35 results about "Proper noun" patented technology

The invention discloses a proper noun speech recognition processing method based on instant messaging and a computer device. The method comprises the following steps: firstly, constructing annotation data sets of different scenes and a user-specific custom word list, and dynamically obtaining related data and a hot word list according to a to-be-recognized voice scene; afterwards, a training voice recognition model is subjected to fine tuning by using the annotation data set to obtain a first model, and after a recognition instruction is received, a hot word list is loaded for recognition to obtain a voice initial recognition text; and after the initial recognition text is obtained, dynamic optimization is carried out by utilizing a user-specific custom word list, and recognition errors are corrected. According to the method, matching data can be dynamically obtained, the model is combined with a scene to understand proper nouns, and the recognition difficulty caused by pronunciation and meaning complexity is reduced; in combination with targeted data and hot word information training, the proper noun recognition accuracy is improved, the defects of an existing model error correction mechanism are overcome, the accuracy of a final recognition result is remarkably improved, and powerful support is provided for speech recognition and subsequent application.

The invention provides a context adaptive speech recognition method integrating entity replication and vector retrieval, and belongs to the technical field of artificial intelligence. The method comprises the following steps: converting input voice into acoustic feature representation; converting the external entity dictionary into vector representation; screening out candidate entities through an index technology, and determining to generate output or copy entities from a standard word list according to a matching degree calculated by an attention mechanism; jointly optimizing the model by comprehensively optimizing the objective function, wherein acoustic modeling, language modeling, entity copying accuracy and entity distinguishing capability are included; continuously updating the index during training; in reasoning, in combination with beam search and confidence threshold mechanisms, selection is made between generation of outputs from a standard word list and copying of entities. In the aspect of recognition performance, a dynamic copy-generation fusion mechanism and a contrast learning strategy are adopted in the method, the accuracy of named entity recognition is effectively improved, particularly, the method is excellent in performance when proper nouns such as personal names and place names are processed, and meanwhile the distinguishing capacity for entities similar in pronunciation is enhanced.

The embodiment of the invention discloses a wrongly written character processing method, device and equipment, and the method comprises the steps: receiving text data of a target domain input by a user, the text data comprising special words of the target domain; performing word segmentation processing on the text data through a preset word segmentation strategy aiming at a target field, and performing identification processing aiming at special words of the target field on segmented words corresponding to the obtained text data to obtain target special words in the segmented words corresponding to the text data; carrying out wrongly written character recognition processing on the target proprietary word through a proprietary word error recognition model for the target field to obtain a first recognition result, and carrying out wrongly written character recognition processing on segmented words, except the target proprietary word, in the segmented words corresponding to the text data through a general word error recognition model to obtain a second recognition result; and based on the first recognition result and the second recognition result, determining wrongly written character information contained in the text data through fusion processing of the two different recognition results.

The present disclosure provides a text translation method, a server, a storage medium, and a program product. The method relates to the field of artificial intelligence, and comprises: acquiring an original text to be translated and a target language; searching a translation database for a translation text pair matching the original text, the translation text pair comprising a source language text and a target language text; and inputting the original text, the target language, and the translation text pair into a text translation model, translating, by means of the text translation model, a source language text appearing in the original text into a corresponding target language text, and generating a translated text in the target language corresponding to the original text. By performing external knowledge intervention on a text translation model on the basis of a pre-customized translation database, incorrect translations of custom vocabularies are effectively avoided without needing to retrain parameters of the text translation model, and the accuracy of translation of the text translation model for custom vocabularies such as proper nouns, terminology, and new terms can be improved, thereby improving the accuracy of text translation results.

