CN113158694B - Online translation terminal system based on 5G network and method thereof - Google Patents
Online translation terminal system based on 5G network and method thereof Download PDFInfo
- Publication number
- CN113158694B CN113158694B CN202110443918.3A CN202110443918A CN113158694B CN 113158694 B CN113158694 B CN 113158694B CN 202110443918 A CN202110443918 A CN 202110443918A CN 113158694 B CN113158694 B CN 113158694B
- Authority
- CN
- China
- Prior art keywords
- translation
- verification
- value
- translated
- result information
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses an online translation terminal system based on a 5G network and a method thereof, relates to the technical field of online translation, and is used for solving the problem that the existing online translation system cannot reasonably distribute a plurality of terminals for translation, so that the translation safety is low.
Description
Technical Field
The invention relates to the technical field of online translation, in particular to an online translation terminal system based on a 5G network and a method thereof.
Background
The translation system is established on the basis of linguistics, mathematics and computer technology, and a computer translates a language into a language information processing system of the language. Automatic translation, also known as machine translation, includes text machine translation and speech machine translation. A further development in this type of language word processing is natural language understanding. The task of machine translation is to utilize an electronic computer to simulate the translation activity of a human, convert a source language into a target language and realize the automation or partial automation of translation.
In patent CN102609409A, an online translation method, device, system and server disclose that the method comprises: receiving an online translation request sent by a user terminal; acquiring communication languages of the two communication parties carried in the online translation request; and performing online real-time translation on the communication information carried in the online translation request according to the communication language. Although the communication information can be carried in the online translation request to be sent, manual copying is not needed, and the online real-time translation is realized while the timely communication is realized. Furthermore, the communication information can be translated by an online translator, and compared with the method of copying the communication information to translation software for translation, the translation accuracy is improved, and the communication quality function is ensured; but there are: the translated content cannot be translated in batches and distributed to different terminals for translation, so that the translated content is easy to leak, and the security is low.
Disclosure of Invention
The invention aims to provide an online translation terminal system based on a 5G network and a method thereof, aiming at solving the problem that the translation security is low because the existing online translation system cannot reasonably distribute a plurality of terminals for translating the translated contents.
The purpose of the invention can be realized by the following technical scheme: an on-line translation terminal system based on 5G network comprises a user terminal, a server and a translation terminal,
the user side sends information to be translated to the server, the server receives the information to be translated and then processes the information to be translated, and the specific processing process is as follows: dividing the characters to be translated into a plurality of translation segments and marking the translation segments as segments to be processed; acquiring a registration terminal in a server, comparing the translation type of the registration terminal with the type in the information to be translated, and marking the translation type containing the type in the information to be translated in the translation type as a primary selection terminal; acquiring the position of a primary selection terminal, calculating the distance difference between the position of the primary selection terminal and the position of a user side to obtain a translation interval, and marking the primary selection terminal with the translation interval smaller than a set interval threshold as a preferred terminal; acquiring translation effective values and accurate values of an optimal terminal, carrying out normalization processing on translation intervals, translation effective values and accurate values of the optimal terminal, taking numerical values, obtaining a selection value of the optimal terminal through numerical analysis, sequencing the optimal terminal according to the selection value from large to small, sequentially selecting optimal terminals with the number equal to that of fragments to be processed from front to back, and marking the selected optimal terminals as translation ends; the server sequentially sends the fragments to be processed to the corresponding translation ends, and simultaneously marks the moment of sending the fragments to be processed as the translation starting moment; the translation end translates the to-be-processed fragment after receiving the to-be-processed fragment, translates the to-be-processed fragment into translation result information corresponding to the name of the translation language, and sends the translation result information to the server; the server receives all translation result information of the characters to be translated, obtains the translated text according to the sequence, and feeds the translated text back to the user side; and the user side receives the translated text information and then displays and plays the speech.
As a preferred embodiment of the present invention, the server includes a valid value analysis module, and the valid value analysis module is configured to collect and analyze a time when the translation end feeds back the translation result information, and specifically includes: marking the moment when the translation end feeds back the translation result information as the translation completion moment; calculating the time difference between the translation finishing time and the translation starting time to obtain translation time length, summing all the translation time lengths smaller than the set translation threshold time length when the translation time length is smaller than the set translation threshold time length, taking the average translation time length to obtain the total translation times of the translation end, normalizing the translation time length and the total translation times, taking the numerical values of the normalization time length and the total translation times, and obtaining the translation effective value of the translation end through numerical analysis.
