Patent US6657643B1 successfully refreshed from Google Patents.
US6657643B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Modulating the behavior of an animated character to reflect beliefs inferred about a user's desire for automated services
Assignee: Microsoft Technology Licensing LLC
•
Filing: 1999-05-17
•
Granted: 2003-12-02
•
Expires: 2019-05-17
Abstract
Abstract Modulating the behavior of an agent for directing automated services such as for messaging and scheduling is disclosed. In one embodiment, a computer-implemented method inputs an action probability. The action probability has a location within a region corresponding to an option that in one embodiment can be one of: (1) inaction, (2) automatic action, and (3) engaging the user in a dialog about the user's desire for automated action, followed by action pending receipt of user approval. The method then modulates the behavior of the agent depending on the location of the action probability within the region. In one embodiment, the region in which the action probability is located is divided into two or more sub-regions, such that the behavior of the agent is modulated based on which sub-region in which it lies. In another embodiment, a continuous function is imposed onto the region in which the probability is located, where the function yields a confidence level based on the location of the action probability within the region, such that the behavior of the agent is modulated based on this confidence level.
Inventors
- 👤 Eric Horvitz
- 👤 Andrew W. Jacobs
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-01 09:46
CPC Classifications
G; G06; G06Q; G06Q10/00; G06Q10/10; G06Q10/109; H; H04; H04M; H04M1/00; H04M1/72; H04M1/724; H04M1/72403; H04M1/7243; H04M1/72448; H04M1/72451
Claims Analysis
Total Claims: 46
Claim 1
Independent Claim
124 words
A computer-implemented method comprising: inputting an action probability, the action probability having a location within a region corresponding to an option selected from the group essentially consisting of: (1) inaction, (2) automatic action, and (3) en-aging the user in a dialog about the user's desire for automated action, followed by action pending receipt of user approval: dividing the region into a plurality of sub-regions ordered in increasing confidence levels such that a first sub-region has a minimum confidence level and a last sub-region has a maximum confidence level, the location of the action probability falling within one of the sub-regions; and, modulating the behavior of an automated assistant based on the one of the sub-regions in which the location of the action probability falls.
Claim 2
Dependent Claim
124 words
A computer-implemented method comprising: inputting an action probability, the action probability having a location within a region corresponding to an option selected from the group essentially consisting of: (1) inaction, (2) automatic action, and (3) en-aging the user in a dialog about the user's desire for automated action, followed by action pending receipt of user approval: dividing the region into a plurality of sub-regions ordered in increasing confidence levels such that a first sub-region has a minimum confidence level and a last sub-region has a maximum confidence level, the location of the action probability falling within one of the sub-regions; and, modulating the behavior of an automated assistant based on the one of the sub-regions in which the location of the action probability falls.
Claim 3
Dependent Claim
25 words
The method of claim 1 , wherein the behavior of the automated assistant comprises at least one of: utterances, speech parameters, sizing, gestures, and invasiveness.
Claim 4
Dependent Claim
28 words
The method of claim 1 , wherein the behavior of the automated assistant comprises at least one of: prosody, energy, pause stricture of speech of the automated assistant.
Claim 5
Dependent Claim
25 words
The method of claim 1 , wherein modulating a behavior of an automated assistant comprises modulating the behavior upon user negation in a predetermined manner.
Claim 6
Dependent Claim
14 words
The method of claim 4 , wherein modulating the behavior by making an apology.
Claim 7
Dependent Claim
25 words
The method of claim 1 , wherein modulating a behavior of an automated assistant comprises modulating behavior upon not hearing an utterance from the user.
Claim 8
Dependent Claim
44 words
The method of claim 1 , wherein modulating a behavior of an automated assistant comprises modulating at least one of a group of classes of behaviors consisting essentially of: (1) utterances: (2) gestures and postures: and, (3) parameters regarding variable components of interaction machinery.
Claim 9
Dependent Claim
54 words
The method of claim 1 , wherein modulating the behavior of the automated assistant based on the one of the sub-regions in which the location of the action probability falls comprises determining the behavior consistent with a confidence level of the one of the sub-regions in which the location of the action probability falls.
