379 results about "Part of speech" patented technology

The invention relates to the technical field of data processing, in particular to a method and system for processing data based on a large language model.The method comprises the following steps that based on inter-sentence punctuation positioning and part-of-speech tagging, sentence blocks are divided to generate functional partitions, themes and relational words are extracted to judge semantic chain starting points, a trigger index sequence is constructed, and logic jump points and breakpoint positions are recognized; and mapping the label structure to the language model output analysis deviation, and generating a label mapping combination list. According to the method, semantic turning nodes can be captured by analyzing the semantic direction change trend, the relation between the semantic turning nodes and verb and noun combinations is judged, the position of a trigger point of an actual information transfer effect is extracted, and the break point area of a semantic path is recognized through the positioning of key word starting and stopping blocks and the logical judgment of noun group cross combination; the path integrity has a clear fracture identifier, a traceable semantic mapping structure path is established in a language model, and the accuracy, coherence and hierarchy clearness of semantic reconstruction are enhanced.

The invention discloses a document analysis and query method based on a knowledge graph, and the method comprises the steps: carrying out the part-of-speech tagging of a received to-be-analyzed document, and obtaining a part-of-speech tagging result; extracting knowledge element information from the part-of-speech tagging result based on a preset power grid domain ontology knowledge base, and constructing an initial knowledge graph based on the knowledge element information; combining nodes in the initial knowledge graph to obtain a fused knowledge graph; constructing a mapping table according to the fused knowledge graph, and generating a candidate query template set based on the mapping table; receiving a natural language query statement input by a user, selecting a target query template from the candidate query template set based on the natural language query statement, and generating a target query statement; querying from the fused knowledge graph by using the target query statement, and outputting a query result; according to the method, the accuracy and comprehensiveness of information analysis can be effectively improved, the query intention of the user can be accurately understood, and the accurate query and analysis requirements of professionals on project documents are met.

The invention provides a structured processing method and device for a contract text, equipment and a storage medium, and the method comprises the steps: carrying out the preprocessing of the contract text, generating a standardized word sequence, and enabling the standardized word sequence to comprise a plurality of word sequences and part-of-speech tagging information of each word sequence; the standardized word sequence is input into a named entity recognition model to recognize key entities in the contract text, key terms in the contract text are extracted based on a machine learning algorithm, the key entities include both parties of the contract, the amount of the contract and the name of a product, and the key terms include payment terms, delivery terms, default responsibility terms and force majeure terms; through dependency syntactic analysis and a semantic role labeling model, analyzing to obtain a semantic relationship between the key entities and the key terms; and storing the extracted key entities, key terms and semantic relationships in a target database in a structured form, and establishing a target index to support quick query. According to the invention, the error rate of manual processing is reduced.

The invention provides a text data automatic labeling method and system integrating a pre-training NLP model, and relates to the technical field of artificial intelligence, the method comprises the following steps: obtaining original text data to be labeled, the text data comprising customer consultation, complaint or feedback dialogue records, evaluations and work orders; performing word segmentation, stop word filtering and part-of-speech tagging processing on the original text data to generate structured text data; inputting the structured text data into a pre-trained NLP model, and correcting semantic features output by the model through a domain adaptation layer to obtain corrected semantic features; and carrying out few-sample learning on the corrected semantic features, enhancing the recognition capability on a low-frequency text mode through a contrast learning mechanism, and generating an enhanced feature vector resistant to long-tail interference. According to the method, automatic annotation of the text data is realized by automatically processing data acquisition and preprocessing and integrating the pre-training NLP model.

The invention provides a BIM technology and project amount intelligent verification method and system, and the method comprises the steps: carrying out the word segmentation and part-of-speech tagging of a progress log, extracting an excavation region, a completion amount and a timestamp of the day, and obtaining a construction progress information set; according to the construction progress information set, identifying a semantic relationship of an excavation area, a completion volume and a time triple, and determining time-space semantic representation; extracting geometric information of each target earthwork logic body from the set of earthwork logic bodies, and calculating a design engineering quantity of each associated logic body in a corresponding preset elevation range in real time in combination with corresponding elevation data extracted from the BIM model to generate a design quantity data set; and according to the early warning result, updating the state attribute of the earthwork logic body in the BIM model, generating a dynamically updated BIM model state in combination with the deviation occurrence timestamp and the difference value, extracting the spatial distribution of the earthwork logic body in the BIM model, and generating a construction path.

