CN107885734B - Language translation method and device - Google Patents
Language translation method and device Download PDFInfo
- Publication number
- CN107885734B CN107885734B CN201711117660.8A CN201711117660A CN107885734B CN 107885734 B CN107885734 B CN 107885734B CN 201711117660 A CN201711117660 A CN 201711117660A CN 107885734 B CN107885734 B CN 107885734B
- Authority
- CN
- China
- Prior art keywords
- information
- translation
- processing
- historical
- information obtained
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/42—Data-driven translation
Abstract
The invention discloses a language translation method, a language translation device and a language translation device, wherein the method comprises the following steps: translating the original information to obtain initial translated information; when a re-translation instruction is received, re-translating the original information by combining with the historical conversation record to obtain re-translated information; and adding the current dialogue information into the historical dialogue record. According to the language translation method provided by the embodiment of the invention, the historical dialogue record is recorded in the translation process, when the single translation is not accurate enough, the original information of the current time is translated again by combining the historical dialogue record, and because the historical dialogue information in the historical dialogue record and the original information of the current time can form a complete dialogue paragraph, the original information of the current time can be more accurately understood by analyzing the whole dialogue paragraph, the translation result obtained on the basis is more accurate, so that the translation accuracy is greatly improved, and the user experience is improved.
Description
Technical Field
The present invention relates to the field of electronic technologies, and in particular, to a method and an apparatus for language translation.
Background
With the rapid development of economy, the communication to the outside is more and more extensive, and for many people, the language is not always a big obstacle to the communication to the outside. To solve the above problems, various translation machines have appeared on the market. The translator is deeply popular with people who have language translation requirements by virtue of small and exquisite portable appearance and strong language translation function, and is also a good helper for people to learn foreign languages. The translator can translate in the process of conversation between two parties, so that users using different languages can communicate without barriers.
When the existing translation machine carries out translation, a single-segment translation mode is mainly adopted, namely, in the process of alternative conversation of a user, the user immediately translates a segment of speech after finishing speaking the segment of speech. Although the translation mode has high efficiency, each segment is isolated during translation, and a complete conversation segment is not combined, so that the translation accuracy is not high, a user feels confused about some translation results, the accurate meaning of the opposite user cannot be understood, misunderstanding of the two users is easily caused, and the user experience is influenced.
Disclosure of Invention
The invention mainly aims to provide a language translation method and a language translation device, aiming at improving the accuracy of translation and improving the user experience.
To achieve the above object, an embodiment of the present invention provides a language translation method, including the following steps:
translating the original information to obtain initial translated information;
when a re-translation instruction is received, re-translating the original information by combining with the historical conversation record to obtain re-translated information;
and adding the current dialogue information into the historical dialogue record.
Optionally, the step of re-translating the original information in combination with a pre-stored historical conversation record, and acquiring re-translated information includes:
s101, sequentially tracing back the historical dialogue information in the historical dialogue record according to the sequence from the late to the early;
s102, the original information is translated again by combining the historical dialogue information;
s103, judging whether the information obtained after the re-translation processing is consistent with the information of the initial translation or not; when the two are consistent, returning to the step S101; when the two are inconsistent, executing the next step;
and S104, acquiring the information obtained after the retranslation processing as retranslation information.
Optionally, the step of re-translating the original information in combination with a pre-stored historical conversation record, and acquiring re-translated information includes:
s201, sequentially tracing back the historical dialogue information in the historical dialogue record from the late to the early according to the time sequence;
s202, combining the historical dialogue information to translate the original information again;
s203, judging whether the information obtained after the re-translation processing is consistent with the information obtained after any previous re-translation processing; when not consistent, returning to step S201; when the two are consistent, executing the next step;
and S204, acquiring the information obtained after the re-translation processing as re-translation information.
Optionally, the step of re-translating the original information in combination with a pre-stored historical conversation record, and acquiring re-translated information includes:
s301, sequentially tracing back the historical dialogue information in the historical dialogue record according to the sequence from the late to the early;
s302, the original information is translated again by combining the historical dialogue information;
s303, judging whether the information obtained after the retranslation processing is consistent with the information of the initial translation or not; when the two are consistent, returning to the step S301; when the two are inconsistent, executing the next step;
s304, judging whether the information obtained after the re-translation processing is consistent with the information obtained after any previous re-translation processing; if not, returning to the step S301; when the two are consistent, executing the next step;
s305, obtaining the information obtained after the retranslation processing as retranslation information.
Optionally, one or at least two pieces of historical dialog information are traced back each time.
Optionally, the step of adding the current session information to the historical session record includes: and adding the original information of this time into the historical dialogue record.
Optionally, the historical dialog record includes historical dialog records of two languages, and the step of adding the current dialog information to the historical dialog record includes: and respectively adding the original information and the translated information of the current time into the historical dialogue records of the corresponding language.
The embodiment of the invention also provides a language translation device, which comprises:
the first translation module is used for translating the original information to acquire initial translated information;
the second translation module is used for carrying out translation processing on the original information again by combining with the historical conversation record when a re-translation instruction is received, and obtaining re-translated information;
and the dialogue recording module is used for adding the dialogue information of this time into the historical dialogue record.
