2337results about How to "Improve recall" patented technology

A search system for searching for electronic documents, and providing a search result in response to a search query is provided. The search system includes a processor, a user interface module adapted to receive a search query from a user, the search query having at least one search query term, and a query processing module that analyzes the search query term to identify candidate synonym words. The query processing module also determines which of the candidate synonym words are equivalent terms to the search query term, and in a same sense as the search query term. In addition, the search system includes a search engine that executes a search based on the search query term and the equivalent terms.

The performance of traditional speech recognition systems (as applied to information extraction or translation) decreases significantly with, larger domain size, scarce training data as well as under noisy environmental conditions. This invention mitigates these problems through the introduction of a novel predictive feature extraction method which combines linguistic and statistical information for representation of information embedded in a noisy source language. The predictive features are combined with text classifiers to map the noisy text to one of the semantically or functionally similar groups. The features used by the classifier can be syntactic, semantic, and statistical.

The present system relates to systems and methods for providing delivery of goods purchased through electronic commerce. An embodiment of the present invention allows a user to purchase an item from a vendor or merchant in an e-commerce environment and have the item shipped to a selected Will-Call Center for pick up by a recipient. The recipient can be the user or some other designated party. The Will-Call Center further automatically notifies the recipient of the availability of the item to be picked up.

Disclosed is a mammographic imaging system and tools for processing mammographic images to enhance image acquisition and review workflow. The systems and tools enable rapid access to digital image information providing for improved workflow management and identification of images, upon initial review. The system and tools also allow for background processing of image information to reduce workflow delay. Specifically, digital images are processed in the background, i.e., they are automatically processed, free from specific task-orientated direction by a user, using resources that are not otherwise occupied addressing user-directed tasks. Background processing that may be supported includes preprocessing and interim processing. Preprocessing refers to processing of an image that occurs prior to initial review of that image by a physician. Interim processing refers to background processing that occurs during a review session, e.g., in a time period between initial review and a subsequent review of an image.

The invention discloses an initiative study-based questioning and answering method and a questioning and answering system adopting the initiative study-based questioning and answering method, wherein the Initiative study-based questioning and answering method comprises the following steps of (1) performing question inputting; (2) performing pretreatment; (3) performing feature extraction; (4) performing question understanding; (5) performing judgment of confidence, a threshold value and credibility; (6) performing information retrieval and information processing; (7) performing answer extraction; (8) performing initiative study; (9) performing guide questioning according to the specific type of the question when the confidence is lower than the credibility, initiatively guiding a user to question without ambiguity and performing a new round of more effective questioning and answering. The questioning and answering system comprises five modules including a question inputting module, a pretreatment module, a semantics understanding module, an initiative study module and an answer outputting module.

Aspects discussed herein present a solution for utilizing large-scale knowledge graphs for inference at scale and generating explanations for the conclusions. In some embodiments, aspects discussed herein learn inference paths from a knowledge graph and determine a confidence score for each inference path. Aspects discussed herein may apply the inference paths to the knowledge graph to improve database lookup, keyword searches, inferences, etc. Aspects discussed herein may generate a natural language explanation for each conclusion or result from one or more inference paths that led to that conclusion or result. Aspects discussed herein may present the best conclusions or results to the user based on selection strategies. The presented results or conclusions may include generated natural language explanations rather than links to documents with word occurrences highlighted.

he invention discloses a medical information extraction system and method based on depth learning and distributed semantic features. The system is composed of a pretreatment module, a linguistic-model-based word vector training module, a massive medical knowledge base reinforced learning module, and a depth-artificial-neural-network-based medical term entity identification module. With a depth learning method, generation of the probability of a linguistic model is used as an optimization objective; and a primary word vector is trained by using medical text big data; on the basis of the massive medical knowledge base, a second depth artificial neural network is trained, and the massive knowledge base is combined to the feature leaning process of depth learning based on depth reinforced learning, so that distributed semantic features for the medical field are obtained; and then Chinese medical term entity identification is carried out by using the depth learning method based on the optimized statement-level maximum likelihood probability. Therefore, the word vector is generated by using lots of unmarked linguistic data, so that the tedious feature selection and optimization adjustment process during medical natural language process can be avoided.

