System and method for distributed search-by-content

• US 9,489,431 B2
• Filed: 12/04/2013
• Issued: 11/08/2016
• 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): Hill, Stanley K
• Assistant Examiner(s): Bharadwaj, Kalpana
• Application Number:
  US14/096,802
• Publication Number:
  US 20140095494A1
• Time in Patent Office: 1,070 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/43 Querying
• CPC Class Codes: H04H 2201/90 characterised by the use of signatures
• CPC Class Codes: H04H 60/37 for identifying segments of broadcast information, e.g. scenes or extracting programme ID
• CPC Class Codes: H04H 60/46 for recognising users' preferences
• CPC Class Codes: H04H 60/47 for recognising genres
• CPC Class Codes: H04H 60/58 of audio determination or detection of speech characteristics in general G10L25/00; speech recognition in general G10L15/00
• CPC Class Codes: H04H 60/59 of video recognising characters or patterns in general G06F18/00, G06V20/00
• CPC Class Codes: H04H 60/65 for using the result on users' side
• CPC Class Codes: H04H 60/73 using meta-information
• 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 method for conducting search-by-content is provided. The method includes responsive to an input multimedia content item provided to a user device, checking if the input multimedia content item matches at least one concept of a plurality of concepts cached in the user device; retrieving characteristics set for a user of the user device; performing a search, using the at least one matching concept, for multimedia content items similar to the input multimedia content item; determining which of the search results are of interest to the user based on the characteristics set for the user; and saving results that are of interest to the user in the user device, wherein the saved results include multimedia content items.

Claims

1. A method for conducting search-by-content, comprising:

responsive to an input multimedia content item provided to a user device,

checking if the input multimedia content item matches at least one concept of a plurality of concepts cached in the user device, wherein the at least one matching concept is a collection of signatures representing a large scale of multimedia content items, the collection is of a signature reduced cluster generated by inter-matching signatures generated for the large scale of multimedia content items, and the at least one matching concept is represented using at least on signature and metadata;

retrieving characteristics set for a user of the user device;

performing a search, using the at least one matching concept, for multimedia content items similar to the input multimedia content item;

determining which of the search results are of interest to the user based on the characteristics set for the user; and

saving results that are of interest to the user in the user device, wherein the saved results include multimedia content items.

2. The method of claim 1, further comprising:

generating at least one signature for the input multimedia content item prior to checking for at least one matching concept, wherein the at least one generated signature is robust to noise and distortion.

3. The method of claim 1, wherein the at least one concept is determined to match the multimedia content item when the at least one signature of a concept matches at least one signature generated for the multimedia content item over a predefined threshold.

4. The method of claim 3, wherein upon identification of at least one matching concept, the at least one signature and the metadata of the at least one matching concept are returned.

5. The method of claim 4, wherein performing the search using the at least one matching concept further comprising:

querying a plurality of data sources using the at least one signature or the metadata of each of the at least one matching concept.

6. The method of claim 1, wherein the data sources include any one of:

websites, data warehouses storing multimedia content items, and a concept database.

7. The method of claim 1, wherein the concept database indexes multimedia data items into concepts.

8. The method of claim 1, further comprising:

checking, for each of the search results, if a search result coincides with one or more of the characteristics set for the user.

9. The method of claim 8, wherein the characteristics include content preferences of the user and demographic information related to the user.

10. The method of claim 1, wherein the cached concepts are created from multimedia content items locally saved in the user device.

11. The method of claim 1, wherein a multimedia content item is any one of:

an image, a graphic, a video stream, a video clip, an audio stream, an audio clip, a video frame, a photograph, an image of signals, a combination thereof, 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 method for search-by-content, comprising:

responsive to an input multimedia content item provided to a user device,

generating at least one signature for the input multimedia content item;

checking if the input multimedia content item matches at least one concept of a plurality of concepts cached in the user device, wherein the at least one matching concept is a collection of signatures representing a large scale of multimedia content items, the collection is of a signature reduce cluster generated by the inter-matching signatures generated for the large scale of multimedia content items, and the at least one matching concept is represented using at least one signature and metadata;

for each of the least one matching concepts, sending at least one signature and metadata of the matching concepts to a server configured to search for multimedia content items similar to the input multimedia content item; and

saving results that are of interest to the user in the storage device, wherein the saved results include multimedia content items.

14. The method of claim 13, wherein the at least one concept is determined to match the multimedia content item when the at least one signature of the concept matches at least one signature generated for the multimedia content item over a predefined threshold.

15. A non-transitory computer readable medium having stored thereon instructions for causing one or more processing units to execute the method according to claim 13.

16. A system for conducting search-by-content, comprising:

a processor;

a deep content classification (DCC) engine connected to the processor;

a storage unit for caching a plurality of concepts;

a memory connected to the processor, wherein the memory contains instructions that, when executed by the processor, configure the system to;

responsive to an input multimedia content item provided to a user device,

check, by the DCC engine, if the input multimedia content item matches at least one concept of the plurality of concepts cached in the storage unit;

retrieve characteristics set for a user of the user device;

perform a search for multimedia content items similar to the input multimedia content item using the at least one matching concept;

determine which of the search results are of interest to the user based on the characteristics set for the user; and

save results that are of interest to the user in the storage unit, wherein the saved results include multimedia content items.

17. The system of claim 16, wherein the system further comprises a signature generator configured to generate least one signature for the input multimedia content item prior to the check performed by the DCC engine, wherein the at least one generated signature is robust to noise and distortion.

18. The system of claim 17, wherein the at least one matching concept is a collection of signatures representing a large scale of multimedia content items, the collection is of a signature reduced cluster generated by inter-matching signatures generated for the large scale of multimedia content items, and the at least one matching concept is represented using at least one signature and metadata.

19. The system of claim 18, wherein the at least one concept is determined to match the multimedia content item when the at least one signature of the at least one concept matches at least one signature generated for the multimedia content item over a predefined threshold.

20. The system of claim 19, wherein upon identification of at least one matching concept, the DCC engine is configured to return the at least one signature and the metadata of the at least one matching concept.

21. The system of claim 20, wherein the system is further configured to query a plurality of data sources using the at least one signature or the metadata of each of the at least one matching concept.