Optionally, the second translation module comprises:
the backtracking unit is used for backtracking the historical dialogue information in the historical dialogue record from late to early in sequence according to time;
the translation unit is used for carrying out translation processing on the original information again by combining the historical dialogue information;
the first judgment unit is used for judging whether the information obtained after the retranslation processing is consistent with the information of the initial translation;
the first obtaining unit is used for obtaining the information obtained after the retranslation processing as retranslation information when the information obtained after the retranslation processing is inconsistent with the information of the initial translation;
and the first notification unit is used for notifying the backtracking unit to backtrack the historical dialogue information in the historical dialogue record again when the information obtained after the retranslation processing is consistent with the information of the initial translation.
Optionally, the second translation module comprises:
the backtracking unit is used for backtracking the historical dialogue information in the historical dialogue record from late to early in sequence according to time;
the translation unit is used for carrying out translation processing on the original information again by combining the historical dialogue information;
the second judgment unit is used for judging whether the information obtained after the re-translation processing is consistent with the information obtained after any one time of re-translation processing;
the second acquisition unit is used for acquiring the information obtained after the retranslation processing as retranslation information when the information obtained after the retranslation processing is consistent with the information obtained after the retranslation processing of any time;
and the second notification unit is used for notifying the backtracking unit to backtrack the historical dialogue information in the historical dialogue record again when the information obtained after the current re-translation processing is inconsistent with the information obtained after any previous re-translation processing.
Optionally, the second translation module comprises:
the backtracking unit is used for backtracking the historical dialogue information in the historical dialogue record from late to early in sequence according to time;
the translation unit is used for carrying out translation processing on the original information again by combining the historical dialogue information;
the first judgment unit is used for judging whether the information obtained after the retranslation processing is consistent with the information of the initial translation;
a second judging unit, configured to, when the information obtained after the re-translation processing is inconsistent with the initially translated information, judge whether the information obtained after the re-translation processing is consistent with the information obtained after any one previous re-translation processing;
a third obtaining unit, configured to obtain, when information obtained after the current re-translation processing is consistent with information obtained after any previous re-translation processing, information obtained after the current re-translation processing as re-translation information;
and the third informing unit is used for informing the backtracking unit to backtrack the historical dialogue information in the historical dialogue record again when the information obtained after the retranslation processing is consistent with the information of the initial translation or the information obtained after the retranslation processing is inconsistent with the information obtained after the retranslation processing for any time.
Optionally, the backtracking unit is configured to: each time one or at least two segments of historical session information are traced back.
Optionally, the dialog recording module is configured to: and adding the original information of this time into the historical dialogue record.
Optionally, the historical conversation record comprises historical conversation records in two languages, and the conversation recording module is configured to: and respectively adding the original information and the translated information of the current time into the historical dialogue records of the corresponding language.
An embodiment of the present invention further provides a translation apparatus, which includes a memory, a processor, and at least one application program stored in the memory and configured to be executed by the processor, where the application program is configured to execute the foregoing language translation method.
According to the language translation method provided by the embodiment of the invention, the historical dialogue record is recorded in the translation process, when the single translation is not accurate enough, the original information of the current time is translated again by combining the historical dialogue record, and because the historical dialogue information in the historical dialogue record and the original information of the current time can form a complete dialogue paragraph, the original information of the current time can be more accurately understood by analyzing the whole dialogue paragraph, the translation result obtained on the basis is more accurate, so that the translation accuracy is greatly improved, and the user experience is improved.
Drawings
FIG. 1 is a flow diagram of one embodiment of a language translation method of the present invention;
FIG. 2 is a schematic illustration of a historical conversation record in an embodiment of the present invention;
FIG. 3 is yet another illustration of a historical conversation record in an embodiment of the invention;
fig. 4 is a detailed flowchart of step S12 in fig. 1;
FIG. 5 is a further detailed flowchart of step S12 in FIG. 1;
FIG. 6 is a more detailed flowchart of step S12 in FIG. 1;
FIG. 7 is a block diagram of an embodiment of a language translation device of the present invention;
FIG. 8 is a block diagram of the second translation module of FIG. 7;
FIG. 9 is a further module diagram of the second translation module of FIG. 7;
FIG. 10 is a further module diagram of the second translation module of FIG. 7.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative only and should not be construed as limiting the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As will be appreciated by those skilled in the art, "terminal" as used herein includes both devices that are wireless signal receivers, devices that have only wireless signal receivers without transmit capability, and devices that include receive and transmit hardware, devices that have receive and transmit hardware capable of performing two-way communication over a two-way communication link. Such a device may include: a cellular or other communication device having a single line display or a multi-line display or a cellular or other communication device without a multi-line display; PCS (Personal Communications Service), which may combine voice, data processing, facsimile and/or data communication capabilities; a PDA (Personal Digital Assistant), which may include a radio frequency receiver, a pager, internet/intranet access, a web browser, a notepad, a calendar and/or a GPS (Global Positioning System) receiver; a conventional laptop and/or palmtop computer or other device having and/or including a radio frequency receiver. As used herein, a "terminal" or "terminal device" may be portable, transportable, installed in a vehicle (aeronautical, maritime, and/or land-based), or situated and/or configured to operate locally and/or in a distributed fashion at any other location(s) on earth and/or in space. As used herein, a "terminal Device" may also be a communication terminal, a web terminal, a music/video playing terminal, such as a PDA, an MID (Mobile Internet Device) and/or a Mobile phone with music/video playing function, or a smart tv, a set-top box, etc.