The invention relates to an alarm clock system. The system according to the invention comprises sensor means for measuring ambient parameters. In particular, a user's body parameters are monitored so as to determine in which stage of sleep he is. Properties of the wake-up stimulus, such as sound volume of the stimulus or moment of generation of the stimulus, are adjusted in dependence on the inferred stage of sleep.

This invention relates to an interactive medication cassette with a machine readable and writable information strip that contains information corresponding to the medication in the cassette. The interactive medication cassette holds the medication and couples the corresponding information to the medication. The cassette is designed for use in a medication distribution and inventory system that includes at least one medication dispensing machine having a sensor for reading the information in the strip and updating or altering this information when medication is added to or removed from the cassette. The cassette travels with the medication during the distribution of the medication to a patient, and its information is reported to one or more memory devices or hospital or pharmacy data base during this process. The cassette is filled by a pharmacy dispensing machine holding a bulk container filled with a particular type of medication and a singulator for counting the quantity of medication added to the cassette. The pharmacy dispensing machine alters the information strip to include medication and quantity information corresponding to the dispensed medication. The cassette is closed and locked to prevent unauthorized access during transport to a hospital floor workstation. A hospital floor dispensing machine incrementally dispense the medication from the cassette, and updates the information strip with additional information including the quantity of medication dispensed from the cassette. When the cassette is returned to the pharmacy and its unused contents is emptied into the bulk container, the information strip on the cassette automatically updates an information strip on the bulk container to indicate the number of doses of medication added to the bulk container. In this manner, a reliable medication distribution and inventory system is achieved while maintaining improved control over the access to the medication on the hospital floor.

A plurality of cameras are controlled to follow a common moving target in a three dimensional environment such that each camera generates a video feed comprising a plurality of video segments captured sequentially. Each video segment comprises a static image of the target at a respective point in time. A resulting video is generated by selecting a sequence of video segments which may include video segments from different cameras and at the same or different points in time to create various video effects. The recorded video segments are categorized for later recall according to camera identification and point in time to allow for instantaneous recall for producing video replays from a variety of camera angles during a live event. Auxiliary video segments can be computer generated for insertion between video segments captured by the cameras for smoothing the appearance of the resulting video.

The present invention discloses a visual target detection and labeling method. The method includes: an image inputting step, to input an image to be detected; a candidate region extracting step, to extract a candidate window as the candidate region from the image to be detected using selectively search algorithm; a feature description extracting step, to perform feature description on the candidate region using a pre-trained large-scale convolutional neural network and output the feature description of the candidate region; a visual target predicting step, to predict the candidate region based on the feature description of the candidate region using a pre-trained object detection module, to estimate regions having the visual target; and a position labeling step, to labeling the position of the visual target according to the estimated result. Experiments show that, compared with the mainstream week supervision visual target detection and labeling method, the present invention has a stronger ability to excavate positive samples and a more general application prospect, and is suitable for visual target detection and automatic labeling tasks on the large-scale data set.

The invention discloses a semantic query expansion method based on domain knowledge, which comprises the following steps: taking concept expression and a knowledge tree system as the basis to construct the domain knowledge; performing primary semantic analysis on query phases input by users to form a semantic item list; utilizing results of the primary semantic analysis and taking the domain knowledge as the basis to construct a semantic map with expansion types and expansion weights; respectively computing semantic distances between each vertex and an initial vertex in the semantic map; determining an expandable item of each item in the semantic item list according to the semantic distances; and finally, combining all expandable items according to AND / OR logic relations to obtain a semantic item set representing the query intension of the users, and submitting the semantic item set to a searching system for searching. In the semantic query expansion method based on the domain knowledge, the computing time is short, the domain knowledge is fully utilized, and newly-added expanded semantic items and the original query phases have definite semantic relations, and the recall ratio and the precision ratio of the searching system can be improved effectively.

