768 results about "Natural language processing" patented technology

The invention relates to dialect speech synthesis, in particular to a semi-supervised dialect emotion speech synthesis system based on hybrid experts, which comprises a text analysis module for preprocessing an input dialect text and generating a text representation vector through feature extraction and feature fusion; the mixed expert module is used for acquiring dialect acoustic features, rhythm features, emotional features and general acoustic features; the dynamic routing module is used for realizing intelligent cooperation among experts through a task-aware soft routing algorithm; the semi-supervised learning module is used for training supervised learning by using the marked dialect emotion voice data and training self-supervised learning by using the unmarked dialect emotion voice data; the acoustic parameter generation module is used for integrating the output of each expert to generate a complete acoustic parameter set; the neural vocoder is used for converting the acoustic parameter set into final dialect emotion voice; the method can effectively overcome the defect that the dialect emotional voice is difficult to accurately synthesize under the condition of lack of sample resources.

A large language model predicts a topic summarization of a long document given a set of segments from the long document that pertain to a topic of interest. The set of segments from the long document are selected by searching for similar segments from other documents that have been labeled to indicate whether or not the segment pertains to a topic of interest. The search is based on an embedding of a segment from the long document closely matching embeddings of the labeled segments. Each segment of the long document is scored based on the labels of the closest-matching similar segments. The segments from the long document are ranked by their respective score and the highest-scored segments are included in a prompt to the large language model for the model to generate a topic summarization of the long document.

A cyber security system that protects against cyber threats including a synthetic clone of a voice of a speaker can include several components. A deep learning model is trained to analyze an audio file and produce one or more embeddings of the audio file. One or more AI classifiers are trained to analyze the one or more embeddings of the audio file from the deep learning model to determine whether it is likely that the voice of the speaker engaging with a user is real or the synthetic clone of the voice of the speaker. The voice clone detection bot can be resident on a computing device of the user and can integrate with different sources of audio data on the computing device of the user in order to collect the audio file containing an attempt to synthetically clone the voice of the speaker protected by the cyber security system.

A device may receive, at a server system, a free-form query. The device may select two-way communication history records from a database associated with the free-form query to identify selected history records. The device may generate individual summaries of individual history records of the selected history records by processing a set of corresponding individual history records using a chunking algorithm, constructing language responses from outputs of the chunking algorithm using a large language model, and aggregating the language responses. The device may process the language responses using the large language model to generate an individual summary for corresponding individual history records.

The invention discloses a language learning assistance application system based on speech recognition, and belongs to the technical field of learning assistance. The system comprises an intelligent voice acquisition and enhancement module for realizing acquisition and preprocessing of high-quality voice signals in a complex environment; the multi-modal feature extraction module dynamically extracts and fuses multi-dimensional learning feature information, completes feature analysis and boundary segmentation of a phoneme level, and is responsible for feature normalization and optimization; the deep speech recognition module is used for realizing high-precision speech recognition based on the normalized features; the intelligent evaluation engine module is used for realizing real-time and multi-dimensional evaluation on the language performance of the learner; the personalized learning management module integrates the evaluation results for dynamically planning an optimal learning path for the learner, manages the learning progress, and provides learning effect prediction and intervention suggestions at the same time; and the learning interaction experience module is responsible for visual presentation of learning feedback, multi-modal man-machine interaction design and user interface optimization.

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 relates to the technical field of language learning, and discloses an English auxiliary pronunciation training method and system based on multi-task learning, and the method comprises the following steps: constructing a multi-task learning framework which comprises at least two subtask models related to pronunciation, comprising the steps of pronunciation accuracy scoring, pronunciation error type positioning and intonation fluency analysis. A voice signal, a lip movement video and a text content of a user are collected through a multi-modal data input module; and performing joint coding on the multi-modal data by using the shared feature extraction layer to generate fused acoustics. According to the English auxiliary pronunciation training method and system based on multi-task learning, the pronunciation training path of the user can be adaptively adjusted, the requirements of different users can be met, the English pronunciation level can be more effectively improved, and through strategies such as multi-modal data input, shared feature extraction, inter-task attention mechanism and adaptive training path adjustment, the English pronunciation training efficiency can be improved. Accurate evaluation and personalized training of English pronunciation are realized.