The invention discloses a railway signal fault text enhancement method, system and device based on improved EDA, and the method comprises the following steps: constructing a railway field entity dictionary, carrying out the proper noun recognition of a preprocessed to-be-enhanced railway signal fault text, and outputting a structured text; on the basis of a railway signal fault related text data set, a similar word bank of railway signal fault text related vocabularies is generated by adopting a Word2Vec model and used for replacing non-professional vocabularies in railway signal fault text statements, and enhancement operation is performed on the basis of a structured text and the similar word bank of the railway signal fault text related vocabularies by adopting an EDA improvement method. Enhancing the railway signal fault text to be enhanced; and screening the enhanced railway signal fault text. According to the method, the integrity and accuracy of domain terms are ensured through an entity fixing mechanism, an enhanced sample conforming to a real scene is generated in combination with a semantic constraint editing strategy, and the problem of unbalanced data distribution is effectively solved.

The invention provides a translation method and a translation system. According to the translation method, firstly, a predefined text knowledge base is adopted to preprocess text segments needing to be precisely processed in a to-be-translated text, so that a prompt of an AI large language model contains a consistent text comparison table customized for the to-be-translated text; wherein fixed translation of specific text segments (such as proper nouns, phrases or sentences) in a to-be-translated text in a target language is defined; and translating the preprocessed text by adopting the AI large language model. The long text such as the novel can be segmented into chapters and sections by adopting an automatic text segmentation technology before translation, and the translated texts of all the chapters and sections are recombined into a target file. According to the technical scheme, the automatic text segmentation technology and a cooperation mechanism of text consistency preprocessing and comparison table guiding type Prompt guidance are combined, the problems of key expression inconsistency, semantic drift and the like occurring in long text translation are effectively avoided, and the continuity and readability of translated texts are improved.

The invention provides a speech translation method, a server, a storage medium and a program product. The method relates to the field of artificial intelligence. The method comprises the following steps: acquiring original voice of a to-be-translated original language and a to-be-translated target language; and searching translation knowledge matched with the original voice in a translation knowledge base, inputting the original voice and the translation knowledge matched with the original voice into a voice translation model, translating the original language voice in the translation knowledge appearing in the original voice into a corresponding target language text through the voice translation model, and generating a translation text of the target language. On the basis of a cross-modal translation knowledge base, external knowledge intervention is carried out on the speech translation model, translation errors of customized vocabularies are effectively avoided on the premise that parameters of the speech translation model do not need to be retrained, the translation accuracy of the speech translation model to customized vocabularies such as proper nouns, terminologies and new words is improved, and the translation efficiency is improved. Therefore, the accuracy of the speech translation result is improved.

This invention relates to a prompt-based machine translation method, belonging to the field of natural language processing technology. It solves the problems of inaccurate, omitted, and mistranslated nouns and proper nouns in existing machine translation models. By constructing a set of nouns and their translations from the text to be translated, the input text and adjustment matrix of the translation model are obtained. The translation model is then used to translate the input text, and the attention calculation of the model is adjusted using the adjustment matrix M, ultimately outputting the translation. Based on the input data containing noun translation prompts and the adjustment matrix, the accuracy of the noun translation by the translation model is guaranteed to a certain extent, solving the problems of omitted and mistranslated nouns, and improving the accuracy of noun translation in machine translation models.

The invention discloses an electric power material supply chain material semantic retrieval method based on large language model seed problem expansion, and provides a seed problem text expansion technology in an electric power material supply chain material low-resource scene by utilizing semantic understanding and text generation capability of a large language model. Intelligent rewriting and expansion are performed by using a very small amount of seed problems, so that the problem of difficulty in semantic retrieval of complex proper nouns and domain terms is solved, and the adaptability of the system to specific fields such as the power industry is enhanced; according to the method, the text training data is expanded, manual intervention and manual labeling are avoided, and the automation level of the system is improved.

The system according to the embodiment comprises a reception unit, an analysis unit, a suggestion unit, and a selection unit. The reception unit is configured to receive a user input. The analysis unit is configured to analyze context based on the input received by the reception unit. The suggestion unit is configured to suggest proper nouns based on the context analyzed by the analysis unit. The selection unit is configured to allow the user to select the proper noun suggested by the suggestion unit.

