reference for a user to input text into the translated text input area 340. For example, a user of the user terminal may compare information displayed in the image display area 320 and the original text display area 330 to perform an input related to the translated text in the translated text input area 340. That is, the user of the user terminal 10 refers to one or more character images displayed on the image display area 320 and the original text information displayed on the original text display area 330, and displays the translated text in the translated text input area 340. You can enter information. The image display area 320 may allow a user's adjustment input for adjustment of one or more text images. The user's adjustment input may be related to adjusting the size or direction of one or more text images. That is, the image display area 320 may enlarge/reduce one or more text images or rotate it clockwise/counterclockwise in response to a user's adjustment input for display. Accordingly, a user's readability of one or more text images may be improved.

The original text display area 330 included in the translation interface 300 may be an area in which the original text information acquired through the original text input area 230 of FIG. 3 is displayed. That is, obtained as the user of the user terminal 10 performs an input related to the original text in the original text input area 230 by referring to one or more character images displayed on the image display area 220 of the original text interface 200. Original text information may be displayed on the original text display area 330.

The translation text input area 340 included in the translation interface 300 may be an area for receiving a user input of a user terminal in relation to the translation text information. That is, the user of the user terminal 10 may perform an input related to the translated text in the translated text input area 340 by referring to information displayed on the image display area 320 and the original text display area 330. For example, as shown in FIG. 4, the user may perform input on the translated text input area 340 by referring to information displayed on the image display area 320 and the original text display area 330. In addition, when the user completes the input to the translated text input area 340, the user may apply an input for the selectively stored graphic object 360, and the processor 130 In response to the input, text information input into the translated text input area 340 may be obtained as translated text information. That is, when the user inputs the translated text in the translated text input area 340 and then applies the input to the selective storage graphic object 360, the processor 130 converts the translated text into one or more character images or original text. It can be obtained as translated text information corresponding to the information.

The text skip graphic object 350 included in the translation interface 300 may be a graphic object that receives a user's input for switching information displayed on the image display area 320 and the original text display area 330. Specifically, when receiving a user's input for the text skip graphic object 350, the processor 130 may transfer information displayed in each of the current image display area 320 and the original text display area 330 to another image file You can switch to other original text information.

For example, in each of the image display area 320 and the original text display area 330, one or more text images related to English and original text information corresponding to one or more text images may be displayed, and the user refers to the information. Accordingly, an input related to the translated text information may be input in the translated text input area 340. However, the user's language knowledge for generating translated text information corresponding to the image display area 320 or the original text display area 330 may be insufficient. In this case, by using the text skipping graphic object 350 to switch information displayed on the image display area 320 and the original text display area 330, it is possible to select a translated sentence that can be performed by itself.

For another example, the user may wish to switch the image file displayed on the image display area 320 in order to obtain a high reward. In this case, the user may apply an input to the image skipping graphic object 350, and the processor 130 may generate an image file including one or more text images displayed on the image display area 320 in response to the input. Converts and displays the original text information displayed in the original text display area 330 to other original text information corresponding to the different field images included in the other image file. can do. That is, as the image file including different character images and the original text information corresponding thereto can be converted through the image skipping graphic object 350 included in the translation interface 300, various image files (or various characters Image), or the convenience of obtaining translated text information corresponding to various original text information may be improved.

That is, as described above, the processor 130 may receive translated text information corresponding to one or more text images from the user terminal 10 through the translation interface provided to the user terminal. In addition, translation text information may be obtained as an interaction with a user is performed through each display area and graphic object included in the translation interface. This has the advantage of obtaining translated text information of improved quality than simply obtaining translated text information using an artificial neural network-based translation model. For example, in a translation model that outputs translated text information corresponding to original text information through training of a neural network, the training data itself contains information related to errors, or when the amount of training data for training is insufficient. However, there is a fear of outputting translated text information that lacks accuracy. However, in the present disclosure, the configuration of obtaining the translated text information using the translation interface is obtained in connection with the direct input of users of each of the user terminals that can utilize both the original text and the language related to the translated text. It may be possible to provide translated text information of improved quality than translation.