System and techniques to facilitate the translation of a sign language into another language are described herein. A modular architecture may be used in which the output of different classifiers may be used to produce intermediate representations, or final translations, of the sign language. These classifiers may be trained on different types of signs to enhance accuracy while reduce training time and complexity.

An interactive method based on a large model, a training method, and an intelligent agent, which relate to fields of artificial intelligence, speech recognition, speech interaction, deep learning, large models, and application scenarios of knowledge search, autonomous driving, intelligent customer service, intelligent speech control, smart e-commerce, AI healthcare. The interactive method includes: acquiring a request speech; performing a speech recognition on the request speech to obtain a speech recognition feature representing a request semantics; and processing the speech recognition feature using the large model to obtain a response text, where the response text includes response words arranged in sequence, a target response word among the response words is determined by processing the speech recognition feature and an associated response word feature using an attention fusion layer of the large model, and the associated response word feature is related to an associated response word arranged before the target response word.

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.

One example method includes enabling a user to define a query that comprises a hybrid search syntax (HSS), and the HSS is in the form of a single string that comprises a lexical component and a semantic component, receiving the query from the user, parsing the lexical component and the semantic component into respective groups of one or more sub-components, performing a lexical search based on the sub-components of the lexical component, and performing a semantic search based on the sub-components of the semantic component, ranking, separately from each other, results of the lexical search and results of the semantic search, combining the results of the lexical search and the results of the semantic search to create aggregate results, and re-ranking the aggregate results.

A system for emotionally enhancing dialogue includes a computing platform having processing hardware and a system memory storing a software code including a predictive model. The processing hardware is configured to execute the software code to receive dialogue data identifying an utterance for use by a digital character in a conversation, analyze, using the dialogue data, an emotionality of the utterance at multiple structural levels of the utterance, and supplement the utterance with one or more emotional attributions, using the predictive model and the emotionality of the utterance at the multiple structural levels, to provide one or more candidate emotionally enhanced utterance(s). The processing hardware further executes the software code to perform an audio validation of the candidate emotionally enhanced utterance(s) to provide a validated emotionally enhanced utterance, and output an emotionally attributed dialogue data providing the validated emotionally enhanced utterance for use by the digital character in the conversation.

The embodiment of the invention discloses a question and answer retrieval method and device, a storage medium and a terminal. Receiving input data corresponding to the question and answer request, and generating an intention recognition cue word according to the input data; inputting the intention recognition cue word into a large language model, and controlling the large language model to recognize a target intention category corresponding to the question and answer request based on the intention recognition cue word; and determining a target retrieval scheme corresponding to the target intention category from the at least one retrieval scheme, performing retrieval on the input data according to the target retrieval scheme to obtain a corresponding retrieval result, and outputting the retrieval result as answer content corresponding to the question and answer request. During query, prompt words are generated for input data and input into the large language model, and the large language model identifies a target intention category implied in the input data. And after the intention category of the query is identified, a matched retrieval scheme is determined according to the information, and after retrieval is executed according to the determined retrieval scheme, a retrieval result conforming to the query intention of the user is obtained.

The present disclosure provides a real-time language translation system embodied in a physical device. Further, the real-time language translation system may include an input device which may be configured for receiving generating a user input data representing a linguistic input from a user. Further, the linguistic input corresponds to a user language. Further, the real-time language translation system may include a processing device which may be configured for generating a translation data based on the user input data. Further, the translation data represents a translation of the linguistic input. Further, the generating may be based on an AI module. Further, the processing device may be communicatively coupled to the input device. Further, the real-time language translation system may include a presentation device which may be configured for presenting the translation data. Further, the presentation device may be communicatively coupled to the processing device.

