KR20240041656A - Rapid translation support apparatus and method supporting joint translation environment using multiple translators - Google Patents

Abstract

A rapid translation support device and method supporting a joint translation environment using multiple translators are disclosed. The rapid translation support device includes a content division unit that divides the content into multiple parts according to preset standards when a request related to content translation is received, and a plurality of translators that select a plurality of translators to perform translation related to the content from a pool of already registered translators. When a request for inspection of the translation work is received from at least one of the translator selection unit, the task designation unit that specifies the translation work by matching the plurality of selected translators for each part of the divided content, and the translator terminal that performs the translation work, It includes an inspection support unit that supports inspection of the corresponding part by the inspector's inspector terminal.

Description

{Rapid translation support apparatus and method supporting joint translation environment using multiple translators}

The present invention relates to a technology for supporting rapid translation, and more specifically, to a rapid translation support device and method that supports a joint translation environment using multiple translators in which multiple translators perform joint translation simultaneously and rapidly translate. It's about.

With the development of information and communication technology, a variety of content is being produced at an exponential rate, and through online networks, any user can easily receive the content they want regardless of country or continent.

However, no matter how high-quality the content you want, if you cannot understand the content due to language problems, it will be worthless from the user's point of view, and you will lose interest in the content.

In particular, in the case of video content such as dramas and movies, fans are spreading across various countries without spatial restrictions, increasing the need to provide content translated into their native language to fans who do not speak multiple languages.

Automatic translation technology is rapidly developing to solve all of these problems, but perfect translation is not currently possible with automatic translation technology. Furthermore, no matter how advanced automatic translation technology is, the lyrical feeling contained in the content or the cultural feeling of the region is not possible. It is difficult to describe it accurately.

Therefore, there is a need to explore various ways to translate content more accurately and quickly.

Korean Patent Publication No. 10-2351408 (2022.01.11.)

The problem to be solved by the present invention is to provide a rapid translation support device and method that supports a joint translation environment using multiple translators, which helps multiple translators each take charge of divided content according to preset standards and perform joint translation. It is done.

In order to solve the above problem, the translation support device according to the present invention includes a content division unit that divides the content into a plurality of pieces according to preset standards when a request related to content translation is received, and a content division unit that divides the content into a plurality of parts according to preset standards, and a pre-registered translator pool related to the content. A translator selection unit that selects a plurality of translators to perform translation, a task designation unit that specifies a translation task by matching the selected plurality of translators for each part of the divided content, and a translator terminal that performs the translation task. When an inspection request for the translation work is received from at least one person, it includes an inspection support unit that supports inspection of the corresponding part by the inspector's terminal.

In addition, the progress of the translation work is monitored, the monitored information is used to manage the translation work to be completed within the content translation deadline, and when the translation work is completed, the translation work is notified to the requester that the translation has been completed. It is characterized in that it further includes a task management unit.

In addition, the task management unit is characterized in that it updates at least one of the time remaining from the deadline, the translated subtitle content for each part, and the progress of the translation work for each part in real time.

In addition, the task management unit provides a reading function for the subtitle content of the remaining parts except for the part designated for each translator terminal, and provides a reading function and a writing function for the subtitle content of the part designated for each translator terminal. .

In addition, the task management unit is characterized in that, when the feedback process performed between the translator terminal and the reviewer terminal is repeatedly performed beyond a preset standard, the feedback process is automatically performed through a learning model to which artificial intelligence technology is applied. do.

In addition, the content dividing unit divides the playback time of the content into N parts, sets the part where the sound signal is not detected within a preset error range based on each N dividing point as the content dividing point, and determines the content dividing point. It is characterized by dividing the content based on a standard to create a plurality of parts.

In addition, the content dividing unit divides the playback time of the content into N parts, sets the part where a scene change occurs based on each N dividing point as a content dividing point, and divides the content based on the set content dividing point. It is characterized by generating a plurality of parts.

In addition, the content dividing unit converts the voice included in the content into text, calculates the number of words of the converted text, and divides the calculated number of words according to a preset standard to generate a plurality of parts. Do it as

In addition, the content division unit calculates the density of the voice included in the content and divides the point at which the calculated density changes suddenly to generate a plurality of parts.

In addition, the translator selection unit sorts the translators among the translator pool in order of high relevance to the requested content, and selects the translators as many as the number of parts according to the sorted order.

In addition, the translator selection unit is characterized in that it calculates the relevance using at least one of the translator's translation work history, the translator's evaluation score, the translator's translation rate, and the translator's knowledge background.

In addition, the task assigning unit analyzes the sound signal of the content for each part, selects a priority for the designated element based on the analyzed result, sets a weight based on the priority, and assigns the designated element to the designated element. It is characterized by applying weights to match the most suitable translator for each part.

In addition, the task designation unit is characterized in that it matches a customized translator for each part by applying the weight to at least one of the translator's translation work history, the translator's evaluation score, the translator's translation speed, and the translator's rate.

In addition, the task specifying unit is characterized in that, when specifying the translation task, it provides at least one of a content structure diagram, a person relationship diagram, and an honorific title relationship diagram for reference in translating the content.

In addition, the review support unit is characterized in that it receives review opinions on errors and mistranslations of the corresponding part from the reviewer terminal and supports a feedback process to ensure that the received review opinions are reflected by the corresponding translator terminal.