The invention discloses a polyphone disambiguation method based on a pointer network and context adaptive modeling, and relates to the technical field of natural language processing and intelligent text processing. According to the method, context range labels and category labels associated with polyphones are predicted at the same time through a pointer network, so that self-adaptive recognition of context granularity required by decision making is achieved. According to different category labels, a local disambiguation process, a global disambiguation process and a proper noun processing process are respectively constructed according to the method: the local process realizes pronunciation judgment of adjacent word levels based on dictionary retrieval and semantic similar word acquisition; the global process is combined with a large language model and a hierarchical semantic dictionary to realize sentence-level semantic-driven pronunciation generation; and the name and place name categories are deduced by directly utilizing entity knowledge of the language model. In addition, the invention further provides a paraphrase enhancement module oriented to an ancient language scene, and through combined modeling of comparative learning and example learning of sentences of the same pronunciation, the model can stably distinguish different pronunciations in an ancient language text and generate corresponding paraphrases. According to the method, the optimal disambiguation path can be automatically selected according to the context dependence characteristics of different polyphones, the accuracy and generalization ability of polyphone pronunciation prediction are effectively improved, and the method is suitable for various text scenes such as modern Chinese and ancient Chinese.

The application relates to an artificial intelligence technology and discloses a question expansion method and device, equipment and a storage medium. The method comprises the following steps: extracting an inquiry mode word and an entity noun in a to-be-expanded question; extracting a standard question containing the inquiry mode word and a synonymous question with the same meaning as the standard question in a question and answer library, and marking the inquiry mode word and the inquiry mode word contained in the synonymous question as a keyword; performing word segmentation and part-of-speech tagging on the standard question and the synonymous question to obtain a sentence structure; extracting a front adjacent substantive word and a rear adjacent substantive word of the keyword in the standard question and the synonymous question according to the sentence structure; extracting the inquiry mode word in the keyword, and extracting the front adjacent substantive word and the rear adjacent substantive word; and according to the keyword, the front adjacent substantive word, the rear adjacent substantive word and the proper noun, composing a preset number of expansion questions in a preset grammar format. The application can automatically generate expansion questions according to an input question.

The invention relates to the technical field of artificial intelligence, in particular to a dynamic dictionary generation and hot update method and system based on conference contexts.In the method, conference context information is automatically obtained, the context information is preprocessed, domain terms related to a conference theme are obtained through domain term extraction; the domain terms and the selectable corresponding weights are constructed into a structured session-level dynamic dictionary, the dynamic dictionary is loaded to an ASR engine at the beginning of a conference or in the real-time transcription process, and recognition and transcription are conducted on the conference real-time voice stream based on the ASR engine subjected to hot updating. By applying the method, efficient and accurate identification of proper nouns and domain terms in a specific conference scene can be realized, the problem of low accuracy is solved, and personalized identification optimization of each conference is realized.

The application discloses a text analysis method and device, a storage medium and a program product, relates to the technical field of artificial intelligence, and comprises the following steps: performing character mention (character proper noun, third person pronoun and character generic phrase) detection on a target text, performing coreference resolution on the detected character mention to determine character mentions that point to the same role; for each quotation in the target text, identifying whether the quotation belongs to dialogue content based on a text sequence containing the quotation and context before and after the quotation, and identifying the speaker and the listener of the quotation when the quotation belongs to the dialogue content; if the quotation belongs to the dialogue content, identifying the first person pronoun and the second person pronoun in the quotation, pointing the identified first person pronoun to the same role as the speaker of the quotation, and pointing the identified second person pronoun to the same role as the listener of the quotation. The application improves the accuracy of role identification.

The invention discloses an intelligent text error correction and term extraction system based on multi-model fusion, and belongs to the technical field of natural language processing. The technical problems that multi-source text coding compatibility is poor, professional term recognition accuracy is low, and error correction quality and efficiency are difficult to balance are solved. According to the technical principle, text standardization is achieved through multi-code compatible preprocessing; a proper noun library containing standard terms, error variants and semantic description is constructed, and millisecond-level retrieval is achieved through vectorization indexing; dynamically injecting a context by adopting an RAG enhancement mechanism; and performing dual optimization by weighting and fusing output results of the three pre-training models and combining model output consistency constraint and performance boundary control. And efficient and accurate text processing is realized through multi-module cooperation and multi-model fusion.

