An error-correction improved translation big data integration method

Abstract

The invention discloses an error-correction improved translation big data integration method, which belongs to the field of translation technology. The method performs multiple sentence segmentation and numbering on the document, translates and integrates it, and finally performs modification and feedback. The above method performs error correction and feedback processing on the translation result, thereby ensuring the accuracy of the translation. At the same time, during the modification process, the results of the machine-converted translation content will be included in the cloud as a reference for the next translation, thereby improving the learning ability of the system and further improving the effect of machine translation.

Description

Technical Field

[0001] The present invention belongs to the field of translation technology, and more specifically, relates to an error-correcting improved translation big data integration method. Background Art

[0002] In today's society, international exchanges are becoming more and more frequent, which leads to an increasing amount of translation and more and more words in documents.

[0003] The accuracy of the translation is controlled by the translation system. Since the translation is machine translation, it is impossible to achieve perfect translation. The translation results need to be modified and edited multiple times to achieve a translation result that is more consistent with the original meaning. At the same time, the modification method and results are included in the cloud as a control plan to improve the machine's learning ability. Summary of the invention

[0004] 1. Technical problem to be solved by the invention

[0005] The purpose of the present invention is to solve the defects that the existing Chinese translation machine translation is stereotyped and the translation results are not consistent with the original meaning.

[0006] 2. Technical solution

[0007] In order to achieve the above object, the technical solution provided by the present invention is:

[0008] The present invention provides an error-correction improved translation big data integration method, the method comprising the following steps:

[0009] S1, import literature;

[0010] S2, the system directly translates the document to obtain translation 1;

[0011] S3, the system performs artificial intelligence correction on the document to obtain translation 2;

[0012] S4, displays the editing interface of translation 2;

[0013] S5, determining whether the translation 2 in the editing interface is manually modified, if so, integrating the modified translation into translation 3 and proceeding to step S6, if not, directly proceeding to step S6;

[0014] S6, traverse the original text, translation 1, translation 2 and translation 3;

[0015] S7, selecting different sentences from translation 1, translation 2 and translation 3 and arranging them from front to back to integrate them into several data packets;

[0016] S8, respectively annotating the nouns and verbs of the corresponding original sentences in the original text in the plurality of data packets selected in S7 to obtain keyword packets;

[0017] S9, transmits the data to the cloud for processing.

[0018] Preferably, the following steps are further performed after step S1:

[0019] S1.1, segment the document and label each sentence in turn, denoted as Yn, where n is a natural number.

[0020] Preferably, step S2 is followed by the following steps:

[0021] S2.1, segment the translation 1 and label each sentence in turn, denoted as On, where n is a natural number;

[0022] S2.2, integrate Yn and On, denoted as YO-n, which represents the original and translated texts of the nth sentence, where n is a natural number.

[0023] Preferably, step S3 is followed by the following steps:

[0024] S3.1, segment the second translation and label each sentence in turn, denoted as Tn, where n is a natural number;

[0025] S3.2, integrate YO-n and Tn, denoted as YOT-n, representing the original text, translation one and translation two of the nth sentence, where n is a natural number.

[0026] Preferably, step S6 is followed by the following steps:

[0027] S6.1, determine whether there is translation 3 after traversal, if yes, go to step S6.2, otherwise go to step S7;

[0028] S6.2, segment the translation 3 and label each sentence in turn, denoted as Sn, where n is a natural number;

[0029] S6.3, integrate YOT-n and Sn, denoted as YOTS-n, representing the original text, translation one, translation two and translation three of the nth sentence, where n is a natural number.

[0030] Preferably, the following steps are further performed after step S9:

[0031] S9.1, retrieve stored sentences containing relevant nouns and verbs from the cloud according to the keyword package;

[0032] S9.2, analyze the stored sentences and YOT-n, compare them, and select the words and sentences with high probability of occurrence for display;

[0033] S9.3, the system stores YOT-n in the database and calculates the number of occurrences.

[0034] 3. Beneficial effects

[0035] Compared with the prior art, the technical solution provided by the present invention has the following beneficial effects:

[0036] (1) The present invention provides an error-correction improved translation big data integration method, which performs error correction and feedback processing on the translation results to ensure the accuracy of the translation. At the same time, during the modification process, the results of the machine-converted translation content will be included in the cloud as a reference for the next translation, thereby improving the learning ability of the system and further improving the effect of machine translation. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The present invention is a flowchart of an error-correction improved translation big data integration method. DETAILED DESCRIPTION

[0038] To facilitate understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Several embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0039] It should be noted that when an element is referred to as being "fixed on" another element, it may be directly on the other element or there may also be a central element; when an element is considered to be "connected to" another element, it may be directly connected to the other element or there may also be a central element; the terms "vertical", "horizontal", "left", "right" and similar expressions used in this article are for illustrative purposes only.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which the present invention belongs; the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the term "and / or" used herein includes any and all combinations of one or more related listed items.