The rapid translation support method according to the present invention includes the steps of dividing the content into a plurality of pieces according to preset standards when a rapid translation support device receives a request related to content translation, and the rapid translation support device divides the content into a plurality of pieces from a pool of pre-registered translators. selecting a plurality of translators to perform related translations, the rapid translation support device matching the selected plurality of translators for each part of the divided content to specify a translation task, and the rapid translation support device When a request for inspection of the translation work is received from at least one of the translator terminals performing the translation work, it includes the step of supporting the inspection of the corresponding part by the reviewer's reviewer terminal.

In addition, before the dividing step, the rapid translation support device uploads information related to the translator pool to a management system, and the rapid translation support device receives a request to join the translator pool from at least one translator terminal. A step of selecting, by the rapid translation support device, a translator to be registered in the translator pool based on the subscription request, and registering, by the rapid translation support device, the selected translator in the translator pool. Do it as

According to an embodiment of the present invention, when content needs to be translated urgently, multiple translators can jointly translate the content to provide a fast and accurate translation to the requester.

In addition, each translator can check the translation progress and translation content of not only the part of the content assigned to him but also the remaining parts in real time, so that he can recognize his own translation speed and feel the sense of unity as if the translated content was translated by one person. can do

In addition, the translator, client, and reviewer access the rapid translation support device through their respective terminals and perform translation-related tasks within the management system provided by the rapid translation support device, thereby facilitating data transfer and data collection between separate terminals. By not managing data, it can lower the system load and support fast calculations.

1 is a configuration diagram for explaining a translation support system according to an embodiment of the present invention.
Figure 2 is a block diagram for explaining a rapid translation support device according to an embodiment of the present invention.
Figure 3 is a diagram for explaining content division according to an embodiment of the present invention.
Figure 4 is a diagram for explaining content division according to another embodiment of the present invention.
Figure 5 is a diagram for explaining the selection of a translator according to an embodiment of the present invention.
Figure 6 is a diagram for explaining task designation according to an embodiment of the present invention.
Figure 7 is a diagram for explaining a content configuration diagram that is reference material for translation according to an embodiment of the present invention.
Figure 8 is a diagram for explaining a character relationship diagram that is reference material for translation according to an embodiment of the present invention.
Figure 9 is a diagram for explaining an honorific title relationship diagram that is reference material for translation according to an embodiment of the present invention.
Figure 10 is a diagram for explaining the user interface of a management system supporting rapid translation according to an embodiment of the present invention.
Figure 11 is a flowchart illustrating a method for supporting rapid translation according to an embodiment of the present invention.
Figure 12 is a flowchart illustrating the creation of a translator pool according to an embodiment of the present invention.
Figure 13 is a block diagram for explaining a computing device according to an embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

In this specification and drawings (hereinafter referred to as “this specification”), duplicate descriptions of the same components are omitted.

Also, in this specification, when a component is mentioned as being 'connected' or 'connected' to another component, it may be directly connected or connected to the other component, but may be connected to the other component in the middle. It should be understood that may exist. On the other hand, in this specification, when it is mentioned that a component is 'directly connected' or 'directly connected' to another component, it should be understood that there are no other components in between.

Additionally, the terms used in this specification are merely used to describe specific embodiments and are not intended to limit the present invention.

Also, in this specification, singular expressions may include plural expressions, unless the context clearly dictates otherwise.

In addition, in this specification, terms such as 'include' or 'have' are only intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, and one or more It should be understood that this does not exclude in advance the presence or addition of other features, numbers, steps, operations, components, parts, or combinations thereof.

Also, in this specification, the term 'and/or' includes a combination of a plurality of listed items or any of the plurality of listed items. In this specification, 'A or B' may include 'A', 'B', or 'both A and B'.

Additionally, in this specification, detailed descriptions of well-known functions and configurations that may obscure the gist of the present invention will be omitted.

1 is a configuration diagram for explaining a translation support system according to an embodiment of the present invention.

Referring to FIG. 1, the translation support system 500 helps multiple translators each take charge of divided content according to preset standards and perform joint translation. In other words, when content needs to be translated urgently, the translation support system 500 supports quick and accurate content translation. The translation support system 500 includes a rapid translation support device 100, a translator terminal 200, a requester terminal 300, and a reviewer terminal 400.

The rapid translation support device 100 provides a management system that allows multiple translators to perform joint translation. Here, the management system helps perform all translation-related tasks while the translator terminal 200, requester terminal 300, and reviewer terminal 400 are each connected, and for this purpose, a user interface (User Interface) suitable for each user is provided. It is a system that supports UI). The rapid translation support device 100 may be a device for a translation support platform.

When the rapid translation support device 100 receives a request related to content translation from the requester terminal 300, it divides the content into a plurality of pieces according to preset standards. The rapid translation support device 100 selects a plurality of translators to perform content-related translation from a pool of pre-registered translators, and matches the selected translators for each part of the divided content. The rapid translation support device 100 specifies a translation task related to the corresponding part to the translator terminal 200 of the matched translator. When the rapid translation support device 100 receives a request for inspection of the translation work from at least one of the translator terminals performing the translation work, it requests the reviewer terminal 300 to inspect the corresponding part. The rapid translation support device 100 receives review opinions on errors and mistranslations of the corresponding part from the reviewer terminal 300, and supports a feedback process in which the received review opinions are reflected by the corresponding translator terminal. When the feedback process is completed, the rapid translation support device 100 transmits the translated and subtitled content to the requester terminal 300.

