279 results about "Structured text" patented technology

The present invention relates to the use of unstructured and untagged text message protocols to form a text message body that can be used to transmit and receive semi-structured, or structured text message bodies, which optionally may also use various, widely used Markup Languages. The semi-structure, or structure used within the text message body can be a format, such as, but not limited to, partitioning and / or comma delimited values, etc. The tagging for use with the text message body can be a protocol, such as, but not limited to, Extensible Markup Language (XML).

A computer system for generating a cause effect matrix as a user interface to develop a control program based on the cause effect matrix and to compile and download the resulting program into a programmable controller. A cause effect matrix diagram is used to develop a function block diagram program which is a standard IEC 1131-3 language. The function block diagram is translated into structured text which is compiled into intermediate code. The intermediate code is translated into the native code for the micro-processor of the target control system, including but not necessarily limited to the Motorola processor MPC-860. The automation of a cause effect matrix diagram to generate a function block diagram permits additional capability by allowing functions for causes, intersections, and effects. Because special functions may be included, the results of a cause generate timing functions or other computations before initiating the effect.

A system and method for classifying text includes a pre-processor, a knowledge base, and a statistical engine. The pre-processor identifies concepts in the text and creates a structured text object that contains the concepts. The structured text object is then passed to a statistical engine, which applies statistical information provided in nodes of a knowledge base to the structured text object in order to calculate a set of match scores, each match score representing the relevance of the text to an associated one of a plurality of predefined categories. The pre-processor may be implemented in the form of an interpreter which selects and executes a script that includes language- and scenario-specific instructions for performing linguistic and semantic analysis of the text.

A system, method and computer program product for conducting questions and answers with deferred type evaluation based on any corpus of data. The method includes processing a query including waiting until a “Type” (i.e. a descriptor) is determined AND a candidate answer is provided. Then, a search is conducted to look (search) for evidence that the candidate answer has the required Lexical Answer Type (e.g., as determined by a matching function that can leverage a parser, a semantic interpreter and / or a simple pattern matcher). Prior to or during candidate answer evaluation, a process is provided for extracting and storing collections of entity-type pairs from semi-structured text documents. During QA processing and candidate answer scoring, a process is implemented to match the query LAT against the lexical type of each provided candidate answer and generate a score judging a degree of match.

In accordance with one aspect of the present invention, disclosed is an image analysis and conversion method and system, where digital ink images are converted to structured object representations of the digital ink images, capable of being edited by a structured text / graphics editor.

The invention provides an event graph construction method based on social media. The method comprises the steps of firstly, performing multi-source data preprocessing; secondly performing multi-sourceevent information extraction on preprocessed data; thirdly, judging a relation between events through event relation evaluation; and finally, performing entity information fusion, and performing attribute complementation on entities in a heterogeneous graph. According to the method, the events are regarded as the abstract entities; basic elements of the events are extracted based on text data pairs of the social media; the events are associated; an existing structured knowledge base is fused to construct an event graph, so that more comprehensive and more direct event-oriented information retrieval services can be provided, and by converting the research of traditional non-structured text contents into the graph-based research, the exploration of deeper information is facilitated.

The invention discloses a generation method of an image description from a structured text. The generation method comprises the steps of downloading pictures from the internet to form a picture training set; conducting morphological analysis on descriptions which correspond to the pictures in the picture training set to form the structured text; using an existing neural network model to extract convolution neural network characteristics of the pictures in the training set, and using <, picture characteristics and structured text < as inputs to form a multitasking recognition model; using the structured text extracted from the training set and a description which corresponds to the structured text as inputs of a recurrent neural network, and conducting training to obtain a parameter of a recurrent neural network model; inputting the convolution neural network characteristics of an image ready to be described, and obtaining a predicted structured text through the multitasking recognition model; inputting the predicted structured text, and obtaining the image description through the recurrent neural network model. Compared with the prior art, a better image description effect, accuracy and sentence variety can be generated through the method, and the generation method of the image description from the structured text can be effectively popularized in an application of image retrieval.

The structure attributes and unstructured attributes of a ticket are used to generate a problem signature. For structured attributes, correlation between field values is determined and fields with the highest weight are identified. For unstructured attributes, data mining techniques are applied to generate a plurality of keywords with a ranking for each ticket by identifying keywords, and commonly used acronyms and corpus variances. The set of structured attributes and the plurality of keywords from unstructured attributes form the signature of a given problem ticket.

