Text translation control methods, devices, electronic equipment, and storage media

Abstract

This application provides a text translation control method, apparatus, electronic device, and storage medium. The method includes: identifying the field type of a field to be translated in the text; obtaining a target translation rule corresponding to the field to be translated from a preset field type-translation rule mapping table according to the field type; and performing field splitting, translation matching, and translation recombination on the field to be translated according to the target translation rule to obtain a translation corresponding to the field to be translated. This method classifies the fields in the text and configures corresponding translation rules for different field types, automatically translating according to different field types, which is highly efficient and targeted, effectively improving the accuracy of translation processing.

Description

Technical Field

[0001] This application belongs to the field of data processing technology, and in particular relates to a text translation control method, apparatus, device and storage medium. Background Technology

[0002] With the continuous maturation and development of internet and big data technologies, data sharing, integration, and analysis have become particularly important for online business services. Given the varying language requirements of different users, business systems providing services need text in different languages ​​to meet diverse user needs. Therefore, business systems typically include a field translation step before providing services. As the volume of data in the business database within these systems increases, the amount of field content requiring translation also grows. Manual translation is labor-intensive, costly, time-consuming, and its accuracy is difficult to guarantee, making it unsuitable for the current translation needs of business systems. Summary of the Invention

[0003] In view of this, embodiments of this application provide a text translation control method, apparatus, device, and storage medium, which can improve translation processing efficiency and / or improve translation accuracy.

[0004] A first aspect of this application provides a text translation control method, the text translation control method comprising:

[0005] Identify the field type of the field to be translated in the text;

[0006] Based on the field type, obtain the target translation rule that matches the field to be translated from the preset field type-translation rule mapping table;

[0007] According to the target translation rules, the field to be translated is split, matched with the translation, and recombined with the translation to obtain the matching translation corresponding to the field to be translated.

[0008] In conjunction with the first aspect, in the first possible implementation of the first aspect, after the step of performing field splitting, translation matching, and translation reorganization on the field to be translated according to the target translation rule to obtain the matching translation corresponding to the field to be translated, the method includes:

[0009] The obtained translations corresponding to the fields to be translated are marked as pending review and the translations are sent to the review end for review and confirmation.

[0010] In conjunction with the first aspect, in the second possible implementation of the first aspect, before the step of performing field splitting, translation matching, and translation reorganization on the field to be translated according to the target translation rule to obtain the matching translation corresponding to the field to be translated, the following steps are included:

[0011] The field to be translated is matched with a preset matching database to determine whether there is original text in the matching database that is the same as the field to be translated.

[0012] If it exists, the translation corresponding to the original text is retrieved from the matching database as the translation corresponding to the field to be translated.

[0013] In conjunction with the second possible implementation of the first aspect, in the third possible implementation of the first aspect, the step of obtaining the translation corresponding to the original text from the matching database as the translation matching the field to be translated includes:

[0014] Determine whether the field type of the original text is the same as the field type of the field to be translated;

[0015] If they are the same, the translation corresponding to the original text is obtained as the translation that matches the field to be translated.

[0016] If they are different, then determine whether the original text is the only original text in the matching database that is the same as the field to be translated. If it is the only original text in the matching database that is the same as the field to be translated, then obtain the translation corresponding to the original text as the translation corresponding to the field to be translated. Otherwise, process the field to be translated according to the target translation rule.

[0017] In conjunction with the second or third possible implementation of the first aspect, in the fourth possible implementation of the first aspect, the matching database includes a field database and a translation memory. After the step of obtaining the translation corresponding to the source text from the matching database as the translation matching the field to be translated, the method further includes:

[0018] Determine whether the original text is stored in the matching database in a memory location;

[0019] If so, the corresponding translation for the field to be translated will be marked as pending review and the translation will be sent to the reviewer for review and confirmation.

[0020] In conjunction with the second possible implementation of the first aspect, in the fifth possible implementation of the first aspect, before the step of performing source text matching processing between the field to be translated and a preset matching database, and determining whether there is source text identical to the field to be translated in the matching database, the following steps are included:

[0021] The text is split according to pre-built data splitting rules to divide the text into several fields to be translated.

[0022] In conjunction with the first aspect, in the sixth possible implementation of the first aspect, the step of performing field splitting, translation matching, and translation reorganization on the field to be translated according to the target translation rule to obtain the matching translation corresponding to the field to be translated includes:

[0023] Identify the punctuation marks contained in the field to be translated, and perform field splitting according to the punctuation marks; or

[0024] Identify the semantic type of the field to be translated, and perform field splitting according to the semantic type, wherein the semantic type includes enterprise registered address, enterprise name, enterprise production object or business scope, and enterprise nature; or

[0025] The fields to be translated are split according to administrative region level; or

[0026] Configure a data template for the field to be translated, and perform field splitting processing according to the data template.

