536 results about "Natural language processing" patented technology

HyperText Markup Language (HTML) content analysis (HCA) using machine learning is described. A feature vector schema may be generated based on domain names corresponding to HTML webpages and corresponding indications of a status of the HTML webpage. The schema may map each position in a feature vector of a given HTML webpage to a resource identifier. Information may be processed using the schema to generate respective feature vectors. The feature vectors may be used to train a model to generate risk indicators for HTML webpages. A potentially parked domain webpage or a potentially malicious domain webpage may be received. A feature vector for the webpage may be generated and inputted to the model. The model may generate a risk indicator for the webpage. The risk indicator may be output and may cause responsive actions. The model may be updated based on a determination indicating whether the webpage was a parked domain webpage or a malicious domain webpage.

The invention provides a context-based intelligent voice semantic understanding analysis method and system, and relates to the technical field of voice interaction, and the method comprises the steps: obtaining an input voice signal, extracting an acoustic feature, and decoding the acoustic feature to obtain a candidate text; constructing context semantic representation to carry out disambiguation processing; establishing a semantic dependency graph and carrying out multi-level correlation analysis; spreading context constraint information to perform multi-hop reasoning; and finally generating intention recognition and slot filling results and updating the session state. The semantic comprehension accuracy and the intelligent degree of the voice interaction system are improved by introducing the context information and the multi-level semantic dependency relationship.

Embodiments of the invention provide a model cue word optimization method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining an initial cue word; inputting the initial cue word into a first large language model to generate a plurality of first cue words; inputting the initial cue word into a second large language model to generate a plurality of second cue words; respectively testing the initial cue word, each first cue word and each second cue word to obtain respective corresponding test results; based on the respective corresponding test results, determining whether a prompt word meeting a preset condition exists at present; if not, determining a plurality of candidate cue words based on the first cue words and the second cue words, respectively taking the initial cue words and the candidate cue words as new initial cue words, and returning to execute the step of inputting the initial cue words into the first large language model until the cue words meeting preset conditions exist; if yes, the cue word meeting the preset condition serves as the target cue word, and the optimization efficiency and the optimization quality of the cue word are improved.

The invention discloses an AI Agent-based low-code outbound verbal skill process configuration method and system, and the method comprises the steps: carrying out the word segmentation and semantic analysis of an original verbal skill text through a verbal skill configuration Agent, recognizing the type of a core business intention, extracting key entity information, carrying out the feature extraction and weight calculation of customer portrait data, and generating a customer feature model, fusing the key entity information with the customer feature model to generate an optimized verbal skill suggestion; performing keyword scanning, semantic rule matching and context association analysis on the optimized verbal skill suggestion through a compliance detection Agent to obtain a latest compliance standard update and generate a compliance detection result; carrying out automatic replacement and risk prompt supplement on violation contents through a dynamic correction function, and generating a compliant version verbal skill; and performing format standardization processing on the verbal skill of the compliant version through the outbound system interface, and then pushing the verbal skill to an outbound execution platform. According to the invention, the problems of low verbal skill configuration efficiency and insufficient compliance detection capability in the prior art are solved.

The embodiment of the invention provides a cue word generation method and device, a program product and a storage medium, and the method comprises the steps: obtaining task description information of a target task; performing prompt word generation operation on the task description information by using a pre-trained target network model to obtain a target prompt word; wherein the generation operation comprises the steps that multiple meta prompts are extracted from the task description information, a meta prompt set is obtained, and the multiple meta prompts all comprise the summary of the target task; target mapping operation is executed on the meta prompt set to obtain a candidate prompt word set comprising a plurality of candidate prompt words, and the target mapping operation comprises construction of a mapping relation among the plurality of candidate prompt words and a mapping relation between the plurality of candidate prompt words and preset candidate prompt words; and extracting a target cue word of which the quality feature is greater than a preset threshold value from the candidate cue word set. Through the method and the device, the problem that accurate cue words cannot be generated in related technologies is solved.

The invention provides a session processing method, system and equipment based on a large language model, and the method comprises the steps: obtaining and analyzing a current dialogue text of a session, and determining whether the task type of the current dialogue text comprises a model switching intention or not; according to whether the current dialogue text comprises a model switching intention, a task type, a session context size after the current active large language model processes the previous dialogue text and a response quality evaluation result, whether the current active large language model is applicable is judged, and if not, a target large language model is determined; converting the session context after the current active large language model processes the previous dialogue text into a session context suitable for the target large language model; and taking the target large language model as a current active large language model, and processing the current dialogue text in combination with the dialogue context applicable to the target large language model to obtain an answer corresponding to the current dialogue text. The answer accuracy can be improved, and session context coherence can be ensured.

