Text processing method and device based on artificial intelligence, computer device and medium

Abstract

The application belongs to the field of artificial intelligence and the field of financial technology, and relates to a text processing method and device based on artificial intelligence, a computer device and a storage medium, which comprises the following steps: receiving an initial text input by a user; performing encoding processing on the initial text based on a target encoding type to obtain first encoding data; performing language recognition processing on the initial text to obtain corresponding language information; performing encoding processing on the language information based on the target encoding type to obtain second encoding data; splicing the first encoding data and the second encoding data to obtain model input text; calling a regular processing model to perform inference processing on the model input text to generate corresponding regularized text results; and returning the regularized text results to the user. In addition, the regularized text results of the application can be stored in a blockchain. Based on the use of the regular processing model, the complexity and dimension difficulty of the text regular system are effectively reduced, and the multilingual universality of the text regular system is improved.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence development technology and financial technology, and in particular to artificial intelligence-based text processing methods, devices, computer equipment and storage media. Background Technology

[0002] In the field of speech synthesis technology, text regularization is a crucial step that plays a vital role in improving the accuracy and naturalness of speech output. This process encompasses multiple aspects, including spelling error correction, grammatical adjustment, and handling of numbers and special characters, aiming to ensure consistency and fluency of speech output in multilingual environments, thereby optimizing the user experience. Effective implementation of text regularization is not only essential for the performance of speech synthesis applications such as voice assistants and voice navigation, but also has a profound impact on improving the accessibility of the technology.

[0003] However, the current field of text regularization faces numerous challenges, especially in multilingual processing. Traditionally, rule-based multilingual text regularization systems require the design of complex rule sets for each language, which not only increases system complexity but also significantly increases maintenance difficulty. Furthermore, existing rule-based multilingual text regularization methods are significantly inadequate in adapting to multilingual text, struggling to flexibly handle diverse language scenarios and failing to achieve true multilingual universality. This limitation means that when processing text containing multiple linguistic elements, current technologies often fail to achieve ideal regularization results, thus impacting the overall performance of speech synthesis and user experience. Summary of the Invention

[0004] The purpose of this application is to propose a text processing method, apparatus, computer device, and storage medium based on artificial intelligence, in order to solve the technical problem that existing rule-based multilingual text regular expression processing requires the design of complex rule sets for each language, which not only increases the complexity of the system, but also greatly increases the maintenance difficulty, and makes it difficult to flexibly cope with diverse language scenarios and achieve true multilingual universality.

[0005] To address the aforementioned technical problems, this application provides an artificial intelligence-based text processing method, employing the following technical solution:

[0006] Receive initial text input from the user;

[0007] The initial text is encoded based on a preset target encoding type to obtain the corresponding first encoded data.

[0008] The initial text is subjected to language identification processing to obtain the language information corresponding to the initial text;

[0009] The language information is encoded based on the target encoding type to obtain the corresponding second encoded data;

[0010] The first encoded data and the second encoded data are concatenated to obtain the corresponding model input text.

[0011] The pre-built regularization processing model is invoked to perform inference processing on the input text of the model, generating a regularized text result corresponding to the input text of the model;

[0012] The regularized text result is returned to the user.

[0013] Furthermore, the step of encoding the initial text based on a preset target encoding type to obtain the corresponding first encoded data specifically includes:

[0014] Obtain the target processing method corresponding to the target encoding type;

[0015] The initial text is encoded based on the target processing method to obtain the corresponding target encoded data.

[0016] The target encoded data is used as the first encoded data.

[0017] Furthermore, the step of performing language identification processing on the initial text to obtain language information corresponding to the initial text specifically includes:

[0018] Invoke the preset language recognition tool;

[0019] The language identification tool is used to perform language identification processing on the initial text to obtain language tags corresponding to the initial text;

[0020] The language tag returned by the language identification tool is received, and the language tag is used as the language information corresponding to the initial text.

[0021] Furthermore, the step of concatenating the first encoded data and the second encoded data to obtain the corresponding model input text specifically includes:

[0022] Obtain the preset splicing order;

[0023] Based on the splicing order, the first encoded data and the second encoded data are spliced ​​together to obtain the spliced ​​encoded data.

[0024] The concatenated encoded data is used as the input text for the model.

[0025] Furthermore, before the step of calling the pre-built regularization processing model to perform inference processing on the model input text and generating a regularized text result corresponding to the model input text, the method further includes:

[0026] Multilingual text sample data is constructed based on a pre-collected multilingual text dataset;

[0027] Invoke the preset language model;

[0028] The language model is pre-trained based on the multilingual text sample data to obtain the corresponding first language model.

[0029] Obtain pre-built multilingual text regular expression task data;

[0030] The first language model is fine-tuned based on the multilingual text regularization task data to obtain the corresponding second language model.

[0031] The second language model is used as the regular expression processing model.

[0032] Furthermore, the step of constructing multilingual text sample data based on a pre-collected multilingual text dataset specifically includes:

[0033] Call the preset multilingual text data corpus;

[0034] A specified number of multilingual text data are obtained from the multilingual text data corpus to obtain the multilingual text dataset;

[0035] The multilingual text dataset is filtered based on preset data filtering rules to obtain the processed multilingual text dataset.

[0036] The processed multilingual text dataset is used as the multilingual text sample data.

