KR102244448B1 - The method for providing the speciality translation service platform - Google Patents

Abstract

The present invention relates to a method for providing a professional translation service platform implemented by at least one processor of a computing device. The method includes: a step of generating at least one translation model so as to correspond to at least one domain; a step of determining an optimal translation model corresponding to a user terminal out of the one or more translation models based on received subscription request information in a case where the subscription request information is received from the user terminal; a step of generating a translation sentence corresponding to a received input sentence by utilizing the optimal translation model in a case where translation request information including the input sentence is received from the user terminal; a step of determining at least one requested translator terminal for retranslation request based on received retranslation request information in a case where the retranslation request information related to the translation sentence is received from the user terminal; a step of making a determination to transmit the retranslation request information to the one or more requested translator terminals; and a step of making a determination to transmit a first retranslation sentence as one of one or more received retranslation sentences to the user terminal in a case where the one or more retranslation sentences are received from the one or more requested translator terminals.

Description

A method to provide a professional translation service platform {THE METHOD FOR PROVIDING THE SPECIALITY TRANSLATION SERVICE PLATFORM}

The present disclosure relates to a translation technology using artificial intelligence, and more specifically, to provide a computing device that provides a more professional translation service according to a user's needs.

As the amount of information that can be processed increases with the advancement of computer technology, artificial intelligence is evolving at a rapid rate, and with the development of artificial intelligence, interest in machine translation is increasing. As a server platform for such machine translation, there are various translators including Google Translator and Naver Translator.

In recent years, as the level of machine translation has risen rapidly through deep learning algorithms, high-quality translation services are currently being supplied. This machine translation has the advantage of being able to provide a translation of the original text quickly in real time and low cost.

However, in the conventional machine translation, there is a limitation in outputting a natural translation that considers the context of an original sentence related to knowledge in a special specialized field. Specifically, since conventional machine translation is a general-purpose translation applied to multiple fields, there is a concern that words used in a specific field may not be properly translated or may not be able to utilize meaning. For example, in the IT field, words such as master/slave can be interpreted as meanings such as'main system', which is the subject of an operation, or'subordinate system', which plays a subordinate role in performing a single task. There is a concern that the accuracy of the generated translated sentences may be insufficient as the machine translation service platform of is simply recognizing the words as master/slave.

Accordingly, there may be a demand in the industry for a platform that provides a more professional translation service in response to the needs of individual users who wish to use the translation service.

Registered Patent Publication No. 10-1818598 (2016.08.09)

The problem to be solved by the present disclosure is to solve the above-described problem, and to provide a computing device that provides a more professional translation service in response to the needs of individual users.

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 providing a professional translation service platform, which is performed in one or more processors of a computing device according to various embodiments of the present disclosure for solving the above-described problems. The method comprises the steps of generating one or more translation models corresponding to one or more domains, when subscription request information is received from a user terminal, corresponding to the user terminal among the one or more translation models based on the received subscription request information Determining an optimal translation model to perform, when a translation request information including an input sentence is received from the user terminal, generating a translation sentence corresponding to the received input sentence by using the optimal translation model, the user When retranslation request information related to the translated sentence is received from a terminal, determining at least one request translator terminal to request retranslation based on the received retranslation request information, and the retranslation request information to the at least one request translator terminal Determining to transmit, and when one or more retranslated sentences are received from the at least one request translator terminal, determining to transmit a first retranslated sentence from among the received one or more retranslated sentences to the user terminal.

In an alternative embodiment, generating one or more translation models corresponding to the one or more domains comprises: obtaining a training data set including a plurality of training data, the plurality of training data based on one or more domains. Classifying and constructing one or more subsets of training data, and generating the one or more translation models by performing training on each of the one or more neural network models through each of the one or more subsets of training data.

In an alternative embodiment, the step of constructing one or more subsets of learning data by classifying the plurality of learning data based on one or more domains includes a result of semantic analysis of each of the plurality of learning data, each of the plurality of learning data. Identifying each domain of the plurality of learning data based on at least one of the number of repetitions of each word and a predetermined topic included in the semantic analysis result, and the one or more learning data subs based on the domains of each of the plurality of learning data Building the set may be included.

In an alternative embodiment, the subscription request information is information serving as a criterion for determining the optimal translation model corresponding to the user terminal, and the translation request information includes user language identification information related to a starting language and a destination language, and It includes user domain identification information, and the retranslation request information is information regarding a retranslation request for the translated sentence, and may be generated based on the translation request information.

In an alternative embodiment, generating a first input sentence by performing reverse translation on the translated sentence, and calculating the translation reliability of the translated sentence based on a comparison between the generated first input sentence and the input sentence. And determining whether to transmit the retranslation request information to the at least one requesting translator terminal based on the translation reliability and determining whether to transmit the translation reliability to the user terminal.

In an alternative embodiment, further comprising receiving translation participation information from each of the plurality of translator terminals and establishing a translator database based on the translation participation information of each of the plurality of translator terminals, the translation participation information, It may include translator language identification information and translator domain identification information.

In an alternative embodiment, the step of determining one or more request translator terminals to request retranslation based on the received retranslation request information comprises: identifying one or more candidate translator terminals corresponding to the retranslation request information by referring to the translator database. And determining the at least one requesting translator terminal based on the translation evaluation score of the identified at least one candidate translator terminal, wherein the translation evaluation score is a translation performed by each translator terminal in response to a previous time point. It may be an evaluation score for.

In an alternative embodiment, the step of determining one or more translator terminals to request retranslation based on the received retranslation request information includes at least one candidate translator terminal corresponding to the domain identification information of the user terminal with reference to the translator database. Identifying the at least one translation service participation request to the at least one candidate translator terminal, and determining the at least one request translator terminal based on the participation response of the at least one candidate translator terminal to the translation service participation request It may include the step of.

In an alternative embodiment, when one or more retranslated sentences are received from the at least one request translator terminal, the step of determining to transmit a first retranslated sentence from among the received one or more retranslated sentences to the user terminal, the at least one request It may include the step of determining the first retranslated sentence from among the one or more retranslated sentences based on evaluation score information of each of the translator terminals.

In an alternative embodiment, determining to transmit the received one or more retranslated sentences to the user terminal, receiving selection information for at least one retranslated sentence among the one or more retranslated sentences from the user terminal, and the reception It may further include the step of identifying the first retranslated sentence from among the one or more retranslated sentences based on the selection information.

In an alternative embodiment, the input sentence and the first retranslated sentence are matched and labeled to generate additional learning data, and the optimal translation model by performing additional learning on the optimal translation model through the additional learning data. It may further include the step of updating.

According to another embodiment of the present disclosure, a computing device for providing a professional translation service platform. 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 a user terminal and a translator terminal, and the processor includes one or more domains corresponding to one or more domains. When the above translation model is generated and subscription request information is received from the user terminal, an optimal translation model corresponding to the user terminal is determined from among the one or more translation models based on the received subscription request information, and from the user terminal When translation request information including an input sentence is received, a translation sentence corresponding to the received input sentence is generated using the optimal translation model, and retranslation request information related to the translated sentence is received from the user terminal , Based on the received retranslation request information, at least one request translator terminal to request retranslation is determined, it is determined to transmit the retranslation request information to the at least one request translator terminal, and at least one retranslation from the at least one request translator terminal When a sentence is received, it may be determined to transmit a first retranslated sentence from among the received one or more retranslated sentences to the user terminal.

