Back to results
US 12,585,965 B2Granted
Interactive machine-learning framework
AssigneeSap SE
InventorsKrishnan Vijayaraghavan, Sparshad Kasote
Life of this patent
Estimating the term…
Abstract
Systems and methods include receipt, from a machine learning system, of a first output based on a first plurality of activity data associated with a user, presentation of the first output to the user, presentation of the first plurality of activity data to the user, receipt of an instruction from the user to designate a first portion of the first plurality of the activity data as unavailable for generation of output, and, in response to the instruction, designation of the first portion of the first plurality of activity data as unavailable for generation of outputs for the user.
Claims17
A system comprising:
- at least one processing unit;
- and
- a non-transitory machine-readable medium storing program code that, when executed by the at least one processing unit, causes the at least one processing unit to perform operations comprising:
- receiving a request for a recommendation from a user;
- in response to the request, inputting a first plurality of activity data associated with the user to a machine learning system;
- receiving, from the machine learning system and in response to the input first plurality of activity data, a first recommendation associated with the user;
- presenting the first recommendation to the user;
- receiving a first user request to present activity data based on which the first recommendation was generated;
- in response to the first user request, presenting the first plurality of activity data to the user;
- receiving an instruction from the user to remove a first portion of the first plurality of the activity data from the first plurality of activity data presented to the user for the first recommendation;
- receiving a second request for a second recommendation from the user;
- in response to the second request, inputting the first plurality of activity data to the machine learning system;
- receiving, from the machine learning system and in response to the input first plurality of activity data, a second instance of the first recommendation
- presenting the second instance of the first recommendation to the user;
- receiving a second user request to present activity data based on which the second instance of the first recommendation was generated;
- and
- in response to the second user request, presenting the first plurality of activity data and not the first portion of the first plurality of the activity data to the user.
14 more elements
A method comprising:
- receiving a request for a recommendation from a user;
- in response to the request, inputting a first plurality of activity data associated with the user to a machine learning system;
- receiving, from the machine learning system and in response to the input first plurality of activity data, a first recommendation associated with the user;
- presenting the first recommendation to the user;
- receiving a first user request to present activity data based on which the first recommendation was generated;
- in response to the first user request, presenting the first plurality of activity data to the user;
- receiving an instruction from the user to remove a first portion of the first plurality of the activity data from the first plurality of activity data presented to the user for the first recommendation;
- receiving a second request for a second recommendation from the user;
- in response to the second request, inputting the first plurality of activity data to the machine learning system;
- receiving, from the machine learning system and in response to the input first plurality of activity data, a second instance of the first recommendation;
- presenting the second instance of the first recommendation to the user;
- receiving a second user request to present activity data based on which the second instance of the first recommendation was generated;
- and
- in response to the second user request, presenting the first plurality of activity data and not the first portion of the first plurality of the activity data to the user.
11 more elements
A non-transitory medium storing processor-executable program code executable by a processing unit of a computing system to cause the computing system to:
- receive a request for a recommendation from a user;
- in response to the request, input a first plurality of activity data associated with the user to a machine learning system;
- receive, from the machine learning system and in response to the input first plurality of activity data, a first recommendation associated with the user;
- present the first recommendation to the user;
- receive a first user request to present activity data based on which the first recommendation was generated;
- in response to the first user request, present the first plurality of activity data to the user;
- receive an instruction from the user to remove a first portion of the first plurality of the activity data from the first plurality of activity data presented to the user for the first recommendation;
- receive a second request for a second recommendation from the user;
- in response to the second request, input the first plurality of activity data to the machine learning system;
- receive, from the machine learning system and in response to the input first plurality of activity data, a second instance of the first recommendation;
- present the second instance of the first recommendation to the user;
- receive a second user request to present activity data based on which the second instance of the first recommendation was generated;
- and
- in response to the second user request, present the first plurality of activity data and not the first portion of the first plurality of the activity data to the user.
11 more elements
Dependencies are inferred from the claim text.