The invention relates to the technical field of language teaching, and discloses an intelligent system applied to Chinese language teaching, and the system comprises a voice recognition module which is used for collecting a voice signal of a learner and converting the voice signal into a phoneme sequence; the pronunciation difference analysis module is used for performing alignment analysis on the dialect phoneme sequence and the mandarin phoneme sequence of the learner to generate pronunciation difference data; the knowledge graph module is used for constructing a multi-layer knowledge graph of dialects and mandarin and describing the relationship among phonemes, grammar rules and vocabularies; and the personalized learning path generation module is used for dynamically generating a personalized mandarin learning path based on the pronunciation difference data and the knowledge graph of the learner. A multi-task learning framework based on a pre-training model Wav2Vec 2.0 is adopted, pronunciation difference analysis is performed through joint recognition of mandarin and dialect voices in combination with a dynamic time warping algorithm, and the technical effect of accurately capturing pronunciation characteristics and differences of learners is achieved.

The invention discloses a knowledge distillation-based Hainan dialect speech recognition optimization system, which comprises a data preprocessing module for processing Hainan dialect speech data and Hainan dialect text data, and outputting to obtain an MFCC speech feature sequence, a labeled text label and Hainan dialect text data; the teacher model module comprises an RNN (Recurrent Neural Network) language model, a CNN (Convolutional Neural Network) language model and a Transform language model, dialect text data are respectively input into the RNN language model, the CNN language model and the Transform language model, and a soft label and a middle layer feature are obtained through dynamic temperature regulation; the student model training module is used for performing knowledge distillation and parameter adjustment and optimization on a student model according to the MFCC voice feature sequence, the marked text tag, the soft tag and the middle layer feature; the output module is used for performing voice recognition on the Hainan dialect by using the student model after knowledge distillation and parameter optimization to obtain a recognition result; moreover, the trained student model is small in size and low in calculation complexity, and an accurate recognition result can be obtained finally.

A real-time pronunciation correction device for English learners belongs to the field of voice processing and comprises an acquisition and preprocessing module, a voice feature extraction module, a standard pronunciation model construction module, a data customization management unit, a pronunciation correction suggestion module, a correction and progress tracking module and an adjustment and optimization module. By combining the deep neural network and the convolutional neural network deep learning technology, the pronunciation characteristics of the learner can be efficiently analyzed and processed. By comparing the difference between the pronunciation of the learner and the standard pronunciation in real time, pronunciation errors are accurately detected, so that high-accuracy pronunciation correction is realized. And in combination with machine learning and data analysis, the equipment can dynamically adjust a pronunciation training strategy according to individual requirements of the learner, and provide customized pronunciation guidance and suggestions. The personalized feedback helps the learner to improve the pronunciation error of the learner in a targeted manner, and the learning efficiency is improved.

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 a topic analysis method based on a large language model. The method comprises the following steps: performing data preprocessing on dialogue content; performing topic classification on the preprocessed dialogue contents, and collecting contents belonging to the same topic together; discussion objects, abbreviations and key phrases appearing in the content are extracted, and additional background knowledge is collected; summarizing contents under the topic by using a large language model to form a topic name and a topic abstract; and performing the same processing on a plurality of topics in the dialogue process to form a topic analysis report of the discussion content. Important information can be efficiently and accurately extracted, and a topic report is formed.

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.

Technologies for language agnostic OCR extraction include identifying a word region of an image using optical character recognition, applying a language agnostic machine learning model to the word region, where the language agnostic machine learning model is trained on training data including a set of image-text pairs and a set of multilingual text translation pairs, receiving, from the language agnostic machine learning model, a word region embedding that is associated with the word region, searching a multilingual index for a text embedding that matches the word region embedding, receiving, from the multilingual index, text associated with the text embedding; and outputting at least one of the text or the text embedding to at least one downstream process, application, system, component, or network.

Techniques are disclosed for semantic moderation of conversational agents. An example system includes a memory having instructions, and a processor communicatively coupled to the memory and configured to execute the instructions. Example instructions include: scoring a received input string against a plurality of target classes to derive two or more scores, wherein each target class is associated with an independent score, and the scoring is performed without applying a softmax function to the independent scores; using the scores to generate a rule-based determination that indicates whether to pass or filter the input string; upon a determination to filter the input string, performing filtering processing on the input string; and otherwise, performing output processing on the input string.