The invention provides a cue word optimization method and system based on a large language model, and the method comprises the steps: generating a theme corresponding to a question in a training set, the training set comprising a question-answer pair, and the question-answer pair comprising the question and a standard answer of the question; searching a first cue word corresponding to the theme in a knowledge base, wherein the knowledge base comprises a knowledge base theme and a cue word corresponding to the knowledge base theme; inputting the first cue word corresponding to the theme and the question into a large language model to obtain a response answer output by the large language model; and if the response answer is wrong compared with the standard answer, generating a new cue word based on the question, the theme, the response answer and the standard answer, and updating the first cue word corresponding to the theme into the new cue word in the knowledge base. The cue word optimization mode of the large language model is remarkably improved, and finally the overall accuracy and generalization ability of the model for answering based on the optimized cue words are improved.

The invention relates to the technical field of semantic understanding, in particular to a steel structure archive retrieval system based on semantic understanding, which comprises a semantic index construction module for reading a document text sentence by sentence based on an original document of a steel structure archive, matching a preset sensitive information ontology dictionary and establishing a steel structure archive security index. According to the method, the original document text of the steel structure archive is read sentence by sentence and matched with the preset sensitive information ontology dictionary to realize the identification of the special node construction and the sensitive information in the document, so that the document content can complete the effective labeling of the safe sensitive information in the index stage, and the safe grading of the archive data is realized from the source. According to the method, document identifiers and sensitive concept categories are aggregated in combination with role identifiers and retrieval keywords in user retrieval requests, document lists meeting conditions are screened out, document access permissions are compared with preset rules item by item, a content rewriting trigger instruction is formed through combination, and it is effectively ensured that user query results are strictly limited by the permission range.

Implementations described herein relate to an application and / or automated assistant that can identify arrangement operations to perform for arranging text during speech-to-text operations—without a user having to expressly identify the arrangement operations. In some instances, a user that is dictating a document (e.g., an email, a text message, etc.) can provide a spoken utterance to an application in order to incorporate textual content. However, in some of these instances, certain corresponding arrangements are needed for the textual content in the document. The textual content that is derived from the spoken utterance can be arranged by the application based on an intent, vocalization features, and / or contextual features associated with the spoken utterance and / or a type of the application associated with the document, without the user expressly identifying the corresponding arrangements. In this way, the application can infer content arrangement operations from a spoken utterance that only specifies the textual content.

The invention relates to a railway traffic field semantic recognition method and device based on few sample data and a medium, and the method comprises the steps: carrying out the preprocessing of the obtained railway traffic field data, and constructing a field dictionary and a rule base; converting the preprocessed domain data into enhanced voice, forming a training pair by the enhanced voice and a corresponding text, and performing domain fine tuning on the ASR model; inputting a voice instruction in the railway traffic field into the field fine-tuned ASR model, and outputting an ASR initial transcription text; on the three levels of sentence level, local word order level and semantic tag level, word legality judgment is performed on the ASR initial transliteration text through a multi-scale model, and a high-credibility anchor point set and uncertain content are recognized; and field semantic rewriting is carried out based on the legitimacy judgment result of the words, and finally a structured instruction text is output. Compared with the prior art, the method has the advantages of realizing accuracy and adaptability of semantic recognition in the field of railway traffic and the like.

The invention relates to the technical field of intelligent questions and answers, in particular to the technical field of artificial intelligence, and provides a data processing method, device and equipment and a storage medium, which are used for effectively reducing the storage overhead of KV data while ensuring the reply precision. The method comprises the following steps: splitting a problem sequence into a plurality of problem lexical elements, and extracting corresponding semantic key value vectors; performing multi-round iterative processing on the question sequence until a reply answer is output; in each round of iteration, based on the semantic key value vector of each historical lexical element, obtaining an answer lexical element of the round; taking the answer lexical elements as new historical lexical elements, and extracting semantic key value vectors of the new historical lexical elements for storage; when the stored semantic key value vector reaches a storage capacity threshold value, obtaining a lexical element compression quantity based on a problem lexical element quantity and a historical lexical element quantity; and based on the attention evaluation value of each historical lexical element for the answer lexical element of the current round, eliminating the historical lexical elements conforming to the lexical element compression quantity and the corresponding semantic key value vectors.