As used herein, a server, as will be understood by those skilled in the art, includes, but is not limited to, a computer, a network host, a single network server, a collection of network servers, or a cloud of servers. Here, the Cloud is composed of a large number of computers or network servers based on Cloud Computing (Cloud Computing), which is a kind of distributed Computing, a super virtual computer composed of a group of loosely coupled computer sets. In the embodiment of the present invention, the server, the terminal device and the WNS server may communicate with each other through any communication method, including but not limited to mobile communication based on 3GPP, LTE and WIMAX, computer network communication based on TCP/IP and UDP protocols, and short-range wireless transmission based on bluetooth and infrared transmission standards.
The language translation method and the language translation device are mainly applied to translation equipment, and the translation equipment can be a special translation machine and can also be terminal equipment such as a mobile phone, a tablet and the like.
Referring to fig. 1, an embodiment of the language translation method of the present invention is provided, which includes the following steps:
and S11, translating the original information to acquire initial translated information.
The translation equipment receives original information input by a user, translates the original information and acquires initial translation information. The translation device may translate the original information locally, translating the original information from one language to another, resulting in the initially translated information. The translation device may also translate the original information through the server, i.e.: the translation device sends the original information to the server, the server translates the original information from one language to another language and returns the translated information to the translation device, and the translation device receives the information initially translated by the server.
The original information is voice information input by a user, and in other embodiments, the original information may also be text information or information in other forms, which is not limited in the present invention.
And S12, when receiving the retranslation command, retranslating the original information by combining the historical conversation records to acquire retranslated information.
After the translation equipment acquires the information of the initial translation, the translation equipment can directly output the information, and can also send the information to a Bluetooth headset of another user, and the Bluetooth headset outputs the information. If the user is not satisfied with the information translated at this time (if the translation is not accurate enough and is difficult to understand), a re-translation instruction can be issued to the translation device, for example, the re-translation instruction is issued by triggering a specific key of the translation device, and after the translation device receives the re-translation instruction, the translation device performs translation processing on the original information again by combining with the historical conversation records between the two users to acquire the re-translated information.
The historical conversation record is the complete conversation information recorded and stored by the translation equipment during the translation process when two users talk in turn. The translation device may order each session in the historical session record in time order from morning to evening or by the number of times the information is recorded and may order each session. A session in the history of conversations is the information of one conversation of a user.
In some embodiments, the historical dialog records store the original information input by the user, and the original information includes two languages corresponding to the two users. As shown in fig. 2, there are N sessions in the history session record, including the complete session information of the a user and the B user, where: the dialogue information of the user A is the original information input by the user A and is in the language A; the dialogue information of the B user is the original information input by the B user and is in the B language.
In other embodiments, the historical conversation record comprises two languages of historical conversation records, each language of historical conversation records containing complete conversation information for two users. As shown in fig. 3, the dialog records are history dialog records of language a and history dialog records of language B, each of the dialog records of language has N sections of dialogs, and includes complete dialog information of user a and user B, where; the history dialogue record of the language A comprises original information input by the user A and information obtained by translating the original information input by the user B into the language A; the history dialogue record of the B language comprises original information input by the B user and information obtained by translating the original information input by the A user into the B language.
Alternatively, a specific process of the translation device re-translating the original information in combination with the pre-stored historical conversation record may be as shown in fig. 4, and includes the following steps:
and S101, sequentially tracing back the historical dialogue information in the historical dialogue record according to the sequence from the late to the early.
And S102, carrying out translation processing on the original information again by combining the historical dialogue information.
S103, judging whether the information obtained after the re-translation processing is consistent with the information of the initial translation. When the two are consistent, returning to the step S101; when not, the next step S104 is executed.
And S104, acquiring the information obtained after the retranslation processing as retranslation information.
In the embodiment of the present invention, the translation device traces back one segment of historical dialog information each time, and certainly, in other embodiments, at least two segments of historical dialog information may also be traced back each time.
For example: during the first backtracking, the translation equipment selects the last session (namely the last stored session information) in the historical session record as the historical session information, combines the last session with the current original information (namely the information to be translated) into a session, understands or analyzes the meaning expressed by the whole session, and then carries out translation processing on the original information again according to the meaning expressed by the whole session; when the translated information is consistent with the initially translated information, backtracking again, selecting the last two sessions in the historical session record as historical session information, and translating the original information again … …; and analogizing until the information obtained after the retranslation processing is inconsistent with the information of the initial translation, and acquiring the information obtained after the retranslation processing at this time as retranslated information. When the retranslated information is inconsistent with the information of the initial translation, the error of the initial translation may be corrected when the retranslation is performed, so that the translation may be more accurate, and the user can be satisfied.
When the historical dialogue information is backtracked, if the historical dialogue records of two languages exist, the historical dialogue record which has the same language as the current original information is selected so as to more accurately understand the meaning of the dialogue paragraph, for example, if the original information received by the translation equipment at this time is the language a, the historical dialogue record of the language a is selected, and the historical dialogue information is backtracked in the historical dialogue record of the language a. If there is only one history dialogue record, the dialogue record has dialogue information in two languages, in order to facilitate better understanding of the meaning of the dialogue paragraphs, the translation device may translate the dialogue information in the history dialogue information in the language different from the language of the original information into dialogue information in the same language as the language of the original information, and of course, the translation device may not perform translation processing, which is not limited in the present invention.