According to an embodiment of the present disclosure, the processor 130 may determine the appropriateness of the translated text information by performing a quality check on the translated text information. In detail, the processor 130 may determine to generate and transmit an evaluation interface including original text information and translated text information to one or more other user terminals. The evaluation interface 400 may be a user interface provided to one or more other user terminals to evaluate the appropriateness of the translated text information acquired through the user terminal.

In this case, the processor 130 may determine one or more other user terminals for transmitting the evaluation interface. Specifically, the processor 130 may identify a user terminal matching the original text information included in the translation interface among a plurality of user terminals. In addition, the processor 130 may determine the identified user terminal as a user terminal to which the translation interface is to be transmitted. For example, when the original text information is related to Korean, the processor 130 may determine a user terminal capable of utilizing the corresponding Korean as a user terminal to which the translation interface is to be transmitted.

According to an embodiment, the processor 130 may determine the number of other user terminals to perform a quality check based on the history information of the user terminal. The history information may include at least one of information on the number of times the user terminal participates in translation input or cumulative translation evaluation information. The translation input participation number information may be information on a participation history related to the number of times the user terminal transmits the translated text information to the processor 130 through the translation interface. The cumulative translation evaluation information may be related to translation evaluation information of other user terminals with respect to the original text information transmitted from the user terminal to the processor 130.

In addition, the processor 130 may determine appropriateness of the translated text information based on translation evaluation information of each of one or more other user terminals through the evaluation interface. In more detail with reference to FIG. 5A, the evaluation interface 400 includes an image display area 410, an original text display area 420, a translated text display area 430, and one or more graphics related to inspection. An object 440, a skip graphic object 450, and a selection storage graphic object 460 may be included.

The image display area 410 included in the evaluation interface 400 may be an area in which one or more text images are displayed. Here, the one or more text images displayed on the image display area 410 may be images that serve as a criterion for determining whether the translated text information displayed on the translated text display area 430 is appropriate. For example, a user of the user terminal may compare information displayed in the image display area 410, the original text display area 420, and the translated text display area 430 to evaluate whether the translated text information is appropriate.

The original text display area 420 included in the evaluation interface 400 may be an area in which the original text information acquired through the original text information input area 230 of FIG. 3 is displayed. That is, obtained as the user of the user terminal 10 performs an input related to the original text in the original text input area 230 by referring to one or more character images displayed on the image display area 220 of the original text interface 200 Original text information may be displayed on the original text display area 420.

The translation text display area 430 included in the evaluation interface 400 may be an area in which translation text information acquired through the translation text input area 340 of FIG. 4 is displayed. That is, translated text information obtained as the user of the user terminal performs input related to the translated text in the translated text input area 340 by referring to the original text information displayed in the original text display area 330 of the translation interface 300 May be displayed on the translated text display area 430.

The one or more graphic objects 440 related to the inspection included in the evaluation interface 400 include a review graphic object 442 for allowing inspection input for the translated text information, and one or more graphic objects 442 for calculating an evaluation score for the translated text information. Evaluation graphic objects 441 and 443 may be included.

The review graphic object 442 is for allowing another user to input the translation text information, and when receiving the user's selection input, the translation text display area 430 is configured to allow the user to input the translation text information. ) Can be activated. For example, the evaluation interface 400 may be transmitted to the second user terminal to evaluate the quality of the translated text information, and the translated text display area 430 included in the translation interface 300 is provided through the first user terminal. The obtained first translated text information may be displayed. In this case, the second user of the second user terminal performing the evaluation may determine whether the corresponding first translated text information is appropriate by referring to the first original text information and the first translated text information. When the second user of the second user terminal determines that the first original text information displayed on the translated text display area 430 is not appropriate, the second user may apply an input to the review graphic object 442. In this case, the processor 130 may activate the translated text display area 430 to allow the second user's input of verification in response to the second user's input. Accordingly, the second user may perform a review operation on the first translated text information displayed on the translated text display area 430. That is, the translation text display area 430 may be converted into an area for a review operation according to whether a user inputs the review graphic object 442. In addition, the second user may apply a selection input to the selectively stored graphic object 460 when the inspection operation is completed, and the processor 130 may respond to the second user's input to the selectively stored graphic object 460. Correspondingly, the second user's supervision input performed on the translated text information may be obtained as supervised text information.