[0037] Furthermore, after the step of calling a pre-built regularization processing model to perform inference processing on the model input text and generating a regularized text result corresponding to the model input text, the method further includes:

[0038] Call the pre-trained speech synthesis model;

[0039] Based on the speech synthesis model, the regularized text result is processed for speech synthesis to obtain speech data corresponding to the regularized text result;

[0040] The speech data is optimized to obtain the corresponding target speech;

[0041] The target speech is returned to the user.

[0042] To address the aforementioned technical problems, this application also provides an artificial intelligence-based text processing device, employing the following technical solution:

[0043] The receiving module is used to receive the initial text input by the user;

[0044] The first processing module is used to encode the initial text based on a preset target encoding type to obtain the corresponding first encoded data.

[0045] The recognition module is used to perform language recognition processing on the initial text to obtain language information corresponding to the initial text;

[0046] The second processing module is used to encode the language information based on the target encoding type to obtain the corresponding second encoded data;

[0047] The splicing module is used to splice the first encoded data and the second encoded data to obtain the corresponding model input text;

[0048] The inference module is used to call a pre-built regularization processing model to perform inference processing on the input text of the model and generate a regularized text result corresponding to the input text of the model.

[0049] The first return module is used to return the regularized text result to the user.

[0050] To address the aforementioned technical problems, this application also provides a computer device that employs the following technical solution:

[0051] Receive initial text input from the user;

[0052] The initial text is encoded based on a preset target encoding type to obtain the corresponding first encoded data.

[0053] The initial text is subjected to language identification processing to obtain the language information corresponding to the initial text;

[0054] The language information is encoded based on the target encoding type to obtain the corresponding second encoded data;

[0055] The first encoded data and the second encoded data are concatenated to obtain the corresponding model input text.

[0056] The pre-built regularization processing model is invoked to perform inference processing on the input text of the model, generating a regularized text result corresponding to the input text of the model;

[0057] The regularized text result is returned to the user.

[0058] To address the aforementioned technical problems, this application also provides a computer-readable storage medium, employing the technical solution described below:

[0059] Receive initial text input from the user;

[0060] The initial text is encoded based on a preset target encoding type to obtain the corresponding first encoded data.

[0061] The initial text is subjected to language identification processing to obtain the language information corresponding to the initial text;

[0062] The language information is encoded based on the target encoding type to obtain the corresponding second encoded data;

[0063] The first encoded data and the second encoded data are concatenated to obtain the corresponding model input text.

[0064] The pre-built regularization processing model is invoked to perform inference processing on the input text of the model, generating a regularized text result corresponding to the input text of the model;

[0065] The regularized text result is returned to the user.

[0066] Compared with the prior art, the embodiments of this application have the following main advantages:

[0067] This application first receives initial text input by a user; then, it encodes the initial text based on a preset target encoding type to obtain corresponding first encoded data; next, it performs language recognition processing on the initial text to obtain language information corresponding to the initial text; and then encodes the language information based on the target encoding type to obtain corresponding second encoded data; subsequently, it concatenates the first encoded data and the second encoded data to obtain the corresponding model input text; further, it calls a pre-built regularization processing model to perform inference processing on the model input text to generate a regularized text result corresponding to the model input text; finally, it returns the regularized text result to the user. This application obtains first encoded data conforming to the input format of the regularization processing model by encoding the initial text based on a target encoding type, and obtains second encoded data conforming to the input format of the regularization processing model by encoding the language information of the initial text based on the target encoding type; concatenates the first encoded data and the second encoded data to obtain the model input text; and then performs inference processing on the model input text based on a pre-built regularization processing model, thereby achieving fast and accurate generation of a regularized text result corresponding to the model input text. Based on the characteristics of target encoding types, this application can support language texts used in most countries around the world, unify the training and inference of various languages, and enable a single regularization processing model to automatically adapt to the text regularization rules of various languages ​​and automatically and accurately output the regularized text results corresponding to the texts of different languages. This effectively reduces the workload of designing independent text regularization rules for each language, reduces the complexity and dimensionality of the text regularization system, and improves the multilingual universality of the text regularization system. Attached Figure Description

[0068] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0069] Figure 1 This is an exemplary system architecture diagram to which this application can be applied;

[0070] Figure 2 A flowchart of an embodiment of the AI-based text processing method according to this application;

[0071] Figure 3 This is a schematic diagram of the structure of an embodiment of the artificial intelligence-based text processing device according to this application;

[0072] Figure 4This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0073] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0074] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0075] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0076] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0077] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc.

[0078] Terminal devices 101, 102, and 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 players (Moving Picture Experts Group Audio Layer IV), laptops, and desktop computers, etc.

[0079] Server 105 can be a server that provides various services, such as a backend server that supports the pages displayed on terminal devices 101, 102, and 103.

[0080] It should be noted that the AI-based text processing method provided in this application is generally executed by a server / terminal device, and correspondingly, the AI-based text processing device is generally located in the server / terminal device.

[0081] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0082] Continue to refer to Figure 2 This document illustrates a flowchart of an embodiment of the AI-based text processing method according to this application. The order of steps in the flowchart can be changed, and some steps can be omitted, depending on different requirements. The AI-based text processing method provided in this application can be applied to any scenario requiring text regularization processing, and thus can be applied to products in these scenarios, such as the regularization processing of financial text data in the financial and insurance fields. The AI-based text processing method includes the following steps:

[0083] Step S201: Receive the initial text input by the user.

