43 results about "Participle" patented technology

The invention provides a credit granting approval process analysis method and device. Comprising the steps of performing word segmentation on text content in a credit granting approval document set, and combining the obtained segmented words to obtain combined phrases; calculating weighted word frequency-inverse document word frequency of the combined phrases; target phrases with weighted word frequency-inverse document word frequency larger than a word frequency threshold value are screened out from the combined phrases, and an amplified word list is generated according to the target phrases and the original word list; training a target word segmentation device based on the amplified word list; finely adjusting the basic vector model according to the training corpus to obtain a term vector model; analyzing the auditing opinion information based on a large language model to obtain an initial risk analysis rule containing a preset dimension; based on a similarity algorithm, a target word segmentation device and a term vector model, grouping and integrating the initial risk analysis rules to obtain risk analysis rules; and processing the information of each examination and approval stage by using a big language model and adopting a risk analysis rule to obtain examination and approval suggestion information.

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

The application belongs to the field of natural language processing, and particularly relates to a method and system for paraphrase recognition based on semantic primitive knowledge and abstract semantic representation, which comprises the following steps: performing word segmentation on a sentence, and performing word-level vector representation and semantic primitive knowledge representation; performing mean value processing on the semantic primitive knowledge representation result, and extracting interactive attention feature information of the mean value processing result by using global semantic information to obtain global semantic primitive representation; performing abstract semantic analysis on a to-be-recognized paraphrase sentence from a sentence structure to obtain a single-root directed acyclic graph, and performing global semantic primitive representation and word-level vector representation; extracting global and local feature information in the order of the directed acyclic graph, and performing distance feature measurement on the information; inputting the distance feature measurement result into a neural network to obtain a recognition result; the application introduces external semantic primitive knowledge to perform semantic representation, the accuracy of the semantic primitive knowledge representation is assisted by global semantic information, and the abstract semantics of a Chinese paraphrase sentence is analyzed to obtain semantic relations, so that the accuracy of paraphrase recognition is improved.

This invention provides a method for calculating semantic similarity based on adjacent word features, relating to the field of natural language processing. First, in the example word extraction module, example words are extracted from the example sentence and the sentence to be matched using the longest common substring algorithm. Second, in the example sentence processing module, word segmentation is performed on the example sentence excluding the example words, and part-of-speech tagging is applied to the example words. Then, in the feature extraction module, features are extracted from the words surrounding the example words in the example sentence. The correlation between the surrounding words and the example words and option words is calculated using a corpus. The calculated results are weighted and combined with their respective features to form the features of the example words and option words. Finally, in the option processing module, the part-of-speech of the option words is compared with that of the example words, and a similarity score is calculated based on the features of the option words to select the optimal option word. This invention determines the features of the current word by extracting features from surrounding words and calculating correlation; it uses a corpus to calculate the mutual information between two words to achieve the correlation between the two words.

A system and method guide an Artificial Intelligence engine to determine the semantic and grammatical correctness of a user-expanded sentence in real-time. The sentence validation process involves receiving input from the user, the input includes sentence fragment that the user wishes to expand and user-expanded sentence that the user constructs on the fragment provided. The inputs are broken down into tokens. The word-level tokenization algorithm is used, which identifies tokens by splitting the text into spaces, punctuation marks, and other delimiters. Further, a token comparison algorithm is used to assess the relationship between the sentence fragment and the user-expanded sentence to analyze order and placement. Once the token comparison is complete, a prompt is generated using prompt generator to evaluate grammatical and semantic evaluation of the user-expanded sentence. Real-time feedback is provided to the user based on grammatical and semantic evaluation.

