264 results about "Text segmentation" patented technology

The invention discloses a text structuring method aiming at power grid fault cases. The method includes: subjecting unstructured texts to named entity recognition, and constructing an entity dictionary aiming at the field of power grid to assist in entity recognition and text segmentation; extracting attribute values and attribute description state quantities, wherein the state quantities includedigital state quantities and non-digital state quantities according to types; extracting and matching digital state quantity modification attributes according to a rule-based method; detailing the non-digital state quantities to divide into phrase form based state quantities and sentence form based state quantities, and extracting respective modification attributes; according to recognized attributes and corresponding state quantities, finally generating a plurality of binary groups formed by the attributes and the corresponding state quantities to complete text structuring.

Text segmentation based on topic boundary detection has been an industry problem in automating information dissemination to targeted users. A system for automatic segmentation of ASR output text involves boundary identification based on “topic” changes. The proposed approach is based on building a weighted graph to determine dependency in input sentences based on bi-directional analysis of the input sentences. Furthermore, the input sentences are segmented based on the notion of segment cohesiveness and the segmented sentences are merged based on preamble and postamble analyses.

The invention relates to a classification system of video and audio content the examination in the terminals. The system, the program source management module preservation program and the source address information; Speech Recognition module on the input audio streams speech recognition; Content analysis module extracts the relevant information and video subtitles information; Subtitles identification module subtitles information will be entered into the text segmentation, recognition; Die Face Recognition block on the importation of video information, facial feature extraction information, face recognition; fusion scoring modules under voice recognition, face recognition subtitles identification and the results of programs points, scoring results from the judgment whether legitimate programs, the decision on the program is immediately blocked or as suspicious file upload Jin to further examinations; strategy server cache module from the audited download updated strategy; decoder module for real-time video and audio decoder paper.

The embodiment of the invention discloses an information processing method and device. The method comprises the steps that an HTML document set which is obtained in advance is analyzed, and text data sets contained in the HTML document set are extracted; word segmentation is conducted on the text data sets, and a text segmentation table is obtained; word frequency analysis is conducted on all words in the text segmentation table, and a text vector space matrix is constructed; discrete point text vectors in the text vector space matrix are eliminated, and a text similarity matrix of all text vectors in the text vector space matrix without the discrete point text vectors is obtained; according to the text similarity matrix, topic cluster is conducted on the text data set. By means of the method, a word list can be accurately constructed, topic cluster is conducted after the discrete point text vectors are eliminated, the topic cluster speed is increased, and the topic cluster accuracy is improved.

The present invention discloses a speech recognition text segmentation method and device. The method comprises: performing endpoint detection on speech data, to obtain speech segments and a starting frame serial number and an ending frame serial number of each speech segment; performing speech recognition on each speech segment, to obtain a recognition text corresponding to each speech segment; extracting a segmentation feature of the recognition text corresponding to each speech segment; by using the extracted segmentation feature and a pre-established segmentation model, performing segmented detection on the recognition text corresponding to the voice data, to determine a position where segmentation is needed; and segmenting the recognition text corresponding to the speech data according to a segmented detection result. According to the method and apparatus disclosed by the present invention, the recognition text can be segmented automatically, so that the structure of the recognition text can be clearer.

A text semantic analysis method and system can realize semantic analysis of text data base on lexical level and sentence level. Aiming at the semantic analysis at the lexical level, the invention firstly adopts an improved word segmentation algorithm to solve the problem that English words are segmented only by spaces. Secondly, based on word segmentation, TF-IDF modeling is performed to obtain weight value; Then the text is vectorized by weighting and summing the weight value and the word vector trained by Word2Vec, and finally the document similarity is solved. At the same time, the invention considers the contribution degree of the vocabulary to the document content and the semantic status to calculate the similarity degree of the document, the result has higher accuracy, and provide agood foundation for subsequent text clustering. The present invention extracts subject-predicate object structure based on text segmentation, part-of-speech tagging, syntactic analysis and dependencyrelation for sentence level semantic analysis. The invention realizes the extraction of subject-predicate-object structures of various sentence types in all aspects, and realizes the noun expansion function, which is more consistent with the manual extraction result.