[0084] In this embodiment, the AI-based text processing method runs on an electronic device (e.g., Figure 1The server / terminal device shown can acquire the initial text via a wired or wireless connection. It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, Wi-Fi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra-Width band) connections, and other currently known or future wireless connection methods. The implementing entity of this application may specifically be a text regularization processing system. The aforementioned initial text is text that needs to undergo regularization processing. This initial text may contain characters, numbers, special symbols, etc., from multiple languages. For example, in a financial insurance business scenario, the initial text may include transaction text data, payment text data, claims text data, etc.

[0085] Step S202: Encode the initial text based on the preset target encoding type to obtain the corresponding first encoded data.

[0086] In this embodiment, the target encoding type is an encoding type that matches the regular expression processing model. By encoding the initial text based on the target encoding type to obtain the first encoded data, it can be ensured that the regular expression processing model can accurately process various languages ​​and special characters contained in the initial text. The specific implementation process of encoding the initial text based on the preset target encoding type to obtain the corresponding first encoded data will be described in further detail in subsequent embodiments of this application, and will not be elaborated upon here.

[0087] Step S203: Perform language identification processing on the initial text to obtain language information corresponding to the initial text.

[0088] In this embodiment, the specific implementation process of performing language identification processing on the initial text to obtain language information corresponding to the initial text will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0089] Step S204: Encode the language information based on the target encoding type to obtain the corresponding second encoded data.

[0090] In this embodiment, the specific implementation process of encoding the language information based on the target encoding type to obtain the corresponding second encoded data can be referred to the subsequent process of encoding the initial text based on the preset target encoding type to obtain the corresponding first encoded data, which will not be elaborated in detail here.

[0091] Step S205: The first encoded data and the second encoded data are concatenated to obtain the corresponding model input text.

[0092] In this embodiment, the specific implementation process of concatenating the first encoded data and the second encoded data to obtain the corresponding model input text will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here. Specifically, by using the language information of the initial text as a prefix for the model input text, additional contextual information can be provided for the subsequent text regularization processing of the regularization model, enabling a reasoning process that guides the regularization model to perform correct text regularization.

[0093] Step S206: Call the pre-built regularization processing model to perform inference processing on the model input text and generate a regularized text result corresponding to the model input text.

[0094] In this embodiment, the model input text corresponding to the language information of the initial text is input into a pre-built regularization processing model. The regularization processing model performs text regularization tasks based on the input initial text and language information, such as spelling error correction, grammar problem handling, standardization of numbers and special characters, and outputs the regularized text result, thus obtaining the above-mentioned regularized text result.

[0095] Step S207: Return the regularized text result to the user.

[0096] In this embodiment, the user's communication information can be obtained, and the regularized text result can be returned to the user based on this communication information. The communication information may include a mobile phone number or email address.

[0097] This application first receives initial text input by a user; then, it encodes the initial text based on a preset target encoding type to obtain corresponding first encoded data; next, it performs language recognition processing on the initial text to obtain language information corresponding to the initial text; and then encodes the language information based on the target encoding type to obtain corresponding second encoded data; subsequently, it concatenates the first encoded data and the second encoded data to obtain the corresponding model input text; further, it calls a pre-built regularization processing model to perform inference processing on the model input text to generate a regularized text result corresponding to the model input text; finally, it returns the regularized text result to the user. This application obtains first encoded data conforming to the input format of the regularization processing model by encoding the initial text based on a target encoding type, and obtains second encoded data conforming to the input format of the regularization processing model by encoding the language information of the initial text based on the target encoding type; concatenates the first encoded data and the second encoded data to obtain the model input text; and then performs inference processing on the model input text based on a pre-built regularization processing model, thereby achieving fast and accurate generation of a regularized text result corresponding to the model input text. Based on the characteristics of target encoding types, this application can support language texts used in most countries around the world, unify the training and inference of various languages, and enable a single regularization processing model to automatically adapt to the text regularization rules of various languages ​​and automatically and accurately output the regularized text results corresponding to the texts of different languages. This effectively reduces the workload of designing independent text regularization rules for each language, reduces the complexity and dimensionality of the text regularization system, and improves the multilingual universality of the text regularization system.

[0098] In some alternative implementations, step S202 includes the following steps:

[0099] Obtain the target processing method corresponding to the target encoding type.

[0100] In this embodiment, the target encoding type is specifically UTF-8 byte encoding. The target processing method is specifically the st r.encode('utf-8') method.

[0101] The initial text is encoded using the target processing method described above to obtain the corresponding target encoded data.

[0102] In this embodiment, the initial text is converted into the corresponding UTF-8 encoding, i.e., the target encoded data, by executing the st r.encode('utf-8') method.

[0103] The target encoded data is used as the first encoded data.

[0104] This application obtains a target processing method corresponding to the target encoding type; then encodes the initial text based on the target processing method to obtain corresponding target encoded data; subsequently, the target encoded data is used as the first encoded data. By obtaining a target processing method corresponding to the target encoding type and then encodes the initial text based on the use of the target processing method, this application can quickly and accurately generate first encoded data that conforms to the target encoding type. In other words, it intelligently converts the initial text into an acceptable input format for the regular expression processing model, effectively ensuring that the subsequent regular expression processing model can smoothly process the first encoded data.