The invention relates to the technical field of data processing, in particular to an intelligent foreign form filling and error correction method and system based on natural language processing. The method comprises the following steps: acquiring text images of a historical corpus and vocabularies; screening segmented words to be corrected; determining the ambiguity of the module based on the frequency proportion of the input vocabulary and the vocabulary type; determining a first possibility based on the co-occurrence probability of the adjacent vocabularies of the to-be-corrected segmented word and the similar segmented word and the similarity of the to-be-corrected segmented word and the similar segmented word; determining a second possibility through an error correction result corresponding to the similar word segmentation history and the image similarity of the word segmentation to be corrected and the similar word segmentation; and determining the total possibility and the necessity of word segmentation error correction through the first possibility, the second possibility and the ambiguity, and completing word segmentation error correction. The error correction accuracy is improved.

This invention relates to a method and system for optimizing machine translation using a large language model, belonging to the field of machine translation technology. It includes: generating a corresponding first translation from a source sentence in a bilingual corpus; segmenting the source sentence into words, counting the frequency of easily misspelled words in each segment, and calculating the easily misspelled word score, obtaining an easily misspelled word set based on the score; calculating the semantic similarity between the sentence to be translated and multiple candidate examples, and calculating the quality scores of the multiple candidate examples; selecting the optimal k candidate examples from the multiple candidate examples based on semantic similarity and quality scores, and constructing them as prompt templates; obtaining training sentence pairs from the bilingual corpus based on the easily misspelled word scores to construct a training set; and using the training set and prompt templates to perform low-rank adaptive training on a large language model to obtain an optimized large language model. This invention not only improves translation quality but also enhances the interpretability of the translation process.

The invention discloses a text generation content security filtering method and system based on semantic detection, and the method comprises the steps: obtaining and preprocessing an original content text generated based on the text to obtain a preprocessed content text, carrying out the sentence segmentation of the preprocessed content text to obtain a plurality of sentences, and determining the overall semantic features of the sentences in the context based on semantic detection; performing word segmentation on the sentence to obtain a plurality of vocabularies, and determining specific semantic features of each vocabulary in the sentence based on semantic detection; and evaluating the content security of each sentence based on the overall semantic feature and the specific semantic feature to obtain a comprehensive security evaluation value, determining the security filtering level of each sentence based on the comprehensive security evaluation value, and performing security filtering on each sentence in the original content text. According to the method, security detection is carried out on the text generation content through a multi-level and fine-grained semantic analysis and evaluation technology, complex harmful content which is difficult to detect through a traditional method can be effectively recognized, and accurate risk grading and intelligent flexible processing are achieved.

The embodiment of the invention provides a text topic determination method and device and a storage medium, which can be applied to the technical field of natural language processing, in any segmented word in the method, according to the transmission weight of the segmented word and the underlying topic in a segmented word transmission matrix, a corresponding underlying topic vector when the segmented word vector of the segmented word is transmitted to the underlying topic is determined, and the underlying topic vector of the segmented word is transmitted to the underlying topic. A bottom-layer topic vector is used as an embedding anchor, the transmission direction of a plurality of segmented words is guided, key information is highlighted, and generation of a coherent fine-grained topic is facilitated; and for any (i-1) th layer of theme, according to the transmission weights of the (i-1) th layer of theme and the ith layer of theme in the theme transmission matrix, determining the corresponding ith layer of theme vector when the (i-1) th layer of theme vector of the segmented word is transmitted to the ith layer of theme, guiding the low-layer theme to be transmitted to the high-layer theme among different layers of themes, and realizing alignment of cross-layer themes, therefore, all layers of themes are kept consistent and hierarchical progressive semantically, and a hierarchical theme structure with interpretability and coverage is obtained.

The embodiment of the application provides a text labeling method, system and storage medium, comprising: obtaining a syntax rule set; dividing syntax rules in the syntax rule set into a first rule subset and a second rule subset; obtaining a Chinese text to be labeled; performing sentence division processing on the Chinese text to be labeled to obtain a sentence set; performing word segmentation processing on each initial sentence in the sentence set to obtain a corresponding word set; traversing the syntax rule set, when the word set corresponding to a sentence matches a first verification condition of any syntax rule, generating a candidate syntax set; performing structure verification based on a second verification condition of a syntax candidate to obtain a screening set; when the syntax candidates in the screening set belong to the same rule subset and there is a preset mutual exclusion relationship between the syntax candidates, performing decision verification based on a decision condition corresponding to the rule subset to which the syntax candidate belongs to generate an actual syntax set; and performing syntax labeling on the Chinese text to be labeled based on the actual syntax set.

