AUTOMATED SCHEME FOR IDENTIFYING USER INTENT IN REAL-TIME

• US 20120131033A1
• Filed: 11/18/2011
• Published: 05/24/2012
• Est. Priority Date: 04/07/2004
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Oracle International Corporation (Oracle Corporation)
• Inventors: Bierner, Gann Alexander
• Granted Patent: US 8,924,410 B2
• Time in Patent Office: Days
• US Class Current: 707/767
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence

Abstract

An intent guessing system receives partial user queries as they are entered by the user. The partial user queries are compared with different intents derived from previously logged queries. Guesses are made as to which of the intents are associated with the partial user query. The intent guesses are then provided as responses to the user query. Features are identified for the earlier logged queries and associated with the derived intents. The derived intents and associated features are then used to identify intents for the partial user queries.

Claims

1-21. -21. (canceled)

22. A method of processing a current user query, comprising:

maintaining, by a computer system, a model comprising a plurality of entries, each entry of the model comprising a query feature, a query intent, and an indication of a statistical association between the query feature and the query intent;

receiving, at the computer system, an initial portion of the current user query, the initial portion including a particular string of text;

guessing, by the computer system, a plurality of intent guesses associated with the initial portion of the current user query but that do not include text strings that match the particular text string while a remainder of the current user query is being received; and

responding, by the computer system, to the initial portion of the current user query with the plurality of intent guesses.

23. The method of claim 22, wherein maintaining the model comprises training the model prior to receiving the initial portion of the current user query, said training comprising:

logging previous user queries;

extracting a question from the logged previous user queries;

analyzing the extracted question to obtain at least one query feature;

assigning a query intent to the extracted question; and

adding an entry to the model and associating the obtained query feature for the extracted question to the assigned query intent for the extracted question in the added entry of the model.

24. The method of claim 22, wherein guessing the plurality of intent guesses comprises:

analyzing the initial portion to obtain at least one feature;

comparing the obtained at least one feature of the initial portion to the query features of the entries in the model;

selecting a plurality of entries from the model based on the comparison;

determining the intent for the initial portion of the current user query according to the query intent in the selected plurality of entries and the statistical association between the query feature and the query intent; and

generating the plurality of intent guesses based on the determined intent for the initial portion of the current user query.

25. The method of to claim 22, wherein maintaining the model comprises updating the model, by the computer system, based on an indication of a user selection of an intent guess.

26. The method of claim 25, wherein the user selection comprises a selection of one of the plurality of intent guesses and wherein updating the model comprises updating the statistical association between the query feature and the query intent for at least one of the entries.

27. The method according to claim 22, further comprising:

identifying, by the computer system, a response associated with each of the plurality of intent guesses;

identifying, by the computer system, an order for the plurality of intent guesses based on the statistical associations between the query feature and the query intent for each or the selected plurality of entries of the model; and

displaying, by the computer system, based on the determined order the response along with the associated intent guess or the response instead of the associated intent guess.

28. The method according to claim 22, further comprising:

identifying, by the computer system, an order for the plurality of intent guesses based on the statistical associations between the query feature and the query intent for each or the selected plurality of entries of the model; and

displaying, by the computer system, the intent guesses in the identified order.

29. A method of processing a current user query, comprising:

maintaining, by a computer system, a model comprising a plurality of entries, each entry of the model comprising a query feature, a query intent, and an indication of a statistical association between the query feature and the query intent;

receiving, at the computer system, an initial portion of the current user query, the initial portion including a particular string of text;

guessing, by the computer system, an intent associated with the initial portion of the current user query while a remainder of the current user query is being received, wherein said guessing using only the initial portion comprises;

analyzing the initial portion to obtain at least one feature,

comparing the obtained at least one feature of the initial portion to the query features of the entries in the model,

selecting a plurality of entries from the model based on the comparison,

determining the intent for the initial portion of the current user query according to the query intent in the selected plurality of entries and the statistical association between the query feature and the query intent, and

generating a plurality of intent guesses that do not include text strings that match the particular text string based on the determined intent for the initial portion of the current user query; and

responding, by the computer system, to the initial portion of the current user query with the plurality of intent guesses.

30. The method of claim 29, wherein maintaining the model comprises training the model prior to receiving the initial portion of the current user query, said training comprising:

logging previous user queries;

extracting a question from the logged previous user queries;

analyzing the extracted question to obtain at least one query feature;

assigning a query intent to the extracted question; and

adding an entry to the model and associating the obtained query feature for the extracted question to the assigned query intent for the extracted question in the added entry of the model.

31. The method of to claim 29, wherein maintaining the model comprises updating the model based on an indication of a user selection of an intent guess, wherein the user selection comprises a selection of one of the plurality of intent guesses, and wherein updating the model comprises updating the statistical association between the query feature and the query intent for at least one of the entries.

32. The method according to claim 29, further comprising:

identifying, by the computer system, a response associated with each of the plurality of intent guesses;

identifying, by the computer system, an order for the plurality of intent guesses based on the statistical associations between the query feature and the query intent for each or the selected plurality of entries of the model; and

displaying, by the computer system, based on the determined order the response along with the associated intent guess or the response instead of the associated intent guess.

33. The method according to claim 32, wherein the responses include links to web pages or additional information associated with the intent guesses.

34. The method according to claim 29, further comprising:

identifying, by the computer system, an order for the plurality of intent guesses based on the statistical associations between the query feature and the query intent for each or the selected plurality of entries of the model; and

displaying, by the computer system, the intent guesses in the identified order.

35. The method of claim 29, wherein the intent guesses do not include a text string that exactly matches the particular text string.

36. The method of claim 29, wherein the intent guesses do not include a same set of words as the particular text string.

37. The method of claim 36, wherein the intent guesses do not include any same words as the particular text string.

38. A method of processing a current user query, comprising:

training a model, said training comprising;

logging previous user queries;

extracting a question from the logged previous user queries;

analyzing the extracted question to obtain at least one feature;

assigning an intent to the extracted question; and

adding an entry to the model and mapping the obtained feature for the extracted question to the assigned intent for the extracted question in the added entry of the model;

receiving an initial portion of the current user query, wherein the initial portion includes a particular string of text;

guessing an intent associated with the initial portion of the current user query while a remainder of the current user query is being received, wherein said guessing using only the initial portion further comprises;

analyzing the initial portion to obtain at least one feature;

comparing, using a processing device, the obtained at least one feature of the initial portion to entries in the model;

selecting, using the processing device, at least one entry from the model based on the comparison; and

determining the intent for the initial portion of the current user query according to an intent included in the selected entry;

wherein the intent guess obtained for the initial portion according to said analyzing, said comparing, said selecting, and said determining, does not include a text string that matches the particular text string; and

responding to the initial portion of the current user query with the intent guess.

39. The method according to claim 38, further comprising:

identifying a parameterized intent guess that includes at least one concept;

identifying words in the current user query that are associated with the concept;

modifying the parameterized intent guess by replacing the concept with the identified words from the current user query; and

responding to the current user query with the modified parameterized intent guess.

40. The method according to claim 38, further comprising:

identifying a response associated with the intent guess; and

either displaying the response along with the associated intent guess or displaying the response instead of the associated intent guess.

41. The method according to claim 38, further comprising:

identifying a plurality of intent guesses associated with the current user query;

identifying an order for the intent guesses of the plurality according to how well the intent guesses match the current user query; and

displaying the intent guesses in the identified order.