Machine learning collaboration techniques
US-2024420212-A1 · Dec 19, 2024 · US
US10152740B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10152740-B2 |
| Application number | US-201615234104-A |
| Country | US |
| Kind code | B2 |
| Filing date | Aug 11, 2016 |
| Priority date | Aug 11, 2016 |
| Publication date | Dec 11, 2018 |
| Grant date | Dec 11, 2018 |
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.
Methods, systems, and computer program products for generating recommendations. In response to receiving a request, the system generates a plurality of suggested recommendations for both a first bound and a second bound of a trip. The system stores the suggested recommendations corresponding to the first bound and the second bound in a memory, where the suggested recommendations corresponding to the second bound coincide to a subset of the suggested recommendations corresponding to the first bound published for display. The system publishes the suggested recommendations corresponding to the first bound for display to a user. In response to receiving an input that indicates a selected recommendation for the first bound, the system determines whether the selected recommendation is one of the subset of the suggested recommendations corresponding to the first bound.
Opening claim text (preview).
What is claimed is: 1. A system comprising: at least one processor; and a memory coupled to the one or more processors, the memory storing data comprising program code that, when executed by the one or more processors, causes the system to: receive a request for a trip including a first departure date for a first bound of the trip and a second departure date for a second bound of the trip; in response to receiving the request, generate a plurality of suggested recommendations corresponding to both the first bound and the second bound of the trip; store the suggested recommendations corresponding to the first bound and the second bound in a memory, wherein the suggested recommendations corresponding to the second bound coincide to a subset of the suggested recommendations corresponding to the first bound published for display; publish the suggested recommendations corresponding to the first bound with departure times of travel conveyances servicing the first bound on the first departure date for display to a user; in response to receiving an input that indicates a selected recommendation for the first bound, determine whether the selected recommendation is one of the subset of the suggested recommendations corresponding to the first bound, the input identifying a specific departure time on the first departure date of a travel conveyance published with the selected recommendation for the first bound; in response to the selected recommendation being one of the recommendations of the subset of recommendations, retrieve the suggested recommendations corresponding to the second bound from the memory; and publish the suggested recommendations corresponding to the second bound for display to the user. 2. The system of claim 1 wherein the program code, when executed by the one or more processors, further causes the system to: in response to the selected recommendation being different than one of the recommendations of the subset of recommendations, calculate an alternative set of recommendations for the second bound that correspond to the selected recommendation for the first bound; and publish the alternative set of recommendations for the second bound for display to the user. 3. The system of claim 1 wherein the subset of the suggested recommendations corresponding to the first bound is based on a percentage of instances when the suggested recommendations corresponding to the second bound from the memory are published instantaneously in response to receiving the input that indicates the selected recommendation for the first bound. 4. The system of claim 1 wherein the program code, when executed by the one or more processors, further causes the system to: determine a quantity, wherein the quantity represents a number of the recommendations corresponding to the second bound that need to be determined such that the suggested recommendations corresponding to the second bound from the memory are published instantaneously in response to receiving the input that indicates a selected recommendation for the first bound. 5. The system of claim 1 wherein the program code, when executed by the one or more processors, further causes the system to: store the suggested recommendations corresponding to the first bound and the second bound to the memory for a predetermined amount of time, wherein the predetermined amount of time is adjustable. 6. The system of claim 5 wherein the predetermined amount of time is based on an average time of a conversation with the user on a website and a volatility of availability data for the trip. 7. The system of claim 1 wherein the first bound an outbound portion of the trip, the second bound is an inbound portion of the trip, and the trip is a round-way trip. 8. The system of claim 1 wherein the program code, when executed by the one or more processors, further causes the system to: in response to receiving another input that indicates another selected recommendation for the second bound, update the suggested recommendations corresponding to the first bound that are published for display to the user. 9. The system of claim 1 wherein the selected recommendation for the first bound is saved to the memory as a specific key. 10. A method of generating recommendations for a trip, the method comprising: receiving, by a computer, a request for the trip including a first departure date for a first bound of the trip and a second departure date for a second bound of the trip; in response to receiving the request, generating, by the computer, a plurality of suggested recommendations for both the first bound and the second bound of the trip; storing the suggested recommendations corresponding to the first bound and the second bound in a memory of the computer, wherein the suggested recommendations corresponding to the second bound coincide to a subset of the suggested recommendations corresponding to the first bound published for display; publishing the suggested recommendations corresponding to the first bound with departure times of travel conveyances servicing the first bound on the first departure date for display to a user; in response to receiving an input that indicates a selected recommendation for the first bound, determining, by the computer, whether the selected recommendation is one of the subset of the suggested recommendations corresponding to the first bound, the input identifying a specific departure time on the first departure date of a travel conveyance published with the selected recommendation for the first bound; in response to the selected recommendation being one of the recommendations of the subset of recommendations, retrieving the suggested recommendations corresponding to the second bound from the memory of the computer; and publishing the suggested recommendations corresponding to the second bound for display to the user. 11. The method of claim 10 further comprising: in response to the selected recommendation being different than one of the recommendations of the subset of recommendations, calculating, by the computer, an alternative set of recommendations for the second bound of the trip that correspond to the selected recommendation for the first bound; and publishing the alternative set of recommendations for the second bound of the trip for display to the user. 12. The method of claim 10 wherein the subset of the suggested recommendations corresponding to the first bound is based on a percentage of instances when the suggested recommendations corresponding to the second bound from the memory of the computer are published instantaneously in response to receiving the input that indicates the selected recommendation for the first bound. 13. The method of claim 12 further comprising: determining a quantity by the computer, wherein the quantity represents a number of the recommendations corresponding to the second bound that need to be determined by the computer such that the suggested recommendations corresponding to the second bound from the memory of the computer are published instantaneously in response to receiving the input that indicates a selected recommendation for the first bound. 14. The method of claim 10 further comprising: storing the suggested recommendations corresponding to the first bound and the second bound to the memory of the computer for a predetermined amount of time, wherein the predetermined amount of time is adjustable. 15. The method of claim 14 wherein the predetermined amount of time is based on an average time of a conversation with the user on a web site and a volatility of availability data for the trip.
Recommending goods or services · CPC title
Travel agencies · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.