237 results about "Participle" patented technology

The invention relates to a knowledge-enhanced large model data analysis agent visualization method, which comprises the following steps of: performing syntactic analysis by using a PCFG algorithm, identifying syntactic components and relationships of sentences, and splitting the sentences into sub-sentences with complete logic; extracting keywords and entity words of the sentences by combining a word segmentation technology with a business word segmentation library; recommending and summarizing candidate segmented words through a recall strategy, carrying out rough arrangement, fine arrangement and fine arrangement on the candidate segmented words, and correcting and complementing a segmented word result; splitting and analyzing the natural language problem based on the fine-tuned large model, and generating SQL statements meeting business requirements; analyzing the data set generated by the SQL, extracting field information and business meanings, and identifying an association relationship between fields; and automatically recommending chart styles according to data features and user preferences, assembling an analysis report and distributing the analysis report according to a specified frequency. According to the method, knowledge enhancement and large model technologies are combined, so that the efficiency and effect of data analysis and visualization are remarkably improved.

The invention discloses a person and post matching recommendation method based on BERT and a latent semantic algorithm model, and relates to the technical field of person and post matching recommendation, and the method comprises the steps: obtaining the related data of job hunters and the post recruitment text data of employers; performing word segmentation and part-of-speech tagging on the obtained text data, screening out candidate words and noun phrases, obtaining candidate word and document word embedding vectors by adopting a trained BERT model, calculating semantic similarity of the embedding vectors, and creating BERT bitmap data according to a calculation result; a latent semantic model is adopted to analyze semantic correlation in text data, preference prediction scores of job hunters for posts are calculated, corresponding class vectors are calculated through a deep random forest method, the matching probability of the job hunters and the posts is extracted, and post matching recommendation is carried out according to a probability sorting list. By adopting the hybrid recommendation method based on the latent semantic model and the deep random forest, the recommendation is more accurate, and the efficiency is higher.

The invention relates to the technical field of language translation, in particular to a translation precision optimization method and system based on artificial intelligence, and the method comprises the steps: obtaining a source language text, carrying out the phrasing operation on the source language text to obtain a source language sentence sequence of the source text, carrying out the word segmentation operation on each source language sentence in the source language sentence sequence, and carrying out the word segmentation operation on each source language sentence; obtaining a word sequence of the source language sentence; and performing sentiment classification on each source language sentence in the source language sentence sequence based on a pre-trained first sentiment classification model. The sentiment classification is performed on the source language sentences and the target language sentences on the basis of the first sentiment classification model and the second sentiment classification model, and the similarity between the sentences is calculated, so that the sentences after translation are kept consistent in sentiment, the problem of sentiment deviation generated in a machine translation process is favorably avoided, and the translation efficiency is improved. Especially for some texts with strong emotion colors, it is ensured that translated emotion information can be correctly conveyed.

The invention relates to the technical field of natural language processing, in particular to an AI reading management and control method and system based on artificial intelligence, and the method comprises the following steps: carrying out text word segmentation processing on an input original text, segmenting the text into independent sentences, recognizing basic word units in each sentence, analyzing semantic adjacency relationships and syntactic structure features among vocabularies, and carrying out word segmentation processing on the word units; screening and extracting potential phrases representing paragraph meanings, and establishing a candidate semantic unit set; according to the method, through word segmentation, syntactic structure recognition and semantic adjacency analysis of the original text, potential phrases capable of representing paragraph significance are extracted, the candidate semantic unit set is constructed, and modeling of the semantic structure in the text is achieved. And associating the set with the reading fixation duration and the playback action of the user sentence by sentence to obtain a reading behavior response of each semantic fragment, and executing semantic weighting and reading behavior cross analysis according to the reading behavior response. Through the linkage mode, the semantic focus actually focused by the user at present can be recognized.

The invention is suitable for the technical field of semantic understanding, and provides a dialogue type AI multi-intention understanding and decision-making method for a tourism scene, and the method comprises the steps: obtaining a tourism scene dialogue text which is input by a user and is expressed by a dialect; dialect expression is converted into standard Chinese statements through a dialect translation engine, and translation semantic deviation is corrected through a semantic correction model; performing multi-intention modeling on the converted standard Chinese statements, adopting a pre-training language model to combine with dynamic word segmentation processing, aligning special words of dialects to a standard Chinese word list through a dialect word mapping table, and adjusting semantic representation to adapt to dialect features; generating word list probability distribution, and generating a dialect compatible reply containing a multi-intention decision result in combination with an autoregression model; a dialogue state tracking model is trained according to geographic information, user historical interaction data and a cross-dialect corpus, intention switching and composite requests in multiple rounds of dialogues are analyzed, and dialect compatibility and intention recognition accuracy are effectively improved.

