WO2022161307A1

WO2022161307A1 - Text translation method and apparatus, and device and medium

Info

Publication number: WO2022161307A1
Application number: PCT/CN2022/073454
Authority: WO
Inventors: 张凯
Original assignee: 维沃移动通信有限公司
Priority date: 2021-01-27
Filing date: 2022-01-24
Publication date: 2022-08-04
Also published as: CN112766005A

Abstract

A text translation method and apparatus, and a device and a medium, which belong to the technical field of electronic devices. The text translation method comprises: acquiring text information to be translated (S101); determining, according to a preset database corresponding to a session to which the text information to be translated belongs, first text information in the text information to be translated (S102); and translating the text information to be translated, so as to obtain first translated text information corresponding to the text information to be translated, and replacing second translated text information, corresponding to the first text information, in the first translated text information with the first text information, so as to obtain target translated text information (S103); or translating second text information other than the first text information in the text information to be translated, so as to obtain third translated text information corresponding to the second text information, and combining the third translated text information and the first text information, so as to obtain target translated text information (S104).

Description

Text translation method, device, equipment and medium

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to Chinese Patent Application No. 202110112331.4 filed in China on Jan. 27, 2021, the entire contents of which are hereby incorporated by reference.

technical field

The present application belongs to the technical field of electronic devices, and in particular relates to a text translation method, device, device and medium.

Background technique

With the continuous improvement and maturity of Neural Machine Translation (NMT) technology, the threshold for cross-language communication has also been lowered, and more and more people are using Native language combined with machine translation for real-time communication with multinational friends.

In the related art, each word in a sentence is translated, and then the translation result corresponding to the sentence is displayed.

However, in the process of realizing this application, the inventor found that there are at least the following problems in the related art: in some cases, if the whole sentence is translated as a whole, the translation result corresponding to the sentence will be inaccurate, and then the display When the translation result corresponding to this sentence is used, it will cause user misunderstanding and affect user experience.

SUMMARY OF THE INVENTION

The purpose of the embodiments of the present application is to provide a text translation method, apparatus, device and medium, which can solve the problem of inaccurate sentence translation.

In order to solve the above technical problems, this application is implemented as follows:

In a first aspect, an embodiment of the present application provides a text translation method, including:

Get the text information to be translated;

determining the first text information in the text information to be translated according to a preset database corresponding to the session to which the text information to be translated belongs;

Translate the text information to be translated, obtain the first translation text information corresponding to the text information to be translated, and replace the second translation text information corresponding to the first text information in the first translation text information with the first text information to obtain the target translation text information; or,

Translate the second text information except the first text information in the text information to be translated, obtain the third translation text information corresponding to the second text information, combine the third translation text information and the first text information, and obtain the target translation text information .

In a second aspect, an embodiment of the present application provides a text translation device, including:

The first acquisition module is used to acquire the text information to be translated;

a first determining module, configured to determine first text information in the text information to be translated according to a preset database corresponding to the session to which the text information to be translated belongs;

A translation module, configured to translate the text information to be translated, obtain first translated text information corresponding to the text information to be translated, and replace the second translated text information corresponding to the first text information in the first translated text information with the first text information , obtain the target translation text information; or, translate the second text information except the first text information in the to-be-translated text information, obtain the third translation text information corresponding to the second text information, and combine the third translation text information and the third translation text information. a text information, and obtain the target translation text information.

In a third aspect, an embodiment of the present application provides an electronic device, the electronic device includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the Steps of the text translation method of the first aspect.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, where programs or instructions are stored on the computer-readable storage medium, and when the programs or instructions are executed by a processor, the steps of the text translation method of the first aspect are implemented.

In a fifth aspect, an embodiment of the present application provides a chip, where the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or instruction to implement the steps of the text translation method of the first aspect.

