112 results about "Word representation" patented technology

The invention relates to the technical field of deep learning, and discloses a cultural and creative product iterative design method and system based on user emotion feedback. The method comprises the following steps: performing multivariate feature fusion on a first user evaluation text to obtain a fine-grained emotion dictionary in the field of cultural and creative products; extracting enhanced word representation and constructing a user emotion feedback information extraction model; processing the second user evaluation text and calculating to-be-optimized design parameters; performing grid division to generate a diversified optimization design scheme set; performing score prediction through the initial design scheme evaluation model to obtain a candidate design scheme set; and iteratively optimizing the candidate design scheme set, updating the initial design scheme evaluation model, and outputting a target design scheme evaluation model and a target creative product design scheme when a termination condition is satisfied. And the schemes can be effectively evaluated and screened.

This invention relates to the field of text processing technology, and in particular to a method, device, and medium for processing navigational notice text based on semantic enhancement. The method includes: first, acquiring a content carrier to be processed; then, acquiring the semantic vector and glyph feature vector of the content carrier; concatenating the two types of vectors to form an enhanced text representation; extracting temporal features from the enhanced text representation to obtain temporal features containing forward and backward logical relationships within the text; acquiring the weights of words and sentences in the temporal features and performing weighting to obtain weighted word representations and weighted sentence representations; performing correction processing on the weighted representations to generate corrected text; and finally, validating the corrected text and outputting the target text. This invention can improve the accuracy and efficiency of content carrier processing.

The invention discloses an equipment health state prediction question-answering system and method for pre-training a large language model. The system comprises an acquisition module, a marking module, an editing module, a prediction module and an interaction module. The acquisition module is used for acquiring time sequence data of industrial production equipment and preprocessing the time sequence data to obtain processed data; the marking module is used for dividing and marking the processed data to obtain a marked sequence; the editing module is used for reprogramming the mark sequence to obtain word representation of the time sequence data; the prediction module is used for collecting the health state of the industrial production equipment for prediction based on the word representation to obtain a prediction result; and the interaction module is used for interacting with the user to complete question and answer communication of the prediction result. According to the method, a large amount of structured and unstructured data can be processed, so that the key indexes and modes of the health state of the equipment are identified more accurately, the health state of the equipment is predicted, instant early warning information is provided, and an enterprise is helped to take measures before a fault occurs.

A method for determining a category responsive to a user query is disclosed. The method includes receiving a training data set comprising a plurality of data pairs, each data pair including: (i) a query; and (ii) an associated one or more categories that are responsive to the query, wherein the one or more categories in the training data set defines a plurality of categories. The method includes training a machine learning algorithm, according to the training data set, to create a trained model, wherein training the machine learning algorithm includes: creating a first co-occurrence data structure defining co-occurrence of respective word representations of the queries with the plurality of categories, and creating a second co-occurrence data structure defining co-occurrence of respective categories in respective data pairs. The method also includes deploying the trained model to return one or more categories in response to a new query input.

Disclosed herein is a method for generating insights from words and phrases mapped in high-dimensional space. The method includes obtaining a plurality of communications. The plurality of communications comprise a plurality of words and phrases. Further, the method includes obtaining a model configured through training to cluster word representations of the plurality of communications. The method also includes applying a constraint to at least a group of the plurality of communications to obtain at least one modified group. The constraint is at least one of a keyword, a phrase, or groupings of words in phrases. Once the modified group is determined, the method proceeds to representing the at least one modified group into word representations then determining a category for the at least one modified group.

Embodiments of the present disclosure provide a method, an apparatus and an electronic device for determining a word representation vector, and a computer-readable storage medium, which belong to a field of processing natural languages. The method includes obtaining a set of glyph units of a text; obtaining a context vector of the text based on the set of glyph units; and predicting next word of the text based on the context vector. The method for determining the word representation vector of the present disclosure can effectively obtain a corresponding set of glyph units even for hieroglyphics in which hyperbolic characters are prone to appear or languages evolved from the hieroglyphics, thereby improving an accuracy of determining the word representation vector.

Aiming at the problem of how to improve the accuracy of a false news detection model, the invention designs a multi-modal false news detection method based on content and external facts. In order to enable the two modes to better focus on own preference parts and eliminate other redundant information as far as possible, a deep heterogeneous graph convolutional network (HDGCN) is introduced as a preference learning device, which can generate own required preference perception for the two models and reduce redundant information. Meanwhile, in order to more effectively model the node representation of the graph neural network, style words in the news are expanded by semantic mining, entity words in the news are expanded by entity links, and the obtained five word representations are jointly used as the node representation of the graph network. Finally, experiments on a public data set show the effectiveness of the model. In the field of false news detection, an idea and a wide application prospect are provided.

