Data processing: artificial intelligence – Having particular user interface
Reexamination Certificate
1998-04-27
2001-11-06
Powell, Mark R. (Department: 2122)
Data processing: artificial intelligence
Having particular user interface
Reexamination Certificate
active
06314410
ABSTRACT:
BACKGROUND OF THE ART
For the purposes of the present invention, “virtual robots” (or “BOTs”) are software programs that interact and/or communicate with users (human, machine or otherwise) that take actions or make responses according to input from these users. BOTs are the subject of the co-pending and co-assigned parent application entitled “Methods for Automatically Selecting Responses for a Virtual Robot”, filed Feb. 3, 1998, U.S. Ser. No. 09/018,213, and incorporated by reference in its entirety herein, which itself is a continuation-in-part of a co-pending and co-assigned parent application entitled “Methods for Automatically Focusing the Attention of a Virtual Robot Interacting with Users”, filed Jun. 4, 1997, U.S. Ser. No. 08/868,713, and incorporated by reference in its entirety herein. A common use of such a BOT is as an interface to a web site wherein the administrator of that site has programmed the BOT to answer simple inquiries that are typically asked by visitors to the site. The above identified application discloses a method of creating BOTs according to “scripts”—i.e. programs that are written in a very high level language that closely resembles a human natural language. These scripts embody a certain amount of information concerning the site that the administrator desires the BOT to communicate to a user during a connection session.
The above identified applications includes a variety of methods for interpreting the “context” in which a question or statement is given to the bot. These methods include a method of maintaining a focus of attention stack that orders the topics discussed by the BOT according to their relevance to the current conversation, and a method of automatically replacing pronouns in user inputs.
However, both of these methods suffer from significant disadvantages in practice. Automatic pronoun replacement is very effective for the pronouns “he”, “she”, “him”, and “her”, but does not work effectively in practice for other pronouns such as “it”, “they”, “that”, and “you”, due to the frequency with which these words are used in senses other than as pronouns. The focus of attention stack is generally successful at distinguishing among multiple answers to a single question (such as “what is it?”) but lacks any effective way of deciding whether such an answer is preferable to a default response such as “I don't know.” For instance, suppose there is one topic that answers the question “where is it?” if the user has been discussing Neuromedia, but no topic that answers the question “where is it?” when “it” refers to San Francisco. In this case, even if the user has been discussing San Francisco and has not mentioned Neuromedia at all, if the user then asks “what is it?” they may get a response describing the location of Neuromedia rather than the correct response, which in this case is probably “I don't know.” Given that a BOT's knowledge is in practice always incomplete, such situations can repeatedly arise during the interaction of a user with a BOT.
Thus, there is a need in the art to have a method of selecting a response to a context-sensitive question or statement, and for that method to allow a question to be answered with a default answer or no answer at all, even when the identical question would get a specific answer if asked in another context.
SUMMARY OF THE INVENTION
The present invention meets these aforementioned needs by providing in a BOT script a method of testing the context of an input when deciding upon the correct response that should be given to an input. In an automated interface program designed to interact and communicate with users, said program executing actions when a category among a predefined set of categories is activated, a method is disclosed for testing the context of an input when selecting a category to activate, the steps of said method comprising:
(a) associating subjects with categories;
(b) maintaining a list of the subjects associated with the most recently activated category;
(c) testing conditions in categories such that the condition is satisfied if the category comprises at least one subject in common with said list of subjects;
(d) activating a set of categories, said set comprising those categories whose conditions are satisfied in step (c).
Other aspects of the category selection mechanism are disclosed in the description given below when read in conjunction with the accompanying figures.
REFERENCES:
patent: 5161110 (1992-11-01), Dorchak
patent: 5371807 (1994-12-01), Register et al.
patent: 5384893 (1995-01-01), Hutchins
patent: 5442786 (1995-08-01), Bowen
patent: 5526407 (1996-06-01), Russell et al.
patent: 5535323 (1996-07-01), Miller et al.
patent: 5553218 (1996-09-01), Li et al.
patent: 5568639 (1996-10-01), Wilcox et al.
patent: 5587903 (1996-12-01), Yale et al.
patent: 5600765 (1997-02-01), Ando et al.
patent: 5606712 (1997-02-01), Hidaka
patent: 5682539 (1997-10-01), Conrad et al.
patent: 5712987 (1998-01-01), Waits et al.
patent: 5758323 (1998-05-01), Case
patent: 5760768 (1998-06-01), Gram
patent: 5801710 (1998-09-01), Cok et al.
patent: 5835087 (1998-11-01), Herz et al.
patent: 5864844 (1999-01-01), James et al.
patent: 5877759 (1999-03-01), Bauer
patent: 5894311 (1999-04-01), Jackson
patent: 5924089 (1999-07-01), Mocek et al.
patent: 5974405 (1999-10-01), McGuinness et al.
patent: 5995921 (1999-11-01), Richards et al.
patent: 6012055 (2000-01-01), Campbell et al.
Microsoft, Getting Results with Microsoft Office 97, 35-40, 1995.*
Kaplan, R.. (1975). “A General Syntactic Processor”In Natural Language Processing. R. Rustin ed., Algorithmics Press, Inc., pp. 193-241.
Reichman, R.. (1978). “Conversational Coherency,”Cognitive Science2:283-327.
Sidner, C.L.. (1985). “Plan Parsing For Intended Response Recongnition in Discourse,”Comput Intell1:1-10.
Cohen, R..(1987). “Analyzing the Structure of Argumentative Discourse,”Computatioal Linguistics13(1-2):11-24.
Grosz, B. et al.. (1987). “Team: An Experiment in the Design of Transportable Natural-Language Interfaces,”Artificial Intelligence32:173-243.
Litman, D. et al.. (1987). “A Plan Recognition Model for Subdialogues In Conversations,”Cognitive Science11:163-200.
Hirschberg, J. et al.. (1993). “Empirical Studies on the Disambiguation of Cue Phrases,”Computational Linguistics19(3):501-530.
Allen, J.. (1995).Natural Language Understanding. The Benjamin/Cummings Publishing Company, Inc., Chapter 14, pp.429-461 entitled “Local Discourse Context and Reference” and Chapter 16 entitled “Discourse Structure” pp. 503-537and Chapter 17 entitled “Defining a Conversational Agent” pp. 541-576.
Reichman, R.. (1985).Getting Computers to Talk Like You and Me. A Bradford Book. The MIT Press, Chapter 2, pp. 21-33, Chapter 5, pp. 67-90 and Chapter 6, pp. 155-166. (Copy attached herewith).
Grosz, B.J. and C. Sidner (1986). “Attention, Intentions, and the Structure of Discourse,”Computational Linguistics12(3):175-204. (Copy attached herewith).
Grosz, B. J. (1986). “The Representation and Use of Focus in a System for Understanding Dialogs”In Readings in Natural Language Processing. B.J. Grosz et al. eds., Morgan Kaufmann Publishers, Inc., pp. 353-362. (Copy attached herewith).
Sidner, C. L. (1986). “Focusing in the Comprehension of Definite Anaphora”In Readings in Natural Language Processing. B.J. Grosz et al. eds., Morgan Kaufmann Publishers, Inc., pp. 363-394. (Copy attached herewith).
Benson Scott S.
Dillinger Ray S.
Tackett Walter A.
Holmes Michael B.
Morrison & Foerster / LLP
NativeMinds, Inc.
Powell Mark R.
LandOfFree
System and method for identifying the context of a statement... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for identifying the context of a statement..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for identifying the context of a statement... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2575518