In the embodiment of the present application, after acquiring the text information to be translated, the first text information in the text information to be translated is determined according to the preset database corresponding to the session to which the text information to be translated belongs, and then the text information to be translated is translated, Obtain the first translated text information corresponding to the text information to be translated, and replace the second translated text information corresponding to the first text information in the first translated text information with the first text information to obtain the target translated text information; or, the text to be translated The second text information other than the first text information in the information is translated to obtain third translated text information corresponding to the second text information, and the third translated text information and the first text information are combined to obtain the target translated text information. That is, the target translated text information includes the first text information in the text information to be translated and the translated text information corresponding to the second text information other than the first text information in the text information to be translated. In the case where the first text information in the text information to be translated does not need to be translated, the target translation text information presents the effect that the first text information in the text information to be translated is not translated, so the accuracy of the translation of the text information can be improved .

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings that need to be used in the embodiments of the present application. For those of ordinary skill in the art, without creative work, the Additional drawings can be obtained from these drawings.

1 is a schematic flowchart of a text translation method provided by an embodiment of the present application;

2 is a schematic diagram of a session interface provided by an embodiment of the present application;

3 is a schematic diagram of displaying target translation text information provided by an embodiment of the present application;

4 is a schematic structural diagram of a text translation device provided by an embodiment of the present application;

5 is a schematic structural diagram of an electronic device provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of a hardware structure of an electronic device implementing an embodiment of the present application.

Detailed ways

The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, but not to limit the present application. It will be apparent to those skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present application by illustrating examples of the present application.

It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any relationship between these entities or operations. any such actual relationship or sequence exists. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device that includes a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element defined by the phrase "comprises" does not preclude the presence of additional identical elements in a process, method, article, or device that includes the element.

The text translation method, apparatus, device, and medium provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings through specific embodiments and application scenarios thereof.

FIG. 1 is a schematic flowchart of a text translation method provided by an embodiment of the present application. As shown in Figure 1, the text translation method can include:

S101: Obtain the text information to be translated;

S102: Determine first text information in the text information to be translated according to a preset database corresponding to the session to which the text information to be translated belongs;

S103: Translate the text information to be translated, obtain first translated text information corresponding to the text information to be translated, and replace the second translated text information corresponding to the first text information in the first translated text information with the first text information to obtain the target translate text messages;

S104: Translate the second text information except the first text information in the text information to be translated, obtain third translation text information corresponding to the second text information, and combine the third translation text information and the first text information to obtain the target translation text information.

The specific implementation of the above steps will be described in detail below.

In some possible implementations of the embodiments of the present application, the session in S102 may be a group chat session in which multiple people chat. As shown in FIG. 2 , FIG. 2 is a schematic diagram of a session interface provided by an embodiment of the present application. Among them, the name of the session shown in Figure 2 is "discussion group about mask", and the session shown in Figure 2 includes: the text information "whole word mask is not support in chinese" input by user H, the text input by user A The information "Can you support Chinese full-character masks in the future?" and the text information entered by user G "Yes, Chinese mask support is still necessary".

Exemplarily, it is assumed that the text information to be translated is "whole word mask is not support in chinese" in FIG. 2 . According to the preset database corresponding to the session "discussion group about mask" shown in Figure 2, it is determined that the first text information in the text information to be translated "whole word mask is not support in chinese" is "mask".

In some possible implementations of the embodiments of the present application, the preset database corresponding to the conversation in S102 may be a database including text information in multiple languages. It can be understood that, at this time, text information of multiple languages is stored in a database.

In some possible implementations of the embodiments of the present application, the preset database corresponding to the session in S102 may include multiple databases, wherein each of the multiple databases corresponds to a language, and each of the multiple databases corresponds to a language. The text information of the language corresponding to the database is stored.

In S103, translate "whole word mask is not support in chinese", and obtain the first translated text information "do not support Chinese full-word mask" corresponding to "whole word mask is not support in chinese". Wherein, the second translation text information corresponding to "mask" in "do not support Chinese full-character mask" is "mask". Replace "mask" in "do not support Chinese full-character mask" with "mask" to get the target translation text information "do not support Chinese full-character mask".