According to various embodiments of the present disclosure, a computing device that provides a more specialized translation service in response to the needs of individual users may be provided.

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 providing a professional translation service platform related to an embodiment of the present disclosure may be implemented.
FIG. 2 is a block diagram illustrating an embodiment of the present disclosure and a computing device for providing a professional translation service platform.
3 shows an exemplary diagram for one or more translation models related to an embodiment of the present disclosure.
4 shows an exemplary flow chart of a method for providing a professional translation service platform related to an embodiment of the present disclosure.
5 is a flowchart illustrating steps for performing a method for providing a professional translation service platform related to an embodiment of the present disclosure.
6 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 providing a professional translation service platform related 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, a translator terminal 20, an external server 30, 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, the translator terminal 20, and the external server 30 according to the embodiments of the present disclosure transmit data for the system according to the exemplary embodiments of the present disclosure through a network. They can transmit and receive each other.

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 is a terminal capable of receiving information related to a translated sentence corresponding to an input sentence through information exchange with the computing device 100, and means a terminal possessed by a user. can do. For example, the user terminal 10 may be a terminal related to a user who wants to translate an input sentence composed of a specific language into another language or a user who wants to inspect the translated sentence. The user may receive a translated sentence and a retranslated sentence corresponding to the input sentence through the user terminal 10.

The translator terminal 20 of the present disclosure provides a retranslated sentence corresponding to an input sentence related to the translation request of the user terminal 10 through information exchange with the computing device 100, and a terminal capable of receiving compensation corresponding thereto. As such, it may mean a terminal possessed by a user (or a translator) performing a translation task. For example, the translator terminal 20 transmits a retranslation sentence related to the result of performing the translation on the input sentence received from the user terminal 10 to the computing device 100, and responds to the result of performing the translation from the computing device 100. It is possible to obtain compensation information. A user (or translator) performing a translation job may receive an input sentence and compensation information related to the translation job through the translator terminal 20.

The user terminal 10 and the translator terminal 20 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 and the translator terminal 20 include a personal computer (PC), a notebook (note book), a mobile terminal, a smart phone, a tablet PC, and It may include a wearable device or the like, and may include all types of terminals capable of accessing a wired/wireless network. In addition, the user terminal 10 and the translator terminal 20 may include any server implemented by at least one of an agent, an application programming interface (API), and a plug-in. In addition, the user terminal 10 and the translator terminal 20 may include an application source and/or a client application. In FIG. 1, only one user terminal and one translator terminal connected to the computing device 100 are exemplarily illustrated, but the computing device of the present disclosure is connected to a plurality of user terminals and a plurality of translator terminals to provide a translation service platform. It will be apparent to those skilled in the art that it can provide.

According to an embodiment of the present disclosure, the external server 30 may be a server that stores training data related to training of a translation model. The translation model of the present disclosure may be a neural network model that receives an input sentence as an input and outputs a translation sentence corresponding to the input sentence. For example, the external server 30 may be a server that stores a plurality of input sentences corresponding to various languages and translation information corresponding to each of the plurality of input sentences. Information stored in the external server 30 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 30 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 learning data set based on input sentences composed of various languages from the external server 30 and translation sentence information corresponding to each input sentence, and one through the learning data set. By performing training on a plurality of neural network models including the above network functions, it is possible to generate a plurality of translation models that perform translation tasks corresponding to each of one or more specialized fields (or domains). In addition, the computing device 100 of the present disclosure may perform augmentation on learning data by transmitting the retranslated sentence received from the translator terminal 20 to the external server 30 in response to the input sentence.

The external server 30 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 computing capability having a memory. The external server 30 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 receive an input sentence from the user terminal 10 and provide a professional translation service for the received input sentence.

Specifically, the computing device 100 may generate one or more translation models corresponding to one or more domains. Here, at least one domain is a reference for classifying a plurality of learning data, and may be related to various specialized fields. For example, one or more domains may be related to various specialized fields, such as the medical field, the legal field, the IT field, or the economic field. The computing device 100 may generate one or more translation models corresponding to each of one or more domains related to various specialized fields.

For example, the computing device 100 may provide a first translation model for performing translation related to the medical field, a second translation model for performing translation related to the legal field, and a translation related to the IT field, corresponding to each of one or more domains. It is possible to generate a third translation model to perform and a fourth translation model to perform translations related to the economic field. Detailed description of the above-described one or more domains and a translation model generated corresponding to each of the domains is only an example, and the present disclosure is not limited thereto.

That is, the computing device 100 may generate one or more translation models that perform translation specialized for each of various fields. For example, as shown in FIG. 3, the computing device 100 may generate a legal translation model 210, an IT translation model 220, and an economic translation model 230 in correspondence with one or more domains, At least one of the legal translation model 210, the IT translation model 220, and the economic translation model 230 may be determined as an optimal translation model corresponding to the user terminal 10. Accordingly, it may be possible to provide a translation model that performs professional translation according to individual needs of each of a plurality of users. Accordingly, the user can obtain a more specialized translated sentence in response to an input sentence through a translation model suitable for his or her needs.

In addition, when receiving retranslation request information from the user terminal 10, the computing device 100 may determine one or more request translator terminals that have requested retranslation based on the received retranslation request information. The retranslation request information may be information on a retranslation request for a translated sentence.

Specifically, the computing device 100 may provide an optimal translation model that meets the user's needs of the user terminal 10. The computing device 100 may generate a translated sentence by processing an input sentence that the user of the user terminal 10 wants to perform as an input to a corresponding optimal translation model. As the computing device 100 transmits the output translated sentence to the user terminal 10, the user terminal 10 may receive a translated sentence corresponding to the input sentence. The user of the user terminal 10 may generate retranslation request information and transmit the retranslation request information to the computing device 100 in the process of inspecting the corresponding translated sentence. For example, the user may apply an input to the user terminal 10 so that retranslation request information is generated when it is determined that the meaning or expression of the translated sentence is not appropriate in the process of reviewing the translated sentence output through the optimal translation model. I can.

The computing device 100 may receive retranslation request information related to a corresponding translation sentence (ie, a translation sentence related to the output of a translation model) from the user terminal 10. In other words, when it is determined that the translated sentence related to the output of the optimal translation model is not appropriate, the user terminal 10 may generate retranslation request information related to the translated sentence and transmit it to the computing device 100. When receiving the retranslation request information, the computing device 100 may determine one or more request translator terminals to request retranslation. In this case, at least one request translator terminal to which the computing device 100 requests retranslation of the input sentence of the user terminal 10 may be a translator terminal corresponding to the input sentence received from the user terminal 10. Specifically, the computing device 100 may determine whether the input sentence is related to which of one or more domains based on the result of semantic analysis of the input sentence. The computing device 100 may determine a translator terminal corresponding to a domain related to the input sentence as one or more request translator terminals to request retranslation of the input sentence. For example, if the input sentence is "if there is no law on civil, it is according to a customary law, and if there is no customary law, it is by cooking.", the computing device 100 analyzes the meaning of the input sentence, and the corresponding input sentence is related to the legal domain. It is determined that it is determined that the translator terminals corresponding to the legal field among the plurality of translator terminals may be determined as one or more requested translator terminals.

