Systems and methods for updating search results based on a conversation

• US 10,650,054 B2
• Filed: 04/24/2018
• Issued: 05/12/2020
• Est. Priority Date: 04/24/2018
• Status: Active Grant

• Current Assignee: Rovi Guides, Inc. (Adeia Inc.)
• Original Assignee: Rovi Guides, Inc. (Adeia Inc.)
• Inventors: Blake, John, Stathacopoulos, Paul, Thomas, William L.
• Primary Examiner(s): Stevens, Robert
• Application Number:
  US15/960,982
• Publication Number:
  US 20190325079A1
• Time in Patent Office: 749 Days
• Field of Search: 707706
• CPC Class Codes: G06F 16/3328 using graphical result space presentation or visualisation
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/732 Query formulation
• CPC Class Codes: G06F 16/735 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/9038 Presentation of query results
• CPC Class Codes: G06F 16/907 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: H04N 21/42203 sound input device, e.g. microphone
• CPC Class Codes: H04N 21/4661 Deriving a combined profile for a plurality of end-users of the same client, e.g. for family members within a home user profiles in network data switching protocols H04L67/306
• CPC Class Codes: H04N 21/472 End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content end-user interfaces for retrieving video data from a database G06F16/739; network services for supporting unicast streaming H04L65/612
• CPC Class Codes: H04N 21/4828 for searching program descriptors retrieval of video data G06F16/739

Abstract

Systems and methods are described herein for updating search results based on a user'"'"'s comment or a conversation among users using a media guidance application. A set of search results may be presented to a user or users. Comments or a conversation about the search results may be analyzed by the media guidance application. Selected comments by a user determined to have a greater weight may be used to update the search results.

Claims

1. A method for modifying search results for a media asset based on a conversation between users, the method comprising:

receiving, at control circuitry, a search request from a first user;

in response to receiving the search request, performing, using the control circuitry, a search for a media asset in a media database based on the search request;

generating, using the control circuitry, a first display of a set of first search results;

detecting, using the control circuitry, a conversation between the first user and a second user;

determining, using the control circuitry, a first weight for the first user, and a second weight for the second user;

analyzing, using the control circuitry, the conversation between the first user and the second user;

adjusting, using the control circuitry, based on the conversation between the first user and the second user, the first weight and the second weight;

determining, using the control circuitry, which of the first weight and the second weight is greater;

selecting, using the control circuitry, words spoken by the first user or the second user, based on the determined greater respective weight; and

performing, using the control circuitry, a second search for a media asset based on the first search results and the selected words.

2. The method of claim 1, wherein determining, using the control circuitry, a first weight for the first user, and a second weight for the second user comprises:

matching in a voice pattern profile database, a first voice pattern for the first user and a second voice pattern for the second user;

identifying the first user based on a first profile associated with the matched first voice pattern profile;

identifying the second user based on a second profile associated with the matched second voice pattern profile;

determining the first weight based on the first profile; and

determining the second weight based on the second profile.

3. The method of claim 2, further comprising:

comparing, using the control circuitry, words spoken in the conversation between the first user and the second user with a preference profile for the first user and the second user;

detecting, using the control circuitry, a match between a word spoken in the conversation and a preference profile for the first user or the second user; and

increasing the respective weight for the first user or the second user based on a matching word.

4. The method of claim 1, wherein analyzing, using the control circuitry, the conversation between the first user and the second user, further comprises:

parsing each word in the conversation to identify a part of speech for the word;

detecting, among the parsed words in the conversation, a pronoun;

determining which of the first user and the second user is associated with the pronoun; and

adjusting the respective weight for the first user or the second user based on the determination of association with the pronoun.

5. The method of claim 1, wherein analyzing, using the control circuitry, the conversation between the first user and the second user further comprises:

comparing each word in the conversation with the first search result terms and metadata associated with the first search results;

determining a matching word among the compared words in the conversation and the first search results terms and metadata associated with the first search results;

determining which of the first user or the second user spoke the matching word, based on a respective voice profile; and

adjusting the first weight or the second weight, based on the determined speaker of the matching word.

6. The method of claim 1, wherein analyzing, using the control circuitry, the conversation between the first user and the second user, further comprises:

parsing each word in the conversation to identify a negative or a positive word;

for an identified negative word in the conversation;

determining which of the first user or the second user spoke the identified negative word, based on a respective voice profile; and

adjusting the respective weight for the determined speaker of the identified negative word.