In S104, the second text information other than "mask" in "whole word mask is not support in chinese" includes "whole", "word", "is", "not", "support", "in" and "chinese". Translate the second text information to obtain translated text information corresponding to "whole", "word", "is", "not", "support", "in" and "chinese" included in the second text information: " All; Complete", "Word", "Yes", "No", "Support", "Zai" and "Chinese; Chinese". Combine "full; complete", "character", "yes", "no", "support", "zai" and "Chinese; Chinese" with "mask" to get the target translation text information "Chinese is not supported Whole word mask".

Displaying target translation text information is shown in FIG. 3 , which is a schematic diagram of displaying translated text information provided by an embodiment of the present application.

In some possible implementations of the embodiments of the present application, the preset database in S102 may include at least one piece of text information. S102 may include: determining the text information in the text information to be translated that matches the text information in the preset database as the first text information.

Exemplarily, it is assumed that the text information included in the preset database is "mask", "bert" and "trans".

For the above text information to be translated "whole word mask is not support in chinese", "mask" in "whole word mask is not support in chinese" matches the text information in the preset database, then "mask" is determined as The above-mentioned first text information.

In some possible implementations of the embodiments of the present application, the preset database in S102 may include at least one piece of text information and a weight corresponding to each text information. S102 may include: determining the text information that matches the text information in the preset database in the text information to be translated, and whose weight is greater than the preset threshold, as the first text information.

Exemplarily, it is assumed that the text information included in the preset database includes "mask", "bert" and "trans", wherein the corresponding weights of "mask", "bert" and "trans" are 95, 10 and 2, respectively. Set the threshold to 30. For the above-mentioned text information to be translated "whole word mask is not support in Chinese", "mask" in "whole word mask is not support in Chinese" is determined as the above-mentioned first text information.

In some possible implementations of the embodiments of the present application, the weight corresponding to each text information included in the preset database may be the number of times the text information appears in the session corresponding to the preset database.

In some possible implementations of the embodiments of the present application, before S102, the text translation method provided by the embodiments of the present application may further include: acquiring target text information other than the text information to be translated in the session to which the text information to be translated belongs; determining the target The second language to which the text information belongs; the third text information that does not correspond to the second language in the target text information is identified; a preset database is constructed according to the third text information.

Illustratively, take the text information in the conversation shown in FIG. 2 as an example, "Can the Chinese full-character mask be supported in the future?" "Can it support Chinese full-character masks in the future" includes Chinese characters and English words, and the number of Chinese characters is more than the number of English words, then determine the language of "Can it support Chinese full-character masks in the future?" Can you support Chinese full-character mask in the future?" The third text information that does not correspond to Chinese is "mask". Then, according to the "mask", a preset database corresponding to the session shown in FIG. 2 is constructed.

Specifically, when there is no preset database for the session shown in FIG. 2 , a preset database corresponding to the session shown in FIG. 2 is first created, and then “mask” is added to the preset database corresponding to the session shown in FIG. 2 . , and assign the weight corresponding to "mask" to 1.

When the session shown in FIG. 2 has its corresponding preset database, the weight corresponding to "mask" in the preset database is increased by 1.

Exemplarily, the preset database corresponding to the session shown in FIG. 2 is shown in Table 1.

Table 1

文本信息text message	权重Weights
maskmask	3434
bertbert	5050

In some possible implementations of the embodiments of the present application, after the preset database is constructed according to the third text information, the text translation method provided by the embodiments of the present application may further include: acquiring a target database, where the target database is the same as the text to be translated The database corresponding to the target session whose domain similarity of the session to which the information belongs is greater than the preset threshold; and the preset database is updated according to the target database.

Exemplarily, the obtained target database corresponding to the target session whose domain similarity shown in FIG. 2 belongs to the session is greater than the preset threshold is shown in Table 2.