[0027] A second aspect of this application provides a text translation control device, the text translation control device comprising:

[0028] The recognition module is used to identify the field type of the field to be translated in the text;

[0029] The matching module is used to obtain the target translation rule that matches the field to be translated from a preset field type-translation rule mapping table according to the field type;

[0030] The translation module is used to perform field splitting, translation matching, and translation reorganization on the field to be translated according to the target translation rules, so as to obtain the translation corresponding to the field to be translated.

[0031] A third aspect of this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the text translation control method as described in any of the first aspects.

[0032] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the text translation control method as described in any of the first aspects.

[0033] The beneficial effects of the embodiments in this application compared with the prior art are:

[0034] This application identifies the field type of the field to be translated in the text; based on the field type, it retrieves the target translation rule corresponding to the field to be translated from a preset field type-translation rule mapping table; and performs field splitting, translation matching, and translation reorganization on the field to be translated according to the target translation rule to obtain the translation corresponding to the field to be translated. By classifying the fields in the text and configuring corresponding translation rules for different field types, different translation rules are selected for automatic translation based on different field types, resulting in high efficiency, strong targeting, and effectively improving the accuracy of translation processing. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 A flowchart illustrating a text translation control method provided in the first embodiment of this application;

[0037] Figure 2 A flowchart illustrating a text translation control method provided in the second embodiment of this application;

[0038] Figure 3 A flowchart illustrating a text translation control method provided in the third embodiment of this application;

[0039] Figure 4 A flowchart illustrating a text translation control method provided in the fourth embodiment of this application;

[0040] Figure 5 A flowchart illustrating a text translation control method provided in the fifth embodiment of this application;

[0041] Figure 6 A schematic diagram of the structure of a text translation control device provided in the sixth embodiment of this application;

[0042] Figure 7 This is a schematic diagram of an electronic device that implements a text translation control method, as provided in the seventh embodiment of this application. Detailed Implementation

[0043] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0044] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0045] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0046] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0047] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0048] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0049] To illustrate the technical solution described in this application, specific embodiments are provided below.

[0050] In some embodiments of this application, please refer to Figure 1 , Figure 1 This is a flowchart illustrating a text translation control method provided in the first embodiment of this application. Details are as follows:

[0051] In step S101, the field type of the field to be translated in the text is identified.

[0052] In this embodiment, the translation requirements of the business system include Chinese-English translation. Taking Chinese-English translation as an example, and considering the product characteristics of the business system, the business text corresponding to the products in the business system is roughly divided into five field types based on field characteristics: person's name, company name, address, product abbreviation, and other content. In this embodiment, when performing translation operations on the business text, the field type of the field to be translated can be determined by identifying the field characteristics of the field to be translated in the business text.

[0053] In step S102, based on the field type, the target translation rule corresponding to the field to be translated is obtained from the preset field type-translation rule mapping table.

[0054] In this embodiment, based on the five major field types categorized according to field characteristics, corresponding translation rules are pre-constructed for each field type, forming a field type-translation rule mapping table. In this mapping table, each field type corresponds to one translation rule. Therefore, during translation operations, the target translation rule matching the field to be translated can be obtained from the field type-translation rule mapping table based on the field type to be translated. This allows for the selection of different translation rules based on the field type of different fields to be translated, enhancing the specificity of the translation method and improving the accuracy of text translation. In this embodiment, the translation rules include, but are not limited to, field splitting methods, translation matching methods, and translation recombination methods. Different field types have different field splitting methods, translation matching methods, and / or translation recombination methods configured in the constructed translation rules. In this embodiment, the translation rules configured for different field types may include, but are not limited to, the following:

[0055] The system identifies punctuation marks in the field to be translated and splits the field according to these marks. For example, for the "Character Name" field type, the field splitting method is configured to identify punctuation marks in the "Character Name" field and split the field to be translated according to these marks. The "Character Name" field type can be split into several corresponding words, and the corresponding translations can be obtained by translating these words into pinyin. After obtaining the translations, the words can be reorganized according to the original text structure to obtain the matching translations for the field to be translated. Furthermore, in this embodiment, for each word obtained from the splitting, the text can be traversed according to the original text of the word to identify all the original text data corresponding to that word. Then, during the translation operation, all the original text data corresponding to that word in the text can be batch-translated to fill in the matching translations. This method improves the translation efficiency of the "Character Name" field type.

