US6842877B2
Expired / Lapsed
US
⏱️ 0.0 years remaining
Contextual responses based on automated learning techniques
Assignee: Microsoft Technology Licensing LLC
•
Filing: 2001-04-02
•
Granted: 2005-01-11
•
Expires: 2021-04-02
Abstract
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.
Inventors
- 👤 James O. Robarts
- 👤 Eric L. Matteson
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-24 16:15
CPC Classifications
G; G06; G06F; G06F1/00; G06F1/16; G06F1/1613; G06F1/163; G06F16/00; G06F16/40; G06F21/00; G06F21/60; G06F21/606; G06F21/62; G06F21/6218; G06F21/6245; G06F3/00; G06F3/01; G06F3/011; G06F3/016; G06N; G06N20/00; G06N3/00; G06N3/004; G06F2221/00; G06F2221/21; G06F2221/2149
Claims Analysis
Total Claims: 53
Claim 1
Independent Claim
276 words
A method in a wearable computing device for improving automated responses to a current context of a user of the wearable computing device based on automated learning techniques, the current context of the user being represented by a plurality of context attributes that each model an aspect of the context, multiple defined contextual situations each specifying values for at least one of the context attributes, multiple automated responses being associated with the defined contextual situations, the method comprising: repeatedly, receiving an indication of current context information about the user that includes current values for each of the plurality of context attributes; determining one of the defined contextual situations that matches the indicated current context information in such a manner that the included current values of the indicated current context information include the values for the context attributes specified by the one defined contextual situation; automatically providing to the user one of the automated responses that is associated with the one defined contextual situation; receiving an indication from the user of an alternate automated response to be provided; and storing an indication of a possible relationship between the indicated current context information and the alternate automated response; automatically detecting a relationship between an identified contextual situation and one of the alternate automated response based on analysis of repeated patterns in the stored indications in which that alternate automated response is indicated by the user; and creating an association between the identified contextual situation and the one alternate automated response, so that when the identified contextual situation is determined in the future to match current context information, the one alternate automated response can be provided to the user.
Claim 2
Independent Claim
276 words
A method in a wearable computing device for improving automated responses to a current context of a user of the wearable computing device based on automated learning techniques, the current context of the user being represented by a plurality of context attributes that each model an aspect of the context, multiple defined contextual situations each specifying values for at least one of the context attributes, multiple automated responses being associated with the defined contextual situations, the method comprising: repeatedly, receiving an indication of current context information about the user that includes current values for each of the plurality of context attributes; determining one of the defined contextual situations that matches the indicated current context information in such a manner that the included current values of the indicated current context information include the values for the context attributes specified by the one defined contextual situation; automatically providing to the user one of the automated responses that is associated with the one defined contextual situation; receiving an indication from the user of an alternate automated response to be provided; and storing an indication of a possible relationship between the indicated current context information and the alternate automated response; automatically detecting a relationship between an identified contextual situation and one of the alternate automated response based on analysis of repeated patterns in the stored indications in which that alternate automated response is indicated by the user; and creating an association between the identified contextual situation and the one alternate automated response, so that when the identified contextual situation is determined in the future to match current context information, the one alternate automated response can be provided to the user.
Claim 3
Dependent Claim
28 words
The method of claim 1 including, before the creating of the association between the identified contextual situation and the one alternate automated response, verifying appropriateness of the association.
Claim 4
Dependent Claim
25 words
The method of claim 2 wherein the verifying of the appropriateness of the association includes receiving explicit authorization from the user to create the association.
Claim 5
Dependent Claim
67 words
The method of claim 3 wherein the receiving of the explicit authorization from the user includes: suggesting the association between the identified contextual situation and the one alternate automated response to the user; receiving from the user a request to explain the suggested association; automatically explaining the suggested association by generating a response based on the analyzed repeated patterns; and receiving from the user the explicit authorization.
Claim 6
Dependent Claim
20 words
The method of claim 2 wherein the verifying of the appropriateness of the association is performed automatically without user intervention.
Claim 7
Dependent Claim
34 words
The method of claim 2 wherein the verifying of the appropriateness of the association includes determining that providing the one alternate automated response when the user is in the identified contextual situation is safe.
Claim 8
Dependent Claim
93 words
The method of claim 1 including, after the creating of the association: receiving an indication of current context information about the user that includes current values for each of the plurality of context attributes; determining that the identified contextual situation matches the indicated current context information in such a manner that the included current values of the indicated current context information include the values for the context attributes specified by the one identified contextual situation; and automatically providing to the user the alternate automated response that is associated with the identified contextual situation.