To this end, the computing device 100 may receive translation participation information from a plurality of translator terminals to establish a translator database. The translation participation information may be generated in relation to the time point at which the translator terminals wish to participate in the translation, and may be information for identifying each of the plurality of translator terminals. In addition, the translation participation information may include translator language identification information and translator domain identification information. The translator language identification information may be information for identifying a language that can be utilized by a user of each translator terminal (ie, a language in which translation can be performed). The translator domain identification information may be information related to one or more domains (or fields) capable of professionally performing translation of each translator terminal. For example, the translator language identification information of the first translator terminal may include information that the first user (or the first translator) can use Korean, English, and Japanese, and the translator domain identification information It may include information that the translation related to the can be performed professionally. The detailed description of the language identification information and the domain identification information of the above-described first translator terminal is only an example, and the present disclosure is not limited thereto. In other words, the computing device 100 may refer to the translator database to determine one or more request translator terminals corresponding to the input sentences received from the user terminal 10. In addition, the computing device 100 may transmit retranslation request information including the input sentence to one or more request translator terminals determined to correspond to the input sentence.

Accordingly, each of the at least one request translator terminal 20 may receive and display an input sentence of the user terminal 10. That is, a user related to translation may generate a retranslated sentence based on an input sentence displayed through each request translator terminal 20 and transmit the generated retranslated sentence to the computing device 100.

The computing device 100 may receive one or more retranslated sentences from each of the one or more request translator terminals 20. Also, the computing device 100 may determine a first retranslated sentence related to an optimal translated sentence from among one or more retranslated sentences. For example, when one or more retranslated sentences are received, the computing device 100 may determine the first retranslated sentence based on translation evaluation scores of request translator terminals related to the generation of each retranslated sentence. The translation evaluation score may be an evaluation score for a translation performed by each translator terminal in response to an advantage point. For a specific example, the translation evaluation scores of each of the first l translator terminal, the second commissioned translator terminal, and the third commissioned translator terminal were 50, 76, and 80, respectively, and the first sub-sentence retranslated from each commissioned translator terminal, and retranslated. When receiving the second sub-sentence and the retranslation third sub-sentence, the computing device 100 identifies that the translation evaluation score of the third requesting translator terminal is the highest, and generates a retranslated third sub-sentence corresponding to the corresponding translator terminal. It can be decided by the first retranslated sentence. The detailed numerical description of the translation evaluation score corresponding to each requested translator terminal is only an example, and the present disclosure is not limited thereto.

That is, the computing device 100 may determine a first retranslated sentence more suitable for the input sentence of the user terminal 10 among one or more retranslated sentences received from each of the at least one request translator terminal and transmit it to the user terminal 10. In other words, the computing device 100 determines a request translator terminal capable of performing a more professional translation in response to a translation request from the user terminal 10 and associates it with the user terminal 10, thereby providing professional translation information. Can provide. In this case, the request translator terminals that the computing device 100 links with the user terminal 10 are terminals related to the user performing translation of the corresponding domain through the translation request information of the user terminal 10, so the input sentence In response to, natural and appropriate translation sentences can be provided. In addition, as the translated sentence is a sentence translated by a professional translator in the field, it is possible to provide a translated sentence for a language expression or language structure that the machine cannot understand, and it is possible to provide a translated sentence that reflects a more appropriate expression. It may be possible, thereby improving the user's service satisfaction.

Also, the computing device 100 may perform augmentation on the learning data based on the input sentence and the first retranslated sentence. Specifically, the computing device 100 may generate additional learning data by matching and labeling the input sentence and the first retranslated sentence. In addition, the computing device 100 may perform additional learning on an optimal translation model corresponding to the user terminal 10 through the additional learning data to be updated. In this case, the updated optimal translation model may be learned to output a first retranslated sentence generated by a professional translator in response to the corresponding input sentence by inputting an input sentence related to the translation request of the user terminal 10 as an input. That is, the computing device 100 augments the learning data through each of the various input sentences received from the plurality of user terminals and the various translation sentences of the translator terminals corresponding thereto, and updates the optimal translation model through the augmented learning data. can do. Accordingly, it may be possible to advance the translation model over time by the above-described process of the computing device 100. This may cause an effect of improving the reliability and accuracy of the translated sentence output through the translation model.

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 for providing a professional translation service platform in response to an individual user in the present disclosure and effects thereof will be described later with reference to FIG. 2.

FIG. 2 is a block diagram illustrating an embodiment of the present disclosure and a computing device for providing a professional translation service platform.

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, a translator terminal 20, and a network unit 110 that transmits and receives data to and from the external server 30. The network unit 110 may transmit and receive data for performing a method for providing a professional translation service platform according to an embodiment of the present disclosure, a training data set for training a neural network model, etc. have. That is, the network unit 110 may provide a communication function between the computing device 100 and the user terminal 10, the translator terminal 20, and the external server 30. For example, the network unit 110 may receive translation request information including an input sentence from the user terminal 10, retranslation request information related to a retranslation request for a translated sentence, and the like. For another example, the network unit 110 may receive a translated sentence from the translator terminal 20. As another example, the network unit 110 may receive a training data set for training the translation model of the present disclosure from the external server 30. Additionally, the network unit 110 may allow information transfer between the computing device 100 and the user terminal 10 and the external server 30 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 providing a professional translation service platform according to an embodiment of the present disclosure, and the stored computer program is the processor 130 Can be read and driven by 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. In addition, the memory 120 may store an input sentence and information related to a translated sentence corresponding to the input sentence. For example, the memory 120 includes input/output data (eg, translation request information including an input sentence, a translation sentence corresponding to the input sentence, and retranslation request information related to a retranslation request of the translated sentence, etc.) Can be stored temporarily or permanently.

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 configured with one or more cores, and a central processing unit (CPU) and a general purpose graphics processing unit (GPGPU) of a computing device. , A tensor processing unit (TPU) may include a processor for data analysis and deep learning.

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 one or more translation models 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 a translated sentence corresponding to an input sentence. According to an embodiment of the present disclosure, the processor 130 may perform calculations for training one or more translation models.

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 generate one or more translation models corresponding to one or more domains. Each of the one or more translation models in the present disclosure may be, for example, a model that performs Neural Machine Translation (NMT) based on an artificial neural network. Each of the one or more translation models may convert an input sentence into a sentence vector form and generate a sentence of an output language based on the converted sentence vector. In this case, a part that converts an input sentence into a sentence vector may be an encoder, and a part that generates an output sentence may be a decoder. The language translation model can automatically learn a number of parameter values constituting an artificial neural network of an encoder and a decoder through training data composed of training input data and training result data.

For another example, each of the one or more translation models may be a neural network model that performs corpus-based machine translation (CMT). The corpus-based machine translation may include example-based machine translation (EBMT) and statistical machine translation (SMT). The example-based machine translation may be a method of storing the translated input sentence and information of the translated sentence, and then outputting a translation result using pre-stored information in response to a request for translation of the same sentence. The statistics-based machine translation may be a machine translation of a method of analyzing the frequency of linguistic correlation between the original text and the translated text, and then statistically converting the frequency of the language correlation between the original text and the translated text.