The invention discloses an information management method based on intelligent classification and efficient retrieval, relates to the technical field of information management, and solves the technical problem of inaccurate retrieval results caused by lack of deep understanding of information semantics and content. Secondary classification is carried out based on semantics, a standard classification result is determined through an integration and screening mechanism, the information classification accuracy is improved, the core content of information is reflected, word segmentation is carried out through a statistical model to determine retrieval heads, the retrieval heads without retrieval content are removed, the retrieval efficiency is improved, the content to be analyzed is screened by calculating the number proportion, and the retrieval efficiency is improved. Retrieval content is screened according to a scientific quantitative standard, information highly related to user requirements can be quickly positioned, the association strength of a retrieval head and retrieval information is accurately analyzed by means of assigning a grammatical position of a pre-selected retrieval head, calculating cosine similarity and the like, and a strong-association retrieval head and a weak-association retrieval head are distinguished.

The embodiment of the invention provides a long text processing method and device, equipment and a medium. The method comprises the following steps: performing word segmentation on a long text to be processed to obtain a token sequence; the token sequence comprises a plurality of tokens; performing prediction processing on the token sequence by adopting a pre-acquired language processing model to obtain a processed token sequence; the processed token sequence comprises the token sequence and at least one prediction token behind the token sequence; the attention layer of the language processing model is obtained based on fusion of a state space model SSM and a self-attention mechanism, the SSM is used for obtaining global attention of the input token, and the self-attention mechanism is used for obtaining local attention of the input token. According to the method, when the long text is modeled, the effects of reducing the calculation complexity of the model and ensuring the semantic integrity and coherence of model text modeling are achieved.

The invention provides a knowledge base and knowledge graph combined text analysis method and system.The method comprises the steps that for each unregistered vocabulary, similar fields related to the unregistered vocabulary are searched for in at least two word segmentation fragments of a word segmentation sequence, the similar fields in the word segmentation sequence are replaced with the unregistered vocabulary, and the unregistered vocabulary is obtained; obtaining an optimized word segmentation sequence; the method comprises the steps of obtaining an optimized word segmentation sequence, converting the optimized word segmentation sequence into an optimized word segmentation vector, calculating a first similarity based on the optimized word segmentation vector, and generating a summary text and a viewpoint list according to the similarity. According to the method, not only can unregistered vocabularies be automatically recognized, but also the most possible meaning of the unregistered vocabularies can be determined according to the context environment of the unregistered vocabularies; and explanations of different types of texts need to be dynamically adjusted, so that the consistency and accuracy of the meanings of the texts are ensured.

The invention provides a training method of a translation model and a text translation method and device.In the training method of the translation model, pronunciation information and word structure information of words in source language corpus in a training sample are extracted; inputting the source language corpus subjected to word segmentation processing, the pronunciation information of each word and the word structure information into a word embedding layer of the to-be-trained translation model to obtain a word feature vector, a pronunciation information feature vector, a word structure information feature vector and a position information feature vector, and increasing the information input into the word embedding layer of the translation model. According to the method, the word embedding vector is determined according to the word feature vector, the pronunciation information feature vector, the word structure information feature vector and the position information feature vector, the translation result of the source language corpus obtained through the translation model according to the word embedding vector is more accurate, and the model parameters of the translation model are adjusted according to the translation result. The training of the translation model considers more pronunciation information features and word structure information features, so that the precision of the trained translation model is higher.

The invention discloses a deep learning and dependency syntax fused process standard entity relationship extraction method, which comprises the following steps: collecting process production process standard unstructured texts, and labeling entities needing to be extracted to establish an entity relationship data set; the method comprises the following steps: building a MacBERT-BiGRU-IDCNN-CRF entity extraction model, and carrying out training; performing entity extraction on a to-be-extracted process production process standard unstructured text through the trained deep learning model; importing the extracted entities into a natural language processing tool through a dictionary; performing word segmentation on sentences of the to-be-extracted process production process standard unstructured text by taking the sentences as units; performing dependency analysis on each constituent part according to a word segmentation result to obtain a dependency relationship of the sentences; according to the dependency relationship of the sentences, performing hyponymy division on each constituent part in the sentences to obtain a hyponymy relationship; and converting the sentence into a triple structure according to a triple establishment rule established according to the hyponymy and the hyponymy, and importing the triple structure into a graph database. The method can effectively solve the problem of dividing the entity boundary of the text by a natural language processing tool; and through a proposed triple construction rule, the method can better adapt to text characteristics in the field of Chinese process standards.

