34 results about "Rule based inference" patented technology

The present invention provides systems and methods for dynamic detection and prevention of electronic fraud and network intrusion using an integrated set of intelligent technologies. The intelligent technologies include neural networks, multi-agents, data mining, case-based reasoning, rule-based reasoning, fuzzy logic, constraint programming, and genetic algorithms. The systems and methods of the present invention involve a fraud detection and prevention model that successfully detects and prevents electronic fraud and network intrusion in real-time. The model is not sensitive to known or unknown different types of fraud or network intrusion attacks, and can be used to detect and prevent fraud and network intrusion across multiple networks and industries.

A video surveillance system uses rule-based reasoning and multiple-hypothesis scoring to detect predefined behaviors based on movement through zone patterns. Trajectory hypothesis spawning allows for trajectory splitting and/or merging and includes local pruning to managed hypothesis growth. Hypotheses are scored based on a number of criteria, illustratively including at least one non-spatial parameter. Connection probabilities computed during the hypothesis spawning process are based on a number of criteria, illustratively including object size. Object detection and probability scoring is illustratively based on object class.

A method and system for computer assisted automatic error detection and diagnosis of file servers. Software modules periodically and continuously review monitoring statistics gathered by the file server regarding its operation. The monitoring statistics are processed by a pattern matching system and a rule-based inference system. Software modules augment known network protocols, by manipulating parameters of lower-level protocols using different higher-level protocols. Using the higher-level protocols, software modules determine if the selected parameters for the lower-level protocols are correct. Software modules track hardware and software configuration changes to the file server, and relate changes in known monitoring statistics to timing of those hardware and software configuration changes.

A method for providing recommendations to a user based on user activity. A plurality of activity data tracking a plurality of activities of a user is obtained. The activity data may be obtained over a wide area network such as the internet or downloaded from a data card which stores activity data whenever the user participates in an activity. The activity data is either stored on the data card or transmitted over the network whenever the user uses a card when participating in any activity such as when making a purchase of goods, paying for services, watching television, etc. The activity data is processed to identify a plurality of user patterns. The user patterns are used to form a user profile and may include user habit data. Recommendations specific to the user based on the user patterns are then created for and provided to the user. The recommendations are provided to a user when the user logs onto a computer network such as the internet. The recommendations may also be provided by electronic mail, electronic pager or other methods. The recommendations are provided by various data analysis techniques including rule based inference engines and other forms of artificial intelligence.

A video surveillance system uses rule-based reasoning and multiple-hypothesis scoring to detect predefined behaviors based on movement through zone patterns. Trajectory hypothesis spawning allows for trajectory splitting and/or merging and includes local pruning to managed hypothesis growth. Hypotheses are scored based on a number of criteria, illustratively including at least one non-spatial parameter. Connection probabilities computed during the hypothesis spawning process are based on a number of criteria, illustratively including object size. Object detection and probability scoring is illustratively based on object class.

A video surveillance system uses rule-based reasoning and multiple-hypothesis scoring to detect predefined behaviors based on movement through zone patterns. Trajectory hypothesis spawning allows for trajectory splitting and/or merging and includes local pruning to managed hypothesis growth. Hypotheses are scored based on a number of criteria, illustratively including at least one non-spatial parameter. Connection probabilities computed during the hypothesis spawning process are based on a number of criteria, illustratively including object size. Object detection and probability scoring is illustratively based on object class.

Provided are an ontology system, a method for managing the ontology system, and a recording medium storing the same. The ontology system includes: a context broker unit for receiving context information from a sensing device and verifying a validity of the received context information; a context managing unit for controlling to generate an ontology structure by transforming the verified context information from the context broker unit to ontology web language (OWL) data and processing the OWL data; a rule-based inference engine unit for transforming the processed context information from the context managing unit to semantic web rule language (SWRL) data and processing the SWRL data through an inference process; a learning managing unit for processing the processed context information from the context managing unit through learning; and a database for storing the context information processed at the context managing unit, the rule-based engine unit, and the learning managing unit.

A video surveillance system uses rule-based reasoning and multiple-hypothesis scoring to detect predefined behaviors based on movement through zone patterns. Trajectory hypothesis spawning allows for trajectory splitting and/or merging and includes local pruning to managed hypothesis growth. Hypotheses are scored based on a number of criteria, illustratively including at least one non-spatial parameter. Connection probabilities computed during the hypothesis spawning process are based on a number of criteria, illustratively including object size. Object detection and probability scoring is illustratively based on object class.

The invention relates to a track profile irregularity amplitude estimation method employing optimal belief rules based inference. According to the method, the mapping relationship between parametric variable input and yield output is modeled by a belief rule base. A corresponding change relationship between vibration frequency domain characteristic data of different measurement points and a track profile irregularity amplitude is described by building the belief rule base. By a sequence linear programming method, an initial belief rules based (BRB) model is optimized through limited historical data; and the effects on the model caused by subjective factors are reduced. According to the sequence linear programming (SLP) method, a nonlinear optimization problem of an original model is converted into a step-by-step linear optimization problem; and various parameters of the optimization model can be relatively simply and rapidly calculated, so that the track profile irregularity amplitude can be accurately and rapidly estimated through belief inference under the condition of given vibration frequency domain characteristic. According to the track profile irregularity amplitude estimation method, the estimation accuracy and the calculation efficiency of the model are improved; and the method has the advantage of being relatively efficient on a track profile irregularity system which needs to be monitored in real time.