[0056] The semantic type of the field to be translated is identified, and the field is split according to the semantic type. For example, the "Company Name" field type can be divided into four semantic types: company registration address, company name, company production object or business scope, and company nature. In this case, the field splitting method is configured to split the field according to the four semantic types contained in the company name field: company registration address, company name, company production object or business scope, and company nature. The field to be translated of the "Company Name" field type can be split into four words, one of which corresponds to one of the content parts mentioned above. When performing the translation operation, the translation matching method for each content part includes: First, the translation matching of the company registration address and company name is performed by transliteration (i.e., using Pinyin). Among them, the administrative division qualifiers in the company registration address (such as city, district, county, etc.) are generally not transliterated. When the company registration address contains place names in minority languages, they are spelled according to the preset transliteration method to obtain the company registration address. Secondly, by using a dictionary lookup method to write common and high-frequency words into a configuration file, and then reading and translating these words from the configuration file to match the translation of the content related to the company's production objects or business scope, for example, for an internet technology company, the configuration file format includes Chinese... <companycn>Network Technology< / companycn> And in English <companyen>Network Technology< / companyen> , <companycn>The system configures Chinese-language information about the enterprise's production targets or business scope. <companyen>The company name should be configured with English translations of its production objects or business scope. This information generally requires a direct translation. When the production objects or business scope contain two parallel components, "&" or "and" is used to connect them; when there are more than two parallel components, "," + "&" or "and" is used. A company name cannot contain two "&" or "and" characters. Third, for the section on company nature, there are generally fixed translation methods for matching the translated text. By pre-establishing a query list (as shown in Table 1), a mapping query can be used to look up Table 1, and the translation of the company nature can be matched based on the Chinese-English mapping relationship in Table 1. Table 1 is as follows:

[0057] Chinese English Chinese English Limited by Share Ltd. Co., Ltd. Company Company Limited Liability Company Co., Ltd. Head Office Corporation Limited Company Co., Ltd. Holding Company / Holdings Co., Ltd. Holdings Co., Ltd. Joint Stock Company Co., Ltd. Group Company / Group Co., Ltd. Group Co., Ltd.

[0058] Table 1

[0059] The fields to be translated are split according to administrative region levels. For example, the "address" field type is configured to be split according to administrative region levels. For instance, dividing the address into multiple levels such as province (autonomous region), city (autonomous prefecture / state / league), county (autonomous county / banner), and town can split the "address" field type to be translated into several corresponding words. During the translation operation, for the split words, the translations of the first two levels are matched according to the order of disclosure. In this embodiment, the address translation matching method includes, but is not limited to: if a province or city is included, only the translation of the province or city is matched; if a province is included but no city is included, only the translation of the city is matched; if the address starts with a county or town, only the translation of the county or town is matched.

[0060] Configure a data template for the field to be translated, and perform field splitting according to the data template. For example, for the "Product Abbreviation" field type, such as the names and abbreviations of financial products, bonds, and other highly similar data, the field splitting method is configured to obtain the data template corresponding to the "Product Abbreviation" field and split it according to the data template. During the translation operation, by comparing the string of the field to be translated ("Product Abbreviation") with the data template, several identical words and several different words can be obtained. Then, by obtaining the translation of the data template and splitting the translation according to the above-mentioned word splitting, and then replacing the translations corresponding to the different words, the matching translation for the "Product Abbreviation" field type is obtained.

[0061] The jieba word segmentation rule is used for field splitting. For example, the "Other Content" field type has no obvious field characteristics, so its field splitting method is configured to use the commonly used jieba word segmentation rule. After splitting, the translation is matched word by word, and then the translations of each word are connected in an orderly manner by combining the grammatical rules and the order of words to obtain the corresponding translation.

[0062] In step S103, the field to be translated is split, matched with the translation, and recombined with the translation according to the target translation rules to obtain the translation corresponding to the field to be translated.

[0063] In this embodiment, the field splitting method, translation matching method, and translation reorganization method configured in the translation rules are specifically configured according to the field type. After obtaining the corresponding target translation rule based on the field type of the field to be translated, the field to be translated is translated according to the field splitting method, translation matching method, and translation reorganization method specifically configured in the target translation rule, thereby obtaining the corresponding matched translation. For example, where:

[0064] For fields of type "person's name" to be translated, such as "Zhang San, Li Si", the processing steps include: splitting the field to obtain the words "Zhang San" and "Li Si", and then translating them using pinyin to obtain the translations of "Zhang San" as "Zhang san" and "Li Si" as "li si". In this embodiment, for fields of type "person's name" to be translated, after obtaining the translations, the original text can be traversed according to the word "Zhang San" to identify all instances of "Zhang San" in the text. Then, during the translation operation, all original data displaying "Zhang San" will be filled with "Zhang san", and the same applies to "Li Si", thereby achieving batch translation of person's names in the text and improving text translation efficiency.

