7217results about "Text database querying" patented technology

A system and computer-implemented is provided for displaying a configurable metric relating to an environment in a graphical display along with a value of the metric calculated over a configurable time period. The metric is used to identify events of interest in the environment based on processing real time machine data from one or more sources. The configurable metric is selected and a corresponding value is calculated based on the events of interest over the configurable time period. The value of the metric may be continuously updated in real time based on receiving additional real-time machine data and displayed in a graphical interface as time progresses. Statistical trends in the value of the metric may also be determined over the configurable time period and displayed in the graphical interface as well as an indication if the value of the metric exceeds a configurable threshold value. Further, a selection of one or more thresholds for the value of the metric may be applied and an indication displayed indicating if the threshold(s) have been exceeded.

Systems and processes for operating a digital assistant are provided. In accordance with one or more examples, a method includes, at a user device with one or more processors and memory, receiving unstructured natural language information from at least one user. The method also includes, in response to receiving the unstructured natural language information, determining whether event information is present in the unstructured natural language information. The method further includes, in accordance with a determination that event information is present within the unstructured natural language information, determining whether an agreement on an event is present in the unstructured natural language information. The method further includes, in accordance with a determination that an agreement on an event is present, determining an event type of the event and providing an event description based on the event type.

An automated name searching system incorporates an automatic name classifier and a multi-path architecture in which different algorithms are applied based on cultural identity of the query name. The name classifier operates with a preemptive list, analysis of morphological elements, length, and linguistic rules. A name regularizer produces a character based computational representation of the name. A pronunciation equivalent representation such as an IPA language representation, and language specific rules to generate name searching keys, are used in a first pass to eliminate database entries which are obviously not matches for the query name. The methods can also be implemented as a callable set of library routines including an intelligent preprocessor and a name evaluator that produces a score comparing a query name and database name, based on a variety of user-adjustable parameters. The user-controlled parameters permit tuning of the search methodologies for specific custom applications.

Multi-level hierarchical routing matrices for pattern-recognition processors are provided. One such routing matrix may include one or more programmable and/or non-programmable connections in and between levels of the matrix. The connections may couple routing lines to feature cells, groups, rows, blocks, or any other arrangement of components of the pattern-recognition processor.

A method for implementing a question answering system based on a question-answer pair comprises the following steps: question analysis, question retrieval and answer selection. After a user submits aquestion expressed in natural language to the question answering system, the question answering system uses question vectorization, keyword extraction, keyword extension and other natural language processing techniques to understand the questioning intent of a user, and then uses the engine searching method in the question-answer pair database to obtain the question-related candidate question-answer pair set, and uses a matching algorithm and sorting algorithm to accurately select the best answer from the candidate sets. The invention obtains the function of the matching degree score between the question and the answer by learning by synthesizing different algorithms and models, the method of choosing the best answer from the candidate question-answer pairs is realized, and an answer selection method based on convolution neural network and Xgboost feature fusion is completed, which provides a better method for the answer selection of the question answering system.

The present disclosure is directed toward a message classification system that allows for improved customer service through intelligent classification of social media messages. For example, the message classification system may detect one or more messages that share a common context from within a group of messages, organize the detected messages into a messaging thread, and analyze messages within the messaging thread to identify a messaging thread classification. Further, the message classification system may analyze users participating in messaging threads to determine user classifications. Using the classified messaging thread and/or user classifications, the message classification system may assist an entity in improving social media customer service.

The invention may be embodied as a method of providing information. The information may be stored as objects in a database. Such a method may use identification codes to identify pointers, and the pointers may indicate the address in a database where desired objects are stored. The invention may also be embodied as a machine having an input device, a database, a processor and executable instructions. The executable instructions may cause the processor to carry out a method according to the invention.

In the present invention, information for content, software or both that a user set as a desired operation target of a content search rank changing process is stored in a operation target management table. Information for software active during a content search processing is stored in a currently active software management table. In case the content or software relates to the retrieved content as search results is present in the operation target management table or the currently active software management table, the relevancy rating of the retrieved content is calculated by adding a prescribed value to the relevancy rating of the retrieved content. Then, the retrieved content is sorted based on the relevancy rating and outputted in order sorted at a display device.

