Customizing responses to users in automated dialogue systems

• US 10,741,176 B2
• Filed: 01/31/2018
• Issued: 08/11/2020
• Est. Priority Date: 01/31/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Canim, Mustafa, Farrell, Robert G., Gunnels, John A., Iyengar, Arun K.
• Primary Examiner(s): Chawan, Vijay B
• Application Number:
  US15/885,072
• Publication Number:
  US 20190237068A1
• Time in Patent Office: 923 Days
• Field of Search: 704 10, 704201, 704257, 704231, 705 1441, 705 1443, 705 1454, 705 1467, 705 728, 705 731, 706 11, 706 46, 707722, 707723, 707769, 707803, 707999003, 715234, 715811, 715816
• CPC Class Codes: G06F 16/219 Managing data history or versioning querying versioned data G06F16/2474; querying temporal data G06F16/2477
• CPC Class Codes: G06F 16/288 Entity relationship models
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Mechanisms are provided for customizing responses to future questions based on identified anomalies in user profile information. An automated dialogue system monitors information associated with a plurality of entities, where the information includes quantities for variable values associated with the entities. The automated dialogue system, in response to determining that a quantity of a variable value associated with an entity in the plurality of entities has changed by an amount equal to or exceeding a corresponding threshold value, generates response information associated with a quantity of the variable value and an entity to respond to at least one future question. In addition, the automated dialogue system stores the responsive information in association with the entity for later retrieval in response to initiation of a dialogue session with the automated dialogue system. Time thresholds may be established for determining when to stop using the responsive information for responding to questions.

Claims

1. A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to implement an automatic dialogue system, for conducting a natural language dialogue between the automatic dialogue system and a user of a client computing device, wherein the automatic dialogue system operates to:

analyze historical dialogue session data representing past dialogue sessions between the user via the client computing device and the automatic dialogue system, to identify a first behavior pattern of dialogue session initiation in response to changes in a value of a variable in a user profile data structure associated with the user;

set a threshold value for the variable based on the first behavior pattern, the threshold value specifying an amount of change in the value of the variable at which corresponding dialogue response information is to be used to generate an automatic dialogue response to the user during a subsequent dialogue session;

receive an initiation of a user dialogue session from the user via the client computing device;

determine whether an amount of change in the value of the variable has occurred that meets or exceeds the threshold value; and

respond, in response to receiving the initiating of the user dialogue and the amount of change in the value of the variable meeting or exceeding the threshold value, to at least one user inquiry submitted to the automatic dialogue system as part of the dialogue session, based on the dialogue response information.

2. The computer program product of claim 1, wherein the computer readable program further causes the automatic dialogue system to analyze historical dialogue session data for past dialogue sessions between a plurality of other users and the automatic dialogue system to identify second behavior patterns of dialogue session initiation in response to changes in the at least one variable in user profile data structures associated with the plurality of other users, wherein the at least one threshold value is set based on the second behavior patterns.

3. The computer program product of claim 1, wherein the computer readable program further causes the automatic dialogue system to:

determine a time threshold specifying a time period during which the dialogue response information is applicable to subsequent dialogue sessions between the user, via the client computing device, and the automatic dialogue system; and

terminate use of the dialogue response information for subsequent dialogue sessions in response to an elapse of the time period of the time threshold, wherein the time threshold is determined based on the first behavior pattern.

4. The computer program product of claim 3, wherein the computer readable program further causes the automatic dialogue system to analyze historical dialogue session data for past dialogue sessions between a plurality of other users and the automatic dialogue system to identify second behavior patterns of dialogue session initiation in response to changes in the at least one variable in user profile data structures associated with the plurality of other users, wherein the at least one threshold value is set based on the second behavior patterns, and wherein the time threshold is determined based on a weighted function of the first behavior pattern, and the second behavior patterns.

5. The computer program product of claim 1, wherein the variable is a rate associated with the user, and wherein the threshold specifies amount of increase or decrease in the value of the variable.

6. The computer program product of claim 1, wherein the computer readable program further causes the automatic dialogue system to analyze historical dialogue session data for past dialogue sessions between a plurality of other users and the automatic dialogue system to identify second behavior patterns of dialogue session initiation in response to changes in the at least one variable in user profile data structures associated with the plurality of other users, wherein the at least one threshold value is set based on the second behavior patterns.

7. The computer program product of claim 6, wherein the variable is one of at least one variable for which behavior patterns are determined, and wherein, for first variables in the at least one variable, for which the user has previously initiated a dialogue session with the automatic dialogue system, the first behavior pattern is used to set an associated threshold value.

8. The computer program product of claim 7, wherein for second variables in the at least one variable, where the user has not previously initiated a dialogue session with the automatic dialogue system, the second behavior patterns are used to set an associated threshold value for the second variables.

9. The computer program product of claim 7, wherein for second variables in the at least one variable where the user has previously initiated a dialogue session with the automatic dialogue system, and other users have previously initiated a dialogue session with the automatic dialogue system, a weighted combination of the first behavior pattern and the second behavior patterns is used to set an associated threshold value for the second variables.

10. The computer program product of claim 1, wherein responding to at least one inquiry submitted by the user as part of the dialogue session comprises:

receiving, by the automatic dialogue system, natural language text corresponding to a user input from the user via the client computing device, the natural language text having either an ambiguous portion of natural language text or a portion of natural language text referencing the variable;

retrieving, by the automatic dialogue system from the user profile data structure, the dialogue response information corresponding to the variable;

generating, by the automatic dialogue system, a natural language response to the at least one user inquiry based on the dialogue response information; and

outputting, by the automatic dialogue system, the natural language response to the client computing device to thereby conduct a natural language dialogue between the automatic dialogue system and the user via the client computing device.

11. An apparatus comprising:

a processor; and

a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to implement an automatic dialogue system for conducting a natural language dialogue between the automatic dialogue system and a user of a client computing device, wherein the automatic dialogue system operates to;

analyze historical dialogue session data representing past dialogue sessions between the user via the client computing device and the automatic dialogue system, to identify a first behavior pattern of dialogue session initiation in response to changes in a value of a variable in a user profile data structure associated with the user;

set a threshold value for the variable based on the first behavior pattern, the threshold value specifying an amount of change in the value of the variable at which corresponding dialogue response information is to be used to generate an automatic dialogue response to the user during a subsequent dialogue session;

receive an initiation of a user dialogue session from the user via the client computing device;

determine whether an amount of change in the value of the variable has occurred that meets or exceeds the threshold value; and

respond, in response to receiving the initiating of the user dialogue and the amount of change in the value of the variable meeting or exceeding the threshold value, to at least one user inquiry submitted to the automatic dialogue system as part of the dialogue session, based on the dialogue response information.