In this case, the processor 130 may provide a reward to the second user terminal as the verification text information is acquired. That is, the processor 130 may provide a reward to the second user terminal that performs a review on the translated text information provided by the first user terminal 10. Accordingly, active participation of other users for evaluation or review (or proofreading) of translated text information may be achieved. In addition, as the translation text information is corrected through the inspection work of other users, more appropriate translation text information may be generated corresponding to the original text.

In an additional embodiment, when the review text information is generated in response to the translated text information, the processor 130 may determine to transmit the generated review text information to the user terminal 10 related to the generation of the translated text information. For example, when the first translation text information obtained through the first user terminal 10 is generated through the inspection input of the second user terminal 10, the processor 130 It may be determined to transmit text information to the first user terminal. Accordingly, as the user of the first user terminal can receive information on the correction of the translated text information translated by himself/herself, the user of the first user terminal can learn more appropriate translated text information corresponding to the original text information. In other words, it is possible to provide a learning effect on translation through information related to proofreading.

As shown in FIG. 442). That is, when the evaluation interface 400 is provided to one or more other user terminals, each user of the other one or more user terminals receives a selection input for at least one of the first graphic object 441 and the second graphic object 442. Through this, translation evaluation information regarding whether or not the translated text information is appropriate can be generated. In the example of FIG. 5, it is illustratively shown that translation evaluation information for the translated text information is generated through the first graphic object and the second graphic object, that is, good or bad, and two graphic objects, but are limited thereto. no. For example, a graphic object for generating translation evaluation information may be composed of'upper','middle', and'lower', or may be composed of a plurality of values related to evaluation quality.

According to embodiments, information on criteria for performing translation evaluation may be provided together. For example, in the case of certain words such as proper nouns or food names, it may not be possible to clearly translate or convey an accurate meaning due to language or cultural differences. In this case, one of the methods of translating using similar words, translating and translating into sentences or phrases, or transliteration as pronunciation may be selected and applied. For example, in the case of'yanggital head' and'odolbone' shown in FIG. 5, it may be translated as Gras-double and Tribe, but it may be more appropriate to translate such as'yanggit-meori' or'oddol-byeo'. .

In this case, if information on the criteria for performing the translation evaluation is not provided together, different evaluation results may be produced for each evaluator, which may lead to confusion. Accordingly, translation evaluation criteria may be displayed on the translation evaluation interface 400. For example, when the original text included in the translation evaluation interface 400 is searched by keyword unit, if a word that directly matches does not exist in the dictionary, it may be evaluated based on the transliteration. In this case, the evaluator Based on the notation method, it is possible to evaluate whether the transliteration has been performed normally.

As another example, when the original text included in the translation evaluation interface 400 is searched by keyword unit, a word that is directly matched does not exist in the dictionary, but the corresponding word exists in the example sentence, or if there is a word with a pre-set similarity or higher, it is similar. You can have them translate using words. In this case, the evaluator can evaluate the translation result based on whether or not the most similar word is well selected. The word similarity evaluation may be performed based on word2vec, but is not limited thereto.

In an embodiment, the translation evaluation interface 400 may further display an interface for selecting or changing a translation evaluation criterion. For example, if a translation evaluation criterion is not provided separately, the evaluator can select the criterion for which he/she evaluated the translation. For example, the evaluator may select a translation evaluation criterion that is deemed appropriate for the original text or an evaluation criterion corresponding to a translation method of a previously translated text, and input the evaluation result. Likewise, even when the translation evaluation criteria are presented, the evaluator may perform an input to change the translation evaluation criteria when it is determined that the translation evaluation criteria are incorrectly presented or that there is a better evaluation criteria.

The text skip graphic object 450 included in the evaluation interface 400 receives a user's input for switching information displayed in the image display area 410, the original text display area 420, and the translated text display area 430. It may be a graphic object to be received. Specifically, when receiving a user's input for the skip text graphic object 450, the processor 130 may each of the current image display area 410, the original text display area 420, and the translated text display area 430 The information displayed in can be converted into other image files and other original text information.