Coreference resolution is the process of identifying when two noun phrases (NP) refer to the same entity. Two main contributions to computational coreference resolution are made. First, this work contributes a new method for recognizing when an NP is anaphoric. Second, traditional approaches to coreference resolution typically select the most appropriate antecedent by recognizing word similarity, proximity, and agreement in number, gender, and semantic class. This work contributes a new source of evidence that focuses on the roles that an anaphor and antecedent play in particular events or relationships. I show that using contextual role knowledge as part of the coreference resolution process increases the number of anaphors that can be resolved, and I demonstrate an unsupervised method for acquiring contextual role knowledge that does not require an annotated training corpus. A probabilistic model based on the Dempster-Shafer model of evidence is used to incorporate contextual role knowledge with traditional evidence sources.

The present invention includes a system and methods for image searching. Embodiments of the system integrate textual features and visual features for improved search performance. The system represents text terms in the visual feature space and develops a text-guided weighting scheme for visual features. The weighting scheme infers intention from query terms and enhances the visual features that are significant in light of such intention.

In an environment where it is desire to perform information extraction over a large quantity of textual data, methods, tools and structures are provided for building a relational text index from the textual data and performing searches using the relational text index.

In an exemplary embodiment of the present technique, a particular POI (66) may be assigned a code (68) representative thereof. Advantageously, by entering the code (68) into a telematics system (16), information about the POI (66) may be obtained. Moreover, in accordance with an exemplary aspect of the present technique, by entering the code (68) a route to the POI may be developed.

The invention discloses a Chinese question answering system based on concept, which mainly comprises a data server, a question pre-treatment module, a candidate question set extracting module and a question sentence similarity calculation module. The invention aims at providing a question answering system which is based on concept, can carry out synonym expansion of keywords which are processed by question sentences which are input by the user, understand question sentences better, carry out searching and improve the recall ratio of the question answering system. Furthermore, the system has a Chinese sentence similarity calculation method based on concept from three aspects: word form, word order and word length, and improves searching precision ratio. Meanwhile, the system adopts a high-efficiency retrieval technology to realize rapid extraction of candidate question set, calculates question sentence similarity, sorts question set quickly and returns the sorted questions and answers to the user. The question answering system of the invention gives more precise understanding in concept to the question sentences input by the user and searches the accurate answers. Experiments show that the question answering system of the invention achieves high recall ratio and precision ratio.

The invention discloses a pedestrian detection method based on an end-to-end convolutional neural network in order to solve the problem that the existing pedestrian detection algorithm has the disadvantages of low detection precision, complex algorithm and difficult multi-module fusion. A novel end-to-end convolutional neural network is adopted, a training sample set with marks is constructed, and end-to-end training is performed to get a convolutional neural network model capable of predicting a pedestrian candidate box and the confidence of the corresponding box. During test, a test picture is input into a trained model, and a corresponding pedestrian detection box and the confidence thereof can be obtained. Finally, non-maximum suppression and threshold screening are performed to get an optimal pedestrian area. The invention has two advantages compared with previous inventions. First, through end-to-end training and testing, the whole model is very easy to train and test. Second, pedestrian scale and proportion problems are solved by constructing a candidate box regression network, the pyramid technology adopted in previous inventions is not needed, and a lot of computing resources are saved.

The invention relates to an establishing and retrieval method for a characteristic matrix of a semantically based Web document, belonging to the information retrieve technical field. During the process of establishing the characteristic matrix for the Web document, position information and particular expression form information are added into an index process of a prior LSA model by utilization of the particular position information and the particular expression form information in the Web document, thereby the prior LSA method is effectively improved. The retrieval process is as follows: firstly, semantic expansion of a concept in a query sentence is performed according to a body; secondly, a query vector is generated according to the query concept and an enlarged concept of the query concept, and the similarity of the query concept and the enlarged concept can be taken into consideration by a vector value, thereby semantic deletion of the prior LSA model is made up in a certain extent. The establishing and retrieval method for the characteristic matrix of tbe semantically based Web document has the advantages of scientific index and effective retrieve of unstructured document information, realization of retrieve of unstructured information in all locations at any moment, and assistance of convenient and in-time acquisition of required information of a user.