That is, each of the one or more translation models may be a neural network model that is trained to generate a translation sentence by inputting an input sentence through a plurality of training data including a plurality of training input data and a plurality of training output data.

In order to generate one or more translation models, the processor 130 may obtain a training data set including a plurality of training data. Specifically, the processor 130 may acquire a training data set through the network unit 110. Acquisition of the training data set according to the exemplary embodiment of the present disclosure may be receiving or loading the training data set stored in the memory 120. For example, acquiring the training data set may be receiving the training data set stored in the external server 30. Receiving the learning data may be receiving or loading original text data from another storage medium, another computing device, or a separate processing module in the same computing device based on a wired/wireless communication means.

In detail, the processor 130 may construct one or more sub-data of learning data by classifying a plurality of learning data based on one or more domains. One or more domains serve as a criterion for classifying a plurality of training data, and may be related to various specialized fields. For example, one or more domains may be related to various specialties, such as the medical field, the legal field, the IT field, or the economic field.

The plurality of learning data may include a plurality of learning input data composed of an original text and a plurality of learning output data composed of a translated text for the corresponding original text. For example, the first learning input data may be a sentence composed of Korean, and the first learning output data may be a sentence composed of English, which is an English translation result for the corresponding sentence. In this case, the first training input data and the first training output data may be labeled training data. That is, in neural network training, the first training input data may be data related to an input of the neural network. The first training output data may be data that is compared with the output of the neural network for the first training input data.

The processor 130 identifies each domain of the plurality of learning data based on at least one of a semantic analysis result of each of the plurality of learning data, the number of repetitions for each word included in the semantic analysis result of each of the plurality of learning data, and a predetermined topic. can do.

Specifically, the processor 130 may determine one or more domains based on a result of semantic analysis of each of the plurality of training data. For example, if each word included in the semantic analysis result is'copyright','in the work','exclusive','exclusive','right','guarantee','is an institution', the processor 130 ) Can be determined as the domain of'copyright' or'right' as it is determined that the meaning of'copyright' or'right' is of relatively high importance. The specific description of the importance of each of the one or more words and the one or more words included in the above-described semantic analysis result is only an example, and the present disclosure is not limited thereto.

In addition, the processor 130 may determine one or more domains for the conversation log based on the number of repetitions for each word included in the result of semantic analysis for each learning input data. The processor 130 may identify the repetition number of each one or more words included in the semantic analysis result, and determine a word having a high repetition number as a domain for each learning input data.

Also, the processor 130 may determine a domain based on a predetermined topic. The processor 130 may determine the subject of the learning input data through the semantic analysis result, and may determine one or more domains corresponding to the determined subject. In this case, each of the plurality of domains may be stored in advance in the memory 120 corresponding to each of the plurality of subjects. For example, domains related to the legal field may be matched to correspond to a subject related to'copyright' and stored in the memory 120 in advance. Specific descriptions of the above-described subject and domains corresponding to the subject are only examples, and the present disclosure is not limited thereto.

The processor 130 may construct one or more subsets of learning data based on each domain of a plurality of learning data. In addition, the processor 130 may generate one or more translation models by performing training on each of one or more neural network models through each of one or more subsets of training data.

For a specific example, a training data set related to training of a neural network may include a plurality of training data related to various domains. In this case, the computing device 100 may generate one or more subsets of learning data by classifying a plurality of training data based on each of one or more domains. For example, one or more subsets of training data may be a combination of subsets of training data, and each subset of training data may be a combination of a plurality of training data based on different domains. For example, one or more subsets of training data constructed by the processor 130 may include a first subset of training data and a second subset of training data. In this case, the first subset of training data may include a plurality of training data related to the medical field, and the second subset of training data may include a plurality of training data related to the legal field. The specific description of the above-described one or more specialized fields is only an example, and the present disclosure is not limited thereto.

More specifically, each subset of learning data may include learning input sub-data composed of a starting language and second learning output sub-data composed of a destination language in relation to each field. In this case, the processor 130 may generate a plurality of translation models by performing training on each neural network model through each subset of training data.

For a specific example, one or more subsets of learning data may include a first subset of learning data related to a legal field, and the first subset of learning data includes first learning input sub-data consisting of Korean and English. It may include the first learning output sub-data. The processor 130 may output first training result data by inputting the first training input sub-data included in the first training data subset into the first neural network model. The processor 130 may derive an error between the output first training result data and the first training output data labeled on the first training input sub-data. In addition, the processor 130 may perform training on the first neural network model by backpropagating the error and adjusting the weight of the neural network so that the first training result data and the first training output sub-data are similar. As the learning of the first neural network model as described above is completed, a first translation model may be generated. That is, the first translation model may output a translated sentence composed of English by inputting an input sentence composed of Korean in relation to the legal field through the above-described learning. In this case, since the training data related to the learning of the first translation model are data related to the legal field by the processor 130, the first translation model can output a more appropriate translation sentence in response to the input sentence in the corresponding legal field. have.

That is, the processor 130 generates a subset of training data by classifying a plurality of training data related to learning of a neural network based on one or more domains related to various specialized fields, and uses the generated subset of training data for each of various fields. It is possible to create one or more translation models that perform translations specific to the application. Accordingly, it may be possible to provide a suitable translation model according to the individual needs of each of a plurality of users. Accordingly, the user can obtain more specialized translation information in response to an input sentence to be translated through a translation model suitable for his or her needs.

According to an embodiment of the present disclosure, the processor 130 may determine an optimal translation model corresponding to a user terminal from among one or more translation models. Specifically, when the subscription request information is received from the user terminal, the processor 130 may determine an optimal translation model corresponding to the user terminal 10 from among one or more translation models based on the received subscription request information. The optimal translation model may be a translation model for outputting more suitable translation information in the field related to the user terminal 10. The subscription request information may be information that serves as a criterion for determining an optimal translation model corresponding to the user terminal. The subscription request information may include at least one of user language identification information and user domain identification information. The user language identification information may include information on a starting language that the user of the user terminal 10 wants to translate and a destination language corresponding to the translation result. For example, the user language identification information may include information that the input sentence to be translated by the user of the first user terminal is Japanese (i.e., the starting language), and the translated sentence to be obtained as a result of the translation is English (i.e., the destination language). I can. The detailed description of the language related to the above-described input sentence and the translated sentence is only an example, and the present disclosure is not limited thereto. The user domain identification information may be information for identifying a field related to an input sentence to be translated by the user of the user terminal 10. For example, the user domain identification information may include information that the input sentence that the user of the first user terminal wants to translate is related to the IT field. As another example, the user domain identification information may include information that the input sentence that the user of the second user terminal wants to translate is related to the legal field. The detailed description of the above-described user language identification information and domain identification information is only an example, and the present disclosure is not limited thereto.

That is, the processor 130 may determine an optimal translation model corresponding to the user terminal from among one or more translation models generated in response to various specialized fields based on the user language identification information and the user domain identification information included in the subscription request information. have. For example, the subscription request information received from the first user terminal 10 indicates that the input sentence that the user wants to translate is Korean, and the translated sentence that the user wants to acquire is English, and user language identification information and input that the user wants to translate. When the sentence includes user domain identification information that is related to the legal field, the processor 130 includes learning input sub-data composed of Korean and learning output sub-data composed of English related to the legal field among one or more translation models. A translation model generated through learning using a data subset may be determined as an optimal translation model corresponding to the first user terminal 10.