A method and system for training a virtual agent is provided herein. The method and system comprises storing conversations between the virtual agent and a user in logs. The method and system further comprises mining the logs to retrieve utterances. The method and system further comprises computing regression for each of the plurality of the charging time segments. The method and system further comprises providing a score to the utterances. Further, the method ranking the utterances based on the score.

The invention discloses a multi-language voiceprint recognition method based on a pre-training voice model. The pre-training voice model WavLM and a traditional voiceprint recognition model ECAPA-TDNN are fused. According to the method, a multi-layer perceptron (MLP) module is introduced for further refining and converting the features extracted by the WavLM, so that the features are more suitable for the input requirement of an ECAPA-TDNN model, and the abstraction and expression ability of the model to the features is enhanced. In the aspect of multilingual voiceprint recognition, the model is finely adjusted by using a small amount of voice data sets, and the method comprises the following basic steps of: firstly, freezing parameters of a pre-trained voice model WavLM, so that the pre-trained voice model WavLM keeps learned knowledge; and then, parameters of the MLP module and the ECAPA-TDNN model are continuously adjusted in training, so that the multilingual voiceprint recognition capability is learned. In the application, a to-be-recognized voice passes through the fusion model to obtain a feature vector, and after the vector is subjected to judgment and decision making, a voiceprint recognition result is obtained.

A method includes obtaining a plurality of training data sets each associated with a respective native language and includes a plurality of respective training data samples. For each respective training data sample of each training data set in the respective native language, the method includes transliterating the corresponding transcription in the respective native script into corresponding transliterated text representing the respective native language of the corresponding audio in a target script and associating the corresponding transliterated text in the target script with the corresponding audio in the respective native language to generate a respective normalized training data sample. The method also includes training, using the normalized training data samples, a multilingual end-to-end speech recognition model to predict speech recognition results in the target script for corresponding speech utterances spoken in any of the different native languages associated with the plurality of training data sets.

A document management system including an OCR (optical character recognition) performing module and a document searching module is disclosed. The document management system is a cloud archiving and indexing system that translate uploaded documents to user-selected language versions and performs OCR on the user-selected language versions to generate searchable PDF documents. Each translated word of the different language versions is indexed to indicate its multilingual meanings, its multidialectal use, its synonymous words, its different character sets ad phonetic adaptations, and so on. The indexing can be used to link to the different language versions while conducting a document search, so as to improve the searching flexibilities.

Embodiments of the present disclosure provide systems and methods for emotion-based call summarization. One method may include receiving an emotion prediction vector for an utterance text segment from a transcript data object, the emotion prediction vector comprising a plurality of emotion prediction scores respectively corresponding to a plurality of emotion identifiers; generating a domain-specific relevancy prediction for the utterance text segment based on a category-relevant subset of the plurality of emotion prediction scores that correspond to one or more category-specific emotion identifiers of the plurality of emotion identifiers associated with a domain-specific summarization category; identifying the utterance text segment as a relevant utterance from the transcript data object based on a comparison between the domain-specific relevancy prediction and a relevancy threshold; and initiating a performance of a machine learning summarization operation based on the utterance text segment.

The invention discloses an AI-based script creation system and method, and the method comprises the steps: receiving an initial cue word, and carrying out the recognition and extraction of script core elements of the initial cue word; inputting the script core elements into a pre-trained script generation model, and generating an initial script by the script generation model; performing text similarity, plot structure similarity and character relationship similarity calculation on the initial script and copyright scripts in a script database, and outputting the initial script only when the similarities are smaller than a preset percentage; according to the method, the overall creation period is shortened, the cost is reduced, the integrity of the script and the copyright security are both considered, and the copyright risk of the script is reduced while the script creation efficiency and quality are improved.

A speech condensation processing system and method includes an ASR system for a source language that receives an audio stream with speech and outputs at least one word sequence and time stamps in the language spoken, a memory that stores a condensation program and corresponding data and databases that store training data, which may include manually condensed data, two-way translated data, and aligned subtitle data, and a processor coupled to the ASR system and memory that executes the condensation program to format and condense text by transforming the at least one word sequence from ASR into human-readable text with proper casing and punctuation, and condenses the text based neural training to remove words from the at least one word sequence that are not relevant for meaning.

