Abstract: An information processing apparatus includes: model learning means for self-organizing, on the basis of a state transition model having a state and state transition to be learned by using time series data as data in time series, an internal state from an observation signal obtained by a sensor; and controller learning means for performing learning for allocating a controller, which outputs an action, to each of transitions of a state or each of transition destination states in the state transition model indicating the internal state self-organized by the model learning means.

Abstract: There are provided methods, computer program products, and systems for indexing a data stream. A method for indexing a data stream having attribute values includes the steps of parsing the data stream, and forming an index of tuples for a subset of attribute values of the data stream. The index is configured for retrieving the top-K tuples that optimize linearly weighted sums of at least some of the attribute values in the subset.

Abstract: A method for analyzing documents is disclosed. The method compares concepts consisting of groups of terms for similarity within a corpus of document, clusters documents that contain certain concept term sets together. It may also rank the documents within each cluster according to the frequency of term co-occurrence within the concepts.

Abstract: A system includes a plurality of hierarchical layers configured to solve a decision-making problem. Each hierarchical layer is configured to generate solution data representing a possible solution to a sub-problem associated with the decision-making problem. Each hierarchical layer is also configured to receive orders and to use the orders during generation of the solution data. The orders include orders based on the solution data from a higher hierarchical layer, orders based on feedback from a lower hierarchical layer, and/or orders that are exogenously provided. Each hierarchical layer could be configured to use the orders to simplify a search for the possible solution to the sub-problem being solved by that hierarchical layer, such as by excluding solutions inconsistent with the orders.

Abstract: In certain embodiments, a method includes accessing a number of target values. Each target value may be associated with a respective design criterion of a computer system. The computer system may be associated with one or more domains. Each domain may be associated with a respective function of the computer system. The method may include determining, based at least in part on a first set of one or more of the number of target values, a respective implementation pattern for each of the one or more domains. The one or more determined implementation patterns may represent a logical architecture for the computer system. The method may include determining a physical architecture for the computer system by determining a respective solution stack for each of the one or more determined implementation patterns based at least in part on a second set of one or more of the plurality of target values.

Abstract: A model refinement system refines initial split rules that define an initial decision tree to generate final split-rules. The model refinement refines the initial split rules by removing clauses that are satisfied by match scores that are less than a threshold match score to generate initial trimmed rules. Using the initial trimmed rules, the model refinement system classifies an initial training set and filters the initial training set to remove negative training pairs that are classified as duplicate pairs resulting in a filtered training set. An intermediate decision tree defined by intermediate split-rules is generated based on the filtered training set. Final split-rules are generated based on the intermediate split rules and input pairs of data records are classified as duplicate pairs based on attribute values of the input pairs and the final split-rules.

Abstract: A training module is described for training a conditional random field (CRF) tagging model. The training module trains the tagging model based on an explicitly-labeled training set and an implicitly-labeled training set. The explicitly-labeled training set includes explicit labels that are manually selected via human annotation, while the implicitly-labeled training set includes implicit labels that are generated in an unsupervised manner. In one approach, the training module can train the tagging model by treating the implicit labels as non-binding evidence that has a bearing on values of hidden state sequence variables. In another approach, the training module can treat the implicit labels as binding or hard evidence. A labeling system is also described for providing the implicit labels.

Abstract: Systems and methods for prediction of gas turbine trips due to component failures such as electro-hydraulic valve (gas control valve) system failures. Exemplary embodiments include prediction of gas turbine trips due to component failures, the method including collecting raw gas turbine operational data and using the raw gas turbine operational data to generate a prognostic indicator for the prediction of a turbine trip due to the failed gas control valves.

Abstract: A system and method solicit decision-making input from a large number of users in a structured manner that facilitates generation of useful recommendations. The individual seeking advice posts a request for advice in the form of a decision question, or identifies a previously posted decision question. Visitors to the website can post secondary questions that are intended to assist the advice-seeker in making the decision. For each secondary question, the user posting the question can specify which choice for the decision question is recommended by each answer to the secondary question. The user can also specify a strength for the recommendation. The advice-seeker then inputs answers to the secondary questions. The advice-seeker can indicate a relative significance value for some or all of the answers. For each secondary answer, a score is generated. Scores are totaled and the results are provided to the advice-seeker to assist in decision-making.

Abstract: The invention relates to a method for performing acid fracturing operations of an oilfield. The method includes obtaining a plurality of historical data of acid fracturing treatments of the oilfield, generating a neural network based on the plurality of historical data, identifying a stimulation parameter, in the neural network, associated with optimal performance of the acid fracturing treatments, and establishing a best practice procedure for performing the acid fracturing operations based on the stimulation parameter.

