1511 results about "Learning data" patented technology

A system and method is provided for learning data values over time as they are entered by a user on a form such as a web page form. An Internet web browser can be modified to suggest previously used data values for any form field that is the same as or similar to a previously used form field. Application programs that use the web browser can gain access to previously used form field values even if they have no knowledge of the field names. Software in a web browser associates field names across different Universal Resource Locators (URLs), so that when a user enters a value into a field (e.g., username) at a first web site, that same value can be automatically suggested when the user displays a different form on a different web site that uses the same field name.

A speech processing apparatus according to an embodiment of the invention includes a conversion-source-speaker speech-unit database; a voice-conversion-rule-learning-data generating means; and a voice-conversion-rule learning means, with which it makes voice conversion rules. The voice-conversion-rule-learning-data generating means includes a conversion-target-speaker speech-unit extracting means; an attribute-information generating means; a conversion-source-speaker speech-unit database; and a conversion-source-speaker speech-unit selection means. The conversion-source-speaker speech-unit selection means selects conversion-source-speaker speech units corresponding to conversion-target-speaker speech units based on the mismatch between the attribute information of the conversion-target-speaker speech units and that of the conversion-source-speaker speech units, whereby the voice conversion rules are made from the selected pair of the conversion-target-speaker speech units and the conversion-source-speaker speech units.

A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired. In detection, using an abort threshold value that has been learned in advance, whether provided data can be obviously judged as a non-face is determined every time one weak hypothesis outputs the result of discrimination. If it can be judged so, processing is aborted. A predetermined Gabor filter is selected from the detected face image by an Adaboost technique, and a support vector for only a feature quantity extracted by the selected filter is learned, thus performing expression recognition.

Disclosed is a speech search device including a recognizer 2 that refers to an acoustic model and language models having different learning data and performs voice recognition on an input speech, to acquire a recognized character string for each language model, a character string comparator 6 that compares the recognized character string for each language models with the character strings of search target words stored in a character string dictionary, and calculates a character string matching score showing the degree of matching of the recognized character string with respect to each of the character strings of the search target words, to acquire both a character string having the highest character string matching score and this character string matching score for each recognized character strings, and a search result determinator 8 that refers to the acquired score and outputs one or more search target words in descending order of the scores.

A tool for learning to relate annotations and transcript of a multimedia sequence to nodes in a formally or semi-formally represented ontology covering a broad range of possible multimedia documents. The device includes learning data preparation that involves certain special techniques for deriving data from the past mappings of annotations to nodes in an ontology, building inverted indices maintaining certain special statistics and a retriever that exploits these special statistics to rank the relevance of the nodes in an ontology for a given a set of new annotations.

The subject invention relates to systems and methods that automatically learn data relevance from past search activities and apply such learning to facilitate future search activities. In one aspect, an automated information retrieval system is provided. The system includes a learning component that analyzes stored information retrieval data to determine relevance patterns from past user information search activities. A search component employs the learning component to determine a subset of current search results based at least in part on the relevance patterns, wherein numerous variables can be processed in accordance with the learning component to efficiently generate focused, prioritized, and relevant search results.

A system for learning driving information in a vehicle, includes a first camera mounted on an inner ceiling of the vehicle and configured to detect a projected position of a nose of a driver; and a second camera mounted on an inner front of the vehicle and configured to detect a front position of the nose of the driver. Further, the system includes a driver's status information processing unit configured to detect the line of sight of the driver by calibrating an image corresponding to the projected position and an image corresponding to the front position in real time, to analyze information about the line of sight that is detected, and to store the analyzed information in a learning data database.

An objective is to identify the health state of mechanical equipment and provide information usable for determining maintenance work timing or the like. A health management system includes a time-series data acquisition unit configured to acquire multi-dimensional sensor data and environmental data from mechanical equipment; a first discrimination unit configured to quantify the equipment state of the mechanical equipment by a statistical method using normal data as learning data; a second discrimination unit configured to quantify the health state indicating the performance or quality of the mechanical equipment by a statistical method using normal data; and an output unit configured to display and / or output to the outside the quantified equipment state and health state.