This invention discloses a hierarchical perception-based method and system for analyzing complex English sentences, relating to the interdisciplinary fields of natural language processing and intelligent education. By defining structural delimiters, sentences are divided into syntactic levels according to the number of effective delimiters, first eliminating invalid parallel structural delimiters; then, a syntactic encoding module completes text segmentation, hierarchical tagging, word embedding, and feature fusion; a hierarchical perception module calculates feature weights and generates target syntactic features; finally, a syntactic decoding module outputs the sentence's main body and modifier decomposition results. The hierarchical framework constructed by this invention fully covers the core modifiers of English, is suitable for the scenario of complex sentences in the College Entrance Examination (Gaokao), and can achieve accurate and lightweight decomposition of all types of complex sentences. It effectively solves the problems of irregular decomposition, poor generalization, and poor adaptability of traditional methods, and the analysis process is clear and teachable.

The invention relates to the technical field of natural language processing, and discloses a word segmentation method and device, equipment and a storage medium. The method comprises the following steps: for any sentence in a text, segmenting the sentence to obtain a plurality of word segmentation results corresponding to the sentence; for any word segmentation result in the plurality of word segmentation results, according to a word vector of any word segmentation in the word segmentation result, based on a frequency domain vector converted by the word vector and a font vector of the word segmentation, determining fusion features corresponding to the word segmentation; wherein the frequency domain vector of the segmented word is obtained by processing the word vector of the segmented word based on Fourier transform, and the font vector of the segmented word is obtained according to the stroke of the segmented word; and determining a target word segmentation result corresponding to the sentence from the plurality of word segmentation results according to the fusion feature corresponding to each word segmentation in each word segmentation result in the plurality of word segmentation results. Therefore, the accuracy of the word segmentation result can be improved.

The application relates to the technical field of natural language processing, and discloses a Chinese numeral quantifier correction method and system, computer equipment and a storage medium. The application constructs a dynamically expandable collocation word table and a numeral dictionary; performs sentence segmentation, word segmentation and part-of-speech tagging on input text, and identifies a three-element structure composed of numerals, quantifiers and nouns; excludes misjudgments on inherent expressions through a fixed phrase filtering mechanism; performs legality verification on the structure based on the collocation word table, and generates processing information for semantic correction if the verification fails; when collocation abnormalities are confirmed and the dictionary is insufficient, a large language model is triggered to replace the quantifier and adapt to the context based on the processing information, so that a final corrected sentence is generated. Through multi-layer cooperation of rule matching, word table verification and large model verification, the application effectively reduces the mis-correction rate while ensuring high-precision correction, and improves the accuracy and practicality of automatic correction of Chinese quantifiers.

The application discloses an entity extraction method based on an MRC framework, which comprises the following steps: firstly, obtaining a target sentence according to a device maintenance manual, generating a corresponding question according to the definition of an entity type, and splicing the target sentence and the question to obtain a corpus; then, performing word segmentation on the corpus by using a word segmentation tool, inputting the corpus into a BERT model after coding to obtain word embedding representation of the target sentence; secondly, obtaining sentence-level features of the target sentence by a sentence classification module; then, combining the sentence-level features and the word embedding representation of the target sentence to integrate into an entity extraction module; finally, combining the sentence classification module and the entity extraction module, training the two modules together, and completing entity extraction according to the two trained modules. The application can use the information at the sentence level in the entity extraction task, which helps to improve the precision of entity extraction and solves the problem of entity extraction in the device maintenance document.

