Conversational System and Method of Searching for Information

• US 20130246392A1
• Filed: 02/04/2013
• Published: 09/19/2013
• Est. Priority Date: 03/14/2012
• Status: Abandoned Application

• Current Assignee: iNAGO, Inc.
• Original Assignee: iNAGO, Inc.
• Inventors: Farmaner, Gary, DiCarlantonio, Ron
• Application Number:
  US13/758,449
• Publication Number:
  US 20130246392A1
• Time in Patent Office: Days
• US Class Current: 707/713
• CPC Class Codes: G06F 16/2453 Query optimisation
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems

Abstract

A system and method for performing an operation based on a contextual command, which operation further comprises interactively searching for information, comprising: receiving an input in a context, returning a result in respect of the received context by at least one of reducing, relaxing, and location handling in respect of the input value, and performing an operation based upon the context of the input criteria. Reducing comprises narrowing the total number of results by their contextual relevance, wherein the narrowing is comprised in dynamically generated real-time interactions. Relaxing further comprises, when an exact result is not found, broadening the input search criteria automatically, and where appropriate, obtaining a result. The location handling further comprises disambiguating addresses and locations where there are conflicts based on an input history, and establishing relationships within addresses based upon the input history.

Claims

1. A computer automated system adapted to interpret commands contextually, and comprising a processing unit and memory element having instructions encoded thereon, which cause the system to:

receive a user input command which corresponds to an instruction for performing an operation in a context;

disambiguate the input command;

perform the operation based on the disambiguated input command; and

return in response to the disambiguated input command, zero or more results.

2. The system of claim 1 wherein the instructions further cause the system to:

if zero results are obtained, broaden the user input criteria to cause the system to return one or more alternate results in an updated context;

if one or more results are obtained, return the one or more results in the input context; and

wherein the one or more results are comprised in dynamically generated real-time interactions based on the disambiguated input context or updated context, respectively.

3. The system of claim 1 wherein the instructions that cause the system to disambiguate the input commands further cause the system to disambiguate at least one of user input intent and user input meaning.

4. In the system of claim 3, to disambiguate user input intent further comprises reduction, wherein in a plurality of obtained results, the system is caused to narrow the total number of results by their contextual relevance;

wherein the said narrowing is comprised in the dynamically generated real-time interactions, which further comprise automatically calculated responses to the input commands to reduce the set of results and the number of steps.

5. The system of claim 3 wherein in disambiguating user input meaning, the encoded instructions further cause the system to:

in response to user input, return a single or plurality of system interpretations for user clarification of an ambiguous input.

6. The computer automated system of claim 1 wherein context includes at least one of:

a content domain, criteria, data fields, GUI state, system state, user'"'"'s locale, user'"'"'s profile and the interaction between the user application and system including user input and returned system response; and

wherein said criteria comprise normalized values for user intent criteria determined from free input and interaction with the system;

wherein said system state comprises contextual relevance of returned response to user input; and

wherein conversation context comprises content exchanged during real-time interaction with the system.

7. The system of claim 6, further comprising instructions that cause the system to:

perform the operation, which further comprises searching multiple values for specific criteria as at least one of a union and an intersection.

8. The system of claim 6, further comprising instructions that cause the system to, in response to the input, perform the operation based on excluded criteria in said input, wherein said excluded criteria comprises inputting what not to look for.

9. The system of claim 6 further comprising instructions that cause the system to:

in respect of a disambiguated input context, determine most relevant criteria to collect based on the distribution of results;

return a single or plurality of determined criteria collected, for user selection; and

narrow the returned result by contextual relevance, wherein the narrowing comprises analysing obtained results in the real time interaction, and returning one or more results comprising items active given the current context of the input criteria.

10. The system of claim 1 further comprising instructions that cause the system to:

in response to a result returned from a user input in a first context, receive an input in an unrelated context, and in response to said unrelated context, temporarily detour away from the said first context;

return a result in respect of the said unrelated context; and

revert back to the said first context;

wherein context comprises the current state of the system.