The invention provides a machine translation system and method based on artificial intelligence, and the method comprises the steps: carrying out the word segmentation of each sentence in a source language text through the semantic complexity of the sentences, and obtaining a word set of each sentence; determining the semantic contribution degree of each sentence on the sentence level in the machine translation process according to the co-occurrence distance and the syntactic dependency relationship among the words in each sentence; further determining the semantic association degree between each sentence and all other sentences on a chapter structure, and determining the chapter-level translation attention of each sentence in the machine translation process through all the semantic association degrees and the semantic complexity of each sentence; and performing text-level machine translation on the source language text based on the semantic contribution degree of each sentence on the sentence level and the translation attention of each sentence on the text level to obtain a target language text. By means of the scheme, semantic association translation between chapter-level sentences can be achieved, and therefore the semantic accuracy of machine translation is improved.

The invention relates to the technical field of text data processing, in particular to a specific domain model training method based on an expert knowledge base, and the method comprises the steps: carrying out word segmentation processing on each sentence in each text in an obtained initial general knowledge base and an initial expert knowledge base; determining a target similarity between every two texts; all texts are clustered, and the initial expert knowledge base and the initial general knowledge base are expanded and deleted respectively; determining a target professional contribution degree corresponding to each target segmented word and a target learning rate corresponding to each sentence in the initial expert knowledge base; and updating the scaling factor, corresponding to each sentence in the initial expert knowledge base, in the LoRA model to a corresponding target learning rate, and performing fine tuning on the language model through the LoRA model to obtain a trained language model. According to the method and the device, the text data in the knowledge base is processed, so that the rationality of training the language model in the specific field is improved.

The invention relates to an access control strategy automatic generation system and method based on multi-task learning, and the method comprises the steps: carrying out the word segmentation, cleaning and embedded vector conversion of an original access control text through a data preprocessing module, and constructing a normative input format; the feature sharing layer module is used for extracting deep semantic features of a text through multi-layer bidirectional coding and an attention mechanism and providing unified representation for downstream tasks; the access control statement identification module is used for judging whether each sentence in the text is an access control statement or not and realizing automatic identification of strategy related contents; and the attribute extraction and annotation module is used for annotating words in the access control statements and extracting subject, object and operation access control attributes. A word coding layer and a sentence coding layer are shared, local and global attention mechanisms are combined, key information of a text is extracted, the semantic understanding ability is enhanced, and cooperative training of statement recognition and attribute extraction is achieved; a conditional random field CRF structure is used for sequence labeling, and the structural rationality of attribute labels is ensured.

The invention discloses a translation quality evaluation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a to-be-evaluated task; for each to-be-evaluated translated sentence, evaluating the target to-be-evaluated translated sentence based on a target reference translated sentence set associated with the target source text statement to obtain a sentence level evaluation attribute corresponding to the target to-be-evaluated translated sentence; evaluating each to-be-evaluated segmented word in the target to-be-evaluated translated sentence based on a reference translated word in the target reference translated sentence set to obtain a word level evaluation attribute corresponding to each to-be-evaluated segmented word; and according to the sentence level evaluation attribute of each to-be-evaluated translated sentence and the word level evaluation attribute of each to-be-evaluated segmented word, generating a translated text evaluation report corresponding to the to-be-evaluated task. The effect of more objectively and accurately evaluating the overall translation quality of the translated text and the translation quality of the proprietary entity is achieved.

The invention discloses an intelligent equipment fault relation extraction method based on multi-semantic knowledge interaction and dynamic pruning. Performing word segmentation and sentence segmentation on the original equipment fault text to obtain a statement set; obtaining a character-level word embedding representation set of the text by using a pre-training language model; extracting fault entity representations, obtaining fault type representations based on the constructed fault type knowledge base, constructing semantic association between the fault type representations, and generating a context feature representation sequence; calculating a correlation score between the enhanced semantic representation and an original text statement based on a dot product attention mechanism, dynamically selecting a core statement set, focusing the core statement, updating the semantic representation, and inputting the semantic representation into a relationship classification module to predict a relationship type between the entity pairs; and finally, outputting a named entity boundary and a relation label based on conditional random field decoding to obtain a final relation extraction result. According to the method, the ability of understanding the context is enhanced, and the fault relation extraction task under the complex context can be better processed.