[0105] In some optional implementations of this embodiment, step S203 includes the following steps:

[0106] Call the preset language recognition tool.

[0107] In this embodiment, the language identification tool can specifically adopt a general language identification library, such as langdetect (Python library) or other similar tools.

[0108] The language identification tool is used to perform language identification processing on the initial text to obtain language tags corresponding to the initial text.

[0109] In this embodiment, the initial text is passed to a language recognition tool to identify the language of the initial text and return the identified language label, such as "en" for English and "zh" for Chinese.

[0110] The language tag returned by the language identification tool is received, and the language tag is used as the language information corresponding to the initial text.

[0111] This application utilizes a pre-defined language recognition tool to process the initial text, obtaining language tags corresponding to the initial text. Subsequently, it receives the language tags returned by the language recognition tool and uses these tags as the language information corresponding to the initial text. By using a language recognition tool to process the initial text, this application achieves rapid and accurate generation of language information corresponding to the initial text, improving both the efficiency and accuracy of language information generation.

[0112] In some alternative implementations, step S205 includes the following steps:

[0113] Get the preset splicing order.

[0114] In this embodiment, the determination of the above-mentioned splicing order is not specifically limited and can be set according to actual business needs. Specifically, the splicing order may be: adding the second encoded data corresponding to the language information before the first encoded data corresponding to the original text, or it may also be: adding the second encoded data corresponding to the language information after the first encoded data corresponding to the original text.

[0115] Based on the splicing order, the first encoded data and the second encoded data are spliced ​​together to obtain the spliced ​​encoded data.

[0116] In this embodiment, the first encoded data and the second encoded data can be concatenated according to the above-described concatenation order to obtain the concatenated encoded data. For example, if the first encoded data corresponding to the original text is b"he llo", and the second encoded data corresponding to the language information is "en", then the concatenated encoded data may be b"enhe llo" or b"he ll oen".

[0117] The concatenated encoded data is used as the input text for the model.

[0118] This application obtains a preset splicing order; then, based on the splicing order, it splices the first encoded data and the second encoded data to obtain spliced ​​encoded data; subsequently, it uses the spliced ​​encoded data as the model input text. This application achieves intelligent and rapid generation of corresponding model input text by splicing the first encoded data and the second encoded data based on the obtained splicing order, thereby improving the generation efficiency and intelligence of model input text.

[0119] In some alternative implementations, prior to step S206, the electronic device may also perform the following steps:

[0120] Multilingual text sample data is constructed based on a pre-collected multilingual text dataset.

[0121] In this embodiment, the specific implementation process of constructing multilingual text sample data based on the pre-collected multilingual text dataset will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0122] Call the preset language model.

[0123] In this embodiment, the language model specifically adopted is the ByT5 model. ByT5 is a pre-trained language model based on the Transformer architecture, which converts all NLP tasks into text-to-text format. Compared to mT5 (multilingual text-to-text transfer converter), ByT5 makes some key architectural changes to directly process byte sequences instead of sub-word token sequences. This includes omitting the SentencePiece vocabulary and directly inputting UTF-8 bytes into the model without any text preprocessing. The ByT5 model uses UTF-8byte encoded input tokens, a move designed to enhance the model's adaptability to multilingual character sets. By using UTF-8byte encoding, the model can more accurately and comprehensively represent characters in various languages, thus better handling the challenges of multilingual text.

[0124] The language model is pre-trained based on the multilingual text sample data to obtain the corresponding first language model.

[0125] In this embodiment, training tasks corresponding to the ByT5 model are pre-constructed. These training tasks include: 1) Self-supervised learning tasks: ByT5 uses self-supervised learning methods for pre-training, including tasks such as fill-in-the-blank and masked language modeling. In the masked language modeling task, the model needs to predict words or byte sequences that are randomly masked in the text. 2) UTF-8 byte encoding: ByT5 operates directly on UTF-8 byte sequences instead of using a traditional vocabulary. This allows the model to handle arbitrary text sequences, including text containing unknown words or special characters.

[0126] Specifically, the training process of the ByT5 model includes training the model using constructed multilingual text sample data. During training, the ByT5 model continuously iterates and optimizes its parameters to better capture semantic information and linguistic features in the text. After training, the resulting first-language model will be capable of processing multilingual text and providing high-quality text representations for downstream tasks.

[0127] During the pre-training phase, ByT5 inherits the self-supervised learning framework of mT5 and is trained on massive amounts of multilingual parallel text data through self-supervised learning methods such as fill-in-the-blank and masking tasks. In this phase, the model learns to map UTF-8byte encoded multilingual text to target language text, which not only strengthens the learning of general representations for multilingual text but also improves its ability to flexibly handle different language character sets and grammatical structures.

[0128] Obtain pre-built multilingual text regular expression task data.

[0129] In this embodiment, to apply the ByT5 model to the text regularization task and optimize its processing capabilities, the ByT5 model needs to be fine-tuned using a labeled dataset containing multilingual text regularization tasks. The labeled dataset includes input text and expected output text relevant to the text regularization task. Furthermore, the labeled dataset is preprocessed (including text encoding and word segmentation) to ensure its format matches the model's input requirements, thus obtaining the aforementioned multilingual text regularization task data.