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 pathological speech evaluation method and device, and the method comprises the steps: carrying out the resampling of pathological speech audio data, and inputting a feature extraction module to extract the potential features of pathological speech; the potential features are subjected to mask processing and then input to a context representation module, and context representation of pathological speech containing advanced features is extracted; the potential features and the context representation are combined to serve as input of a hybrid expert module, hidden layer features are distributed to expert networks through a gating network, and each expert network is composed of a linear layer; taking the output of the last layer in the context representation module as the input, and performing semantic recognition on the pathological speech to obtain a loss function; and constructing a joint loss function, carrying out gradient updating on a pathological voice evaluation task by taking the joint loss function as a loss function, and after multiple rounds of training, finally obtaining a classification evaluation result based on pathological voice damage severity in the hybrid expert module by the model.

The embodiment of the invention provides a cue word processing method and device.The cue word processing method comprises the steps that in the cue word generating process, labeled data and data labels are input into a large language model through an intelligent agent for labeling rule recognition, and labeling rules are obtained; and inputting the labeled data and the labeling cue word containing the labeling rule into a large language model for data labeling processing to obtain a data labeling result, comparing the data labeling result with a data label, and updating the labeling rule according to the comparison result to obtain a target labeling rule after reinforcement learning is completed, and generating a target annotation prompt word based on the target annotation rule.

The invention belongs to the technical field of electronic teaching aids, and discloses a voice training system and a data training method after complete denture repair, and the system comprises a feedback analysis and decision device which is used for carrying out the error classification of a used object, and obtaining the type of a high-frequency problem through a clustering algorithm; the dynamic content generation engine is used for recording a historical error pattern of the use object, presetting pronunciation training logic and generating personalized training content; the intelligent difficulty adjusting device is used for adopting a dynamic difficulty algorithm: scoring according to a result of a use object, and automatically adjusting the level difficulty; and the adaptive content generator is used for analyzing the pronunciation content of the use object, identifying wrong phonemes or grammar problems, and generating training content according with difficulty in real time according to the current level and error type of the use object. The method can help a user to recover clear voice as soon as possible, improves the use enthusiasm, and can solve the problems that personalized training is not available, real-time monitoring and feedback cannot be performed, and pronunciation cannot be corrected in time.

The invention relates to the technical field of query systems, in particular to a semantic recognition system for guiding treatment information query based on LUTS symptoms. The information receiving module is used for receiving voice information, the preprocessing module is used for converting the voice information into text information based on a preset time interval, and the extraction module is used for obtaining a plurality of keywords. The matching module is used for carrying out key information retrieval on the basis of the key words, judging whether retrieval for the key information meets standards or not on the basis of retrieval results of the key information and generating corresponding processing instructions, and the control module is used for re-determining operation parameters of corresponding components on the basis of the processing instructions. The output module is used for outputting a retrieval result; and the database is used for storing a plurality of pieces of preset key information comprising a plurality of preset keywords. According to the method and the system, accurate query of guidance information and treatment information of the LUTS symptom by the semantic recognition system is effectively realized, and the operation efficiency of the semantic recognition system for information query of the LUTS symptom is effectively improved.

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 provides an intelligent record generation method and system, and a terminal, and the method comprises the steps: recognizing spokesmen of collected original question and answer voice data through a pre-trained voice recognition model, and generating the speech text data of each spokesman, thereby achieving the real-time recording of the speech of each part, supporting the multi-role recognition, and achieving the real-time recording of the speech of each part. Automatically marking speech text data of different spokesmen; through a case analysis model based on pre-training, case basic information of a current case is identified, applicable legal provisions and similar discriminants are determined, and corresponding legal suggestions are generated, so that effective legal references are provided for political and law workers, and consistency of legal application is ensured; by automatically generating the record document of the specified type, the uniformity and speciality of the format of the record document are ensured, the case handling time is effectively shortened, and the case handling efficiency is improved.