Claim 9
Dependent Claim
29 words
The method of claim 1 including, after each of the received indications from the user to provide an alternate automated response, providing that alternate automated response to the user.
Claim 10
Dependent Claim
36 words
The method of claim 1 wherein at least some of the automated responses include presenting information to the user that is appropriate based on the one defined contextual situation determined to match the current context information.
Claim 11
Dependent Claim
63 words
The method of claim 1 including, after one of the automatic providings to the user of one of the automated responses associated with one of the defined contextual situations: receiving from the user a request to explain the providing of the automated response; and explaining the provided response based on the association between that one automated response and that one defined contextual situation.
Claim 12
Dependent Claim
23 words
The method of claim 1 wherein the analysis of the repeated patterns in the stored indications is based on an automated learning algorithm.
Claim 13
Dependent Claim
29 words
The method of claim 1 wherein the identified contextual situation is not a defined contextual situation, and wherein the creating of the association includes defining the identified contextual situation.
Claim 14
Dependent Claim
48 words
The method of claim 1 wherein before the creating of the association the identified contextual situation is a defined contextual situation having an existing association with an automated response distinct from the one alternate automated response, and wherein the creating of the association includes modifying the existing association.
Claim 15
Dependent Claim
43 words
The method of claim 1 wherein the identified contextual situation represents an explicit context rules that matches current context information, and wherein the alternate automated response includes processing the matching current context information in order to provide additional context information about the user.
Claim 16
Dependent Claim
24 words
The method of claim 1 wherein the alternate automated response includes presenting information to the user that is appropriate to the identified contextual situation.
Claim 17
Dependent Claim
24 words
The method of claim 1 wherein the alternate automated response includes presenting functionality to the user that is appropriate to the identified contextual situation.
Claim 18
Dependent Claim
28 words
The method of claim 1 wherein the alternate automated response includes presenting a graphical user interface control to the user that is appropriate to the identified contextual situation.
Claim 19
Dependent Claim
23 words
The method of claim 1 wherein the alternate automated response includes automatically performing at least some of the steps in a multi-step task.
Claim 20
Dependent Claim
19 words
The method of claim 1 wherein the alternate automated response includes prompting the user to take an indicated change.
Claim 21
Dependent Claim
18 words
The method of claim 1 wherein the alternate automated response includes notifying the user of a pre-defined occurrence.
Claim 22
Dependent Claim
23 words
The method of claim 1 wherein at least one of the context attributes represents information about a user of the wearable computing device.
Claim 23
Dependent Claim
17 words
The method of claim 21 wherein the represented information reflects a modeled mental state of the user.
Claim 24
Dependent Claim
20 words
The method of claim 1 wherein at least one of the context attributes represents information about the wearable computing device.
Claim 25
Dependent Claim
19 words
The method of claim 1 wherein at least one of the context attributes represents information about a physical environment.
Claim 26
Dependent Claim
26 words
The method of claim 1 wherein at least one of the context attributes represents information about a cyber-environment of a user of the wearable computing device.
Claim 27
Dependent Claim
228 words
A computer-readable medium whose contents cause a wearable computing device to improve automated responses to a current context for a user of the wearable computing device based on automated learning, the current context being represented by a plurality of context attributes that each model an aspect of the context, multiple defined contextual situations each specifying values for at least one of the context attributes, multiple automated responses being associated with the defined contextual situations, by performing a method comprising: repeatedly, receiving an indication of current context information that includes current values for each of at least some of the plurality of context attributes; determining one of the defined contextual situations that matches the indicated current context information; automatically providing one of the automated response that is associated with the one defined contextual situation; receiving an indication from the user of an alternate automated response to be provided; and storing an indication of the indicated current context information and the alternate automated response; automatically detecting a relationship between an identified contextual situation and one of the alternate automated responses based on analysis of patterns of that alternate automated response being indicated by the user; and creating an association between the identified contextual situation and the one alternate automated response so that the one alternate automated response can in the future be provided to the user for that contextual situation.
Claim 28
Dependent Claim
228 words
A computer-readable medium whose contents cause a wearable computing device to improve automated responses to a current context for a user of the wearable computing device based on automated learning, the current context being represented by a plurality of context attributes that each model an aspect of the context, multiple defined contextual situations each specifying values for at least one of the context attributes, multiple automated responses being associated with the defined contextual situations, by performing a method comprising: repeatedly, receiving an indication of current context information that includes current values for each of at least some of the plurality of context attributes; determining one of the defined contextual situations that matches the indicated current context information; automatically providing one of the automated response that is associated with the one defined contextual situation; receiving an indication from the user of an alternate automated response to be provided; and storing an indication of the indicated current context information and the alternate automated response; automatically detecting a relationship between an identified contextual situation and one of the alternate automated responses based on analysis of patterns of that alternate automated response being indicated by the user; and creating an association between the identified contextual situation and the one alternate automated response so that the one alternate automated response can in the future be provided to the user for that contextual situation.