In a further embodiment, the subscription request information received from the user terminal 10 may include a customized learning data set. Here, the customized learning data set is information related to the user's unique translation style of the user terminal 10, and may be used as training data for generating an optimal translation model more suitable for the user. For example, the customized learning data set may include information related to a translation work performed by a corresponding user in the past. That is, the customized training data set may be training data reflecting a translation style of a specific user. Accordingly, the processor 130 may identify whether the customized learning data set is included in the subscription request information received from the user terminal 10. In addition, when it is identified that the subscription request information includes a customized learning data set corresponding to the user, the processor 130 trains a neural network model composed of one or more network functions through the customized learning data set, thereby establishing an optimal translation model. Can be generated. In other words, when the processor 130 receives the customized training data set, which is a set of information on the user's own translation style, from the user terminal 10, the processor 130 may generate an optimal translation model through the customized learning data set. have. In this case, the optimal translation model generated by the processor 130 is a neural network model learned through training data related to the user's existing translation style (i.e., a customized training data set), and thus the user's needs in response to the input sentence You can output a translated sentence that is more consistent with.

That is, the processor 130 may generate a plurality of translation models in relation to various domains, and select and provide an optimal translation model that is expected to be more suitable for the user terminal 10 from among the generated plurality of translation models. In addition, when the processor 130 receives the customized training data set reflecting the user's own unique translation characteristics from the user terminal 10, the processor 130 may generate and provide an optimal translation model specialized to the user through the corresponding training data. have.

According to an embodiment of the present disclosure, the processor 130 may receive translation request information including an input sentence from a user terminal. The input sentence may mean a sentence composed of a starting language in which the user of the user terminal 10 intends to perform translation.

When the translation request information is received from the user terminal 10, the processor 130 may generate a translation sentence corresponding to the translation request information by using an optimal translation model. In this case, the optimal translation model, as described above, is determined based on user language identification information and user domain identification information corresponding to the user terminal 10, and corresponds to the input sentence received from the user terminal 10. It may be a translation model that generates more suitable translation sentences. Specifically, the processor 130 may generate a translation sentence corresponding to the input sentence by identifying an input sentence from the received translation request information and processing the identified input sentence as an input of an optimal translation model.

According to an embodiment of the present disclosure, the processor 130 may calculate a translation reliability for a translated sentence. In more detail, the processor 130 may generate a back-translated sentence by performing back-translation on a translated sentence generated (or translated) corresponding to an input sentence. In this case, the reverse translation performed by the processor 130 may mean translating the translated sentence into a language corresponding to the input sentence. The processor 130 may calculate the translation reliability for the translated sentence based on the comparison between the reverse translation sentence and the input sentence.

For a specific example, in a case in which an input sentence composed of Korean is to be translated into a translated sentence composed of English, the processor 130 may generate a translated sentence by processing the input sentence as an input of a translation model. In this case, the processor 130 may calculate a translation reliability corresponding to the translated sentence in order to determine the accuracy of the translation of the translated sentence. The processor 130 processes the translated sentence written in English as an input of another translation model (e.g., a translation model related to the same domain and outputting a translated sentence composed of Korean by inputting an input sentence composed of English as an input) You can create reverse translation sentences composed of Korean.

Also, the processor 130 may calculate a translation reliability based on a comparison between an input sentence composed of the same Korean language and a reverse translation sentence. For example, when a comparison result of a first input sentence and a first reverse translation sentence corresponding to the first input sentence, and it is determined that the structure or meaning of each sentence is similar, the processor 130 By judging that the accuracy of the translation is high, a higher reliability of the translation can be calculated. For another example, when it is determined that the structure or meaning of each sentence is not similar as a result of comparing the second input sentence with the second reverse translation sentence corresponding to the second input sentence, the processor 130 It is determined that the accuracy of the translation for the sentence is low, so that a lower translation reliability can be calculated. Specific descriptions of the above-described input sentences, translation sentences, and reverse translation sentences are only examples, and the present disclosure is not limited thereto.

That is, the processor 130 may calculate the translation reliability of the translated sentence by performing reverse translation on the translated sentence generated in response to the input sentence. The translation reliability corresponding to such a translated sentence indicates the accuracy of the translation, and may be used as information to allow the user to recognize the accuracy of the translation for the translated sentence during the inspection process.

According to an embodiment of the present disclosure, the processor 130 may receive translation participation information from each of a plurality of translator terminals. The translation participation information may be generated in relation to the time point at which the translator terminals wish to participate in the translation, and may be information for identifying each of the plurality of translator terminals. In addition, the translation participation information may include translator language identification information and translator domain identification information. The translator language identification information may be information for identifying a language that can be utilized by a user of each translator terminal (ie, a language in which translation can be performed). The translator domain identification information may be information related to one or more fields capable of professionally performing translation of each translator terminal. For example, the translator language identification information of the first translator terminal may include information that the first user (or the first translator) can use Korean, English, and Japanese, and the translator domain identification information It may include information that the translation related to the can be performed professionally. The detailed description of the language identification information and the domain identification information of the above-described first translator terminal is only an example, and the present disclosure is not limited thereto.

In addition, the processor 130 may build a translator database based on translation participation information of each of the plurality of translator terminals. When the translation participation information is received from each of the plurality of translator terminals, the processor 130 may build a translator database based on the corresponding translation participation information. The translator database may be referred to by the computing device 100 when the user terminal 10 transmits translation request information corresponding to a specific input sentence to the computing device 100.

According to an embodiment of the present disclosure, the processor 130 may receive retranslation request information from a user terminal. The retranslation request information is information on a retranslation request for a translated sentence, and may be information generated based on the translation request information. Accordingly, the retranslation request information may include an input sentence and domain identification information corresponding to the translation request information. Specifically, the retranslation request information may include an input sentence to be translated, user language identification information and user domain identification information included in the translation request information.

When retranslation request information is received from the user terminal 10, the processor 130 may determine one or more request translator terminals to request retranslation based on the received retranslation request information. Specifically, the processor 130 may identify one or more translator terminals corresponding to the retranslation request information by referring to the translator database. For example, the processor 130 may determine one or more candidate translator terminals corresponding to user language identification information and user domain identification information included in retranslation request information among a plurality of translator terminals included in the translator database.

For a specific example, the domain in which the retranslation request information of the user terminal 10 indicates that the input sentence to be translated by the user is Korean, and the translated sentence to be translated is English, and the user language identification information and the input sentence are related to the legal field. When including the identification information, the processor 130 refers to a plurality of translator databases including translator language identification information and translator domain identification information of each of the plurality of translator terminals, and corresponds to the user language identification information and the user domain identification information. One or more candidate translator terminals may be identified. In this case, the one or more candidate translator terminals identified by the processor 130 may be terminals related to translators who are fluent in Korean and English utilization and professionally perform translations in the legal field.

In addition, the processor 130 may determine one or more request translator terminals based on the translation evaluation scores of the identified one or more candidate translator terminals. The translation evaluation score may be an evaluation score for a translation performed by each translator terminal in response to a previous time point. For example, the translation evaluation score may be a translation evaluation score received from a user terminal or other translator terminals. For example, if the first translator terminal participated in generating a translated sentence three times at this point of time, and the translation evaluation sub-scores corresponding to each time were 5, 7 and 9, the processor 130 The translation evaluation score of the first translator terminal may be calculated as 7 through the average of the translation evaluation subscore per episode. Detailed numerical descriptions of the number of previous translation participation, translation evaluation subscore, and translation evaluation score in the translator terminal are only examples, and the present disclosure is not limited thereto.