The application provides a question answering method and device based on a proper noun, which can be used in the financial field or other technical fields. The method comprises the following steps: receiving an inquiry request sent by a client, wherein the inquiry request comprises a consultation question; if it is determined that the consultation question comprises a proper noun based on a proper noun list, querying corresponding related information according to the proper noun comprised in the consultation question as reply information of the consultation question; wherein the proper noun list is obtained in advance; and returning the reply information of the consultation question to the client. The device is used for executing the above method. The question answering method and device based on a proper noun provided in the embodiment of the application improve the accuracy of the reply to the consultation question.

1. Name of the product in this design: Original audio translation and subtitle editing module for a video creation graphical user interface of an electronic device. 2. Application of this design: This design is intended for use in an electronic device. 3. The key design features of this product are the graphical user interface portion for which protection is sought. 4. The image or photograph that best illustrates the design's key features: the front view. 5. Uses of the graphical user interface: Overall use: video creation interaction; Local use: enabling users to edit AI-translated subtitles and translated subtitles, generate and preview AI dubbing results, and add proper nouns and translations through changes in user operations. 6. Other situations requiring explanation are illustrated in the following figures: This design protects the original audio translation subtitle editing module; as shown in the main view, the left side is the text editing area, and the right side is the video preview area, supporting operations such as original audio subtitle translation editing, generating dubbing, and previewing; clicking the "Proper Nouns" option will bring up a pop-up window, as shown in the changing state diagram, where commonly used nouns and their corresponding translations can be entered, modified, added, or deleted; the usage state reference diagram shows the effect of displaying this user interface, and the main view and changing state diagram correspond to usage state reference diagrams 1-2 respectively.

This invention discloses a hierarchical collaborative method and system for secure reasoning using a large language model, belonging to the field of secure reasoning technology for large models. The method includes: on the client side, firstly, named entity recognition is performed on the original document, and sensitive proper nouns are replaced with secure generalized descriptors based on entity type and differential privacy mechanisms, generating an intermediate document and entity type metadata; subsequently, the intermediate document undergoes lexical-level differential privacy semantic perturbation to generate a perturbed document; the perturbed document is sent to a cloud-based large language model to obtain the initial generated text; finally, on the client side, a local lightweight model is used to generate high-quality final text based on entity type metadata, context, and the initial text returned from the cloud. This invention, through a hierarchical collaborative privacy protection framework and under provable differential privacy protection, solves the problem of balancing proper noun protection and generation quality, and is suitable for secure reasoning scenarios involving sensitive texts in finance, healthcare, and other fields.

This application proposes a task processing method, apparatus, electronic device, chip, and storage medium, relating to the field of artificial intelligence. The method includes: hierarchically marking the long text based on its text type to obtain multi-level hierarchical marking information; generating first contextual information based on the multi-level hierarchical marking information; the first contextual information indicating the text structure and logical relationships of the long text; splitting the long text based on the first contextual information to obtain at least one sub-text; performing a processing task on the sub-text according to the multi-level hierarchical marking information and the first contextual information to obtain the processing result of the sub-text; and fusing the processing results of each sub-text to generate the processing result of the processing task. This not only avoids problems such as referential breaks, logical misalignments, or proper noun fragmentation caused by forced truncation, but also enhances the understanding of cross-paragraph dependencies and global semantic structure.

