40results about How to "Reduce translation costs" patented technology

A computer system and method tests various language installations of an application program using a single test script. The various language translations existing with the application program are used to provide translations of test command strings from one language to the specific language of the application program (operating system locale for executing the program). The test script may then be translated at runtime using the predefined program-established translations to allow the testing program to test the application program in accordance with the language of the application program/operating system locale.

The invention discloses a video translation method, a system and a device and a storage medium. The method comprises the following steps: acquiring video data; performing voice segmentation on the video data to obtain a voice segment and a video segment corresponding to the voice segment; performing voice recognition on the voice segment to obtain a first text, and translating the first text to obtain a second text; obtaining synthetic voice according to the second text, and enabling the synthetic voice to be matched with the video clip by adjusting the synthetic voice and the video clip corresponding to the synthetic voice; and detecting and adjusting the lip shape in the video clip so as to enable the lip shape to be synchronously matched with the synthetic voice. According to the method, the function of automatically translating the video is realized, the audio of the target language sound can be generated, the video with the sound matched with the lip shape is generated, the communication obstacle between different languages is solved, manual dubbing is not needed, the translation cost is reduced, and the method can be widely applied to the field of video processing.

The embodiment of the invention discloses a translation method and device based on a neural network. The method comprises the following steps that: obtaining the initial translation of a sentence to be translated, wherein the initial translation carries unlisted words; splitting the unlisted words in the initial translation into characters, and inputting a character sequence formed by the characters obtained by splitting into a first multilayer neural network; through the first multilayer neural network, obtaining the character vector of each character in the character sequence, and inputtingall character vectors of the character sequence into a second multilayer neural network; using the second multilayer neural network and a preset common word database to code all character vectors to obtain a semantic vector; and inputting the semantic vector into a third multilayer neural network, decoding the semantic vector through the third multilayer neural network, and combining with the initial translation of the sentence to be translated to determine the final translation of the sentence to be translated. The method has the advantages that the translation operability of the unlisted words can be improved, the translation cost of machine translation is lowered, and the translation quality of the machine translation is improved.

The embodiment of the invention provides a spoken language text processing method and device, a server and a readable storage medium, and the method comprises the steps: building an intermediate object of a written language text of an initial spoken language text between the initial spoken language text and a target language translation text, and carrying out machine translation based on the written language text during machine translation. Therefore, the translation accuracy and translation efficiency of the initial spoken language text are improved and the translation cost of manual proofreading is reduced by utilizing the characteristic of high accuracy of the machine translation for the written language text. Furthermore, along with the machine translation, the preset written language conversion library can be enriched and updated based on each difference phrase between the initial oral language text and the second written language text, so that the written language conversion quality can be continuously improved, and the translation quality of subsequent machine translation can be continuously improved; and the translation workload of manual correction is further reduced.

The invention relates to a translation system and a translation method. The translation system comprises a translation module and a reviewing module, wherein the translation module is used for acquiring the translation contents of vocabulary entries (to be translated in a file) submitted by a client; and the reviewing module is used for carrying out reviewing according to the translation contents submitted by the client, and updating the translation contents subjected to approval in the file. In the invention, a system which can participate in the improvement on the translation quality of game files is provided for a client, and game scores (virtual currency in games) are rewarded to a game user according to the quality of translation contents of game files submitted by the game user client without directly paying fees, therefore, the translation cost of a game developer is saved; meanwhile, the system can timely update the approved translation contents submitted by the game user client to a game, so that an effect of updating while translating is achieved, and the translation procedure of a network game subjected to releasing and operation in the process of updating is simplified.

The invention discloses a method for combining a translation memory bank and MT in a CAT system. The method comprises the following steps: sending an original translation text to the translation memory bank when a user performs the original translation text in the CAT; matching the original translation text with the translation memory bank; if the original translation text successfully matches thetranslation memory bank, sending a translation version in the translation memory bank corresponding to the original translation text to the user; and if the original translation text does not successfully match the translation memory bank, translating the original translation text by a machine and sending the translation version translated by the machine to the user. The invention discloses a system adopting the method. When the method and system for combining the translation memory bank and MT in the CAT system are applied to the professional field, the translation version translated by themachine can be used as a reference. Additionally, a large number of translation samples are generated. Therefore, the translation memory bank is expanded in the professional field, thereby avoiding adefect of overly depending on human translation in the professional field. The translation efficiency is raised and translation cost is reduced.