Claim 10
Dependent Claim
40 words
The method of claim 1 , wherein dividing the region into a plurality of sub-regions comprises dividing the region into two sub-regions comprising the first sub-region having the minimum confidence level and the last sub-region having the maximum confidence level.
Claim 11
Dependent Claim
52 words
The method of claim 1 , wherein modulating a behavior comprises: imposing a continuous junction onto the region, the function yielding a confidence level based on the location of the action probability within the region; modulating the behavior of the automated assistant based on the confidence level yielded by the continuous function.
Claim 12
Dependent Claim
14 words
The method of claim 10 , wherein the continuous function comprises a linear function.
Claim 13
Dependent Claim
15 words
The method of claim 10 , wherein the continuous function comprises the action probability itself.
Claim 14
Dependent Claim
17 words
The method of claim 10 , wherein the continuous function comprises a computed expected utility of action.
Claim 15
Dependent Claim
49 words
The method of claim 1 , wherein modulating a behavior of an automated assistant depending on the location of the action probability within the region comprises simulating the behavior of the automated assistant from a set of behaviors appropriate to the location of the action probability within the region.
Claim 16
Dependent Claim
88 words
A computer-implemented method comprising: using a graphical user interface to receive ail action probability having a location within a region; dividing the region into a plurality of sub-regions ordered in increasing confidence levels such that a first sub-region has a minimum confidence level and a last sub-region has a maximum confidence level, the location of the action probability falling within one of the sub-regions; and, modulating the behavior of the automated assistant based on the one of the sub-regions in which the location of the action probability falls.
Claim 17
Dependent Claim
88 words
A computer-implemented method comprising: using a graphical user interface to receive ail action probability having a location within a region; dividing the region into a plurality of sub-regions ordered in increasing confidence levels such that a first sub-region has a minimum confidence level and a last sub-region has a maximum confidence level, the location of the action probability falling within one of the sub-regions; and, modulating the behavior of the automated assistant based on the one of the sub-regions in which the location of the action probability falls.
Claim 18
Dependent Claim
54 words
The method of claim 15 , wherein modulating the behavior of the automated assistant based on the one of the sub-regions in which the location of the action probability falls comprises determining the behavior consistent with a confidence level of the one of the sub-regions in which the location of the action probability falls.
Claim 19
Dependent Claim
40 words
The method of claim 15 , wherein dividing the region into a plurality of sub-regions comprises dividing the region into two sub-regions comprising the first sub-region having the minimum confidence level and the last sub-region having the maximum confidence level.
Claim 20
Dependent Claim
107 words
A computer-implemented method comprising: using a graphical user interface to receive an action probability having a location within a region; imposing a continuous function onto the region, the function yielding a confidence level based on the location of the action probability within the region; and, dividing the region into a plurality of sub-regions ordered in increasing confidence levels such that a first sub-region has a minimum confidence level and a last sub-region has a maximum confidence level the location of the action probability falling within one of the sub-regions: and, modulating the behavior of the automated assistant based on the confidence level yielded by the continuous function.
Claim 21
Dependent Claim
107 words
A computer-implemented method comprising: using a graphical user interface to receive an action probability having a location within a region; imposing a continuous function onto the region, the function yielding a confidence level based on the location of the action probability within the region; and, dividing the region into a plurality of sub-regions ordered in increasing confidence levels such that a first sub-region has a minimum confidence level and a last sub-region has a maximum confidence level the location of the action probability falling within one of the sub-regions: and, modulating the behavior of the automated assistant based on the confidence level yielded by the continuous function.
Claim 22
Dependent Claim
14 words
The method of claim 18 , wherein the continuous function comprises a linear function.
