901 results about "Automatic learning" patented technology

An adaptive interface for a programmable system, for predicting a desired user function, based on user history, as well as machine internal status and context. The apparatus receives an input from the user and other data. A predicted input is presented for confirmation by the user, and the predictive mechanism is updated based on this feedback. Also provided is a pattern recognition system for a multimedia device, wherein a user input is matched to a video stream on a conceptual basis, allowing inexact programming of a multimedia device. The system analyzes a data stream for correspondence with a data pattern for processing and storage. The data stream is subjected to adaptive pattern recognition to extract features of interest to provide a highly compressed representation which may be efficiently processed to determine correspondence. Applications of the interface and system include a VCR, medical device, vehicle control system, audio device, environmental control system, securities trading terminal, and smart house. The system optionally includes an actuator for effecting the environment of operation, allowing closed-loop feedback operation and automated learning.

Systems and methods are described that automatically adjust a value of a parameter relating to the delivery of media content, such as audio content or image content, based on both environmental conditions and on automatically-learned user preference data. For example, a first embodiment adjusts a volume setting used to control the delivery of an audio signal based both on environmental noise conditions and upon automatically-learned user preference information, wherein the user preference information is derived by monitoring user-implemented adjustments to the volume setting after application of an automatic adjustment thereto. As another example, a second embodiment adjusts a brightness setting used to control the brightness of a display used for rendering images based both on an ambient light level and upon automatically-learned user preference information, wherein the user preference information is derived by monitoring user-implemented adjustments to the brightness setting after application of an automatic adjustment thereto.

Various embodiments facilitate generation, distribution, and presentation of a video program on a virtual channel. In one embodiment, an electronic program guide (“EPG”) manager is provided for execution on a receiving device, such as a set-top box. The EPG manager receives from a program distributor a video stream that has plurality of video programs having program content. Each program has been preassigned for presentation on a particular channel. A virtual channel is linked to one or more users. The EPG manager tracks the types of programs that a user watches and records metadata associated with the programs that the user actually views. When sufficient data is stored in the data base, the virtual channel is provided that program that a user will likely wish to view based on this past viewing history.

Disclosed is a device carrying out whole-course, real-time and comprehensive monitoring, such as parameter detection, analysis, learning, control, display, external communication and the like, for the charging-discharging process of a lithium battery pack, namely an intelligent management system for power lithium batteries, which mainly comprises a voltage detection device, a current detection device for detecting electric current in the process of charging and discharging of the lithium battery pack, a temperature detection device, a control device, a charging-discharging state judgment device, a computing device, a data storage device, a parameter correction device, an automatic learning device, a data display device, a communication device, a protection device, a system automatic diagnosis device and an alarm display device. Further disclosed is a device (instrument) for detecting the performance of the lithium battery, which mainly comprises a voltage detection device, a current detection device, a temperature detection device, a control device, a computing device, a data storage device, a parameter correction device, a residual capacity judgment device, a data display device, a communication device, a protection device, a system automatic diagnosis device and an alarm display device.

Typical conventional content based database security scheme mechanisms employ a predefined criteria for identifying access attempts to sensitive or prohibited data. An operator, identifies the criteria indicative of prohibited data, and the conventional content based approach scans or “sniffs” the transmissions for data items matching the predefined criteria. In many environments, however, database usage tends to follow repeated patterns of legitimate usage. Such usage patterns, if tracked, are deterministic of normal, allowable data access attempts. Similarly, deviant data access attempts may be suspect. Recording and tracking patterns of database usage allows learning of an expected baseline of normal DB activity, or application behavior. Identifying baseline divergent access attempts as deviant, unallowed behavior, allows automatic learning and implementation of behavior based access control. In this manner, data access attempts not matching previous behavior patterns are disallowed.

A computerized learning multi-modal fraud prevention system and method for generating a data signature of a user, such as one engaged in electronic commerce, to prevent fraudulent activities by machines and persons imitating the user. Steps comprise: fetching a signal of a user's signature stored in memory; generating at least one challenge sequence based on the signal to create a second signature; presenting the generated challenge sequence to the user; collecting the user's challenge response to the generated challenge sequence; computing a quality factor between the user's challenge response and the generated challenge sequence; computing a transaction quality factor and content quality factor and reporting an impostor or re-challenging if the quality factor is below a threshold. Lastly, generating a new signature based on any portion of a user's challenge response and/or any portion of the previously generated signature and/or any portion of collectable information from the user's device memory.