[0130] The first language model is fine-tuned based on the multilingual text regularization task data to obtain the corresponding second language model.

[0131] In this embodiment, a fine-tuning task for the ByT5 model is pre-built. The fine-tuning task includes: 1) Text regularization task: During the fine-tuning phase, the ByT5 model will be trained for the text regularization task. This includes spelling correction, handling grammatical issues, and normalization of numbers and special characters. 2) Task-specific parameter tuning: Based on the requirements of the fine-tuning task, certain parameters of the model can be adjusted to optimize the model's performance on that task.

[0132] Specifically, the fine-tuning process for the first language model includes: fine-tuning the first language model using the aforementioned multilingual text regularization task data. During the fine-tuning process, the model learns how to transform the input text into the desired output text and continuously optimizes its parameters to improve performance. After fine-tuning, the resulting second language model will be optimized for a specific task, achieving better performance on that task.

[0133] During the fine-tuning phase, ByT5 further optimized the model by using multilingual text regularization task data. UTF-8byte encoded multilingual text was introduced, and the model was adjusted to perform text regularization tasks such as spelling correction, handling grammatical issues, and normalization of numbers and special characters. The purpose of fine-tuning was to precisely adjust the model parameters to better suit the specific needs of multilingual text regularization, thereby achieving higher accuracy and consistency when processing mixed multilingual text.

[0134] The second language model is used as the regular expression processing model.

[0135] In this embodiment, the training process of the ByT5 model is a process from general to specific. In the pre-training phase, the model learns general text representation capabilities through a large-scale multilingual text dataset; in the fine-tuning phase, the model is trained and optimized for a specific task (text regularization task) to improve its performance on that task. This training method enables the ByT5 model to not only process multilingual text but also to efficiently process specific tasks.

[0136] The ByT5 model is used to model multilingual text regularization, simplifying the entire text regularization system process. Leveraging the characteristics of UTF-8, the text regularization system can support texts in most languages ​​used globally. Unifying training and inference across languages ​​allows the system to automatically adapt text rules for various languages ​​using a single model, eliminating the need for manual design and adjustments. Furthermore, introducing multilingual data helps reduce the model's dependence on specific languages; the model simultaneously learns the distribution of each language in the same feature space, improving consistency and effectiveness when handling different languages. In addition, the introduction of multilingual regularization data makes the model more robust; the synergistic effect of regularization modeling across languages ​​enhances the model's generalization ability, thereby improving overall performance and user experience.

[0137] This application constructs multilingual text sample data based on a pre-collected multilingual text dataset; then calls a preset language model; subsequently, it pre-trains the language model based on the multilingual text sample data to obtain a corresponding first language model; next, it acquires pre-constructed multilingual text regularization task data; further, it fine-tunes the first language model based on the multilingual text regularization task data to obtain a corresponding second language model; finally, it uses the second language model as the regularization processing model. This application achieves rapid and accurate training of a regularization processing model capable of processing multiple languages ​​and efficiently handling text regularization tasks, effectively improving the intelligence of the regularization processing model construction and ensuring its performance. Furthermore, the introduction of multilingual regularization data makes the model more adaptable to multiple languages, enabling more accurate processing of text in different languages ​​and ensuring the accuracy and naturalness of speech synthesis in a multilingual environment. Furthermore, the use of regular expression-based models reduces the workload of designing independent text regularization rules for each language, improving the versatility of the text regularization system. This helps reduce the deployment and maintenance costs of speech synthesis applications. In multilingual environments, the improved text regularization system can process text from different languages, providing more universal and widely applicable speech synthesis services to global users, which is particularly important for cross-cultural and multi-context applications.

[0138] In some optional implementations of this embodiment, constructing multilingual text sample data based on a pre-collected multilingual text dataset includes the following steps:

[0139] Call the preset multilingual text data corpus.

[0140] In this embodiment, the ByT5 model is typically pre-trained using a large multilingual text dataset. Specifically, the multilingual text corpus can be the mC4 corpus, which is a large, unlabeled multilingual text corpus.

[0141] A specified number of multilingual text data are obtained from the multilingual text data corpus to obtain the multilingual text dataset.

[0142] In this embodiment, the specified number is not specifically limited and can be set according to the actual model training requirements. The multilingual text dataset contains a large amount of diverse text, covering multiple languages.

[0143] The multilingual text dataset is filtered based on preset data filtering rules to obtain the processed multilingual text dataset.

[0144] In this embodiment, the data filtering rules include data filtering processing to remove noise, duplicates and useless information. By using data filtering rules to filter the multilingual text dataset, the quality and diversity of the processed multilingual text dataset can be ensured.

[0145] The processed multilingual text dataset is used as the multilingual text sample data.

[0146] This application obtains a multilingual text dataset by calling a pre-defined multilingual text data corpus; then, it obtains a specified number of multilingual text data from the corpus; subsequently, it filters the multilingual text dataset based on pre-defined data filtering rules to obtain a processed multilingual text dataset; finally, it uses the processed multilingual text dataset as multilingual text sample data. By obtaining a specified number of multilingual text data from a pre-defined multilingual text data corpus to obtain the multilingual text dataset, and then filtering the dataset based on pre-defined data filtering rules, this application can quickly and accurately construct multilingual text sample data for pre-training language models, effectively ensuring the quality and diversity of the obtained multilingual text sample data.