The invention discloses a fusion semantic vector space mapping-based translation ambiguity term accurate matching method, which comprises the following steps of: S1, obtaining source language ambiguity terms, context texts and a target language candidate translation list, and extracting domain tags and term matching features to form a multi-modal data set; s2, using improved XLM-R model coding to generate term-level, sentence-level and translation-level semantic vectors; s3, training a dynamic mapping matrix based on a bilingual parallel corpus, and aligning source side vectors to a shared semantic space; s4, fusing the source-side basic vector and the multi-dimensional features through a double-channel attention fusion network, and generating source-side and translation-side comprehensive semantic vectors; s5, introducing term-context attention weight to correct cosine similarity; and S6, outputting an optimal translation through normalized sorting and part-of-speech secondary judgment. According to the method, multi-field ambiguous term accurate matching is realized, the term translation precision and efficiency in professional fields are improved, and the requirements of high reliability of term translation in the fields of medicine, machinery, computers and the like are met.

The invention discloses an artificial intelligence generated paper detection method and a related device, and relates to the technical field of artificial intelligence, and the method comprises the steps: respectively extracting a deep semantic feature, a text statistical feature and a quality evaluation feature of a to-be-processed paper through three feature channels of a paper detection large language model, the deep semantic features represent word-level and sentence-level semantic information, part-of-speech semantic information and inter-sentence semantic consistency information of the to-be-processed paper, the text statistical features represent language style features of the to-be-processed paper, and the quality evaluation features represent overall quality features of the to-be-processed paper. And a feature decoding module in the thesis detection large language model is utilized to obtain a target detection result representing whether the to-be-processed thesis is an artificial intelligence generated thesis according to the extracted features. According to the method, the feature information of the to-be-processed papers is extracted from multiple angles through the three feature channels, the to-be-processed papers can be accurately classified, and the classification accuracy of the target detection result is improved.

The invention discloses an intelligent analysis method and system for enterprise digital transformation, and relates to the technical field of enterprise digital transformation, and the method comprises the following specific steps: perception and preprocessing: employing a network data capture technology to obtain scene factor related text information from multiple channels, according to the method, key information such as policy and regulation update and market dynamic change is captured in real time by utilizing a plurality of information acquisition channels, and a knowledge graph system containing rich enterprise knowledge is constructed; according to the technical scheme of the invention, new scene factors can be deeply associated and accurately matched with knowledge such as business processes and technical architectures inside an enterprise, so that the system can provide more scientific and accurate digital transformation decision suggestions for the enterprise, the enterprise is helped to better cope with external environment changes, the internal management process is optimized, and the business operation efficiency is improved.

The invention relates to the technical field of information retrieval, in particular to a Chinese semantic enhanced fuzzy retrieval method and system based on adaptive weight, and aims to solve the problems that an existing fuzzy retrieval method cannot balance the recall rate and the accuracy rate, semantic weight quantization is missing, and sorting is inaccurate. The method comprises the following steps: performing semantic analysis on a query condition; calculating a part-of-speech weight value of each query segmented word in combination with a predefined part-of-speech weight rule and a part-of-speech combination rule; determining a domain weight value associated with the query condition based on preset domain or context information; applying a correlation scoring algorithm, combining the part-of-speech weight value and the domain weight value as weighting factors, and calculating correlation scores of the candidate documents; and sorting and outputting the candidate documents according to the scoring result. According to the method, double dynamic weights of part-of-speech combination and the industry field are introduced, the understanding ability of Chinese semantics is enhanced through a dynamic weight learning mechanism, and the correlation and accuracy of fuzzy retrieval results are effectively improved.

