Attribute extraction

• US 9,336,290 B1
• Filed: 07/02/2015
• Issued: 05/10/2016
• Est. Priority Date: 01/23/2007
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Truher, Joel
• Primary Examiner(s): Phillips, III, Albert
• Assistant Examiner(s): Bui, Tiffany Thuy
• Application Number:
  US14/791,071
• Time in Patent Office: 313 Days
• Field of Search: 707/706, 707/708
• US Class Current: 1/1
• CPC Class Codes: G06F 16/21 Design, administration or maintenance of databases
• CPC Class Codes: G06F 16/254 Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: H04L 67/1085 involving dynamic management of active down- or uploading connections

Abstract

A data object submitted for storage is analyzed, and a set of values is extracted from the data object that can correspond to a set of attributes. The analysis of the data object can also identify possible new ontology terms. One or more extracted values are presented to the entity which submitted the data object for approval and feedback. This feedback can be used to characterize the data object with appropriate terms, train the extraction process for future extractions, and/or expand the set of known ontology terms.

Claims

1. A method comprising:

receiving a document from a user device;

analyzing the document to extract a plurality of values having corresponding attributes associated with attribute-value pairs in one or more domain models, wherein the analysis is based at least in part on associating the document with the one or more domain models of a plurality of domain models generated through analysis of a plurality of documents from one or more corpora and using an ontology associated with the one or more domain models to determine one or more attributes from the document, wherein the ontology includes terms relevant to particular domains corresponding to the one or more domain models, and wherein the attributes from the document are associated with particular terms of the ontology;

associating the determined one or more attributes with the document; and

using the associated attributes to generate search results responsive to a received search query.

2. The method of claim 1, wherein the analysis is used to extract one or more values from the document as corresponding to ontology terms and one or more candidate ontology terms associated with respective attributes.

3. The method of claim 2, comprising providing a user interface to a client, the user interface configured to present at least one question as to whether an extracted value of the one or more values paired with its corresponding attribute accurately characterizes the document, wherein at least one extracted value paired with its corresponding attribute is a candidate ontology term not found in the ontology and is presented in the at least one question.

4. The method of claim 3, comprising receiving a response to the at least one question from the client though the user interface indicating that the attribute-value pair accurately characterizes the data object.

5. A system comprising:

one or more computers including one or more storage devices and one or more processor devices configured to perform operations comprising;

receiving a document from a user device;

analyzing the document to extract a plurality of values having corresponding attributes associated with attribute-value pairs in one or more domain models, wherein the analysis is based at least in part on associating the document with the one or more domain models generated through analysis of a plurality of documents from one or more corpora and using an ontology associated with the one or more domain models to determine one or more attributes from the document, wherein the ontology includes terms relevant to particular domains corresponding to the one or more domain models, and wherein the attributes from the document are associated with particular terms of the ontology;

associating the determined one or more attributes with the document; and

using the associated attributes to generate search results responsive to a received search query.

6. The system of claim 5, wherein the analysis is used to extract one or more values from the document as corresponding to ontology terms and one or more candidate ontology terms associated with respective attributes.

7. The system of claim 6, comprising providing a user interface to a client, the user interface configured to present at least one question as to whether an extracted value of the one or more values paired with its corresponding attribute accurately characterizes the document, wherein at least one extracted value paired with its corresponding attribute is a candidate ontology term not found in the ontology and is presented in the at least one question.

8. The system of claim 7, comprising receiving a response to the at least one question from the client though the user interface indicating that the attribute-value pair accurately characterizes the data object.

9. A method comprising:

analyzing a document using one or more trained classifiers to extract a plurality of text values from the document and determine corresponding attributes for the text values based at least in part on an ontology containing a plurality of ontology terms relevant to a particular area of interest and that are associated with particular attributes, wherein each of the corresponding attributes is associated with a respective confidence value determined by one of the trained classifiers, wherein the confidence value represents a level of confidence in assigning the respective attribute to the document;

in response to a particular text value that is associated with a confidence value that does not satisfy a threshold but is greater than a minimum confidence value, presenting the corresponding attribute as a question to a client user;

assigning each of one or more of the plurality of text values to a corresponding attribute for the text value that is associated with a respective confidence value that satisfies the threshold;

associating the attributes with the document; and

using the associated attributes to generate search results responsive to a received search query.

10. The method of claim 9, comprising:

providing a user interface to a client, the user interface configured to present at least one question as to whether an extracted text value of the plurality of text values paired with its assigned attribute accurately characterizes the document.

11. The method of claim 10, wherein at least one extracted text value is a candidate ontology term not found in the ontology and is presented in the at least one question.

12. The method of claim 9, comprising analyzing a plurality of objects from a corpora to generate one or more domain models, and wherein analyzing the document comprises associating the data object with the domain models.

13. A system comprising:

one or more computers including one or more storage devices and one or more processor devices configured to perform operations comprising;

analyzing a document using one or more trained classifiers to extract a plurality of text values from the document and determine corresponding attributes for the text values based at least in part on an ontology, wherein each of the corresponding attributes is associated with a respective confidence value determined by one of the trained classifiers;

in response to a particular text value that is associated with a confidence value that does not satisfy a threshold but is greater than a minimum confidence value, presenting the corresponding attribute as a question to a client user;

assigning each of one or more of the plurality of text values to a corresponding attribute for the text value that is associated with a respective confidence value that satisfies the threshold;

associating the attributes with the document; and

using the associated attributes to generate search results responsive to a received search query.

14. The system of claim 13, comprising:

providing a user interface to a client, the user interface configured to present at least one question as to whether an extracted text value of the plurality of text values paired with its assigned attribute accurately characterizes the document.

15. The system of claim 13, wherein at least one extracted text value is a candidate ontology term not found in the ontology and is presented in the at least one question.

16. The system of claim 13, comprising analyzing a plurality of objects from a corpora to generate one or more domain models, and wherein analyzing the document comprises associating the data object with the domain models.