Table 2

文本信息text message	权重Weights
maskmask	6060
transtrans	4040

The above Table 1 is updated according to the above Table 2, and the updated preset database corresponding to the session shown in FIG. 2 is obtained, as shown in Table 3.

table 3

文本信息text message	权重Weights
maskmask	9494
bertbert	5050
transtrans	4040

In some possible implementations of the embodiments of the present application, before acquiring the target database, the text translation method provided by the embodiments of the present application may further include: according to the first vocabulary included in the session to which the text information to be translated belongs and the first vocabulary in the to-be-translated The number of occurrences in the session to which the text information belongs, and a first vocabulary distribution table corresponding to the session to which the text information to be translated belongs is generated; according to the second vocabulary included in the target session and the number of occurrences of the second vocabulary in the target session, the target session corresponding the second vocabulary distribution table; according to the first vocabulary distribution table and the second vocabulary distribution table, determine the similarity of the domain of the conversation to which the text information to be translated belongs and the target conversation.

In some possible implementations of the embodiments of the present application, for each conversation, each word included in all conversations in its history and the number of occurrences of each word in the conversation may be counted to generate a word distribution table.

In this embodiment of the present application, the word distribution may be a vector characterization of the conversation, and each dimension in the vector is the number of occurrences of each different word in the conversation. The words that appear in the dialogue of a conversation can reflect the domain of the conversation. For example, if a conversation includes more words related to the medical field, the more likely the conversation is in the medical field. Therefore, the lexical distribution can be used to characterize the domain features of group chats.

Exemplarily, the first vocabulary distribution table is shown in Table 4, and the second vocabulary table is shown in Table 5.

Table 4

第一词汇first word	出现次数The number of occurrences
wholewhole	22
支持support	3030
翻译translate	55
我们us	33
wordword	22
maskmask	100100
……...	……...

table 5

第二词汇second vocabulary	出现次数The number of occurrences
整all	55
支持support	5656
supportsupport	5050
transtrans	3333
wordword	2525
maskmask	33
……...	……...

In some possible implementations of the embodiments of the present application, when determining the similarity between the fields of the conversation to which the text information to be translated belongs and the target conversation according to the first vocabulary distribution table and the second vocabulary distribution table, the first vocabulary distribution table may be calculated. Cosine similarity or Pearson correlation coefficient with the second vocabulary distribution table, etc.

In some possible implementations of the embodiments of the present application, when generating the vocabulary distribution table corresponding to each conversation, numbers, prepositions, adverbs, conjunctions, pronouns, etc. in all conversations in the history of the conversation may be eliminated first. Based on the number of occurrences of each word included in the conversation after excluding the above numbers, prepositions, adverbs, conjunctions and pronouns, a word distribution table corresponding to the conversation is generated.

In some possible implementations of the embodiments of the present application, for each conversation, the number of occurrences of each word in all dialogues in the conversation history may be counted to form a word distribution table corresponding to the conversation. Then, delete numbers, prepositions, adverbs, conjunctions, and pronouns in the vocabulary distribution table.

In some possible implementations of the embodiments of the present application, before acquiring the target database, the text translation method provided in the embodiments of the present application may further include: determining a session that has the same domain identification information as the session to which the text information to be translated belongs as a session with the same domain identification information. A target session whose similarity in the domain of the session to which the text information to be translated belongs is greater than a preset threshold. The realm identification information is used to identify the realm to which the session belongs.

In some possible implementations of the embodiments of the present application, the user may set realm identification information for the session.

Specifically, for a certain session, when creating the session, the user can select one realm identification information from multiple realm identification information as the realm identification information of the session.

In some possible implementations of the embodiments of the present application, before S102, the text translation method provided by the embodiments of the present application may further include: receiving a first input of the text information to be translated. Correspondingly, S102 may include: in response to the first input, determining the first text information in the text information to be translated according to a preset database corresponding to the session to which the text information to be translated belongs.

Exemplarily, if the user clicks the translation button corresponding to the text information to be translated, it means that the user performs the first input.

In some possible implementations of the embodiments of the present application, before the text information is translated, the text translation method provided by the embodiments of the present application may further include: determining a third language corresponding to the text information to be translated; The text information included in the conversation determines the fourth language corresponding to the conversation to which the text information to be translated belongs. Further, the translation model from the third language to the fourth language is used to translate the text information to be translated or the second text information.