The invention discloses a tree species identification method based on visual word bag representation and state space modeling, and relates to the technical field of tree species cross section microscopic image identification, and the method is characterized in that the method comprises the following steps: S1, data set construction; s2, extracting local features by using a visual word bag model; s3, extracting global features by using the state space model; s4, performing multi-level feature fusion; s5, data oversampling and classifier training are carried out; and S6, identifying tree species. The technical problem to be solved by the invention is to provide a tree species identification method based on visual word bag representation and state space modeling, a state space model is introduced to model a feature sequence of a tree species image, a long-term dependency relationship of the feature sequence is mined, and global feature information is extracted. Through fusion of local and global features, multi-level feature representation with strong discrimination capability is constructed. Samples are balanced by adopting a synthetic minority class oversampling technology so as to improve the discrimination capability of a support vector machine classifier.

The invention relates to the technical field of text processing, in particular to a navigation announcement text processing method and device based on semantic enhancement and a medium, and the method comprises the steps: firstly obtaining a to-be-processed content carrier; then obtaining a semantic vector and a font feature vector of a to-be-processed content carrier; splicing the two types of vectors to form enhanced text representation; performing time sequence feature extraction on the enhanced text representation to obtain a time sequence feature containing a forward and backward logic relationship of the text; obtaining weights of words and sentences in the time sequence features and completing weighting to obtain weighted word representation and weighted sentence representation; performing correction processing on the weighted representation to generate a corrected text; and finally, checking the corrected text, and outputting a target text. According to the invention, the processing accuracy and efficiency of the content carrier can be improved.

The invention belongs to the technical field of approximate semantic matching of texts, and particularly relates to a rule retelling matching method and system based on deep learning and cosine similarity matching. Comprising the following steps of: 1, constructing a graph structure of a text, expressing text information as a graph node mode, and expressing a relationship between vocabularies by using edges of a graph; 2, introducing a nuclear power professional vocabulary library; 3, modeling context vocabulary correlation by a language knowledge attention model, iteratively updating word representation and semantic representation, and fusing useful information of the word representation and the semantic representation; and 4, fusing word representation into a character level, matching two character sequences by using a bilateral multi-view matching mechanism, and predicting a relationship between two sentences by using a relationship classifier by using a sentence vector as an input. The method has the beneficial effects that the problem that accurate matching is difficult due to the fact that the repeated text and the original procedure text are the same in semantics and different in vocabularies during personnel retelling can be solved.

The present disclosure relates to a text representation method, a word representation method, a corresponding device, a medium and equipment, the text representation method comprising: obtaining a text and performing word segmentation on the text to obtain a word sequence; generating a text vector of the text, and performing at least one round of iteration on the text vector, each round of iteration comprising multiple sub-iterations; in the i-th sub-iteration of each round of iteration, based on a sliding window with a length of k, after sliding the sliding window of the last sub-iteration on the word sequence backward, performing weighted combination on the real word vector of the k words in the current sliding window and the text vector optimized in the last sub-iteration, taking the vector after the weighted combination as the predicted word vector of the next word outside the current sliding window; optimizing the text vector according to the predicted word vector and the real word vector of the next word; and after completing the at least one round of iteration, obtaining a final text vector for representing the text. The present disclosure can accurately obtain the vector representation of the text.

The present application provides a method, apparatus, electronic device, computer-readable medium and computer program product for processing multimodal data. The method of the present application includes: obtaining a text feature vector by performing word representation processing on the text content of the data to be processed; if the data to be processed contains a predetermined number of pictures, obtaining a picture feature vector by extracting the picture features of each picture and mapping the picture features to the text feature space; if the number of pictures in the data to be processed is less than the predetermined number, then after mapping the picture features to the text feature space, the mapping result is zero-filled according to the preset input sequence length; the multimodal fusion features obtained by feature fusion of the text feature vector and the picture feature vector are used as the input of the multimodal model; the multimodal model is trained to output the prediction result of the predetermined prediction task in the multimodal model based on the input multimodal fusion features. The present application realizes the use of one model to simultaneously process pure text data and data containing text and pictures, saving computing resources.