Here, the rapid translation support device 100 may create a translator pool in advance by selecting translators who will perform emergency translation from among all translators before performing the translation task.

The translator terminal 200 is a terminal used by a translator who translates various languages, and includes a plurality of terminals 200a, 200b, and 200c. The translator terminal 200 connects to the rapid translation support device 100 and supports the translator to perform translation work on the designated part while connected. At this time, the translator terminal 200 directly performs the translation work through the user interface of the management system provided by the rapid translation support device 100 and uploads the translation at the same time. Additionally, the translator terminal 200 can perform a feedback process with the reviewer terminal 400 within the management system. Preferably, the translator terminal 200 may be a personal computer system such as a smartphone, laptop, desktop, tablet PC, or handheld computer. Here, the translator does not need to use the fixed translator terminal 200 to access the rapid translation support device 100. That is, a translator can access the rapid translation support device 100 using various types of translator terminals 200. For example, a translator may access the rapid translation support device 100 using a tablet PC, and on other days, a translator may access the rapid translation support device 100 using a smartphone.

The client terminal 300 is a terminal used by a client who owns or distributes content, and includes at least one. The requester terminal 300 connects to the rapid translation support device 100 and supports the requester to perform content translation-related requests while connected. The requester terminal 300 can directly input a translation request through the user interface of the management system provided by the rapid translation support device 100. At this time, the requester can register information (language information, historical background information, etc.) related to the requested translation in the rapid translation support device 100 along with the requested translation. Additionally, the requester terminal 300 receives a message (pop-up window, push message, etc.) notifying that the content translation is complete within the management system, and can download the translated and subtitled content. Preferably, the requester terminal 300 may be a personal computer system such as a smartphone, laptop, desktop, tablet PC, or handheld computer. Here, the requester does not need to use the fixed requester terminal 300 to access the rapid translation support device 100. That is, the requester can access the rapid translation support device 100 using various types of requester terminals 300. For example, the requester may access the rapid translation support device 100 using a tablet PC, or on another day, the requester may access the rapid translation support device 100 using a smartphone.

The reviewer terminal 400 is a terminal used by a reviewer who reviews the translator's translation, and includes at least one terminal. The reviewer terminal 400 connects to the rapid translation support device 100 and, while connected, supports the reviewer to provide feedback on the inspection of the translation with the corresponding translator. At this time, the inspector terminal 400 can directly perform the feedback process through the user interface of the management system provided by the rapid translation support device 100. Preferably, the inspector terminal 400 may be a personal computer system such as a smartphone, laptop, desktop, tablet PC, or handheld computer. Here, the reviewer does not need to use the fixed reviewer terminal 400 to access the rapid translation support device 100. That is, the reviewer can access the rapid translation support device 100 using various types of reviewer terminals 400. For example, the inspector may access the rapid translation support device 100 using a tablet PC, or on another day, the inspector may access the rapid translation support device 100 using a smartphone.

Meanwhile, the translation support system 500 establishes a communication network 550 between the rapid translation support device 100, the translator terminal 200, the requester terminal 300, and the reviewer terminal 400 to support communication between them. . The communication network 550 may be composed of a backbone network and a subscriber network. The backbone network may be composed of one or more integrated networks among the X.25 network, Frame Relay network, ATM network, MPLS (Multi Protocol Label Switching) network, and GMPLS (Generalized Multi Protocol Label Switching) network. Subscriber networks include FTTH (Fiber To The Home), ADSL (Asymmetric Digital Subscriber Line), cable network, zigbee, Bluetooth, and Wireless LAN (IEEE 802.11b, IEEE 802.11a, IEEE 802.11g, IEEE 802.11n). ), Wireless Hart (ISO/IEC62591-1), ISA100.11a (ISO/IEC 62734), CoAP (Constrained Application Protocol), MQTT (Message Queuing Telemetry Transport), WIBro (Wireless Broadband), Wimax, 3G, HSDPA (High Speed Downlink Packet Access), 4G, 5G and 6G, etc. In some embodiments, the communication network 550 may be an Internet network or a mobile communication network. Additionally, the communication network 550 may include any wireless or wired communication method that is widely known or will be developed in the future.

FIG. 2 is a block diagram for explaining a rapid translation support device according to an embodiment of the present invention, FIG. 3 is a diagram for explaining content division according to an embodiment of the present invention, and FIG. 4 is another embodiment of the present invention. Figure 5 is a diagram for explaining content division according to an example, Figure 5 is a diagram for explaining selection of a translator according to an embodiment of the present invention, Figure 6 is a diagram for explaining task designation according to an embodiment of the present invention, FIG. 7 is a diagram illustrating a content structure diagram that is a reference material for translation according to an embodiment of the present invention, and FIG. 8 is a diagram illustrating a character relationship diagram that is a reference material for translation according to an embodiment of the present invention. 9 is a diagram illustrating an honorific title relationship diagram that is reference material for translation according to an embodiment of the present invention.