The invention discloses a user-oriented information search engine system and a method. The system comprises eight modules of a search term pushing module, a user initiating search module, a user concern updating module, a primary search module, a user interest deducing module, a user concern result word segmentation module, a search word refactoring module and a secondary search module. The method includes analyzing and pushing user selectable search words, performing user initiating search, updating user concerns, executing the primary search, deducing user interests, performing word segmentation for user concern results, refactoring the search words and executing the secondary search. Accordingly, the system has the advantages of being complete in inquiring range and high in inquiring accuracy. Besides, by means of the system, the select input and automatic sequencing of the search words can be achieved, the accuracy of following inquiring results can be improved through the interactive operation, and a flexible, convenient and intelligent interactive interface is provided for the user to execute information search.

Systems and methods for representing, editing, and operating on multi-dimensional data efficiently, compactly, and in real-time with an intuitive graphical user interface without requiring extensive user training are provided. The multi-dimensional data consist of data pertaining to the allocation of labor, equipment, and material to project cost centers in business, educational, non-profit, and governmental organizations. The multi-dimensional data are stored in a multi-dimensional database that is accessed by the graphical user interface. The graphical user interface enables users to manipulate a large amount of data in a limited display area.

The invention relates to a special audio event layered and generalized identification method based on a combination of an SVM (Support Vector Machine) and a GMM (Gaussian Mixture Model), and belongs to the technical field of a computer and audio event identification. The special audio event layered and generalized identification method comprises the following steps of: firstly, obtaining an audio characteristic vector file of a training sample; secondly, respectively carrying out model training on a great quantity of audio characteristic vector files (of the training samples) with various types by using a GMM method and an SVM method, so as to obtain the GMM model with generalization capability and an SVM classifier, and complete offline training; and finally, carrying out layered identification on the audio characteristic vector files to be identified by using the GMM model and the SVM classifier. With the adoption of the method provided by the invention, the problems that the conventional special audio event identification is low in identification efficiency on a continuous audio stream, very short in continuing time, high in audio event false dismissal probability can be solved. The method can be applied to searching a special audio and monitoring a network audio based on contents.

A system and method for graphically displaying global resources and their associated parameter values and apply the global resources across multiple design projects. The system and method also provide a graphical interface which displays the possible parameter values of an associated global resource. This graphical interface utilizes pop up menu to for viewing the possible parameter values and the selection of the current parameter value. The system and method also provide tracking and updating of the hardware resources which utilize the parameter values of the global resources. Further, the system also allows the storage of these parameters values of the global resources. By storing these parameter values of the global resources, these parameter values can be set as default global settings. These default global settings can be recalled and associated with different projects without manual entry of the parameter values.

The invention discloses a voice interaction method and a voice interaction device. The method comprises steps: after a voice recognition text is received, the voice recognition text is distributed to each service respectively, and semantic understanding is carried out respectively; and based on the obtained semantic understanding result and the application state of a client, confidence ranking is carried out, a semantic understanding result with the highest confidence is acquired, and a response is given to the semantic understanding result with the highest confidence. As confidence ranking of semantic understanding results on multidimensional-based information not only considers the matching degree between a semantic understanding result and each service but also considers the application state of the client, for example, whether the client is in a navigation state or a music listening state, the application of the client and the application state are possibly objects to be processed by voice interaction, semantic understanding on the multidimensional-based information can effectively enhance the accuracy of judging the service belonging, the accuracy of man-machine interaction semantic understanding is improved, and the user experience is enhanced.

The invention discloses a web-based text classification mining system and a web-based text classification mining method. The system mainly comprises a text pre-processing module, a word segmentation processing module and a classification algorithm module, wherein the text pre-processing module is used for automatically screening specific information from texts to be tested, pre-processing the specific information, and filtering out irrelevant information to effectively represent the texts; the word segmentation processing module is used for carrying out word segmentation on the texts, finding attributes / attributive words of each text, and making preparation for selection of characteristic words; and the classification algorithm module is used for carrying out characteristic selection to obtain an optimum characteristic sub-set, or finding corresponding probabilities according to data which is provided by a file of a training result, comparing the corresponding probabilities to obtain the type of the maximum probability, drawing a conclusion and storing the conclusion in the file finally. The system overcomes the shortcoming of conditional independence assumption of a naive Bayes algorithm by using a hypertext markup language (HTML) tag weight, improves a classifier and can improve the recall ratio and precision ratio of data mining.