Optionally, a specific process of the translation device re-translating the original information in combination with the pre-stored historical conversation record may also be as shown in fig. 5, and includes the following steps:
s201, the historical dialogue information in the historical dialogue record is traced back forward in sequence according to the time sequence from the late to the early.
And S202, carrying out translation processing on the original information again by combining the historical dialogue information.
S203, judging whether the information obtained after the re-translation processing is consistent with the information obtained after any previous re-translation processing. When not consistent, returning to step S201; when consistent, the next step S204 is performed.
And S204, acquiring the information obtained after the re-translation processing as re-translation information.
The difference between the scheme and the previous scheme is that the translation equipment compares the information obtained after each re-translation process with all the information obtained after the previous re-translation process, and when the information is consistent with the information obtained after any previous re-translation process, backtracking and re-translation are stopped, and the information obtained after the current re-translation process is obtained as re-translated information. Because when the translation is carried out again by combining different historical dialogue information twice to obtain a consistent translation result, the translation results of the two times should be more accurate, so that the user can be satisfied.
Optionally, a specific flow of the translation device performing the translation processing on the original information again in combination with the pre-stored historical conversation record may also be as shown in fig. 6, and includes the following steps:
s301, the historical dialogue information in the historical dialogue record is traced back forward in sequence according to the time sequence from the late to the early.
And S302, carrying out translation processing on the original information again by combining the historical conversation information.
S303, judging whether the information obtained after the retranslation processing is consistent with the information of the initial translation. When the two are consistent, returning to the step S301; when not, the next step S304 is performed.
S304, judging whether the information obtained after the re-translation processing is consistent with the information obtained after any previous re-translation processing. If not, returning to the step S301; when consistent, the next step S305 is performed.
S305, obtaining the information obtained after the retranslation processing as retranslation information.
According to the scheme, the two schemes are combined, the translation equipment compares the information obtained after each re-translation processing with the information of the initial translation and all the information obtained after the previous re-translation processing, when the information is inconsistent with the information of the initial translation and is consistent with the information obtained after any previous re-translation processing, backtracking and re-translation are stopped, and the information obtained after the re-translation processing is obtained and used as the information of re-translation. Therefore, the accuracy of the translation result is improved to the maximum limit.
After obtaining the retranslated information, the translation device may directly output the information, or may send the information to a bluetooth headset of another user, and the bluetooth headset outputs the information.
And S13, adding the current dialogue information into the historical dialogue record.
When the translation is completed, the translation device adds the current dialogue information to the historical dialogue record, for example, automatically adds the current dialogue information to the end of the historical dialogue record and marks the conversation record.
When only one historical dialogue record exists, the translation device adds the original information of the time (namely the dialogue information input by the user of the time) into the historical dialogue record.
When the historical dialogue records comprise the historical dialogue records of two languages, the translation device respectively adds the original information (namely the dialogue information input by the user at this time) and the translated information (namely the dialogue information output to the user at this time) of this time to the historical dialogue records of the corresponding language. For example, if the language of the current original information is B language, the original information is added to the history dialogue log of B language, and the translated information is added to the history dialogue log of a language, where the translated information is information to be translated again if re-translated, and is information to be initially translated if not re-translated.
For example, assume that the original information of this time is English and needs to be translated into Chinese. The original information has a word of "claims" which is translated into "claim" when translated for the first time, and when the original information is translated again, the translation device can translate the "claims" correction into "claim" when the historical dialogue information is found to have "patent" (patent).
According to the language translation method provided by the embodiment of the invention, the historical dialogue record is recorded in the translation process, when the single-paragraph translation is not accurate enough, the original information of the current time is translated again by combining the historical dialogue record, and because the historical dialogue information in the historical dialogue record and the original information of the current time can form a complete dialogue paragraph, the original information of the current time can be more accurately understood by analyzing the whole dialogue paragraph, and the translation result obtained on the basis is more accurate, so that the translation accuracy is greatly improved, and the user experience is improved.
Referring to fig. 7, an embodiment of the language translation apparatus of the present invention is provided, the apparatus includes a first translation module 10, a second translation module 20 and a conversation recording module 30, wherein: the first translation module 10 is configured to perform translation processing on original information to obtain information of initial translation; the second translation module 20 is configured to, when a retranslation instruction is received, perform retranslation processing on the original information in combination with the historical conversation record to obtain retranslated information; and the dialogue recording module 30 is used for adding the dialogue information of this time into the historical dialogue record.
The first translation module 10 receives original information input by a user, and performs translation processing on the original information to obtain initial translated information. The first translation module 10 may translate the original information locally, translating the original information from one language to another, resulting in the initially translated information. The first translation module 10 may also translate the original information through a server, namely: the first translation module 10 sends the original information to the server, the server translates the original information from one language to another language and returns the translated information to the first translation module 10, and the first translation module 10 receives the information initially translated by the server.
The original information is voice information input by a user, and in other embodiments, the original information may also be text information, which is not limited in the present invention.
