Text conversion method and device, electronic equipment and computer readable storage medium

Abstract

The invention relates to the technical field of data processing, and provides a text conversion method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: obtaining a to-be-converted text; performing query processing on a preset vocabulary database according to the to-be-converted text to obtain a plurality of original word roots; screening a plurality of target roots from the plurality of original roots according to the root popularity of the original roots; performing text division processing on the to-be-converted text according to the plurality of target roots to obtain a plurality of sub-texts; and performing text conversion processing on the plurality of sub-texts according to the conversion texts corresponding to the plurality of target roots to obtain text conversion information. By means of the technical scheme, intelligent text conversion processing can be achieved, the text conversion efficiency is improved, and the text conversion quality is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to, but are not limited to, the field of data processing technology, and in particular, to a text conversion method, device, electronic device, and computer-readable storage medium. Background Art

[0002] At present, in order to meet the requirements of business development, the insurance industry often needs to translate relevant professional terms in the insurance industry; due to the professionalism and complexity of relevant professional terms, there are many professional terms and concepts involved, and the translation is difficult. In order to solve the above problems, the existing translation process often needs to rely on manual translation, which has low translation efficiency and is prone to human errors in the translation process, thereby reducing the quality of translation. Summary of the invention

[0003] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0004] In order to solve the problems mentioned in the above background technology, the embodiments of the present application provide a text conversion method, device, electronic device and computer-readable storage medium, which can realize intelligent text conversion processing, improve the efficiency of text conversion, and improve the quality of text conversion.

[0005] In a first aspect, an embodiment of the present application provides a text conversion method, the method comprising:

[0006] Get the text to be converted;

[0007] Performing query processing on a preset vocabulary database according to the text to be converted to obtain a plurality of original word roots;

[0008] According to the root heat of the original root, a plurality of target root words are obtained by screening the plurality of original root words;

[0009] Performing text segmentation processing on the text to be converted according to the multiple target word roots to obtain multiple sub-texts;

[0010] According to the conversion texts corresponding to the multiple target word roots, text conversion processing is performed on the multiple subtexts to obtain text conversion information.

[0011] According to some embodiments of the present application, querying a preset vocabulary database according to the text to be converted to obtain a plurality of original word roots includes:

[0012] Performing semantic recognition processing on the text to be converted to obtain text semantic information;

[0013] The text semantic information is matched with a plurality of word roots in the vocabulary database to obtain a plurality of the original word roots.

[0014] According to some embodiments of the present application, the text semantic information includes a plurality of sub-information, and the plurality of target word roots are obtained by screening the plurality of the original word roots according to the word root heat of the original word roots, including:

[0015] sorting the plurality of original word roots according to the word root heats of the plurality of original word roots that match the sub-information;

[0016] The original root word with the highest root word heat is used as the target root word corresponding to the sub-information.

[0017] According to some embodiments of the present application, performing text conversion processing on the plurality of subtexts according to the conversion texts corresponding to the plurality of target word roots to obtain text conversion information includes:

[0018] Determining the corresponding conversion text according to each of the target word roots from the vocabulary database, wherein the conversion text corresponds to the subtext;

[0019] The conversion texts corresponding to each of the target word roots are concatenated to obtain the text conversion information.

[0020] According to some embodiments of the present application, after performing text conversion processing on the plurality of subtexts according to the conversion texts corresponding to the plurality of target word roots to obtain text conversion information, the method further includes:

[0021] Adjusting the root heat of the plurality of target root words;

[0022] The root heat of the corresponding original root in the vocabulary database is modified according to the adjusted target root.

[0023] According to some embodiments of the present application, matching the text semantic information with a plurality of word roots in the vocabulary database to obtain a plurality of the original word roots includes at least one of the following:

[0024] In the case where the text semantic information matches the root word in the vocabulary database, using the corresponding root word as the original root word;

[0025] In the case that the text semantic information does not match the word root in the vocabulary database, a new word root is created according to the text semantic information, and the new word root is used as the original word root.

[0026] According to some embodiments of the present application, the vocabulary database is constructed in the following manner:

[0027] Acquire a plurality of the root words and the converted texts corresponding to the root words;

[0028] The vocabulary database is constructed by using the root word as a key value and the corresponding converted text as a content field.