Automatically learning and providing software development team structure and methodologies. A software development knowledgebase repository is generated by mining for software processes data over a network of computer systems. A team structure specification and project requirement associated with a target project is received. A software development methodology is selected from the software development knowledgebase repository based on the team structure specification and project requirement associated with a target project, a team members knowledgebase, a teams knowledgebase, and a past projects knowledgebase. A machine learning module automatically learns a software development methodology to select. Based on the software development methodology, a software development environment infrastructure for the target project is built.

The invention relates to an adaptive extraction and diagnosis method for degree features of a mechanical fault through a stack-type sparse automatic coding depth neural network, and belongs to the technical field of mechanical equipment state monitoring and reliability evaluation. The method aims at a problem of intelligent diagnosis of the degree of the mechanical fault, and comprises the steps: carrying out the stacking of sparse automatic coding, adding a classification layer, and constructing the stack-type sparse automatic coding depth neural network which integrates the adaptive learning and extraction of the degree features of the fault and fault recognition; employing the advantage that the sparse automatic coding can automatically learn the internal features of data, and adding noise coding to be integrated in the sparse automatic coding for improving the robustness of feature learning; carrying out the layer-by-layer no-supervision adaptive learning and supervision fine tuning of the original input complex data through multilayer sparse automatic coding, completing the automatic extraction and expression of the degree features of the mechanical fault and achieving the intelligent diagnosis of the degree of the fault. The method is used for the diagnosis of the degree of faults of rolling bearings under different work conditions, and obtains a good effect of feature extraction and diagnosis.

An intelligent information retrieval system for finding information components corresponding to an input query word. The system includes a synonym block for finding synonymous indexed keywords of the query word; an information indexing block for finding corresponding information components based on the indexed keyword; a component ranking-filtering block for ranking and filtering the found information components and outputting the desired information components being selected; a synonym adjusting block for adjusting the fuzzy mechanism of the synonym block based on the found information components; and a filtering adjusting block for adjusting the fuzzy mechanism of the ranking-filtering block based on the found information components. The aforementioned synonym block and information-indexing block are implemented by neuro-fuzzy networks for accelerating parallel processing and automatic learning. Further, the synonym block can tolerate input errors by way of query word encoding and position shift compensation.

The invention provides a method for positioning three-dimensional human body joints in monocular color videos. The method comprises the following steps of: S1, constructing a configurable depth model and importing time sequence information in the depth model; S2, collecting training samples and learning parameters of the depth model by utilizing the training samples; and S3, initializing the depth model by utilizing the parameters learnt in S2, and converting monocular color video data needing three-dimensional human body joint positioning into a plurality of frames of continuous two-dimensional images, inputting the images into the depth model to carry out analysis, and aiming at each frame of two-dimensional image, outputting three-dimensional human body joint coordinates of figures in the image. According to the method, a deep-level convolutional neural network is constructed by utilizing deep learning so as to automatically learn effective spatial-temporal features from a lot of training samples without depending on prior conditions of artificial design and human body joint structural constraints; and through the learnt effective features, the human body joint positions are directly regressed.

The invention discloses a data mining method based on extraction of Web numerical value tables. The method is based on domain knowledge base, adopts generation of numerical value knowledge element base as a basic target, and mainly comprises construction of domain knowledge base basic set, positioning of Web numerical value tables, recognition of table structure, integration of table content, semantic representation of extract result, data retrieval, automatic learning of domain knowledge and data mining processing and the like. The invention is based on the method of extraction of Web numerical value tables in specific domain, can carry out extraction to data, information and knowledge included in numerical value tables in Web pages, converts semi-structured data into structured data and provides services of data retrieval, data mining analysis and the like. The data mining method can completely and accurately extract valuable numerical value knowledge in large amount of Web numerical tables dispersed on Web and meets the requirements of data query and data analysis of a user.

The invention relates to a method for programming a robot, in particular a robot comprising a robotic arm, in which method a movement to be performed by the robot is set up preferably in a robot programme by means of a predefined motion template, the motion template is selected from a database comprising a plurality of motion templates, the motion template comprises one or more execution modules that can be parameterized and at least one learning module, the one or more execution modules are used for planning and/or performing the robot movement or part of the robot movement, the leaning module records one or more configurations of the robot during an initialization process, in particular in the form of a teaching process, and the learning module calculates parameters for the one or more execution modules on the basis of the recorded configurations, preferably using an automatic learning process. Also disclosed is a corresponding system for programming a robot.