After receiving the re-translation instruction, the second translation module 20 performs re-translation processing on the original information by combining with the historical conversation record between the two users, and obtains re-translated information. The historical conversation record is the complete conversation information recorded and stored by the translation equipment during the translation process when two users talk in turn. The translation device may order each session in the historical session record in time order from morning to evening or by the number of times the information is recorded and may order each session. A session in the history of conversations is the information of one conversation of a user.
In some embodiments, the historical dialog records store the original information input by the user, and the original information includes two languages corresponding to the two users. As shown in fig. 2, there are N sessions in the history session record, including the complete session information of the a user and the B user, where: the dialogue information of the user A is the original information input by the user A and is in the language A; the dialogue information of the B user is the original information input by the B user and is in the B language.
In other embodiments, the historical conversation record comprises two languages of historical conversation records, each language of historical conversation records containing complete conversation information for two users. As shown in fig. 3, the dialog history record includes a history dialog record of language a and a history dialog record of language B, each of which includes N pieces of dialog, including complete dialog information of user a and user B; the history dialogue record of the language A comprises original information input by the user A and information obtained by translating the original information input by the user B into the language A; the history dialogue record of the B language comprises original information input by the B user and information obtained by translating the original information input by the A user into the B language.
Optionally, the second translation module 20 may include, as shown in fig. 8, a backtracking unit 21, a translation unit 22, a first determining unit 23, a first obtaining unit 24, and a first notifying unit 25, where: a backtracking unit 21, configured to backtrack the historical dialog information in the historical dialog record sequentially according to a time sequence from late to early; a translation unit 22 for performing a translation process on the original information again in combination with the history dialogue information; a first judgment unit 23, configured to judge whether information obtained after the re-translation processing is consistent with information of the initial translation; a first obtaining unit 24, configured to obtain, when the information obtained after the retranslation processing is inconsistent with the information of the initial translation, information obtained after the retranslation processing of this time as retranslated information; a first notifying unit 25, configured to notify the backtracking unit 21 to backtrack the historical dialog information in the historical dialog record again when the information obtained after the retranslation process is consistent with the initially translated information.
In the embodiment of the present invention, the backtracking unit 21 backtracks one segment of historical dialog information each time, and certainly, in other embodiments, at least two segments of historical dialog information may be backtracked each time.
For example: during the first backtracking, the backtracking unit 21 selects the last session (i.e., the last stored session information) in the historical session record as the historical session information, and the translation unit 22 combines the last session and the current original information (i.e., the information to be translated) into a session, understands the meaning expressed by the whole session, and then re-translates the original information according to the meaning expressed by the whole session; when the translated information is consistent with the initially translated information, the first notifying unit 25 notifies the backtracking unit 21 to backtrack again, selects the last two sessions in the history session record as history session information, and the translating unit 22 performs the translation processing … … on the original information again; and so on until the information obtained after the retranslation processing is inconsistent with the information of the initial translation, at this time, the first obtaining unit 24 obtains the information obtained after the retranslation processing this time as the retranslated information. When the retranslated information is inconsistent with the information of the initial translation, the error of the initial translation may be corrected when the retranslation is performed, so that the translation may be more accurate, and the user can be satisfied.
When the historical dialogue information is traced back, if there are historical dialogue records of two languages, the tracing back unit 21 selects the historical dialogue record having the same language as the current original information, so as to more accurately understand the meaning of the dialogue paragraph, for example, the original information received by the translation device at this time is the language a, the tracing back unit 21 selects the historical dialogue record of the language a, and the historical dialogue information is traced back in the historical dialogue record of the language a. If there is only one history dialog record, which has dialog information in two languages, in order to better understand the meaning of the dialog paragraphs, the translation unit 22 may translate the dialog information in the history dialog information in the language different from the language of the original information into the dialog information in the same language as the language of the original information, and of course, the translation device may not perform the translation process, which is not limited in the present invention.
Optionally, the second translation module 20 may also include, as shown in fig. 9, a backtracking unit 21, a translation unit 22, a second determination unit 26, a second obtaining unit 27, and a second notification unit 28, where: a backtracking unit 21, configured to backtrack the historical dialog information in the historical dialog record sequentially according to a time sequence from late to early; a translation unit 22 for performing a translation process on the original information again in combination with the history dialogue information; a second judging unit 26, configured to judge whether information obtained after the current re-translation processing is consistent with information obtained after any previous re-translation processing; a second obtaining unit 27 configured to obtain, as retranslation information, information obtained after the present retranslation process when the information obtained after the present retranslation process coincides with information obtained after any one of the previous retranslation processes; a second notifying unit 28, configured to notify the backtracking unit 21 to backtrack the historical dialog information in the historical dialog record again when the information obtained after the current re-translation processing is inconsistent with the information obtained after any previous re-translation processing.
The present scheme differs from the previous scheme in that the second determining unit 26 compares the information obtained after each re-translation process with all the information obtained after the previous re-translation process, and when the information is consistent with the information obtained after any previous re-translation process, the backtracking unit 21 and the translating unit 22 stop backtracking and re-translating, and the second obtaining unit 27 obtains the information obtained after the current re-translation process as the re-translated information. Because when the translation is carried out again by combining different historical dialogue information twice to obtain a consistent translation result, the translation results of the two times should be more accurate, so that the user can be satisfied.