The application discloses a Chinese word segmentation method, device and storage medium, and belongs to the technical field of natural language processing. The Chinese word segmentation method comprises the following steps: S1, a second language translation sentence of a to-be-detected sentence is acquired; S2, a Chinese Bert pre-training language model is used to code the to-be-detected sentence, so as to acquire vector representation of semantic information of the whole sentence and a sentence vector representation sequence; S3, a second language Bert pre-training language model is used to code the translation sentence, so as to acquire vector representation of semantic information of the whole sentence; S4, semantic features of the to-be-detected sentence and the translation sentence are fused, so as to acquire a predicted category of each word of the to-be-detected sentence; and S5, the to-be-detected sentence is segmented according to the predicted category, so as to acquire a word segmentation result. The method improves the accuracy of word segmentation, and has a good word segmentation effect on foreign words in particular.

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

The application discloses a text coding method, which comprises the following steps: data cleaning and preprocessing of a corpus, sentence division and word division of the corpus, extraction of relevant features, coding representation of the sentence, addition of three dimensions on the basis of coding, and construction of an upper model; compared with the prior art, the difference of the application lies in that the previous additional features are mostly intra-sentence features, such as part of speech, syntax dependency, relative position, absolute position and the like, while the application adds global statistical information, the overall operation is simple, the training cost is low, the prior knowledge injection based on global statistical information is carried out on the sentence level coding, and the accuracy of the upstream task is improved.

The application provides a pre-training language model training method, a text sentiment classification method and device, and relates to the technical field of natural language processing. The pre-training language model training method comprises the following steps: obtaining a training sample and sequence text information corresponding to the training sample; performing word segmentation processing on the sequence text information to obtain a plurality of segmented words included in the training sample; obtaining a basic feature vector of each segmented word in the plurality of segmented words and a semantic element feature vector of each segmented word, and splicing the basic feature vector of each segmented word and the semantic element feature vector of each segmented word to obtain an input text vector; processing the input text vector based on a masking task and a sentence relationship task in the pre-training language model to obtain a loss function of the pre-training language model, and training the pre-training language model based on the loss function. By adopting the technical scheme, the semantic representation between sentences can be improved, and the classification of the text sentiment can be accurately predicted.

The application discloses an event trigger word extraction method, which comprises the following steps: S1, inputting a text; S2, segmenting the text and calculating a segment feature vector; S3, calculating a trigger degree attenuation coefficient of different paragraphs; S4, calculating a value coefficient of a sentence n at different positions in the same paragraph; S5, calculating a sentence score according to the paragraph attenuation coefficient and the sentence value coefficient, taking the sentence score as a word position gain, and obtaining an event trigger sentence candidate set; S6, segmenting the sentences in the event trigger sentence candidate set and marking the parts of speech and the word sentiment polarity; and S7, calculating an event trigger degree according to the sentence position gain, the parts of speech and the sentiment polarity, and extracting the event trigger word. The application can be applied to long text level event trigger word extraction, and the purpose of accuracy, rapidity and wide range can be achieved.

The application discloses a question and answer data processing method and device, and a specific embodiment comprises the following steps: in response to a question and answer request, determining a request field, calling a knowledge base to obtain corresponding implication relationship words and synonymous relationship words; performing word segmentation processing on a sentence in the question and answer request, and then removing implied segmented words in the sentence after the word segmentation processing based on the implication relationship words to obtain a to-be-searched sentence; calling a preset corpus, performing similarity calculation on the to-be-searched sentence through the synonymous relationship words to obtain a sentence with the highest similarity and outputting the sentence. Thus, the application can solve the problem that the similarity calculation result is deviated due to redundant information and field synonymous words in a sentence in the prior art, and overcome the shortcoming of the labeling requirement of a large amount of data in a supervised mode.