The invention belongs to the technical field of multi-document summarization and provides a multi-document summarization method based on text segmentation, which comprises the following steps of: using HowNet to obtain a concept, building a concept vector space model, conducting text segmentation by adopting an improved DotPlotting model and a sentence concept vector space, calculating sentence weight by using the built concept vector space model, generating a summary according to the sentence weight, the text segmentation and the similarity situation, and evaluating the generated summary by using the ROUGE-N evaluation method and using F_Score as an evaluation index. According to the result, the multi-document summarization by using a text segmentation technique is effective, relevant documents provided by users can be gathered to form a summary by adopting the multi-document summarization method, the summary is displayed to the users in a proper way, the information acquisition efficiency is greatly improved, the practicability is high and the popularization and application values are greater.

The invention discloses a method for generating a recommended delivery place name. The method mainly comprises the steps of performing text segmentation for a known address, matching segmented words, checking in a database, calculating the matching frequency, and resetting frequency threshold. The invention also discloses a device for generating the recommended delivery place name. With the adoption of the method and device, the recommended delivery place name can be automatically, timely, quickly and accurately generated.

A system to automatically enhance, tag, classify, categorize, cluster and index products described in unstructured text-based electronic documents. The system and method incorporate the use of text normalization, regular expressions, product number matching rules, text segmentation, entity detection, language models, predictive modeling, hierarchal subspace clustering, formal concept analysis, and a weighted combination of all techniques to detect and infer knowledge extracted from a digital version of raw, unstructured product text. Knowledge extracted and inferred comprises knowledge units including: main conceptual entity, entity text patterns, product language models, and conceptual hierarchies. The extracted knowledge units are utilized to store and index products in a product knowledge database and the products and knowledge units are made available to users via a user interface.

The invention discloses a method and a device for classification of mails. The method for the classification of the mails includes the steps: enabling the mails to be classified to be through text segmentation to get an entry set; matching entries in the entry set with feature words which represents categories of the mails in a feature word bank, and calculating conditional probability of the categories which the mails belong to according to a matching result; and confirming the categories of the mails according to the conditional probability. The method for the classification of the mails resolves the problems that in the prior art, the method for classification of the mails is less in quantity and low in accuracy, accordingly the effects of high-efficiency accurate classification of the mails and filtering of junk mails are achieved, and performance of a system is improved and user experience is also improved.

The invention relates to a text big data based digitized emergency management case library establishment method and device. The method comprises the steps that data is acquired at regular intervals, and the acquired data is preprocessed to obtain Chinese text segmentation results; based on the Chinese text segmentation results, identification of emergency related data is achieved through data cleaning according to a set emergency field keyword vocabulary to obtain emergency classification results; based on the emergency classification results, identification and tracking of special emergencies are performed; structuralized information description is conducted on special data about emergency identification and tracking by utilizing an information extraction method to obtain various emergency case libraries. The emergency related data can be automatically acquired, and secondary emergency classification can be automatically achieved. The special emergency identification and tracking can be automatically performed, and analysis and information extraction conducted on designated emergency related data are represented through cases to form emergency case representation.

The invention relates to an evaluative text-oriented kernel entity identification method and apparatus. The method comprises the following steps of 1) inputting an evaluative text, and identifying a kernel entity in the evaluative text according to expert rules and an industry specialized dictionary, 2) identifying a kernel entity via a well-trained bidirectional LSTM model for evaluation texts yet to be identified, 3) generating a candidate entity for a kernel entity according to existing entity set statistics and a combination of text segmentation and part-of-speed tagging for evaluative texts yet to be identified. The apparatus comprises a rule matching module, a model identifying module and a candidate generation module. For various types mixed evaluative texts, the kernel entity in the text can be accurately and effectively extracted; and powerful foundation can be laid for user decision judgment.