The invention discloses an English vocabulary follow-up pronunciation correction method based on English teaching, and relates to the technical field of voice processing, and the method comprises the following steps: S1, constructing a standard vocabulary pronunciation unit; s2, carrying out phoneme difference positioning by using a standard vocabulary pronunciation unit; s3, performing syllable dynamic comparison by using the phoneme deviation distribution of the learner; s4, performing vocabulary level comparison by using the learner phoneme deviation distribution and the syllable deviation mapping; and S5, performing difference mapping output by using the vocabulary pronunciation difference set. By setting the difference comparison between the actual pronunciation of the learner and the standard pronunciation, an accurate alignment relationship can be established at the phoneme level, and the difference between the actual pronunciation and the standard pronunciation in the aspects of acoustic characteristics, pronunciation duration, phoneme boundaries and the like is quantized, so that compared with the prior art, only the overall similarity or fuzziness judgment can be given, and the accuracy of pronunciation is improved. And a difference comparison mechanism can provide a clearer error correction reference, so that the learner can clearly recognize the position and degree of the problem when receiving the result.

An example process includes receiving a speech input from a user and obtaining a representation of the speech input. The process further includes in accordance with a determination that at least one entity within the representation requires disambiguation: adjusting the representation by adding an indication to the at least one entity, and providing the adjusted representation to a language model. The process further includes in accordance with a determination that the adjusted representation requires modification: modifying, by the language model, the adjusted representation, and providing an output based on the modified and adjusted representation.

The invention provides a vertical field corpus extraction method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, and the method comprises the following steps: obtaining a plurality of general corpora, and field keywords and sample corpora of a target vertical field; filtering the plurality of general corpora based on the field keyword to obtain a plurality of candidate corpora; and filtering the plurality of candidate corpora based on the semantic relevancy between the candidate corpora and the sample corpora to obtain the corpora of the target vertical field. According to the method and device provided by the invention, a multi-stage filtering mechanism is adopted, filtering is carried out through the keyword and semantic relevancy, and it is ensured that the finally screened corpus is not only related to the vocabulary level, but also highly matched with the target vertical field on the semantic level; related vertical field corpora are accurately and efficiently extracted from general large-scale corpora, and the performance and reliability of a large model in the vertical field are improved.

The embodiment of the invention provides an anonymization privacy protection method and system for voice information retention. The method comprises the following steps: extracting speaker embedding of an original audio, eliminating the tone of the speaker, and keeping semantic and rhythm speaker irrelevant features; embedding and inputting a speaker into a speaker anonymous module matched with a three-stage stream based on a U-Net architecture to obtain anonymous embedding; and combining irrelevant features of the speaker with anonymous embedding by using a pre-trained voice reconstruction model to generate anonymized voice with tone privacy. According to the embodiment of the invention, voice anonymization facing content privacy and tone privacy reserved by voice information is realized, the effectiveness of the anonymized voice generated by using the method in a downstream task is superior to that of a baseline model, meanwhile, the privacy of a speaker is also guaranteed, and safe use of data is realized.

Techniques are provided for generating training data to facilitate fine-tuning embedding models. Training data including anchor utterances is obtained. Positive utterances and negative utterances are generated from the anchor utterances. Tuples including the anchor utterances, the positive utterances, and the negative utterances are formed. Embeddings for the tuples are generated and a pre-trained embedding model is fine-tuned based on the embeddings. The fine-tuned model can be deployed to a system.

In various examples, controlling dialogue using contextual information for conversational artificial intelligence (AI) systems and applications is described herein. Systems and methods are disclosed that use various sources of contextual information, along with textual inputs (e.g., queries), to generate textual outputs (e.g., responses) associated with a dialogue between a user (e.g., a user's character) and another character (e.g., a non-playable character) of an application. For instance, the contextual information may be stored in one or more databases, such as one or more vector databases, and / or in a specific form, such as embeddings that represent the contextual information. One or more language models may then process a textual input and / or at least a portion of the stored contextual information in order to generate a textual output. This textual output may then be used to generate speech that is output by the other character.

The invention discloses a dialect speech enhancement method and device based on cross-modal and confrontation verification, and belongs to the technical field of speech recognition and enhancement. According to the method, the dialect voice and the lip movement video are jointly modeled, so that the accuracy and the naturalness of a dialect generation task are remarkably improved; a set of generation-adversarial-feedback closed-loop enhancement framework is constructed, and a multi-dimensional adversarial verification mechanism is introduced, so that the model is self-evolved, and enhancement data is ensured to be diversified and accord with real use habits of dialects. The dialect knowledge graph and the voice generation model are creatively fused, double enhancement of semantic and cultural levels is achieved, the generated dialect voice content better conforms to the real language environment and cultural background of the dialect voice content, and the method is particularly suitable for protection and inheritance of endangered or small dialects. The method can be directly applied to subsequent dialect recognition, synthesis or protection and the like.

