Advanced System and Method for Automated-Context-Aware-Dialog with Human Users

• US 20140297268A1
• Filed: 09/19/2012
• Published: 10/02/2014
• Est. Priority Date: 09/19/2011
• Status: Active Grant

• Current Assignee: Personetics Technologies Limited (Personetics Technologies, Inc.)
• Original Assignee: Personetics Technologies Limited (Personetics Technologies, Inc.)
• Inventors: Govrin, David D., Sosna, David, Ophir, Ido, Vatnik, Dan
• Granted Patent: US 9,495,331 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/00 Handling natural language data speech analysis or synthesis, speech recognition G10L
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2013/083 Special characters, e.g. punctuation marks
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages

Abstract

Apparatus for conducting a dialog with a user of at least one computerized enterprise system, the apparatus comprising an ontological topic definer using at least one ontological entity to define user dialog topics, each topic including an item, a block identifying executable computer code operative to resolve the item; and at least one input parameter passed to the block; and a dialog server operative for conducting a dialog with a user of at least one computerized enterprise system about an individual topic from among said user dialog topics.

Claims

1. Apparatus for conducting a dialog with a user of at least one computerized enterprise system, the apparatus comprising:

an ontological topic definer including a processor using at least one ontological entity to define user dialog topics including items; and

a computerized dialog server operative for conducting a dialog with a user of at least one computerized enterprise system about an individual topic from among said user dialog topics, including generating a directed graph based on item references, from links between said items, by applying closure-based variable scoping in conjunction with backward-chaining-based logic to said directed graph.

3. Apparatus according to claim 1 wherein said dialog server interacts with an Intent Scoring functionality for scoring various intents on the part of a user approaching a virtual agent, the functionality'"'"'s operation comprising:

predicting priority topics, including gathering first data and employing the first data to discern and seek user confirmation of at least one possible intent on the part of the user; and

subsequent to receipt of said confirmation, gathering second data and employing the second data to provide service to the user to suit the user'"'"'s confirmed intent.

4. Apparatus according to claim 1 wherein said dialog server interacts with a data-gathering system comprising:

a data-aware knowledge base storing knowledge on relative costs of obtaining various data items; and

a data retrieval decision making processor operative, when an individual data element is sought to be retrieved, to determine whether or not to retrieve said data element by comparing at least one parameter representing need for said data element with at least one parameter, retrieved from said data-aware knowledge base, which represents relative cost of obtaining said data element.

32. Apparatus according to claim 1 wherein each topic includes:

an item,

a block identifying executable computer code operative to resolve the item; and

at least one input parameter passed to the block.

33. Apparatus according to claim 1 wherein each topic includes items and item references.

34. Apparatus according to claim 33 wherein the item references reference the items by a natural name.

2. A computer program product, comprising a non-transitory tangible computer-readable medium having computer-readable program code embodied therein, said computer-readable program code adapted to be executed to implement a method for conducting a dialog with a user of at least one computerized enterprise system, the method comprising:

using at least one ontological entity to define user dialog topics including items; and

conducting a dialog with a user of at least one computerized enterprise system about an individual topic from among said user dialog topics, including generating a directed graph based on item references, from links between said items, by applying closure-based variable scoping in conjunction with backward-chaining-based logic to said directed graph.

5. A method for conducting a dialog with a user of at least one computerized enterprise system, the method comprising:

using at least one ontological entity to define user dialog topics including items; and

conducting a dialog with a user of at least one computerized enterprise system about an individual topic from among said user dialog topics, including generating a directed graph based on item references, from links between said items, by applying closure-based variable scoping in conjunction with backward-chaining-based logic to said directed graph.

6. A method according to claim 5 wherein at least one logic code segment is used for a plurality of different discussion entry points.

7. A method according to claim 5 wherein said conducting comprises conducting at least first and second dialogs with at least first and second users respectively, of at least first and second corresponding computerized enterprise systems respectively, including using a single logic code segment for at least first and second dialog portions, of the first and second dialogs respectively, which pertain to first and second products respectively, of the first and second corresponding computerized enterprise systems respectively.

8. A method according to claim 5, the method also comprising:

generating a topological graph having a multiplicity of nodes each representing a step or a decision, each step including an interaction with a user of at least one computerized enterprise system, a data lookup, or a data processing operation; and

conducting a dialogue with a user of at least one computerized enterprise system by proceeding through the graph including making at least one decision, based on collected information, as to which of a plurality of possible next steps in the graph to execute.

9. A method according to claim 8 wherein said data lookup comprises looking up statistical data about at least one population of users to which the user belongs.

10. A method according to claim 7 wherein the first and second enterprise systems comprise first and second banks respectively and wherein said first and second products comprise first and second financial services offered by the first and second banks respectively.

11. A method according to claim 8 wherein said data lookup comprises looking up data about the user, which is stored in said enterprise system.

12. A method according to claim 5 wherein said item, block and at least one parameter are stored as an ordered list.

13. A method according to claim 5 wherein at least one item includes a segment of interactive dialog to be presented to a user.

14. A method according to claim 5 wherein at least one item includes a computation to be performed.

15. A method according to claim 5 wherein at least one item includes a query to be presented to an external computerized system.

16. A method according to claim 5 wherein at least one item includes at least one action to be executed on an external computerized system.

17. A method according to claim 5 wherein at least one parameter comprises at least one ItemReference including a reference to at least one other item (referenced item) to be used as an input for a block.

18. A method according to claim 5 wherein each item includes an autoResolve flag indicating whether or not the item is to be resolved.

19. A method according to claim 5 wherein each item includes a condition indicating whether or not an item is to be executed based on the item'"'"'s input parameters.

20. A method according to claim 17 wherein at least one parameter comprises a logical expression (valueExpression) which generates a result value of the parameter by combining an itemReference with at least one of:

another itemReference; and

a constant.

21. A method according to claim 17 wherein at least one ItemReference includes an isRequired flag indicating whether the item is an optional input for said block or a required input for said block.

22. A method according to claim 17 wherein at least one ItemReference includes a quantification of said referenced item'"'"'s business value to the item which includes (owns) the parameter.

23. A method according to claim 5 wherein at least one topic includes an indication of a level of user authentication required to execute said topic.

24. A method according to claim 17 wherein said block comprises a reference to at least one of a procedure, class, and rule base, thereby to identify executable computer code operative to resolve the item.

25. A method according to claim 5 wherein said generating said directed graph employs a topic context tree having a root.

26. A method according to claim 25 wherein name references are translated into graph edges by searching for item names starting from bottom topic context and going up said topic context tree until said root is reached.

27. A method according to claim 5 and also comprising identifying and scoring potential discussion forks based on said directed graph.

28. A method according to claim 5 wherein Backward chaining is used over the directed graph to resolve a next item.

29. A method according to claim 5 wherein topic context closures are used to generate said directed graph of item references.

30. A method according to claim 5 wherein each link has the following form:

Item X→

parameter→

itemReference→

item Y.

31. A method according to claim 5 wherein nested topic contexts are created at runtime, thereby to resolve topics.

35. A method according to claim 5 wherein a topic context runtime ontology supports nested topic contexts.