Recommendations with consequences exploration
AssigneeAirbnb, Inc.
InventorsElizabeth Daly, Oznur Alkan
Life of this patent
Estimating the term…
Abstract
Disclosed are ways to generate and present recommendations which provide a user with the ability to explore the follow-on consequences of accepting the recommendations. In some aspects, a method includes receiving a first user input including a recommendation topic, presenting, via a display, an exploration structure including a node corresponding to the recommendation topic, receiving data corresponding to the node from a knowledge repository, analyzing the received data to determine at least one follow-on recommendation based on the node, and presenting each determined follow-on recommendation in the exploration structure as a child node of the node corresponding to the recommendation topic.
Claims15
A method implemented by at least one processor comprising hardware, the method comprising:
- receiving a user input including a recommendation topic;
- presenting, via a display interface, an exploration structure including a node corresponding to the recommendation topic;
- receiving data corresponding to the node from a knowledge repository;
- analyzing the received data to determine at least one follow-on recommendation that is positively correlated to the node, the follow-on recommendation being a follow-on action to achieve a specified outcome, wherein determining that the at least one follow-on recommendation is positively correlated to the node comprises:
- accessing a set of potential follow-on actions;
- for each respective potential follow-on action, determining a number of users that previously performed the respective potential follow-on action and achieved the specified outcome;
- and
- determining whether each respective potential follow-on action is positively correlated to the node based on a comparison of the number of users that previously performed the respective potential follow-on action to a threshold number;
- and
- presenting, via the display interface;
- each determined follow-on action recommendation in the exploration structure as additional child nodes of the node corresponding to the recommendation topic.
A system comprising:
- one or more computer processors;
- and
- one or more computer-readable mediums storing instructions that, when executed by e one or more computer processors, cause the system to perform operations comprising:
- receiving a user input including a recommendation topic;
- presenting, via a display interface, an exploration structure including a node corresponding to the recommendation topic;
- receiving data corresponding to the node from a knowledge repository;
- analyzing the received data to determine at least one follow-on recommendation that is positively correlated to the node, the follow-on recommendation being a follow-on action to achieve a specified outcome, wherein determining that the at least one follow-on recommendation is positively correlated to the node comprises:
- accessing a set of potential follow-on actions;
- for each respective potential follow-on action, determining a number of users that previously performed the respective potential follow-on action and achieved the specified outcome;
- and
- determining whether each respective potential follow-on action is positively correlated to the node based on a comparison of the number of users that previously performed the respective potential follow-on action to a threshold number;
- and
- presenting, via the display interface, each determined follow-on action recommendation in the exploration structure as additional child nodes of the node corresponding to the recommendation topic.
A non-transitory computer-readable medium storing instructions that, when executed by one or more computer processors of one or more computing devices, cause the one or more computing devices to perform operations comprising:
- receiving a user input including a recommendation topic;
- presenting, via a display interface, an exploration structure including a node corresponding to the recommendation topic;
- receiving data corresponding to the node from a knowledge repository;
- analyzing the received data to determine at least one follow-on recommendation that is positively correlated to the node, the follow-on recommendation being a follow-on action to achieve a specified outcome, wherein determining that the at least one follow-on recommendation is positively correlated to the node comprises:
- accessing a set of potential follow-on actions;
- for each respective potential follow-on action, determining a number of users that previously performed the respective potential follow-on action and achieved the specified outcome;
- and
- determining whether each respective potential follow-on action is positively correlated to the node based on a comparison of the number of users that previously performed the respective potential follow-on action to a threshold number;
- and
- presenting, via the display interface, each determined follow-on action recommendation in the exploration structure as additional child nodes of the node corresponding to the recommendation topic.
Dependencies are inferred from the claim text.