[0029] In a second aspect, the embodiment of the present application further provides a text conversion device, including:

[0030] A first processing module, used for obtaining the text to be converted;

[0031] A second processing module is used to query a preset vocabulary database according to the text to be converted to obtain a plurality of original word roots;

[0032] A third processing module is used to filter multiple target word roots from the multiple original word roots according to the word root heat of the original word roots;

[0033] A fourth processing module is used to perform text segmentation processing on the text to be converted according to the plurality of target word roots to obtain a plurality of sub-texts;

[0034] The fifth processing module is used to perform text conversion processing on the multiple sub-texts according to the conversion texts corresponding to the multiple target word roots to obtain text conversion information.

[0035] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the text conversion method as described in the first aspect above is implemented.

[0036] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the text conversion method described in the first aspect above.

[0037] According to the text conversion method of the embodiment provided by the present application, there are at least the following beneficial effects: in the process of text conversion, firstly, the text to be converted is obtained; then, a preset vocabulary database is queried and processed according to the text to be converted, so that an original root word can be obtained; then, according to the root heat of the original root word, multiple target roots are screened from multiple original roots to obtain multiple sub-texts; then, the text to be converted is divided according to the multiple target roots to obtain multiple sub-texts; finally, according to the conversion texts corresponding to the multiple target roots, text conversion processing is performed on the multiple sub-texts to obtain text conversion information; through the above technical scheme, intelligent text conversion processing can be realized, the efficiency of text conversion is improved, and the quality of text conversion is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings are used to provide further understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

[0039] Figure 1 is a flowchart of a text conversion method provided by an embodiment of the present application;

[0040] Figure 2 is a specific flow chart of step S200 provided in one embodiment of the present application;

[0041] Figure 3 is a specific flow chart of step S300 provided in one embodiment of the present application;

[0042] Figure 4 is a specific flow chart of step S500 provided in one embodiment of the present application;

[0043] Figure 5 is a flowchart of a text conversion method provided by another embodiment of the present application;

[0044] Figure 6 is a specific flow chart of step S220 provided in one embodiment of the present application;

[0045] Figure 7 is a flowchart of constructing a vocabulary database provided by an embodiment of the present application;

[0046] Figure 8 is a schematic diagram of a text conversion device provided by an embodiment of the present application;

[0047] Fig. 9 It is a schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0049] It should be noted that although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification and claims and the above drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0050] It should be noted that, unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0051] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0052] AI is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science. Artificial intelligence attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robots, language recognition, image recognition, natural language processing and expert systems. Artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0053] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0054] Artificial intelligence is AI. AI is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0055] The servers involved in artificial intelligence technology can be independent servers or cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), as well as big data and artificial intelligence platforms.

[0056] The present application provides a text conversion method, device, electronic device and computer-readable storage medium. In the process of text conversion, the text to be converted is first obtained; then, a preset vocabulary database is queried and processed according to the text to be converted to obtain original roots; then, according to the root heat of the original roots, multiple target roots are screened from multiple original roots to obtain multiple sub-texts; then, the text to be converted is divided according to the multiple target roots to obtain multiple sub-texts; finally, according to the conversion texts corresponding to the multiple target roots, the multiple sub-texts are converted to obtain text conversion information; through the above technical solution, intelligent text conversion processing can be realized, the efficiency of text conversion is improved, and the quality of text conversion is improved.

[0057] The text conversion method provided in the embodiment of the present application relates to the field of data processing technology. The text conversion method provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server side, and can also be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the text conversion method, etc., but is not limited to the above forms.

[0058] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0059] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0060] The embodiments of the present application are further described below in conjunction with the accompanying drawings.

[0061] like Figure 1 As shown, Figure 1 It is a flowchart of a text conversion method provided by an embodiment of the present application. The text conversion method includes but is not limited to steps S100 to S500.

[0062] Step S100, obtaining the text to be converted;

[0063] Step S200, querying a preset vocabulary database according to the text to be converted to obtain a plurality of original word roots;

[0064] Step S300, filtering multiple target word roots from multiple original word roots according to the word root heat of the original word roots;

[0065] Step S400, dividing the text to be converted according to multiple target word roots to obtain multiple sub-texts;

[0066] Step S500 , performing text conversion processing on multiple subtexts according to conversion texts corresponding to multiple target word roots to obtain text conversion information.