11. The system of claim 1 wherein the instructions further cause the system to obtain contextually relevant results, which comprises:

automatically broadening input criteria when zero results are obtained;

determining by analyzing the results obtained based on broadened input criteria, the most relevant results to collect, which determining is based on the distribution of results among active, broadened criteria; and

returning one or more determined, relevant results.

12. The system of claim 11 wherein the analyzing further comprises:

mapping a user input to meaning which comprises matching words and phrases of the input command to a normalized semantic form for comparison with the content;

creating a hierarchical structure for allowing matching of the input command to at least one of general ancestors and descendants; and

converting a string in natural language into a structured format for determining meaning semantics.

13. The system of claim 1 further comprising instructions to create a normal for a genre that the input content belongs to, wherein creating the normal comprises:

defining a matching grammar that matches the input command;

capturing information in that input; and

passing the captured information to a specific conversion routine to create the normal from the captured data;

wherein the conversion routine is content defined.

14. The system of claim 13 further comprising instructions that cause the system to:

implement genre mapping, which comprises matching user input against genre mapping rules, wherein any tagged input is consumed as the rules are applied.

15. The system of claim 1 further comprising instructions which cause the system to, in response to the input command, query and obtain results from a content provider optimized for a context aware interactive search.

16. The system of claim 1 further comprising instructions which cause the system to, in response to the input command, request an external system to perform an operation based on criteria obtained from a context aware interaction.

40. The system of claim 1 wherein the command further comprises the instruction to perform a search or an operation in the input context.

17. In a computer automated system adapted to interpret commands contextually, and comprising a processing unit and memory element having instructions encoded thereon, a method comprising:

receiving a user input command which corresponds to an instruction for performing an operation in a context;

disambiguating the input command;

performing the operation based on the disambiguated input command; and

returning in response to the disambiguated input command, zero or more results.

18. The method of claim 17 further comprising:

if zero results are obtained, broadening the user input criteria to cause the system to return a single or plurality of alternate results in an updated context;

if one or more results are obtained, returning the one or more results in the input context; and

wherein the one or more results are comprised in dynamically generated real-time interactions based on the disambiguated input context or updated context, respectively.

19. The method of claim 17 wherein disambiguating the input commands comprises causing the system to disambiguate at least one of user input intent and user input meaning.

20. The method of claim 19 wherein disambiguating user input intent further comprises:

reduction, wherein in a plurality of obtained results, narrowing the total number of results by their contextual relevance;

wherein the said narrowing is comprised in the dynamically generated real-time interactions, which further comprise automatically calculating responses to the input commands to reduce the set of results and the number of steps.

21. The system of claim 19 wherein disambiguating user input meaning comprises:

in response to user input, returning a single or plurality of system interpretations for user clarification of an ambiguous input.

22. The method of claim 17 further comprising:

determining context which comprises normalizing values for input criteria which values are determined from real-time user input;

determining system state based on results returned in response to user input; and

determining conversation context based on content exchanged during real-time user interaction; and

wherein the said context includes at least one of a content domain, criteria, data fields, a GUI state, system state, user'"'"'s locale, user'"'"'s profile and the interaction between the user application and system including user input and returned system response.

23. The method of claim 22 further comprising, performing an operation comprising searching multiple values for specific criteria as at least one of a union and an intersection.

24. The method of claim 22 further comprising allowing the system to, in response to the input, performing an operation based on input excluded criteria.

25. The method of claim 22 further comprising:

in respect of a disambiguated input context, determining most relevant criteria to collect based on the distribution of results;

returning a single or plurality of determined criteria collected, for user selection; and

narrowing the returned result by contextual relevance, wherein the narrowing comprises analysing obtained results in the real time interaction, and returning one or more results comprising items active given the current context of the input criteria.

26. The method of claim 17 further comprising analyzing context and content of user input wherein the analyzing comprises:

mapping a user input to meaning which comprises matching words and phrases of the input command to a normalized semantic form for comparison with the content;

creating a hierarchical structure for allowing matching of the input command to at least one of a single or plurality of general ancestors and a single of plurality of descendants; and

converting a string in natural language into a structured format for determining meaning semantics.