[0065] For a field of type "Company Name" to be translated, such as "Changzhou Diwu Copper Co., Ltd.", the processing steps include: splitting the field to obtain four terms: Changzhou, Diwu, Copper, and Co., Ltd.; matching the term "Changzhou" to obtain "Changzhou", "Diwu" to obtain "Diwu", "Copper" to obtain "Copper", and "Co., Ltd." to obtain "Co., Ltd."; thus, the translation of the company name field to be translated is "Changzhou DiwuCopper Co., Ltd."

[0066] For fields to be translated that are of the "address" field type, such as "Wanxiang Road, Xiaoshan Economic and Technological Development Zone, Hangzhou City, Zhejiang Province", the processing of the fields to be translated includes: splitting the field to obtain four words: Zhejiang Province, Hangzhou City, Xiaoshan Economic and Technological Development Zone, and Wanxiang Road; and obtaining the translation matching method corresponding to the "address" field type, which is "Zhejiang (province)Hangzhou (city)".

[0067] For fields of the "Product Abbreviation" type, fields with high similarity are suitable for translation. For example, in the fields "Chongqing First Real Estate Development Co., Ltd.", "Chongqing Second Real Estate Development Co., Ltd.", "Chongqing Third Real Estate Development Co., Ltd.", and "Chongqing Fourth Real Estate Development Co., Ltd.", string comparison reveals that "Chongqing" and "Real Estate Development Co., Ltd." are the same, while "First", "Second", "Third", and "Fourth" are different. Using the translation rules constructed for the "Company Name" field type, the translation of one of the highly similar data points can be obtained as a data template. For example, using "Chongqing First Real Estate Development Co., Ltd." as the data template, its translation is "Chongqing Diyi Real Estate Development Co., Ltd.", which can be split into three parts: "Chongqing", "Diyi", and "Real Estate Development Co., Ltd." The other data points with high similarity to the template can be translated by replacing the word "First" with "Diyi".

[0068] The text translation control method provided in the above embodiments automatically translates text by dividing it into field types and configuring different translation rules for different field types. This method is highly efficient, targeted, and effectively improves the accuracy of translation processing.

[0069] In some embodiments of this application, the translation obtained by matching the target translation rule to the field to be translated and processing it according to the target translation rule will be marked as pending review and sent to the review end for manual review and confirmation to ensure the accuracy of the translation.

[0070] In some embodiments of this application, please refer to Figure 2 , Figure 2 A flowchart illustrating a text translation control method provided in the second embodiment of this application is shown below. Details are as follows:

[0071] Step S201: Perform original text matching processing on the field to be translated and the preset matching database to determine whether there is original text in the matching database that is the same as the field to be translated;

[0072] Step S202: If it exists, then retrieve the translation corresponding to the original text from the matching database as the translation corresponding to the field to be translated.

[0073] In this embodiment, a dictionary and / or translation memory, consisting of source text and translated text, is constructed based on the product characteristics of the business system as a matching database for the text translation control method. The source and translated texts stored in the dictionary have been screened and confirmed as accurate translations. The source and translated texts stored in the translation memory are saved through automatic or manual translation, and their accuracy is lower than that of the dictionary. In this embodiment, based on this matching database, the field to be translated can be matched with the matching database, and then the corresponding translation can be obtained from the matching database based on the matching result. The source and translated text data in the matching database are also stored according to field type. For example, corresponding data tables are configured for five field types: person name, company name, address, product abbreviation, and other content. The source and translated texts in the data tables are mapped and associated. Based on this, in this embodiment, when performing source text matching processing between the field to be translated and the matching database, the data table corresponding to the field type of the field to be translated can be found in the matching database for query matching. If the source text that completely matches the field to be translated can be found in the data table, the translation corresponding to the source text can be directly obtained as the translation corresponding to the field to be translated. There is no need to translate each field to be translated in the text using the target translation rule, which effectively improves the translation efficiency of the text translation process.

