Feedback enhanced attribute extraction

• US 9,087,084 B1
• Filed: 09/14/2012
• Issued: 07/21/2015
• 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): Perveen, Rehana
• Assistant Examiner(s): Bui, Tiffany Thuy
• Application Number:
  US13/620,641
• Time in Patent Office: 1,040 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 data object from a user device, wherein the data object is an uploaded document;

analyzing, using one or more computers having one or more processors and one or more non-transitory computer storage media, the data object to extract a plurality of values having corresponding attributes, wherein the analysis is based at least in part on an ontology and wherein the analysis is used to extract one or more values from the data object as corresponding to ontology terms and one or more candidate ontology terms associated with respective attributes, wherein the analysis of the data object further comprises associating the data object with one or more domain models generated through analysis of a plurality of objects from one or more corpora;

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 plurality of values paired with its corresponding attribute accurately characterizes the data object, 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;

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;

in response to the indication that the attribute-value pair accurately characterizes the data object, analyzing the attribute-value pair to determine if the attribute and the value are in the ontology;

if it is determined that the attribute is not in the ontology, updating the ontology to add the attribute to the ontology;

if it is determined that the value is not in the ontology, updating the ontology to add the value to the ontology; and

training the analysis to extract values from additional received data objects according to the updated ontology.

2. The method of claim 1, wherein each of one or more of the plurality of values are assigned to a corresponding attribute for the value that is associated with a respective confidence value that satisfies a threshold.

3. The method of claim 1, wherein the values are text values.

4. The method of claim 1, wherein the candidate ontology term is added to the ontology if the response indicates that the attribute-value pair accurately characterizes the data object.

5. The method of claim 1, wherein the extracted plurality of values having corresponding attributes are associated with attribute-value pairs in the plurality of domain models.

6. The method of claim 1, wherein the data object comprises a text file.

7. The method of claim 1, wherein the data object comprise an audio file.

8. A system comprising:

a user device; and

one or more computers having one or more processors and one or more non-transitory computer storage media, the one or more computers configured to interact with the user device and to perform operations comprising;

receiving a data object from a user device, wherein the data object is an uploaded document;

analyzing the data object to extract a plurality of values having corresponding attributes, wherein the analysis is based at least in part on an ontology and wherein the analysis is used to extract one or more values from the data object as corresponding to ontology terms and one or more candidate ontology terms associated with respective attributes, wherein the analysis of the data object further comprises associating the data object with one or more domain models generated through analysis of a plurality of objects from one or more corpora;

providing a user interface to the user device, the user interface configured to present at least one question as to whether an extracted value of the plurality of values paired with its corresponding attribute accurately characterizes the data object, 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;

receiving a response to the at least one question from the user device though the user interface indicating that the attribute-value pair accurately characterizes the data object;

in response to the indication that the attribute-value pair accurately characterizes the data object, analyzing the attribute-value pair to determine if the attribute and the value are in the ontology;

if it is determined that the attribute is not in the ontology, updating the ontology to add the attribute to the ontology;

if it is determined that the value is not in the ontology, updating the ontology to add the value to the ontology; and

training the analysis to extract values from additional received data objects according to the updated ontology.

9. The system of claim 8, wherein each of one or more of the plurality of values are assigned to a corresponding attribute for the value that is associated with a respective confidence value that satisfies a threshold.

10. The system of claim 8, wherein the values are text values.

11. The system of claim 8, wherein the candidate ontology term is added to the ontology if the response indicates that the attribute-value pair accurately characterizes the data object.

12. The system of claim 8, wherein the extracted plurality of values having corresponding attributes are associated with attribute-value pairs in the plurality of domain models.

13. The system of claim 8, wherein the data object comprises a text file.

14. The system of claim 8, wherein the data object comprise an audio file.

15. A non-transitory computer storage medium encoded with a computer program, the program comprising instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

receiving a data object from a user device, wherein the data object is an uploaded document;

analyzing the data object to extract a plurality of values having corresponding attributes, wherein the analysis is based at least in part on an ontology and wherein the analysis is used to extract one or more values from the data object as corresponding to ontology terms and one or more candidate ontology terms associated with respective attributes, wherein the analysis of the data object further comprises associating the data object with one or more domain models generated through analysis of a plurality of objects from one or more corpora;

providing a user interface to the user device, the user interface configured to present at least one question as to whether an extracted value of the plurality of values paired with its corresponding attribute accurately characterizes the data object, 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;

receiving a response to the at least one question from the user device though the user interface indicating that the attribute-value pair accurately characterizes the data object;

in response to the indication that the attribute-value pair accurately characterizes the data object, analyzing the attribute-value pair to determine if the attribute and the value are in the ontology;

if it is determined that the attribute is not in the ontology, updating the ontology to add the attribute to the ontology;

if it is determined that the value is not in the ontology, updating the ontology to add the value to the ontology; and

training the analysis to extract values from additional received data objects according to the updated ontology.