Specifically, the processor 130 may determine the top three candidate translator terminals having the highest translation evaluation scores among the translation evaluation scores of each of the one or more candidate translator terminals as one or more request translator terminals. For another example, the processor 130 may determine one or more requesting translator terminals based on whether a translation evaluation score of each of the one or more candidate translator terminals exceeds a predetermined threshold evaluation score. The detailed description of the method for determining the request translator terminal described above is only an example, and the present disclosure is not limited thereto.

That is, the processor 130 may transmit retranslation request information to verified translators by determining one or more request translator terminals based on the translation evaluation score of each candidate translator terminal among one or more candidate translator terminals. In other words, it is possible to form a virtuous cycle system that improves the quality of service by first providing a service opportunity to a translator terminal that has been highly evaluated by the user.

According to another embodiment of the present disclosure, the processor 130 may determine to generate and transmit candidate translator list information including one or more candidate translator terminals to the user terminal. The candidate translator list information may be information listing translator terminals related to each of one or more translators capable of performing a desired translation by a user of the user terminal.

Specifically, the processor 130 may determine to transmit a translation service participation request to one or more candidate translator terminals. In this case, each of the one or more candidate translator terminals may transmit a participation signal in response to a participation request for whether to perform a translation service for an input sentence. As the participation response transmission process exists, the translator terminal may select whether to perform a service related to a request to participate in a translation service. Accordingly, the translator terminal can avoid the allocation of translation services by not responding to the translation service without much experience in performing the translation.

In response to this, the processor 130 may provide an incentive for the number of times that the translation service is performed, thereby increasing a transmission rate of a participation response to a service by a translator terminal. Through the above process, the translator will immediately respond to requests for services that are experienced and confident, so the quality and efficiency of the service can be improved compared to a system that unconditionally allocates translation services to translators. In addition, the processor 130 may receive a participation signal corresponding to a translation service participation request from each of the one or more candidate translator terminals, and may determine to generate and transmit the translation user list information to the user terminal based on the received participation signal. .

Also, the processor 130 may determine a translator terminal to perform a translation service desired by the user based on the user terminal's response to the translation user list information.

According to another embodiment of the present disclosure, when receiving retranslation request information from the user terminal 10, the processor 130 generates translator terminal list information based on the service history information of the user terminal 10, and the It may be determined to transmit the generated translator terminal list information to the user terminal 10. In this case, the service history information may include information on one or more translation terminals that have performed a translation service in relation to the user terminal 10 at a previous time.

According to an additional embodiment, when receiving the retranslation request information from the user terminal 10, the processor 130 identifies candidate translator terminals that have been highly evaluated by users to generate translator terminal list information, and the generated translator terminal It may be determined to transmit the list information to the user terminal 10.

In an additional embodiment, the processor 130 may determine whether to transmit the retranslation request information to one or more requesting translator terminals based on the translation reliability of the translated sentence. The translation reliability of the translated sentence indicates the accuracy of the translation related to the output of the translation model, and may be used as information to allow the user to recognize the accuracy of the translation for the translated sentence during the inspection process.

Specifically, when the translation reliability of the translated sentence is less than a predetermined threshold reliability, the processor 130 may determine to transmit the retranslation request information to one or more requesting translator terminals. In addition, the processor 130 may determine not to transmit the retranslation request information to one or more requesting translator terminals when the translation reliability of the translated sentence is greater than or equal to a predetermined threshold reliability.

That is, the processor 130 determines whether or not the translated sentence has a reliable level of translation based on the translation reliability of the translated sentence, and the input sentence of the user terminal is automatically transmitted to one or more request translator terminals (i.e., requesting translation). You can decide whether to do it or not). In other words, it is possible to automatically link with the requesting translator terminal based on the calculated translation reliability without the user's separate review process for the translated sentence related to the output of the optimal translation model. Accordingly, a separate inspection process for a translated sentence may be omitted, and user convenience may be improved.

According to an embodiment of the present disclosure, the processor 130 may determine to transmit retranslation request information to one or more requested translator terminals. Here, the retranslation request information may include an input sentence, and the input sentence may mean a sentence that the user of the user terminal 10 wants to translate. Specifically, the processor 130 may determine to transmit retranslation request information corresponding to the translation request information received from the user terminal 10 to one or more requested translator terminals determined through the translation evaluation information. Accordingly, at least one request translator terminal may generate a retranslated sentence corresponding to the input sentence. In addition, the retranslated sentences generated through one or more requested translator terminals may be transmitted to the processor 130.

In an additional embodiment, the processor 130 may determine to transmit the translated sentence to one or more requesting translator terminals based on the translation reliability of the translated sentence output through the optimal translation model. Specifically, when the translation reliability of the translated sentence corresponding to the input sentence is equal to or greater than a predetermined threshold reliability, the processor 130 may determine to transmit the translated sentence to one or more request translator terminals. For example, the translation reliability may be information indicating appropriateness of translation for a translated sentence. Accordingly, the processor 130 may determine to transmit the translated sentence to one or more requesting translator terminals when it is determined that the translated sentence has an appropriateness of a predetermined reference value or more through the translation reliability of the translated sentence. In this case, the at least one request translator terminal may be a translator terminal that has received the input sentence in order to generate a translation sentence corresponding to the input sentence. That is, when the translation reliability of the translation sentence related to the output of the translation model is equal to or higher than a predetermined reference value (ie, equal to or higher than a predetermined threshold reliability), the corresponding translated sentence may be transmitted to each of the at least one request translator terminal together with the input sentence.

In this case, the requesting translator terminal may simultaneously receive the input sentence and the translated sentence output by the optimal translation model corresponding to the input sentence. Accordingly, the user (or translator) of the requesting translator terminal can refer to the translated sentence in the process of generating the retranslated sentence corresponding to the input sentence. The corresponding translated sentence is a translated sentence having a translation reliability of a certain standard or higher, and may be a sentence with relatively few corrections or corrections. Therefore, it is possible to improve the efficiency of the translator's translation work by providing a translated sentence that guarantees a certain level of reliability or higher in the process of generating a retranslated sentence for an input sentence.

According to an embodiment of the present disclosure, when one or more retranslated sentences are received from one or more requested translator terminals, the processor 130 may determine to transmit a first retranslated sentence from among the received one or more retranslated sentences to the user terminal. . Specifically, the processor 130 may determine a first retranslated sentence from among one or more retranslated sentences based on a translation evaluation score of each of the at least one request translator terminal. The first retranslated sentence may mean a sentence having the most appropriate expression or structure among retranslated sentences received by the requesting translator terminals. For example, the processor 130 may determine the retranslated sentence received from the request translator terminal having the highest translation evaluation score among one or more retranslated sentences as the first retranslated sentence.

According to another embodiment of the present disclosure, when one or more retranslated sentences are received from one or more request translator terminals, the processor 130 may determine to transmit the received one or more retranslated sentences to the user terminal. Specifically, the processor 130 may determine to generate candidate retranslation list information including one or more retranslation sentences and transmit the information to the user terminal. The candidate retranslation list information may be information listing one or more retranslation sentences received from each of the one or more request translator terminals.