As a preferred embodiment of the present invention, the server further includes an accurate analysis module, where the accurate analysis module is configured to accurately verify translation result information, and specifically: feeding back a verification instruction of the translation result information to the user side, and when the user side receives the verification instruction and feeds back an agreement instruction to the accurate analysis module, marking the translation result information corresponding to the segment to be translated as a verification segment by the accurate analysis module; sending the verification fragments to an intelligent terminal of a verifier; the verification personnel translate the verification fragments and mark the translation result as verification result information, and the verification personnel feed the verification result information back to the accurate analysis module through the intelligent terminal; the accurate analysis module receives the verification result information and compares the verification result information with the translation result information to obtain a similarity value; when the similarity value is smaller than one, the verification result information of the verification personnel is fed back to the user side, and the accurate analysis module sums all the similarity values of the translation end and takes the average value to obtain the accurate value of the translation end;
as a preferred embodiment of the present invention, the specific process of the accurate analysis module being sent to the intelligent terminal of the verifier is as follows: acquiring an intelligent terminal which is provided with translation software and is operated on line by corresponding translators, and marking the translators which contain verification texts in translation types corresponding to the translators as verification persons; sending a position acquisition instruction to an intelligent terminal of a verifier, acquiring the position of the verifier, calculating the distance between the position of the verifier and the position of a server to obtain a verification distance between the position of the verifier and the position of the server, setting all translation companies to correspond to a preset translation value, matching the translation company to which the verifier belongs with all translation companies to obtain a corresponding preset translation value, setting all certificates to correspond to a certificate value, matching the certificate of the verifier with all certificates to obtain corresponding certificate values, summing all matched certificate values to obtain a total certificate value, normalizing the verification distance, the preset translation value and the total certificate value of the verifier and taking a value, obtaining a verification optimal value of the verifier through numerical analysis, and sending a verification segment to the intelligent terminal of the verifier with the maximum verification optimal value;
as a preferred embodiment of the present invention, the information to be translated includes the characters to be translated, primitive names, names and types of the translated words, and the location and translation of the user side; the primitive names and the translated language names comprise Chinese names, foreign language names and the like; the type comprises the step of translating the characters to be translated into characters of corresponding languages;
as a preferred embodiment of the present invention, the server further includes a terminal registration module, the terminal registration module is used for the user or the translator to submit the terminal information through the intelligent terminal for registration and send the terminal information which is successfully registered to the server, and the server marks the intelligent terminal which is successfully registered as the registration terminal;
an online translation terminal method based on a 5G network is characterized by comprising the following steps:
s1: the method comprises the following steps that a user side sends information to be translated to a server, the server receives the information to be translated and then processes the information to be translated, and the specific processing steps are as follows:
s101: dividing the characters to be translated into a plurality of translation segments and marking the translation segments as segments to be processed; acquiring a registration terminal in a server, comparing the translation type of the registration terminal with the type in the information to be translated, and marking the translation type containing the type in the information to be translated in the translation type as a primary selection terminal; acquiring the position of a primary selection terminal, calculating the distance difference between the position of the primary selection terminal and the position of a user side to obtain a translation interval, and marking the primary selection terminal with the translation interval smaller than a set interval threshold as a preferred terminal;
s102: marking the translation interval of the preferred terminal as M1; acquiring a translation effective value and an accurate value of an optimal terminal and sequentially marking the translation effective value and the accurate value as M2 and M3; normalizing the translation distance, the translation effective value and the translation accurate value and taking the numerical values of the translation distance, the translation effective value and the translation accurate value;
s103: using formulas
Obtaining a selective interpretation value FY of a preferred terminal; lambda is a correction factor, and the value of lambda is 0.847; b1, b2 and b3 are all preset proportionality coefficients;
s104: sorting the optimized terminals according to the selected translation values from large to small, sequentially selecting the optimized terminals with the number equal to that of the fragments to be processed from front to back, and marking the selected optimized terminals as translation ends;
s2: the server sequentially sends the fragments to be processed to the corresponding translation ends, and simultaneously marks the moment of sending the fragments to be processed as the translation starting moment; the translation end translates the to-be-processed fragment after receiving the to-be-processed fragment, translates the to-be-processed fragment into translation result information corresponding to the name of the translation language, and sends the translation result information to the server;