[0074] In some embodiments of this application, please refer to Figure 3 , Figure 3 This is a flowchart illustrating a text translation control method provided in the third embodiment of this application. Details are as follows:

[0075] Step S301: Determine whether the field type of the original text is the same as the field type of the field to be translated;

[0076] Step S302: If they are the same, then obtain the translation corresponding to the original text as the translation that matches the field to be translated;

[0077] Step S303: If they are different, determine whether the original text is the only original text in the matching database that is the same as the field to be translated. If it is the only original text in the matching database that is the same as the field to be translated, obtain the translation corresponding to the original text as the translation corresponding to the field to be translated. Otherwise, process the field to be translated according to the target translation rule.

[0078] In this embodiment, when performing source text matching between the field to be translated and the matching database, the following special case may occur: A source text that completely matches the field to be translated can be found in the matching database, but the field type of the source text may be different from that of the field to be translated. In this case, after determining that a source text identical to the field to be translated exists in the matching database, further judgment is made to determine whether the field type of the source text is the same as that of the field to be translated. The field type of the source text obtained from the matching database can be determined based on the data table where it is stored. If the field types of both are the same, it means that the scenarios described in the texts are consistent. In this case, the translation corresponding to the source text can be directly obtained as the translation matching the field to be translated. If the two fields belong to different types, it means that the scenarios they describe in the text may differ. In this case, it can be further determined whether the original text is the only original text in the matching database that is the same as the field to be translated. If so, the translation corresponding to the original text can be obtained as the translation corresponding to the field to be translated. If it is not the only original text, it means that the translation control method may not be able to determine the scenario described by the field to be translated. In this case, the translation control method can process the field to be translated according to the target translation rules.

[0079] In some embodiments of this application, please refer to Figure 4 , Figure 4 This is a flowchart illustrating a text translation control method provided in the fourth embodiment of this application. Details are as follows:

[0080] Step S401: Determine whether the storage location of the original text in the matching database is a memory;

[0081] Step S402: If yes, mark the translation corresponding to the field to be translated as pending review and send the translation to the review end for review and confirmation.

[0082] In this embodiment, the matching database includes a field library and a translation memory. The dictionary library stores source and translation texts that have been screened and confirmed for accurate translation. The translation memory stores source and translation texts saved through automatic or manual translation, and its accuracy is lower than that of the dictionary library. In this embodiment, by identifying the storage location of source text in the matching database that matches the field to be translated, it can be determined whether the storage location of that source text in the matching database is the translation memory. If it is the translation memory, it indicates that the translation corresponding to the field to be translated needs confirmation. In this case, it can be marked as pending review and the translation can be sent to the review end for manual review and confirmation to ensure the accuracy of the translation.

[0083] In some embodiments of this application, please refer to Figure 5 , Figure 5 This is a flowchart illustrating a text translation control method provided in the fifth embodiment of this application. Figure 5 As shown in this embodiment, when performing original text matching processing between the field to be translated and the preset matching database, the specific execution flow includes the following:

[0084] Step S501: Compare the field to be translated with the original text stored in the dictionary.

[0085] Step S502: Determine whether the original text stored in the dictionary matches the field to be translated one-to-one. If yes, proceed to step S503; otherwise, proceed to step S504.

[0086] Step S503: Determine whether the field type of the original text in the dictionary that matches the field to be translated one-to-one is the same as the field type of the field to be translated. If so, obtain the translation corresponding to the original text as the translation of the field to be translated and mark the translation as reviewed. Otherwise, obtain the translation corresponding to the original text as the translation of the field to be translated and mark the translation as pending review. In this embodiment, the translation of the field to be translated is filled in the translation text. The unreviewed and pending review status of the translation can also be displayed in the translation text generated by this translation operation to remind relevant translators to conduct manual review.

[0087] Step S504: Determine whether the original text stored in the dictionary is a one-to-many match with the field to be translated. If yes, proceed to step S505; otherwise, proceed to step S506.

[0088] Step S505: Obtain the latest stored original text from the multiple original texts that match the field to be translated in the dictionary, and use the translation corresponding to the latest stored original text as the translation of the field to be translated, and mark the translation as pending review.

[0089] Step S506: The field to be translated is split, matched with the target translation, and recombined according to the target translation rules. If a recombined translation can be generated, the recombined translation is used as the translation of the field to be translated and the translation is marked as pending review. Otherwise, proceed to step S507.

[0090] Step S507: Compare the field to be translated with the original text stored in the translation memory.

[0091] Step S508: Determine whether the original text stored in the memory bank matches the field to be translated one-to-one. If yes, proceed to step S509; otherwise, proceed to step S510.