1 to 9, the rapid translation support device 100 includes a communication unit 10, a control unit 30, and a storage unit 50.

The communication unit 10 communicates with the translator terminal 200, the requester terminal 300, and the reviewer terminal 400. The communication unit 10 supports the translator terminal 200, the requester terminal 300, and the reviewer terminal 400 to access the management system and perform tasks related to content translation.

The control unit 30 performs overall control of the rapid translation support device 100. The control unit 30 provides a management system that supports content translation and operates the management system. To this end, the control unit 30 includes a content division unit 31, a translator selection unit 32, a task designation unit 33, and an inspection support unit 34, and may further include a task management unit 35.

The content dividing unit 31 divides the content requested for translation into a plurality of pieces. The content division unit 31 determines the number of parts to be divided based on the playback time of the content and the number of translators in the translator pool, and divides or divides the content based on the determined number N (N is a natural number of 2 or more). Based on the number of parts to be done, the number of translators in the translator pool can be determined, and the content can be divided based on the determined number of N people. In this way, the content division unit 31 can divide the content using various methods.

For example, the content division unit 31 divides the playback time (t) of the content into N parts and sets the content division section within a preset error range based on each N dividing point. The content division unit 31 sets the part where the sound signal is not detected within the set content division section as the content division point, and divides the content based on the set content division point to create a plurality of parts (N). There is (Figure 4).

Additionally, the content division unit 31 divides the playback time of the content into N parts, and sets the portion where a scene change occurs based on each N division point as the content division section. The content division unit 31 sets the part where a scene change occurs within the set content division section as the content division point, and divides the content based on the set content division point to form a plurality of parts (N). can be created (Figure 5).

Additionally, the content division unit 31 converts the voice included in the content into text and calculates the number of words in the converted text. The content division unit 31 may generate a plurality of parts (N) by dividing the calculated total number of words according to a preset standard. Here, the preset standards may be standards such as dividing the number of words into N equal parts and ratio (%).

Additionally, the content division unit 31 may calculate the density of the voice included in the content and divide the points at which the calculated density changes rapidly to generate a plurality of parts (N). That is, the content division unit 31 may determine that a section where the voice density changes rapidly is a screen change point and divide the section.

The translator selection unit 32 selects a translator to translate the divided parts from the translator pool. To this end, the translator selection unit 32 sorts the translators among the translator pool in order of their highest relevance to the requested content. The translator selection unit 32 can select as many translators as the number of parts according to the sorted order. Preferably, the translator selection unit 32 calculates relevance using at least one of the translator's translation work history, the translator's evaluation score, the translator's translation rate (translation cost per minute), and the translator's knowledge background. The translator selection unit 32 may sequentially select translators in the order of calculated relevance.

For example, the translator selection unit 32 analyzes the history of content genres that each translator included in the translator pool has worked on in the past, calculates the similarity between the analyzed history and the requested content, and selects a translator based on the calculated similarity. Set the selection factor to 1. Genres here include period drama, science, medicine, romance, comedy, action, mukbang, games, etc. The translator selection unit 32 sets the evaluation scores of each translator's past translations as selection factor 2 for selecting a translator. The translator selection unit 32 sets the translation rate for each translator as selection factor 3 for selecting a translator. Here, the translation rate refers to the translation cost per minute, and each translator can decide the translation rate on his or her own. The translator selection unit 32 analyzes the knowledge background of the translator, calculates the similarity between the analyzed knowledge background and the requested content, and sets the calculated similarity as selection factor 4 for selecting a translator. Here, the knowledge background includes major field, academic background, language available for translation, presence of native language, etc. The translator selection unit 32 calculates relevance by adding up selection elements 1 to 4, and selects translators in the order of highest relevance.

Additionally, the translator selection unit 32 can select a translator to translate multiple parts from the translator pool using a learning model applied with artificial intelligence. That is, the translator selection unit 32 calculates the relevance of each translator by applying at least one of the translation work history, evaluation score, translation rate, and knowledge background as an input vector of the learning model, and selects the translators using the calculated relevance. You can. Here, the learning model can be created by applying various artificial intelligence technologies such as machine learning, deep learning, and artificial neural networks.

The task designation unit 33 matches the selected plurality of translators with each part of the divided content, and designates the translation task related to the part to the translator terminal of the matched translator. When specifying a translation task, the task specifying unit 33 may determine the translation work deadline for each part by considering the amount of translation work, translation work speed, etc. That is, the task designation unit 33 performs optimal matching according to the characteristics of each part. To this end, the task designation unit 33 analyzes the sound signal of the content for each part to determine the genre, background, playback time, expertise, etc. of the content, and selects priorities for the designated elements based on the determined results. Here, priority means listing in order the parts that need to be focused on and translated when translating content. The task designation unit 33 sets a weight based on the selected priority and applies the weight to the designation elements to match the most suitable customized translator for each part. The specified element may include at least one of the translator's translation work history, the translator's evaluation score, the translator's translation speed, and the translator's translation rate. In addition, weights of different sizes can be assigned to each designated element, and can preferably be changed depending on the peculiarities of the content, translation deadline, importance, etc. In other words, if the content is a period drama, since there are translation characteristics unique to a period drama, the most weight can be set on the translation work history, and if the content's deadline is not far away, the most weight can be set on the translation speed.