Exemplarily, it is determined that the language corresponding to the text information to be translated "whole word mask is not support in chinese" is English. The language corresponding to the conversation shown in Figure 2 is Chinese. Then use the English-to-Chinese "English to Chinese" translation model to translate "whole word mask is not support in chinese" or translate the text information except "mask" in "whole word mask is not support in chinese".

The text translation method provided by the embodiments of the present application will be described below with reference to specific examples.

For a certain conversation (such as conversation A), when there is a new dialogue sentence in the conversation A, the language of the sentence is identified. Assuming that the new dialogue sentence is "Can the whole Chinese word mask be supported in the future?", determine the language of the sentence as Chinese, and identify the word that does not correspond to Chinese in the sentence as "mask". According to "mask", update the The preset database corresponding to session A. It is assumed that the updated preset database corresponding to the session A is shown in Table 6.

Table 6

文本信息text message	权重Weights
maskmask	3434
bertbert	5050

For the session A, the first vocabulary included in the session A and the number of occurrences of the first vocabulary in the session A are counted, and a corresponding first vocabulary distribution table of the session A is generated.

For any conversation in other conversations (such as conversation B), the second vocabulary included in the conversation B and the number of occurrences of the second vocabulary in the conversation B are counted, and the corresponding second vocabulary distribution table of the conversation B is generated.

According to the first vocabulary distribution table and the second vocabulary distribution table, the similarity of the domain of session A and other sessions is calculated, and the session with the similarity of the domain of session A greater than the preset threshold is used as the target session.

Exemplarily, a session with a similarity in the domain of session A that is greater than a preset threshold is session C. The preset database corresponding to session C is shown in Table 7.

Table 7

文本信息text message	权重Weights
maskmask	6060
transtrans	4040

The above-mentioned Table 6 is updated based on the above-mentioned Table 7, and the updated preset database of the session A is obtained as shown in Table 8.

Table 8

When the user chooses to translate "whole word mask is not support in chinese" in session A, first, according to Table 8, it is determined that the first text information in "whole word mask is not support in chinese" is "mask", Then, it is determined that the language corresponding to "whole word mask is not support in chinese" is English. The language corresponding to this session A is Chinese.

Using the "English to Chinese" translation model from English to Chinese, translate "whole word mask is not support in chinese", and get the translated text information corresponding to "whole word mask is not support in chinese" "does not support Chinese whole word mask" .

Replace the text information "mask" corresponding to "mask" in the translation text information "does not support Chinese full-character mask" with "mask" to obtain the target translation text information "does not support Chinese full-character mask".

It should be noted that, in the text translation method provided by the embodiments of the present application, the execution subject may be a text translation device, or a control module in the text translation device for executing the text translation method. In the embodiment of the present application, the text translation device provided by the embodiment of the present application is described by taking the text translation method performed by the text translation device as an example.

FIG. 4 is a schematic structural diagram of a text translation apparatus provided by an embodiment of the present application. As shown in FIG. 4, the text translation apparatus 400 may include:

The first obtaining module 401 is used to obtain text information to be translated;

The first determining module 402 is configured to determine the first text information in the text information to be translated according to the preset database corresponding to the session to which the text information to be translated belongs;

The translation module 403 is configured to translate the text information to be translated, obtain the first translated text information corresponding to the text information to be translated, and replace the second translated text information corresponding to the first text information in the first translated text information with the first text information, obtain the target translation text information; or, translate the second text information except the first text information in the to-be-translated text information, obtain the third translation text information corresponding to the second text information, and combine the third translation text information and For the first text information, target translation text information is obtained.

In some possible implementations of the embodiments of the present application, the preset database includes at least one text information and a weight corresponding to each text information; the first determination module 402 may be specifically used for:

The text information to be translated matches the text information in the preset database, and the text information whose weight is greater than the preset threshold is determined as the first text information.