[0041] Example 1

[0042] See attached Figure 1 As shown, an error-correction improved translation big data integration method of this embodiment includes the following steps:

[0043] S1, import literature;

[0044] S2, the system directly translates the document to obtain translation 1;

[0045] S3, the system performs artificial intelligence correction on the document to obtain translation 2;

[0046] S4, displays the editing interface of translation 2;

[0047] S5, determining whether the translation 2 in the editing interface is manually modified, if so, integrating the modified translation into translation 3 and proceeding to step S6, if not, directly proceeding to step S6;

[0048] S6, traverse the original text, translation 1, translation 2 and translation 3;

[0049] S7, selecting different sentences from translation 1, translation 2 and translation 3 and arranging them from front to back to integrate them into several data packets;

[0050] S8, respectively annotating the nouns and verbs of the corresponding original sentences in the original text in the plurality of data packets selected in S7 to obtain keyword packets;

[0051] S9, transmits the data to the cloud for processing.

[0052] The following steps are further performed after step S1 of this embodiment:

[0053] S1.1, segment the document and label each sentence in turn, denoted as Yn, where n is a natural number.

[0054] The following steps are further followed after step S2 of this embodiment:

[0055] S2.1, segment the translation 1 and label each sentence in turn, denoted as On, where n is a natural number;

[0056] S2.2, integrate Yn and On, denoted as YO-n, which represents the original and translated texts of the nth sentence, where n is a natural number.

[0057] The following steps are further followed after step S3 of this embodiment:

[0058] S3.1, segment the second translation and label each sentence in turn, denoted as Tn, where n is a natural number;

[0059] S3.2, integrate YO-n and Tn, denoted as YOT-n, representing the original text, translation one and translation two of the nth sentence, where n is a natural number.

[0060] The following steps are further followed after step S6 of this embodiment:

[0061] S6.1, determine whether there is translation 3 after traversal, if yes, go to step S6.2, otherwise go to step S7;

[0062] S6.2, segment the translation 3 and label each sentence in turn, denoted as Sn, where n is a natural number;

[0063] S6.3, integrate YOT-n and Sn, denoted as YOTS-n, representing the original text, translation one, translation two and translation three of the nth sentence, where n is a natural number.

[0064] After step S9 in this embodiment, there are the following steps:

[0065] S9.1, retrieve stored sentences containing relevant nouns and verbs from the cloud according to the keyword package;

[0066] S9.2, analyze the stored sentences and YOT-n, compare them, and select the words and sentences with high probability of occurrence for display;

[0067] S9.3, the system stores YOT-n in the database and calculates the number of occurrences.

[0068] The above method performs error correction and feedback processing on the translation results to ensure the accuracy of the translation. At the same time, during the modification process, the results of the machine-converted translation content will be recorded in the cloud as a reference for the next translation, which improves the learning ability of the system and further improves the effect of machine translation.

[0069] The above-described embodiments only express a certain implementation mode of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the patent scope of the present invention. It should be pointed out that, for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be based on the attached claims.

Claims

1. An error-correction improved translation big data integration method, characterized in that: The method comprises the following steps: S1, importing documents; S2, the system directly translates the document to obtain translation 1; S3, the system performs artificial intelligence correction on the document to obtain translation 2; S4, displays the editing interface of translation 2; S5, determining whether the translation 2 in the editing interface is manually modified, if so, integrating the modified translation into translation 3 and proceeding to step S6, if not, directly proceeding to step S6; S6, traverse the original text, translation 1, translation 2 and translation 3; S7, selecting different sentences from translation 1, translation 2 and translation 3 and arranging them from front to back to integrate them into several data packets; S8, respectively annotating the nouns and verbs of the corresponding original sentences in the original text in the plurality of data packets selected in S7 to obtain keyword packets; S9, data is transmitted to the cloud for processing; The step S6 is followed by the following steps: S6.1, determine whether there is translation 3 after traversal, if yes, go to step S6.2, otherwise go to step S7; S6.2, segment the translation 3 and label each sentence in turn, denoted as Sn, where n is a natural number; S6.3, integrate YOT-n and Sn, denoted as YOTS-n, representing the original text, translation one, translation two and translation three of the nth sentence, where n is a natural number, wherein the YOT-n is obtained by integrating YO-n and Tn, the YO-n is obtained by integrating Yn and On, the Yn is obtained by numbering each sentence in turn after segmenting the document, the On is obtained by numbering each sentence in turn after segmenting translation one, and the Tn is obtained by numbering each sentence in turn after segmenting translation two.

2. According to claim 1, the error-correcting improved translation big data integration method is characterized in that: After step S1, there are the following steps: S1.1, segment the document and label each sentence in turn, denoted as Yn, where n is a natural number.

3. The error-correcting improved translation big data integration method according to claim 1, characterized in that: After step S2, there are the following steps: S2.1, segment the translation 1, and label each sentence in turn, denoted as On, where n is a natural number; S2.2, integrate Yn and On, denoted as YO-n, which represents the original and translated texts of the nth sentence, where n is a natural number.

4. The error-correcting improved translation big data integration method according to claim 1, characterized in that: After step S3, there are the following steps: S3.1, segment the second translation, and label each sentence in turn, denoted as Tn, where n is a natural number; S3.2, integrate YO-n and Tn, denoted as YOT-n, representing the original text, translation one and translation two of the nth sentence, where n is a natural number.

5. The error-correction improved translation big data integration method according to claim 1, characterized in that: After step S9, there are the following steps: S9.1, retrieving stored sentences containing relevant nouns and verbs from the cloud according to the keyword package; S9.2, analyze the stored sentences and YOT-n, compare them, and select the words and sentences with high probability of occurrence for display; S9.3, the system stores YOT-n in the database and calculates the number of occurrences.

Images