Embodiments of the present application provide a kind of identification method of procurement category, computer equipment and storage medium, the method comprises: obtaining first procurement demand text, and procurement proper noun set;Based on the first procurement demand text, the corresponding stop word set is obtained;Based on the procurement proper noun set and the stop word set, the first procurement demand text is carried out word segmentation operation, and the first keyword set is obtained;The first keyword set is vectorized representation, and the first keyword set after vectorization is input into the target category identification model pre-trained, and the category identification result is obtained.The embodiments of the present application aim to identify procurement demand text based on target category identification model, to obtain the identification result with higher accuracy.Especially for the category identification of medical consumables in the procurement process, the category identification efficiency of medical consumables and the accuracy of category identification result can be improved.

The invention discloses a method for injecting an external knowledge base into a language model with a loop architecture, and the method comprises the steps: firstly carrying out the intelligent segmentation and three-wheel semantic processing of the external knowledge base, extracting and screening key proper nouns, and generating a structured triple; converting the triple into a key / value basic vector by using a pre-training sentence encoder, and mapping the key / value basic vector to an embedding space of an RWKV model through a parameter efficient adapter to form a read-only knowledge key value tensor; in the reasoning stage, a cyclic rectangular attention mechanism is innovatively provided, the mechanism serves as a bridge between a knowledge token of KBLAM and a cyclic state of an RWKV model, and an external knowledge base can be injected into a language model with a cyclic architecture; in the training stage, the illusion is effectively inhibited by adopting a synthetic knowledge base and an instruction fine tuning strategy containing a rejection sample. According to the method, the defects of the large-scale language model of the loop architecture in the aspects of knowledge timeliness, accuracy and vertical field adaptation can be overcome.

To suppress a risk of information leakage that may occur due to use of an external service.SOLUTION: An information processing system S according to an embodiment includes a proper noun detection section 103 that detects a proper noun from one or a plurality of sentences when execution of a predetermined process on a processing target sentence including one or a plurality of sentences is instructed, a converted sentence generation section 104 that generates a converted sentence by converting the proper noun detected by the proper noun detection section 103 into another proper noun in a sentence in which a proper noun is detected by the proper noun detection section 103 in the processing target sentence, and a query generation section 105 that generates a query including a processing requesting sentence in which a sentence in which a proper noun is detected by the proper noun detection section 103 in the processing target sentence is replaced with the converted sentence and a sentence in which a proper noun is not detected by the proper noun detection section 103 in the processing target sentence is maintained as it is and an execution request of the predetermined process on the processing requesting sentence.SELECTED DRAWING: Figure 2

Examples relate to a system including a processor that can perform certain operations. The operations can include obtaining input text. The operations also can include generating a set of vectors from an ensemble of machine-learning models based on the input text. The ensemble of machine-learning models can include a pre-trained language model configured to determine capitalization for mixed cases and acronyms, a pre-trained named entity recognition (NER) model configured to determine capitalization for general proper nouns, and a question-answer NER (QA-NER) model configured to determine capitalization for brand names. The QA-NER model can include a transformer language model and a linear layer. The operations additionally can include generating corrected sentence-case text by modifying capitalization of the input text based on the set of vectors and outputting the corrected sentence-case text on a draft advertisement user interface. Other embodiments are described.

The invention provides a text translation method, a server, a storage medium and a program product. The method relates to the field of artificial intelligence, and comprises the steps of obtaining a to-be-translated original text and a target language; searching a translation text pair matched with the original text in a translation database, wherein the translation text pair comprises an original language text and a target language text; the method comprises the following steps: inputting an original text, a target language and a translated text pair into a text translation model, translating an original language text appearing in the original text into a corresponding target language text through the text translation model, and generating a translated text of the target language corresponding to the original text; according to the method, external knowledge intervention is carried out on the text translation model, translation errors of customized vocabularies are effectively avoided on the premise that parameters of the text translation model do not need to be retrained, the translation accuracy of the text translation model on customized vocabularies such as proper nouns, terminologies and new words can be improved, and therefore the accuracy of a text translation result is improved.