A method and system learns functions to be associated with data fields of forms to be incorporated into an electronic document preparation system. The functions are essentially sets of operations required to calculate the data field. The method and system receive form data related to a data field that expects data values resulting from performing specific operations. The method and system utilize machine learning and training set data to generate, test, and evaluate candidate functions to determine acceptable functions.

The invention discloses a malicious traffic detection method. The method comprises the following steps: correspondingly establishing malicious and normal data sample libraries by using obtained malicious and normal data traffic samples; executing a data cleaning operation and a preprocessing operation on the data sample libraries in sequence to obtain training data, and constructing a traffic detection model by using the training data and a deep learning algorithm; judging whether to-be-measured data traffic contains malicious data by using the traffic detection model; and if so, sending alarminformation carrying the to-be-measured data traffic belonging to malicious data via a preset oath. Feature learning and training are performed by using the malicious and normal data traffic samplesvia the automatic learning property of the deep learning algorithm, the feature information extraction operation is completed without consuming precious human resources, thereby improving the improving the work efficiency and improving the discrimination of the malicious traffic. Precision. The invention further discloses a malicious traffic detection system and apparatus and a computer readable storage medium, which have the above beneficial effects.

An efficient binary translator uses peephole translation rules to directly translate executable code from one instruction set to another. In a preferred embodiment, the translation rules are generated using superoptimization techniques that enable the translator to automatically learn translation rules for translating code from the source to target instruction set architecture.

The present invention provides a technology for controlling an IoT gateway command control based packet, preemptively blocking information leakage by detecting/blocking command not allowed through a DB updated by automatically learning new commands recognized based thereon in real-time, determining whether they correspond to each other through search/comparison in each pattern DB corresponding thereto and selectively processing the corresponding packet according to the determined result, generating a session table based on the processed result and determining whether there is an abnormal act by checking a predetermined item, and blocking access to IoT server of abnormal packet by performing a policy according to packet blocking rule management flow.

The invention relates to the technical field of biomedicine, and relates to a biomedicine event trigger word identification method based on characteristic automatic learning. The biomedicine event trigger word identification method comprises the following steps of 1, data pre-processing; 2, construction of an event trigger word dictionary; 3, construction of candidate trigger word examples; 4, characteristic learning by means of a convolutional neural network model; 5, training by means of a neural network model; and 6, classification of event trigger words. The biomedicine event trigger word identification method is advantaged in that 1, complex preprocessing to data is simplified, and tedious steps for carrying out a characteristic design by people are saved; 2, domain knowledge is introduced, and a lot of external resources such as unlabeled linguistic data are effectively utilized; 3, characteristic automatic learning is carried out by means of a convolutional neural network, manual intervention is reduced, sentence level characteristics in a deeper level can be excavated and explored, through the fusion of local characteristics, implicit global characteristics are discovered, and the category of trigger words can be identified; and 4, a better experiment result is obtained in MLEE linguistic data, and the whole performance on event trigger word detection is improved.

A computerized learning fraud prevention system and method for generating a voice signature of a user, such as one engaged in electronic commerce, to prevent fraudulent activities by machines and persons imitating the user. Steps comprise: fetching a signal of a user's signature stored in memory; generating at least one challenge sequence based on the signal to create a second signature; presenting the generated challenge sequence to the user; collecting the user's challenge voice response to the generated challenge sequence; computing a quality factor between the user's challenge response and the generated challenge sequence; computing a transaction quality factor and content quality factor and reporting an impostor or re-challenging if the quality factor is below a threshold. Lastly, generating new signature based on any portion of user's challenge voice response and/or any portion of the previously generated signature and/or any portion of collectable information from user's device memory.

Disclosed method and apparatus for automatic information filtering are capable of improving both precision and recall and accurately judging inappropriateness of the content even for a page that contains very few or no text information and only displays images, by utilizing an upper level URL of a URL given in a hierarchical structure. Also, disclosed method and apparatus for automatic information filtering are capable of setting weights of words easily and accurately and judging inappropriateness of the information by utilizing these weights, by using an automatic learning based on a linear discrimination function that can discriminate the inappropriate information and the appropriate information on a vector space.