The invention relates to a construction method of a knowledge map question answering system in the field of electric power communication based on deep learning, which comprises the following steps: Step 1, semantic analysis, that is, preprocessing a question q put forward by a user in a natural language, extracting a keyword of a user inquiry, a focus of a query sentence and the like as an entityw of a question sentence from the question q; Step 2: semantic expression, namely, vectorization of the natural language question after preprocessing, and vectorization of the candidate set of answera, are used to calculate the matching degree of the question q and the answer a; and Step 3, the answer a most matched with the question q and most accurate is found through the method of semantic matching degree calculation, query and inference, so that the score S (q, a) of the question-answer pair (q, a) is the highest. The invention studies the feasibility of the question answering system constructed by the knowledge map in the field of communication of the State Grid.

The invention relates to a network security dynamic early-warning method based on a knowledge graph. After the knowledge graph is constructed according to network security data and domain knowledge of a complicated heterogeneous environment, a graph query method toward a network security domain is used for extracting target information, through the disposal and analysis for the security data, precise description is carried out, and finally, the target information is obtained. According to the network security dynamic early-warning method based on the knowledge graph, the difficulty and complexity of network security data processing can be reduced.

The invention relates to an entity relationship joint extraction method and system based on an attention mechanism. The method comprises the following steps of: converting an entity marked in trainingdata and a triple of a relationship into a form that each word corresponds to a predefined type of tag; Mapping each word in the sentences of the training data into a corresponding word vector, inputting the word vectors into a neural network model based on an attention mechanism, and performing training through a back propagation algorithm to obtain a label prediction model; And inputting the sentences needing to be subjected to entity relationship extraction into the trained label prediction model, predicting a label corresponding to each word, and obtaining entity relationship triples existing in the sentences according to the corresponding relationship between the labels and the words in the triples. The system comprises a preprocessing module, a model training module and a result processing module. According to the method, by more effectively utilizing the key information in the sentences, the joint extraction performance of the relational entities is improved, and the method hasgood practicability.

An enterprise content management system such as an electronic contract system manages a large number of secure documents for many organizations. The search of these private documents for different organizational users with role-based access control is a challenging task. A content-based extensible mark-up language (XML)-annotated secure-index search mechanism is provided that provides an effective search and retrieval of private documents with document-level security. The search mechanism includes a document analysis framework for text analysis and annotation, a search indexer to build and incorporate document access control information directly into a search index, an XML-based search engine, and a compound query generation technique to join user role and organization information into search query. By incorporating document access information directly into the search index and combining user information in the search query, search and retrieval of private contract documents can be achieved very effectively and securely with high performance.

A method for searching a document collection includes providing an index of terms indicating the documents in which the terms appear. A first statistical distribution of each of at least some of the terms in the index and a second statistical distribution of each of at least some of the categories are estimated a over the documents in the collection. A query including one or more of the terms and a category restriction referring to at least one of the categories is accepted. A modified term distribution is produced by operating on the first estimated statistical distribution of at least one of the terms in the query using the second estimated statistical distribution of the at least one of the categories, responsively to the category restriction. The query is applied to the index so as to return a response, in which occurrences of the at least one of the terms are scored responsively to the modified term distribution.

The invention provides a deep text matching method and device based on word migration learning, and the method comprises the steps: firstly, carrying out the fusion of a BERT model and carrying out the pre-training of the BERT model during the training of a deep matching model; secondly, utilizing a pre-trained BERT model to respectively represent sentences in the input sentence pairs by using initial word vectors, and then performing similarity weighting on the sentences in the sentence pairs represented by the initial word vectors to obtain weighted sentence vectors; and finally, according to the loss value corresponding to the similarity value of the statement vector, adjusting model parameters, and carrying out text matching on the input statement by utilizing a depth matching model obtained through parameter adjustment. The parameters of the pre-trained BERT model are no longer randomly initialized parameters, and part-of-speech prediction is added into the pre-trained BERT model,so that the word vector semantic information is enriched. Therefore, semantics, represented by word vectors, of sentences in the sentence pairs are more accurate through the trained BERT model, and the matching accuracy of the trained model is promoted to be improved.

