Computer graphics processing and selective visual display system – Display driving control circuitry – Controlling the condition of display elements
Reexamination Certificate
1999-05-17
2003-12-02
Kincaid, Kristine (Department: 2173)
Computer graphics processing and selective visual display system
Display driving control circuitry
Controlling the condition of display elements
C345S215000, C345S215000, C345S215000, C345S215000
Reexamination Certificate
active
06657643
ABSTRACT:
FIELD OF THE INVENTION
This invention relates generally to automated services such as messaging and scheduling, and more particularly to modulating the behavior of an agent for such automated services.
BACKGROUND OF THE INVENTION
Messaging and scheduling have become important applications in many computer users' lives. Messaging programs generally allow a user to send and receive electronic mail (e.g., messages) to and from other computer users, for example, over a local- or a wide-area network, or over an intranet, extranet, or the Internet. Scheduling programs generally allow a user to track appointments in a calendar. More sophisticated scheduling programs allow one user to schedule a group meeting with other computer users—checking the latter users' schedule availability, and receiving confirmation from the users upon them accepting or rejecting the group meeting appointment.
Within the prior art, however, messaging and scheduling programs are generally not very well integrated, even if they are components within the same computer program. For example, a user may receive a message from a colleague stating “Looking forward to seeing you at 2 on Thursday.” Generally, however, the prior art does not provide for automatically directing the scheduling program to make a meeting appointment at 2 p.m. on Thursday. Instead, typically the user who has received the message has to open the scheduling program, access Thursday's calendar, and manually enter an appointment at 2 p.m. on Thursday's calendar. Because of the many steps required to go from reading the message within the messaging program to entering the information into the scheduling program, many users choose not to even use scheduling programs, or to only use them sparingly.
One solution to this difficulty is described in the parent application to the present application, entitled “Systems and Methods for Directing Automated Services for Messaging and Scheduling.” In this application, a scheduling probability, which can be generalized to be referred to as an action probability, is determined based on the text of a message (e.g., of an electronic e-mail), and also potentially contextual information such as information regarding recent user activity; the scheduling probability in one embodiment is an inferred probability that the user has a goal of scheduling and/or reviewing calendar information. The probability falls within one of the regions: an inaction region; a suggested action with user approval region (also referred to as a dialog region); and an automated action region.
In the first region, the inaction region, the probability is low enough that no automated service is performed. In the last region, the automated action region, the probability is high enough that an automated action is performed. Finally, in the middle region, the dialog region, the probability is such that the user is approached with a suggested action, which if approved by the user, is then performed in an automated manner. Threshold boundaries separate the first and the middle regions, and the middle and the last regions. The threshold boundaries may be user set, or may be calculated in accordance with decision theory as described in the parent application to the present application.
In one embodiment, an animated graphical and talking agent is utilized to provide a an anthropomorphic interface for the automated action direction process. For example, in the case of the probability lying in the middle region, an agent may appear on the screen and engage the user in a dialog as to whether the user wishes to have the suggested action be automatically performed. In one embodiment, speech recognition is used for the user to provide either an affirmative or a negative answer. As another example, in the case of the probability lying in the last region, an agent may appear on the screen to indicate to the user that an action will soon be performed. The use of an animated graphical and talking agent thus provides a more social interface to communicate with the user regarding automated actions.
The present application provides for a more sophisticated animated graphical and talking agent for use in the automated action direction process, by modulating the social behavior of the agent more closely in regard to the probability inferred automatically about a user's goals.
SUMMARY OF THE INVENTION
The invention relates to modulating the behavior of an agent for directing automated services such as for messaging and scheduling. In one embodiment, a computer-implemented method inputs an action probability, such as a scheduling probability as referred to in the parent application to the current application. The action probability has a location within a region corresponding to an option which 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. In one embodiment of the invention, the action probability is generally defined as the inferred probability that a user desires a service. Next, the method modulates the behavior of an automated assistant, also referred to as an agent, depending on the location of the action probability within the region. For example, 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 assistant is modulated based on the sub-region in which it lies. As another example, in one 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.
Embodiments of the invention provide for advantages not found within the prior art. The agent behaves more naturally, in accordance with the manner by which a human assistant might act to share his or her confidence with the recipient of the assistance, about his or her confidence in the need for assistance—showing appropriate courtesy, humility, tentativeness, etc., for example, when confidence is low. For example, the region in which the action probability is located may be the dialog region, such that the region is divided into two sub-regions, a low-confidence sub-region and a high-confidence sub-region. If the action probability lies in the low-confidence sub-region, then the agent may be more deferential to the user, asking “I was just thinking that you might like me to create an appointment in your calendar based on the e-mail you're reading?”. A corresponding animation may be invoked during the utterance that expresses tentativeness in a natural manner, such as the raising of eyebrows, leaning forward with a slightly cocked head, and opening the hands to the user. Conversely, if the action probability lies in the high-confidence sub-region, then the agent may be more direct with the user, stating and then asking “I'd be happy to create an appointment for you based on the e-mail you're reading. Should I go ahead and schedule it?”. A corresponding animation might include a more confident, relaxed expression combined with the gesture of the raising of one arm, and pointing the index finger of the associated hand upward to express in a natural manner the agent's more confident reflection about the value of assisting the user. Furthermore, in other embodiments of the invention, modulating the prosody, energy, and pause structure of the speech of the animation can also be modified, as can be appreciated by those of ordinary skill within the art.
REFERENCES:
patent: 5621903 (1997-04-01), Luciw et al.
patent: 5758029 (1998-05-01), Hall
patent: 5864848 (1999-01-01), Horvitz et al.
patent: 5930700 (1999-07-01), Pepper et al.
patent: 5953393 (1999-09-01), Culbreth et al.
patent: 5963913 (1999-10-01), Henneuse et al.
patent: 6064976 (2000-05-01), Tolopka
patent: 6094681 (2000-07-01)
Horvitz Eric
Jacobs Andrew W.
Kincaid Kristine
Microsoft Corporation
Nguyen Thomas T.
LandOfFree
Modulating the behavior of an animated character to reflect... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Modulating the behavior of an animated character to reflect..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Modulating the behavior of an animated character to reflect... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3147533