The invention provides a word segmentation-based Chinese grammar error correction method on an unsupervised synthetic data set, which comprises the following steps of: structuring an operation sequence, firstly segmenting words and then carrying out dynamic mask strategy and consistency training; according to the method, an original Chinese sentence containing errors is mapped into an operation sequence containing four types of labels of KP keeping, RP replacing, IN inserting and DL deleting, and accurate error correction of a model is guided; the method comprises the following steps: randomly masking word units which are marked as KP and do not need to be modified after word segmentation, synchronously generating an MS (masking) label, and forcing a model to depend on context semantics instead of a surface form, so as to efficiently learn sentence semantic information; in addition, a Jensen-Shannon (JS) divergence loss function is adopted to reduce the difference between an operation sequence generated by the low-quality synthetic data and a target operation sequence, and the model robustness is improved. The method aims at improving the performance of an unsupervised Chinese grammar error correction (GEC) task by combining the advantages of seq2Edit and seq2seq series models and utilizing word segmentation to mask.

The invention discloses a new word and first event identification method and device, and the method comprises the steps: obtaining hot line work order text data according to a preset period, and carrying out the preprocessing of the hot line work order text data, and obtaining a structured text stream; performing word segmentation and sliding window processing on the text stream to obtain an initial phrase candidate set; performing statistical admission screening on the initial phrase candidate set, and performing alias merging on the candidate phrases passing statistical admission by adopting a consistency rule of a specified dimension to obtain an entry-level candidate set; updating a current space-time reference baseline based on the entry candidate set, and recalculating historical total data according to a specified fixed period to recalibrate the space-time reference baseline; whether there is a new word in the entry-level candidate set is determined based on the recalibrated spatio-temporal reference baseline, and whether there is a first event is determined. And the new word and the first onset can be accurately and timely determined based on the unified space-time reference baseline.

The application provides a large-scale exploration and development BERT classification method based on semantic fault tolerance, which comprises the following steps: applying a certain proportion of random noise to literature and expanding the corpus; adopting a BERT algorithm to realize context-related first-order classification according to the expanded corpus, and obtaining classified sentences; and adopting an open-source Jieba word segmentation module to perform word segmentation on the classified sentences. Through input text, the number of sentences is expanded while the text chapter structure is kept unchanged, and the BERT algorithm is adopted to take a sentence pair as input, so that the memory of the 1-type grammar to the context before and after the sentence is realized, and the understanding of the chapter structure knowledge is indirectly realized.

The invention relates to a large language model machine translation optimization method and system, and belongs to the technical field of machine translation. Comprising the steps of generating a corresponding first translation for a source end sentence in a bilingual corpus; performing word segmentation processing on the source end sentence, counting the occurrence frequency of error-prone vocabularies in each segmented word, calculating error-prone word scores of the error-prone vocabularies, and obtaining an error-prone word set according to the scores; calculating semantic similarity between the sentence to be translated and the plurality of candidate examples, and calculating quality scores of the plurality of candidate examples; according to the semantic similarity and the quality score, screening out the optimal k candidate examples from the plurality of candidate examples, and constructing the optimal k candidate examples into a prompt template; according to the error-prone word score, obtaining training sentence pairs from the bilingual corpus to construct a training set; and performing low-rank adaptation training on the large language model by using the training set and the prompt template to obtain an optimized large language model. According to the method, the translation quality is improved, and the interpretability of the translation process is enhanced.

The application discloses a Chinese joint event extraction method based on dependency analysis, first introduces dependency analysis to construct a syntactic structure and strengthens the depth interaction of information; secondly, three types of edge representations are designed to calculate graph convolution features in order to bridge the inconsistency of words; finally, the cascade error propagation problem of the traditional pipeline method is relieved through joint learning of the event trigger word classification task and the event argument classification task, and the effect of extracting event triggers and arguments from documents is improved. The Chinese joint event extraction model based on dependency analysis integrates syntactic structure information while encoding semantics, enhances the information flow between words, and designs different types of edge representations for the construction of an undirected graph according to the characteristics of Chinese word segmentation. The application enriches semantic feature representation by integrating the syntactic structure knowledge contained in the Chinese text, and effectively improves the effect of sentence-level event extraction by using the joint learning method.

