Recommending results in multiple languages for search queries based on user profile

• US 10,769,210 B2
• Filed: 09/29/2017
• Issued: 09/08/2020
• Est. Priority Date: 09/29/2017
• Status: Active Grant

• Current Assignee: ROVI Product Corporation (Xperi Inc.)
• Original Assignee: Rovi Guides, Inc. (Adeia Inc.)
• Inventors: Sreedhara, Arun
• Primary Examiner(s): Ly, Cheyne D
• Application Number:
  US15/720,917
• Publication Number:
  US 20190102480A1
• Time in Patent Office: 1,075 Days
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/953 Querying, e.g. by the use of web search engines
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: G10L 25/54 for retrieval

Abstract

Systems and methods for a media guidance application that generates results in multiple languages for search queries. In particular, the media guidance application resolves multiple language barriers by taking automatic and manual user language settings and applying those settings to a variety of potential search results.

Claims

1. A method for generating results for search queries based on multiple language models, comprising:

receiving, via an audio input device, a first voice query from a user, wherein the user corresponds to a user profile that is stored in memory;

applying a first language model, based on the user profile, to the first voice query to identify a first plurality of search results based on the first voice query, wherein the first language model corresponds to a first language;

generating for display, on a display device, the first plurality of search results;

retrieving first metadata for a first search result of the first plurality of search results and second metadata for a second search result of the first plurality of searcch results;

automatically determining, using control circuitry, that the first metadata for the first search result of the first plurality of search results indicates that the first search result corresponds to a first language;

automatically determining, using control circuitry, that the second metadata for the second search result of the first plurality of search results indicates that the second search result corresponds to a second language;

in response to determining that the second metadata for the second search result of the first plurality of search results indicates that the second search result corresponds to a second language, updating the user profile to apply the second language model to searches, wherein the second language model corresponds to the second language;

receiving a second voice query from the user;

applying both the first language model and the second language model, based on the updated user profile, to the second voice query to identify a second plurality of search results based on the second voice query; and

generating for display, on the display device, the second plurality of search results.

2. The method of claim 1, wherein the user profile is automatically updated, without user input, in response to determining that the second metadata for the second search result of the first plurality of search results indicates that the second search result corresponds to the second language.

3. The method of claim 2, wherein the user profile is updated after receiving a user confirmation to apply the second language model to searches, wherein a prompt for receiving the user confirmation is generated for display in response to determining that the second metadata for the second search result of the first plurality of search results indicates that the second search result corresponds to the second language.

4. The method of claim 3, wherein updating the user profile further comprises:

retrieving a language setting from the user profile;

comparing a language corresponding to the language setting to the second language; and

determining that the second language does not correspond to the language corresponding to the language setting.

5. The method of claim 4, further comprising:

in response to determining that the first metadata for the first search result of the first plurality of search results indicates that the first search result corresponds to the first language, maintaining a language setting in the user profile that applies the first language model to searches.

6. The method of claim 5, further comprising:

automatically determining that the second metadata for the second search result of the first plurality of search results also indicates that the second search result corresponds to a first dialect of the second language;

in response to determining that the second metadata for the second search result of the first plurality of search results also indicates that the second search result corresponds to the first dialect of the second language, updating the user profile to apply a third language model to searches, wherein the third language model corresponds to the first dialect of the second language.

7. The method of claim 6, wherein the first language model indicates a first set of phonemes used to identify the first plurality of search results.

8. The method of claim 7, further comprising:

parsing the first voice query to identify a first audio segment and a second audio segment based on audible breaks in the first voice query; and

comparing the first audio segment to the first set of phonemes to determine a first resolved word corresponding to the first audio segment; and

determining a first text query based on the first resolved word.

9. The method of claim 8, wherein applying the first language model, based on the user profile, to the first voice query to identify the first plurality of search results based on the first voice query further comprises:

determining a first numerical ranking for the first resolved word in the first language and a second numerical ranking for a second resolved word in the first language based on a likelihood of usage of the first resolved word in the first language and the second resolved word in the first language; and

determining a first composite score for the first text query based on summing the first numerical ranking and the second numerical ranking.

10. The method of claim 9, further comprising generating for display, on the display device, a first search result for the first text query, wherein the first search result is ordered among search results based on the first composite ranking.

11. A system for generating results for search queries based on multiple language models, comprising:

memory configured to store a plurality of language models; and

control circuitry configured to;

receive, via an audio input device, a first voice query from a user, wherein the user corresponds to a user profile that is stored in memory;

apply a first language model, based on the user profile, to the first voice query to identify a first plurality of search results based on the first voice query, wherein the first language model corresponds to a first language;

generate for display, on a display device, the first plurality of search results;

retrieve first metadata for a first search result of the first plurality of search results and second metadata for a second search result of the plurality of search results;

determine that the first metadata for the first search result of the first plurality of search results indicates that the first search result corresponds to a first language;

determine that the second metadata for the second search result of the first plurality of search results indicates that the second search result corresponds to a second language;

determine that the second metadata for the second search result of the first plurality of search results indicates that the second search result corresponds to the second language, and thus updates the user profile to apply a second language model to searches, wherein the second language model corresponds to the second language;

receive a second voice query from the user;

apply both the first language model and the second language model, based on the updated user profile, to the second voice query to identifying a second plurality of search results based on the second voice query; and

generate for display, on the display device, the second plurality of search results.

12. The system of claim 11, wherein the user profile is automatically updated, without user input, in response to determining that the second metadata for the second search result of the first plurality of search results indicates that the second search result corresponds to the second language.

13. The system of claim 12, wherein the user profile is updated after receiving a user confirmation to apply the second language model to searches, wherein a prompt for receiving the user confirmation is generated for display in response to determining that the second metadata for the second search result of the first plurality of search results indicates that the second search result corresponds to the second language.

14. The system of claim 13, wherein updating the user profile further comprises:

retrieving a language setting from the user profile;

comparing a language corresponding to the language setting to the second language; and

determining that the second language does not correspond to the language corresponding to the language setting.

15. The system of claim 14, wherein updating the user profile further comprises:

retrieving a language setting from the user profile;

comparing a language corresponding to the language setting to the second language; and

determining that the second language does not correspond to the language corresponding to the language setting.

16. The system of claim 15, wherein the control circuitry is further configured to:

automatically determine that the second metadata for the second search result of the first plurality of search results also indicates that the second search result corresponds to a first dialect of the second language;

in response to determining that the second metadata for the second search result of the first plurality of search results also indicates that the second search result corresponds to the first dialect of the second language, update the user profile to apply a third language model to searches, wherein the third language model corresponds to the first dialect of the second language.

17. The system of claim 16, wherein the first language model indicates a first set of phonemes used to identify the first plurality of search results.

18. The system of claim 17, wherein the control circuitry is further configured to:

parse the first voice query to identify a first audio segment and a second audio segment based on audible breaks in the first voice query; and

compare the first audio segment to the first set of phonemes to determine a first resolved word corresponding to the first audio segment; and

determine a first text query based on the first resolved word.

19. The system of claim 18, wherein applying the first language model, based on the user profile, to the first voice query to identify the first plurality of search results based on the first voice query further comprises:

determining a first numerical ranking for the first resolved word in the first language and a second numerical ranking for a second resolved word in the first language based on a likelihood of usage of the first resolved word in the first language and the second resolved word in the first language; and

determining a first composite score for the first text query based on summing the first numerical ranking and the second numerical ranking.

20. The system of claim 11, wherein the control circuitry is further configured to generate for display, on the display device, a first search result for the first text query, wherein the first search result is ordered among search results based on the first composite ranking.