An object of the present invention is to propose a technique that enables even a person who is not an expert to easily identify a DF in order to support creation of a scenario in accordance with an actual situation of an organization such as a company.According to the present invention, there is provided a strategic planning support device 3 that supports strategic planning of a company, the device 3 including: a relationship analysis unit 34 configured to analyze a word representing human behavior or regulations related to each of a plurality of detailed items in a financial index of a predetermined organization, the financial index varying due to a past similar event similar to an event of the predetermined organization; and an output unit 35 configured to output, as each element of a coordinate axis of a driving force, a first word representing human behavior related to a first detailed item having the largest ratio in the financial index and a second word representing human behavior related to a second detailed item in which an absolute value of a correlation coefficient related to a correlation with the human behavior or regulations related to the first detailed item is equal to or less than a threshold value, among the plurality of detailed items.

The embodiment of the application provides a kind of multi-modal large model image segmentation method and device based on hierarchical word representation, mask image is encoded into word sequence by designing mask marker, and progressive generation from shape prototype to local detail is realized by causal attention mechanism.Three-stage training strategy is adopted, first, the marker is trained through the mask reconstruction task, then the mask word is integrated into the large multi-modal model and jointly trained, finally, it is fine-tuned using high-resolution data.Multi-level supervision is carried out based on hierarchical mask loss function, and accurate segmentation of natural language description target is realized.The method effectively solves the deficiencies of traditional technology in complex scene understanding, model training and mask generation, and significantly improves the performance of multi-modal image segmentation.

The application discloses a Chinese named entity recognition method based on pinyin enhancement, and the method comprises the following steps: obtaining a two-dimensional pinyin grid embedding vector and a word representation vector of a text to be recognized; projecting based on the word representation vector to obtain a two-dimensional grid feature vector; calculating a fusion feature between any two characters of the text to be recognized based on the pinyin grid embedding vector and the two-dimensional grid feature vector; calculating a first corresponding prediction score vector based on the fusion feature between any two characters by fusing the pinyin grid embedding vector and the two-dimensional grid feature vector; calculating a second corresponding prediction score vector based on the word representation vector; calculating a total prediction score vector based on the first corresponding prediction score vector and the second corresponding prediction score vector; and outputting the named entity of the text to be recognized based on the total prediction score vector, so that the efficiency of the Chinese named entity recognition based on pinyin enhancement is improved.

The application discloses a kind of multi-modal aspect-level sentiment analysis method, device, equipment and storage medium.The application includes: obtaining multi-modal input data;The multi-modal input data includes input sentence and input image;The input image is input into pre-training conversion model, and the image caption of the input image is output;The context text representation of the input sentence and the context image caption description representation of the image caption are generated;Based on attention mechanism, the context text representation and the context image caption description representation are used to generate semantic information;The syntax mask matrix is constructed using the semantic information;Aspect word representation is obtained by performing graph convolution operation on the syntax mask matrix;The aspect word representation includes text representation and image representation;The text representation and image representation are interactively predicted to obtain the sentiment classification of the multi-modal input data.

The invention belongs to the field of computer vision, and relates to a semantic disambiguity-based image-text retrieval method, a storage medium and a semantic disambiguity-based image-text retrieval device, which comprises the following steps of: obtaining a to-be-retrieved text word, and encoding text data by adopting a Bi-GRU model and a Bert model; carrying out ambiguous word updating on the encoded text by adopting a GAT network; calculating the significance similarity between the updated ambiguous words by adopting a related layer, and generating weight distribution of perceptual significance according to the significance similarity; embedding each ambiguous word into the original text according to the weight distribution to obtain a new ambiguous word expression; aligning the new ambiguous word expression with the image region features; matching the aligned words and images; according to the method, an image-text alignment perception mechanism is designed, and joint optimization of semantic disambiguation and image-text retrieval is achieved. Experiments show that the method significantly improves the accuracy, robustness and practicability of cross-modal image-text retrieval.

Systems and methods for incorporating machine learning to predict post operative right ventricular failure using echocardiograms are described. In an embodiment, the system obtains echocardiography video data describing a patient's heart, generates several dense trajectory descriptors based on the echocardiography video data, reduces the dense trajectory descriptors to a bag-of-words representation, generates a first prediction metric of RV failure based on the bag-of-words representation, generates a second prediction metric based on the echocardiography video data using a neural network, and generates an output prediction metric by applying a weighted classifier to the first prediction metric and the second prediction metric.

The invention discloses a dialogue aspect-based emotional tetrad extraction method, which comprises the following steps of: 1) extracting context-aware word representation for each utterance in a dialogue D; 2) carrying out overall modeling on the semantics of the whole dialogue, and refining the incidence relation between the utterances; 3) performing cross-utterance grammar analysis on a word level; 4) fusing multi-level associated information; and 5) based on the word level representation obtained in the step 4), processing all possible word pairs in the dialogue to obtain a complete emotion tetrad. According to the multi-level association optimization network framework, the association expression of the utterance level is remarkably enhanced through overall semantic modeling, meanwhile, by means of cross-utterance grammar analysis, the association modeling capacity of the word level is effectively improved, and the accuracy of overall tetrad extraction is improved.