The invention discloses a lightweight knowledge graph rapid construction method and system based on an NLP technology. The method comprises the steps of preprocessing an unstructured text and segmenting the unstructured text into semantic segments; unsupervised clustering is combined with the contour coefficient to determine the optimal clustering number, and a semantic association fragment cluster is obtained; performing word segmentation, part-of-speech tagging, NER and entity linking on the fragment cluster, extracting an entity and initial relationship, and fusing semantic similarity, TF-IDF word frequency collaboration degree and co-occurrence frequency to calculate a relationship edge weight; constructing a lightweight knowledge graph; in the question and answer stage, questions are disassembled through a process engine, related sub-graphs are retrieved, and answers with reasoning links are generated. The system correspondingly comprises a text preprocessing module, a clustering module, an entity relation processing module, a graph construction module, a question and answer reasoning module and a storage module. According to the method, the construction cost is reduced, the interpretability and the module coupling degree are improved, multiple scenes such as government and enterprise public opinions and medical assistance are adapted, and the problems of weak generalization, poor real-time performance and'black box 'in the traditional technology are solved.

The invention relates to the technical field of digital people, and discloses a real-time high-fidelity voice-driven digital people system which integrates six modules of voice acquisition, voice recognition, semantic analysis, sentiment analysis, animation generation and rendering generation. According to the invention, through contrastive analysis with the input voice, determination of accent and language styles in the early stage, conversion of the voice into the text, and word segmentation and part-of-speech tagging by using advanced machine learning and deep learning technologies, intentions and demands of a user are deeply understood, and all modules of the digital human system are driven to cooperate; a series of signal processing and feature extraction methods of the sentiment analysis module are applied, and a machine learning or deep learning model is combined to accurately recognize the sentiment polarity in the user voice, so that the system can make corresponding feedback according to a sentiment analysis result, for example, in an intelligent customer service scene, a reply strategy is adjusted according to the user sentiment, and the user experience is improved. And more personalized and humanized services are provided, and emotion resonance of interaction between the user and the digital human is enhanced.

The invention relates to the technical field of intelligent questioning and answering workers, in particular to a power grid equipment intelligent questioning and answering optimization method and system based on a large language model. The method comprises the following steps: acquiring problem data of power grid equipment, and creating a dynamically updated power grid equipment vocabulary to store the problem data; a part-of-speech tagging model of a conditional random field is used for tagging part-of-speech of question data, power grid equipment knowledge retrieval and large language model building are performed based on the question data of tagging and semantic roles, parameter updating is performed on the built large language model, and answer optimization is performed according to a processing result of the large language model. According to the method, a position coding formula combined with semantic information is introduced, so that a large language model can better understand the relationship between a word order and semantics in a text in the field of power grid equipment, semantic logic in the text can be more deeply mastered, the ability of understanding the operation process and the equipment relationship is improved, and answers more conforming to professional logic are output.

The embodiment of the invention provides a project text optimization processing method and device, and the method comprises the steps: deeply analyzing text structure features and semantic features through a knowledge graph and relation extraction, and forming a differentiated text template library; a segmentation processing strategy is adopted, text boundaries are recognized in combination with part-of-speech tagging and syntactic analysis, sequence modeling is conducted on semantic coherence through a recurrent neural network, and semantic breaking points are accurately positioned. A text optimization strategy network is constructed based on a reinforcement learning algorithm, grammar error positions, semantic coherence breaking points and a text template are used as state input, a repair strategy is dynamically generated, and intelligent optimization of a text is achieved. By means of the method, the defects of a traditional technology in the aspects of semantic coherence evaluation, optimization strategy making and the like are effectively overcome, and the professionality and efficiency of project text optimization are remarkably improved.

The invention relates to the technical field of document intelligent review, in particular to a multi-mode digital publishing intelligent review system and method based on a large model, and the system comprises a sample construction module, a multi-mode analysis module, a structure recognition module, a term verification module and an annotation output module. According to the method, a model configuration data set is generated by analyzing a subject-object combination relationship in a text and jointly screening part-of-speech, sentence pattern and semantic structure, the accuracy of semantic recognition and structure judgment is improved, and local features of semantic offset and image-text expression separation are recognized by combining a comparison relationship between an image action path and a text behavior object; a paragraph logic structure and a theme connection mode are analyzed based on semantic offset information, the problems of content dislocation and theme jump between paragraphs are effectively revealed, matching change tracks and part-of-speech continuation fluctuation in term cross-paragraph contexts are recognized, label overlapping and coverage redundancy conditions are analyzed from sentence group hierarchy, and the term cross-paragraph contexts are obtained. And forming a label combination suggestion and constructing an annotation structure record.