For example, the task assignment unit 33 analyzes the history of content genres on which each translator included in the translator pool has worked on past translations, calculates the degree of suitability by applying a preset first weight to the analyzed history, and calculates the degree of suitability. The degree of suitability is set to 1, a designation factor for specifying a translator. The task designation unit 33 calculates a degree of suitability by applying a preset second weight to the evaluation scores for translations translated in the past by each translator, and sets the calculated degree of suitability as designation factor 2 for designating a translator. The task designation unit 33 calculates the suitability by applying a preset third weight to the average of the translation speeds of each translator's past translations, and sets the calculated suitability as designation factor 3 for translator designation. The task designation unit 33 calculates the suitability by applying a preset fourth weight to the translation rate for each translator, and sets the calculated suitability as designation factor 4 for translator designation. The task assignment unit 33 calculates the suitability for each part by adding up designation elements 1 to 4, and designates the translator with the highest suitability for each part. Here, when one translator has the highest suitability across a plurality of parts, the task designation unit 33 may preferentially designate the translator with the highest suitability to the part with higher importance among the parts.

Additionally, the task designation unit 33 can designate a translator to translate each part from among the translators selected using a learning model to which artificial intelligence is applied. That is, the task specifying unit 33 calculates the suitability for each translator by applying at least one of designation element 1, designation element 2, designation element 3, and designation element 4 as an input vector of the learning model, and uses the calculated suitability to calculate suitability for each translator. You can designate a translator for each part.

Meanwhile, when specifying a translation task, the task specifying unit 33 may provide the translator terminal 200 with at least one piece of information among a content structure diagram, a person relationship diagram, and an honorific title relationship diagram for reference in translating the content. The content structure includes overall information about the content, such as plot, background, class (hierarchy) relationship, language style, terminology selection, etc. The character relationship diagram is a relationship diagram between characters appearing in content based on the main character, and includes information that shows various relationships such as friendly relationships, superior-subordinate relationships, and role relationships in an easy-to-understand manner. The honorific relationship diagram is a relationship diagram that shows the relationship between each character using at least one of honorifics and common words, and can be essential information, especially in the case of a period drama. Here, the content structure diagram, person relationship diagram, and honorific title relationship diagram may be provided by the client or automatically generated by the task specifying unit 33 based on information related to the requested translation received from the client.

The inspection support unit 34 receives a request for inspection of the translation work from at least one of the translator terminals performing the translation work. The review request may be a message (pop-up window, push message, etc.) indicating a request for review of content translation within the management system. When the inspection support unit 34 receives an inspection request, it requests inspection of the corresponding part from the inspector terminal 400 of the inspector in charge of translation work for the corresponding part. At this time, when the translation amount of content is large and the deadline is tight, the inspection support unit 34 may request inspection of the translation work from a plurality of inspector terminals 400. The inspection support unit 34 receives review opinions on errors and mistranslations in the corresponding part from the inspector terminal 400.

The review support department 34 supports the feedback process by transmitting information about the review opinions to the relevant translator terminal so that the received review opinions are reflected in the translation work. Here, the review support unit 34 may include a messenger function that supports real-time conversation between the translator and the reviewer so that the feedback process can run more smoothly. Through this, the review support department 34 helps ensure that review opinions are reflected in the translation work more quickly and accurately.

The task management unit 35 monitors the progress of the translation work in real time. That is, the task management unit 35 updates the management system in real time with at least one of the time remaining from the deadline, the translated subtitle content for each part, and the progress of the translation work for each part. At this time, the task management unit 35 provides a reading function for the subtitle content of the remaining parts except for the part designated for each translator terminal, and provides a reading function and a writing function for the subtitle content of the part designated for each translator terminal. Through this, the work management unit 35 supports the creation of an overall unified translation even when multiple translators perform the translation work, while preventing problems that may arise between other translators by blocking access to their own translation by translators other than themselves. can be prevented in advance. Additionally, a plurality of translators can simultaneously access the rapid translation support device 100 through their translator terminals 200 and perform translation work on assigned parts. As a result, as a plurality of parts translated by a plurality of translators are automatically connected to one translation, the rapid translation support device 100 does not need to separately perform a collection operation for the plurality of parts translated by a plurality of translators. does not exist.

The task management unit 35 uses the monitored information to manage the translation work to be completed within the content translation deadline. At this time, if the feedback process performed between the translator terminal 200 and the reviewer terminal 400 is repeatedly performed beyond a preset standard, the task management unit 35 automatically performs the feedback process through a learning model to which artificial intelligence technology is applied. can do. That is, if the feedback process is performed longer than the preset time, the task management unit 35 forcibly stops the feedback process to manage the deadline and automatically controls the translation to be completed.

When the translation work is completed, the task management unit 35 notifies the requester terminal 300 that sent the request that the translation has been completed. At this time, the task management unit 35 may send notification messages such as pop-up windows and push messages within the management system.

Additionally, the task management unit 35 performs management system operation and member management. That is, the work management unit 35 manages the procedures for membership registration when at least one new member among the translator, client, and reviewer wishes to join, and the procedures for membership withdrawal when at least one existing member wishes to withdraw. and perform member management.