Embodiments of the invention relate to a computer-implemented method for generating explanatory data from a personalized recommendations process for a primary user based at least on stored data about the primary user. The method comprises a server computer obtaining data related to one or more users who are relevant to the primary user, then determining at least one group of users relevant to the primary user. The server computer also obtains data related to one or more entities, determines one or more entities relevant to the primary user, and associates the at least one relevant group of users with the one or more relevant entities. One or more potential candidate factors are generated. A set of factors are selected from the one or more potential candidate factors, wherein the potential candidate factors are used as explanatory data to determine recommendations to the primary user.

The invention discloses a cross-modal hash retrieval method and system for fusing supervision information. The method comprises the following steps: constructing an image network, a text network and afusion network; The training sample pairs of image and text features are obtained and input into image network and text network respectively. Taking the output characteristics of the image network and the text network as the inputs of the fusion network, and defining the output of the fusion network; Constructing an objective function for learning a unified hash code according to the output of the converged network and the similarity between pairs; Solving the objective function to obtain a unified hash code; The unified hash code is used as the supervisory information and the semantic information is combined to train the hash network of a specific mode. The invention simultaneously learns the feature representation and the hash coding based on the end-to-end depth learning framework, canmore effectively capture the correlation between different modal data, and is conducive to the improvement of the cross-modal retrieval accuracy.

The invention discloses an intelligent customer service response method and system, relates to the technical field of intelligent customer service, and can solve the problems of low response efficiency and poor user experience caused by relying on manual customer service in the prior art. The method comprises the steps of preprocessing the customer service historical chat statements to export customer service corpora, and conducting the word segmentation training on the customer service corpora to obtain a language recognition model; carrying out intention identification on corpora asked by auser to match a corresponding service module, carrying out retrieval analysis in an elasticsearch database corresponding to the service module by utilizing an intention identification result, and summarizing output associated keyword answers to form a pre-selected data set; taking a text formed after word segmentation of the question corpus of the user as an input, and carrying out Elasticsearch retrieval in a pre-selected data set to output candidate keyword answers; converting the segmented keywords and the candidate keyword answers into word vectors respectively, calculating the similaritybetween the segmented keywords and the candidate keyword answers in pairs by using a WMD algorithm, and selecting the keyword answers based on the similarity values to respond to the user.

The invention discloses an information retrieval-based question and answer system and method for knowledge graph energization, which integrally improve the question and answer effect of the system, expand the user consultation range and improve the question feedback accuracy. According to the technical scheme, the system comprises a knowledge map database for storing domain knowledge map information; a word segmentation and part-of-speech tagging module which segments the user questions and tags the part-of-speech of the user questions; an entity identification and link module which identifiesentities in the user questions and links the entities to nodes in the knowledge graph database; an intention understanding module which obtains an intention understanding result of the user problem based on the entity link result and the distributed representation vector; a retrieval module which retrieves a plurality of corresponding question and answer pairs as roughing results according to theinformation in the user questions based on the retrieval data source; a sorting module which is used for resorting the roughing results by utilizing the distributed representation vectors of the entities; and a semantic matching module which scores the reordering result by using the distributed representation vector of the entity and finally outputs an answer.

The invention provides a language model training method and a prediction method. The training method comprises the following steps of: obtaining training text sequences, randomly generating a target position of a character or a word which needs to be modeled and analyzed through a language model in the training text sequence; carrying out mask replacement on characters or words at a target position; generating a text sequence subjected to mask replacement, generating a limited word list of replaced characters or words, generating probability distribution on a limited word list space accordingto the text sequence subjected to mask replacement and the limited word list, calculating a cross entropy function according to the replaced characters or words and the probability distribution on thelimited word list space, and carrying out iterative optimization. According to the method, the limited word list is introduced to the decoding end of the model, and the original word information is fully utilized during model training, so that confusable words are easier to distinguish by the language model, and the effect of the language model on tasks such as error detection or error correctionis improved.