Claim 23
Dependent Claim
138 words
A machine readable medium having instructions stored thereon for execution by a processor to perform a method comprising: inputting an action probability, the action probability having a location within a region corresponding to an option selected from the group essentially consisting of: (1) inactions, (2) automatic action, and (3) engaging the user in a dialog about the user's desire for automated action, followed by action pending receipt of user approval: dividing the region into a plurality of sub-regions ordered in increasing confidence levels such that a first sub-region has a minimum confidence level and a last sub-region has a maximum confidence level, the location of the action probability falling within one of the sub-regions; and, modulating the behavior of an automated assistant based on the one of tie sub-regions in which tile location of the action probability falls.
Claim 24
Dependent Claim
138 words
A machine readable medium having instructions stored thereon for execution by a processor to perform a method comprising: inputting an action probability, the action probability having a location within a region corresponding to an option selected from the group essentially consisting of: (1) inactions, (2) automatic action, and (3) engaging the user in a dialog about the user's desire for automated action, followed by action pending receipt of user approval: dividing the region into a plurality of sub-regions ordered in increasing confidence levels such that a first sub-region has a minimum confidence level and a last sub-region has a maximum confidence level, the location of the action probability falling within one of the sub-regions; and, modulating the behavior of an automated assistant based on the one of tie sub-regions in which tile location of the action probability falls.
Claim 25
Dependent Claim
25 words
The medium of claim 20 , wherein the behavior of the automated assistant comprises at least one of: utterances, speech parameters, sizing, gestures, and invasiveness.
Claim 26
Dependent Claim
28 words
The medium of claim 20 , wherein the behavior of the automated assistant comprises at least one of: prosody, energy, pause structure of speech of the automated assistant.
Claim 27
Dependent Claim
26 words
The medium of claim 20 , wherein the modulating a behavior of an automated assistant comprises modulating the behavior upon user navigation in a predetermined manner.
Claim 28
Dependent Claim
14 words
The medium of claim 23 , wherein modulating the behavior by making an apology.
Claim 29
Dependent Claim
25 words
The medium of claim 20 , wherein modulating a behavior of an automated assistant comprises modulating behavior upon not hearing an utterance from the user.
Claim 30
Dependent Claim
44 words
The medium of claim 20 , wherein modulating a behavior of an automated assistant comprises modulating at least one of a group of classes of behaviors consisting essentially of: (1) utterances; (2) gestures and postures: and, (3) parameters regarding variable components of interaction machinery.
Claim 31
Dependent Claim
49 words
The medium of claim 20 , wherein modulating a behavior of an automated assistant depending on the location of the action probability within the region comprises simulating the behavior of the automated assistant from a set of behaviors appropriate to the location of the action probability within the region.
Claim 32
Dependent Claim
94 words
A machine-readable medium having instructions stored thereon for execution by a processor to perform a method comprising: inputting an action probability having a location within a region; dividing the region into a plurality of sub-regions ordered in increasing confidence levels such that a first sub-region has minimum confidence level and a last sub-region has a maximum confidence level, the location of the action probability falling within one of the sub-regions; and, modulating the behavior of the automated assistant based on the one of die sub-regions in which the location of the action probability falls.
Claim 33
Dependent Claim
94 words
A machine-readable medium having instructions stored thereon for execution by a processor to perform a method comprising: inputting an action probability having a location within a region; dividing the region into a plurality of sub-regions ordered in increasing confidence levels such that a first sub-region has minimum confidence level and a last sub-region has a maximum confidence level, the location of the action probability falling within one of the sub-regions; and, modulating the behavior of the automated assistant based on the one of die sub-regions in which the location of the action probability falls.
Claim 34
Dependent Claim
54 words
The medium of claim 28 , wherein modulating the behavior of the automated assistant based on the one of the sub-regions in which the location of the action probability falls comprises determining the behavior consistent pith a confidence level of the one of the sub-regions in which the location of the action probability falls.
Claim 35
Dependent Claim
40 words
The medium of claim 28 , wherein dividing the region into a plurality of sub-regions comprises dividing the region into two sub-regions comprising the first sub-region having the minimum confidence level and the last sub-region having the maximum confidence level.