The storage unit 50 stores a program or algorithm for the rapid translation support device 100 to run. The storage unit 50 stores member information about a plurality of translators, a plurality of reviewers, and a plurality of clients registered in the management system. The storage unit 50 stores information about requested content. At this time, the storage unit 50 may separately store the original content at the time of request and the content that has been translated and subtitled. Additionally, if the content is a series, the storage unit 50 may store terms used in the content in the form of a dictionary. The storage unit 50 may store learning models used in translator selection, task assignment, and inspection support. The learning model is a model using previously learned artificial intelligence technology, which produces the most optimized results in various situations and can learn information about translation work at preset intervals or in real time. The storage unit 50 includes a flash memory type, hard disk type, multimedia card micro type, card type memory (for example, SD or XD memory, etc.), Random Access Memory (RAM), Static Random Access Memory (SRAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read-Only Memory (PROM), magnetic memory, It may include at least one storage medium of a magnetic disk and an optical disk.

Although not shown in the drawing, the rapid translation support device 100 may further include an input unit (not shown). The input unit receives user input from an administrator who manages the rapid translation support device 100. User input is input by an administrator and may be a control signal related to the translation task.

Figure 10 is a diagram for explaining the user interface of a management system supporting rapid translation according to an embodiment of the present invention.

Referring to Figures 1 and 10, the rapid translation support device 100 helps translators, clients, and reviewers smoothly perform translation work within the system through a user interface supported by the management system. The management system shown in FIG. 10 may be a translation support platform included in the rapid translation support device 100.

The rapid translation support device 100 may provide different user interfaces for each user logged in to the management system, that is, for each translator, requester, and reviewer. Preferably, if the rapid translation support device 100 is a translator, it provides a user interface to perform the translation work while maintaining an optimal state, and if a requester, it provides a user interface to easily request a translation. In addition, if you are a reviewer, you can provide a user interface to review the translated work while maintaining it in optimal condition.

For example, the rapid translation support device 100 may provide a user interface 40 as shown in FIG. 10 to a translator. The user interface 40 displays at the top the order number 41 and time range 42 of the area in which the translator must work. At this time, the user interface 40 displays a timeline for the playback time below the sequence number 41 and the time range 42, and preferably the area for the translator to translate (indicated by a dotted line) is displayed in bolder color than the remaining areas. You can. The user interface 40 displays a screen 44 on which content is played on the left, the source language 45 included in the content on the lower left, and subtitles 46 on which translation work is performed on the right. displayed. In the user interface 40, the area for the subtitle translator to translate (dotted line display) may be displayed in bolder color than the remaining areas.

Figure 11 is a flowchart illustrating a method for supporting rapid translation according to an embodiment of the present invention.

Referring to Figures 1 and 11, in the rapid translation support method, when content needs to be translated urgently, multiple translators jointly translate the content to provide a fast and accurate translation to the requester. The rapid translation support method allows each translator to check in real time the translation progress and translation contents of not only the part of the content assigned to them, but also the remaining parts, so that they can recognize their own translation speed and at the same time ensure that the translated content is similar to that translated by one person. It can make you feel the same sense of unity. In addition, the rapid translation support method involves the translator, client, and reviewer accessing the rapid translation support device through their respective terminals and performing translation-related tasks within the management system provided by the rapid translation support device 100. By not performing data management such as data transfer or data collection, the system load can be lowered and faster calculations can be performed.

In step S101, the translator terminal 200, the requester terminal 300, and the reviewer terminal 400 connect to the rapid translation support device 100. The translator terminal 200, the requester terminal 300, and the reviewer terminal 400 log in to the management system provided by the rapid translation support device 100 and access the system. At this time, terminals that have not registered as members can log in to the management system after registering as members.

In step S103, the requester terminal 300 requests content translation from the rapid translation support device 100. The requester terminal 300 can request content translation by uploading the requested content while connected to the management system. Here, the request contents may include the original content requested for translation, deadline, information related to translation, special matters, etc.

In step S105, the rapid translation support device 100 divides the requested content. The rapid translation support device 100 divides the requested content into a plurality of pieces according to preset standards. The rapid translation support device 100 divides the playback period of the content into N parts, and sets the part where the sound signal is not detected within a preset error range based on each N part point as the content division point. The rapid translation support device 100 divides the content based on a set content division point to create a plurality of parts. Alternatively, the rapid translation support device 100 divides the playback time of the content into N parts and sets the part where a scene change occurs based on each N part point as the content division point. The rapid translation support device 100 divides the content based on a set content division point to create a plurality of parts.

In step S107, the rapid translation support device 100 selects a plurality of translators to perform the translation task. The rapid translation support device 100 selects a plurality of translators to perform content-related translation from a pool of pre-registered translators. The rapid translation support device 100 sorts the translator pool in order of relevance to the requested content, and selects translators corresponding to the number of parts according to the sorted order. At this time, the rapid translation support device 100 may calculate relevance using at least one of the translator's translation work history, the translator's evaluation score, the translator's translation rate, and the translator's knowledge background.