s3: the server receives all translation result information of the characters to be translated, obtains the translated text according to the sequence, and feeds the translated text back to the user side; the user side receives the translated text information and then displays and plays the translated text information in voice;
s4: the translation result information is accurately verified, a verification instruction of the translation result information is fed back to the user side, and when the user side receives the verification instruction and feeds back an agreement instruction to the accurate analysis module, the accurate analysis module marks the translation result information corresponding to the segment to be translated as a verification segment;
s5: acquiring an intelligent terminal which is provided with translation software and is operated on line by corresponding translators, and marking the translators which contain verification texts in translation types corresponding to the translators as verification persons; sending a position acquisition instruction to an intelligent terminal of the verifier, acquiring the position of the verifier, and calculating the distance between the position of the verifier and the position of the server to obtain a verification distance between the position of the verifier and the position of the server and marking the verification distance as YG1; setting all translation companies to correspond to a preset translation value, and matching the translation company to which the verifier belongs with all translation companies to obtain the corresponding preset translation value and marking the preset translation value as YG2; setting all certificates to correspond to one certificate value, matching the certificates of the verifier with all the certificates to obtain corresponding certificate values, summing all the matched certificate values to obtain a total certificate value, and marking the total certificate value as YG3; carrying out normalization processing on the verification distance of the verification personnel, the preset translation value and the certificate total value and taking a numerical value;
s6: obtaining the verification optimal value YD of the verifier by using a formula YD = YG2 × 0.4+ YG3 × 0.5-YG1 × 0.1; the verification fragments are sent to an intelligent terminal of a verifier with the maximum verification figure of merit, the verifier translates the verification fragments and marks the translated result as verification result information, and the verifier feeds the verification result information back to an accurate analysis module through the intelligent terminal; the accurate analysis module receives the verification result information and compares the verification result information with the translation result information to obtain a similarity value; when the similarity value is less than one, the verification result information of the verification personnel is fed back to the user side;
as a preferred embodiment of the present invention, the translation valid value is obtained by processing through a server valid value analysis module, and specifically includes: marking the moment when the translation end feeds back the translation result information as the translation completion moment; calculating the time difference between the translation completion time and the translation starting time to obtain translation time length, and when the translation time length is less than the set translation threshold time length, summing all the translation time lengths less than the set translation threshold time length, taking the average translation time length, and marking the average translation time length as FY1; marking the total times of translation at the translation end as FY2; normalizing the translation average time length and the total translation times, and taking the numerical values, and obtaining a translation effective value M2 of a translation end by using a formula M2= (1/FY 1). Times.b 4+ FY2 x b 5; wherein b4 and b5 are preset weight coefficients.
Compared with the prior art, the invention has the beneficial effects that:
1. the method comprises the steps that a user side sends information to be translated to a server, the server processes the information to be translated after receiving the information to be translated, the characters to be translated are divided into a plurality of translation segments, normalization processing is carried out by combining translation intervals, translation effective values and accurate values, numerical values are obtained, the selected translation value of a preferred terminal is obtained through numerical value analysis, the preferred terminal is sequenced according to the selected translation value from large to small, the translation end is further selected reasonably, the server sends the segments to be processed to the corresponding translation end in sequence, translation processing is carried out through the translation ends, translation efficiency is improved, meanwhile, safety of translation contents is guaranteed, and leakage of the translation contents is avoided;
2. the accurate analysis module accurately verifies the translation result information, feeds back a verification instruction of the translation result information to the user side, and marks the translation result information corresponding to the segment to be translated as a verification segment when the user side receives the verification instruction and feeds back an agreement instruction to the accurate analysis module; sending the verification fragments to an intelligent terminal of a verifier; the verification personnel translate the verification fragments and mark the translation result as verification result information, and the verification personnel feed the verification result information back to the accurate analysis module through the intelligent terminal; the accurate analysis module receives the verification result information and compares the verification result information with the translation result information to obtain a similarity value; when the similarity value is smaller than one, the verification result information of the verification personnel is fed back to the user side, and the translation accuracy of the information to be translated is further improved by verifying the translation result information.
Drawings
In order to facilitate understanding for those skilled in the art, the present invention will be further described with reference to the accompanying drawings.
