Contextual responses based on automated learning techniques
First Claim
1. A method in a computing device for improving responses to context information based on automated learning techniques, multiple responses each being associated with a group of context information, the method comprising:
- employing a processor executing computer executable instructions to perform the following acts;
receiving indications of past user actions by at least one user related to each of multiple automatically generated responses and of context information related to each of the multiple responses, the context information includes at least one attribute provided by a sensing device, the at least one attribute includes an attribute value and a timestamp indicating the age of the attribute value;
automatically detecting a relationship between a group of context information and one of the responses based on the received indications and at least one defined theme, wherein the at least one defined theme includes a related set of attributes that reflect a context of a user; and
creating an association between the group of context information and the one response, so that the one response can be provided in the future in response to a context that matches the group of context information.
2 Assignments
0 Petitions
Accused Products
Abstract
Techniques are disclosed for using a combination of explicit and implicit user context modeling techniques to identify and provide appropriate computer actions based on a current context, and to continuously improve the providing of such computer actions. The appropriate computer actions include presentation of appropriate content and functionality. Feedback paths can be used to assist automated machine learning in detecting patterns and generating inferred rules, and improvements from the generated rules can be implemented with or without direct user control. The techniques can be used to enhance software and device functionality, including self-customizing of a model of the user'"'"'s current context or situation, customizing received themes, predicting appropriate content for presentation or retrieval, self-customizing of software user interfaces, simplifying repetitive tasks or situations, and mentoring of the user to promote desired change.
660 Citations
19 Claims
-
1. A method in a computing device for improving responses to context information based on automated learning techniques, multiple responses each being associated with a group of context information, the method comprising:
employing a processor executing computer executable instructions to perform the following acts; receiving indications of past user actions by at least one user related to each of multiple automatically generated responses and of context information related to each of the multiple responses, the context information includes at least one attribute provided by a sensing device, the at least one attribute includes an attribute value and a timestamp indicating the age of the attribute value; automatically detecting a relationship between a group of context information and one of the responses based on the received indications and at least one defined theme, wherein the at least one defined theme includes a related set of attributes that reflect a context of a user; and creating an association between the group of context information and the one response, so that the one response can be provided in the future in response to a context that matches the group of context information. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14)
-
15. A system for improving responses to context information based on automated learning techniques, multiple responses each being associated with a group of context information, comprising:
-
at least one processor configured to execute; a processor; a memory communicatively coupled to the processor, the memory having stored therein computer-executable instructions to implement the system, including; a learning component that receives indications of past user actions by at least one user related to each of multiple automatically generated responses and of context information related to each of the multiple responses, the context information includes at least one attribute, the at least one attribute includes an attribute value and an uncertainty value of the attribute value, wherein the uncertainty value indicates a range of values around the attribute value that the attribute value will likely be within, and the learning component automatically detects a relationship between a group of context information and one of the responses based on the received indications and at least one defined theme, wherein the theme includes a related set of attributes that reflect a context related to a user; and a response modifier component that creates an association between the group of context information and the one response. - View Dependent Claims (16)
-
-
17. A system for improving responses to context information based on automated learning techniques, multiple responses each being associated with a group of context information, comprising:
-
a processor; a memory communicatively coupled to the processor, the memory having stored therein computer-executable instructions to implement the system, including; means for receiving indications of past user actions by at least one user related to each of multiple automatically generated responses and of context information related to each of the multiple responses; at least one processor configured to automatically detect a relationship between a group of context information and one of the responses based on the received indications and an automatically selected one of a plurality of defined themes, wherein a t-he theme includes a related set of attributes that reflect a context of a user;
where each of the plurality of themes is assigned a priority by the at least one user, the automatic selection of one of the plurality of themes is based at least upon priority; andmeans for creating an association between the group of context information and the one response.
-
-
18. A computer-readable storage medium whose contents cause a computing device to improve responses to context information based on automated learning techniques, multiple responses each being associated with a group of context information, by:
employing a processor executing computer executable instructions embodied on the computer readable storage medium to perform the following acts; receiving indications of past user actions by at least one user related to each of multiple automatically generated responses and of context information related to each of the multiple responses, the context information includes a plurality of attributes; automatically detecting a relationship between a group of context information and one of the responses based on the received indications and at least one automatically selected theme from a plurality of defined themes, wherein a defined theme includes a related set of attributes that reflect a context of a user, wherein each attribute of the related set of attributes within the defined theme has an indicator of whether the attribute is required for the defined theme, the selected theme is selected based upon a degree of match between required attributes of the defined theme versus the presence of the required attribute amongst the plurality of attributes included in the context information, the selected theme has the highest degree of match; and creating an association between the group of context information and the one response. - View Dependent Claims (19)
Specification