Systems, methods and apparatus for automatic signal detection with temporal feature extraction in an RF environment are disclosed. An apparatus learns the RF environment in a predetermined period based on statistical learning techniques, thereby creating learning data. A knowledge map is formed based on the learning data. The apparatus automatically extracts temporal features of the RF environment from the knowledge map. A real-time spectral sweep is scrubbed against the knowledge map. The apparatus is operable to detect a signal in the RF environment, which has a low power level or is a narrowband signal buried in a wideband signal, and which cannot be identified otherwise.

A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired. In detection, using an abort threshold value that has been learned in advance, whether provided data can be obviously judged as a non-face is determined every time one weak hypothesis outputs the result of discrimination. If it can be judged so, processing is aborted. A predetermined Gabor filter is selected from the detected face image by an Adaboost technique, and a support vector for only a feature quantity extracted by the selected filter is learned, thus performing expression recognition.

The invention provides a universal machine learning data analysis platform. The universal machine learning data analysis platform comprises an interface module, a data storage module, a preprocessing module, a feature extraction module, a feature conversion module, an algorithm module and a selection optimization module, wherein the feature extraction module extracts feature parameters from to-be-analyzed data according to the feature parameters set by a user; the feature conversion module is used for converting features set by the user to be in a representation form required by the user; the algorithm module comprises a plurality of algorithm models for the user to select and build, and the user builds at least one group of models; the selection optimization module selects out an optimal model and an optimal parameter from the built models and then stores the optimal model; and data generated by the modules is stored in the data storage module. According to the platform, the user can freely combine and use the modules and the algorithm models, and also can build a complex model and quickly and iteratively develop a novel analytic model, so that the working efficiency is greatly improved.

A course guiding system based on non-zero start point and knowledge point in network education belongs to the field of computer technologies. The invention includes an initial knowledge domain construction module, an individualized knowledge domain generation module, an individualized learning route generation module, a history learning record module, a knowledge structure level evaluation module, and an individualized learning resource recommendation module. With knowledge point as the core, the invention constructs courses into the corresponding knowledge point tree and graph among knowledge points; learners are examined on knowledge points at each stage; by the analysis of learners' learning data and test of learning effect, the system obtains the learning status of learners at each knowledge point, their learning prediction result and knowledge point structure, recommends the corresponding learning resources and students to learners, and helps learners form the self-organized learning community to enhance the learning quality.

Systems, methods and apparatus are disclosed for automatic signal detection in an RF environment. An apparatus comprises at least one receiver and at least one processor coupled with at least one memory. The apparatus is at the edge of a communication network. The apparatus sweeps and learns the RF environment in a predetermined period based on statistical learning techniques, thereby creating learning data. The apparatus forms a knowledge map based on the learning data, scrubs a real-time spectral sweep against the knowledge map, and creates impressions on the RF environment based on a machine learning algorithm. The apparatus is operable to detect at least one signal in the RF environment.

The invention discloses a machine learning model generation method and a machine learning model generation device. According to a specific embodiment, the method comprises the following steps: generating model parameter combinations, and generating machine learning models respectively corresponding to the model parameter combinations; dividing preset machine learning data into training data and verification data; training the machine learning models in parallel based on the training data; verifying the learning accuracy of the trained machine learning models based on the verification data to get verification scores, and determining an optimal model parameter combination corresponding to a machine learning model to be generated based on the verification scores, and generating a machine learning model corresponding to the optimal model parameter combination. Through the method and the device, machine learning models corresponding to all model parameter combinations can be trained and verified in parallel, the whole process of parameter optimization is improved, and an ideal machine learning model can be generated quickly.

The present invention relates to a method of implementing, using and also testing a machine learning system. Preferably the system employs the Naïve Bayesian prediction algorithm in conjunction with a feature data structure to provide probability distributions for an input record belonging to one or more categories. Elements of the feature data structure may be prioritised and sorted with a view to selecting relevant elements only for use in the calculation of a probability indication or distribution. A method of testing is also described which allows the influence of one input learning data record to be removed from the system with the same record being used to subsequently test the accuracy of the system.