FIG. 1 is a functional block diagram of the present invention;
fig. 2 is a schematic diagram of an encrypted circle according to the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an online translation terminal system based on a 5G network includes a user terminal, a server, and a translation terminal; the user side and the translation side are in communication connection with the server through a 5G network; the user side is an intelligent terminal with the functions of inputting, displaying, receiving and playing characters or voice; the intelligent terminal comprises an intelligent mobile phone, a tablet computer and the like;
the translation end is an intelligent terminal provided with translation software or an intelligent terminal which is simultaneously provided with translation software and is operated on line by corresponding translators;
the server comprises a terminal registration module, a database, an effective value analysis module and an accurate analysis module;
the terminal registration module is used for a user or a translator to submit terminal information through the intelligent terminal for registration and send the terminal information which is successfully registered to the server, and the server marks the intelligent terminal which is successfully registered as a registration terminal; the terminal information filled by the user comprises the model, the translation type and the communication number of the intelligent terminal; the terminal information filled by the translator comprises the model, the translation type and the communication number of the intelligent terminal, the translation type corresponding to the translator, the translation company, the certificate corresponding to the translation and the translation working time;
when the translation end is an intelligent terminal provided with translation software, the user end sends information to be translated to the server, wherein the information to be translated comprises characters to be translated, primitive names, names and types of translation words and the position and translation of the user end; the primitive names and the translated language names comprise Chinese names, foreign language names and the like; the type comprises the steps of translating the characters to be translated into characters of corresponding languages;
after receiving the information to be translated, the server processes the information to be translated, and the specific processing is as follows:
dividing the characters to be translated into a plurality of translation segments and marking the translation segments as segments to be processed; wherein the fragments to be processed are divided according to punctuation marks, and each fragment to be processed is a sentence;
acquiring a registration terminal in a server, comparing the translation type of the registration terminal with the type in the information to be translated, and marking the translation type containing the type in the information to be translated in the translation type as a primary selection terminal;
acquiring the position of a primary selection terminal, calculating the distance difference between the position of the primary selection terminal and the position of a user side to obtain a translation interval, and marking the primary selection terminal of which the translation interval is smaller than a set interval threshold value as a preferred terminal;
marking the translation interval of the preferred terminal as M1; acquiring a translation effective value and an accurate value of an optimal terminal and sequentially marking the translation effective value and the accurate value as M2 and M3;
normalizing the translation distance, the translation effective value and the translation accurate value and taking the numerical values of the translation distance, the translation effective value and the translation accurate value; using formulas
Obtaining a selective interpretation value FY of a preferred terminal; wherein, the lambda is a correction factor and takes a value of 0.847; b1, b2 and b3 are all preset proportionality coefficients with values of 1.34, 1.65 and 1.87 respectively;
sorting the optimized terminals according to the selected translation values from large to small, sequentially selecting the optimized terminals with the number equal to that of the fragments to be processed from front to back, and marking the selected optimized terminals as translation ends; the server sequentially sends the fragments to be processed to the corresponding translation ends, and simultaneously marks the moment of sending the fragments to be processed as the translation starting moment; after receiving the to-be-processed segment, the translation end translates the to-be-processed segment, specifically: translating the segment to be processed into translation result information corresponding to the name of the translation language, sending the translation result information to a server, and marking the total number of translations of the translation end as one time;
the server receives all translation result information of the characters to be translated, obtains the translated text according to the sequence, and feeds the translated text back to the user side;
the user side receives the translated text information and then displays and plays the translated text information in voice;
the effective value analysis module is used for acquiring and analyzing the time when the translation end feeds back the translation result information, and specifically marking the time when the translation end feeds back the translation result information as the translation completion time; calculating the time difference between the translation finishing time and the translation starting time to obtain translation time length, and when the translation time length is less than the set translation threshold time length, summing all the translation time lengths less than the set translation threshold time length, taking the average translation time length and marking the average translation time length as FY1; marking the total times of translation at the translation end as FY2; normalizing the translation average time length and the total translation times, and taking the numerical values, and obtaining a translation effective value M2 of a translation end by using a formula M2= (1/FY 1). Times.b 4+ FY2 x b 5; wherein b4 and b5 are preset weight coefficients; the value is 0.65 and 0.35;
the accurate analysis module is used for accurately verifying the translation result information; the method specifically comprises the following steps:
feeding back a verification instruction of the translation result information to the user side, and marking the translation result information corresponding to the segment to be translated as a verification segment by the accurate analysis module when the user side receives the verification instruction and feeds back an agreement instruction to the accurate analysis module;
acquiring an intelligent terminal which is provided with translation software and is operated on line by corresponding translators, and marking the translators which comprise verification texts in translation types corresponding to the translators as verifiers; sending a position acquisition instruction to an intelligent terminal of the verifier, acquiring the position of the verifier, and calculating the distance between the position of the verifier and the position of the server to obtain a verification distance between the position of the verifier and the position of the server and marking the verification distance as YG1;