Claim 29
Dependent Claim
29 words
The computer-readable medium of claim 26 including, before the creating of the association between the identified contextual situation and the one alternate automated response, verifying appropriateness of the association.
Claim 30
Dependent Claim
34 words
The computer-readable medium of claim 26 including, after the creating of the association, detecting the identified contextual situation and in response providing the alternate automated response that is associated with the identified contextual situation.
Claim 31
Dependent Claim
30 words
The computer-readable medium of claim 26 wherein at least some of the automated responses each include presenting information to the user that is appropriate based on a current contextual situation.
Claim 32
Dependent Claim
52 words
The computer-readable medium of claim 26 including, after one of the automatic providings to the user of one of the automated responses associated with one of the defined contextual situations, explaining to the user the provided response based on the association between that one automated response and that one defined contextual situation.
Claim 33
Dependent Claim
19 words
The computer-readable medium of claim 26 wherein the analysis of the patterns is based on an automated learning algorithm.
Claim 34
Dependent Claim
30 words
The computer-readable medium of claim 26 wherein the identified contextual situation is not a defined contextual situation, and wherein the creating of the association includes defining the identified contextual situation.
Claim 35
Dependent Claim
24 words
The computer-readable medium of claim 26 wherein at least one of the context attributes represents information about a user of the wearable computing device.
Claim 36
Dependent Claim
18 words
The computer-readable medium of claim 33 wherein the represented information reflects a modeled mental state of the user.
Claim 37
Dependent Claim
21 words
The computer-readable medium of claim 26 wherein at least one of the context attributes represents information about the wearable computing device.
Claim 38
Dependent Claim
20 words
The computer-readable medium of claim 26 wherein at least one of the context attributes represents information about a physical environment.
Claim 39
Dependent Claim
27 words
The computer-readable medium of claim 26 wherein at least one of the context attributes represents information about a cyber-environment of a user of the wearable computing device.
Claim 40
Dependent Claim
17 words
The computer-readable medium of claim 26 wherein the computer-readable medium is a memory of a computing device.
Claim 41
Dependent Claim
23 words
The computer-readable medium of claim 26 wherein the computer-readable medium is a data transmission medium transmitting a generated data signal containing the contents.
Claim 42
Dependent Claim
22 words
The computer-readable medium of claim 26 wherein the contents are instructions that when executed cause the computing device to perform the method.
Claim 43
Dependent Claim
219 words
A wearable computing system configured to improve automated responses to a current context for a user, the current context being represented by a plurality of context attributes that each model an aspect of the context, multiple defined contextual situations each specifying values for at least one of the context attributes, multiple automated responses being associated with the defined contextual situations, comprising: a first component that is configured to repeatedly, receive an indication of current context information that includes current values for each of at least some of the plurality of context attributes, determine one of the defined contextual situations that matches the indicated current context information, determine one of the automated responses that is associated with the one defined contextual situation, receive an indication from the user of an alternate automated response, and store an indication of the indicated current context information and the alternate automated response; and a second component that is configured to automatically detect a relationship between an identified contextual situation and one of the alternate automated responses based on that alternate automated response being previously indicated by the user and to create an association between the identified contextual situation and the one alternate automated response so that the one alternate automated response can in the future be provided to the user for that contextual situation.
Claim 44
Dependent Claim
219 words
A wearable computing system configured to improve automated responses to a current context for a user, the current context being represented by a plurality of context attributes that each model an aspect of the context, multiple defined contextual situations each specifying values for at least one of the context attributes, multiple automated responses being associated with the defined contextual situations, comprising: a first component that is configured to repeatedly, receive an indication of current context information that includes current values for each of at least some of the plurality of context attributes, determine one of the defined contextual situations that matches the indicated current context information, determine one of the automated responses that is associated with the one defined contextual situation, receive an indication from the user of an alternate automated response, and store an indication of the indicated current context information and the alternate automated response; and a second component that is configured to automatically detect a relationship between an identified contextual situation and one of the alternate automated responses based on that alternate automated response being previously indicated by the user and to create an association between the identified contextual situation and the one alternate automated response so that the one alternate automated response can in the future be provided to the user for that contextual situation.
