Resolving pronoun ambiguity in voice queries

• US 10,635,860 B1
• Filed: 06/15/2018
• Issued: 04/28/2020
• Est. Priority Date: 06/01/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Taubman, Gabriel, Lee, John J.
• Primary Examiner(s): Patel, Shreyans A
• Application Number:
  US16/009,529
• Time in Patent Office: 683 Days
• CPC Class Codes: G06F 16/635 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 25/87 Detection of discrete points within a voice signal

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for resolving ambiguity in received voice queries. An original voice query is received following one or more earlier voice queries, wherein the original voice query includes a pronoun or phrase. In one implementation, a plurality of acoustic parameters is identified for one or more words in the original voice query. A concept represented by the pronoun is identified based on the plurality of acoustic parameters, wherein the concept is associated with a particular query of the one or more earlier queries. The concept is associated with the pronoun. Alternatively, a concept may be associated with a phrase by using grammatical analysis of the query to relate the phrase to a concept derived from a prior query.

Claims

1. A computer-implemented method comprising,

receiving, by a server, a particular voice query that is based on an utterance of a user that was detected by a microphone of a device that is located remotely from the server;

determining, by the server, that at least a portion of the voice query includes a phrase that refers to a concept related to at least one query of a plurality of other queries that were received by the server before the particular voice query;

obtaining, by the server, the phrase that refers to the concept;

determining, by the server, that the phrase includes a determiner word;

identifying, by the server, an object word of the determiner word;

determining, based on the identified object word, a set of hypernyms for the object word;

determining, by the server, a value that reflects a level of similarity between the obtained portion of the particular voice query and each of the plurality of queries that were previously received by the server, wherein determining the value comprises;

comparing the obtained phrase and the set of hypernyms to each of the plurality of queries, and

determining, based on the comparison of the obtained phrase and the set of hypernyms to each of the plurality of queries, a value that reflects a level of similarity between the obtained portion of the particular voice query and each of the plurality of queries that were previously received;

identifying, by the server and based on the determined value that reflects the level of similarity, a first query of the plurality of queries; and

generating, by the server, a data structure that includes data representing an association between the concept of the first query and the particular voice query.

2. The method of claim 1, wherein determining, by the server, a value that reflects a level of similarity between the obtained portion of the particular voice query and each of the plurality of queries that were previously received by the server further comprises:

comparing the obtained phrase to each of the plurality of queries; and

determining, based on the comparison of the obtained phrase to each of the plurality of queries, a value that reflects a level of similarity between the obtained portion of the particular voice query and each of the plurality of queries that were previously received.

3. The method of claim 1, wherein comparing the obtained phrase and the set of hypernyms to each of the plurality of queries comprises:

for each query of the plurality of queries;

evaluating one or more factors that includes respective distance between terms of the obtained phrase and distance between terms of the query, a number of shared hypernyms between the obtained phrase and the query, or a longest term of the obtained phrase to a longest term of the query.

4. The method of claim 1, wherein generating, by the server, a data structure that includes data representing an association between the concept of the first query with the particular voice query comprises:

generating, by the server, a second search query that is based on the concept of the first query and the particular query.

5. The method of claim 4, the method further comprising:

executing, by the server, a search of one or more databases using the generated second query;

generating, by the server, one or more search results that are responsive to the executed search; and

providing, by the server, data describing the one or more search results to the device for output by the device using the speaker of the device.

6. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by one or more computers, to cause the one or more computers to perform the operations comprising;

receiving, by a server, a particular voice query that is based on an utterance of a user that was detected by a microphone of a device that is located remotely from the server;

determining, by the server, that at least a portion of the voice query includes a phrase that refers to a concept related to at least one query of a plurality of other queries that were received by the server before the particular voice query;

obtaining, by the server, the phrase that refers to the concept;

determining, by the server, that the phrase includes a determiner word;

identifying, by the server, an object word of the determiner word;

determining, based on the identified object word, a set of hypernyms for the object word;

determining, by the server, a value that reflects a level of similarity between the obtained portion of the particular voice query and each of the plurality of queries that were previously received by the server, wherein determining the value comprises;

comparing the obtained phrase and the set of hypernyms to each of the plurality of queries, and

determining, based on the comparison of the obtained phrase and the set of hypernyms to each of the plurality of queries, a value that reflects a level of similarity between the obtained portion of the particular voice query and each of the plurality of queries that were previously received;

identifying, by the server and based on the determined value that reflects the level of similarity, a first query of the plurality of queries; and

generating, by the server, a data structure that includes data representing an association between the concept of the first query and the particular voice query.