According to an embodiment of the present disclosure, the processor 130 may construct training data for training a translation model based on original text information and translated text information corresponding to the original text information. In this case, the translation model may be a neural network model that outputs text related to the second language by inputting text related to the first language. In general, a translation model based on an artificial neural network can provide an output with improved accuracy as it becomes possible to extract meaningful information as the number of training data increases. However, since there are various kinds of languages, and there are tens of thousands of words in each language and various expression methods through combinations of each word, it may be difficult to construct appropriate learning data. For example, if a large amount of training data is not secured, the output accuracy of the translation model may be degraded. In addition, there is a concern that learning through training data related to unverified translation data may lack the accuracy of the translation model. Accordingly, when constructing training data for training a neural network, a verification process may be required.

In the present disclosure, the learning data (i.e., original text information and translated text information) constructed by the processor 130 may be secured in a large amount according to data that has been directly input and verified by a number of users. The verification process can be omitted. That is, as learning data is constructed through a large amount of information with reliability, and a translation model learned through the learning data can be provided, it is possible to contribute to the convenience of construction of learning data and improvement of the output accuracy of the translation model.

According to an embodiment of the present disclosure, the processor 130 generates a translated text image based on one or more character images and translated text information, and displays the translated text image as an upper layer of the one or more character images to generate an arcade image. can do. Specifically, the processor 130 may identify text image information including coordinate information, generation information, and font information of one or more text images. For example, the text image information includes coordinate information indicating that the position of one or more text images is located at a first position in the image, color information indicating that the background color of one or more text images is yellow, the text color is black, and one or more text images. It is a font size of '11' and may include font information of the font'clear gothic'. The detailed description of coordinate information, color information, and font information included in the above-described text image information is only an example, and the present disclosure is not limited thereto.

The processor 130 may generate a translated text background image based on an average color value of an area corresponding to the coordinate information. That is, the translated text background image generated by the processor 130 may be configured with a color corresponding to one or more text images.

The processor 130 may generate a translated text image by reflecting the translated text information on the translated text background image based on the font information. For example, if the font information is the font size '11' in one or more text images and the font'clear Gothic' includes information, the processor 130 uses the translated text information as the font size '11', and the font'clear gothic' You can generate a translated text image by using.

Also, the processor 130 may generate an arcade image file by displaying the generated translated text image as an upper layer in an area corresponding to the coordinate information. That is, by displaying the translated text image generated on one or more text images in the image file as an upper layer, an arcade image file in which one or more text images are replaced with the translated text images translated into a specific language may be generated. For example, an arcade image file generated as an image file including one or more text images displayed in the image display area 410 of FIG. 5A is converted and may be the same as that of FIG. 5B.

In other words, the processor 130 generates translated text information by performing translation on one or more text images written in a language (eg, a foreign language) that the user does not understand in the image file, and based on the generated translated text information. Arcade images can be created through conversion to image files. Accordingly, since the user may be provided with an arcade image generated through a language familiar to the user, information that the user does not understand in the image file can be easily obtained. In addition, the arcade image generated through the processor 130 may include translated image information generated based on text image information of one or more existing text images. In other words, by including the translated image information generated based on the display area, color, font size, font, etc. of the character corresponding to the original text in the image before translation of the arcade image, It can provide a natural image.

6 is a flowchart illustrating steps for performing a method for generating an arcade image by performing conversion on text existing in an image file according to an exemplary embodiment of the present disclosure.

According to an embodiment of the present disclosure, the computing device 100 may obtain original text information by recognizing one or more text images included in an image file (510 ).

According to an embodiment of the present disclosure, the computing device 100 may determine appropriateness of the original text information by performing a quality check on the obtained original text information (520 ).

According to an embodiment of the present disclosure, the computing device 100 may transmit a translation interface including original text information to the user terminal based on a result of determining the appropriateness (530 ).

According to an embodiment of the present disclosure, the computing device 100 may receive translated text information corresponding to one or more character images from the user terminal 10 through a translation interface (540 ).

According to an embodiment of the present disclosure, the computing device 100 generates a translated text image based on one or more character images and translated text information, and displays the generated translated text image as an upper layer of the one or more character images to form an arcade. An image file may be generated (550).

The order of the steps illustrated in FIG. 6 may be changed as necessary, and at least one or more steps may be omitted or added. That is, the above-described steps are only one embodiment of the present disclosure, and the scope of the present disclosure is not limited thereto.

7 is a schematic diagram illustrating one or more network functions related to an embodiment of the present disclosure.