The invention relates to the technical field of risk portrait generation based on a knowledge graph, and discloses a risk portrait generation method based on the knowledge graph. According to the scheme, the document is segmented through the sentence end symbols, semantic coherence is ensured, and the accuracy and stability of candidate word extraction are improved. Continuous Chinese character sequence segmentation is adopted, dependence of a word segmentation tool is avoided, the occurrence frequency and position of candidate words are recorded, and a detailed statistical basis is provided for risk factor screening. A minimum occurrence number constant is set, noise interference and information coverage are balanced, the screening flexibility is improved, and candidate word screening is more representative. And counting the co-occurrence relationship of candidate words in the sentence, quantifying the co-occurrence frequency through an indicator function, enhancing word association expression, and providing key data for initial graph construction. Finally, the scheme constructs a knowledge graph based on the candidate words and the co-occurrence relation thereof, ensures clear expression of risk information, and improves the accuracy of the system in risk identification and portrait generation.

The invention discloses a Chinese sentence semantic similarity calculation method based on a recursive convolutional neural network. Belongs to the field of data cleaning in data mining, and the method performs calculation based on a semantic similarity network model, and comprises the following steps: obtaining a sentence pair data set, and extracting sentence pairs in the data set to obtain word-segmented text sentence pairs; extracting preliminary semantic features and deep semantic features of the sentence pairs; using an Attention layer to generate weights of feature vectors of the sentence pairs according to the deep semantic features of the sentence pairs; and inputting the weights of the feature vectors of the sentence pairs into the full connection layer to generate the similarity of the sentence pairs. According to the method, the output connotation of the word vector is enriched, the input of the original sentence pair is better reflected by using the self-adaptive pooling layer, and the performance of the model is improved; according to the method, an Attention layer is designed to distribute corresponding weights for sentence pair features, so that a model is focused on key information in data, a more direct semantic dependency relationship in sentences is extracted, and the accuracy of semantic similarity judgment of the sentences is improved.

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 present invention relates to the technical field of language translation, and specifically to a method and system for optimizing translation accuracy based on artificial intelligence, including: obtaining a source language text, performing a sentence segmentation operation on the source language text to obtain a source language sentence sequence of the source text, and performing a word segmentation operation on each source language sentence in the source language sentence sequence to obtain a word sequence of the source language sentence; performing sentiment classification on each source language sentence in the source language sentence sequence based on a pre-trained first sentiment classification model. The present invention performs sentiment classification on the source language sentence and the target language sentence respectively based on the first sentiment classification model and the second sentiment classification model, and calculates the similarity between them to ensure that the translated sentence is consistent in sentiment, which helps to avoid the problem of sentiment deviation in the process of machine translation, especially for some texts with strong sentiment colors, and ensures that the sentiment information of the translation can be conveyed correctly.

The present invention belongs to the technical field of large-model natural language processing, and discloses a text generation method and device based on automated hallucination detection and large models. The method comprises: obtaining an input initial text; extracting a number of vocabulary units of the initial text using a word segmenter; constructing a knowledge database using automated hallucination detection, wherein the knowledge database is composed of a number of knowledge fragments, each of which is associated with a number of candidate words; determining the similarity between the several vocabulary units and each of the knowledge fragments; determining a number of target candidate words based on the similarity; and generating a target text based on the several target candidate words. In the above manner, low hallucination data is obtained from the knowledge base data through an automated hallucination detection and recognition algorithm, and the data in the knowledge base is integrated to adjust the probability distribution of the candidate words in the decoding process to enhance the reliability of the generated text, thereby improving the accuracy of the generated text.

To provide a data processing method on natural language processing, deep learning technology, and large-scale language model technology, a data processing model, and a training method therefor.SOLUTION: A data processing method comprises: determining input data containing a plurality of participles; and determining the correlation between each participle of the plurality of participles and each expert network of a plurality of expert networks on the basis of a gating matrix, the plurality of expert networks being used to strengthen the plurality of participles. The data processing method also comprises: distributing the plurality of participles to the plurality of expert networks in a uniform manner on the basis of the correlation and the preset capacity of each expert network; and reinforcing the plurality of participles and determining the data processing results on the basis of the plurality of enhanced participles.SELECTED DRAWING: Figure 2

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 invention provides a multi-word expression-oriented machine translation differential test method aiming at the problem of inaccurate multi-word expression semantic translation in a mainstream machine translation system. The method comprises the following steps that a word segmentation tool based on deep learning is adopted to divide words into vocabulary units, syntactic labels are distributed in combination with a pre-training sequence marking model, and a dependency analysis tool spaCy is utilized to mark the syntactic relation between the words; converting the tagged corpus into a standard CoNLL format, extracting a multi-word expression of a sentence through an automatic tool, and establishing a test data set of a sentence-level and phrase-level corresponding relationship; inputting the test set into a multi-translation system to generate a translation, and using an alignment tool AWESOME to accurately locate a corresponding relationship between a source language and a target language MWEs; the translation similarity is calculated based on BERTScore, mistranslation, translation omission and non-translation are recognized through an intra-group and inter-group dual check mechanism in combination with a dynamic threshold value, and evaluation of the translation accuracy of machine translation on multi-word expression is completed. According to the method provided by the invention, multi-word expression translation errors can be accurately recognized, and the accuracy of phrase-level semantic translation of a machine translation system is finely evaluated through a differential test method.