Claim 45
Dependent Claim
29 words
The computing system of claim 41 including, before the creating of the association between the identified contextual situation and the one alternate automated response, verifying appropriateness of the association.
Claim 46
Dependent Claim
34 words
The computing system of claim 41 including, after the creating of the association, detecting the identified contextual situation and in response providing the alternate automated response that is associated with the identified contextual situation.
Claim 47
Dependent Claim
30 words
The computing system of claim 41 wherein at least some of the automated responses each include presenting information to the user that is appropriate based on a current contextual situation.
Claim 48
Dependent Claim
52 words
The computing system of claim 41 including after one of the automatic providings to the user of one of the automated responses associated with one of the defined contextual situations, explaining to the user the provided response based on the association between that one automated response and that one defined contexual situation.
Claim 49
Dependent Claim
20 words
The computing system of claim 41 wherein the automatic detecting of the relationship is based on an automated learning algorithm.
Claim 50
Dependent Claim
30 words
The computing system of claim 41 wherein the identified contextual situation is not a defined contextual situation, and wherein the creating of the association includes defining the identified contextual situation.
Claim 51
Dependent Claim
41 words
The computing system of claim 41 wherein the computing system includes a memory configured to store at least portions of the first and second components and includes a processing unit configured to execute code associated with the first and second components.
Claim 52
Dependent Claim
212 words
A wearable computing system configured to improve automated responses to a current context for a user, the current context being represent by a plurality of context attributes that each model an aspect of the context, multiple defined contextual situations each specifying values for at least one of the context attributes, multiple automated responses being associated with the defined contextual situations, comprising: first means for repeatedly receiving an indication of current context information that includes current values for each of at least some of the plurality of context attributes, determining one of the defined contextual situations that matches the indicated current context information, determining one of the automated responses that is associated with the one defined contextual situation, receiving an indication from the user of an alternate automated response, and storing an indication of the indicated current context information and the alternate automated response; second means for automatically detecting a relationship between an identified contextual situation and one of the alternate automated responses based on that alternate automated response being previously indicated by the user; and third means for creating an association between the identified contextual situation and the one alternate automated response so that the one alternate automated response can in the future be provided to the user for that contextual situation.
Claim 53
Dependent Claim
212 words
A wearable computing system configured to improve automated responses to a current context for a user, the current context being represent by a plurality of context attributes that each model an aspect of the context, multiple defined contextual situations each specifying values for at least one of the context attributes, multiple automated responses being associated with the defined contextual situations, comprising: first means for repeatedly receiving an indication of current context information that includes current values for each of at least some of the plurality of context attributes, determining one of the defined contextual situations that matches the indicated current context information, determining one of the automated responses that is associated with the one defined contextual situation, receiving an indication from the user of an alternate automated response, and storing an indication of the indicated current context information and the alternate automated response; second means for automatically detecting a relationship between an identified contextual situation and one of the alternate automated responses based on that alternate automated response being previously indicated by the user; and third means for creating an association between the identified contextual situation and the one alternate automated response so that the one alternate automated response can in the future be provided to the user for that contextual situation.
References Cited (Backward Citations)
US5227614A
Cited
US4916441A
Cited
US5201034A
Cited
WO1990008361A1
Cited
US5032083A
Cited
US5214757A
Cited
US5852814A
Cited
US5781913A
Cited
US5568645A
Cited
US5208449A
Cited
US5751260A
Cited
JPH05260188A
Cited
US6108197A
Cited
US5535323A
Cited
US5335276A
Cited
US5995956A
Cited
US5416730A
Cited
US5555376A
Cited
US5603054A
Cited
US5611050A
Cited
US5812865A
Cited
US5544321A
Cited
US5493692A
Cited
US6064943A
Cited
US5470233A
Cited
EP0823813A2
Cited
US5646629A
Cited
US5559520A
Cited
US5601435A
Cited
US5959611A
Cited
US5642303A
Cited
US5873070A
Cited
WO1997003434A1
Cited
JPH0991112A
Cited
US5878274A
Cited
US6127990A
Cited
US5726660A
Cited
US5948041A
Cited
US5910799A
Cited
US5790974A
Cited
US6047301A
Cited
US5719744A
Cited
US5938721A
Cited
US5902347A
Cited
US5798733A
Cited
US6023729A
Cited
US5991687A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2008-01-11 | 2008-07-12 | 2009-01-11 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2012-01-11 | 2012-07-12 | 2013-01-11 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2016-01-11 | 2016-07-12 | 2017-01-11 | $7700.00 | Window Closed / Lapsed |