27. The method of claim 17 further comprising creating a normal for a genre that the input content belongs to, wherein creating the normal comprises:

defining a matching grammar that matches the input command;

capturing information in that input; and

passing the captured information to a specific conversion routine to create the normal from the captured data;

wherein the conversion routine is content defined.

28. The method of claim 24 further comprising instructions that cause the system to:

implement genre mapping, which comprises matching user input against genre mapping rules, wherein any tagged input is consumed as the rules are applied.

29. The method of claim 17 further comprising, in response to the input, optimizing content obtained from a content provider, which optimization is based on user input context and content relevance.

30. The method of claim 21 further comprising disambiguating of the said input meaning based on at least one of context of the input content, user location, gender, and input language.

31. The method of claim 17 further comprising:

in response to a result returned from a user input in a first context, receiving an input in an unrelated context, and in response to said unrelated context, temporarily detouring away from the said first context;

returning a result in respect of the said unrelated context; and

reverting back to the said first context;

wherein context comprises the current state of the system.

32. The method of claim 17 further comprising:

in response to the input returning no result, automatically relaxing criteria from the said input to obtain contextually relevant results;

analyzing the input and based on the values input returning active items given the current context of the input criteria.

33. A system comprising a processing unit and memory element, and having instructions encoded thereon, which instructions cause the system to:

receive an input in a context;

return a result in respect of the received context by at least one of narrowing, broadening, and location handling in respect of the input value;

wherein an operation is performed based upon the context of input criteria;

wherein the narrowing further comprises returning a one or more relevant items based on a current result returned in response to the input, and comprising possible criteria values;

wherein the broadening further comprises, when an exact result is not found, broadening the input criteria automatically, and where appropriate, to obtain a result; and

wherein the location handling further comprises disambiguating addresses and locations where there are conflicts based on an input history, and establishing relationships within addresses based upon an input history.

34. A dynamic, self-evolving, computer automated system comprising a processing unit and a memory element, and having instructions encoded thereon which instructions cause the system to:

develop evolving interactive capability without human authoring of scenarios for each user interaction, wherein said evolving further comprises determining a user interaction based on the context and content;

automatically define rules that enhance the automated functionality;

implement natural language processing wherein said natural language processing comprises mapping a user input to meaning, and which mapping further comprises genre tagging;

differentiate between a set which comprises a grouping and a set which comprises the action of making a change; and

create a hierarchical structure for allowing matching of input to at least one of a single or plurality of general ancestors and a single or plurality of descendants.

35. The system of claim 34 wherein the natural language processing further comprises automatic conversion of a string in a natural language to a structured, machine readable format which provides a basis for determining meaning.

36. The system of claim 34 wherein the said genre tagging further comprises:

matching of words and phrases of user input to a normalized semantic form for comparison with content; and

analyzing parts of speech to disambiguate ambiguous input.

37. In a computer automated system comprising a processing unit and a memory element, and having instructions encoded thereon, a method for dynamic self-evolving of the computer automated system, comprising:

developing evolving interactive capability without human authoring of scenarios for each user interaction, wherein said evolving further comprises determining a user interaction based on the context and content;

automatically defining rules to enhance the automated functionality;

implementing natural language processing wherein said natural language processing further comprises mapping a user input to meaning, and which mapping further comprises genre tagging;

differentiating between a set which comprises a grouping and a set which comprises the action of making a change;

creating a hierarchical structure for allowing matching to at least one of a single or plurality of general ancestors or a single or plurality of descendants.

38. The method of claim 37 wherein the natural language processing further comprises automatic conversion of a string in a natural language to a structured, machine readable format which provides a basis for determining meaning.

39. The method of claim 37 wherein the said genre tagging further comprises:

matching of words and phrases of user input to a normalized semantic form for comparison with content; and

analyzing parts of speech to disambiguate ambiguous input.