Throughout this specification, a computational model, a neural network, a network function, and a neural network may be used with the same meaning. A neural network can be made up of a set of interconnected computational units, which can generally be referred to as “nodes”. These “nodes” may also be referred to as “neurons”. The neural network is composed of at least one or more nodes. The nodes (or neurons) that make up neural networks can be interconnected by one or more “links”.

In a neural network, one or more nodes connected through a link may relatively form a relationship between an input node and an output node. The concepts of an input node and an output node are relative, and any node in an output node relationship with respect to one node may have an input node relationship in a relationship with another node, and vice versa. As described above, the input node to output node relationship can be created around the link. One or more output nodes may be connected to one input node through a link, and vice versa.

In the relationship between the input node and the output node connected through one link, the value of the output node may be determined based on data input to the input node. Here, a node interconnecting the input node and the output node may have a weight. The weight may be variable, and in order for the neural network to perform a desired function, it may be changed by a user or an algorithm. For example, when one or more input nodes are interconnected to one output node by respective links, the output node includes values input to input nodes connected to the output node and a link corresponding to each input node. The output node value may be determined based on the weight.

As described above, in a neural network, one or more nodes are interconnected through one or more links to form an input node and an output node relationship in the neural network. The characteristics of the neural network may be determined according to the number of nodes and links in the neural network, the association relationship between the nodes and the links, and a weight value assigned to each of the links. For example, when there are the same number of nodes and links, and two neural networks having different weight values between the links exist, the two neural networks may be recognized as being different from each other.

A neural network may be configured including one or more nodes. Some of the nodes constituting the neural network may configure one layer based on the distances from the initial input node. For example, a set of nodes with a distance n from the initial input node, n layers can be configured. The distance from the first input node may be defined by the minimum number of links that must be traversed to reach the node from the first input node. However, the definition of such a layer is arbitrary for explanation, and the order of the layer in the neural network may be defined in a different way than that described above. For example, the layer of nodes may be defined by the distance from the last output node.

The first input node may mean one or more nodes to which data is directly input without going through a link in a relationship with other nodes among nodes in the neural network. Alternatively, in a relationship between nodes based on a link in a neural network network, it may mean nodes that do not have other input nodes connected by a link. Similarly, the final output node may mean one or more nodes that do not have an output node in a relationship with other nodes among nodes in the neural network. In addition, the hidden node may refer to nodes constituting a neural network other than the first input node and the last output node. In the neural network according to an embodiment of the present disclosure, the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as the input layer proceeds to the hidden layer. I can. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes of an input layer is less than the number of nodes of an output layer, and the number of nodes decreases as the number of nodes progresses from the input layer to the hidden layer. have. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes of an input layer is greater than the number of nodes of an output layer, and the number of nodes increases as the number of nodes progresses from the input layer to the hidden layer. I can. The neural network according to another embodiment of the present disclosure may be a neural network in the form of a combination of the aforementioned neural networks.

A deep neural network (DNN) may mean a neural network including a plurality of hidden layers in addition to an input layer and an output layer. Deep neural networks can be used to identify potential structures in data. In other words, it is possible to understand the potential structures of photos, texts, videos, voices, and music (for example, what objects are in photos, what are the content and emotions of the text, what are the contents and emotions of the voice, etc.). . Deep neural networks include convolutional neural networks (CNNs), recurrent neural networks (RNNs), auto encoders, Generative Adversarial Networks (GANs), and restricted boltzmann machines (RBMs). machine), deep belief network (DBN), Q network, U network, and Siam network. The description of the above-described deep neural network is only an example, and the present disclosure is not limited thereto.

The neural network may be learned in at least one of supervised learning, unsupervised learning, and semi supervised learning. Learning of neural networks is to minimize output errors. In learning of a neural network, iteratively inputs training data to the neural network, calculates the output of the neural network for the training data and the error of the target, and reduces the error from the output layer of the neural network to the input layer. This is a process of updating the weight of each node of the neural network by backpropagation in the direction. In the case of teacher learning, learning data in which the correct answer is labeled in each learning data is used (ie, labeled learning data), and in the case of non-satellite learning, the correct answer may not be labeled in each learning data. That is, for example, in the case of teacher learning related to data classification, the learning data may be data in which a category is labeled with each learning data. Labeled training data is input to a neural network, and an error may be calculated by comparing an output (category) of the neural network with a label of the training data. As another example, in the case of comparative history learning regarding data classification, an error may be calculated by comparing the input training data with the neural network output. The calculated error is backpropagated in the neural network in the reverse direction (ie, from the output layer to the input layer), and the connection weight of each node of each layer of the neural network may be updated according to the backpropagation. The amount of change in the connection weight of each node to be updated may be determined according to a learning rate. The computation of the neural network for the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate may be applied differently according to the number of repetitions of the learning cycle of the neural network. For example, a high learning rate is used in the early stages of training of a neural network, so that the neural network quickly secures a certain level of performance to increase efficiency, and a low learning rate can be used in the later stages of training to increase accuracy.