[0092] Step S509: If yes, then obtain the translation corresponding to the original text as the translation of the field to be translated and mark the translation as unreviewed. In this embodiment, the translation of the field to be translated is filled in the translation text. The unreviewed and pending-review status of the translation can also be displayed in the translation text generated by this translation operation, reminding relevant translators to conduct manual review.

[0093] Step S510: Determine whether the original text stored in the memory bank matches the field to be translated in a one-to-many manner. If yes, proceed to step S511; otherwise, proceed to step S512.

[0094] Step S511: Obtain the latest stored original text from the multiple original texts that match the field to be translated in the memory, and use the translation corresponding to the latest stored original text as the translation of the field to be translated, and mark the translation as pending review.

[0095] Step S512: The field to be translated is split, matched with the target translation, and recombined according to the target translation rules. If the split, matched, and recombined translation can generate a recombined translation, the recombined translation is used as the translation of the field to be translated and the translation is marked as pending review. Otherwise, the manual translation process begins.

[0096] In some embodiments of this application, a data splitting rule is pre-constructed to split the text to be translated before translation control, thereby splitting the text into several fields that can be translated by the translation control method. In this embodiment, the data splitting rule first performs format standardization preprocessing on the text to be translated. Format standardization preprocessing includes removing spaces and line breaks from the text. Specific removal methods include, but are not limited to: for text consisting entirely of Chinese characters plus punctuation, removing all spaces and line breaks; and for text that is not entirely in Chinese, removing only leading and trailing spaces and all line breaks. Additionally, format standardization preprocessing also includes changing punctuation marks from Chinese to English. After format standardization preprocessing, a splitting condition list is invoked, and the text is traversed according to this list to split the text into several fields that meet the conditions for translation. In this embodiment, the splitting conditions listed in the splitting condition list include, but are not limited to: splitting when the text contains Chinese data; splitting when the text contains serial numbers and begins with a serial number, such as when it belongs to one of the following cases: single number + comma + Chinese character, single number + pause + Chinese character, single number + dot + Chinese character, single number + space + Chinese character, etc.; when the text contains numbers but the numbers only exist in parentheses; when the text contains one of the following cases: number + ETF, number + life cycle, CSI 300, SSE + number, CSI + number, wealth management + number, etc., etc. In this embodiment, the data splitting rules also include one or more of the following splitting rules:

[0097] The text is split according to the serial number, period, semicolon, comma, and pause mark as identifiers;

[0098] For text containing only a single identifier, split the text directly according to the identifier;

[0099] For text containing multiple identifiers, the text is split according to only one identifier, with the following priority: serial number, period, semicolon, comma, and pause mark;

[0100] In text containing "Co., Limited", the punctuation marks between "Co., Ltd." are not treated as identifiers.

[0101] In text containing "LTD", the first dot or comma before or after "LTD" is not used as an identifier split (three forms: LTD, Ltd, ltd);

[0102] In text containing "Limited", the comma before "Limited" is not used as an identifier for splitting;

[0103] In text containing "Corp", punctuation marks before or after "Corp" are not treated as identifiers for splitting.

[0104] In text containing "Co., Limited", the punctuation marks between "Co., Limited" are not treated as identifiers for splitting.

[0105] In text containing "LLC", the punctuation mark before "LLC" is not treated as an identifier split;

[0106] In text containing "Inc.", the punctuation mark before Inc. is not treated as an identifier for splitting;

[0107] In text containing "LP", the punctuation mark before "LP" is not treated as an identifier for splitting;

[0108] Text in the format of "letters + punctuation marks + Chinese characters" is treated as a whole and not broken down.

[0109] Text consisting of letters and punctuation marks is treated as a whole and not broken down.

[0110] Punctuation marks within parentheses in text are not split as identifiers.

[0111] In the text, the punctuation marks in the middle of combinations are not split as identifiers. Combinations include but are not limited to: Chinese numerals + punctuation marks + Chinese numerals, "the" + Chinese numerals + punctuation marks, "the" + Chinese numerals + "session" + punctuation marks + "the" + Chinese numerals, Chinese numerals + "session" + punctuation marks + Chinese numerals, Chinese numerals + "issue" + punctuation marks + Chinese numerals, Chinese numerals + "number" + punctuation marks + Chinese numerals, Chinese numerals + "building" + punctuation marks + Chinese numerals, Chinese numerals + "floor" + punctuation marks + Chinese numerals, Chinese numerals + "area" + punctuation marks + Chinese numerals, Chinese numerals + "layer" + punctuation marks + Chinese numerals, Chinese numerals + "village" + punctuation marks + Chinese numerals, Chinese numerals + "construction" + punctuation marks + Chinese numerals, Chinese numerals + "society" + punctuation marks + Chinese numerals, Chinese numerals + "group" + punctuation marks + Chinese numerals, Chinese numerals + "street" + punctuation marks + Chinese numerals, etc.;

[0112] When the text contains numbers, commas and decimal points between the numbers are not used as identifiers to separate them.