Methods and apparatus for analyzing financial data generally includes a predictive modeling system. The predictive modeling system may include an artificial agent responsive to an input data set. The artificial agent may produce an estimated data set including a market conditions data set. The market conditions data may include an estimate of at least one of liquidity of a market, strategy of a counterparty, and an effect of information leakage. The artificial agent may determine a predictability value for the estimated data set. The predictive modeling system may also include an agent factory responsive to the input data set. The agent factory may generate an artificial agent in response to the input data set.

The invention discloses a mobile terminal comprehensive learning system based on massive learning resources. The learning system comprises a resource library system, an intelligent knowledge diagnosis system, an online tutoring system, a student management system, a teacher management system, a parent management system, a learning PK system and an infinite extension system. According to the learning system, a learning resource library and a teacher team platform need to be built first, and after logging into the learning system, students acquire various learning resources such as synchronous videos, synchronous teaching materials, synchronous auxiliary teaching materials, synchronous question banks, knowledge points and micro videos. Questions which the students encounter in the learning process can be solved in two ways; in one way, the students communicate with teachers in a one-to-one mode through online tutoring, and in the other way, the students submit the questions to the question banks of the system and wait for other students or teachers to answer the questions. The students can carry out intelligent knowledge diagnosis on knowledge they have learnt to examine the knowledge mastering condition of themselves and can also interact with other students in communities.

The invention discloses a mobile terminal learning method and a learning system thereof. The mobile terminal learning method comprises the following steps of step 1: capturing a text image through a camera of a mobile terminal, identifying the type of information on the image, and transmitting the image to a server through the mobile terminal, wherein the type of information comprises character information type and picture information type; step 2: identifying the information of the image and extracting character or / and picture information on the image through the server; step 3: invoking relative learning material information in a server database according to the identified character or / and picture information; and step 4: transmitting the learning material information to the mobile terminal, overlaying the learning material information and an original text image captured by the camera and displaying on a display interface of the mobile terminal. According to the mobile terminal learning method and the learning system thereof, disclosed by the invention, internet information is obtained and is provided for a user by constructing connection between the server and the mobile terminal, so that a simple, practical, abundant-content and visual learning manner is provided for the user, and the internet information can be updated in real time.

The present tool and method relate to device fault detection, diagnosis and prognosis. More particularly, the present tool and method store in a database a plurality of measured indicators representative of at least one dynamic condition of the device. The present tool and method further binarize by a processor the plurality of measured indicators, and analyze the plurality of binarized measured indicators using a machine learning data tool for extracting at least one pattern from the binarized measured indicators by adding at least one different constraint to each iteration. The at least one extracted pattern is indicative of whether the device has a fault or not.

Disclosed herein are a language learning system and a language learning method. A language learning system includes a user terminal configured to receive utterance information of a user as a speech or text type and to output learning data transferred through a network to the user as the speech or text type, and a main server which includes a learning processing unit configured to analyze a meaning of the utterance information of the user, to generate at least one response utterance candidate corresponding to dialogue learning in a predetermined domain to induce a correct answer of the user, and to connect a dialogue depending on the domain and a storage unit linked with the learning processing unit and configured to store material data or a dialogue model depending on the dialogue learning.

In learning for pattern recognition, an aggregation of different types of object image data is inputted, and local features having given geometric structures are detected from each object image data inputted. The detected local features are put through clustering, plural representative local features are selected based on results of the clustering, and a learning data set containing the selected representative local features as supervisor data is used to recognize or detect an object that corresponds to the object image data. The learning thus makes it possible to appropriately extract, from an aggregation of images, local features useful for detection and recognition of subjects of different categories.

A battery pack includes a battery module that charges and discharges electricity to be used to drive a vehicle, and a monitoring controller for monitoring charge of the battery module. The monitoring controller stores past charge records and past discharge records in a charge-discharge history. Based on an analysis of learning data of a charge-discharge cycle in the charge-discharge history, the monitoring controller determines a charge operation, which may either be a normal charge or a quick charge, for charging the battery. The normal charge provides a charging electric current per unit time that is less than the charging current per unit time of the quick charge.

