摘要:
A multi-agent system is provided for automatically acquiring desired information from one or more information sources. The multi-agent system includes a plurality of data provider filter agents associated with the one or more information sources. The data provider filter agents are configured to search for the desired information within the respective information sources based on an assessment of the one or more information sources. The multi-agent system also includes a content extraction agent configured to acquire a plurality of articles containing the desired information from the one or more information sources based on the search.
摘要:
A method for constructing data patterns of interest is provided. The method includes creating one or more alert clause expressions and evaluating the one or more alert clause expressions based on a parameter of interest and a plurality of conditions. The method further includes combining the one or more alert clause expressions in a selected manner to generate an alert signal. The one or more data patterns of interest are described by the one or more alert clause expressions and the alert signal.
摘要:
A robust system for automating the tuning and maintenance of decision-making systems is described. A configurable multi-stage mutation-based evolutionary algorithm optimally tunes the decision thresholds and internal parameters of fuzzy rule-based and case-based systems that decide the risk categories of insurance applications. The tunable parameters have a critical impact on the coverage and accuracy of decision-making, and a reliable method to optimally tune these parameters is critical to the quality of decision-making and maintainability of these systems.
摘要:
A method and system for fusing a collection of classifiers used for an automated insurance underwriting system and/or its quality assurance is described. Specifically, the outputs of a collection of classifiers are fused. The fusion of the data will typically result in some amount of consensus and some amount of conflict among the classifiers. The consensus will be measured and used to estimate a degree of confidence in the fused decisions. Based on the decision and degree of confidence of the fusion and the decision and degree of confidence of the production decision engine, a comparison module may then be used to identify cases for audit, cases for augmenting the training/test sets for re-tuning production decision engine, cases for review, or may simply trigger a record of its occurrence for tracking purposes. The fusion can compensate for the potential correlation among the classifiers. The reliability of each classifier can be represented by a static or dynamic discounting factor, which will reflect the expected accuracy of the classifier. A static discounting factor is used to represent a prior expectation about the classifier's reliability, e.g., it might be based on the average past accuracy of the model, while a dynamic discounting is used to represent a conditional assessment of the classifier's reliability, e.g., whenever a classifier bases its output on an insufficient number of points it is not reliable.
摘要:
Searching and matching a set of query strings used for accessing information in a database directory. In this disclosure, a user community administration tool queries a database directory containing user information associated with a user community. In the user community administration tool, there is an input query generation component that generates an input query having a search pattern that includes a combination of attribute names, logical, operators and attribute values. An accessing component accesses a library of queries used for accessing the user information in the database directory. A partitioning component partitions each of the queries in the library into logical units. Each logical unit comprises a combination of an attribute name, logical operator and attribute value. A comparing component compares the search pattern of the input query to each partitioned logical unit for each of the queries in the library. The comparing component compares the attribute name of the input query to the attribute name in the logical unit, the operator used in the input query to the operator used in the logical unit and the attribute value in the input query to the attribute value in the logical unit. A determining component determines whether there is a match between the input query and any of the logical units associated with each of the queries in the library.
摘要:
A method and system of forecasting reliability of an asset is provided. The method includes identifying peer units of the asset by using selected criteria, performing a search for the peer units based upon the selected criteria, and constructing local predictive models using the peer units. The method also includes estimating the future behavior of the asset based upon the local predictive models and dynamically updating the local predictive models to reflect at least one change in the criteria.
摘要:
A method and system for fusing a collection of classifiers used for an automated insurance underwriting system and/or its quality assurance is described. Specifically, the outputs of a collection of classifiers are fused. The fusion of the data will typically result in some amount of consensus and some amount of conflict among the classifiers. The consensus will be measured and used to estimate a degree of confidence in the fused decisions. Based on the decision and degree of confidence of the fusion and the decision and degree of confidence of the production decision engine, a comparison module may then be used to identify cases for audit, cases for augmenting the training/test sets for re-tuning production decision engine, cases for review, or may simply trigger a record of its occurrence for tracking purposes. The fusion can compensate for the potential correlation among the classifiers. The reliability of each classifier can be represented by a static or dynamic discounting factor, which will reflect the expected accuracy of the classifier. A static discounting factor is used to represent a prior expectation about the classifier's reliability, e.g., it might be based on the average past accuracy of the model, while a dynamic discounting is used to represent a conditional assessment of the classifier's reliability, e.g., whenever a classifier bases its output on an insufficient number of points it is not reliable.
摘要:
A technique is provided for acquiring desired information from one or more information sources. The technique includes assessing the one or more information sources for the desired information, searching for the desired information within the one or more information sources based on the assessment, and automatically acquiring the desired information based on the search.
摘要:
Establishment and maintenance of a managed community. In this disclosure there is an approach and tool that enables an administration tool to manage communities whose information resides in separate and differently structured directories and databases. In addition, this disclosure describes an approach and tool that enables an administration tool to establish information to be managed from the broad range of directories and databases, which includes defining information that is to be managed and information that is not to be managed and the discovering of new information to manage.
摘要:
A method and system for fusing a collection of classifiers used for an automated insurance underwriting system and/or its quality assurance is described. Specifically, the outputs of a collection of classifiers are fused. The fusion of the data will typically result in some amount of consensus and some amount of conflict among the classifiers. The consensus will be measured and used to estimate a degree of confidence in the fused decisions. Based on the decision and degree of confidence of the fusion and the decision and degree of confidence of the production decision engine, a comparison module may then be used to identify cases for audit, cases for augmenting the training/test sets for re-tuning production decision engine, cases for review, or may simply trigger a record of its occurrence for tracking purposes. The fusion can compensate for the potential correlation among the classifiers. The reliability of each classifier can be represented by a static or dynamic discounting factor, which will reflect the expected accuracy of the classifier. A static discounting factor is used to represent a prior expectation about the classifier's reliability, e.g., it might be based on the average past accuracy of the model, while a dynamic discounting is used to represent a conditional assessment of the classifier's reliability, e.g., whenever a classifier bases its output on an insufficient number of points it is not reliable.