The invention relates to the technical field of contract intelligent auditing, in particular to an international trade contract intelligent auditing system based on natural language processing, which comprises a data acquisition preprocessing module, a key vocabulary extraction module, a key vocabulary analysis screening module and a text similarity association module, the data acquisition preprocessing module carries out word segmentation and segmentation on a contract text and a regulation standard text, then the key word extraction module extracts a key word set in each text segment through a word frequency statistical method, and in order to prevent the situation that the key word set extracted by the key word extraction module is inaccurate, the key word set is extracted by the key word extraction module. The key vocabulary analyzing and screening module analyzes the paraphrases of the key vocabularies in the corresponding words, removes the key vocabularies which are not nouns in the key vocabulary set, provides a paraphrasing basis for the vocabulary same paraphrasing mapping unit, unifies same paraphrasing word vectors, and transmits the same paraphrasing word vectors to the key vocabulary same paraphrasing mapping unit; and the contract and the regulation text are deeply associated in terms of vocabulary semantics.

The present application provides a method and device for processing polyphones, and a model training method and device, wherein the polyphone processing method includes receiving a Chinese sentence containing polyphones, and determining a first position feature of the polyphones in the Chinese sentence; segmenting the Chinese sentence, and determining the part-of-speech feature of the polyphones based on the words obtained by the word segmentation and the part-of-speech of the words; obtaining a word containing the polyphone, and determining a second position feature of the polyphone in the word containing the polyphone; inputting the first position feature, the part-of-speech feature, and the second position feature into a polyphone disambiguation model to obtain the pronunciation corresponding to the polyphone.

The present invention provides a method, device, electronic device and storage medium for constructing parallel sentence pairs, wherein the method comprises: obtaining a first sentence and a second sentence, wherein the first sentence and the second sentence correspond to different languages; determining a first semantic feature of the first sentence and a second semantic feature of the second sentence based on a cross-language language model, wherein the cross-language language model is obtained by training based on a semantic relationship between each participle in a first sample sentence and each participle in a second sample sentence, wherein the first sample sentence and the second sample sentence correspond to different languages; constructing parallel sentence pairs based on a similarity between the first semantic feature and the second semantic feature, wherein in an embodiment of the present invention, model training is performed using the semantic relationship between the participles contained in sample sentences of different languages, so that the performance of the trained model can be improved, and when facing a scarce resource language, the accuracy of sentence embedding is improved, the construction process of parallel sentence pairs is refined, and the quality of parallel sentence pair construction is improved.

The present disclosure provides a semantic recognition method, a semantic recognition device, a computer-readable storage medium and an electronic device, and relates to the technical field of natural language processing. The semantic recognition method comprises: obtaining a sentence to be recognized, performing word segmentation processing on the sentence to be recognized according to a semantic template, obtaining a set of words to be recognized and a first template word set corresponding to the set of words to be recognized; determining the evaluation index value corresponding to each word based on each word in the set of words to be recognized and the word type of each word, and calculating the first similarity between the sentence to be recognized and the semantic template using the evaluation index value corresponding to each word; calculating the second similarity between the sentence to be recognized and the semantic template based on the sum of the lengths of each word in the set of words to be recognized and the sum of the lengths of each word in the first template word set; and outputting the first recognition sentence corresponding to the sentence to be recognized based on the first similarity and the second similarity. The present disclosure can improve the recognition rate of semantics and expand the recognition range of semantics.

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

The present application discloses a pronunciation prediction method and related devices. First, the text to be synthesized is segmented to obtain a segmentation sequence. For the first category of words in the segmentation sequence, the pronunciation information of the first category of words is determined based on a preset corpus resource library. For the second category of words other than the first category of words in the segmentation sequence, their pronunciation categories are determined based on the part-of-speech information of each word in the segmentation sequence, and their pronunciation information is determined based on the pronunciation information determination method corresponding to their pronunciation category. In the present application, combined with the corpus resource library and the preset pronunciation information determination method corresponding to each pronunciation category, it is possible to cover the pronunciation information determination in various situations. Therefore, it is possible to accurately determine the pronunciation information of each word in the text to be synthesized, thereby improving the effect of speech synthesis.

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.