In addition, the processor 130 may receive selection information for at least one retranslated sentence from among one or more retranslated sentences from the user terminal 10. Specifically, the processor 130 may transmit candidate retranslation list information including one or more retranslation sentences to the user terminal 10, and the user terminal 10 may transmit at least one of the one or more retranslation sentences included in the candidate retranslation list information. A user's selection input for one sentence may be received. In this case, the user terminal 10 may generate selection information for a specific retranslated sentence in response to a user's selection input and transmit it to the processor 130. Accordingly, the processor 130 may identify the first retranslated sentence from among one or more retranslated sentences based on the selection information received from the user terminal 10.

That is, the processor 130 may determine a retranslated sentence related to the user's selection from among one or more retranslated sentences from the at least one request translator terminal as the first retranslated sentence. In other words, the processor 130 may present various retranslated sentences generated in response to the input sentence so that the user of the user terminal 10 can determine his or her desired translated sentence according to his or her preference.

According to an embodiment of the present disclosure, the processor 130 may augment the learning data based on the input sentence and the first retranslated sentence. Specifically, the processor 130 may generate additional learning data by matching and labeling the input sentence and the first retranslated sentence. In addition, the processor 130 may update the optimal translation model by performing additional learning on the optimal translation model through the additional learning data. In this case, the optimal translation model is a translation model determined based on subscription request information of the user terminal 10, and may be a translation model that outputs a more appropriate translation sentence in a field related to the input sentence that the user wants to translate. . In addition, the updated optimal translation model is an optimal translation model additionally learned to output the first retranslated sentence generated by a professional translator in response to the input sentence by inputting an input sentence related to the translation request of the user terminal 10 as an input. I can.

That is, the processor 130 augments the learning data through each of the various input sentences received from the plurality of user terminals and the various translation sentences of the translator terminals 20 corresponding thereto, and builds a translation model through the augmented learning data. Can be updated. Accordingly, it is possible to advance the translation model over time by the above-described steps of the processor 130. This can lead to an effect of improving the reliability and accuracy of the translated sentence related to the output of the translation model. In addition, a translation model corresponding to each user terminal is provided, and as each corresponding translation model is continuously updated in relation to each input sentence of the user terminal 10, it can be optimized as a translation model more suitable for each individual user. .

4 shows an exemplary flow chart of a method for providing a professional translation service platform related to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the user terminal 10 may transmit subscription request information to the computing device (301). The subscription request information may include at least one of user language identification information and user domain identification information. The user language identification information may include information on a starting language that the user of the user terminal 10 wants to translate and a destination language corresponding to the translation result.

According to an embodiment of the present disclosure, the computing device 100 may determine an optimal translation model corresponding to the user terminal 10 (303 ). Specifically, when subscription request information is received from the user terminal, the computing device 100 may determine an optimal translation model corresponding to the user terminal 10 from among one or more translation models based on the received subscription request information. The optimal translation model may be a translation model for outputting more suitable translation information in the field related to the user terminal 10. The one or more translation models may refer to each of the translation models that perform professional translation corresponding to each of the one or more domains.

According to an embodiment of the present disclosure, the user terminal 10 may transmit translation request information to the computing device 100 (305 ). In this case, the translation request information may include an input sentence composed of a starting language for which the user wants to perform translation.

According to an embodiment of the present disclosure, the computing device 100 may generate a translation sentence corresponding to the translation request information by using an optimal translation model, and transmit the generated translation sentence to the user terminal 10 (307). . In this case, the optimal translation model is determined based on the user language identification information and the user domain identification information corresponding to the user terminal 10, and a more suitable translation sentence is provided in response to the input sentence received from the user terminal 10. It may be a translation model to generate. Specifically, the computing device 100 may generate a translation sentence corresponding to the input sentence by identifying an input sentence from the received translation request information and processing the identified input sentence as an input of an optimal translation model.

According to an embodiment of the present disclosure, the translator terminal 20 may transmit translation participation information to the computing device 100 (309). The translation participation information may be generated in relation to the time point at which the translator terminals wish to participate in the translation, and may be information for identifying each of the plurality of translator terminals. In addition, the translation participation information may include translator language identification information and translator domain identification information. The translator language identification information may be information for identifying a language that can be utilized by a user of each translator terminal (ie, a language in which translation can be performed). The translator domain identification information may be information related to one or more fields capable of professionally performing translation of each translator terminal.

According to an embodiment of the present disclosure, the computing device 100 may build a translator database (311). When translation participation information is received from each of the plurality of translator terminals, the computing device 100 may build a translator database based on the corresponding translation participation information. The translator database may be referred to by the computing device 100 when the user terminal 10 transmits translation request information corresponding to a specific input sentence to the computing device 100.

According to an embodiment of the present disclosure, the user terminal 10 may transmit retranslation request information to the computing device 100 (313). The retranslation request information is information on a retranslation request for a translated sentence, and may be information generated based on the translation request information. Accordingly, the retranslation request information may include an input sentence and domain identification information corresponding to the translation request information. For example, the user may apply an input to the user terminal 10 so that retranslation request information is generated when it is determined that the meaning or expression of the translated sentence is not appropriate in the process of reviewing the translated sentence output through the optimal translation model. I can.

Specifically, the retranslation request information may include an input sentence to be translated, user language identification information and user domain identification information included in the translation request information. When retranslation request information is received from the user terminal 10, the computing device 100 may determine one or more request translator terminals to request retranslation based on the received retranslation request information. Specifically, the computing device 100 may identify one or more translator terminals corresponding to the retranslation request information by referring to the translator database. For example, the computing device 100 may determine one or more candidate translator terminals corresponding to user language identification information and user domain identification information included in retranslation request information among a plurality of translator terminals included in the translator database.

According to an embodiment of the present disclosure, the translator terminal 20 may transmit one or more retranslated sentences to the computing device 100 (315). When one or more retranslated sentences are received from one or more request translator terminals, the computing device 100 may determine to transmit a first retranslated sentence from among the received one or more retranslated sentences to the user terminal. Specifically, the computing device 100 may determine a first retranslated sentence from among one or more retranslated sentences based on translation evaluation scores of each of the at least one request translator terminal. The first retranslated sentence may mean a sentence having the most appropriate expression or structure among retranslated sentences received by the requesting translator terminals. For example, the computing device 100 may determine the retranslated sentence received from the request translator terminal having the highest translation evaluation score among one or more retranslated sentences as the first retranslated sentence.

According to an embodiment of the present disclosure, the computing device 100 may transmit the first retranslated sentence to the user terminal 10 (317).

According to an embodiment of the present disclosure, the computing device 100 may update the optimal translation model through the input sentence and the first translation sentence (319 ). The computing device 100 may generate additional learning data by matching and labeling the input sentence and the first retranslated sentence. In addition, the computing device 100 may update the optimal translation model by performing additional learning on the optimal translation model through the additional learning data. In this case, the optimal translation model is a translation model determined based on subscription request information of the user terminal 10, and may be a translation model that outputs a more appropriate translation sentence in a field related to the input sentence that the user wants to translate. . In addition, the updated optimal translation model is an optimal translation model additionally learned to output the first retranslated sentence generated by a professional translator in response to the input sentence by inputting an input sentence related to the translation request of the user terminal 10 as an input. I can.