Embodiments of the present application provide a method and device for determining word representation vectors, electronic equipment and computer readable storage medium, and belong to the field of natural language processing. The method comprises: obtaining a set of word units of a text; obtaining a context vector of the text based on the set of word units; and predicting a next word of the text based on the context vector. The method for determining word representation vectors can effectively obtain a corresponding set of word units even for pictographic characters or languages evolved from pictographic characters that are prone to out-of-vocabulary words, thereby improving the accuracy of determining word representation vectors.

Embodiments of the present application provide an information retrieval method and device, electronic equipment and computer readable storage medium, and relate to the field of artificial intelligence. The method comprises: dividing a question to obtain at least one question word, and dividing a target document containing an answer to obtain at least one document word; determining at least one document word representation corresponding to at least one document word based on at least one question word and at least one document word; dividing the target document into at least one short sentence, and determining at least one short sentence representation corresponding to at least one short sentence based on at least one document word representation; and determining at least one target short sentence from at least one short sentence as an answer corresponding to the question based on at least one short sentence representation. The present application solves the problems of incomplete semantics and missing extraction in the prior art when extracting long answers, thereby saving the time cost of user information retrieval and improving the user's retrieval experience.

The invention discloses a training method of a cue word quality evaluation model and a quality evaluation method.The training method comprises the steps that a cue word training text is obtained, text sequence word segmentation is conducted on the cue word training text, and a semantic accuracy sequence, an expression integrity sequence and a logic continuity sequence of the cue word training text are obtained; according to the semantic accuracy sequence, the expression integrity sequence and the logic continuity sequence, performing multi-dimensional parallel coding fusion processing to obtain a target cue word representation vector; performing double-branch prediction fusion on the target cue word representation vector to obtain fused prediction data; and according to the fusion prediction data, performing parameter updating on the initialized cue word quality evaluation model to obtain a trained cue word quality evaluation model. According to the training method, a cue word quality evaluation model can be provided, and the model can be beneficial to improving the interpretability and accuracy of cue word quality evaluation. The invention relates to the technical field of natural language processing.

The application discloses a kind of aspect-level sentiment analysis method based on multilevel knowledge enhancement, belong to sentiment analysis field. Including the following steps: S1: text word vector is obtained using GloVe word embedding tool, the syntax dependency tree of sentence is constructed using Stanza, and the dependency graph is constructed accordingly;S2: the context representation of sentence is extracted by inputting word vector into BiLSTM, and the dependency graph is updated using sentiment dictionary and sensitive relationship set, to realize the sentiment and syntax enhancement of sentence;S3: the enhanced dependency graph is input into GCN to model node features, to obtain specific aspect representation;S4: aspect word is enhanced using concept atlas to obtain aspect word representation, which is fused with specific aspect representation to obtain aspect representation;S5: aspect representation and context representation are coordinated and optimized using interactive attention, to obtain the final representation of sentence, so as to determine aspect sentiment tendency.The application can effectively improve the accuracy of specific aspect sentiment classification, and help merchants accurately locate problems in products or services.

The invention discloses a network public opinion monitoring method and system based on a big data platform. The method comprises the steps of collecting a large amount of historical public opinion data; preprocessing and word segmentation are carried out on the historical public opinion data, and a set of all different words appearing in all the historical public opinion data is obtained and recorded as a word bank; obtaining a bag-of-word representation of each piece of historical public opinion data by using a word library, and marking a tag vector of each piece of public opinion data; calculating parameters pi < c > and theta < jc > of a Beyer classifier by using the bag-of-word representation of the corresponding public opinion data in the training set and the corresponding label vector; the method comprises the steps of obtaining real-time public opinion data of a target object, carrying out word segmentation on the real-time public opinion data, calculating the posterior probability that each word is positive information and negative information, calculating and comparing the posterior probability of the positive information and the posterior probability of the negative information of the real-time public opinion data, and outputting the data with the large numerical value as a prediction result of the real-time public opinion data. According to the invention, the model training period is short, and maintenance is easy.