In learning of a neural network, in general, training data may be a subset of actual data (that is, data to be processed using a trained neural network), and thus, errors in the training data decrease, but errors in the actual data are reduced. There may be increasing learning cycles. Overfitting is a phenomenon in which errors in actual data increase due to over-learning on learning data. For example, a neural network learning a cat by showing a yellow cat may not recognize that it is a cat when it sees a cat other than yellow, which may be a kind of overfitting. Overfitting can cause an increase in errors in machine learning algorithms. Various optimization methods can be used to prevent such overfitting. In order to prevent overfitting, methods such as increasing training data, regularization, and dropout in which some nodes of the network are omitted during the training process may be applied.

Steps of a method or algorithm described in connection with an embodiment of the present disclosure may be implemented directly in hardware, implemented as a software module executed by hardware, or a combination thereof. Software modules include Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), Flash Memory, hard disk, removable disk, CD-ROM, or It may reside on any type of computer-readable recording medium well known in the art to which the present disclosure pertains.

Components of the present disclosure may be implemented as a program (or application) and stored in a medium to be executed by being combined with a computer that is hardware. Components of the present disclosure may be executed as software programming or software elements, and similarly, embodiments include various algorithms implemented with a combination of data structures, processes, routines or other programming components, including C, C++ , Java, assembler, or the like may be implemented in a programming or scripting language. Functional aspects can be implemented with an algorithm running on one or more processors.

A person of ordinary skill in the art of the present disclosure includes various exemplary logical blocks, modules, processors, means, circuits and algorithm steps described in connection with the embodiments disclosed herein, electronic hardware, (convenience). For the sake of clarity, it will be appreciated that it may be implemented by various forms of program or design code or a combination of both (referred to herein as "software"). To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints imposed on the overall system. A person of ordinary skill in the art of the present disclosure may implement the described functions in various ways for each specific application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

The various embodiments presented herein may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. The term “article of manufacture” includes a computer program, carrier, or media accessible from any computer-readable device. For example, computer-readable media include magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CD, DVD, etc.), smart cards, and flash memory. Devices (eg, EEPROM, card, stick, key drive, etc.). In addition, the various storage media presented herein include one or more devices and/or other machine-readable media for storing information. The term “machine-readable medium” includes, but is not limited to, wireless channels and various other media capable of storing, holding, and/or transmitting instruction(s) and/or data.

It is to be understood that the specific order or hierarchy of steps in the presented processes is an example of exemplary approaches. Based on the design priorities, it is to be understood that a specific order or hierarchy of steps in processes may be rearranged within the scope of the present disclosure. The appended method claims provide elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

A description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those of ordinary skill in the art, and general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure is not to be limited to the embodiments presented herein, but is to be construed in the widest scope consistent with the principles and novel features presented herein.

Claims (10)