A method is provided for training a statistical pattern recognition decoder on new data while preserving its accuracy of old, previously learned data. Previously learned data are represented as constrained equations that define a constrained domain (T) in a space of statistical parameters (K) of the decoder. Some part of a previously learned data is represented as a feasible point on the constrained domain. A training procedure is reformulated as optimization of objective functions over the constrained domain. Finally, the constrained optimization functions are solved. This training method ensures that previously learned data is preserved during iterative training steps. While an exemplary speech recognition decoder is discussed, the inventive method is also suited to other pattern recognition problems such as, for example, handwriting recognition, image recognition, machine translation, or natural language processing.

A concierge robot system, a concierge service method, and a concierge robot are provided. The system provides an antificial intelligence type of concierge service, and includes: a user interface device that receives an external image and an external voice, and outputs the received image or voice on a screen or by voice; a storage device where a program that provides data through the user interface device based on learning data generated by using a neural network model is stored; and a processor that executes the program, wherein the program includes instructions for recognizing an emotion of a user, identified from the external image based on the learning data, outputting data that represents an emotion according to the emotion recognition to the screen, generating a conversation sentence that corresponds to natural language of web data externally collected through web scraping based on the learning data and outputting it by voice, generating user recommendation data for the identified user based on the learning data, and outputting the user recommendation data on the screen or processing it into natural language and outputting a corresponding conversation sentence by voice.

An apparatus and a system to teach a user a subject based on his questions. The system allows the user to control his learning process, and helps to fill in gaps of misunderstanding in the subject. In one embodiment, the system, including a database, presents study materials on the subject to the user. After working on the presented materials, the user enters his question into the system, which generates an answer to the question, and presents it to him. Then the system compares the question with one or more questions previously entered by the user to determine his understanding level in the subject. Based on the determination, the system may present to the user appropriate study materials. The user typically asks more than one question, and the process of answering his question by the system repeats.

The present invention relates to a method of implementing, using and also testing a machine learning system. Preferably the system employs the Naïve Bayesian prediction algorithm in conjunction with a feature data structure to provide probability distributions for an input record belonging to one or more categories. Elements of the feature data structure may be prioritized and sorted with a view to selecting relevant elements only for use in the calculation of a probability indication or distribution. A method of testing is also described which allows the influence of one input learning data record to be removed from the system with the same record being used to subsequently test the accuracy of the system.

The invention relates to a spare part assembling demand forecasting information processing method applied to inventory management, comprising the following steps:1) take one part of historical sales data as method learning data and take the other part of the historical sales data as weight building data; 2) use the method learning data to practice an ARMA (Autoregression and Moving Average) method, a multiple linear regression method and a BP (Back Propagation) neural network approach respectively for each spare part; 3) apply the above three methods respectively by using the weight building data, so as to obtain forecasting relative error values for different methods; 4) calculate the weights of the above methods; 5)construct an assembling demand forecasting model; 6) forecast the future sales demands of all spare parts. Compared with the prior art, the method is suitable for the spare parts with different demand features, and has the advantages of strong objectivity, high forecasting precision, and can greatly reduce the inventory cost on the premise of having a certain service level and improves the supply chain management efficiency and customer satisfaction.

A computer-implemented method, computer program product and computing system for receiving user content for analysis. Key content included within the user content is identified. Surplus content included within the user content is identified.

The present disclosure relates to a self-learning system for water sport users which comprises a wearable camera device, a computer and a learning data base. The carrying camera comprises a fixing element, a bearing element and a waterproof camera. The fixing element is disposed on a human body. The bearing element is disposed on the fixing element. The bearing element is bendable and has adjustable length. The waterproof camera is disposed on the bearing element. The waterproof camera shoots human postures of water sport. The waterproof camera transforms image signal to digital signal. The computer receives and processes the digital signal, and then through a water-sport learning module assesses human posture as well as provides swimming information. The present disclosure also relates to a self-learning system for water sport users which comprises a carrying camera, a computer and a learning network platform.