Claim 36
Dependent Claim
119 words
A machine-readable medium having instructions stored thereon for execution by a processor to perform a method comprising: inputting an action probability having a location within a region; imposing a continuous function onto the region, the function yielding a confidence level based on the location of the action probability within the region; dividing the region into a plurality of sub-regions ordered in increasing confidence levels such that a first sub-region has a minimum confidence level and a last sub-region has a maximum confidence level, the location of the action probability falling within one of the sub-regions; and, modulating the behavior of an automated assistant based on the one of the sub-regions in which the location of the action probability falls.
Claim 37
Dependent Claim
119 words
A machine-readable medium having instructions stored thereon for execution by a processor to perform a method comprising: inputting an action probability having a location within a region; imposing a continuous function onto the region, the function yielding a confidence level based on the location of the action probability within the region; dividing the region into a plurality of sub-regions ordered in increasing confidence levels such that a first sub-region has a minimum confidence level and a last sub-region has a maximum confidence level, the location of the action probability falling within one of the sub-regions; and, modulating the behavior of an automated assistant based on the one of the sub-regions in which the location of the action probability falls.
Claim 38
Dependent Claim
14 words
The medium of claim 31 , wherein the continuous function comprises a linear function.
Claim 39
Dependent Claim
15 words
The medium of claim 31 , wherein the continuous function comprises the action probability itself.
Claim 40
Dependent Claim
17 words
The method of claim 31 , wherein the continuous function comprises a computed expected utility of action.
Claim 41
Dependent Claim
68 words
A computer-implemented method comprising: determining a message to analyze; determining a probability that the message should be scheduled based al least in part on the message and contextual information; providing a selection option of at least one of: (1) inaction, (2) automatic action, and (3) suggested action with user approval; and performing a scheduling action based at least in part on the scheduling probability and a selected option.
Claim 42
Dependent Claim
68 words
A computer-implemented method comprising: determining a message to analyze; determining a probability that the message should be scheduled based al least in part on the message and contextual information; providing a selection option of at least one of: (1) inaction, (2) automatic action, and (3) suggested action with user approval; and performing a scheduling action based at least in part on the scheduling probability and a selected option.
Claim 43
Dependent Claim
67 words
A machine-readable medium having processor instructions stored thereon for execution by a processor to cause performance of a method comprising: determining a message to analyze; determining a probability that the message should be scheduled; providing a selection option of at least one of: (1) inaction, (2) automatic action, and (3) performing a scheduling action based at least in part on the scheduling probability and a selected option.
Claim 44
Dependent Claim
67 words
A machine-readable medium having processor instructions stored thereon for execution by a processor to cause performance of a method comprising: determining a message to analyze; determining a probability that the message should be scheduled; providing a selection option of at least one of: (1) inaction, (2) automatic action, and (3) performing a scheduling action based at least in part on the scheduling probability and a selected option.
Claim 45
Dependent Claim
90 words
A computerized system comprising: a scheduling program in which a user is able to track appointments within a calendar; and, a scheduling direction program to determine a probability that a message should be scheduled based in part on the message and an input; the input enabling an option selected from at least one of: (1) inaction, (2) automatic action, and (3) suggested action with user approval; the scheduling direction program perform a scheduling action within the scheduling program based at least in part on the scheduling probability and the input.
Claim 46
Dependent Claim
90 words
A computerized system comprising: a scheduling program in which a user is able to track appointments within a calendar; and, a scheduling direction program to determine a probability that a message should be scheduled based in part on the message and an input; the input enabling an option selected from at least one of: (1) inaction, (2) automatic action, and (3) suggested action with user approval; the scheduling direction program perform a scheduling action within the scheduling program based at least in part on the scheduling probability and the input.
References Cited (Backward Citations)
US5621903A
Cited
US5930700A
Cited
US5758029A
Cited
US5953393A
Cited
US5864848A
Cited
US5963913A
Cited
US6094681A
Cited
US6064976A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2006-12-01 | 2007-06-02 | 2007-12-02 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2010-12-01 | 2011-06-02 | 2011-12-02 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2014-12-01 | 2015-06-02 | 2015-12-02 | $7700.00 | Window Closed / Lapsed |