The invention discloses an unstructured text entity recognition and relation extraction method under small sample learning, which relates to the technical field of natural language processing, and comprises the following steps of: 1, preprocessing an unstructured text, including word segmentation, part-of-speech tagging and syntactic analysis, and converting the text into structured word vector representation; a pre-training language model is adopted to encode the text, and context semantic features of the text are obtained; 2, constructing a meta-learning model by utilizing a meta-learning algorithm based on context semantic features of the text, training through a small number of labeled samples and a large number of unlabeled samples, and learning common knowledge among different tasks; 3, based on the meta-learning model, word vectors in the text are processed, and entities including boundaries and types are recognized; and according to the identified entities, analyzing a semantic relationship between the entities, extracting a relationship type between the entities, and optimizing a dependency relationship between the entities and the relationship by adopting a dynamic planning method.

The invention discloses a low-delay speech synthesis method and device, a medium and equipment, and belongs to the technical field of speech processing, and the method comprises the steps: S10, carrying out the normalization processing of an input text, and obtaining a normalized text; s20, performing word segmentation processing, part-of-speech tagging processing and rhythm information analysis on the standardized text to obtain a language structured text; s30, performing feature extraction on the language structured text by using a deep learning algorithm to obtain a text feature vector; and S40, converting the text feature vector into a voice signal by using a non-autoregressive voice synthesis model based on a converter. According to the invention, the delay time of speech synthesis is reduced, and the naturalness and expressive force of speech are improved.

Example methods and systems are directed to generating knowledge graph entities from text. Natural language text is received as input and processed using named entity recognition (NER), part of speech (POS) recognition, and business object recognition (BOR). The outputs of the NER, POS, and BOR processes are combined to generate knowledge entity triples comprising two entities and a relationship between them. Keywords are extracted from the text using NER to generate a set of entities. A node in a knowledge graph is created for at least some of the entities. A POS tagger identifies verbs in the text, generating a set of verbs. Relational verbs (e.g., “talk to” or “communicated with”) are detected and used to create edges in the knowledge graph. The knowledge graph may be converted back to natural language text using a trained machine learning model.

The invention discloses an artificial intelligence question answering system and method based on multi-knowledge-base association. The method comprises the following steps: acquiring a question input by a student; preprocessing the questions, including operations of word segmentation, part-of-speech tagging, stop word removal and the like; identifying a plurality of knowledge points and themes involved in the questions; associating a plurality of related knowledge bases based on the identified knowledge points; carrying out vectorization processing on the questions and the content in the knowledge base, and constructing high-dimensional vector representation; matching the question vector with the knowledge base vector by using a vector database, and retrieving knowledge content most relevant to the question; based on the retrieved knowledge content, adopting a generative pre-training model to generate a high-quality answer; and feeding back the generated answer to the student, and collecting the evaluation and feedback of the student on the answer to continuously optimize the system performance. According to the method, complex questions related to multiple knowledge points can be effectively processed, and the matching degree and the answering quality of the question answering system are improved through a multi-knowledge-base association and vectorization matching method. According to the method, the limitation of a single knowledge base and simple text slice reasoning in the prior art is overcome, the artificial intelligence question-answering system has higher intelligence and adaptability, and the constantly changing requirements in the education field are better met.

The invention discloses a teaching aid book intelligent correction and editing system, which comprises a knowledge graph construction module used for collecting authoritative teaching materials, academic literatures, teaching programs and other data, constructing a knowledge graph covering knowledge points of each subject by applying a natural language processing technology and a knowledge extraction algorithm, and establishing an association relationship among the knowledge points, and a text analysis module used for analyzing the association relationship among the knowledge points. An input teaching aid book text can be split into sentences and paragraphs, the technologies of part-of-speech tagging, syntactic analysis and the like are utilized, information such as keywords and key phrases is extracted, the grammatical structure and semantic information of the text are analyzed, and the intelligent proofreading module is used for conducting intelligent proofreading on the basis of a knowledge graph constructed by the knowledge graph construction module and an analysis result of the text analysis module. The knowledge points in the text are compared with the standard knowledge points in the knowledge graph, omissions possibly caused by manual correction and editing are effectively avoided, the correction and editing quality is improved, the workload of manual correction and editing is greatly reduced, and the correction and editing speed is increased.