A computerized neural-network based mechanism for providing an intermediary configured for intervening in searches is described. Corresponding methods, computer-readable media, systems, devices, and apparatuses are also contemplated. The neural network can include a multi-headed attention layer. The intermediary may be, in some embodiments, a human “man in the middle” mechanism invoked where there is low confidence that pre-existing categories map to a user's search string. The mechanism provides a specially configured interface adapted to enable a search specialist to quickly select one or more categories that match or are otherwise associated with the search query from a set of acceptable categories. Received outputs and detected user behaviors are utilized to update a neural network model.

The invention relates to a convolutional neural network matching text recognition method based on an attention enhancement mechanism, and the method comprises the steps: 1, carrying out the preprocessing of an input text, and carrying out the pre-training of a text corpus, and obtaining an initial word vector; 2, converting sentences in the input text into a matrix composed of initial word vectorsby utilizing the initial word vectors; 3, encoding the matrix through a convolutional neural network with an attention enhancement mechanism and generating a low-dimensional sentence vector; and 4, obtaining the correlation of the low-dimensional sentence vectors corresponding to every two sentences, and identifying the overall text according to the correlation result. Compared with the prior art, the defect that two sentences are completely independent in the sentence modeling process is avoided, the relevant attention information in the other sentence is added on the basis that the convolutional neural network acquires the local context information, so that the two sentences interact as soon as possible, and multi-granularity information obtained by combining convolution kernels of different sizes is obtained.

The invention provides an electronic medical record processing method and device and equipment, and the method comprises the steps: obtaining a to-be-processed medical record text; identifying a medical entity and attribute information in the medical record text; determining a corresponding relationship between the medical entity and the attribute information; and generating a structured medical record according to the corresponding relationship. Therefore, by identifying the medical entities in electronic medical records, describing the attribute information of the medical entities and generating structured medical records, the structured requirements for the medical records are met, the efficiency is improved, and the cost is reduced.

The invention discloses a text classification method based on a local and global mutual attention mechanism, and the method comprises the following steps: obtaining text data, carrying out the preprocessing of the text data, and expressing text words through a pre-trained word vector; Capturing global long-term dependence of the text sequence by using a long-short-term memory network, and acquiring local semantic features of the text sequence by using a multi-scale convolutional neural network; Taking the global long-term dependency and the local semantic features as input of a local and global mutual attention mechanism to obtain weighted global long-term dependency and weighted local semantic features; Carrying out weighted pooling to obtain a final global representation vector and a final local representation vector; And inputting the vectors to a full connection layer to fuse the global representation vector and the local representation vector, and then inputting the vectors to a classification layer to classify. According to the method, global long-term dependency and local semantic features are captured in parallel, interaction between the two features is learned in an explicit mode, better text global and local feature representation is obtained, and the text classification precision is further improved.

Described is a system and method to create an index for a plurality of documents, the index including hash codes corresponding to each word in the plurality of documents, wherein each hash code corresponds to one or more of the plurality of documents, receive a query including a search word, create a search hash code from the search word, compare the search hash code to the hash codes in the index and return the one or more of the plurality of documents corresponding to one of the hash codes matching the search hash code.

Interactive system for building and sharing one's own databank of wisdom bytes, such as words of wisdom, basic truths and/or facts and feats, in one or more languages, it being accepted that one may want to build such data based on one's personal interest, by well-defined classifications, that uses a computer system comprising of; a One or more database to store data user wise; b. A well classified (i) User Database; (ii) At least one data input, organizing & management module(s) allowing a user to input, append and/or Modify data, with or without Voice; (iii) Module allowing a user to invoke a Wisdom Bytes Session; (iv) Module allowing a user to Schedule such Wisdom Bytes on the user's computer, including hand held devices, at predefined and/or periodic intervals, with or without Voice; (v) Module allowing the User to Export data from the database; (vi) Module allowing the user to Import data built by another user using the same System; (vii) Module allowing the user to Translate data into one or more languages; (viii) Reports Module.

