Inferring informational goals and preferred level of detail of answers based on application employed by the user based at least on informational content being displayed to the user at the query is received

• US 7,778,820 B2
• Filed: 08/04/2008
• Issued: 08/17/2010
• Est. Priority Date: 06/29/2001
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Zukerman, Ingrid, Horvitz, Eric J.
• Primary Examiner(s): OPSASNICK, MICHAEL N
• Application Number:
  US12/185,753
• Publication Number:
  US 20090037398A1
• Time in Patent Office: 743 Days
• Field of Search: None
• US Class Current: 704/9
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

A system and method for inferring informational goals and preferred level of details in answers in response to questions posed to computer-based information retrieval or question-answering systems is provided. The system includes a query subsystem that can receive an input query and extrinsic data associated with the query and which can output an answer to the query, and/or rephrased queries or sample queries. The query subsystem accesses an inference model to retrieve conditional probabilities that certain informational goals are present. One application of the system includes determining a user'"'"'s likely informational goals and then accessing a knowledge data store to retrieve responsive information. The system includes a natural language processor that parses queries into observable linguistic features and embedded semantic components that can be employed to retrieve the conditional probabilities from the inference model. The inference model is built by employing supervised learning and statistical analysis on a set of queries suitable to be presented to a question-answering system. Such a set of queries can be manipulated to produce different inference models based on demographic and/or localized linguistic data.

Claims

1. A system for inferring an information goal given a query, comprising:

a query subsystem that receives a user query and extrinsic data relating to the user, the query subsystem operatively coupled to an inference model and a knowledge data store, the query subsystem comprising;

an inference engine that infers one or more informational goals and a preferred level of detail for an answer to the query,

the inference based at least in part on the query,

the extrinsic data, and

inference data stored in the inference model, wherein the extrinsic data includes at least informational content being displayed to the user at the time the query is received.

2. The system of claim 1, where the informational goals include at least one of a type of information requested in the query, a topic of the query, and a focal point of the query.

3. The system of claim 2, comprising:

an input query log that stores one or more queries and one or more pieces of extrinsic data; and

a learning system operatively coupled to the input query log, the learning system produces and refines the inference model.

4. The system of claim 3, where the learning system comprises:

a natural language processor that parses the query to produce linguistic data relating to one or more linguistic features;

a tagging tool that facilitates manipulating the linguistic data; and

one or more taggers that manipulates the linguistic data.

5. The system of claim 4, wherein the linguistic data comprises a parse tree, the parse tree containing extractable information concerning the nature of and relationships between observable linguistic features.

6. The system of claim 5, wherein the observable linguistic features in the extractable information comprise at least one of word-based features, structural features, and hybrid linguistic features.

7. The system of claim 6, wherein the word-based features indicate the presence of one or more candidate terms useful in predicting an informational goal.

8. The system of claim 4, wherein the inference model comprises one or more decision trees, the decision trees storing conditional probabilities associated with one or more informational goals, the decision trees traversable by the linguistic data.

9. The system of claim 3, wherein the natural language processor parses the query into one or more parts suitable for retrieving one or more conditional probabilities stored in the inference model.

10. The system of claim 9, wherein the one or more parts comprise at least one of logical forms, adjectival phrases, adverbial phrases, noun phrases, verb phrases, prepositional phrases, or parse trees.

11. The system of claim 10, the inference engine infers one or more informational goals based on at least one of the query, the extrinsic data, the one or more parts, or the one or more conditional probabilities stored in the inference model.

12. The system of claim 3, the query subsystem further comprising an answer generator that produces one or more responses to the query, wherein the one or more responses are based at least on the inferred informational goals and the preferred level of detail.

13. The system of claim 12, wherein the one or more responses vary in at least one of length, precision, or detail based at least on the inferred informational goals and the preferred level of detail.

14. A method using a microprocessor for presenting answers to queries, comprising:

receiving a query from a user;

parsing the query into component parts of speech and logical forms to produce parse data;

receiving extrinsic data relating to the user, the extrinsic data including at least informational content being displayed to the user at the time the query is received;

employing the parse data and the extrinsic data to infer one or more informational goals and a preferred level of detail for answers to the query;

generating at least one answer to the query in accordance with the inferred informational goals and preferred level of detail.

15. The method of claim 14, wherein parsing the query comprises determining at least one of sentence structure, sentence length, sentence phrasing, common word regularity, or common word non-regularity.

16. The method of claim 14, further comprising selecting a set of resources in which to search for an answer to the query based at least on the inferred informational goals.

17. The method of claim 14, further comprising presenting a user interface dialog to the user to facilitate manual confirmation of the inferred level of detail or the extrinsic data.

18. The method of claim 14, further comprising

submitting the parse data to a decision model storing conditional probabilities concerning a likelihood that specific informational goals are related to a query;

and

retrieving predicted informational goals from the decision model given the submitted parse data.

19. The method of claim 18, further comprising selecting the decision model based at least on linguistic data parsed from the query.

20. A system for generating a response to a query at a preferred level of detail, comprising:

means for inputting a query from a user;

means for parsing the query into component parts of speech and logical forms to produce parse data;

means for employing the parse data to access a decision model, the decision model storing conditional probabilities concerning a likelihood that specific informational goals are related to a query;

means for receiving extrinsic data, the extrinsic data including at least informational content displayed to the user at the time the query is inputted;

means for employing the decision model and the extrinsic data to infer one or more informational goals associated with the query and a preferred level of detail for an response to the query; and

means for producing a response to the query in accordance with the inferred informational goals and preferred level of detail.