setting all translation companies to correspond to a preset translation value, and matching the translation company to which the verifier belongs with all translation companies to obtain the corresponding preset translation value and marking the preset translation value as YG2;
setting all certificates to correspond to a certificate value, matching the certificates of the verifier with all the certificates to obtain corresponding certificate values, summing all the matched certificate values to obtain a total certificate value, and marking the total certificate value as YG3;
normalizing the verification distance, the preset translation value and the total certificate value of the verifier, and taking a numerical value to obtain a verification optimal value YD of the verifier by using a formula YD = YG2 × 0.4+ YG3 × 0.5-YG1 × 0.1;
the verification fragments are sent to an intelligent terminal of a verification person with the maximum verification merit value, the verification person translates the verification fragments and marks the translated result as verification result information, and the verification person feeds the verification result information back to an accurate analysis module through the intelligent terminal;
the accurate analysis module receives the verification result information and compares the verification result information with the translation result information to obtain a similarity value; when the similarity value is smaller than one, the verification result information of the verification personnel is fed back to the user side, and the accurate analysis module sums all the similarity values of the translation end and takes the average value to obtain the accurate value of the translation end;
the database is used for encrypting and storing the information to be translated, the translation result information and the verification result information; the method comprises the following specific steps:
setting all characters to correspond to a unique numerical value, and matching characters and symbols in the information to be translated, the translation result information and the verification result information with all characters to obtain corresponding numerical values; obtaining numerical value texts by numerical values according to the sequence;
sending a value acquisition instruction to a user side, inputting a conversion value by a corresponding user through the user side and feeding back the conversion value to a database; adding a conversion numerical value to each numerical value in the numerical value text, and marking the numerical value text added with the conversion numerical value as a conversion text;
carrying out encryption conversion on a first numerical value in the conversion text, setting a reference circle, acquiring the number of bits corresponding to the first numerical value, and equally dividing the inside of the reference circle into sector areas with the same number as the number of the bits;
setting 0 to 9 to correspond to a preset color; matching the number corresponding to the first numerical value with the preset color corresponding to 0-9, and filling the matched color in a sector of a reference circle to obtain a first encrypted circle of the converted text; reducing all encrypted graphs by a certain proportion and placing the encrypted graphs on a blank picture; then storing; the concrete expression is as follows: setting the first value to 1348; if the settings 1 is red, 3 is yellow, 4 is black, and 8 is green; then, as shown in fig. 2, the color is represented by the text. The information to be translated, the translation result information and the verification result information are encrypted and stored through the database, so that the safety of translation content storage is improved;
the above formulas are obtained by collecting a large amount of data and performing software simulation, and the coefficients in the formulas are set by those skilled in the art according to actual conditions.
When the translation device is used, a user side sends information to be translated to a server, the server processes the information to be translated after receiving the information to be translated, the characters to be translated are divided into a plurality of translation segments, normalization processing is carried out by combining translation intervals, translation effective values and accurate values, numerical values are obtained, the selected translation value of a preferred terminal is obtained through numerical value analysis, the preferred terminal is sequenced according to the selected translation value from large to small, then the translation end is selected reasonably, the server sends the segments to be processed to the corresponding translation end in sequence, translation processing is carried out through the translation ends, translation efficiency is improved, meanwhile, safety of translation contents is guaranteed, and leakage of the translation contents is avoided;
the accurate analysis module accurately verifies the translation result information, feeds back a verification instruction of the translation result information to the user side, and marks the translation result information corresponding to the segment to be translated as a verification segment when the user side receives the verification instruction and feeds back an agreement instruction to the accurate analysis module; sending the verification fragments to an intelligent terminal of a verifier; the verification personnel translate the verification fragments and mark the translation result as verification result information, and the verification personnel feed the verification result information back to the accurate analysis module through the intelligent terminal; the accurate analysis module receives the verification result information and compares the verification result information with the translation result information to obtain a similarity value; when the similarity value is smaller than one, the verification result information of the verification personnel is fed back to the user side, and the translation accuracy of the information to be translated is further improved by verifying the translation result information.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (5)
1. An online translation terminal system based on a 5G network comprises a user side, a server and a translation side; the method is characterized in that:
the user side sends the information to be translated to the server, the server processes the information to be translated after receiving the information to be translated, and the specific processing process is as follows: dividing the characters to be translated into a plurality of translation segments and marking the translation segments as segments to be processed; acquiring a registration terminal in a server, comparing the translation type of the registration terminal with the type in the information to be translated, and marking the translation type containing the type in the information to be translated in the translation type as a primary selection terminal; acquiring the position of a primary selection terminal, calculating the distance difference between the position of the primary selection terminal and the position of a user side to obtain a translation interval, marking the translation interval as M1, and marking the primary selection terminal of which the translation interval is smaller than a set interval threshold value as a preferred terminal; acquiring translation effective values and accurate values of the optimized terminal, sequentially marking the translation effective values and the accurate values as M2 and M3, and normalizing the translation space, the translation effective values and the accurate values of the optimized terminalAnd taking the value of the equation
Obtaining a selective interpretation value FY of a preferred terminal; lambda is a correction factor, and the value of lambda is 0.847; b1, b2 and b3 are all preset proportionality coefficients; sorting the optimized terminals according to the selected translation values from large to small, sequentially selecting the optimized terminals with the number equal to that of the fragments to be processed from front to back, and marking the selected optimized terminals as translation ends; the server sequentially sends the fragments to be processed to the corresponding translation ends, and simultaneously marks the moment of sending the fragments to be processed as the translation starting moment; after receiving the to-be-processed fragments, the translation end translates the to-be-processed fragments into translation result information corresponding to the names of the translation words and sends the translation result information to the server; the server receives all translation result information of the characters to be translated, obtains the translated text according to the sequence, and feeds the translated text back to the user side; the user side receives the translated text information and then displays and plays the translated text information in voice;
the server comprises a virtual value analysis module, the virtual value analysis module is used for collecting the time when the translation end feeds back translation result information and analyzing, and specifically comprises the following steps: marking the moment when the translation end feeds back the translation result information as the translation completion moment; calculating the time difference between the translation completion time and the translation starting time to obtain translation time length, and when the translation time length is less than the set translation threshold time length, summing all the translation time lengths less than the set translation threshold time length and taking the average value to obtain translation average time length which is marked as FY1; marking the total times of translation at the translation end as FY2; normalizing the translation average time length and the total translation times, and taking the numerical values, and obtaining a translation effective value M2 of a translation end by using a formula M2= (1/FY 1). Times.b 4+ FY2 x b 5; wherein b4 and b5 are preset weight coefficients;
the server also comprises an accurate analysis module, the accurate analysis module is used for accurately verifying the translation result information, and the accurate analysis module specifically comprises: feeding back a verification instruction of the translation result information to the user side, and when the user side receives the verification instruction and feeds back an agreement instruction to the accurate analysis module, marking the translation result information corresponding to the segment to be translated as a verification segment by the accurate analysis module; sending the verification fragments to an intelligent terminal of a verifier; the verification personnel translate the verification fragments and mark the translation result as verification result information, and the verification personnel feed the verification result information back to the accurate analysis module through the intelligent terminal; the accurate analysis module receives the verification result information and compares the verification result information with the translation result information to obtain a similarity value; when the similarity value is smaller than one, the verification result information of the verification personnel is fed back to the user side, and the accurate analysis module sums all the similarity values of the translation end and takes the average value to obtain the accurate value of the translation end;
the specific process that the accurate analysis module sends to the intelligent terminal of the verification personnel is as follows: acquiring an intelligent terminal which is provided with translation software and is operated on line by corresponding translators, and marking the translators which contain verification texts in translation types corresponding to the translators as verification persons; sending a position acquisition instruction to an intelligent terminal of the verifier, acquiring the position of the verifier, and calculating the distance between the position of the verifier and the position of the server to obtain a verification distance between the position of the verifier and the position of the server and marking the verification distance as YG1; setting all translation companies to correspond to a preset translation value, matching the translation company to which the verifier belongs with all translation companies to obtain the corresponding preset translation value, and marking the preset translation value as YG2; setting all certificates to correspond to a certificate value, matching the certificates of the verifier with all the certificates to obtain corresponding certificate values, summing all the matched certificate values to obtain a total certificate value, and marking the total certificate value as YG3; carrying out normalization processing on the verification distance of the verification personnel, the preset translation value and the certificate total value and taking numerical values; obtaining the verification optimal value YD of the verifier by using a formula YD = YG2 × 0.4+ YG3 × 0.5-YG1 × 0.1; the verification fragments are sent to an intelligent terminal of a verifier with the maximum verification figure of merit, the verifier translates the verification fragments and marks the translated result as verification result information, and the verifier feeds the verification result information back to an accurate analysis module through the intelligent terminal; the accurate analysis module receives the verification result information and compares the verification result information with the translation result information to obtain a similarity value; and when the similarity value is less than one, feeding back the verification result information of the verification personnel to the user side.
2. The on-line translation terminal system based on 5G network according to claim 1, wherein the information to be translated comprises the characters to be translated, primitive names, names and types of translated words, and the position and translation of the user terminal; the primitive names and the translated language names comprise Chinese and foreign language names; the type includes translating the text to be translated into text of the corresponding language.