The invention relates to the technical field of natural language processing, in particular to a foreign trade letter intelligent semantic error correction and business term optimization method and device, and the method comprises the steps: obtaining a target foreign trade letter, and constructing a target corpus; performing Chinese word segmentation and part-of-speech tagging on the target foreign trade letter; performing term optimization based on the word segmentation result and the knowledge graph; identifying the letter title by using a conditional random field model, and converting the letter title into structured data; a Bi-LSTM-CRF model is adopted to carry out risk point detection, including Bi-LSTM coding, feature engineering and Max-pooling technologies, a part-of-speech sequence is obtained through a softmax function and a Viterbi path, and sequence labeling is carried out to obtain a risk point detection result; and finally, performing Chinese error correction based on the word segmentation result after part-of-speech tagging and the knowledge graph. The recognition and correction accuracy of foreign trade terminologies is improved, and communication obstacles caused by nonstandard use of the terminologies are effectively reduced.

The invention relates to the technical field of text processing, in particular to an internet-oriented illegal advertisement recognition method, device and system. According to the method, text information data carried by an advertisement is specifically analyzed, the high distribution consistency condition of part-of-speech and word frequency of each segmented word in a local text before and after special symbol processing and the similarity condition of an overall text are compared and analyzed, and the necessary processing degree of a special symbol is obtained in combination with the connection association condition of words before and after the special symbol processing; through the processed text data and the abnormal possibility of the image and the release time, the violation score of the advertisement is evaluated and identified, and a more accurate evaluation result is obtained. According to the method, by comparing semantic change conditions represented by coherent text contents before and after special symbol processing, interference special symbols carried in the advertisement text are processed, the accuracy of advertisement violation information identification is improved, and violation advertisement identification is more comprehensive and reliable.

The invention relates to the technical field of natural language processing, and discloses a short text classification processing method utilizing a graph attention network, which comprises the following steps of: cleaning short text data, performing word segmentation and part-of-speech tagging, removing redundant words, converting each word into a vector representation with a fixed length by utilizing a word embedding technology, and extracting the vector representation by utilizing a graph attention network; obtaining a text vector matrix; constructing a text graph based on the text vector matrix, and constructing a tag graph according to a known tag relationship; a graph attention mechanism is applied to nodes in the text graph and the label graph, attention coefficients between the nodes are calculated, feature weighted summation is carried out, and updated node embedding representation is obtained. The short text classification processing method using the graph attention network aims at solving the problem that in an existing short text classification processing method, due to the fact that sparsity and characteristics of short texts are insufficient, labels are difficult to predict accurately through a traditional classification method.

The invention discloses a multi-language general part-of-speech recognition method and system based on a large language model, and relates to the technical field of natural language processing and part-of-speech recognition, and the method comprises the steps: employing the large language model as a core base model, and carrying out the efficient fine tuning, language design and multi-field vocabulary and syntactic analysis through a low-rank adaptation technology, model distillation is used for migrating knowledge of a large model to a small model so as to reduce the size and calculation cost of the model, standardized cue words are designed to guide the model to generate standardized output, a part-of-speech recognition task is automatically completed from the standardized output, and finally JSON format data are generated through code analysis model output. And therefore, the front-end display and the back-end service logic processing can be efficiently supported. The output part-of-speech information can be used for various downstream tasks such as intelligent search, text classification, code analysis and grammar verification, and data support is provided for various service systems.

A computer-implemented method for a machine learning based rules compiler, the method comprising receiving machine learning generated ripple down rules, the ripple down rules comprising exception rules for tags in a tag set, the exception rules comprising tag string comparisons. The method further comprises compiling the ripple down rules into optimized computer code. Compiling the rules into computer code further comprises generating an enumeration statement for an enumeration containing the tag set, translating the exception rules for each tag in the tag set into if-else statements for a respective tag, including replacing the tag string comparisons with the enumeration; and generating a switch case statement for a current tag, the switch case statement having cases corresponding the tags in the tag set and including the if-else statements for the respective tag. The optimized computer code comprises the enumeration statement and the switch case statement.