The invention discloses a convolutional neutral network-based attribute extraction method. The method comprises the following steps of (1) constructing an external knowledge library; (2) obtaining text data; (3) obtaining attribute-containing sentences by using a remote supervision method; (4) obtaining the sentences by utilizing a word vector method and performing vectorization; and (5) inputting the sentences to a convolutional neutral network, and performing training and classification. According to the method, the attribute-containing candidate sentences are extracted from a non-structured text data set based on artificially defined mapping by utilizing the external knowledge library in combination with remote supervision and convolutional neutral network models, and sentence classifications are classified in combination with the convolutional neutral network model, so that an attribute extraction task is finished.

The invention discloses a broadcast television voice recognition method and system. The method comprises the following steps: extracting audio data according to broadcast television data; pre-processing the audio data to obtain feature text data; transmitting the feature text data to a cloud server for recognition to achieve male and female voice recognition, speaker recognition and voice recognition results; fusing the male and female voice recognition, speaker recognition and voice recognition results and marking a structured text to generate a structured voice recognition result. According to the method, the conventional voice recognition method is improved; various broadcast television data pre-processing technologies and broadcast television voice recognition methods are integrated; voice data is identified to meet data processing requirements in broadcast television industry; various recognition results are integrated to generate the structured voice recognition result; basic data can be provided for intelligent processing of other service of subsequent broadcast television programs; processing speed is increased; the accuracy is improved.

The present invention relates to the use of free delivery to create a new system, method, and apparatus for delivering hard copy advertising and marketing materials to a consumer, and / or configured as a system, method, and apparatus for uploading, listening, and downloading of music. The data in the present invention may be exchanged using unique data encoding unstructured and untagged text message protocols to form a text message body that can be used to transmit and receive semi-structured, or structured text message bodies, which optionally may also use various, widely used Markup Languages. In addition, the present invention may include a coupon exchange system, method, and apparatus.

The invention discloses an automatic voice quality inspection method, a system thereof, a device and a storage medium. The method includes the following steps: obtaining a voice file to be inspected;processing the voice file to be inspected, and converting the voice file to be inspected into a structured text file; scoring the voice file to be inspected and the structured text file according to apreset quality inspection scoring dimension and a preset score rule, and obtaining the score corresponding to each quality inspection scoring dimension; wherein, the quality inspection scoring dimension includes speech rate and silent analysis scoring, emotional analysis scoring, keyword and sensitive word detection scoring, and quality inspection rule matching scoring; and obtaining the final score of the voice file to be inspected according to the score corresponding to each quality inspection scoring dimension. The method can realize automatic voice quality inspection, and improves qualityinspection efficiency and accuracy.

A method and system for developing fault models from structured text documents, such as service procedures. A service procedure or other structured text document is parsed using diagnostic rules to extract symptoms, failure modes, and correlations. Testing procedures and repair instructions are also parsed to create a fault tree and identify additional symptoms and failure modes. Reachability analysis is then used to find hidden dependencies in the fault tree, thus yielding additional correlations. The resultant symptoms, failure modes, and correlations are then assembled into a fault model, which can be used for real-time fault diagnosis onboard a vehicle, or for off-board diagnosis at service shops.

The disclosure describes one or more embodiments of a structured text summary system that generates structured text summaries of digital documents based on an interactive graphical user interface. For example, the structured text summary system can collaborate with users to create structured text summaries of a digital document based on automatically generating document tags corresponding to the digital document, determining segments of the digital document that correspond to a selected document tag, and generating structured text summaries for those document segments.

The invention provides a method for realizing electronic medical history and a device thereof; the method comprises the following steps of: element construction, chapter construction, element embedding and medical history construction; a format of the element construction is a standard format for inputting diagnosis and treatment data which can be standardized; a format of the chapter construction is a free format for inputting diagnosis and treatment information in a natural language form; a format of the medical history construction consists of chapters for inputting diagnosis and treatment records. The invention realizes the fusion of natural texts and structured texts of the electronic medical history and can meets the requirements of stationarytype and flexibility simultaneously.

Disclosed herein is a method and system for providing a response to a user's request for information. The user calls into an intelligent information delivery system requests for the information. The information request is recorded as an audio file at the intelligent information delivery system. A structured text form of the audio file is refined into an optimized search query. The optimized search query is input to retrieve search results comprising information of interest from a data server. The search results are processed into an agent readability enhanced and context specific output and displayed to the agent. The agent selects context specific results from the displayed output. The selected context specific results are formatted to an optimized speech deliverable text form. Content of the optimized speech deliverable text form is converted into a voice stream. The voice stream is then communicated to the user.