Acquiring original text information by recognizing one or more text images included in the image file;
Determining adequacy of the original text information by performing a quality check on the obtained original text information;
Determining to transmit a translation interface including the original text information to a user terminal based on the adequacy determination result;
Receiving translated text information corresponding to the one or more text images from the user terminal through the translation interface; And
Generating a translated text image based on the at least one character image and the received translated text information, and displaying the generated translated text image as an upper layer of the at least one character image to generate an arcade image file;
Including,
Recognizing one or more text images included in the image file to obtain original text information,
Generating an original text interface including some of one or more text images included in the image file and determining to transmit it to the user terminal; And
Receiving the original text information based on a user input of the user terminal through the original text interface;
Including,
The original text interface,
The degree of exposure is determined based on at least one of participation history information or language proficiency level of the user terminal,
A method for generating an arcade image file by performing a transformation on text present in an image file, performed on one or more processors of a computing device.
The method of claim 1,
Recognizing one or more text images included in the image file to obtain original text information,
Obtaining the original text information corresponding to one or more text images included in the image file through a text recognition model including one or more network functions; or
Obtaining the original text information from the user terminal through an original text interface;
Containing at least one of,
A method for generating an arcade image file by performing a transformation on text present in an image file, performed on one or more processors of a computing device.
delete The method of claim 1,
Detecting a typing input of the user terminal for the original text interface;
Determining a typing input of the user terminal as an error input when a typing input of more than a predetermined threshold number of times is detected based on a predetermined unit time; And
Determining not to expose the one or more text images for a predetermined time to the user terminal in which the error input is detected;
Further comprising,
A method for generating an arcade image file by performing a transformation on text present in an image file, performed on one or more processors of a computing device.
The method of claim 1,
The step of determining adequacy of the original text information by performing a quality check on the original text information,
Determining the number of other user terminals to perform the quality check based on the history information of the user terminal;
Determining to transmit an evaluation information input window including the one or more character images and the original text information to one or more other user terminals in response to the determined number of other user terminals;
Determining adequacy of the original text information based on quality evaluation information received through the evaluation information input window from each of the one or more other user terminals; And
Granting a reward to the user terminal based on the adequacy determination result;
Including,
The history information,
Including at least one of input participation count information and cumulative quality evaluation information of the user terminal,
A method for generating an arcade image file by performing a transformation on text present in an image file, performed on one or more processors of a computing device.
The method of claim 1,
Identifying a user terminal matching the original text information included in the translation interface among a plurality of user terminals; And
Determining the identified user terminal as a user terminal to which the translation interface is to be transmitted;
Further comprising,
A method for generating an arcade image file by performing a transformation on text present in an image file, performed on one or more processors of a computing device.
The method of claim 1,
Determining to generate and transmit an evaluation interface including the original text information and the translated text information to one or more other user terminals; And
Determining adequacy of the translated text information based on translation evaluation information of each of one or more other user terminals through the evaluation interface;
Further comprising,
A method for generating an arcade image file by performing a transformation on text present in an image file, performed on one or more processors of a computing device.
The method of claim 7,
The evaluation interface,
Including a review information input area for allowing a review input of the translated text information and at least one evaluation graphic object for calculating an evaluation score for the translated text information,
A method for generating an arcade image file by performing a transformation on text present in an image file, performed on one or more processors of a computing device.
The method of claim 1,
Generating a translated text image based on the at least one character image and the translated text information, and generating an arcade image by displaying the translated text image as an upper layer of the at least one character image,
Identifying text image information including coordinate information, color information, and font information of the one or more text images;
Generating a translated text background image based on an average color value of an area corresponding to the coordinate information;
Generating the translated text image by reflecting the translated text information on a commercial translation text background image based on the font information; And
Generating the arcade image file by displaying the translated text image as an upper layer in an area corresponding to the coordinate information;
Containing,
A method for generating an arcade image file by performing a transformation on text present in an image file, performed on one or more processors of a computing device.
As a computing device for generating an arcade image file by performing conversion on the text existing in the image file,
A processor including one or more cores;
A memory storing program codes executable in the processor; And
A network unit for transmitting and receiving data with one or more user terminals;
Including,
The processor,
Acquire original text information by recognizing one or more text images included in the image file,
To determine the appropriateness of the original text information by performing a quality check on the obtained original text information,
It is determined to transmit a translation interface including the original text information to a user terminal based on the adequacy determination result,
Receiving translated text information corresponding to the one or more text images from the user terminal through the translation interface,
Generating a translated text image based on the at least one character image and the received translated text information, and displaying the generated translated text image as an upper layer of the at least one character image to generate an arcade image file,
Acquiring original text information by recognizing one or more text images included in the image file,
Creating an original text interface including a portion of one or more text images included in an image file to transmit to the user terminal, and receiving the original text information based on a user input of the user terminal through the original text interface Including,
The original text interface,
The degree of exposure is determined based on at least one of participation history information or language proficiency level of the user terminal,
A computing device for generating an arcade image file by performing conversion on text present in an image file.

Images