Data item aggregate probability analysis system
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06F-017/30
G06N-007/00
G06F-003/0484
G06T-011/20
출원번호
US-0381518
(2016-12-16)
등록번호
US-9886525
(2018-02-06)
발명자
/ 주소
Soman, Satej
Hoffman, Duncan
al Khafaji, Salar
Kowalik, Jakub
Sanzovo, Pedro
Punukollu, Gautam
출원인 / 주소
Palantir Technologies Inc.
대리인 / 주소
Knobbe, Martens, Olson & Bear, LLP
인용정보
피인용 횟수 :
0인용 특허 :
37
초록▼
Computer-implemented systems and methods are disclosed for automatically aggregating, analyzing, and presenting probabilities associated with data items. Data items may be associated with probabilities or risks, and the data items may have various characteristics. A grouping of data items may be det
Computer-implemented systems and methods are disclosed for automatically aggregating, analyzing, and presenting probabilities associated with data items. Data items may be associated with probabilities or risks, and the data items may have various characteristics. A grouping of data items may be determined based on these characteristics, and probabilities within groups of data items may be aggregated and analyzed. Aggregated probabilities may be used to determine incremental probabilities for individual data items, to assess cumulative risk associated with a group of data items, and to analyze probabilities associated with a particular data item group. User interfaces may be generated to facilitate selection and grouping of data items, selection of risk models, and analysis of aggregate probabilities.
대표청구항▼
1. A system comprising: a data store configured to store data items and probabilities; anda processor in communication with the data store, the processor configured to execute specific computer-executable instructions to at least: receive information regarding a first data item;determine a geographi
1. A system comprising: a data store configured to store data items and probabilities; anda processor in communication with the data store, the processor configured to execute specific computer-executable instructions to at least: receive information regarding a first data item;determine a geographic location of the first data item;determine, based at least in part on a risk model, an event probability associated with a geographic region, the event probability indicating a probability that an event affecting the geographic region will occur, the geographic region including the geographic location of the first data item;obtain, from the data store, a plurality of data items, wherein each of the plurality of data items is associated with a respective geographic location in the geographic region;determine, based at least in part on the risk model, the event probability, and one or more attributes of the first data item, a probability that the event will change a first attribute of the first data item, and a predicted attribute change to the first attribute of the first data item;for individual data items of the plurality of data items, determine, based at least in part on the risk model, the event probability, and one or more attributes of the data item, a probability that the event will change the first attribute of the data item, and a predicted change to the first attribute of the data item;determine a probability associated with the geographic region based at least in part on the event probability, the probabilities that the event will change the first attributes, and the predicted changes to the first attributes;determine a probability category of the first data item based at least in part on: the probability associated with the geographic region, the probability that the event will change the first attribute of the first data item, and the probabilities that the event will change the first attribute of individual data items of the plurality of data items;generate for display a user interface, the user interface including at least: a geographic map identifying the geographic region, the geographic location of the first data item, and the geographic locations of the plurality of items, wherein a shading of an icon displayed at the geographic location of the first data item indicates the probability category of the first data item, and wherein a size of the icon indicates the predicted change to the first attribute of the first data item; andcause display of the user interface. 2. The system of claim 1, wherein the data store is further configured to store geographic regions, and wherein the processor is configured to obtain the geographic region from the data store. 3. The system of claim 1, wherein the processor is configured to determine the probability associated with the geographic region based at least in part on one or more previous events associated with the geographic region. 4. The system of claim 3, wherein the processor configured to determine the probability associated with the geographic region is configured to: determine the probability associated with the geographic region based at least in part on a predicted change to a second attribute of individual data items within the plurality of data items. 5. The system of claim 1, wherein the geographic map includes at least the geographic region. 6. The system of claim 5, wherein the map display further includes an area of interest. 7. The system of claim 6, wherein the area of interest comprises at least one of a storm track, weather track, flood plain, drought zone, earthquake zone, tsunami zone, avalanche zone, tornado zone, volcano zone, or wildfire zone. 8. The system of claim 6, wherein the area of interest comprises a predicted weather track. 9. The system of claim 6, wherein the area of interest comprises a geographic route. 