Abstract: A method and apparatus are provided for dynamically determining a primary adapter in a heterogeneous N-way adapter configuration. Each of the adapters generates information about itself and exchanges the information with all other adapters. First a decision-making adapter is identified. Then the decision-making adapter compares the adapter-generated information of all the adapters and makes a decision determining the primary adapter. The decision-making adapter communicates the decision to all other adapters. The determined primary adapter assumes a role as the primary adapter and the other adapters assume a role as a secondary adapter.

Abstract: An automated method for the generation of (i) human models comprehensive of shape and joint centers information and/or (ii) subject specific models from multiple video streams is provided. To achieve these objectives, a kinematic model is learnt space from a training data set. The training data set includes kinematic models associated with corresponding morphological models. A shape model is identified as well as one or more poses of the subject. The learnt kinematic model space and the identified shape model are combined to generate a full body model of the subject starting from as few as one-static pose. Further, to generate a full body model of an arbitrary human subject, the learnt kinematic model space and the identified shape model are combined using a parameter set. The invention is applicable for fully automatic markerless motion capture and generation of complete human models.

Abstract: In some embodiments, a method includes receiving an electronic document that comprising a list of one or more features specified for use during processing of the electronic document by an application. The method also includes determining if one or more specified features from the list of specified features is not supported by the application. The method includes executing an operation that is defined by a prescription associated with one or more specified features, in response to a determination that the one or more specified features is not supported by the application, wherein the prescription defines at least one of an operation to be performed or a restriction to be applied by the application as part of subsequent processing of the electronic document.

Abstract: Reinforcement learning is one of the intellectual operations applied to autonomously moving robots etc. It is a system having excellent sides, for example, enabling operation in unknown environments. However, it has the basic problem called the “incomplete perception problem”. A variety of solution has been proposed, but none has been decisive. The systems also become complex. A simple and effective method of solution has been desired. A complex value function defining a state-action value by a complex number is introduced. Time series information is introduced into a phase part of the complex number value. Due to this, the time series information is introduced into the value function without using a complex algorithm, so the incomplete perception problem is effectively solved by simple loading of the method.

Abstract: Described is a method for governing the operation of a generalist agent within a multi-agent complex adaptive system such that the generalist agent maintains the stability of the system. The method includes the steps of migrating about the system, badging with the specialty agents, participating in the respective function performed by the specialty agents, collecting information while functionally participating as a specialty agent, evaluating the collected information, reconfiguring source code in view of the evaluated information, testing the reconfigured source code through additional functional participation, determining the usefulness of the reconfigured source code, archiving any reconfigured source code determined to be useful, and distributing the useful reconfigured source code.

Abstract: In selected embodiments a recommendation generator builds a network of interrelationships between venues, reviewers and users based on their attributes and reviewer and user reviews of the venues. Each interrelationship or link may be positive or negative and may accumulate with other links (or anti-links) to provide nodal links the strength of which are based on commonality of attributes among the linked nodes and/or common preferences that one node, such as a reviewer, expresses for other nodes, such as venues. The links may be first order (based on a direct relationship between, for instance, a reviewer and a venue) or higher order (based on, for instance, the fact that two venue are both liked by a given reviewer). The recommendation engine in certain embodiments determines recommended venues based on user attributes and venue preferences by aggregating the link matrices and determining the venues which are most strongly coupled to the user.

Abstract: A method and system for satisfying rules through a configuration of list processing methods. A document received from a calling application includes items being processed. A procedure for satisfying rules is identified by matching, via a database, a combination of values to the procedure. The combination of values includes attributes of the calling application and the document. Steps included in the procedure are determined by matching, via the database, the procedure to the steps. The order for executing the steps is determined by identifying, via the database, predecessor and successor steps. Sets of one or more list processing methods are determined and associated with each step. The order for executing each set of list processing methods is determined. The steps are executed. A selection list of elements is displayed to facilitate a selection of an element to characterize an item included in the document.

Abstract: A method for detecting people of interest from information sources. Method performs automatic community model generation based on uni-parity data. Correlation analysis is employed to identify links within the community. Method may be particularized for solving specific problems, for example, such as determining the activities between individuals within a money laundering ring.

Abstract: A method and apparatus for efficient token matching using complex rules. In one embodiment, the method and apparatus comprises searching a token stream to determine an earliest, narrowest token match range within a token stream.

Abstract: In embodiments of the present invention improved capabilities are described for identifying a classification scheme associated with product attributes of a grouping of products of an entity, receiving a record of data relating to an item of a competitor to the entity, the classification of which is uncertain, receiving a dictionary of attributes associated with products, and assigning a product code to the item, based on probabilistic matching among the attributes in the classification scheme, the attributes in the dictionary of attributes and at least one known attribute of the item.