Cross-platform analysis

Patent metadata

Field	Value
Publication number	US-9843837-B2
Application number	US-201514817105-A
Country	US
Kind code	B2
Filing date	Aug 3, 2015
Priority date	Aug 3, 2015
Publication date	Dec 12, 2017
Grant date	Dec 12, 2017

Abstract

A method includes receiving, at a processor, a first data stream from a first platform and a second data stream from a second platform. The first data stream includes content and the second data stream includes the content. The method also includes performing an analysis operation on the first data stream and the second data stream to interpret the content. Performing the analysis operation includes performing a statistical analysis on the first data stream and the second data stream using one or more Artificial Neural Network (ANN) nodes of an analytical network. Performing the analysis operation also includes performing a syntactic analysis on the first data stream and the second data stream using one or more Markov Logic Network (MLN) nodes of the analytical network.

First claim

What is claimed is:

1. A method comprising:
receiving, at a processor, a first data stream from a first platform, the first data stream including content;
receiving a second data stream from a second platform, the second data stream including the content;
generating a first vector based on a first modality of the content, wherein the first modality includes visual properties of the content, and wherein the first vector has a first component associated with the first data stream and a second component associated with the second data stream,
generating a second vector based on a second modality of the content, wherein the second vector includes audio properties of the content, and wherein the second vector has a first component associated with the first data stream and a second component associated with the second data stream; and
performing an analysis operation on the first data stream and the second data stream to interpret the content, wherein performing the analysis operation comprises:
performing a statistical analysis on the first data stream and the second data stream using artificial neural network nodes of an analytical network by providing a first artificial neural network node of the analytical network with the first vector and by providing a second artificial neural network node of the analytical network with the second vector; and
performing a syntactic analysis on the first data stream and the second data stream using Markov logic network nodes of the analytical network.

2. The method of claim 1 , wherein interpreting the content includes determining whether the content from the first data stream is synchronized with the content from the second data stream.

3. The method of claim 1 , wherein interpreting the content includes identifying user content preferences based on the content.

4. The method of claim 1 , wherein interpreting the content includes integrating user profiles across the first platform and the second platform based on the content.

5. The method of claim 1 , further comprising providing a result of the first artificial neural network node to a Markov logic network node of the analytic network.

6. The method of claim 1 , further comprising:
at the first artificial neural network node:
applying a first weight to the first vector to generate a first weighted vector;
applying a first activation function to the first weighted vector to generate a first modified vector; and
providing the first modified vector to a first Markov logic network node; and

at the second artificial neural network node:
applying a second weight to the second vector to generate a second weighted vector;
applying a second activation function to the second weighted vector to generate a second modified vector; and
providing the second modified vector to a second Markov logic network node.

7. The method of claim 6 , further comprising:
at the first Markov logic network node:
applying first order logic to the first modified vector and to the first vector using Boolean information to determine first syntactic statistics associated with the first vector and the first modified vector; and
generating a first resulting vector based on the first syntactic statistics; and

at the second Markov logic network node:
applying first order logic to the second modified vector and to the second vector using Boolean information to determine second syntactic statistics associated with the second vector and the second modified vector; and
generating a second resulting vector based on the second syntactic statistics.

8. The method of claim 1 , further comprising providing a result of the second artificial neural network node to a Markov logic network node of the analytic network.

9. An apparatus comprising:
a first artificial neural network node configured to receive a first vector based on a first modality of content, the content included in a first data stream from a first platform and included in a second data stream from a second platform, apply a first weight to the first vector to generate a first weighted vector, and apply a first activation function to the first weighted vector to generate a first modified vector;
a second artificial neural network node configured to receive a second vector based on a second modality of the content;
a first Markov logic network node configured to receive the first modified vector; and
a second Markov logic network node configured to receive an output of the second artificial neural network node,
wherein the first artificial neural network node, the second artificial neural network node, the first Markov logic network node, and the second Markov logic network node are included in an analytical network configured to perform an analysis operation on the first data stream and the second data stream to interpret the content.

10. The apparatus of claim 9 , wherein the analysis operation determines whether the content from the first data stream is synchronized with the content from the second data stream.

11. The apparatus of claim 9 , wherein the analysis operation identifies user content preferences based on the content.

12. The apparatus of claim 9 , wherein the analysis operation integrates user profiles across the first platform and the second platform based on the content.

13. The apparatus of claim 9 , wherein the first modality of the content includes visual properties of the content, and wherein the second modality of the content includes audio properties of the content.

14. The apparatus of claim 9 , wherein the second artificial neural network node is configured to:
apply a second weight to the second vector to generate a second weighted vector;
apply a second activation function to the second weighted vector to generate a second modified vector; and
provide the second modified vector to the second Markov logic network node.

15. The apparatus of claim 14 , wherein the first Markov logic network node is configured to:
apply first order logic to the first modified vector and to the first vector using Boolean information to determine first syntactic statistics associated with the first vector and the first modified vector; and
generate a first resulting vector based on the first syntactic statistics.

16. The apparatus of claim 15 , wherein the second Markov logic network node is configured to;
apply first order logic to the second modified vector and to the second vector using Boolean information to determine second syntactic statistics associated with the second vector and the second modified vector; and
generate a second resulting vector based on the second syntactic statistics.

17. The apparatus of claim 14 , wherein the first Markov logic network node is configured to receive a first result from the first artificial neural network node, and wherein the second Markov logic network node is configured to receive a second result from the second artificial neural network node.

18. A computer-readable storage device comprising instructions that, when executed by a processor, cause the processor to perform operations comprising:
receiving a first data stream from a first platform, the first data stream including content;
receiving a second data stream from a second platform, the second data stream including the content;
generating a first vector based on a first modality of the content, the first vector having a first component associated with the first data stream and a second component associated with the second data stream;
generating a second vector based on a second modality of the conte

Assignees

• At & T Ip I Lp

Inventors

• Gopalan Raghuraman

Classifications

• H04N21/44008

  involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream (arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59) · CPC title

• H04N21/4667

  Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections · CPC title

• H04N21/442

  Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk {(arrangements for monitoring broadcast services or broadcast-related services H04H60/29; arrangements for identifying or recognising characteristics with a direct linkage to broadcast information H04H60/35; monitoring of user activities for profile generation for accessing a video database G06F16/739; monitoring in wireless networks H04W24/00)} · CPC title

• H04N21/4666 Primary

  using neural networks, e.g. processing the feedback provided by the user · CPC title

• H04N21/4302

  Content synchronisation processes, e.g. decoder synchronisation · CPC title