A text cataloging method includes a step of cataloging already-analyzed-text data obtained from an analysis of a logical structure of a text to be cataloged in a text database, a step of creating a structure index by sequentially superposing logical structures of texts to be cataloged, wherein a single metaelement is used for representing a group of elements in the texts having the same position of appearance in one of the texts and the same element type, a single piece of meta-character-string data is used for representing a group of pieces of character-string data in the texts having the same position of appearance in one of the texts, and a context identifier is assigned to each metanode composing a tree-like structure of the structure index for uniquely identifying the metanode; a step of generating structured-full-text data composed of definitions of associative relations between all pieces of character-string data included in already-analyzed-text data of each text to be cataloged, and context identifiers of pieces of meta-character-string data in the structure index used for representing the pieces of character-string data; and a character-string-index updating step, including the sub-steps of extracting partial character strings, generating structured-character-position information, and updating a character-string index.

The invention discloses a structured text detection method and a structured text detection system. The method comprises the following steps: inputting a structured text picture to be detected and a group of text area templates into a trained convolutional neural network; obtaining actual positions of a group of areas to be detected of the structured text picture to be detected by processing of the convolutional neural network, wherein the position of each template in the group of text area templates is a mean value of the positions of corresponding text areas in multiple structured text pictures of the same type of the structured text picture to be detected; the positions of the group of text area templates are determined as the group of areas to be detected of the structured text picture to be detected by the convolutional neural network. According to the method and the system, the detection accuracy is ensured, meanwhile, the calculated amount is reduced as much as possible, and the structured text detection efficiency is greatly improved.

The invention discloses a soft PLC configuration development method based on XML technology, including the steps: abstracting and packaging basic components of a PLC graphic program in an object-oriented manner to obtain primitive components; according to the type of the primitive components, creating a corresponding project; constructing a PLC configuration development environment, and loading acorresponding primitive component library; maintaining the primitive components, and arranging and combining the primitive components by dragging in the way of graph visualization; configuring the attributes and parameters of the primitive components, and establishing the connection relationship between the primitive components; storing the attributes and logic relationships of the primitive components, and according to TC6_XML_V201. Xsd file, describing a configuration PLC graphic program to obtain an XML file according with the IEC61131 standard; converting the XML file into an instruction table or structured text; generating a source file and further generating a target file; and deploying the target file to the running system of soft PLC to complete the development of the whole soft PLC system. The invention can effectively improve the efficiency and flexibility of soft PLC development.

The invention provides a sequence text information-combined knowledge graph expression learning method and a knowledge graph expression learning device. According to the method, not only the ternary relation group information between entities is utilized, but also the sequence text information containing the entities in a designated corpus is fully utilized. An energy equation is constructed, so that the entities have different expression vectors in the structured ternary relation group information and the non-structured text information. Meanwhile, a marginal-based evaluation function is minimized, and the expression of structure-based entity vectors, text-based entity vectors and relation vectors is learned. Therefore, the expression learning effect of a knowledge graph is remarkably improved. According to the method and the device, the learned knowledge graph expression fully utilizes the sequence text information of entities contained in the corpus. Therefore, the higher accuracy can be obtained in the tasks such as ternary group relation classification, ternary group head and tail entity prediction and the like. The good practicability is achieved, and the expression performance of the knowledge graph is improved.

The invention discloses a word2vec-based remotely supervised non-taxonomic relation extraction method and system, which can extract non-taxonomic relations in the field of vegetables. The method comprises the steps of crawling network vegetable field non-structured text data of a network encyclopedia and a large vegetable website to serve as corpora, and preprocessing the corpora in sequence to obtain primary training corpora; and training a word2vec model by utilizing the primary training corpora, and obtaining a spatial vector of each sentence by utilizing the word2vec model; aggregating the primary training corpora according to the types of the non-taxonomic relations, and for aggregated data of each relation, extracting a common sentence mode and an uncommon sentence mode; selecting two sentence spatial vectors accordant with two different modes as initial centers of a k-means clustering method, clustering all sentence spatial vectors, selecting a category accordant with the common sentence mode, and obtaining the training corpora with relatively high quality; and training a convolutional neural network model by the training corpora with relatively high quality, and through a fully connected softmax layer, extracting the non-taxonomic relations.