[0113] It is understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0114] In some embodiments of this application, please refer to Figure 6 , Figure 6 A schematic diagram of a text translation control device provided in the sixth embodiment of this application is described in detail below:

[0115] In this embodiment, the text translation control device includes: an identification module 601, a matching module 602, and a translation module 603. The identification module 601 identifies the field type of the field to be translated in the text. The matching module 602 retrieves a target translation rule corresponding to the field to be translated from a preset field type-translation rule mapping table based on the field type. The translation module 603 performs field splitting, translation matching, and translation recombination on the field to be translated according to the target translation rule to obtain a translation corresponding to the field to be translated.

[0116] The text translation control device corresponds one-to-one with the text translation control method described above, and will not be repeated here.

[0117] In some embodiments of this application, please refer to Figure 7 , Figure 7 This is a schematic diagram of an electronic device implementing a text translation control method, as provided in the seventh embodiment of this application. Figure 7 As shown, the electronic device 7 of this embodiment includes: a processor 71, a memory 72, and a computer program 73 stored in the memory 72 and executable on the processor 71, such as a translation control program. When the processor 71 executes the computer program 72, it implements the steps in the above-described text translation control method embodiments. Alternatively, when the processor 71 executes the computer program 73, it implements the functions of each module / unit in the above-described device embodiments.

[0118] For example, the computer program 73 can be divided into one or more modules / units, which are stored in the memory 72 and executed by the processor 71 to complete this application. The one or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 73 in the electronic device 7. For example, the computer program 73 can be divided into:

[0119] The recognition module is used to identify the field type of the field to be translated in the text;

[0120] The matching module is used to obtain the target translation rule that matches the field to be translated from a preset field type-translation rule mapping table according to the field type;

[0121] The translation module is used to perform field splitting, translation matching, and translation reorganization on the field to be translated according to the target translation rules, so as to obtain the translation corresponding to the field to be translated.

[0122] The electronic device may include, but is not limited to, a processor 71 and a memory 72. Those skilled in the art will understand that... Figure 7 This is merely an example of electronic device 7 and does not constitute a limitation on electronic device 7. It may include more or fewer components than shown, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0123] The processor 71 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0124] The memory 72 can be an internal storage unit of the electronic device 7, such as a hard disk or memory. The memory 72 can also be an external storage device of the electronic device 7, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. Furthermore, the memory 72 can include both internal and external storage units of the electronic device 7. The memory 72 is used to store the computer program and other programs and data required by the electronic device. The memory 72 can also be used to temporarily store data that has been output or will be output.

[0125] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0126] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0127] This application provides a computer program product that, when run on a mobile terminal, enables the mobile terminal to implement the steps described in the above-described method embodiments.

[0128] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0129] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0130] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0131] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0132] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0133] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0134] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.< / companyen> < / companycn>

Claims

1. A translation control method of a text, characterized by, The application comprises the following steps: Identify the field type to which the field to be translated in the business text belongs through the field characteristics of the field to be translated in the business text; The field type is selected from one of the following: person name, enterprise name, address, product abbreviation, and other content, and the field characteristics are the semantic properties of the field to be translated in the business scenario; According to the field type, obtain the target translation rule corresponding to the field to be translated from the pre-set field type-translation rule mapping relationship table; According to the target translation rule, perform field splitting, translation matching, and translation reorganization processing on the field to be translated to obtain the matching translation corresponding to the field to be translated; The translation rule includes field splitting method, translation matching method, and translation reorganization method. Different field types have different field splitting methods, translation matching methods, and / or translation reorganization methods in the constructed translation rule. The person name field is split by punctuation and matched with pinyin translation. The enterprise name field is split by semantic type and matched with transliteration, dictionary matching, or fixed mapping. The address field is split by administrative region level and matched with hierarchical translation. The product abbreviation field is split by a pre-set data template and matched with template replacement. Before the step of performing field splitting, translation matching, and translation reorganization processing on the field to be translated according to the target translation rule to obtain the matching translation corresponding to the field to be translated, the following steps are included: Match the field to be translated with the pre-set matching database to determine whether there is the same original text in the matching database as the field to be translated; If not, perform field splitting, translation matching, and translation reorganization processing on the field to be translated according to the target translation rule to obtain the matching translation corresponding to the field to be translated; The matching database includes a field library storing accurate translation data and a memory library storing automatic / human translation data.