Optionally, the second translation module 20 may further include, as shown in fig. 10, a backtracking unit 21, a translation unit 22, a first determining unit 23, a second determining unit 26, a third obtaining unit 29, and a third notifying unit 30, where: a backtracking unit 21, configured to backtrack the historical dialog information in the historical dialog record sequentially according to a time sequence from late to early; a translation unit 22 for performing a translation process on the original information again in combination with the history dialogue information; a first judgment unit 23, configured to judge whether information obtained after the re-translation processing is consistent with information of the initial translation; a second judging unit 26, configured to, when the information obtained after the retranslation processing is inconsistent with the initially translated information, judge whether the information obtained after the retranslation processing is consistent with the information obtained after any one previous retranslation processing; a third obtaining unit 29, configured to obtain, as retranslation information, information obtained after the present retranslation process when the information obtained after the present retranslation process is identical to information obtained after any one previous retranslation process; and the third notifying unit 30 is configured to notify the backtracking unit 21 to backtrack the historical dialog information in the historical dialog record again before when the information obtained after the re-translation processing is consistent with the information of the initial translation or the information obtained after the current re-translation processing is inconsistent with the information obtained after any previous re-translation processing.
In the present scheme, the two schemes are combined, the first determining unit 23 and the second determining unit 26 respectively compare the information obtained after each re-translation processing with the initially translated information and all the information obtained after the previous re-translation processing, when the information is inconsistent with the initially translated information and consistent with the information obtained after any previous re-translation processing, the backtracking unit 21 and the translating unit 22 stop backtracking and re-translating, and the third obtaining unit 29 obtains the information obtained after the current re-translation processing as the re-translated information. Therefore, the accuracy of the translation result is improved to the maximum limit.
When the translation is completed, the dialog recording module 30 adds the dialog information of this time to the history dialog record, for example, automatically adds the dialog information to the end of the history dialog record and marks the dialog information.
When there is only one historical dialog record, the dialog logging module 30 adds the current original information (i.e. the current dialog information input by the user) to the historical dialog record.
When the historical dialog records include historical dialog records of two languages, the dialog recording module 30 adds the current original information (i.e. the current dialog information input by the user) and the current translated information (i.e. the current dialog information output to the user) to the historical dialog records of the corresponding language respectively. For example, the language of the original information of this time is B language, the dialogue recording module 30 adds the original information to the historical dialogue record of B language, and adds the translated information to the historical dialogue record of a language. The translated information described here is information to be translated again if retranslation is performed, and information to be translated initially if retranslation is not performed.
According to the language translation device provided by the embodiment of the invention, the historical dialogue records are recorded in the translation process, when the single-paragraph translation is not accurate enough, the original information of the current time is translated again by combining the historical dialogue records, because the historical dialogue information in the historical dialogue records and the original information of the current time can form a complete dialogue paragraph, the original information of the current time can be more accurately understood by analyzing the whole dialogue paragraph, and the translation result obtained on the basis is more accurate, so that the translation accuracy is greatly improved, and the user experience is improved.
The invention also proposes a translation device comprising a memory, a processor and at least one application stored in the memory and configured to be executed by the processor, the application being configured for performing the language translation method. The language translation method comprises the following steps: translating the original information to obtain initial translated information; when a re-translation instruction is received, re-translating the original information by combining with the historical conversation record to obtain re-translated information; and adding the current dialogue information into the historical dialogue record. The language translation method described in this embodiment is the language translation method according to the above embodiment of the present invention, and is not described herein again.
Those skilled in the art will appreciate that the present invention includes apparatus directed to performing one or more of the operations described in the present application. These devices may be specially designed and manufactured for the required purposes, or they may comprise known devices in general-purpose computers. These devices have stored therein computer programs that are selectively activated or reconfigured. Such a computer program may be stored in a device (e.g., computer) readable medium, including, but not limited to, any type of disk including floppy disks, hard disks, optical disks, CD-ROMs, and magnetic-optical disks, ROMs (Read-Only memories), RAMs (Random Access memories), EPROMs (Erasable Programmable Read-Only memories), EEPROMs (Electrically Erasable Programmable Read-Only memories), flash memories, magnetic cards, or optical cards, or any type of media suitable for storing electronic instructions, and each coupled to a bus. That is, a readable medium includes any medium that stores or transmits information in a form readable by a device (e.g., a computer).
It will be understood by those within the art that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by computer program instructions. Those skilled in the art will appreciate that the computer program instructions may be implemented by a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, implement the features specified in the block or blocks of the block diagrams and/or flowchart illustrations of the present disclosure.