[0067] It should be noted that, in the process of text conversion, the text to be converted is first obtained; then, the preset vocabulary database is queried based on the text to be converted to obtain original roots; then, based on the root heat of the original roots, multiple target roots are screened from multiple original roots to obtain multiple sub-texts; then, the text to be converted is divided according to the multiple target roots to obtain multiple sub-texts; finally, according to the conversion texts corresponding to the multiple target roots, the multiple sub-texts are converted to obtain text conversion information; through the above technical solution, intelligent text conversion processing can be realized, the efficiency of text conversion is improved, and the quality of text conversion is improved.

[0068] It is worth noting that in the insurance industry, in order to cope with the further development of various businesses, it is often necessary to translate relevant professional terms from Chinese to English. Since the relevant professional terms have certain professionalism and complexity, there are many professional terms and concepts involved, and the translation is difficult; and currently it is generally completed by manual translation, which will make the translation inefficient and prone to errors and omissions. Based on the technical solution of the embodiment of the present application, it is possible to realize text conversion in an automated manner, improve the conversion efficiency of the text, and can well improve the accuracy of the text conversion, reducing human errors and omissions.

[0069] It is worth noting that in the process of obtaining the text to be converted, the embodiments of the present application will first obtain the user's permission or consent, and the collection, use and processing of these data will comply with relevant laws, regulations and standards. In addition, when the embodiments of the present application need to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or jump to a confirmation page. After the user's separate permission or consent is clearly obtained, the necessary user-related data for the normal operation of the embodiments of the present application will be obtained.

[0070] It is worth noting that in the process of querying the preset vocabulary database according to the text to be converted, multiple original roots can be queried; the preset vocabulary database refers to a vocabulary collection pre-built for a specific purpose or application scenario, and these databases usually contain a large number of words and related information, such as definitions, synonyms, antonyms, examples, etc.; they can be used to support various language processing tasks, such as text analysis, natural language understanding, machine translation, etc. The vocabulary database in the embodiment of the present application includes multiple original roots. The original roots can be historical roots.

[0071] It should be noted that each original root in the vocabulary database corresponds to a root heat. In the subsequent screening process of target roots, multiple target roots can be screened from multiple original roots according to the root heat of the original roots; subsequently, the text to be converted can be processed by text segmentation according to the obtained multiple target roots to obtain multiple sub-texts; then, according to the conversion texts corresponding to the multiple target roots, the multiple sub-texts are processed by text conversion to obtain corresponding text conversion information. Exemplarily, the multiple target roots obtained by screening correspond to the translation content, and subsequently, the text conversion information can be obtained by performing text translation according to the multiple sub-texts obtained by segmentation.

[0072] In some embodiments of the present application, the root heat of an original root is the number of times the root has been selected in the past. The higher the root heat, the more times the root has been selected previously. If the root heat of an original root is lower, it means that the root has been selected less times previously.

[0073] It is worth noting that in the process of text conversion, the text to be converted is first divided according to multiple target word roots to obtain multiple sub-texts, thereby making prerequisite preparations for the subsequent rapid and accurate conversion of the text.

[0074] In some embodiments of the present application, a root is a basic part of a word, which carries the basic meaning. In many languages, especially derived languages ​​like English, words are usually composed of roots and affixes (prefixes and suffixes). The root is the core of the word, while the affixes are used to change the meaning or grammatical function of the root.

[0075] It is worth noting that when translating models and indicators, a combination of word segmentation technology and machine translation technology can be used. Word segmentation technology can segment Chinese semantics for more accurate translation. Machine translation technology can use big data and algorithms to automatically translate Chinese semantics, and compare and correct them. In addition, artificial intelligence algorithms and natural language generation technologies can be introduced to improve translation accuracy and efficiency. Regular evaluation and improvement of translation quality is required to ensure the accuracy and consistency of translation. The evaluation can be conducted through the review of professionals and customer feedback to collect and analyze feedback and suggestions, and optimize and upgrade the vocabulary library and translation algorithm. In addition, machine learning technology and data mining algorithms can be introduced to monitor and predict translation quality, discover and solve problems in a timely manner, and continuously improve translation quality and efficiency. Establish a standardized translation process and document management system. In order to ensure the consistency and accuracy of translation, a standardized translation process and document management system need to be established. The translation process should include translation, proofreading, review and release, and each link needs to have clear responsibilities and standards. The document management system can perform version control and management on the translated documents to ensure the integrity and security of the documents. Training and improving the ability and quality of the translation team to ensure the professionalism and accuracy of the translation requires training and improving the ability and quality of the translation team. The training can include language skills, professional knowledge, translation skills and software operation. In addition, an evaluation and incentive mechanism for professional translators can be established to encourage them to actively participate in translation work and improve their own abilities. At the same time, external experts and consultants can be introduced to provide professional guidance and support for the translation team.