2. The translation control method of text according to claim 1, characterized in that, After the step of performing field splitting, translation matching, and translation reorganization processing on the field to be translated according to the target translation rule to obtain the matching translation corresponding to the field to be translated, the following steps are included: Mark the obtained matching translation corresponding to the field to be translated as a to-be-audited state and send the translation to the audit end for audit confirmation.

3. The translation control method of text according to claim 1, characterized in that, If so, obtain the translation corresponding to the original text from the matching database as the matching translation corresponding to the field to be translated.

4. The translation control method of text according to claim 3, characterized in that, The step of obtaining the translation corresponding to the original text from the matching database as the matching translation corresponding to the field to be translated includes: Determine whether the field type to which the original text belongs is the same as the field type to which the field to be translated belongs; If so, obtain the translation corresponding to the original text as the matching translation corresponding to the field to be translated; If not, it is determined whether the original text is the only original text in the matching database that is identical to the field to be translated. If so, the translation corresponding to the original text is obtained as the matching translation of the field to be translated. Otherwise, the field to be translated is processed according to the target translation rule.

5. The translation control method of text according to claim 3 or 4, characterized in that, After the step of obtaining the translation corresponding to the original text from the matching database as the matching translation of the field to be translated, the method further comprises: determining whether the storage location of the original text in the matching database is a memory bank; If so, the matching translation of the field to be translated is marked as a to-be-audited state and sent to an auditing end for auditing and confirmation.

6. The translation control method of text according to claim 3, characterized in that, Before the step of performing original text matching processing on the field to be translated with a preset matching database to determine whether there is an original text identical to the field to be translated in the matching database, the method comprises: According to the pre-constructed data splitting rule, the text is split to split the text into a plurality of fields to be translated.

7. The translation control method of text according to claim 1, characterized by, In the step of performing field splitting, translation matching and translation recombination processing on the field to be translated according to the target translation rule to obtain the matching translation of the field to be translated, the field splitting processing comprises: identifying the punctuation contained in the field to be translated and performing field splitting processing according to the punctuation; or identifying the semantic type of the field to be translated and performing field splitting processing according to the semantic type, wherein the semantic type includes enterprise registration address, enterprise name, enterprise production object or business scope, and enterprise nature; or performing field splitting processing on the field to be translated according to the administrative region level; or configuring a data template for the field to be translated and performing field splitting processing according to the data template.

8. A translation control apparatus for text, characterized by, The text translation control device comprises: an identification module configured to identify the field type to which the field to be translated in the business text belongs through the field characteristics of the field to be translated in the business text, wherein the field type is selected from one of a person's name, an enterprise's name, an address, a product's abbreviation, and other content, and the field characteristics are semantic attributes of the field to be translated in a business scenario; a matching module configured to obtain a target translation rule corresponding to the field to be translated from a preset field type-translation rule mapping relationship table according to the field type; a translation module configured to perform field splitting, translation matching and translation recombination processing on the field to be translated according to the target translation rule to obtain the matching translation of the field to be translated. The translation rules include a field splitting mode, a translation matching mode, and a translation recombination mode, different field types correspond to different field splitting modes, translation matching modes, and / or translation recombination modes configured in the constructed translation rules, a person name field is split according to punctuation and matched with a pinyin translation, an enterprise name field is split according to semantic types and matched with a transliteration, dictionary matching, or fixed mapping, an address field is split according to administrative region levels and matched with a hierarchical translation, and a product abbreviation field is split according to a preset data template and matched with a template replacement mode; The translation module is further configured to, before processing the to-be-translated field according to the target translation rule to split the to-be-translated field, match a translation, and recombine a translation to obtain a matched translation corresponding to the to-be-translated field, perform original text matching processing on the to-be-translated field and a preset matching database, and determine whether the matching database contains the same original text as the to-be-translated field; if not, processing the to-be-translated field according to the target translation rule to split the to-be-translated field, match a translation, and recombine a translation to obtain a matched translation corresponding to the to-be-translated field; The matching database includes a field library storing accurate translation data and a memory library storing automatic / human translation data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The computer program is executed by the processor to implement the steps of the text translation control method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to implement the steps of the text translation control method according to any one of claims 1 to 7.

Images