The invention provides a natural scene text detection method and system. The system comprises two neural network models: a text detection network based on multi-level semantic feature fusion and a detection screening network based on an attention mechanism, wherein the text detection network is an FCN-based image feature extraction fusion network, and is used for extracting multi-semantic level information of input data, carrying out full fusion of multi-scale features, and finally predicting the position and confidence degree of text information in a natural scene by carrying out convolutionoperation on the fused multi-scale information. According to the detection screening network, the trained convolutional recurrent neural network is used for discriminating and scoring an initial detection result output by the convolutional neural network of the first part, so that a background which is easy to confuse with foreground characters is filtered out, and the accuracy of natural scene text recognition is further improved.

The invention relates to a system for extracting web page information and a method thereof. The system comprises a template generation module, a web page homogenization module, an automatic tagging module, a wrapper file generation module and an on-line extraction module, wherein, the template generation module is used for selecting web pages to be automatically tagged from a web page collection, and the web pages to be automatically tagged is classified according to training web pages tagged by a user, so as to generate a classified category web page template; the web page homogenization module is used for screening out the difference between the automatic tagging web pages and the web page template belonging to the same category with automatic tagging web; the automatic tagging module is used for analyzing training web pages corresponding to the category, so as to generate a first wrapper file; automatic tagging can be performed on the automatic tagging web pages according to the fisrt wrapper file, so as to generate new training web pages; the wrapper file generation module is used for analyzing all the training web pages and generating a second wrapper file; and the on-line extraction module is applied to the second wrapper document, and is used for extracting unselected web page information in the web page collection. The invention ensures that a plurality of templates corresponding to inhomogeneous web pages can be generated, and extracting can be performed on a plurality of records in a web page and a plurality of attributes of each record.

The invention discloses improved random forest algorithm based system and method for software fault prediction. The system comprises a data processing layer, a prediction model building layer and a fault predication layer. The method includes calculating a software project attribute set used for acquiring a training model to acquire a training data set of a software prediction model, and performing equalization to the training data set; building a prediction model according to an improved random forest algorithm; screening the model according to performance limiting of accuracy rate and recall ratio; and predicting a software project according to attribute set information of the to-be-predicted software project and a trained prediction model and displaying prediction results and the prediction model. The improved random forest algorithm based system and method for software fault prediction have the advantages of high prediction accuracy rate, performance stability and high execution efficiency, can evaluate whether a final software product reaches specified quality or meets expectation of a user or not, and can guide developers to formulate distribution strategies of software testing and formal verification resources.

A system and method for composing application services includes an indexing module configured to index words in a request and available application descriptions to create a semantic similarity map. A semantic matcher is configured to determine semantic similarity between concepts / terms in both domain-independent and domain-specific ontologies for the semantic similarity map. A prefiltering module is configured to determine candidate compositions for the request based on the semantic similarity map and the available descriptions. A metric guided composition method is configured to run algorithms to generate a set of alternative compositions by determining which applications can be composed with which others using the semantic similarity map.

The invention discloses a kind of auto question-answering system, which includes interface unit, illation unit, language knowledge base, illation knowledge base, normalization table of keyword, and normalization unit, the illation unit inquires said illation knowledge base according to sequence of normalization to find the answer corresponding with the question with same sequence of keyword, and the answer is as the system response to be output by said interface unit. The invention also discloses a kind of auto question-answering method, which can be used in the system with language knowledge base, illation knowledge base, normalization table of keyword, and it can divide the input question; and the normalization is done for the sequence of keyword; and the normalized keyword can find the setting question with same keyword; and it can search the answer according to the question; and said answer is output as system response. Thee invention can reduce the working capacity for building illation knowledge base by the normalization of synonymous keywords.