Those of skill in the art will appreciate that various operations, methods, steps in the processes, acts, or solutions discussed in the present application may be alternated, modified, combined, or deleted. Further, various operations, methods, steps in the flows, which have been discussed in the present application, may be interchanged, modified, rearranged, decomposed, combined, or eliminated. Further, steps, measures, schemes in the various operations, methods, procedures disclosed in the prior art and the present invention can also be alternated, changed, rearranged, decomposed, combined, or deleted.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (8)
1. A method of language translation, comprising the steps of:
translating the original information to obtain initial translated information;
when a re-translation instruction is received, re-translating the original information by combining with the historical conversation record to obtain re-translated information;
adding the current dialogue information into the historical dialogue record;
the original information is retranslated by combining the historical conversation record, and the step of acquiring retranslated information comprises the following steps:
s101, sequentially tracing back the historical dialogue information in the historical dialogue record according to the sequence from the late to the early;
s102, the original information is translated again by combining the historical dialogue information;
s103, judging whether the information obtained after the re-translation processing is consistent with the information of the initial translation or not; when the two are consistent, returning to the step S101; when the two are inconsistent, executing the next step;
and S104, acquiring the information obtained after the retranslation processing as retranslation information.
2. The method for translating a language according to claim 1, wherein the step of re-translating the original information in conjunction with the history conversation record and acquiring re-translated information comprises:
s201, sequentially tracing back the historical dialogue information in the historical dialogue record from the late to the early according to the time sequence;
s202, combining the historical dialogue information to translate the original information again;
s203, judging whether the information obtained after the re-translation processing is consistent with the information obtained after any previous re-translation processing; when not consistent, returning to step S201; when the two are consistent, executing the next step;
and S204, acquiring the information obtained after the re-translation processing as re-translation information.
3. The method for translating a language according to claim 1, wherein the step of re-translating the original information in conjunction with the history conversation record and acquiring re-translated information comprises:
s301, sequentially tracing back the historical dialogue information in the historical dialogue record according to the sequence from the late to the early;
s302, the original information is translated again by combining the historical dialogue information;
s303, judging whether the information obtained after the retranslation processing is consistent with the information of the initial translation or not; when the two are consistent, returning to the step S301; when the two are inconsistent, executing the next step;
s304, judging whether the information obtained after the re-translation processing is consistent with the information obtained after any previous re-translation processing; if not, returning to the step S301; when the two are consistent, executing the next step;
s305, obtaining the information obtained after the retranslation processing as retranslation information.
4. A method of language translation according to any of claims 2 to 3 wherein one or at least two pieces of historical dialog information are traced back each time.
5. A language translation apparatus, comprising:
the first translation module is used for translating the original information to acquire initial translated information;
the second translation module is used for carrying out translation processing on the original information again by combining with the historical conversation record when a re-translation instruction is received, and obtaining re-translated information;
the dialogue recording module is used for adding the dialogue information of this time into the historical dialogue record;
the second translation module comprises:
the backtracking unit is used for backtracking the historical dialogue information in the historical dialogue record from late to early in sequence according to time;
the translation unit is used for carrying out translation processing on the original information again by combining the historical dialogue information;
the first judgment unit is used for judging whether the information obtained after the retranslation processing is consistent with the information of the initial translation;
the first obtaining unit is used for obtaining the information obtained after the retranslation processing as retranslation information when the information obtained after the retranslation processing is inconsistent with the information of the initial translation;
and the first notification unit is used for notifying the backtracking unit to backtrack the historical dialogue information in the historical dialogue record again when the information obtained after the retranslation processing is consistent with the information of the initial translation.
6. The language translation device of claim 5, wherein the second translation module comprises:
the backtracking unit is used for backtracking the historical dialogue information in the historical dialogue record from late to early in sequence according to time;
the translation unit is used for carrying out translation processing on the original information again by combining the historical dialogue information;
the second judgment unit is used for judging whether the information obtained after the re-translation processing is consistent with the information obtained after any one time of re-translation processing;
the second acquisition unit is used for acquiring the information obtained after the retranslation processing as retranslation information when the information obtained after the retranslation processing is consistent with the information obtained after the retranslation processing of any time;
and the second notification unit is used for notifying the backtracking unit to backtrack the historical dialogue information in the historical dialogue record again when the information obtained after the current re-translation processing is inconsistent with the information obtained after any previous re-translation processing.
7. The language translation device of claim 5, wherein the second translation module comprises:
the backtracking unit is used for backtracking the historical dialogue information in the historical dialogue record from late to early in sequence according to time;
the translation unit is used for carrying out translation processing on the original information again by combining the historical dialogue information;
the first judgment unit is used for judging whether the information obtained after the retranslation processing is consistent with the information of the initial translation;
a second judging unit, configured to, when the information obtained after the re-translation processing is inconsistent with the initially translated information, judge whether the information obtained after the re-translation processing is consistent with the information obtained after any one previous re-translation processing;
a third obtaining unit, configured to obtain, when information obtained after the current re-translation processing is consistent with information obtained after any previous re-translation processing, information obtained after the current re-translation processing as re-translation information;
and the third informing unit is used for informing the backtracking unit to backtrack the historical dialogue information in the historical dialogue record again when the information obtained after the retranslation processing is consistent with the information of the initial translation or the information obtained after the retranslation processing is inconsistent with the information obtained after the retranslation processing for any time.