3. The on-line translation terminal system based on the 5G network as claimed in claim 1, wherein the server further comprises a terminal registration module, the terminal registration module is used for a user or a translator to submit terminal information for registration through the intelligent terminal and send the terminal information with successful registration to the server, and the server marks the intelligent terminal with successful registration as the registration terminal.
4. An online translation method based on a 5G network is characterized by comprising the following steps:
s1: the method comprises the following steps that a user side sends information to be translated to a server, the server processes the information to be translated after receiving the information to be translated, and the specific processing steps are as follows:
s101: dividing the characters to be translated into a plurality of translation segments and marking the translation segments as segments to be processed; acquiring a registration terminal in a server, comparing the translation type of the registration terminal with the type in the information to be translated, and marking the translation type containing the type in the information to be translated in the translation type as a primary selection terminal; acquiring the position of a primary selection terminal, calculating the distance difference between the position of the primary selection terminal and the position of a user side to obtain a translation interval, and marking the primary selection terminal with the translation interval smaller than a set interval threshold as a preferred terminal;
s102: marking the translation interval of the preferred terminal as M1; acquiring a translation effective value and an accurate value of an optimal terminal and sequentially marking the translation effective value and the accurate value as M2 and M3; normalizing the translation interval, the translation effective value and the translation accurate value and taking the numerical values;
s103: using formulas
Obtaining a selective interpretation value FY of a preferred terminal; lambda is a correction factor, and the value of lambda is 0.847; b1, b2 and b3 are all preset proportionality coefficients;
s104: sorting the optimized terminals according to the selected translation values from large to small, sequentially selecting the optimized terminals with the number equal to that of the fragments to be processed from front to back, and marking the selected optimized terminals as translation ends;
s2: the server sequentially sends the fragments to be processed to the corresponding translation ends, and simultaneously marks the moment of sending the fragments to be processed as the translation starting moment; after receiving the to-be-processed fragments, the translation end translates the to-be-processed fragments into translation result information corresponding to the names of the translation words and sends the translation result information to the server;
s3: the server receives all translation result information of the characters to be translated, obtains the translated text according to the sequence, and feeds the translated text back to the user side; the user side receives the translated text information and then displays and plays the translated text information in voice;
s4: the translation result information is accurately verified, a verification instruction of the translation result information is fed back to the user side, and when the user side receives the verification instruction and feeds back an agreement instruction to the accurate analysis module, the accurate analysis module marks the translation result information corresponding to the segment to be translated as a verification segment;
s5: acquiring an intelligent terminal which is provided with translation software and is operated on line by corresponding translators, and marking the translators which contain verification texts in translation types corresponding to the translators as verification persons; sending a position acquisition instruction to an intelligent terminal of the verifier, acquiring the position of the verifier, and calculating the distance between the position of the verifier and the position of the server to obtain a verification distance between the position of the verifier and the position of the server and marking the verification distance as YG1; setting all translation companies to correspond to a preset translation value, matching the translation company to which the verifier belongs with all translation companies to obtain the corresponding preset translation value, and marking the preset translation value as YG2; setting all certificates to correspond to a certificate value, matching the certificates of the verifier with all the certificates to obtain corresponding certificate values, summing all the matched certificate values to obtain a total certificate value, and marking the total certificate value as YG3; carrying out normalization processing on the verification distance of the verification personnel, the preset translation value and the certificate total value and taking a numerical value;
s6: obtaining the verification optimal value YD of the verifier by using a formula YD = YG2 × 0.4+ YG3 × 0.5-YG1 × 0.1; the verification fragments are sent to an intelligent terminal of a verification person with the maximum verification merit value, the verification person translates the verification fragments and marks the translated result as verification result information, and the verification person feeds the verification result information back to an accurate analysis module through the intelligent terminal; the accurate analysis module receives the verification result information and compares the verification result information with the translation result information to obtain a similarity value; and when the similarity value is less than one, feeding back the verification result information of the verifier to the user side.