The invention relates to the field of household appliances, and provides a smart home multi-modal dialogue method, device and equipment and a medium, and the method comprises the steps: inputting equipment dialogue data into a multi-modal dialogue model, and extracting word features of text information in the equipment dialogue data, part-of-speech features corresponding to the word features and relation features between adjacent word features, performing text enhancement on the word features and the part-of-speech features according to the relation features, extracting context vectors according to text information, combining the part-of-speech features and the word features after text enhancement to obtain a decoded word sequence, predicting a user emotional state according to device dialogue data, and combining the decoded word sequence to generate a reply prediction result. According to the method, the defect that a multi-mode dialogue technology is difficult to meet human emotion requirements is overcome, and it can be ensured that the generated reply not only conforms to logic in content, but also is matched with a user state in emotion expression.

The invention relates to the technical field of artificial intelligence, data processing and information monitoring, in particular to an early warning method for public opinion screening and public opinion abstracts based on an AI agent. Multiple AI agents are used for collecting public opinion data in parallel from microblog, jittering and other multi-source channels, collection parameters are automatically adjusted according to platform interface specifications and data formats, and the data are efficiently grabbed. After collection, repeated and wrong data are removed through a cleaning algorithm, and word segmentation, part-of-speech tagging and entity recognition of the text are completed by means of tools such as Jieba word segmentation and Harbin Institute of Technology LTP. And based on deep learning models such as CNN, LSTM and the like, AI agent is trained to screen key public opinions. And for the screened public opinions, generating an abstract by using a generative AI agent of a Transform architecture. Meanwhile, public opinions are scored in multiple dimensions and weights are dynamically adjusted in combination with an emotion dictionary, machine learning and other methods. And finally, early warning thresholds such as popularity and emotional intensity are set, real-time early warning is realized, and related subjects are assisted to quickly respond to public opinions.

The invention discloses a malicious content detection method and device, electronic equipment and a storage medium, which are used for solving the problem of low detection accuracy of the existing malicious content detection method, and the method comprises the following steps: obtaining a to-be-detected text; performing word segmentation processing on the to-be-detected text to obtain a word sequence corresponding to the to-be-detected text; the word sequence is input into a malicious content detection model, sensitive words in the word sequence and context information of the sensitive words are output, the malicious content detection model is obtained through training based on feature vectors, part-of-speech features and dependency syntax features of words in a training sample text, the part-of-speech features represent the types of the words, and the dependency syntax features represent the types of the words; the dependency syntactic features represent a syntactic association relationship between the word and other words in the sentence to which the word belongs. According to the malicious content detection model, on the basis of the features of the words of the training sample text, the part-of-speech features and dependency syntax features of the words are combined for training, key features of the text are highlighted, the context perception ability of the model to the malicious content is enhanced, and the detection accuracy of the malicious content is improved.

The invention provides an accounting document classification method and system based on artificial intelligence, and the method comprises the steps: determining a label dependency relationship between text information and a label data set according to the part-of-speech of effective lexical elements in each text keyword; determining text label features in the target accounting document through the label dependency relationship and the semantic loss of each text keyword; performing semantic association matching on the semantic features of the voucher image and each data tag in the tag data set to obtain a semantic inline relationship between the voucher image and the tag data set, and determining image tag features of semantic lexical elements in the target accounting voucher based on the semantic inline relationship; and performing modal fusion on the image tag features and the text tag features, generating a credible tag of the target accounting document based on the tag features after modal fusion, and performing multi-tag classification on the target accounting document by using the credible tag. Based on the scheme, multi-label classification of accounting documents can be realized in combination with feature fusion of the text modality and the image modality.

The invention discloses a retail terminal man-machine interaction method, system and device based on voice recognition and a medium, belongs to the technical field of intelligent terminals and voice recognition, and aims to solve the technical problems of how to realize effective connection between voice input and actual services, simplify a large amount of manual operation processes, improve man-machine interaction efficiency and reduce the labor intensity of workers. According to the technical scheme, the method comprises the steps that real-time voice is obtained and converted into characters, the real-time voice is obtained through a bottom layer interface of real-time voice recognition, the real-time voice is converted into the characters through a voice recognition model, high-precision converted characters are used for correcting and outputting at the end of a voice sentence, and the output characters are provided with punctuations; named entity recognition: performing named entity recognition on the characters subjected to voice recognition through a named entity model, and distinguishing product words, modifiers and quantifiers which can be understood by the business; character conversion vectors; identifying part-of-speech tagging; and scheduling logic.