A method and apparatus for providing accurate detection of confidential information is described. In one embodiment, the method includes searching a text document for multiple classified data patterns associated with confidential information that is represented as personal identifiers. The method further includes finding, in the text document, one or more personal identifier candidates matching any of the classified data patterns, and validating each of the personal identifier candidates using one or more personal identifier validators to provide accurate detection of the confidential information in the text document.

The invention discloses a cross-model Hash retrieval method on the basis of cooperative training and matrix decomposition. By the aid of the cross-model Hash retrieval method, the similarity between models and the internal similarity of the models can be effectively constrained for unlabeled cross-model data. The cross-model Hash retrieval method includes implementation steps of acquiring original data and carrying out normalization processing on the original data; carrying out cooperative training to obtain constraints between the models; acquiring internal constraints of the models by the aid of neighbor relations; decomposing training data matrixes and adding the constraints between the models and the internal constraints of the models into the training data matrixes to obtain objective functions; carrying out alternate iteration to obtain expressions of basis matrixes, coefficient matrixes and projection matrixes; carrying out quantization to obtain Hash codes of training data sets and test data sets; computing the Hamming distances between every two Hash codes of the data sets; sorting the Hamming distances to obtain retrieval results. The cross-model Hash retrieval method has the advantages that constraints on the similarity between the models of the cross-model data can be obtained by the aid of cooperative training processes, accordingly, the image and text mutual retrieval performance can be improved, and the cross-model Hash retrieval method can be used for picture and text mutual search service of mobile equipment, internets of things and electronic commerce.

A method for training a system is provided. The method may include storing one or more backend communication logs, each of the one or more backend communication logs including a user query and a corresponding backend query. The method may further include parsing the one or more backend communication logs to extract statistical information and generating a mapping between each user query and a corresponding set of language tags. The method may also include sorting the one or more backend communication logs based upon, at least in part, the extracted statistical information.

The invention belongs to the technical field of cross-modal retrieval, and particularly relates to an image-text retrieval system and method based on a multi-angle self-attention mechanism. The systemcomprises a deep convolutional network, a bidirectional recurrent neural network, an image, a text self-attention network, a multi-modal space mapping network and a multi-stage training module. The deep convolutional network is used for acquiring an embedding vector of an image region feature in an image embedding space. The bidirectional recurrent neural network is used for acquiring an embedding vector of a word feature in a text space, and the two vectors are respectively input to the image and the text self-attention network. The image and text self-attention network is used for acquiringan embedded representation of an image key area and an embedded representation of key words in sentences. The multi-modal space mapping network is used for acquiring the embedded representation of the image text in the multi-modal space. The multi-stage training module is used for learning parameters in the network. A good result is obtained on a common data set Flickr30k and an MSCOCO, and the performance is greatly improved.

The invention provides a knowledge graph driving type legal intelligent consultation system. The knowledge graph driving type legal intelligent consultation system comprises a knowledge construction module used for constructing a question and answer corpus and a legal knowledge base; a legal language understanding module used for training to obtain a corresponding entity recognition model, an intention attribute recognition model and a question answer pair matching recognition model; a feature recognition module used for recognizing legal features; a knowledge association module used for searching attributes associated with the questions; a query matching module used for querying and matching answers in a knowledge base and forming a system question and answer log; and a knowledge operation module used for screening out effective questions in the system question and answer logs and updating answers matched with the effective questions into a knowledge base. According to the system andthe method, the user can be intelligently answered and guided to solve legal knowledge problems, the cost of legal consultation of common people is saved, manpower and material resources are saved, and the working efficiency of the user and legal professionals is improved.