Feature engineering with question generation
US-2024079000-A1 · Mar 7, 2024 · US
US9495442B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9495442-B2 |
| Application number | US-201213440865-A |
| Country | US |
| Kind code | B2 |
| Filing date | Apr 5, 2012 |
| Priority date | Oct 22, 2009 |
| Publication date | Nov 15, 2016 |
| Grant date | Nov 15, 2016 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Systems and methods are disclosed to automatically publish data items associated with a news event. In one embodiment, a method comprises determining, using one or more processors, an event of a plurality of events as associated with a heightened user interest, identifying one or more listings from a plurality of listings as matching the event associated with the heightened user interest, and presenting a visual representation of a relationship between the event and the one or more listings such that the one or more listings are displayed as visually related to the event.
Opening claim text (preview).
What is claimed is: 1. A method comprising: creating a search query category data structure, the search query category data structure containing a plurality of different search queries, each different search query in the search query category data structure corresponding to a single search query category, the search query category data structure further containing monitoring data comprising baseline frequency information including a log of past searches for the plurality of different search queries in the search query category data structure, the log of past searches indicating a frequency of search for each of the plurality of different search queries in the search query category data structure, the frequencies indicating a baseline user interest in the search query category; receiving a search query from a user; performing a search using the search query, the search resulting in a plurality of search results; determining that the search query from the user matches a search query in the plurality of different search queries in the search query category data structure; determining, using one or more processors, a news event of a plurality of news events, the news event corresponding to a recent increase in user interest above a baseline user interest for search queries, other than the search query from the user, in the search query category data structure, based on the monitoring data; storing an identification of the news event in an event database; identifying a subset of the search results as containing one or more listings that match the news event associated with the user interest by comparing keywords in each of the search results to news event identifications in the news event database; and presenting, to the user, a visual representation of a relationship between the news event and the one or more listings such that the one or more listings are displayed as visually related to the news event. 2. The method of claim 1 , wherein the recent increase in user interest is measured based on a number of search requests for the news event within a predetermined period of time. 3. The method of claim 1 , wherein the recent increase in user interest is measured based on an indication of a change in a search request frequency associated with one or more search queries. 4. The method of claim 3 , wherein the change in the search request frequency is identified based on monitoring search query requests over a specified period of time. 5. The method of claim 1 , wherein at least one listing of the one or more listings corresponds to an item for sale. 6. The method of claim 5 , wherein the at least one listing comprises one or more item listings received from a network-based marketplace. 7. The method of claim 1 , wherein at least one listing of the one or more listings corresponds to news. 8. The method of claim 7 , wherein the at least one listing comprises one or more news listings received from a news service provider. 9. The method of claim 1 , wherein at least one listing of the one or more listings corresponds to at least one of multimedia content or stock. 10. The method of claim 1 , wherein the news event comprises a first news event and a second news event, wherein the presenting comprises displaying a first subset of the one or more listings in relation with the first news event and displaying a second subset of the one or more listings in relation with the second news event. 11. The method of claim 1 , wherein at least one listing of the one or more listings corresponds to an item, wherein the presenting comprises displaying at least one of a link to an item page of the item, a description about the item, a picture of the item, an advertisement for the item, an interface to purchase the item or any other information associated with the item. 12. The method of claim 1 , wherein the presenting comprises displaying a name of the news event and additional information associated with the news event. 13. A system comprising: a memory to store a plurality of listings; an event database; and one or more processors to execute an event-listing matching module, the event-listing matching module configured to: create a search query category data structure, the search query category data structure containing a plurality of different search queries, each different search query in the search query category data structure corresponding to a single search query category, the search query category data structure further containing monitoring data comprising baseline frequency information including a log of past searches for the plurality of different search queries in the search query category data structure, the log of past searches indicating a frequency of search for each of the plurality of different search queries in the search query category data structure, the frequencies indicating a baseline user interest in the search query category; receive a search query from a user; perform a search using the search query, the search resulting in a plurality of search results; determine that the search query from the user matches a search query in the plurality of different search queries in the search query category data structure; determine a news event of a plurality of events, the news event corresponding to a recent increase in user interest above a baseline user interest for search queries, other than the search query from the user, in the search query category data structure, based on the monitoring data; store an identification of the news event in the event database; identify a subset of the search results as containing one or more listings that match the news event associated with the user interest by comparing keywords in each of the search results to news event identifications in the news event database; and present, to the user, a visual representation of a relationship between the news event and the one or more listings such that the one or more listings are displayed as visually related to the news event. 14. The system of claim 13 , wherein the event-listing matching module is configured to: query a third party event provider to determine the news event associated with the user interest. 15. The system of claim 14 , the third party event provider comprises a news service provider. 16. The system of claim 13 , wherein the event-listing matching module is configured to: compare a first search request frequency associated with the news event with a second search request frequency associated with the event to identify a change in the search request frequency. 17. The system of claim 16 , wherein the first search request frequency comprises a baseline frequency reflecting an average number of search queries detected during a first time interval and wherein the second search request frequency comprises an absolute frequency reflecting an actual number of search queries detected during a second time interval. 18. The system of claim 16 , wherein the first search request frequency is associated with a first set of search queries and the second search request frequency is associated with a second set of search queries, wherein the first and second sets of queries are associated with a same search category. 19. The system of claim 13 , wherein the news event comprises a first news event and a second news event, wherein the event-listing matching module is configured to: display a first subset of the one or more listings in relation with the first news event and display a second subset of the one or more listings in relation with
using document space presentation or visualization, e.g. category, hierarchy or range presentation and selection · CPC title
Selection or weighting of terms from queries, including natural language queries · CPC title
Browsing; Visualisation therefor · CPC title
Recommending goods or services · CPC title
Physics · mapped topic
Related publications grouped by family.
Answers are generated from the same data shown on this page.