7. The method of claim 1, further comprising:

generating, using the control circuitry, a second display of a set of second search results;

detecting, using the control circuitry, a second conversation between the first user and the second user;

analyzing, using the control circuitry, the words of the second conversation;

readjusting, using the control circuitry, based on the second conversation between the first user and the second user, the first weight and the second weight; and

performing a third search for a media asset based on selected words in the second conversation, the first search, and the second search.

8. The method of claim 7, wherein selecting the words used to perform the third search comprises:

parsing each word in the second conversation;

detecting, among the parsed words, a deferential word;

identifying, using the control circuitry;

the first user as speaker of the deferential word based on a respective voice pattern profile; and

selecting words spoken by the second user in the second conversation.

9. The method of claim 7, further comprising:

ranking, using the control circuitry, the set of second search results in an order ranked based on a preference profile for the first user or the second user.

10. The method of claim 1, further comprising:

initiating, using the control circuitry, a home assistant device to monitor the conversation between the first user and the second user for a period, wherein the home assistant device is selected based on its proximity to the display of the first search results and proximity to the first user and the second user.

11. A system for modifying search results for a media asset based on a conversation between users, the system comprising:

input/output (I/O) interface circuitry configured to receive a user input; and

control circuitry configured to;

receive a search request from a first user;

in response to receiving the search request, perform a search for a media asset in a media database based on the search request;

generate a first display of a set of first search results;

detect a conversation between the first user and a second user;

determine a first weight for the first user, and a second weight for the second user;

analyze the conversation between the first user and the second user;

adjust, based on the conversation between the first user and the second user, the first weight and the second weight;

determine which of the first weight and the second weight is greater;

select words spoken by the first user or the second user, based on the determined greater respective weight; and

perform a second search for a media asset based on the first search results and the selected words.

12. The system of claim 11, wherein the control circuitry configured to determine a first weight for the first user, and a second weight for the second user is further configured to:

match in a voice pattern profile database, a first voice pattern for the first user and a second voice pattern for the second user;

identify the first user based on a first profile associated with the matched first voice pattern profile;

identify the second user based on a second profile associated with the matched second voice pattern profile;

determine the first weight based on the first profile; and

determine the second weight based on the second profile.

13. The system of claim 12 wherein the control circuitry is further configured to:

compare words spoken in the conversation between the first user and the second user with a preference profile for the first user and the second user;

detect a match between a word spoken in the conversation and a preference profile for the first user or the second user; and

increase the respective weight for the first user or the second user based on a matching word.

14. The system of claim 11, wherein the control circuitry configured to analyze the conversation between the first user and the second user, is further configured to:

parse each word in the conversation to identify a part of speech for the word;

detect among the parsed words in the conversation, a pronoun;

determine which of the first user and the second user is associated with the pronoun; and

adjust the respective weight for the first user or the second user based on the determination of association with the pronoun.

15. The system of claim 11, wherein the control circuitry configured to analyze the conversation between the first user and the second user, is further configured to:

compare each word in the conversation with the first search result terms and metadata associated with the first search results;

determine a matching word among the compared words in the conversation and the first search results terms and metadata associated with the first search results;

determine which of the first user or the second user spoke the matching word, based on a respective voice profile; and

adjust the first weight or the second weight, based on the determined speaker of the matching word.

16. The system of claim 11, wherein the control circuitry configured to analyze the conversation between the first user and the second user, is further configured to:

parse each word in the conversation to identify a negative or a positive word;

for an identified negative word in the conversation;

determine which of the first user or the second user spoke the identified negative word, based on a respective voice profile; and

adjust the respective weight for the determined speaker of the identified negative word.

17. The system of claim 11, wherein the control circuitry is further configured to:

generate a second display of a set of second search results;

detect a second conversation between the first user and the second user;

analyze the words of the second conversation;

readjust based on the second conversation between the first user and the second user, the first weight and the second weight; and

perform a third search for a media asset based on selected words in the second conversation, the first search, and the second search.

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

parse each word in the second conversation;

detect, among the parsed words, a deferential word;

identify the first user as speaker of the deferential word based on a respective voice pattern profile; and

select words spoken by the second user in the second conversation.

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

rank the set of second search results in an order ranked based on a preference profile for the first user or the second user.

20. The system of claim 11, wherein the control circuitry is further configured to:

initiate a home assistant device to monitor the conversation between the first user and the second user for a period, wherein the home assistant device is selected based on its proximity to the display of the first search results and proximity to the first user and the second user.