[0147] In some optional implementations of this embodiment, after step S206, the electronic device may further perform the following steps:

[0148] Call the pre-trained speech synthesis model.

[0149] In this embodiment, the selection of the aforementioned speech synthesis model is not specifically limited and can be determined according to the actual needs of the speech synthesis task. For example, any one of the following can be used as the speech synthesis model: a speech synthesis model based on statistical parameter modeling (such as HMM-based), a speech synthesis model based on deep learning (such as RNN, CNN, Transformer, etc.), or an end-to-end speech synthesis model (such as Tacotron, FastSpeech, etc.). Specifically, the training process of the speech synthesis model includes: training the model using a large amount of labeled speech data. The labeled speech data includes text and corresponding speech waveforms. During the training process, the model learns the mapping relationship from text to speech, including features such as pronunciation, intonation, and speech rate, and finally obtains the trained speech synthesis model.

[0150] The speech synthesis model is used to process the regularized text result into speech data to obtain the speech data corresponding to the regularized text result.

[0151] In this embodiment, the regularized text result is input into the speech synthesis model, which then generates a corresponding speech waveform, i.e., the aforementioned speech data, based on the input regularized text result. The speech waveform generation process includes multiple steps such as text-to-phoneme conversion, acoustic feature prediction, and waveform generation.

[0152] The speech data is optimized to obtain the corresponding target speech.

[0153] In this embodiment, the above optimization process may include noise reduction and smoothing. By optimizing the speech data, the speech quality of the obtained target speech can be effectively improved.

[0154] The target speech is returned to the user.

[0155] In this embodiment, the target voice can be returned to the user by acquiring the user's communication information. This communication information may include a mobile phone number or a communication address.

[0156] This application automatically performs speech synthesis processing on the user's input text by calling a pre-trained speech synthesis model; then, based on the speech synthesis model, it performs speech synthesis processing on the regularized text result to obtain speech data corresponding to the regularized text result; subsequently, it optimizes the speech data to obtain the corresponding target speech; and finally, it returns the target speech to the user. After calling a pre-built regularization processing model to perform inference processing on the model input text and generate a regularized text result corresponding to the model input text, this application intelligently calls a pre-trained speech synthesis model to perform speech synthesis processing on the regularized text result to obtain speech data corresponding to the regularized text result, optimizes the speech data to obtain the corresponding target speech, and then returns the target speech to the user. This achieves automatic speech synthesis processing of the user's initial input text, eliminating the need for the user to perform speech synthesis processing again, thus improving user efficiency and user experience.

[0157] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0158] It should be emphasized that, in order to further ensure the privacy and security of the above-mentioned regularized text results, the above-mentioned regularized text results can also be stored in a node of a blockchain.

[0159] The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0160] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. 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 that knowledge to obtain optimal results.

[0161] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0162] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0163] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0164] Further reference Figure 3 As a response to the above Figure 2 The implementation of the method shown in this application provides an embodiment of an artificial intelligence-based text processing device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0165] like Figure 3 As shown, the AI-based text processing device 300 described in this embodiment includes: a receiving module 301, a first processing module 302, a recognition module 303, a second processing module 304, a splicing module 305, an inference module 306, and a first return module 307. Wherein:

[0166] The receiving module 301 is used to receive the initial text input by the user;

[0167] The first processing module 302 is used to encode the initial text based on a preset target encoding type to obtain the corresponding first encoded data.

[0168] The recognition module 303 is used to perform language recognition processing on the initial text to obtain language information corresponding to the initial text;

[0169] The second processing module 304 is used to encode the language information based on the target encoding type to obtain the corresponding second encoded data.

[0170] The splicing module 305 is used to splice the first encoded data and the second encoded data to obtain the corresponding model input text;

[0171] The reasoning module 306 is used to call a pre-built regularization processing model to perform reasoning processing on the model input text and generate a regularized text result corresponding to the model input text.

[0172] The first return module 307 is used to return the regularized text result to the user.

[0173] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based text processing method in the aforementioned embodiments, and will not be repeated here.

[0174] In some optional implementations of this embodiment, the first processing module 302 includes:

[0175] The first acquisition submodule is used to acquire the target processing method corresponding to the target encoding type;

[0176] The encoding submodule is used to encode the initial text based on the target processing method to obtain the corresponding target encoded data;

[0177] The first determining submodule is used to use the target encoded data as the first encoded data.

[0178] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based text processing method in the aforementioned embodiments, and will not be repeated here.

[0179] In some optional implementations of this embodiment, the identification module 303 includes:

[0180] The first submodule is used to invoke the preset language recognition tool;

[0181] The identification submodule is used to perform language identification processing on the initial text using the language identification tool to obtain language tags corresponding to the initial text.

[0182] The second determining submodule is used to receive the language tag returned by the language identification tool and use the language tag as the language information corresponding to the initial text.

[0183] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based text processing method in the aforementioned implementation method, and will not be repeated here.

[0184] In some optional implementations of this embodiment, the splicing module 305 includes:

[0185] The second acquisition submodule is used to acquire the preset splicing order;

[0186] The splicing submodule is used to splice the first encoded data and the second encoded data based on the splicing order to obtain the spliced ​​encoded data;

[0187] The third determining submodule is used to use the concatenated encoded data as the input text of the model.