A video surveillance system uses rule-based reasoning and multiple-hypothesis scoring to detect predefined behaviors based on movement through zone patterns. Trajectory hypothesis spawning allows for trajectory splitting and/or merging and includes local pruning to managed hypothesis growth. Hypotheses are scored based on a number of criteria, illustratively including at least one non-spatial parameter. Connection probabilities computed during the hypothesis spawning process are based on a number of criteria, illustratively including object size. Object detection and probability scoring is illustratively based on object class.

A video surveillance system uses rule-based reasoning and multiple-hypothesis scoring to detect predefined behaviors based on movement through zone patterns. Trajectory hypothesis spawning allows for trajectory splitting and/or merging and includes local pruning to managed hypothesis growth. Hypotheses are scored based on a number of criteria, illustratively including at least one non-spatial parameter. Connection probabilities computed during the hypothesis spawning process are based on a number of criteria, illustratively including object size. Object detection and probability scoring is illustratively based on object class.

The invention provides an ontology-based sewage decision-support system and method. The system comprises a data collection layer, a diagnosis layer and a decision-support layer, wherein the data collection layer is used for obtaining online sensor data, offline measurement data and data subjected to calculation through an online sensor and a laboratory; the diagnosis layer is used for respectively processing and diagnosing data from the data collection layer by adopting a rule-based reasoning module and a case-based reasoning module, and diagnosing and processing the data from the data collection module by adopting a sewage body module if the two modules are incapable of obtaining a diagnosis result; and the decision-support module comprises a user interface and a monitor module, the monitor module is used for providing complete decision information and corresponding ontology types according to the diagnosis result from the diagnosis layer, the user interface is used by a user to activate a sewage treatment system for selecting a sewage treatment mode, and the user can inquire a specific reason of the sewage treatment mode by virtue of the user interface. According to the invention, the reliability of the sewage decision-support system is improved, sewage knowledge is reused and shared, and the transportability of the whole system is improved.

The invention discloses a remote fault diagnosis system based on an expert system. The remote fault diagnosis system comprises a gateway and server part and the expert system part. The expert system is the core of the remote fault diagnosis system and comprises a network interface, a man-machine interface, a knowledge base, a database, an explanation machine and an inference machine, wherein the network interface receives and converts data transmitted by a server, the man-machine interface is used for conducting information interaction between a user and various modules of the expert system, the knowledge base is connected with the inference machine, the explanation machine and the like and used for storing facts and rules, the database is connected with the explanation machine, the inference machine and the interface and used for storing the inference procedure, information records and the like, the explanation machine explains the faults through the method shown through the inferencepath based on rule inference, and the inference machine diagnoses the faults through inference due to fusion of two mechanisms including the neural network and the rule-based inference.

A method and system for adding processes to print production workflows utilizing asset metadata and automated reasoning system is disclosed. The asset metadata can be extracted from the resources associated with a print product description such as PDF files and image and artwork files. The asset metadata can be processed through an automated reasoning system in order to infer additional metadata. The inferred metadata can be utilized to add and parameterize a process node in order to build a more effective and useful process network. The reasoning system can be a rule based reasoning system and/or ontology based reasoning system.

The invention relates to a ground unmanned platform tactical mission planning system based on a CLanguage Integration Generation System (CLIPS). The system includes a man-machine interface module, a task receiving module, a chariot management module, a map operation module, a knowledge editing module, a knowledge reasoning module, a command decision-making module, a model library planning module and a CLIPS expert system. For a structured task, a model library algorithm is used to obtain a task scheme; and for unstructured tasks, the expert system is introduced to implement rule-based reasoning to meet complex and diversified task requirements. The system of the invention has the advantages of being high in practicality and capable of satisfying real needs of a ground unmanned platform; being wide in application range, capable of satisfying diversified task requirements, and being high in accuracy and timeliness; and being simple in process, convenient in operation and easy to use.

The invention discloses a motor vehicle traffic violation behavior automatic detection technology based on computer vision. The motor vehicle traffic violation behavior automatic detection technologycomprises the following steps: constructing a target detection data set; loading a YOLOv3 model to perform a parameter initialization process of the model, constructing a model, and training the model; predicting a target category and position coordinates by using the trained YOLOv3 model; and inferring traffic violations according to the target category and the position coordinates. For the motorvehicle traffic violation behavior automatic detection technology, based on computer vision, a target detection algorithm based on deep learning and a reasoning mode based on rules are used for automatically detecting traffic violation behaviors; a new thought is provided for traffic violation behavior detection of motor vehicles; and the motor vehicle traffic violation behavior automatic detection technology has excellent extraction efficiency and accuracy.