System and method for brand monitoring and trend analysis based on deep-content-classification

• US 9,218,606 B2
• Filed: 04/30/2013
• Issued: 12/22/2015
• Est. Priority Date: 10/26/2005
• Status: Active Grant

• Current Assignee: Cortica Ltd.
• Original Assignee: Cortica Ltd.
• Inventors: Raichelgauz, Igal, Odinaev, Karina, Zeevi, Yehoshua Y.
• Primary Examiner(s): Gaffin, Jeffrey A
• Assistant Examiner(s): Chubb, Mikayla
• Application Number:
  US13/874,115
• Publication Number:
  US 20130238393A1
• Time in Patent Office: 966 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0245 Surveys
• CPC Class Codes: H04N 21/25891 being end-user preferences retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/2668 Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles information retrieval from the Internet by querying with filtering and personalisation G06F16/9535; arrangements for replacing or switching information during the broadcast H04H20/10; push services over packet-switching network H04L12/1859; adaptation of message content in packet-switching networks H04L51/063
• CPC Class Codes: H04N 21/466 Learning process for intelligent management, e.g. learning user preferences for recommending movies services using the results of monitoring in broadcast systems H04H60/61
• CPC Class Codes: H04N 21/8106 involving special audio data, e.g. different tracks for different languages
• CPC Class Codes: H04N 7/17318 Direct or substantially direct transmission and handling of requests

Abstract

A system and method for monitoring a brand sentiment through a plurality of different web sources are provided. The method comprises receiving a request to monitor a brand; searching the plurality of web sources for multimedia content elements related to the brand; generating at least one signature for each multimedia content element determined to be related to the brand, wherein each of the at least one generated signatures represents a concept; and correlating the concepts respective of the generated signatures to determine a context of the multimedia content elements determined to be related to the brand, wherein the context is the brand sentiment.

Claims

1. A method for monitoring a brand sentiment through a plurality of different web sources, comprising:

receiving a request to monitor a brand;

searching the plurality of web sources for multimedia content elements related to the brand;

generating at least one signature for each multimedia content element determined to be related to the brand, wherein each of the at least one generated signatures represents a concept, wherein the concept is an abstract description of the content to which the signature was generated; and

correlating the concepts respective of the generated signatures to determine a context of the multimedia content elements determined to be related to the brand, wherein the context is the brand sentiment.

2. The method of claim 1, further comprising:

storing the brand sentiment, a time stamp, and the signatures generated for multimedia content elements related to the brand in a database.

3. The method of claim 1, wherein the request to monitor the brand includes an input multimedia content element representing the brand.

4. The method of claim 3, further comprising:

generating at least one signature for the input multimedia content element, wherein the at least one signature is robust to noise and distortions.

5. The method of claim 4, further comprising:

determining if a multimedia content element found through the search is related to the brand by matching at least one signature generated for the multimedia content element to the at least one signature generated for the input multimedia content element, wherein the multimedia content element is determined to be related to the brand if its respective at least one signature is substantially similar to the at least one signature generated for the input multimedia content element.

6. The method of claim 1, wherein determining the context of the multimedia content elements further comprises:

establishing a strong context, wherein the brand sentiment is set based on the strong context.

7. The method of claim 6, wherein the strong context is established based on at least one of:

a volume of appearances of the brand throughout the web sources, a number of concepts satisfying a predefined condition being set respective of a certain sentiment.

8. The method of claim 7, wherein the certain sentiment is any one of:

a positive sentiment, a natural sentiment, a negative sentiment.

9. The method of claim 1, wherein each of the plurality of different web sources is any one of:

a social network, a blog, a web site, a news feed.

10. The method of claim 1, further comprising:

tracking a trendiness of the brand sentiment by monitoring changes in the brand segments over time.

11. The method of claim 1, wherein each of the plurality of multimedia content elements is at least one of:

an image, graphics, a video stream, a video clip, an audio stream, an audio clip, a video frame, a photograph, images of signals, and portions thereof.

12. A non-transitory computer readable medium having stored thereon instructions for causing one or more processing units to execute the method according to claim 1.

13. A system for monitoring a brand sentiment through a plurality of different web sources, comprising:

an interface to a network for receiving a request to monitor a brand and an input multimedia content element representing the brand; and

a processing unit configured to;

search the plurality of web sources for multimedia content elements related to the brand; and

correlate concepts respective of signatures for determining multimedia content elements determined to be related to the brand, and a context of the multimedia content elements determined to be related to the brand, wherein the context is the brand sentiment, wherein the concept is an abstract description of the content to which the signature was generated.

14. The system of claim 13, further comprises:

a database for storing the brand sentiment, a time stamp, and the signatures generated for multimedia content elements related to the brand.

15. The system of claim 13, further comprises:

a signature generator system for generating the at least one signature for the input multimedia content element and at least one signature for each of the multimedia content elements determined to be related by reference to the brand, wherein each of the at least one generated signatures represents a concept.

16. The system of claim 15, wherein each of the at least one generated signatures is robust to noise and distortions.

17. The system of claim 15, wherein the signature generator system comprises a plurality of computational cores enabled to receive the multimedia content elements, each computational core of the plurality of computational cores having properties that are at least partly statistically independent of other of the computational cores, the properties are set independently of each other core.

18. The system of claim 15, wherein the processing unit is further configured to determine if a multimedia content element found through the search is related to the brand by matching at least one signature generated for the multimedia content element to the at least one signature generated for the input multimedia content element, wherein the multimedia content element is determined to be related to the brand if its respective at least one signature is substantially similar to the at least one signature generated for the input multimedia content element.

19. The system of claim 18, wherein the processing unit is further configured to:

determine the context of the multimedia content elements by establishing a strong context, wherein the brand sentiment is set based on the strong context.

20. The system of claim 19, wherein the strong context is established based on at least one of:

a volume of appearances of the brand throughout the web sources, a number of concepts satisfying a predefined condition being set respective of a certain sentiment.

21. The system of claim 20, wherein the certain sentiment is any one of:

a positive sentiment, a natural sentiment, a negative sentiment.

22. The system of claim 13, wherein each of the plurality of different web sources is any one of:

a social network, a blog, a web site, a news feed.

23. The system of claim 13, wherein the system is further configured to:

track a trendiness of the brand sentiment by monitoring changes in the brand segments over time.