[0076] Through the above technical solutions, by establishing a professional terminology vocabulary and adopting word segmentation technology and machine translation technology, enterprises can improve the accuracy and consistency of translation and avoid information confusion and misunderstanding. In addition, regular translation quality assessment and improvement can timely discover and solve problems and continuously improve translation quality and efficiency. Reduce translation costs and improve efficiency. The use of machine translation technology and natural language generation technology can greatly reduce translation costs and improve translation efficiency. In addition, establishing a standardized translation process and document management system can optimize the translation process and improve work efficiency and quality. Improve corporate competitiveness and influence. By improving translation quality and accuracy, enterprises can better meet customer needs, strengthen customer trust and loyalty, and improve corporate competitiveness and influence. In addition, enterprises can customize according to the special needs of the insurance industry to further improve business quality and efficiency. Optimize personnel resources and enhance team capabilities. By adopting automated translation tools and standardized translation processes, enterprises can optimize personnel resources and improve team work efficiency and quality. In addition, training and improving the capabilities and qualities of the translation team can strengthen team cohesion and creativity, laying a good foundation for the long-term development of the enterprise. In summary, the implementation of the proposed solutions can help enterprises improve translation quality and efficiency, reduce costs, increase competitiveness and influence, and optimize human resources and enhance team capabilities.

[0077] In some embodiments, Figure 2 As shown, the above step S200 may include but is not limited to steps S210 to S220.

[0078] Step S210, performing semantic recognition processing on the text to be converted to obtain text semantic information;

[0079] Step S220, matching the text semantic information with a plurality of word roots in a vocabulary database to obtain a plurality of original word roots.

[0080] It should be noted that in the process of querying the preset vocabulary database according to the text to be converted to obtain multiple original root words, the text to be converted can first be semantically recognized to obtain text semantic information; then the text semantic information can be matched with multiple root words in the vocabulary database to obtain multiple original root words; then the corresponding target root words can be screened out according to the root heat of the obtained original root words, so as to make the prerequisite preparation for the subsequent text conversion.

[0081] It should be noted that during the process of semantic recognition and processing of the text to be converted, semantic recognition and processing of the text to be converted is a complex process, involving multiple technologies and steps in natural language processing. The following are the general steps of this process: segment continuous text into individual words or phrases; remove stop words: delete common words with little meaning, such as "de" (of), "shi" (is), etc.; restore words to their basic forms, for example, restore the past tense of a verb to its original form; label the part of speech for each word; convert the text into a vector of word occurrence frequencies; use a pre-trained model to convert words into dense vectors to capture semantic information. Analyze the dependency relationships between words in a sentence. Identify the phrase structure in a sentence. Determine the roles of each component in a sentence. Identify entities (person names, place names, organization names, etc.) in the text. Identify the relationships between entities. Judge the sentiment tendency of the text (positive, negative or neutral). Convert the entire sentence or paragraph into a fixed-length vector to represent its semantic content. Perform semantic representation on the entire document for tasks such as document classification and clustering.

[0082] It should be noted that by matching the semantic information of the text with multiple root words in the lexical database, the corresponding original root words can be matched from the lexical database according to the semantic information of the text, laying a prerequisite for subsequent text conversion.

[0083] In some embodiments, as Figure 3 shown, the semantic information of the text includes multiple sub-information, and the above step S300 may include but is not limited to steps S310 to S320.

[0084] Step S310, sort the multiple original root words according to the root word popularity of the multiple original root words that match the sub-information;

[0085] Step S320, use the original root word with the highest root word popularity as the target root word corresponding to the sub-information.

[0086] It should be noted that during the process of screening multiple target root words from multiple original root words according to the root word popularity of the original root words, first sort the multiple original root words according to the root word popularity of the multiple original root words that match the sub-information; then use the original root word with the highest root word popularity as the target root word corresponding to the sub-information, thereby laying a prerequisite for subsequent text conversion.