The present application relates to a kind of large model atlas question answering method and device based on potential unit fine-tuning, the method includes the following steps: based on the knowledge graph of symbolization and relationship path and the variable of using high-dimensional prompt word representation potential unit, potential relationship learning is carried out between large language model and knowledge graph, and relationship reasoning path is generated, wherein the input layer of large language model is additionally trainable potential unit;And potential unit is randomly initialized by normal distribution, and is fine-tuned with large language model in hidden learning process;Relevance evaluation is carried out to relationship reasoning path, and the most relevant relationship reasoning path is selected;Input natural language question, and the answer in knowledge graph is obtained by the most relevant relationship reasoning path.The present application filters out irrelevant and misleading context fragments using these fine-tuned potential units, while improving response efficiency and performance.

The invention discloses a lexical element representation method and device and electronic equipment. The method comprises the following steps: S1, performing word segmentation on an input text by adopting a first word segmentation device to obtain a first lexical element sequence arranged according to the sequence of the input text; s2, performing word segmentation on the input text by adopting a second word segmentation device to obtain a second lexical element sequence arranged according to the sequence of the input text; extracting lexical units, different from the first lexical unit sequence, in the second lexical unit sequence to form a combined phrase set; s3, converting the lexical elements corresponding to the first lexical element sequence into a first embedded sequence, converting the lexical elements corresponding to the phrases in the combined phrase set into embedded vectors, and fusing the embedded vectors into a second embedded sequence; and replacing the corresponding elements in the first embedding sequence with the elements in the second embedding sequence to obtain a compressed embedding sequence. On the premise that an original model embedding matrix can be reused, high-frequency cross-word boundary phrases are dynamically fused to shorten the sequence length, and therefore the calculation efficiency and the expression capacity of a subsequent model are improved.

Embodiments of the present invention relate to an intelligent question-answering method, device, equipment and storage medium, which use two context-aware transformations to incorporate context information into the word representation in the dialogue scenario; store the dialogue scenario and the knowledge base semantic information separately; understand the user's current statement through a memory network, and activate the current dialogue generation task; the working memory dynamically controls the "activation" of the long-term memory, reads the content related to the current task from the long-term memory into the short-term storage, and then generates the current reply word by word based on a heuristic strategy. The present invention can store the dialogue scenario and the knowledge base semantic information separately, and utilize the information stored in these two ways through memory reasoning, can efficiently utilize the external knowledge base information, and greatly improves the performance of task-based dialogue generation.

The invention discloses a named entity recognition system and method based on parallel LSTM (Long Short Term Memory) and a gating mechanism, and relates to the technical field of computer data processing, and the system comprises a character modeling module which is used for generating character-level word representation from an input character sequence; the statement modeling module is used for splicing the character-level word representation and a word-level pre-training representation searched from an external pre-training word vector library according to a word index to obtain a word representation matrix, and obtaining a statement-level word representation based on the word representation matrix; and the sequence decoding module is used for performing sequence-level labeling decoding on the statement-level word representation and outputting an entity label sequence. The method can reduce redundant calculation and stabilize reasoning.

The invention discloses a Chinese named entity recognition method based on pinyin enhancement. The Chinese named entity recognition method based on pinyin enhancement comprises the steps of obtaining a two-dimensional pinyin grid embedding vector and a word representation vector of a to-be-recognized text; performing projection based on the word representation vector to obtain a two-dimensional grid feature vector; based on the pinyin grid embedding vector and the two-dimensional grid feature vector, calculating a fusion feature between every two arbitrary characters of the to-be-recognized text; the method comprises the following steps: by fusing a pinyin grid embedding vector and a two-dimensional grid feature vector, calculating a first corresponding prediction score vector based on a fusion feature between every two arbitrary characters; calculating a second corresponding prediction score vector based on the word representation vector; calculating a total prediction score vector based on the first corresponding prediction score vector and the second corresponding prediction score vector; and outputting the named entity of the to-be-recognized text based on the total prediction score vector. The Chinese named entity recognition efficiency based on pinyin enhancement is improved.

The invention discloses a word sense disambiguation method based on quasi-quantum non-homologous representation constraint. The method comprises the following steps: obtaining target word representation corresponding to a target word in a to-be-disambiguated text; obtaining word meaning definition representation and word meaning example representation in the dictionary; based on the target word representation and the word meaning definition representation, respectively calculating similarity scores of the target word representation and each word meaning representation, namely traditional word meaning recognition scores; calculating a similarity score of the target word representation and the word meaning representation obtained under each non-homologous representation constraint mechanism, namely a quantum word meaning recognition score; and adding the results of the traditional word meaning recognition score and the quantum word meaning recognition score to serve as a word meaning recognition result finally output by the word meaning disambiguation model.