Identifying underserved command inputs

• US 9,812,124 B1
• Filed: 06/15/2017
• Issued: 11/07/2017
• Est. Priority Date: 06/25/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Uszkoreit, Jakob D., Liang, Percy, Bikel, Daniel M.
• Primary Examiner(s): Neway, Samuel G
• Application Number:
  US15/624,339
• Time in Patent Office: 145 Days
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

A language processing system identifies first command input sentences that do not successfully parse by any parsing rule in a set of parsing rules. Each of the parsing rules is associated with an action, and a user device performs the action associated with a parsing rule in response to an input sentence being successfully parsed by the parsing rule. For each of these identified first sentences, the system determines whether the first input sentence has an underserving signal that is indicative of one or more actions being underserved. If the first sentence has the underserving signal, then the first sentence is selected as a candidate input sentence. Each candidate input sentence is provided to an action analysis processes that determines whether a candidate input sentence is to be associated with one action, and upon a positive determination generates a parsing rule for the candidate input sentence.

Claims

1. A computer-implemented method performed by a data processing apparatus, the method comprising:

identifying, from input sentences, first input sentences that do not successfully parse by any parsing rule in a set of parsing rules, each of the parsing rules being associated with an action, and wherein each parsing rule causes a user device to perform the action associated with the parsing rule in response to an input sentence received from the user device being successfully parsed by the parsing rule;

selecting, from the first input sentences, candidate input sentences, the selection of each candidate input sentence based on data from user interactions in response to data provided in response to the first input sentence; and

for each candidate input sentence, determining whether the candidate input sentence is to be associated with one of a plurality of actions and upon a positive determination generates a parsing rule for the candidate input sentence, wherein the generated parsing rule is associated with the one of the plurality of actions and a successful parse of an input sentence received at a user device by the generated parsing rule causes the user device to perform the one of the plurality of actions associated with the generated parsing rule.

2. The computer-implemented method of claim 1, further comprising persisting each generated parsing rule and data describing the action with which the generated parsing rule is associated to command models data that is accessible by a language processing system that parses command input sentences by the generated parsing rules and determines actions to perform based on a successful parses.

3. The computer-implemented method of claim 2, wherein selecting, from the first input sentences, candidate input sentences, comprises determining, for each first input sentence, a quality score is a measure of user satisfaction that is dependent on user interactions.

4. The computer-implemented method of claim 3, wherein determining the quality score comprises, for each first input sentence:

determining that the first input sentence was processed as an input request;

determining a quality metric value for data provided in response to the input request; and

determining the quality score from the quality metric value.

5. The computer-implemented method of claim 1, wherein the input sentences are generated from voice command inputs.

6. The computer-implemented method of claim 1, wherein the parsing rules are grammar based rules.

7. A non-transitory computer readable storage medium storing instructions executable by a data processing apparatus and that upon such execution causes the data processing apparatus to perform operations comprising:

identifying, from input sentences, first input sentences that do not successfully parse by any parsing rule in a set of parsing rules, each of the parsing rules being associated with an action, and wherein each parsing rule causes a user device to perform the action associated with the parsing rule in response to an input sentence received from the user device being successfully parsed by the parsing rule;

selecting, from the first input sentences, candidate input sentences, the selection of each candidate input sentence based on data from user interactions in response to data provided in response to the first input sentence; and

for each candidate input sentence, determining whether the candidate input sentence is to be associated with one of a plurality of actions and upon a positive determination generates a parsing rule for the candidate input sentence, wherein the generated parsing rule is associated with the one of the plurality of actions and a successful parse of an input sentence received at a user device by the generated parsing rule causes the user device to perform the one of the plurality of actions associated with the generated parsing rule.

8. The non-transitory computer readable storage medium of claim 7, further comprising persisting each generated parsing rule and data describing the action with which the generated parsing rule is associated to command models data that is accessible by a language processing system that parses command input sentences by the generated parsing rules and determines actions to perform based on a successful parses.

9. The non-transitory computer readable storage medium of claim 8, wherein selecting, from the first input sentences, candidate input sentences, comprises determining, for each first input sentence, a quality score is a measure of user satisfaction that is dependent on user interactions.

10. The non-transitory computer readable storage medium of claim 9, wherein determining the quality score comprises, for each first input sentence:

determining that the first input sentence was processed as an input request;

determining a quality metric value for data provided in response to the input request; and

determining the quality score from the quality metric value.

11. The non-transitory computer readable storage medium of claim 7, wherein the input sentences are generated from voice command inputs.

12. The non-transitory computer readable storage medium of claim 7, wherein the parsing rules are grammar based rules.

17. The system of claim 8, wherein the input sentences are generated from voice command inputs.

18. The system of claim 8, wherein the parsing rules are grammar based rules.

13. A system, comprising:

a data processing apparatus; and

a non-transitory computer readable storage medium in data communication with the data processing apparatus storing instructions executable by the data processing apparatus and that upon such execution causes the data processing apparatus to perform operations comprising;

identifying, from input sentences, first input sentences that do not successfully parse by any parsing rule in a set of parsing rules, each of the parsing rules being associated with an action, and wherein each parsing rule causes a user device to perform the action associated with the parsing rule in response to an input sentence received from the user device being successfully parsed by the parsing rule;

selecting, from the first input sentences, candidate input sentences, the selection of each candidate input sentence based on data from user interactions in response to data provided in response to the first input sentence; and

for each candidate input sentence, determining whether the candidate input sentence is to be associated with one of a plurality of actions and upon a positive determination generates a parsing rule for the candidate input sentence, wherein the generated parsing rule is associated with the one of the plurality of actions and a successful parse of an input sentence received at a user device by the generated parsing rule causes the user device to perform the one of the plurality of actions associated with the generated parsing rule.

14. The system of claim 13, the operations further comprising persisting each generated parsing rule and data describing the action with which the generated parsing rule is associated to command models data that is accessible by a language processing system that parses command input sentences by the generated parsing rules and determines actions to perform based on a successful parses.

15. The system of claim 14, wherein selecting, from the first input sentences, candidate input sentences, comprises determining, for each first input sentence, a quality score is a measure of user satisfaction that is dependent on user interactions.

16. The system of claim 15, wherein determining the quality score comprises, for each first input sentence:

determining that the first input sentence was processed as an input request;

determining a quality metric value for data provided in response to the input request; and

determining the quality score from the quality metric value.