In step S109, the rapid translation support device 100 designates a translator to perform the translation task for each part. The rapid translation support device 100 analyzes the sound signal of the content for each part and selects priorities for designated elements based on the analyzed results. The rapid translation support device 100 sets weights based on priority and applies the set weights to designated elements to match the most appropriate translator for each part. Meanwhile, the rapid translation support device 100 can omit the process of asking the translator (or the translator terminal 200) whether to participate in the translation work (accept or reject) in order to quickly proceed with the translation work.

In step S111, the rapid translation support device 100 designates a translator in charge of each part. The rapid translation support device 100 uploads specified information to the management system and supports the translator terminal 200 of the translator designated for each part to confirm the information.

In step S113, the translator terminal 200 performs translation for the designated part. The translator terminal 200 can input translations translated by the translator and upload them to the management system in real time. Through this, the management system monitors the translations translated by translators in real time and supports all translators to check the uploaded translations.

In step S115, the translator terminal 200 uploads a review request related to translation. When the translation work is completed, the translator terminal 200 uploads an inspection request to the management system to request inspection of the translated work. At this time, the translation can be first inspected by the management system in real time when the translator inputs the translated content. For example, once the client's translation style is set, the management system can check in real time whether the translated content entered by the translator matches the style and provide an error alarm in real time. When an inspection request is uploaded by the translator terminal 200, the inspection request is uploaded to the management system so that the inspector terminal 400 in charge of the inspection can confirm the relevant information.

In step S117, the translator terminal 200 and the reviewer terminal 400 perform a feedback process related to inspection. The reviewer terminal 400 uploads the review opinions reviewed by the inspector to the management system, and the translator terminal 200 provides the uploaded review opinions to the translator so that the translator can respond to the review opinions. The translator terminal 200 and the reviewer terminal 400 proceed with the inspection by repeatedly performing this process.

In step S119, the inspector terminal 400 uploads that the inspection is complete. When the reviewer terminal 400 completes the inspection of all parts of the content, it uploads the inspection completion to the management system to inform the requester that the translation has been completed.

In step S121, when the inspection completion is uploaded to the management system, the rapid translation support device 100 notifies the translation completion to the client terminal 300 that requested the translation. At this time, the rapid translation support device 100 may notify the requester terminal 300 of the completion of translation through a pop-up window, push message, etc.

In step S123, the requester terminal 300 downloads the subtitled content. The requester terminal 300 downloads the translated and subtitled content from the management system.

Figure 12 is a flowchart for explaining the creation of a translator pool according to an embodiment of the present invention.

Referring to Figures 1 and 12, the rapid translation support method creates a translator pool by selecting translators who have performed rapid translation before requesting content translation.

In step S201, the translator terminal 200 connects to the rapid translation support device 100. The translator terminal 200 logs into the management system provided by the rapid translation support device 100 and connects to the system. At this time, terminals that have not registered as members can log in to the management system after registering as members.

In step S203, the rapid translation support device 100 uploads information related to the translator pool. The rapid translation support device 100 uploads a notice seeking a translator to perform rapid translation to the management system. The announcement includes the participation conditions (specifications, rate, experience, etc.) of the applying translator and can be uploaded by the administrator.

In step S205, the translator terminal 200 uploads a request to join the translator pool to the management system. The request to join the translator pool includes information such as the translator's personal information, specifications, rates, and experience, and includes an agreement to unconditionally perform the rapid translation task if assigned.

In step S207, the rapid translation support device 100 selects a translator. The rapid translation support device 100 selects translators to be registered in the translator pool based on information included in the translator pool membership request. Preferably, translators can be selected based on the genre of content requested on average.

In step S209, the rapid translation support device 100 registers the selected translator in the translator pool. The rapid translation support device 100 can create at least one translator pool in which selected translators are registered, and preferably can create a translator pool by genre to ensure smooth translation work.

In step S211, the rapid translation support device 100 uploads information related to translator pool registration to the management system. The rapid translation support device 100 uploads a notice about translator pool registration to the management system and supports translators who have requested to join the translator pool to confirm the information.

Figure 13 is a block diagram for explaining a computing device according to an embodiment of the present invention.

Referring to FIG. 13, the computing device TN100 may be a device described in this specification (eg, a rapid translation support device, a translator terminal, a requester terminal, and a reviewer terminal, etc.).

The computing device TN100 may include at least one processor TN110, a transceiver device TN120, and a memory TN130. Additionally, the computing device TN100 may further include a storage device TN140, an input interface device TN150, an output interface device TN160, etc. Components included in the computing device TN100 may be connected by a bus TN170 and communicate with each other.

The processor TN110 may execute a program command stored in at least one of the memory TN130 and the storage device TN140. The processor TN110 may refer to a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to embodiments of the present invention are performed. Processor TN110 may be configured to implement procedures, functions, and methods described in connection with embodiments of the present invention. The processor TN110 may control each component of the computing device TN100.

Each of the memory TN130 and the storage device TN140 can store various information related to the operation of the processor TN110. Each of the memory TN130 and the storage device TN140 may be comprised of at least one of a volatile storage medium and a non-volatile storage medium. For example, the memory TN130 may be comprised of at least one of read only memory (ROM) and random access memory (RAM).

The transceiving device TN120 can transmit or receive wired signals or wireless signals. The transmitting and receiving device (TN120) can be connected to a network and perform communication.