[0087] It can be understood that, according to the root heat of multiple original root words matching the sub-information, the obtained multiple original root words are sorted; and the original root word with the highest root heat is used as the target root word corresponding to the sub-information; in the embodiment of the present application, the original root word with the highest root heat is selected, which can make the subsequent text conversion process more accurate and reliable. The higher the root heat, it means that the root word has been screened multiple times before, and the subsequent text conversion process will be more accurate and reliable.

[0088] In some embodiments, Figure 4 As shown, the above step S500 may include but is not limited to step S510 to step S520.

[0089] Step S510, determining a corresponding conversion text according to each target root from the vocabulary database, wherein the conversion text corresponds to the subtext;

[0090] Step S520: concatenate the conversion texts corresponding to each target word root to obtain text conversion information.

[0091] It should be noted that, in the process of performing text conversion processing on multiple sub-texts according to the conversion texts corresponding to multiple target word roots to obtain text conversion information, firstly, the corresponding conversion text is determined from the vocabulary database according to each target word root, wherein the conversion text corresponds to the sub-text; then, the conversion text corresponding to each target word root is spliced ​​to obtain the corresponding text conversion information. Through the above technical solution, the text conversion information can be quickly and accurately spliced.

[0092] It is worth noting that the corresponding conversion text is determined from the vocabulary database according to each target root, and then the conversion text corresponding to the determined target root can be spliced ​​and processed, so that the corresponding text conversion information can be obtained conveniently and accurately, and intelligent text conversion processing can be realized. The whole process is efficient and accurate.

[0093] In some embodiments, Figure 5 As shown, after executing the above step S500, steps S610 to S620 may also be included but not limited to.

[0094] Step S610, adjusting the root heat of multiple target root words;

[0095] Step S620: modify the root heat of the corresponding original root in the vocabulary database according to the adjusted target root.

[0096] It should be noted that, after performing text conversion processing on multiple sub-texts according to the conversion texts corresponding to multiple target roots and obtaining the text conversion information, the root temperatures of the multiple target roots can be adjusted first; then, the root temperatures of the corresponding original roots in the vocabulary database can be corrected according to the adjusted target roots, in order to make the prerequisite preparations for the subsequent text conversion and make the subsequent text conversion more accurate.

[0097] It is worth noting that after obtaining the text conversion information, the root heat of multiple target roots can be adjusted; illustratively, based on the target root selected in the previous round, the root heat of the target root will increase by 1; after adjusting the root heat of the target root, the root heat of the corresponding original root in the vocabulary database can be corrected to prepare for subsequent text conversion.

[0098] In some embodiments, Figure 6 As shown, the above step S220 may include but is not limited to step S221 to step S222.

[0099] Step S221, when the text semantic information matches the root word in the vocabulary database, the corresponding root word is used as the original root word;

[0100] Step S222: when the text semantic information does not match the root word in the vocabulary database, a new root word is created according to the text semantic information, and the new root word is used as the original root word.

[0101] It should be noted that in the process of matching text semantic information with multiple word roots in the vocabulary database to obtain multiple original word roots, when the text semantic information matches the word roots in the vocabulary database, the corresponding word roots are used as the original word roots; when the text semantic information does not match the word roots in the vocabulary database, new word roots are created according to the text semantic information, and the new word roots are used as the original word roots, so as to make prerequisite preparations for the subsequent automatic text conversion.

[0102] It is worth noting that when the text semantic information does not match the root word in the vocabulary database, the large language model can be used to convert the text semantic information into a new root word, and the new root word is used as the original root word. Among them, the large language model converts the semantic information of the text into a new root word, which is actually achieved through a technology called word embedding. Word embedding is a key concept in natural language processing. It involves mapping words or phrases to vectors in a high-dimensional space. These vectors can capture the semantic information of words and the relationship between them. The following is the general process of converting text semantic information into root word vectors by the large language model: Preprocessing: Clean the input text, including removing stop words, punctuation, stem extraction or word form restoration, etc. Word segmentation: Split the text into separate words or phrases. Word embedding: Use a pre-trained model to convert each word or phrase into a dense vector. These models can capture the semantic information of words and the similarity between them. Context encoding: In some advanced models, a self-attention mechanism is used to encode the context information of words to generate vectors that can reflect the meaning of words in sentences. Sentence embedding: For an entire sentence or paragraph, the average of all word vectors can be taken. Semantic Identification: By comparing the embedding vectors of different sentences or documents, the semantic similarities or differences between them can be identified.