That is, the computing device 100 augments the learning data through each of the various input sentences received from the plurality of user terminals and the various translation sentences of the translator terminals 20 corresponding thereto, and a translation model through the augmented learning data. Can be updated.

5 is a flowchart illustrating steps for performing a method for providing a professional translation service platform related to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the computing device 100 may generate one or more translation models corresponding to one or more domains (410).

According to an embodiment of the present disclosure, when subscription request information is received from a user terminal, the computing device 100 may determine an optimal translation model corresponding to the user terminal from among one or more translation models based on the received subscription request information. There is (420).

According to an embodiment of the present disclosure, when translation request information is received from a user terminal, the computing device 100 may generate a translation sentence corresponding to the received input sentence by using the first translation model (430). .

According to an embodiment of the present disclosure, when retranslation request information related to a translated sentence is received from a user terminal, the computing device 100 may determine one or more request translator terminals to request retranslation based on the received retranslation request information. There is (440).

According to an embodiment of the present disclosure, the computing device 100 may determine to transmit retranslation request information to one or more requested translator terminals (450 ).

According to an embodiment of the present disclosure, when one or more retranslated sentences are received from one or more request translator terminals, the computing device 100 may determine a first retranslated sentence from among the received one or more retranslated sentences as the user terminal (460). ).

The order of the steps illustrated in FIG. 5 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.

6 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 (12)

Generating one or more translation models corresponding to one or more domains;
When subscription request information is received from a user terminal, determining an optimal translation model corresponding to the user terminal from among the one or more translation models based on the received subscription request information;
When translation request information including an input sentence is received from the user terminal, generating a translation sentence corresponding to the received input sentence by using the optimal translation model;
When retranslation request information related to the translated sentence is received from the user terminal, determining at least one request translator terminal to request retranslation based on the received retranslation request information;
Generating a first input sentence by performing reverse translation on the translated sentence, and calculating a translation reliability of the translated sentence based on a comparison between the generated first input sentence and the input sentence;
Determining to transmit the translation reliability to the user terminal;
Determining whether to transmit the retranslation request information to the at least one request translator terminal based on the translation reliability;
Determining to transmit the retranslation request information to the at least one request translator terminal; And
When one or more retranslated sentences are received from the at least one request translator terminal, determining to transmit a first retranslated sentence from among the received one or more retranslated sentences to the user terminal;
Containing,
A method for providing a professional translation services platform, performed on one or more processors of a computing device.
The method of claim 1,
Generating one or more translation models corresponding to the one or more domains,
Obtaining a training data set including a plurality of training data;
Classifying the plurality of training data based on one or more domains to construct one or more subsets of training data; And
Generating the at least one translation model by performing training on each of at least one neural network model through each of the at least one subset of training data;
Containing,
A method for providing a professional translation services platform, performed on one or more processors of a computing device.
The method of claim 2,
Classifying the plurality of training data based on one or more domains to construct one or more subsets of training data,
Identifying domains of each of the plurality of learning data based on at least one of a semantic analysis result of each of the plurality of learning data, a repetition number of words included in the semantic analysis result of each of the plurality of learning data, and a predetermined topic ; And
Constructing the one or more subsets of the learning data based on the domains of each of the plurality of learning data;
Containing,
A method for providing a professional translation services platform, performed on one or more processors of a computing device.
The method of claim 1,
The subscription request information,
It is information that serves as a criterion for determining the optimal translation model corresponding to the user terminal,
The translation request information,
Contains user language identification information and user domain identification information related to the starting language and the destination language,
The above retranslation request information,
Information on a retranslation request for the translated sentence, which is generated based on the translation request information,
A method for providing a professional translation services platform, performed on one or more processors of a computing device.
delete The method of claim 1,
Receiving translation participation information from each of a plurality of translator terminals; And
Establishing a translator database based on translation participation information of each of the plurality of translator terminals;
Including more,
The above translation participation information,
Including translator language identification information and translator domain identification information,
A method for providing a professional translation services platform, performed on one or more processors of a computing device.
The method of claim 6,
Determining one or more request translator terminals to request retranslation based on the received retranslation request information,
Identifying one or more candidate translator terminals corresponding to the retranslation request information by referring to the translator database; And
Determining the at least one requesting translator terminal based on the translation evaluation score of the identified at least one candidate translator terminal;
Including more,
The translation evaluation score is,
The evaluation score for the translation performed by each translator terminal in response to the previous time point,
A method for providing a professional translation services platform, performed on one or more processors of a computing device.
The method of claim 1,
Determining one or more translator terminals to request retranslation based on the received retranslation request information,
Identifying one or more candidate translator terminals corresponding to domain identification information of the user terminal with reference to the translator database;
Determining to transmit a translation service participation request to the at least one candidate translator terminal; And
Determining the at least one request translator terminal based on the participation response of the at least one candidate translator terminal to the request to participate in the translation service;
Including,
A method for providing a professional translation services platform, performed on one or more processors of a computing device.
The method of claim 1,
When one or more retranslated sentences are received from the at least one request translator terminal, determining to transmit a first retranslated sentence from among the received one or more retranslated sentences to the user terminal,
Determining the first retranslated sentence from among the one or more retranslated sentences based on evaluation score information of each of the at least one request translator terminal;
Containing,
A method for providing a professional translation services platform, performed on one or more processors of a computing device.
The method of claim 1,
Determining to transmit the received one or more retranslated sentences to the user terminal;
Receiving selection information for at least one retranslated sentence from among the one or more retranslated sentences from the user terminal; And
Identifying the first retranslated sentence from among the one or more retranslated sentences based on the received selection information;
Further comprising,
A method for providing a professional translation services platform, performed on one or more processors of a computing device.
The method of claim 1,
Generating additional learning data by matching and labeling the input sentence with the first retranslated sentence; And
Updating the optimal translation model by performing additional learning on the optimal translation model through the additional learning data;
Further comprising,
A method for providing a professional translation services platform, performed on one or more processors of a computing device.
As a computing device for providing a professional translation service platform,
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 a user terminal and a translator terminal;
Including,
The processor,
Generate one or more translation models corresponding to one or more domains,
When subscription request information is received from the user terminal, an optimal translation model corresponding to the user terminal is determined from among the one or more translation models based on the received subscription request information,
When translation request information including an input sentence is received from the user terminal, a translation sentence corresponding to the received input sentence is generated using the optimal translation model,
When retranslation request information related to the translated sentence is received from the user terminal, at least one request translator terminal to request retranslation is determined based on the received retranslation request information,
Performing reverse translation on the translated sentence to generate a first input sentence, and calculating the translation reliability of the translated sentence based on a comparison between the generated first input sentence and the input sentence,
Determine to transmit the translation reliability to the user terminal,
Determine whether to transmit the retranslation request information to the at least one request translator terminal based on the translation reliability,
Determine to transmit the retranslation request information to the at least one request translator terminal,
When one or more retranslated sentences are received from the at least one request translator terminal, determining to transmit a first retranslated sentence from among the received one or more retranslated sentences to the user terminal,
A computing device for providing a professional translation service platform.

Images