[0188] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based text processing method in the aforementioned embodiments, and will not be repeated here.

[0189] In some optional implementations of this embodiment, the AI-based text processing device further includes:

[0190] The building module is used to construct multilingual text sample data based on a pre-collected multilingual text dataset;

[0191] The first calling module is used to call the preset language model;

[0192] The pre-training module is used to pre-train the language model based on the multilingual text sample data to obtain the corresponding first language model.

[0193] The acquisition module is used to acquire pre-built multilingual text regular expression task data;

[0194] The fine-tuning module is used to fine-tune the first language model based on the multilingual text regularization task data to obtain the corresponding second language model.

[0195] A determination module is used to use the second language model as the regularization processing model.

[0196] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based text processing method in the aforementioned embodiments, and will not be repeated here.

[0197] In some optional implementations of this embodiment, the building module includes:

[0198] The second calling submodule is used to call a preset multilingual text data corpus;

[0199] The third acquisition submodule is used to acquire a specified number of multilingual text data from the multilingual text data corpus to obtain the multilingual text dataset;

[0200] The filtering submodule is used to filter the multilingual text dataset based on preset data filtering rules to obtain the processed multilingual text dataset.

[0201] The fourth determination submodule is used to use the processed multilingual text dataset as the multilingual text sample data.

[0202] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based text processing method in the aforementioned embodiments, and will not be repeated here.

[0203] In some optional implementations of this embodiment, the AI-based text processing device further includes:

[0204] The second calling module is used to call the pre-trained speech synthesis model;

[0205] The synthesis module is used to perform speech synthesis processing on the regularized text result based on the speech synthesis model to obtain speech data corresponding to the regularized text result.

[0206] The optimization module is used to optimize the speech data to obtain the corresponding target speech;

[0207] The second return module is used to return the target voice to the user.

[0208] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the artificial intelligence-based text processing method in the aforementioned embodiments, and will not be repeated here.

[0209] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0210] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected via a system bus. It should be noted that only the computer device 4 with components 41-43 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), digital digital processors (DSPs), embedded devices, etc.

[0211] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0212] The memory 41 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as the hard disk or memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, smart memory card (SMC), secure digital card (SD) card, flash card, etc. of the computer device 4. Of course, the memory 41 may also include both the internal storage unit and the external storage device of the computer device 4. In this embodiment, the memory 41 is typically used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions for text processing methods based on artificial intelligence. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or will be output.

[0213] In some embodiments, the processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to execute computer-readable instructions stored in the memory 41 or to process data, for example, to execute computer-readable instructions of the artificial intelligence-based text processing method.

[0214] The network interface 43 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 4 and other electronic devices.

[0215] Compared with the prior art, the embodiments of this application have the following main advantages:

[0216] In this embodiment, the initial text is encoded based on a target encoding type to obtain first encoded data conforming to the input format of the regularization model, and the language information of the initial text is encoded based on the target encoding type to obtain second encoded data conforming to the input format of the regularization model. The first and second encoded data are then concatenated to obtain the model input text. This input text is then used for inference processing based on a pre-built regularization model, thereby enabling the rapid and accurate generation of regularized text results corresponding to the model input text. Based on the characteristics of the target encoding type, this application can support language texts used in most countries worldwide, unifying the training and inference for various languages. This allows a single regularization model to automatically adapt to the text regularization rules of various languages ​​and automatically and accurately output regularized text results corresponding to texts in different languages. This effectively reduces the workload of designing independent text regularization rules for each language, lowers the complexity and dimensionality of the text regularization system, and improves the multilingual versatility of the text regularization system.

[0217] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the artificial intelligence-based text processing method described above.

[0218] Compared with the prior art, the embodiments of this application have the following main advantages:

[0219] In this embodiment, the initial text is encoded based on a target encoding type to obtain first encoded data conforming to the input format of the regularization model, and the language information of the initial text is encoded based on the target encoding type to obtain second encoded data conforming to the input format of the regularization model. The first and second encoded data are then concatenated to obtain the model input text. This input text is then used for inference processing based on a pre-built regularization model, thereby enabling the rapid and accurate generation of regularized text results corresponding to the model input text. Based on the characteristics of the target encoding type, this application can support language texts used in most countries worldwide, unifying the training and inference for various languages. This allows a single regularization model to automatically adapt to the text regularization rules of various languages ​​and automatically and accurately output regularized text results corresponding to texts in different languages. This effectively reduces the workload of designing independent text regularization rules for each language, lowers the complexity and dimensionality of the text regularization system, and improves the multilingual versatility of the text regularization system.