8. The language translation device according to any one of claims 5 to 7, wherein the backtracking unit is configured to: each time one or at least two segments of historical session information are traced back.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711117660.8A CN107885734B (en) | 2017-11-13 | 2017-11-13 | Language translation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711117660.8A CN107885734B (en) | 2017-11-13 | 2017-11-13 | Language translation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107885734A CN107885734A (en) | 2018-04-06 |
| CN107885734B true CN107885734B (en) | 2021-07-20 |
Family
ID=61776881
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711117660.8A Active CN107885734B (en) | 2017-11-13 | 2017-11-13 | Language translation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107885734B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111339790B (en) * | 2020-02-25 | 2023-04-04 | 北京字节跳动网络技术有限公司 | Text translation method, device, equipment and computer readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101025735A (en) * | 2006-02-20 | 2007-08-29 | 株式会社东芝 | Apparatus and method for supporting in communication through translation between different languages |
| CN102193914A (en) * | 2011-05-26 | 2011-09-21 | 中国科学院计算技术研究所 | Computer aided translation method and system |
| CN102760122A (en) * | 2012-06-12 | 2012-10-31 | 上海量明科技发展有限公司 | Method, client and system for translating interactive contents in common language |
| CN103329123A (en) * | 2011-01-06 | 2013-09-25 | 高通股份有限公司 | Methods and apparatuses for use in providing translation information services to mobile stations |
| CN103744843A (en) * | 2013-12-25 | 2014-04-23 | 北京百度网讯科技有限公司 | Online voice translation method and device |
| CN104750677A (en) * | 2013-12-25 | 2015-07-01 | 株式会社东芝 | Speech translation apparatus, speech translation method and speech translation program |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7711571B2 (en) * | 2004-03-15 | 2010-05-04 | Nokia Corporation | Dynamic context-sensitive translation dictionary for mobile phones |
| CN106951416A (en) * | 2017-03-21 | 2017-07-14 | 成都星阵地科技有限公司 | Multilingual instant translation system based on big data processing and manual intervention |
-
2017
- 2017-11-13 CN CN201711117660.8A patent/CN107885734B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101025735A (en) * | 2006-02-20 | 2007-08-29 | 株式会社东芝 | Apparatus and method for supporting in communication through translation between different languages |
| CN103329123A (en) * | 2011-01-06 | 2013-09-25 | 高通股份有限公司 | Methods and apparatuses for use in providing translation information services to mobile stations |
| CN102193914A (en) * | 2011-05-26 | 2011-09-21 | 中国科学院计算技术研究所 | Computer aided translation method and system |
| CN102760122A (en) * | 2012-06-12 | 2012-10-31 | 上海量明科技发展有限公司 | Method, client and system for translating interactive contents in common language |
| CN103744843A (en) * | 2013-12-25 | 2014-04-23 | 北京百度网讯科技有限公司 | Online voice translation method and device |
| CN104750677A (en) * | 2013-12-25 | 2015-07-01 | 株式会社东芝 | Speech translation apparatus, speech translation method and speech translation program |
Non-Patent Citations (1)
| Title |
|---|
| 计算机辅助翻译软件WordFisher评介;许汉成 等;《中国科技翻译》;20020531;第15卷(第2期);第30-33页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107885734A (en) | 2018-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108615527B (en) | Data processing method, device and storage medium based on simultaneous interpretation | |
| US10333904B2 (en) | Voice access and control | |
| CN102638797B (en) | Access the method for wireless network, terminal, access network node and authentication server | |
| US20190198027A1 (en) | Audio frame loss recovery method and apparatus | |
| CN1333385C (en) | Voice browser dialog enabler for a communication system | |
| US10277252B2 (en) | Encoding data with polar codes for control channels | |
| US20160239568A1 (en) | Extension of Third Party Application Functionality for Intent Determination | |
| KR101271285B1 (en) | A method of providing a multi language translation for messages included in chatting window | |
| US20140324424A1 (en) | Method for providing a supplementary voice recognition service and apparatus applied to same | |
| CN106156009A (en) | Voice translation method and device | |
| CN110362372A (en) | Page translation method, device, medium and electronic equipment | |
| CN103699530A (en) | Method and equipment for inputting texts in target application according to voice input information | |
| CN103686591A (en) | Method and system for acquiring position information | |
| CN105306815A (en) | Shooting mode switching device, method and mobile terminal | |
| CN105450289A (en) | Multichannel Beidou satellite communication method | |
| CN104753677A (en) | Password hierarchical control method and system | |
| CN104216896A (en) | Contact information searching method and device | |
| CN107885734B (en) | Language translation method and device | |
| US9787759B2 (en) | Method and apparatus for providing shared user interface view | |
| KR101753649B1 (en) | The real-time auto translation and interpretation service system based on position information and method thereof | |
| CN103873251A (en) | Method and equipment for establishing connection by audio frequency | |
| CN101448216B (en) | Information searching method and search service device | |
| KR101351264B1 (en) | System and method for message translation based on voice recognition | |
| KR20160047244A (en) | Method, mobile device and computer-readable medium for providing translation service | |
| CN103379022B (en) | A kind of instant communication method based on Internet map search and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210903 Address after: 518000 201, No.26, yifenghua Innovation Industrial Park, Xinshi community, Dalang street, Longhua District, Shenzhen City, Guangdong Province Patentee after: Shenzhen waterward Information Co.,Ltd. Address before: 518000 B, 503, 602, digital city building, garden city, 1079 Shekou Road, Shekou, Nanshan District, Shenzhen, Guangdong. Patentee before: SHENZHEN WATER WORLD Co.,Ltd. |
|
| TR01 | Transfer of patent right |