10. The system of claim 1, wherein the user interface further includes at least one of a scatterplot display or a bar chart display. 11. The system of claim 1, wherein the data store is further configured to store risk models, and wherein the processor is further configured to: obtain, from the data store, the risk model. 12. The system of claim 11, wherein the processor is further configured to determine the probability associated with the geographic region based at least in part on the risk model. 13. The system of claim 11, wherein the processor is further configured to receive, via the user interface, an indication of a selection of the risk model. 14. The system of claim 1, wherein the processor is further configured to: receive, via the user interface, an indication of an area of interest;determine a subset of the plurality of data items, wherein each data item of the plurality of data items is associated with a geographic location within the area of interest;generate a second user interface, the second user interface including at least the subset of the plurality of data items; andcause display of the second user interface. 15. The system of claim 1, wherein the probability category of the first data item comprises a high risk category. 16. The system of claim 1, wherein the probability category of the first data item comprises a category of data items having a high risk-to-loss ratio. 17. A system comprising: a data store configured to store data items, respective geographic locations associated with the data items, and respective probabilities associated with the data items; anda processor in communication with the data store, the processor configured to execute specific computer-executable instructions to at least: receive an indication of geographic grouping criteria;determine, based on the geographic grouping criteria, a plurality of geographic regions;analyze the data items and associated geographic locations to determine a plurality of groups of data items associated with respective geographic regions;for each group in the plurality of groups of data items, analyze the data items of the group to determine, based at least in part on a risk model and one or more attributes of individual data items of the group, an aggregate probability associated with the group of data items, the aggregate probability indicating a level of exposure to a risk associated with at least a portion of the respective geographic region; andgenerate user interface data useable for rendering a user interface, the user interface including graphical representations of the geographic regions, wherein the graphical representations include visualizations indicative of the aggregate probabilities associated with the groups associated with the geographic regions and visualizations of individual data items from at least one group of data items, wherein a first attribute of a visualization of an individual data item indicates a probability category of the individual data item, and wherein a second attribute of the visualization of the individual data item indicates a predicted change to the one or more attributes of the individual data item. 18. The system of claim 17, wherein the processor is further configured to receive an indication of filtering criteria. 19. The system of claim 18, wherein the processor is further configured to determine the plurality of groups of data items based at least in part on the filtering criteria. 20. The system of claim 17, wherein the geographic grouping criteria specify a granularity of the plurality of geographic regions.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (37)
Ma, Songtao; Huria, Sangeeta; Klein, Eric; Crews, Tim, Banking system controlled responsive to data bearing records.
Gabbert, Charles Keith; Robbins, Mark Wayne; Lombard, Robin J.; Woolums, Thomas Michael; Moiceanu, Corneliu, Centralized terminology and glossary development.
Greenstein, Paul G.; Grunin, Galina; Nguyen, Luu Q., Facilitating management of service elements usable in providing information technology service offerings.
Gopinathan Krishna M. ; Biafore Louis S. ; Ferguson William M. ; Lazarus Michael A. ; Pathria Anu K. ; Jost Allen, Fraud detection using predictive modeling.
Vishniac, Ephraim Meriwether; Isman, Marshall A.; Bay, Paul; Bromley, H. Mark; Richardson, John L., Managing storage of individually accessible data units.
Kantrowitz, Mark, Method and apparatus for efficient identification of duplicate and near-duplicate documents and text spans using high-discriminability text fragments.
Bunzel, Breeana D.; Rangara, Akbar A.; Chan, Kai Chun, Method and system for automatic correlation of check-based payments to customer accounts and/or invoices.
Pednault,Edwin Peter Dawson, Method for constructing segmentation-based predictive models from data that is particularly well-suited for insurance risk or profitability modeling purposes.
Creeden, Denis Michael; Glionna, Jesse; Poulter, Martha Cecilia; Kaptinski, John Stephen; Persico, James Robert; Doolittle, William Roy; Cascade, Ryan Stuart; van Heyst, Amanda Jenks; Ernst, David Andrew; Chomienne, Kathleen Mary; Bellish, Robert Wayne; Crowley, Robert Francis, Methods and systems for managing risk management information.
Burns, Michael J.; West, Robert A.; Brumfield, Harris; Ziemkiewicz, Peter F., System and method for money management in electronic trading environment.
Evanitsky, Eugene Stephen; Moore, John A.; Coene, Matthew Dylan; Schlonski, Steve; Chlebove, Wilma Wandersleben, System and method of on-demand document processing.
Ginter Karl L. ; Shear Victor H. ; Sibert W. Olin ; Spahn Francis J. ; Van Wie David M., Systems and methods for secure transaction management and electronic rights protection.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.