Text translation method, electronic device, storage medium and computer program product

Abstract

The invention discloses a text translation method, electronic equipment, a storage medium and a computer program product, and relates to the technical field of text translations, and the text translation method comprises the following steps: identifying an original house resource information text in a house resource information picture; segmenting the original house resource information text to obtain a text field, and translating the text field into a target language through a first preset large model to obtain a first translation field; detecting whether the first translation field accords with a use scene of a target language or not through a second preset large model to obtain a translation guidance opinion, and correcting the text field based on the translation guidance opinion to obtain a second translation field; and obtaining the target housing resource information text according to the second translation field. The technical problem of poor translation accuracy is solved.

Claims

1. A text translation method, characterized in that: The text translation method comprises: Identify the original listing information text in the listing information image; The original house source information text is segmented to obtain text fields, and the text fields are translated into a target language using a first preset large model to obtain a first translation field; Using a second preset large model to detect whether the first translation field conforms to the usage scenario of the target language, obtaining translation guidance, and modifying the text field based on the translation guidance to obtain a second translation field; The target property information text is obtained according to the second translation field.

2. The text translation method according to claim 1, characterized in that: The step of identifying the original house information text in the house information picture comprises: Detecting a text block in the house information picture and determining a layout rule of the text block; The text content in the text block is extracted by optical character recognition technology, and the logical order of the text content is adjusted in combination with the typesetting rules to obtain the original house information text.

3. The text translation method according to claim 1, characterized in that: The usage scenario of the target language includes a katakana translation index, a sentence structure translation index, and a unit translation index, the translation guidance includes a first translation guidance, and the step of detecting whether the first translation field conforms to the usage scenario of the target language by using a second preset large model to obtain the translation guidance includes: When the second preset large model recognizes that the translation of the katakana in the text field by the first translation field is not a transliteration or a corresponding translation in the target language, determining that the first translation field does not meet the katakana translation index, and generating a katakana translation difference of the first translation field; Identify the sentence structure of the first translation field by using the second preset large model, and if a component of the sentence structure is missing and affects the meaning of the first translation field, determine that the first translation field does not meet the sentence structure translation index, and generate a sentence structure translation difference of the first translation field; When the second preset large model identifies that the translation of the unit in the text field by the first translation field does not conform to the corresponding unit in the target language, determining that the first translation field does not conform to the unit translation index, and generating a unit translation difference of the first translation field; The first translation guidance is obtained by combining the Katakana translation difference, the sentence structure translation difference and the unit translation difference.

4. The text translation method according to claim 1, characterized in that: The target language usage scenario further includes an expression translation index, a semantic translation index, and a logical translation index, the translation guidance also includes a second translation guidance, and the step of detecting whether the first translation field conforms to the target language usage scenario through the second preset large model and obtaining the translation guidance also includes: When the second preset large model identifies that the expression of the first translation field does not conform to the polite expression of the target language, determining that the first translation field does not conform to the expression translation index, and generating an expression translation difference of the first translation field; When the second preset large model identifies whether the translation of the idiom or phrase in the text field by the first translation field conforms to the corresponding semantic expression of the target language, it is determined that the first translation field does not conform to the semantic translation index, and a semantic translation difference of the first translation field is generated; When the second preset large model identifies that the word order of the first translation field is disordered or the meaning of the sentence is unclear, it is determined that the first translation field does not meet the logical translation index, and a logical translation difference of the first translation field is generated; The second translation guidance is obtained by combining the expression translation difference, the semantic translation difference and the logical translation difference.

5. The text translation method according to claim 1, characterized in that: The target language usage scenario further includes a proper noun translation index, a housing source information translation index, and a housing structure translation index, the translation guidance also includes a third translation guidance, and the step of detecting whether the first translation field conforms to the target language usage scenario through the second preset large model and obtaining the translation guidance also includes: When the second preset large model identifies that the translation of the proper noun in the text field by the first translation field does not meet the standard expression of proper nouns in the real estate field, it is determined that the first translation field does not meet the proper noun translation index, and a proper noun translation difference of the first translation field is generated; When the second preset large model identifies that the translation of the housing source information in the text field by the first translation field does not conform to the standard expression of information in the real estate field, it is determined that the first translation field does not conform to the housing source information translation index, and a housing source information translation difference of the first translation field is generated; When the second preset large model identifies that the translation of the apartment structure in the text field by the first translation field does not conform to the standard description of the apartment structure in the real estate field, it is determined that the first translation field does not conform to the apartment structure translation index, and a translation difference of the apartment structure of the first translation field is generated; A third translation guidance opinion is obtained by combining the proper noun translation difference, the housing source information translation difference and the apartment structure translation difference.

6. The text translation method according to claim 1, characterized in that: The step of obtaining the target property information text according to the second translation field comprises: Integrate the second translation field into a translation text; The corresponding part of the original housing information text in the translated text is adjusted according to the preset field dictionary.

7. The text translation method according to claim 6, characterized in that: The step of adjusting the corresponding part of the original house information text in the translated text according to the preset field dictionary comprises: Extracting system fields from the original property information text; A match is performed in a preset field dictionary based on the system field to obtain a standard translation field corresponding to the system field, and a portion of the system field corresponding to the translation text is replaced with the standard translation field.

8. An electronic device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the text translation method according to any one of claims 1 to 7.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the text translation method according to any one of claims 1 to 7 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the text translation method according to any one of claims 1 to 7 are implemented.

Images