Abstract:
A method and system for processing informational items originating from a plurality of information sources into a derived document for topical analysis thereof. Informational items are collated from a one of the sources in accordance with a predetermined plurality of relevant attributes and a key property value of common to select ones of the relevant attributes. Informational items are then grouped from the plurality of sources associated with the key common property value to form a document, wherein the informational items therein are marked on the informational source thereof. The document is then analyzed for topical identification.
Abstract:
There is disclosed a method of conducting an auction under execution uncertainty to satisfy incentive compatibility, individual rationality, and efficiency by leveraging bonuses and penalties. A buyer posts a task including multiple sub-tasks. The buyer specifies temporal and precedence relationships among the sub-tasks. The buyer also specifies the time interval for the sub-tasks. Suppliers submit bids including their interested sub-tasks, prices, and proposed schedules. A winner determination problem is formulated based on bid prices, suppliers' success probabilities in delivering the sub-tasks, and the suppliers' schedules of undertaking sub-tasks. Having decided the winners, suppliers who delivered with success will be granted bonuses and those who were not able to deliver will be imposed penalties. The bonuses and penalties are formulated under a verification assumption. The combinatorial mechanism using the formulated winner determination rule and payment rule including bonuses and penalties satisfy economic properties such as incentive compatibility, individual rationality, and efficiency.
Abstract:
The disclosed embodiments illustrate methods and systems for determining strategies in crowdsourcing. The method includes generating first graphs representative of an association between workers, between crowdsourcing tasks, or between workers and crowdsourcing tasks, at first time instance. The method includes determining values of metrics associated with first graphs, comparing determined values of metrics and threshold values of metrics, and generating second graphs based on comparison. The second graphs are representative of an association between workers, between crowdsourcing tasks, or between workers and crowdsourcing tasks, at second time instance. The second time instance precedes first time instance. Thereafter, the method includes determining strategies based on second graphs. The strategies comprise recommendation to a first set of workers for attempting a first set of crowdsourcing tasks or recommendation to first set of workers for increasing interaction with second set of workers. The method is performed by one or more microprocessors.
Abstract:
A method and system for processing informational items originating from a plurality of information sources into a derived document for topical analysis thereof. Informational items are collated from a one of the sources in accordance with a predetermined plurality of relevant attributes and a key property value of common to select ones of the relevant attributes. Informational items are then grouped from the plurality of sources associated with the key common property value to form a document, wherein the informational items therein are marked on the informational source thereof. The document is then analyzed for topical identification.