The invention provides a scene text segmentation method based on weak supervision deep learning, and the method comprises the following steps: enabling a scene picture to be superposed with any text to generate a scene text picture, generating a training sample, and labeling the training sample as the scene picture; performing feature extraction by using a convolutional neural network to obtain high-level semantics step by step; performing up-sampling through deconvolution to gradually recover the high-level semantic feature map to the size of the input image; carrying out multi-scale fusion on the feature maps output by the convolution layer and the deconvolution layer; activating the fused feature map to obtain a dichotomy black-and-white image of the scene and the text; setting a loss function for training; and corroding and expanding the scene text segmentation map obtained after training to generate a text region bounding box. The method does not need any strongly supervised pixel-level annotation sample, simply and efficiently solves the text segmentation problem in scene text detection, greatly reduces the algorithm cost, and improves the scene text segmentation efficiency.

The present invention is a text display system with speech output that uses a method of text segmentation in which segments of text are presented one after another for reading text sequentially. To indicate the location of text a user is currently reading, the current sentence is emphasized by presenting the surrounding text in faded colors. The current sentence is segmented into phrases where the points of segmentation are chosen by a series of grammatical rules and the desired number of words in each segment. When the text is presented sequentially, each segment is highlighted within the current sentence. With the use of a text-to-speech output system, each segment is spoken out with a pause before the next segment is presented. In a non-linear/selective reading scenario, a user can select a text segment, for which the span of the segment can be automatically generated or manually selected by the user.

The invention relates to a character recognition method and apparatus. The method comprises: obtaining an input text image; performing text line segmentation on the text image to obtain a text line region of the text image; performing character region segmentation on the text line region according to text character attributes to obtain character region information; and according to the character region information, performing single character segmentation in combination with the text image to obtain a character segmentation result. According to the character recognition method and apparatus, the text segmentation can be accurately performed, so that the recognition performance of OCR (Optical Character Recognition) is greatly improved; and the scheme has relatively high practical values in various text recognition applications.

The invention provides a semantic comprehension system and method oriented to a Chinese text. Based on deep learning, a deep learning text classification model is provided; the model is divided into an input layer, a convolutional layer, a pooling layer, a GRU (Gated Recurrent Unit) layer, a fully connected layer and an output layer; a pinyin characteristic sequence of text segmentation is used asinput; characteristics are obtained through multi-layer characteristic extraction; and an intention category is predicted to obtain a text classification result. According to the semantic comprehension system and method oriented to the Chinese text, the part of speech of a statement does not need to be judged, a complex preprocessing process such as a syntax analysis tree and the like does not need to be generated, the text only needs to be segmented and the segmented text is converted into pinyin, and the problems that the relation between words and words cannot be measured, a lot of external prior knowledge is needed and the curse of dimensionality is easily generated when large-scale corpuses are processed in a conventional characteristic extraction method are solved.

A method for segmentation of characters in text that segments text into lines, words and slices and determines at least one of fixed pitch and proportional pitch prior to segmentation. The method computes histograms of the lines and defines widths of lobes of the histograms of the lines as the character pitches. In addition, the method further analyzes the character pitches; segments lines into words; computes histograms of the words and aggregating the histograms of the words at predetermined points. Moreover, the method segments the words; slicing them words into an upper slice and lower slice and further segments the upper slice and the lower slice. The results are then combined to provide for both coarse and fine segmentation that enhance the performance of character OCR for documents scanned as at least one of gray-scale images and color images.

A hybrid n-gram/lexical analysis tokenization system including a lexicon and a hybrid tokenizer operative to perform both N-gram tokenization of a text and lexical analysis tokenization of a text using the lexican, and to construct either of an index and a classifier from the results of both of the N-gram tokenization and the lexical analysis tokenization, where the hybrid tokenizer is implemented in at least one of computer hardware and computer software and is embodied within a computer-readable medium.