The invention provides a machine translation method based on a translation memory bank. The method comprises the following steps: searching a corpus original text with the highest similarity with a to-be-translated original text and a translation of the corpus original text from the translation memory bank; comparing the to-be-translated original text with the corpus original text to obtain a difference part different from the to-be-translated original text in the corpus original text; mapping the difference part to a translated text of the corpus original text, and replacing the translated text mapped by the difference part in the translated text of the corpus original text with a mask; taking the replaced translated text of the corpus original text and the to-be-translated original text as the input of a machine translation model, and outputting the translated text of the to-be-translated original text; wherein the machine translation model is obtained by taking a translation original text sample as a sample and taking a translation corresponding to the translation original text sample as a label for training. According to the method, the translation of the to-be-translated original text and the translation of the corpus original text are combined for translation, so that the translation efficiency can be improved, the translation cost can be reduced, and the translation accuracy can be improved.

The invention discloses a write-back system of drawing interpretation data in a DWG format. The write-back system comprises a device used for obtaining files of DXF formats converted by files of DWG formats; a device used for obtaining text data to be translated and position information of text data to be translated, wherein the text data to be translated and position information of text data to be translated are obtained by extraction of files of DXF formats, a device used for obtaining translation data corresponding to text data to be translated, a device used for writing position information on translation data corresponding to text data to be translated into files of DXF formats, a device used for converting files of DXF files written with translation data to files of DWG formats with translation data, and a device used for guiding files of DWG formats with translation data.

The invention discloses a method for newly adding a translation in a DWG format file. The method comprises the following steps that a DXF format file converted by the DWG format file is obtained; the DXF format file is analyzed, and a textbox position coordinate group code value and a textbox height group code value of to-be-translated text data in the DXF format file are acquired, wherein the textbox position coordinate group code value of the to-be-translated text data is (X,Y), and the textbox height group code value of the to-be-translated text data is H; a textbox coordinate group code value of translation data is calculated to be (X,Y-H) or (X,Y+H); a set of group codes and the group code value of the translation are written into the DXF format file.

The invention provides an identifying data processing method, comprising the step of: S102, a first client identifies the data in a document where the problems lie in and sends the identified data to a second client; S104, the second client processes the identified data to generate identifying reply data and sends the identifying reply data to the first client; and S106, after the first client receives the identifying reply data, applying the identifying reply data automatically to the document. The invention realizes a real time information exchange in process of information conversion process (for example translation), solves the communication problem between the specialist and the translator in the service related to the information conversion process (for example translation), improves translation quality, reduces translation cost and translation difficulty of the translator, reduces checking cost as well as accelerates project period.

The invention provides an intelligent obtaining method of international resources, a storage medium. The method comprises the following steps: a preset term template comprises a Chinese name, a current language identification and a translation set; according to the preset entry template, the dictionary entries are extracted from the translated resource database; entries of items to be translated are extracted to obtain entries to be translated; the dictionary entries to be translated are used for filling; if the filled entries are incomplete, the filled entries are submitted to the translationend; and if the filled entries are incomplete, the filled entries are submitted to the translation end. A complete entry to be translated is received and stored as a dictionary entry. The invention can not only continuously improve the speed of responding to the translation requirement; but also ensure the correctness of translation; Furthermore, the cost of translation is saved.

The embodiment of the invention provides a machine translation method and device, electronic equipment and a readable storage medium, and relates to the technical field of computers. The method comprises the following steps: receiving a voice recognition text; translating the voice recognition text, and determining a translation text of at least one language of the voice recognition text; writingthe translation text into a message device channel of a corresponding language according to the language of the translation text; receiving a target subscription message sent by a target terminal, wherein the target subscription message comprises target language information; determining a target message device channel corresponding to the target subscription message, wherein a translation text inthe target message device channel is a translation text of a language corresponding to the target language information; and accessing the target terminal to the target message device channel, and enabling the target terminal to acquire the translation text in the target message device channel. Therefore, the translation cost can be reduced, and the translation pressure of the server is reduced.

The invention discloses a language translation processing method and device. The method comprises the steps that an original text to be translated is preprocessed; a target sentence pattern and a target keyword are obtained, wherein at least one reserved position used for containing the target keyword exists in the target sentence pattern, and the target keyword and the target sentence pattern form the original text to be translated; translation results corresponding to the target sentence pattern and the target keyword are determined in sequence; and a translation result of the to-be-translated original text is determined based on the determined translation results. According to the invention, various problems (such as translation ambiguity problem and translation cost problem) existing in translation management during multi-country multi-language issuing of a game in related technologies are solved.

The invention discloses a barrier-free conference system supporting sign language online translation. The barrier-free conference system comprises conference control equipment, a sign language customer service terminal and a handheld terminal respectively connected with the control equipment, voice acquisition equipment used for acquiring voice, image acquisition equipment used to acquire sign language, and voice playing equipment used for voice playing. The conference control equipment is in control connection with the sign language customer service terminal, transmits sign language translation images translated from the sign language customer service terminal to the hand-held terminals for display, and controls the translation voice translated from the sign language customer service terminal to the sign language to be played through the voice playing equipment. The barrier-free conference device has the advantages of simple structure, low cost, convenience in barrier-free participation of deaf-mute people in a conference, flexibility in application and the like.