In some possible implementations of the embodiments of the present application, the text translation apparatus 400 provided by the embodiments of the present application may further include:

a second acquisition module, configured to acquire target text information other than the text information to be translated in the session to which the text information to be translated belongs;

The second determining module is used to determine the second language to which the target text information belongs;

an identification module for identifying third text information in the target text information that does not correspond to the second language;

The building module is used for building a preset database according to the third text information.

The 3rd acquisition module is used to acquire the target database, wherein, the target database is the database corresponding to the target session whose similarity degree is greater than the preset threshold with the session to which the text information to be translated belongs;

The updating module is used for updating the preset database according to the target database.

The first generation module is configured to generate a first vocabulary corresponding to the session to which the text information to be translated belongs according to the first vocabulary included in the session to which the text information to be translated belongs and the number of occurrences of the first vocabulary in the session to which the text information to be translated belongs distribution table;

The second generation module is used to generate the second vocabulary distribution table corresponding to the target session according to the second vocabulary included in the target session and the number of occurrences of the second vocabulary in the target session;

The third determining module is configured to determine, according to the first vocabulary distribution table and the second vocabulary distribution table, the similarity between the domain of the conversation to which the text information to be translated belongs and the target conversation.

The text translation apparatus in this embodiment of the present application may be an apparatus, or may be a component, an integrated circuit, or a chip in a terminal. The apparatus may be a mobile electronic device or a non-mobile electronic device. Illustratively, the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a palmtop computer, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (personal digital assistant). assistant, PDA), etc., non-mobile electronic devices can be servers, network attached storage (Network Attached Storage, NAS), personal computer (personal computer, PC), television (television, TV), teller machine or self-service machine, etc., this application Examples are not specifically limited.

The text translation apparatus in this embodiment of the present application may be an apparatus with an operating system. The operating system may be an Android (Android) operating system, an ios operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.

The text translation apparatus provided in the embodiments of the present application can implement each process in the text translation method embodiments shown in FIG. 1 to FIG. 3 , and to avoid repetition, details are not repeated here.

Optionally, as shown in FIG. 5 , an embodiment of the present application further provides an electronic device 500, including a processor 501, a memory 502, and a program or instruction stored in the memory 502 and executable on the processor 501, the program Or when the instruction is executed by the processor 501, each process of the above text translation method embodiment can be implemented, and the same technical effect can be achieved. To avoid repetition, details are not described here.

It should be noted that the electronic devices in the embodiments of the present application include the aforementioned mobile electronic devices and non-mobile electronic devices.

FIG. 6 is a schematic diagram of a hardware structure of an electronic device implementing an embodiment of the present application. The electronic device 600 includes but is not limited to: a radio frequency unit 601, a network module 602, an audio output unit 603, an input unit 604, a sensor 605, a display unit 606, a user input unit 607, an interface unit 608, a memory 609, and a processor 610, etc. part.

Those skilled in the art can understand that the electronic device 600 may also include a power source (such as a battery) for supplying power to various components, and the power source may be logically connected to the processor 610 through a power management system, so as to manage charging, discharging, and power management through the power management system. consumption management and other functions. The structure of the electronic device shown in FIG. 6 does not constitute a limitation on the electronic device, and the electronic device may include more or less components than those shown in the figure, or combine some components, or arrange different components, which will not be repeated here. .

The processor 610 is configured to: obtain text information to be translated; determine the first text information in the text information to be translated according to a preset database corresponding to the session to which the text information to be translated belongs; translate the text information to be translated to obtain the text information to be translated For the first translation text information corresponding to the text information, the second translation text information corresponding to the first text information in the first translation text information is replaced with the first text information to obtain the target translation text information; The second text information other than the first text information is translated to obtain third translated text information corresponding to the second text information, and the third translated text information and the first text information are combined to obtain the target translated text information.

In some possible implementations of the embodiments of the present application, the preset database includes at least one text information and a weight corresponding to each text information; the processor 610 may be specifically configured to:

In some possible implementations of the embodiments of the present application, the processor 610 may also be used for:

Obtain the target text information other than the to-be-translated text information in the session to which the to-be-translated text information belongs;

Determine the second language to which the target text information belongs;

Identifying third text information that does not correspond to the second language in the target text information;

According to the third text information, a preset database is constructed.