The method for mapping a noun phrase to a description logic concept based on epitaxy firstly exhaustively lists all text segments of the noun phrase, generates a mapping table of the text segments to resources in a knowledge base; then generates an analysis sequence according to the word segmentation, part-of-speech tagging and syntax tree of the noun phrase; and finally, according to the analysis sequence, continuously refines basic concepts generated by the indexed resources from the concept of EL++, until all words are analyzed, to obtain the description logic concept to which the noun phrase is mapped. The application can automatically process complex noun phrases containing implicit relations and generate high-quality description logic concepts through analysis of the syntax tree.

The invention belongs to the technical field of document processing, and particularly relates to a synonymous sentence recognition method based on semantic feature analysis. Comprising the following steps: segmenting and splicing an input text, and establishing a statement set; performing normalization processing on the statements, eliminating invalid data and performing word segmentation processing; clue words of the candidate synonymous sentences are extracted according to the word segmentation result; screening and filtering, and establishing a statement set index; and generating a translated text by using a machine translation technology, and respectively performing embedded representation on the original statement and the translated text to obtain a polymorphic text representation result. On the basis of semantic representation of the generated words and sentences and translations thereof, word and sentence semantic representation results in various forms can be obtained, synonym features in original words and sentences and translated words are fully utilized to further enhance the accuracy and recognition approach of synonym recognition, judgment on whether the words and sentences are synonymous or not is enhanced, the synonym recognition effect is improved, and the recognition efficiency of the synonym sentences is improved. Efficient data processing of words and sentences and translations thereof is achieved, and a technical basis is provided for practical application of the synonymous sentence recognition method.

The application provides a Chinese event detection method based on a part-of-speech attention mechanism, which is based on a public data set. First, the sentence is divided into words using a word segmentation tool on the data set, and then the part-of-speech sequence of the sentence is obtained using a part-of-speech tagging tool. The part-of-speech sequence of the sentence is input into a CBOW model to obtain a pre-trained part-of-speech vector, so as to learn the fixed collocation information between words, such as "suffered an injury" as a "verb + adverb + noun" structure. Then, the part-of-speech vector, the word vector and the character vector are used to extract the word-level information and the character-level information of the sentence, respectively. When extracting features, a convolutional neural network is used to extract features on the word matrix, the character matrix and the part-of-speech matrix of the sentence. Then, the part-of-speech features are used to calculate the attention score, which is used to assist the model to focus on the verb when calculating; the part-of-speech attention is provided, and after the part-of-speech features are added, the accuracy and efficiency of the model in the trigger word extraction and event type classification tasks are higher.

The application provides a method, device, system, electronic equipment and storage medium for processing text. The method obtains original text and summary text corresponding to conference media content, determines first target vectors of each viewpoint sentence in the summary text and second target vectors of each text sentence in the original text. The first target vector includes a first dense vector and a first sparse vector, and the second target vector includes a second dense vector and a second sparse vector. The dense vector of a sentence indicates the overall semantics of the sentence, and the sparse vector of the sentence indicates the semantics of multiple words in the sentence. In this way, the similarity between the first target vector and the second target vector in the method can reflect the similarity between the text sentence and the viewpoint sentence at the sentence semantic level and the word semantic level, the text sentence that matches each viewpoint sentence can be accurately determined from the original text based on the similarity, and the summary text can be verified.

The application relates to an artificial intelligence technology and discloses a multi-layer attention-based dialogue generation method which can be used in the medical or financial fields, comprising the following steps: performing word segmentation on dialogue text to obtain a word segmentation sequence set; using a first encoder to encode the word segmentation sequence set to obtain a topic sentence vector set; using an attention mechanism to weight the topic sentence vector set to obtain a final sentence vector set; using a second encoder to perform fusion encoding on the final sentence vector set, calculating the similarity between a fusion vector and the topic sentence vector set, weighting and summing the topic sentence vector set according to the similarity to obtain an overall topic vector; using a self-attention mechanism to weight the final sentence vector set to obtain an attention vector set; and using a decoder to decode and splice the overall topic vector and the attention vector set to obtain an answer text. The application further discloses a multi-layer attention-based dialogue generation device, an electronic device and a storage medium. The application can improve the dialogue generation accuracy.