[0103] In some embodiments, Figure 7 As shown, the vocabulary database may also be constructed through but not limited to step S110 and step S120.

[0104] Step S110, obtaining a plurality of word roots and conversion texts corresponding to the word roots;

[0105] Step S120 , using the root word as a key value and the corresponding converted text as a content field, to construct a vocabulary database.

[0106] It should be noted that in the process of constructing a vocabulary database, multiple word roots and the conversion texts corresponding to the word roots are first obtained; then the word roots are used as key values ​​and the corresponding conversion texts are used as content fields to construct the vocabulary database; through the above construction method, the construction process of the vocabulary database can be simpler, faster and more reliable, and thus can make good preparations for subsequent text conversion.

[0107] In addition, if Figure 8 As shown, an embodiment of the present application further provides a text conversion device 10, comprising:

[0108] The first processing module 100 is used to obtain the text to be converted;

[0109] The second processing module 200 is used to query a preset vocabulary database according to the text to be converted to obtain a plurality of original word roots;

[0110] The third processing module 300 is used to filter multiple target word roots from multiple original word roots according to the word root heat of the original word roots;

[0111] A fourth processing module 400 is used to perform text segmentation processing on the text to be converted according to multiple target word roots to obtain multiple sub-texts;

[0112] The fifth processing module 500 is used to perform text conversion processing on multiple subtexts according to the conversion texts corresponding to the multiple target word roots to obtain text conversion information.

[0113] It should be noted that, in the process of text conversion, the text to be converted is first obtained; then, the preset vocabulary database is queried based on the text to be converted to obtain original roots; then, based on the root heat of the original roots, multiple target roots are screened from multiple original roots to obtain multiple sub-texts; then, the text to be converted is divided according to the multiple target roots to obtain multiple sub-texts; finally, according to the conversion texts corresponding to the multiple target roots, the multiple sub-texts are converted to obtain text conversion information; through the above technical solution, intelligent text conversion processing can be realized, the efficiency of text conversion is improved, and the quality of text conversion is improved.

[0114] It is worth noting that in the process of obtaining the text to be converted, the embodiments of the present application will first obtain the user's permission or consent, and the collection, use and processing of these data will comply with relevant laws, regulations and standards. In addition, when the embodiments of the present application need to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or jump to a confirmation page. After the user's separate permission or consent is clearly obtained, the necessary user-related data for the normal operation of the embodiments of the present application will be obtained.

[0115] It is worth noting that in the process of querying the preset vocabulary database according to the text to be converted, multiple original roots can be queried; the preset vocabulary database refers to a vocabulary collection pre-built for a specific purpose or application scenario, and these databases usually contain a large number of words and related information, such as definitions, synonyms, antonyms, examples, etc.; they can be used to support various language processing tasks, such as text analysis, natural language understanding, machine translation, etc. The vocabulary database in the embodiment of the present application includes multiple original roots. The original roots can be historical roots.

[0116] It should be noted that each original root in the vocabulary database corresponds to a root heat. In the subsequent screening process of target roots, multiple target roots can be screened from multiple original roots according to the root heat of the original roots; subsequently, the text to be converted can be processed by text segmentation according to the obtained multiple target roots to obtain multiple sub-texts; then, according to the conversion texts corresponding to the multiple target roots, the multiple sub-texts are processed by text conversion to obtain corresponding text conversion information. Exemplarily, the multiple target roots obtained by screening correspond to the translation content, and subsequently, the text conversion information can be obtained by performing text translation according to the multiple sub-texts obtained by segmentation.

[0117] The specific implementation of the text conversion device 10 is substantially the same as the specific implementation of the above-mentioned text conversion method, and will not be described in detail herein.

[0118] In addition, if Fig. 9 As shown, an embodiment of the present application further provides an electronic device 700 , which includes: a memory 720 , a processor 710 , and a computer program stored in the memory 720 and executable on the processor 710 .

[0119] The processor 710 and the memory 720 may be connected via a bus or in other ways.

[0120] The non-transitory software programs and instructions required to implement the text conversion methods of the above embodiments are stored in the memory 720 , and when executed by the processor 710 , the text conversion methods of the above embodiments are executed.