[0220] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0221] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A text processing method based on artificial intelligence, characterized in that, Includes the following steps: Receive initial text input from the user; The initial text is encoded based on a preset target encoding type to obtain the corresponding first encoded data. The initial text is subjected to language identification processing to obtain the language information corresponding to the initial text; The language information is encoded based on the target encoding type to obtain the corresponding second encoded data; The first encoded data and the second encoded data are concatenated to obtain the corresponding model input text. The pre-built regularization processing model is invoked to perform inference processing on the input text of the model, generating a regularized text result corresponding to the input text of the model; The regularized text result is returned to the user; The step of calling a pre-built regularization processing model to perform inference processing on the model input text and generating a regularized text result corresponding to the model input text further includes: Multilingual text sample data is constructed based on a pre-collected multilingual text dataset; Invoke the preset language model; The language model is pre-trained based on the multilingual text sample data to obtain the corresponding first language model. Obtain pre-built multilingual text regular expression task data; The first language model is fine-tuned based on the multilingual text regularization task data to obtain the corresponding second language model. The second language model is used as the regularization model; The fine-tuning task of the pre-built language model includes: text regularization task: During the fine-tuning phase, the language model will be trained for the text regularization task, which includes spelling error correction, handling grammatical problems, and normalization of numbers and special characters; task-specific parameter adjustment: According to the requirements of the fine-tuning task, some parameters of the model are adjusted to optimize the model's performance on the task; Specifically, the process of fine-tuning the first language model includes: using the above-mentioned multilingual text regularization task data to fine-tune the first language model; During the fine-tuning process, the model will learn how to transform the input text into the desired output text and continuously optimize its parameters to improve performance. After the fine-tuning is completed, the resulting second language model will be optimized for the specific task and will be able to achieve better performance on the task.

2. The text processing method based on artificial intelligence according to claim 1, characterized in that, The step of encoding the initial text based on a preset target encoding type to obtain the corresponding first encoded data specifically includes: Obtain the target processing method corresponding to the target encoding type; The initial text is encoded based on the target processing method to obtain the corresponding target encoded data. The target encoded data is used as the first encoded data.

3. The text processing method based on artificial intelligence according to claim 1, characterized in that, The step of performing language identification processing on the initial text to obtain language information corresponding to the initial text specifically includes: Invoke the preset language recognition tool; The language identification tool is used to perform language identification processing on the initial text to obtain language tags corresponding to the initial text; The language tag returned by the language identification tool is received, and the language tag is used as the language information corresponding to the initial text.

4. The text processing method based on artificial intelligence according to claim 1, characterized in that, The step of concatenating the first encoded data and the second encoded data to obtain the corresponding model input text specifically includes: Obtain the preset splicing order; Based on the splicing order, the first encoded data and the second encoded data are spliced ​​together to obtain the spliced ​​encoded data. The concatenated encoded data is used as the input text for the model.

5. The text processing method based on artificial intelligence according to claim 1, characterized in that, The steps for constructing multilingual text sample data based on a pre-collected multilingual text dataset specifically include: Call the preset multilingual text data corpus; A specified number of multilingual text data are obtained from the multilingual text data corpus to obtain the multilingual text dataset; The multilingual text dataset is filtered based on preset data filtering rules to obtain the processed multilingual text dataset. The processed multilingual text dataset is used as the multilingual text sample data.

6. The text processing method based on artificial intelligence according to claim 1, characterized in that, After the step of calling a pre-built regularization processing model to perform inference processing on the model input text and generating a regularized text result corresponding to the model input text, the method further includes: Call the pre-trained speech synthesis model; Based on the speech synthesis model, the regularized text result is processed for speech synthesis to obtain speech data corresponding to the regularized text result; The speech data is optimized to obtain the corresponding target speech; The target speech is returned to the user.

7. A text processing device based on artificial intelligence, characterized in that, include: The receiving module is used to receive the initial text input by the user; The first processing module is used to encode the initial text based on a preset target encoding type to obtain the corresponding first encoded data. The recognition module is used to perform language recognition processing on the initial text to obtain language information corresponding to the initial text; The second processing module is used to encode the language information based on the target encoding type to obtain the corresponding second encoded data; The splicing module is used to splice the first encoded data and the second encoded data to obtain the corresponding model input text; The inference module is used to call a pre-built regularization processing model to perform inference processing on the input text of the model and generate a regularized text result corresponding to the input text of the model. The first return module is used to return the regularized text result to the user; Among them, the AI-based text processing device also includes: The building module is used to construct multilingual text sample data based on a pre-collected multilingual text dataset; The first calling module is used to call the preset language model; The pre-training module is used to pre-train the language model based on the multilingual text sample data to obtain the corresponding first language model. The acquisition module is used to acquire pre-built multilingual text regular expression task data; The fine-tuning module is used to fine-tune the first language model based on the multilingual text regularization task data to obtain the corresponding second language model. A determining module is used to use the second language model as the regularization processing model; The fine-tuning task of the pre-built language model includes: text regularization task: During the fine-tuning phase, the language model will be trained for the text regularization task, which includes spelling error correction, handling grammatical problems, and normalization of numbers and special characters; task-specific parameter adjustment: According to the requirements of the fine-tuning task, some parameters of the model are adjusted to optimize the model's performance on the task; Specifically, the process of fine-tuning the first language model includes: using the above-mentioned multilingual text regularization task data to fine-tune the first language model; During the fine-tuning process, the model will learn how to transform the input text into the desired output text and continuously optimize its parameters to improve performance. After the fine-tuning is completed, the resulting second language model will be optimized for the specific task and will be able to achieve better performance on the task.

8. A computer device comprising a memory and a processor, the memory storing computer-readable instructions, wherein the processor, when executing the computer-readable instructions, implements the steps of the artificial intelligence-based text processing method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the artificial intelligence-based text processing method as described in any one of claims 1 to 6.

Images