The invention discloses a literature classification method and system based on a large language model, and relates to the technical field of large language models.The literature classification method based on the large language model comprises the specific steps that an n-level category system is defined, naming is conducted through an upper concept, the category relation and unique identification are clarified, a tree structure is formed and coded, and a dimension set is defined; the method comprises the following steps of: binding core terms of fine-level categories and literature types classified according to text features, determining a sample format, performing progressive sampling according to the levels of the categories, constructing a user-defined rule base, judging whether the standard is reached or not through a consistency rate, calculating a rule conformity and a feature word coincidence rate, and further determining a labeling qualification rate. And according to the marked qualified rate, reasons of unqualified categories are positioned and processed. According to the method, the literature can be further distinguished according to the text features, and rich dimensions are provided for subsequent literature analysis, retrieval and management.

The invention discloses a text-to-SQL (Structured Query Language) generation and auditing method and device based on retrieval enhancement, and the method comprises the steps: analyzing a user intention by utilizing a generative Schema routing model, and automatically selecting a target database and a related table to form a query range; an example similar to the current question is retrieved from the historical question and answer corpus and serves as a Few-Shot prompt to be provided for the large language model; then, self-adaptively constructing a joint prompt according to the difficulty of the problem, guiding the LLM to generate a preliminary SQL query, and correcting an error through a cyclic feedback mechanism; an LLM-driven SQL script automatic auditing and optimization suggestion module is introduced, comprehensive auditing is conducted on the generated SQL from the aspects of grammar specifications, query performance, structure optimization, safety protection and the like, and optimization suggestions are given out and serve as filtering and feedback links before the SQL falls into a library. According to the method, retrieval enhancement and prompt generation technologies are fully combined, and the generation efficiency, reliability and safety are improved while the correctness of the query result is ensured.

The invention provides a retrieval enhancement generation method and system based on context semantics and hybrid reordering, and relates to the technical field of retrieval enhancement generation, and the method comprises the following steps: segmenting a knowledge base according to paragraphs to obtain a plurality of independent paragraphs, segmenting the knowledge base into a plurality of logic blocks according to a logic structure, and correspondingly generating summary information; enhancing the target paragraph according to the logic block associated with the target paragraph screened out by the user query statement and the summary information of the logic block to obtain an enhanced text; generating a context abstract for the corresponding target paragraph based on the enhanced text, vectorizing the enhanced text and the context abstract, storing the vectorized text and context abstract in a vector database, and synchronously constructing a keyword index database; performing mixed retrieval in a vector database and a keyword index database according to the user query statement to obtain a retrieval result; and the retrieval results are reordered according to the answer correlation in an inverted order to obtain an inverted sequence. The method has the beneficial effects that knowledge waste caused by text block isolation and position prejudice is avoided, and the retrieval precision is greatly improved.

The invention provides a voice data generation method based on a large model and a method for training the large model, and relates to the technical field of artificial intelligence, in particular to the technical fields of voice generation, intelligent customer service, video production and the like. The large model-based voice data generation method comprises the following steps of: receiving a rhythm description text and a voice text, wherein the rhythm description text describes a pronunciation rhythm intention of a plurality of text words in the voice text; semantic fusion is conducted on the rhythm description text and the voice text through a large model, rhythm fusion features are obtained, sub-features in the rhythm fusion features represent the pronunciation rhythm of the voice segments for the text words, and the to-be-generated target voice data comprise the voice segments; and according to the rhythm fusion feature and a specified pronunciation attribute related to the specified object, generating target voice data which represents that the specified object pronunciates according to the pronunciation rhythm intention and corresponds to the voice text.

The present application relates to the field of automated translation technology and discloses an intelligent translation method and system based on translation forms. The method comprises: upon receiving a first market information form for a target product sent by a Chinese website, determining whether a first translation form corresponding to the target region and the target product exists in an overseas backend system, wherein the first translation form is used to translate the first market information form; upon determining the first translation form, translating the first market information form according to a data dictionary of the first translation form to obtain first translation information; adjusting the format of the first translation information according to the reading habits of the target region to obtain second translation information, and upon determining that the second translation information passes translation quality verification, pushing the second translation information in real time to the overseas site and / or overseas server corresponding to the target region. The present application can accurately translate industry-specific vocabulary and improve information dissemination efficiency.