7. The system of claim 6, wherein determining, by the server, a value that reflects a level of similarity between the obtained portion of the particular voice query and each of the plurality of queries that were previously received by the server further comprises:

comparing the obtained phrase to each of the plurality of queries; and

determining, based on the comparison of the obtained phrase to each of the plurality of queries, a value that reflects a level of similarity between the obtained portion of the particular voice query and each of the plurality of queries that were previously received.

8. The system of claim 6, wherein comparing the obtained phrase and the set of hypernyms to each of the plurality of queries comprises:

for each query of the plurality of queries;

evaluating one or more factors that includes respective distance between terms of the obtained phrase and distance between terms of the query, a number of shared hypernyms between the obtained phrase and the query, or a longest term of the obtained phrase to a longest term of the query.

9. The system of claim 6, wherein generating, by the server, a data structure that includes data representing an association between the concept of the first query with the particular voice query comprises:

generating, by the server, a second search query that is based on the concept of the first query and the particular query.

10. The system of claim 9, the operations further comprising:

executing, by the server, a search of one or more databases using the generated second query;

generating, by the server, one or more search results that are responsive to the executed search; and

providing, by the server, data describing the one or more search results to the device for output by the device using the speaker of the device.

11. A computer-readable storage device having stored thereon instructions, which, when executed by data processing apparatus, cause the data processing apparatus to perform operations comprising:

receiving, by a server, a particular voice query that is based on an utterance of a user that was detected by a microphone of a device that is located remotely from the server;

determining, by the server, that at least a portion of the voice query includes a phrase that refers to a concept related to at least one query of a plurality of other queries that were received by the server before the particular voice query;

obtaining, by the server, the phrase that refers to the concept;

determining, by the server, that the phrase includes a determiner word;

identifying, by the server, an object word of the determiner word;

determining, based on the identified object word, a set of hypernyms for the object word;

determining, by the server, a value that reflects a level of similarity between the obtained portion of the particular voice query and each of the plurality of queries that were previously received by the server, wherein determining the value comprises;

comparing the obtained phrase and the set of hypernyms to each of the plurality of queries, and

determining, based on the comparison of the obtained phrase and the set of hypernyms to each of the plurality of queries, a value that reflects a level of similarity between the obtained portion of the particular voice query and each of the plurality of queries that were previously received;

identifying, by the server and based on the determined value that reflects the level of similarity, a first query of the plurality of queries; and

generating, by the server, a data structure that includes data representing an association between the concept of the first query and the particular voice query.

12. The computer-readable storage device of claim 11, wherein determining, by the server, a value that reflects a level of similarity between the obtained portion of the particular voice query and each of the plurality of queries that were previously received by the server further comprises:

comparing the obtained phrase to each of the plurality of queries; and

determining, based on the comparison of the obtained phrase to each of the plurality of queries, a value that reflects a level of similarity between the obtained portion of the particular voice query and each of the plurality of queries that were previously received.

13. The computer-readable storage device of claim 11, wherein comparing the obtained phrase and the set of hypernyms to each of the plurality of queries comprises:

for each query of the plurality of queries;

evaluating one or more factors that includes respective distance between terms of the obtained phrase and distance between terms of the query, a number of shared hypernyms between the obtained phrase and the query, or a longest term of the obtained phrase to a longest term of the query.

14. The computer-readable storage device of claim 11,

wherein generating, by the server, a data structure that includes data representing an association between the concept of the first query with the particular voice query comprises:

generating, by the server, a second search query that is based on the concept of the first query and the particular query;

wherein the operations further comprise;

executing, by the server, a search of one or more databases using the generated second query;

generating, by the server, one or more search results that are responsive to the executed search; and

providing, by the server, data describing the one or more search results to the device for output by the device using the speaker of the device.