Meanwhile, the embodiments of the present invention are not only implemented through the apparatus and/or method described so far, but may also be implemented through a program that realizes the function corresponding to the configuration of the embodiment of the present invention or a recording medium on which the program is recorded. This implementation can be easily implemented by anyone skilled in the art from the description of the above-described embodiments.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements made by those skilled in the art using the basic concept of the present invention defined in the following claims are also possible. It falls within the scope of invention rights.

10: Department of Communications
30: control unit
31: Content division part
32: Translator selection department
33: Work assignment section
34: Inspection Support Department
35: Task management department
50: storage unit
51: Member information storage unit
52: Project information storage unit
53: Learning model storage unit
100: Rapid translation support device
200: Translator terminal
300: Requester terminal
400: Inspector terminal
500: Translation support system
550: communication network

Claims (17)

When a request related to content translation is received, a content division unit that divides the content into a plurality of pieces according to preset standards;
a translator selection unit that selects a plurality of translators to perform translation related to the content from a pool of already registered translators;
a task specifying unit that specifies a translation task by matching the plurality of selected translators for each part of the divided content; and
When a request for inspection of the translation work is received from at least one of the translator terminals performing the translation work, an inspection support unit that supports inspection of the corresponding part by the inspector's reviewer terminal;
Translation support device including. According to clause 1,
Monitoring the progress of the translation work, managing the translation work to be completed within the deadline for content translation using the monitored information, and notifying the requester that the translation has been completed when the translation work is completed. Management;
A rapid translation support device further comprising: According to clause 2,
The work management department,
A rapid translation support device, characterized in that at least one of the time remaining from the deadline, the translated subtitle content for each part, and the progress of the translation work for each part is updated in real time. According to clause 3,
The work management department,
A rapid translation support device that provides a reading function for subtitle content of parts other than those designated for each translator terminal, and provides a reading function and writing function for subtitle content of parts designated for each translator terminal. According to clause 2,
The work management department,
A rapid translation support device characterized in that, when the feedback process performed between the translator terminal and the reviewer terminal is repeatedly performed beyond a preset standard, the feedback process is automatically performed through a learning model to which artificial intelligence technology is applied. According to clause 1,
The content division unit,
Divide the playback time of the content into N parts, set the part where the sound signal is not detected within a preset error range based on each N part point as the content division point, and divide the content based on the set content division point. A rapid translation support device characterized by generating a plurality of parts. According to clause 1,
The content division unit,
Divide the playback time of the content into N parts, set the part where the scene change occurs based on each N dividing point as the content division point, and divide the content based on the set content division point to create a plurality of parts. A rapid translation support device characterized in that. According to clause 1,
The content division unit,
A rapid translation support device that converts the voice included in the content into text, calculates the number of words of the converted text, and divides the calculated number of words according to a preset standard to generate a plurality of parts. . According to clause 1,
The content division unit,
A rapid translation support device characterized by calculating the density of the voice included in the content and generating a plurality of parts by dividing the point where the calculated density changes rapidly. According to clause 1,
The translator selection department said,
A rapid translation support device, characterized in that, among the translator pool, the translators are sorted in order of high relevance to the requested content, and the translators are selected as many as the number of parts according to the sorted order. According to clause 10,
The translator selection department said,
A rapid translation support device, wherein the relevance is calculated using at least one of the translator's translation work history, the translator's evaluation score, the translator's translation rate, and the translator's knowledge background. According to clause 1,
The task designation unit is,
Analyze the sound signal of the content for each part, select priorities for designated elements based on the analyzed results, set weights based on the priorities, and apply the weights to the designated elements for each part. A rapid translation support device characterized by matching the most suitable translator. According to clause 12,
The task designation unit is,
A rapid translation support device characterized by matching a customized translator for each part by applying the weight to at least one of the translator's translation work history, the translator's evaluation score, the translator's translation speed, and the translator's rate. According to clause 1,
The task designation unit is,
When specifying the translation task, a rapid translation support device characterized in that it provides at least one of a content structure diagram, a person relationship diagram, and an honorific title relationship diagram for reference in translating the content. According to clause 1,
The inspection support department said,
A rapid translation support device, characterized in that it receives review opinions on errors and mistranslations of the corresponding part from the reviewer terminal and supports a feedback process so that the received review opinions are reflected by the corresponding translator terminal. When the rapid translation support device receives a request related to content translation, dividing the content into a plurality of pieces according to preset standards;
selecting, by the rapid translation support device, a plurality of translators to perform translation related to the content from a pool of pre-registered translators;
specifying a translation task by matching, by the rapid translation support device, the plurality of selected translators for each part of the divided content; and
When the rapid translation support device receives a request for inspection of the translation work from at least one of the translator terminals performing the translation work, supporting the inspection of the corresponding part by the reviewer's reviewer terminal;
Rapid translation support method including. According to clause 16,
Before the dividing step,
Uploading, by the rapid translation support device, information related to the translator pool to a management system;
receiving, by the rapid translation support device, a request to join the translator pool from at least one translator terminal;
selecting, by the rapid translation support device, a translator to be registered in the translator pool based on the subscription request; and
registering, by the rapid translation support device, the selected translator in the translator pool;
A rapid translation support method further comprising:

Images