The invention relates to a system for implementing standardized semantic description of facial features. The system comprises a face detection and normalization module, an automatic facial feature point positioning module and a head and face feature parametric description module. The invention further relates to a method for realizing the standardized semantic description of the facial features. By the application of the system and the method, facial information extraction on a video and the structured text description under a semantic network architecture are realized, facial features and facial organ features in a monitoring scenario are concentrated into multiple types convenient for understanding, valuable information and auxiliary functions are collected and provided for video monitoring public security information, and basic information classified and distinguished is provided based on face identification. The system is simple in structure, convenient to operate, rapid in operation, visual and practical in result, stable and reliable in operation performance, applicable to various occasions and worthy of wider application range.

The invention provides a graph convolutional network relationship extraction method based on dependency analysis and keywords, which comprises the following steps of: firstly, performing sentence dependency analysis on a structured text to generate a dependency analysis graph, and trimming sentences through keywords; obtaining a word embedding vector and a position embedding vector of the sentenceby utilizing word2vec, and performing splicing to obtain a word vector sequence; performing a bidirectional GRU neural network on the word vector sequence to obtain an output vector matrix; processing the output vector matrix by adopting a graph convolution network to obtain dependency representation of sentences; combining the output vector matrix and the dependency representation of the sentence through a multi-head attention mechanism to obtain a representation vector of the sentence; and establishing a relationship and entity type prediction model by adopting a softmax function, and taking the representation vector of the sentence as the input of the prediction model, thereby performing training to obtain a relationship with the maximum prediction probability as an extraction result.

The invention discloses an intelligent contract security vulnerability detection method based on machine learning, and the method comprises the steps: firstly collecting intelligent contract source code data, carrying out the data preprocessing, and constructing a sample set of machine learning; determining a vulnerability label for the sample set data through a public intelligent contract vulnerability detector; translating the smart contract source code into an XML structured text; on this basis, carrying out feature extraction on intelligent contract source codes in a data set, and for different vulnerability types of intelligent contracts, considering the limited current Solidy intelligent contract sample data, so that two different machine learning algorithms are adopted to carry outanalysis according to the number of label samples, a random forest algorithm is adopted to construct a model for multiple data samples, transfer learning is adopted to construct a detection model forfew data samples, and the Solidy smart contract vulnerability can be detected more efficiently and automatically.

The invention discloses a commodity recommending method and system. The commodity recommending method comprises the following steps that voice information input by a target user is received; the voice information is recognized and converted into text information; the text information is processed to generate structured text; inquiring is conducted to obtain a voice inquiring result; the structured text is recorded into a log of the target user; clustering analysis is conducted, and a user cluster which the target user belongs to is obtained; the user closest to the target user is searched for; potential grades, given by the target user, of commodities are calculated according to the average grades, given by the user closet to the target user, of the commodities and the average grades of the target user, and the commodities are screened according to the potential grades to generate a commodity set; a plurality of commodities are selected from the commodity set and recommended to the target user according to the structured text. The commodity recommending method and system avoid a large amount of irrelevant information generated when the user searches for needed commodities in the browsing process in e-commerce, greatly improve the efficiency of the e-commerce and meanwhile greatly improve the use experience of the user.

The invention discloses a text information extraction method for a structured text, which is used for solving the problem of relatively low efficiency of performing text information extraction on thestructured text in the prior art. The method provided by the invention comprises the steps of splitting the current structured text into text paragraphs according to preset paragraph topics; for eachtext paragraph, selecting an analytic character string matched with the paragraph topic corresponding to the text paragraph from preset analytic character strings; for each text paragraph, analyzing the text paragraph by adopting the selected analytic character string, and extracting text information corresponding to the text paragraph; and after the text information corresponding to each text paragraph is extracted, summarizing the text information according to a preset template to obtain the text information of the structured text. The invention furthermore provides a storage medium and a server.

The invention relates to a text structuring method, device and system and a nonvolatile storage medium. The method comprises the steps that an unstructured text is obtained and preprocessed, and the preprocessed unstructured text is disaggregated into multiple sub-clauses; structured items in the structured text and question and answer databases corresponding to the structured items are acquired;questions are put according to questions in the question and answer databases, the content of the sub-clauses is matched to the corresponding structured items respectively, and a sub-clause structuring result can be obtained; according to the sub-clause structuring result, a structured text is obtained. According to the text structuring method, device and system and the nonvolatile storage medium,the question and answer databases are combined, unstructured text information can be completely converted into structured information, the conversion effect is good, the accuracy is high, sub-clausesstructuring processing is carried out through two LSTM networks, diversified expression manners in a free text can be processed, and good robustness is achieved.