The application relates to a conference minutes generation method combining text optimization and semantic relationship analysis. First, the voice recognition component is used to transcribe the conference recording in real time, and the transcription result is processed again by combining a text optimization model to improve the consistency of the transcription text and the voice content. Then, the optimized text is subjected to deep semantic analysis to automatically identify key information such as conference theme, topic, decision and task content, and generate a structured conference minutes document under the constraint of a template engine to realize efficient arrangement and automatic archiving of conference content. The application has the advantages that the accuracy and professional adaptability of voice transcription are improved, the homonym confusion, proper noun recognition error and word order ambiguity problem are effectively solved, and high-quality, structured and semantically coherent conference minutes generation is realized.

An automotive storage device according to the present disclosure includes a non-volatile memory device configured to store map information including road information, and a storage controller configured to receive a first image data obtained by capturing a proper noun sign and position information of a vehicle, generate proper noun sign information about letters of the proper noun sign based on the first image data, modify the position information based on the road information and the proper noun sign information when an accuracy distance of the position information exceeds a threshold distance, and generate proper noun sign position information including the modified position information and the proper noun sign information.

Systems and methods of computational transliteration of an input sequence of characters in a source language such as Thai to a target language such as Latin. The output may include Romanization of Thai names. The output sequence may be used for machine transliteration understanding of words such as proper nouns. A system may execute a higher-order function that calls a reducing function that iterates through sliding windows of an input sequence and updates, with each iteration, an accumulator map that includes a vector of characters and an indication of a number of characters that can be skipped when processing the next window. Each window includes multiple characters in the input sequence for context-based transliteration using contextual transcription rules. Characters can be skipped when they have already been processed in a previous sliding window. Transliteration of certain source languages may include transposition, deletion, insertion, and transcription.

This invention discloses a method and system for speech recognition and student process evaluation based on dynamic vocabulary injection, relating to the fields of artificial intelligence and smart education technology. This invention aims to solve the problem of low recognition rate of homophones in existing speech recognition technologies, leading to inaccurate attribution of process evaluation results and high manual recording costs. The method includes: obtaining a student list for the target teaching scenario; pre-injecting the list as a dynamic vocabulary into an ASR (Automatic Speech Recognition) engine for decoding weight bias; acquiring real-time teaching speech streams, using the ASR engine with injected dynamic vocabulary for accurate recognition, and outputting text containing specific student names; using a Natural Language Processing (NLP) model to extract entities from the text, separating name entities and performance evaluation entities; finally, inputting the performance evaluation entities into an AI scoring model to automatically generate a quantitative score and include it in the student's process evaluation file. This invention completely solves the problem of recognizing homophones and proper nouns, realizing an accompanying, seamless, automated evaluation scoring closed loop, greatly reducing the recording burden on teachers.

The present disclosure provides a computer-implemented proper noun correction method, which relates to natural language processing, and particularly relates to the identification of proper nouns. The implementation is as follows: obtaining a plurality of candidate words based on first text content; in response to determining that a first candidate word in the plurality of candidate words matches a first proper noun in a preset proper noun library, generating second text content by replacing the first candidate word in the first text content with a specific identifier; determining whether to replace the first candidate word based on the first text content and the second text content; and in response to determining to replace the first candidate word, replacing the first candidate word in the first text content with the first proper noun.

The present application relates to a kind of methods for extracting important opinions in public opinion events.The present application utilizes machine learning and algorithm model, extracts specific phrases and proper nouns in industry from mass text based on mutual information and left-right cross entropy, utilizes industry corpus to train word vector model based on glove model, utilizes word vector to recall the synonyms of "say" and "express", extracts the proper noun dictionary, and according to expert rules, the sentences belonging to speech opinions are recalled, whether the speaker field in the opinion contains the entity type specified by the business is judged using NER model, the opinion is screened, the lexical dependency relationship of speaker field is analyzed using syntax dependency tree, the speaker entity relationship is obtained as important opinion basis.The present technology can be extended to multiple industries and multiple types of events, is not limited to a single data type, supports multiple data types, and clusters multiple opinions under large data, which is convenient for viewing and understanding.