Systems and methods for news event organization

US9817908B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-9817908-B2
Application numberUS-201414583905-A
CountryUS
Kind codeB2
Filing dateDec 29, 2014
Priority dateDec 29, 2014
Publication dateNov 14, 2017
Grant dateNov 14, 2017

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

Generally discussed herein are systems, apparatuses, and methods for organizing and/or searching news events. In one or more embodiments, a method can include encoding a news event based on named entities, actors, and actions mentioned in the news event, calculating a locality sensitive hash (LSH) key on the news event encoding, comparing the calculated LSH key to a plurality of LSH keys of respective stories, wherein each story of the respective stories comprises one or more associated news events that include LSH keys that are within a specified distance from each other, and associating the news event with a story of the respective stories that includes an LSH key that has a smallest distance from the LSH key of the received news event and is less than the specified distance.

First claim

Opening claim text (preview).

What is claimed is: 1. A system configured for news event organization, the system comprising: a database comprising past news events; hardware processing circuitry coupled to the database, the hardware processing circuitry to: encode a news event based on named entities, actors, and actions mentioned in the news event; calculate a locality sensitive hash (LSH) key on the news event encoding; compare the calculated LSH key to a plurality of LSH keys of respective stories, wherein each story of the respective stories comprises one or more associated news events that include LSH keys that are within a specified distance from each other; remove another news event corresponding to a same LSH key as the news event; associate the news event with a story of the respective stories that includes an LSH key that has a smallest distance from the LSH key of the received news event if the smallest distance is less than the specified distance; and a user interface to provide a view of the storyline of the associated story the storyline including one or more past news events and the news event. 2. The system of claim 1 , wherein the processing circuitry is to create a new story including the news event if the distance is greater than the specified distance. 3. The system of claim 1 , wherein the processing circuitry is to, in response to the associating the news event with the story, chain the news event with other news events of the story. 4. The system of claim 3 , wherein the processing circuitry is to compare the news event to all other news events of the associated story that include a time parameter that is within a specified time of a time parameter of the news event, wherein the time parameter corresponds to a date the news event was reported. 5. The system of claim 4 , wherein the processing circuitry is to calculate a smoothness between the news event and each of the news events of the associated story and place the news event in a location in the story associated with the maximum calculated smoothness. 6. The system of claim 4 , wherein the processing circuitry is to calculate a coherence between the news event and each of the news events of the associated story and place the news event in a location in the story associated with the maximum calculated coherence. 7. The system of claim 1 , wherein the processing circuitry is to calculate a distance between an LSH key of the news event and an LSH key of the story includes the processing circuitry to determine a Hamming distance between the LSH keys. 8. A method for news event organization, the method comprising: encoding, by processing circuitry, a news event based on named entities, actors, and actions mentioned in the news event; calculating a locality sensitive hash (LSH) key on the news event encoding; comparing the calculated LSH key to a plurality of LSH keys of respective stories, wherein each story of the respective stories comprises one or more associated news events that include LSH keys that are within a specified distance from each other; removing another news event that has a same LSH key as the news event; associating the news event with a story of the respective stories that includes an LSH key that has a smallest distance from the LSH key of the received news event and is less than the specified distance; and providing, by a user interface, a view of a storyline of the associated story the storyline including one or more past news events of the associated story and the news event. 9. The method of claim 8 , further comprising creating a new story including the news event if the distance is greater than the specified distance. 10. The method of claim 8 , further comprising, in response to associating the news event with the story, chaining the news event with other news events of the story. 11. The method of claim 10 , wherein chaining includes comparing the news event to all other news events of the associated story that include a time parameter that is within a specified time of a time parameter of the news event, wherein the time parameter corresponds to a date the news event was reported. 12. The method of claim 11 , wherein comparing the news event to all other news events of the associated story includes calculating a smoothness between the news event and each of the news events of the story and placing the news event in a location in the story associated with the maximum calculated smoothness. 13. The method of claim 11 , wherein comparing the news event to all other news events of the associated story includes calculating a coherence between the news event and each of the news events of the story and placing the news event in a location in the story associated with the maximum calculated coherence. 14. The method of claim 8 , wherein calculating a distance between an LSH key of the news event and an LSH key of the story includes determine a Hamming distance between the LSH keys. 15. A non-transitory computer readable storage device including instructions that, when executed by a machine, configure the machine to perform operations for news event organization, the operations comprising: encode a news event based on named entities, actors, and actions mentioned in the news event; calculate a locality sensitive hash (LSH) key on the news event encoding; compare the calculated LSH key to a plurality of LSH keys of respective stories, wherein each story of the respective stories comprises one or more associated news events that include LSH keys that are within a specified distance from each other; remove another news event that has a same corresponding LSH key as the news event; associate the news event with a story of the respective stories that includes an LSH key that has a smallest distance from the LSH key of the received news event and is less than the specified distance; and provide signals that cause a user interface to provide a view of a storyline of the associated story the storyline including one or more past news events of the associated story and the news event. 16. The storage device of claim 15 , further comprising instructions, which when executed by the machine, configure the machine to create a new story including the news event if the distance is greater than the specified distance. 17. The storage device of claim 15 , further comprising instructions, which when executed by the machine, configure the machine to, in response to associating the news event with the story, chain the news event with other news events of the story. 18. The storage device of claim 17 , wherein the instructions for chaining include instructions, which when executed by the machine, configured the machine to compare the news event to all other news events of the associated story that include a time parameter that is within a specified time of a time parameter of the news event, wherein the time parameter corresponds to a date the news event was reported. 19. The storage device of claim 18 , wherein the instructions for comparing the news event to all other news events of the associated story include instructions, which when executed by the machine, configure the machine to calculate a smoothness and coherence between the news event and each of the news events of the story and place the news event in a location in the story associated with the maximum calculated smoothness or coherence. 20. The storage device of claim 16 , further comprising wherein the instructions for calculating a distance between the LSH key of the news event and the LSH key of

Assignees

Inventors

Classifications

  • Spatial or temporal dependent retrieval, e.g. spatiotemporal queries · CPC title

  • Physics · mapped topic

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US9817908B2 cover?
Generally discussed herein are systems, apparatuses, and methods for organizing and/or searching news events. In one or more embodiments, a method can include encoding a news event based on named entities, actors, and actions mentioned in the news event, calculating a locality sensitive hash (LSH) key on the news event encoding, comparing the calculated LSH key to a plurality of LSH keys of res…
Who is the assignee on this patent?
Raytheon Co, Penn State Res Found
What technology area does this patent fall under?
Primary CPC classification G06F16/9537. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Nov 14 2017 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 8 related publications on this page (citations in our corpus or others sharing the same primary CPC).