5. The online translation method based on the 5G network according to claim 4, wherein the translation valid value is obtained by processing through a valid value analysis module in the server, and specifically comprises: marking the moment when the translation end feeds back the translation result information as the translation completion moment; calculating the time difference between the translation finishing time and the translation starting time to obtain translation time length, and when the translation time length is smaller than a set translation threshold time length, summing all the translation time lengths smaller than the set translation threshold time length and taking the average value to obtain translation average time length which is marked as FY1; marking the total times of translation at a translation end as FY2; normalizing the translation averaging time length and the total translation times, taking the numerical values of the translation averaging time length and the total translation times, and obtaining a translation effective value M2 of a translation end by using a formula M2= (1/FY 1) × b4+ FY2 × b 5; wherein, b4 and b5 are preset weight coefficients.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110443918.3A CN113158694B (en) | 2021-04-23 | 2021-04-23 | Online translation terminal system based on 5G network and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110443918.3A CN113158694B (en) | 2021-04-23 | 2021-04-23 | Online translation terminal system based on 5G network and method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113158694A CN113158694A (en) | 2021-07-23 |
| CN113158694B true CN113158694B (en) | 2023-01-13 |
Family
ID=76870011
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110443918.3A Active CN113158694B (en) | 2021-04-23 | 2021-04-23 | Online translation terminal system based on 5G network and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113158694B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1851690A (en) * | 2006-06-05 | 2006-10-25 | 北京金山软件有限公司 | Method and system for translating web page |
| CN106776583A (en) * | 2015-11-24 | 2017-05-31 | 株式会社Ntt都科摩 | Machine translation evaluation method and apparatus and machine translation method and equipment |
| CN110210721A (en) * | 2019-05-14 | 2019-09-06 | 长沙手之声信息科技有限公司 | A kind of long-range sign language translation on line customer service distribution method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8805672B2 (en) * | 2011-06-30 | 2014-08-12 | International Business Machines Corporation | Translation cache prediction |
| CN106022987A (en) * | 2016-05-21 | 2016-10-12 | 李林瑛 | Real-person online translation system and method |
-
2021
- 2021-04-23 CN CN202110443918.3A patent/CN113158694B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1851690A (en) * | 2006-06-05 | 2006-10-25 | 北京金山软件有限公司 | Method and system for translating web page |
| CN106776583A (en) * | 2015-11-24 | 2017-05-31 | 株式会社Ntt都科摩 | Machine translation evaluation method and apparatus and machine translation method and equipment |
| CN110210721A (en) * | 2019-05-14 | 2019-09-06 | 长沙手之声信息科技有限公司 | A kind of long-range sign language translation on line customer service distribution method and device |
Non-Patent Citations (2)
| Title |
|---|
| s Effects on the Evaluation of Automated Transliteration Systems;Sarvnaz Karimi et al;《Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics》;20070630;640-647 * |
| 基于语言模型的机器翻译评价方法及其性能评价方法研究;高俊涛等;《中国科技信息》;20081015(第20期);110-113 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113158694A (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021135910A1 (en) | Machine reading comprehension-based information extraction method and related device | |
| CN112037077B (en) | Seal identification method, device, equipment and storage medium based on artificial intelligence | |
| CN112183036B (en) | Format document generation method, device, equipment and storage medium | |
| CN112347226B (en) | Document knowledge extraction method, device, computer equipment and readable storage medium | |
| CN106971002A (en) | A kind of data auditing method and system | |
| CN107220243A (en) | A kind of Database Interactive translation system | |
| CN104503960A (en) | Text data processing method for English translation | |
| CN114610892A (en) | Knowledge point annotation method and device, electronic equipment and computer storage medium | |
| CN112464283A (en) | Data storage system based on block chain | |
| CN113656547A (en) | Text matching method, device, equipment and storage medium | |
| CN112580108A (en) | Signature and seal integrity verification method and computer equipment | |
| CN115147849A (en) | Training method of character coding model, character matching method and device | |
| CN113158694B (en) | Online translation terminal system based on 5G network and method thereof | |
| CN116934278A (en) | Method and device for auditing construction scheme | |
| CN106775914B (en) | A kind of code method for internationalizing and device for automatically generating key assignments | |
| CN113536770B (en) | Text analysis method, device and equipment based on artificial intelligence and storage medium | |
| CN113283231B (en) | Method for acquiring signature bit, setting system, signature system and storage medium | |
| CN116469111B (en) | Character generation model training method and target character generation method | |
| CN103064967A (en) | Method and device used for establishing user binary relation bases | |
| CN103810365A (en) | Automatic grading method based on hydroelectric simulation training system | |
| CN111260512B (en) | Background course autonomous distribution method and device | |
| CN109522015A (en) | Banking guide page face generates system | |
| CN112800281B (en) | Engineering cost data processing method and device | |
| CN111680515B (en) | Answer determination method and device based on AI (Artificial Intelligence) recognition, electronic equipment and medium | |
| CN115659929B (en) | Annotating interaction method and system based on multiple documents |
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 |