[0121] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0122] In addition, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are executed by a processor 710 or a controller, for example, by a processor 710 in the above-mentioned device embodiment, so that the above-mentioned processor 710 can execute the text conversion method in the above-mentioned embodiment.

[0123] The above embodiments may be used in combination, and modules with the same name in different embodiments may be the same or different.

[0124] The above describes specific embodiments of the present application, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0125] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and computer-readable storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0126] The apparatus, device, computer-readable storage medium and method provided in the embodiments of the present application correspond to each other. Therefore, the apparatus, device and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the corresponding apparatus, device and computer storage medium will not be repeated here.

[0127] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0128] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0129] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0130] For the convenience of description, the above devices are described in terms of functions and are divided into various units. Of course, when implementing the embodiments of the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0131] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the embodiments of the present application may adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0132] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0135] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0136] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0137] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0138] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0139] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0140] Embodiments of the present application may be described in the general context of computer executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. Embodiments of the present application may also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0141] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0142] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A text conversion method, characterized in that: The method comprises: Get the text to be converted; Performing query processing on a preset vocabulary database according to the text to be converted to obtain a plurality of original word roots; According to the root heat of the original root, a plurality of target root words are obtained by screening the plurality of original root words; Performing text segmentation processing on the text to be converted according to the multiple target word roots to obtain multiple sub-texts; According to the conversion texts corresponding to the multiple target word roots, text conversion processing is performed on the multiple subtexts to obtain text conversion information.

2. The text conversion method according to claim 1, characterized in that: The query processing is performed on a preset vocabulary database according to the text to be converted to obtain a plurality of original word roots, including: Performing semantic recognition processing on the text to be converted to obtain text semantic information; The text semantic information is matched with a plurality of word roots in the vocabulary database to obtain a plurality of the original word roots.

3. The text conversion method according to claim 2, characterized in that: The text semantic information includes a plurality of sub-information, and the plurality of target word roots are obtained by screening the plurality of the original word roots according to the word root heat of the original word roots, including: sorting the plurality of original word roots according to the word root heats of the plurality of original word roots that match the sub-information; The original root word with the highest root word heat is used as the target root word corresponding to the sub-information.

4. The text conversion method according to claim 1, characterized in that: The step of performing text conversion processing on the plurality of subtexts according to the conversion texts corresponding to the plurality of target word roots to obtain text conversion information includes: Determining the corresponding conversion text according to each of the target word roots from the vocabulary database, wherein the conversion text corresponds to the subtext; The conversion texts corresponding to each of the target word roots are concatenated to obtain the text conversion information.

5. The text conversion method according to claim 1, characterized in that: After performing text conversion processing on the plurality of subtexts according to the conversion texts corresponding to the plurality of target word roots to obtain text conversion information, the method further includes: Adjusting the root heat of the plurality of target root words; The root heat of the corresponding original root in the vocabulary database is modified according to the adjusted target root.

6. The text conversion method according to claim 2, characterized in that: The matching process of the text semantic information with the multiple word roots in the vocabulary database to obtain the multiple original word roots includes at least one of the following: In the case where the text semantic information matches the root word in the vocabulary database, using the corresponding root word as the original root word; In the case that the text semantic information does not match the word root in the vocabulary database, a new word root is created according to the text semantic information, and the new word root is used as the original word root.

7. The text conversion method according to claim 1, characterized in that: The vocabulary database is constructed in the following way: Acquire a plurality of the root words and the converted texts corresponding to the root words; The vocabulary database is constructed by using the root word as a key value and the corresponding converted text as a content field.

8. A text conversion device, characterized in that: include: A first processing module, used for obtaining the text to be converted; A second processing module is used to query a preset vocabulary database according to the text to be converted to obtain a plurality of original word roots; A third processing module is used to filter multiple target word roots from the multiple original word roots according to the word root heat of the original word roots; A fourth processing module is used to perform text segmentation processing on the text to be converted according to the plurality of target word roots to obtain a plurality of sub-texts; The fifth processing module is used to perform text conversion processing on the multiple sub-texts according to the conversion texts corresponding to the multiple target word roots to obtain text conversion information.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the text conversion method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing computer-executable instructions, characterized in that: The computer executable instructions are used to execute the text conversion method described in any one of claims 1 to 7.

Images