Acquiring a target database, wherein the target database is a database corresponding to a target session whose similarity with the domain to which the session to which the text information to be translated belongs belongs is greater than a preset threshold;

According to the target database, the preset database is updated.

In some possible implementations of the embodiments of the present application, in some possible implementations of the embodiments of the present application, the processor 610 may also be used for:

generating a first vocabulary distribution table corresponding to the session to which the text information to be translated belongs according to the first vocabulary included in the session to which the text information to be translated belongs and the number of occurrences of the first vocabulary in the session to which the text information to be translated belongs;

generating a second vocabulary distribution table corresponding to the target session according to the second vocabulary included in the target session and the number of occurrences of the second vocabulary in the target session;

According to the first vocabulary distribution table and the second vocabulary distribution table, the similarity of the domain of the conversation to which the text information to be translated belongs and the target conversation are determined.

It should be understood that, in this embodiment of the present application, the input unit 604 may include a graphics processor (Graphics Processing Unit, GPU) 6041 and a microphone 6042. Such as camera) to obtain still pictures or video image data for processing. The display unit 606 may include a display panel 6061, which may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 607 includes a touch panel 6071 and other input devices 6072 . The touch panel 6071 is also called a touch screen. The touch panel 6071 may include two parts, a touch detection device and a touch controller. Other input devices 6072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which are not described herein again. Memory 609 may be used to store software programs as well as various data, including but not limited to application programs and operating systems. The processor 610 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and an application program, and the like, and the modem processor mainly processes wireless communication. It can be understood that, the above-mentioned modulation and demodulation processor may not be integrated into the processor 610.

The embodiments of the present application further provide a computer-readable storage medium, where a program or an instruction is stored on the computer-readable storage medium. When the program or instruction is executed by a processor, each process of the above text translation method embodiment can be achieved, and the same can be achieved. In order to avoid repetition, the technical effect will not be repeated here.

The processor is the processor in the electronic device in the above embodiment. The processor may be, but is not limited to, a general-purpose processor, a special-purpose processor, an application-specific processor, or a field programmable logic circuit. Examples of computer-readable storage media include non-transitory machine-readable storage media such as electronic circuits, semiconductor memory devices, read-only memory (ROM), flash memory, erasable ROM (EROM), floppy disks, CDs -ROM, CD-ROM, HDD, etc.

The embodiment of the present application also provides a chip, including a processor and a communication interface, the communication interface is coupled with the processor, and the processor is used for running a program or an instruction, implementing each process of the above text translation method embodiment, and can achieve the same technology The effect, in order to avoid repetition, is not repeated here.

It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, a system-on-chip, a system-on-a-chip, or a system-on-a-chip, or the like.

It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in the reverse order depending on the functions involved. To perform functions, for example, the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to some examples may be combined in other examples.

From the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is better implementation. Based on this understanding, the technical solutions of the present application can be embodied in the form of software products in essence or the parts that make contributions to related technologies, and the computer software products are stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) ), including several instructions to enable a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of this application.

The embodiments of the present application have been described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific embodiments, which are merely illustrative rather than restrictive. Under the inspiration of this application, without departing from the scope of protection of the purpose of this application and the claims, many forms can be made, which all fall within the protection of this application.

Claims

A text translation method comprising:

Get the text information to be translated;

determining the first text information in the text information to be translated according to a preset database corresponding to the session to which the text information to be translated belongs;

Translate the to-be-translated text information to obtain first translated text information corresponding to the to-be-translated text information, and replace the second translated text information corresponding to the first text information in the first translated text information with For the first text information, the target translation text information is obtained; or,

Translate the second text information other than the first text information in the text information to be translated, obtain third translation text information corresponding to the second text information, and combine the third translated text information and the The first text information is obtained, and the target translation text information is obtained.
The method according to claim 1, wherein the preset database includes at least one text information and a weight corresponding to each text information;

The determining of the first text information in the text information to be translated according to the preset database corresponding to the session to which the text information to be translated belongs includes:

The text information to be translated matches the text information in the preset database, and the text information whose weight is greater than the preset threshold is determined as the first text information.
The method according to claim 1, wherein before determining the first text information in the text information to be translated according to the preset database corresponding to the session to which the text information to be translated belongs, the method further comprises: :

Acquiring target text information in the session other than the to-be-translated text information;

determining the second language to which the target text information belongs;

Identifying third text information that does not correspond to the second language in the target text information;

The preset database is constructed according to the third text information.
The method according to claim 3, wherein after constructing the preset database according to the third text information, the method further comprises:

Acquiring a target database, wherein the target database is a database corresponding to a target session whose similarity in the field to which the session belongs is greater than a preset threshold;

According to the target database, the preset database is updated.
The method according to claim 4, wherein, before the acquiring the target database, the method further comprises:

generating a first vocabulary distribution table corresponding to the conversation according to the first vocabulary included in the conversation and the number of occurrences of the first vocabulary in the conversation;

generating a second vocabulary distribution table corresponding to the target session according to the second vocabulary included in the target session and the number of occurrences of the second vocabulary in the target session;

According to the first vocabulary distribution table and the second vocabulary distribution table, the similarity of the domain of the conversation and the target conversation is determined.
A text translation device, comprising:

The first acquisition module is used to acquire the text information to be translated;

a first determining module, configured to determine first text information in the text information to be translated according to a preset database corresponding to the session to which the text information to be translated belongs;

A translation module, configured to translate the text information to be translated, obtain first translation text information corresponding to the text information to be translated, and convert the second translation text information corresponding to the first text information in the first translated text information The translated text information is replaced with the first text information to obtain the target translated text information; or, the second text information other than the first text information in the to-be-translated text information is translated to obtain the second text information. For the third translated text information corresponding to the text information, the third translated text information and the first text information are combined to obtain the target translated text information.
The apparatus according to claim 6, wherein the preset database includes at least one text information and a weight corresponding to each text information;

The first determining module is specifically used for:

The text information to be translated matches the text information in the preset database, and the text information whose weight is greater than the preset threshold is determined as the first text information.
The apparatus of claim 6, wherein the apparatus further comprises:

a second acquisition module, configured to acquire target text information other than the to-be-translated text information in the session;

a second determining module, configured to determine the second language to which the target text information belongs;

an identification module, configured to identify third text information that does not correspond to the second language in the target text information;

and a building module, configured to build the preset database according to the third text information.
The apparatus of claim 8, wherein the apparatus further comprises:

A third obtaining module, configured to obtain a target database, wherein the target database is a database corresponding to a target session whose similarity in the field to which the session belongs is greater than a preset threshold;

An update module, configured to update the preset database according to the target database.
The apparatus of claim 9, wherein the apparatus further comprises:

a first generating module, configured to generate a first vocabulary distribution table corresponding to the conversation according to the first vocabulary included in the conversation and the number of occurrences of the first vocabulary in the conversation;

A second generating module, configured to generate a second vocabulary distribution table corresponding to the target session according to the second vocabulary included in the target session and the number of occurrences of the second vocabulary in the target session;

The third determining module is configured to determine the similarity between the domain of the conversation and the target conversation according to the first vocabulary distribution table and the second vocabulary distribution table.
An electronic device, comprising: a processor, a memory, and a program or instruction stored on the memory and executable on the processor, the program or instruction being executed by the processor to implement claims 1 to 5. The steps of any one of the text translation methods.
A computer-readable storage medium storing programs or instructions on the computer-readable storage medium, when the programs or instructions are executed by a processor, the steps of the text translation method according to any one of claims 1 to 5 are implemented.
An electronic device configured to perform the steps of the text translation method of any one of claims 1 to 5.
A computer program product executed by at least one processor to implement the steps of the text translation method of any one of claims 1 to 5.
A chip, comprising a processor and a communication interface, wherein the communication interface is coupled with the processor, and the processor is used for running a program or an instruction to implement the steps of the text translation method according to any one of claims 1 to 5 .