APPARATUS AND METHOD FOR INFERRING INFORMATION USING A COMPUTER NETWORK

• US 20170154246A1
• Filed: 11/29/2016
• Published: 06/01/2017
• Est. Priority Date: 11/30/2015
• Status: Abandoned Application

• Current Assignee: Allegro Artificial Intelligence Ltd.
• Original Assignee: Seematics Systems Limited
• Inventors: Guttmann, Moshe
• Application Number:
  US15/363,454
• Publication Number:
  US 20170154246A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 18/217 Validation; Performance evaluation; Active pattern learning techniques
• CPC Class Codes: G06F 18/2411 based on the proximity to a decision surface, e.g. support vector machines
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06V 10/776 Validation; Performance evaluation
• CPC Class Codes: G06V 10/94 Hardware or software architectures specially adapted for image or video understanding
• CPC Class Codes: H04L 51/224 providing notification on incoming messages, e.g. pushed notifications of received messages
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04W 4/38 for collecting sensor information
• CPC Class Codes: H04W 4/60 Subscription-based services using application servers or record carriers, e.g. SIM application toolkits

Abstract

Apparatuses and methods for inferring information are provided. Input data and inference model may be obtained. A result of applying the input data to the inference model may be generated. Information based on the generated result may be transmitted. Update to the inference model may be received. The updated inference model may be used to obtain additional results.

Claims

1. An apparatus comprising:

at least one communication device; and

at least one processing unit configured to;

obtain a first inference model;

obtain first input data;

generate a first result by applying the first input data to the first inference model;

transmit performance information using the at least one communication device, the performance information is based, at least in part, on the first result;

receive an update using the at least one communication device, the update is based, at least in part, on the performance information;

obtain a second inference model, the second inference model is based, at least in part, on the update;

obtain second input data; and

generate a second result by applying the second input data to the second inference model.

2. The apparatus of claim 1, wherein the first inference model comprises a classifier.

3. The apparatus of claim 1, wherein the first inference model comprises a regression model.

4. The apparatus of claim 1, wherein the first inference model is based, at least in part, on an output of at least one neural network.

5. The apparatus of claim 1, further comprising at least one audio sensor, and wherein the first input data and the second input data comprises audio data captured from an environment of the apparatus using the at least one audio sensor.

6. The apparatus of claim 1, wherein the first input data and the second input data comprises information associated with at least one of:

temperature, position, orientation, motion, and acceleration.

7. The apparatus of claim 1, further comprising at least one image sensor, and wherein the first input data and the second input data comprises image data captured from an environment of the apparatus using the at least one image sensor.

8. The apparatus of claim 7, wherein the first result comprises a mapping, the mapping associates segments of the image data with values.

9. The apparatus of claim 7, wherein the first inference model comprises at least one of:

a face detector and an object detector.

10. The apparatus of claim 1, wherein the first result comprises spatial information.

11. The apparatus of claim 1, wherein the first result comprises temporal information.

12. The apparatus of claim 1, wherein the first result comprises a mapping, the mapping associates points in time with values.

13. The apparatus of claim 1, wherein the performance information comprises at least part of the first result.

14. The apparatus of claim 1, wherein the performance information comprises at least part of the first input data.

15. The apparatus of claim 1, wherein the update comprises at least part of the second inference model.

16. The apparatus of claim 1, wherein the first inference model comprises a plurality of components;

wherein the update comprises at least one updated component; and

wherein obtaining the second inference model comprises replacing at least one of the plurality of components with the at least one updated component.

17. The apparatus of claim 1, wherein the at least one processing unit is further configured to:

receive, using the at least one communication device, a data request, the data request is based, at least in part, on the performance information;

select a portion of the first input data based, at least in part, on the data request; and

transmit, using the at least one communication device, the selected portion of the first input data.

18. A method comprising:

obtaining a first inference model;

obtaining first input data;

generating, by a computing system comprising one or more computers, a first result by applying the first input data to the first inference model;

transmitting performance information using at least one communication device, the performance information is based, at least in part, on the first result;

receiving an update using the at least one communication device, the update is based, at least in part, on the performance information;

obtaining a second inference model, the second inference model is based, at least in part, on the update;

obtaining second input data; and

generating, by a computing system comprising one or more computers, a second result by applying the second input data to the second inference model.

19. The method of claim 18, wherein the first inference model comprises a classifier.

20. The method of claim 18, wherein the first inference model comprises a regression model.

21. The method of claim 18, wherein the first inference model is based, at least in part, on an output of at least one neural network.

22. The method of claim 18, wherein the first input data and the second input data comprises audio data captured from an environment using at least one audio sensor.

23. The method of claim 18, wherein the first input data and the second input data comprises information associated with at least one of:

temperature, position, orientation, motion, and acceleration.

24. The method of claim 18, wherein the first input data and the second input data comprises image data captured from an environment using at least one image sensor.

25. The method of claim 24, wherein the first result comprises a mapping, the mapping associates segments of the image data with values.

26. The method of claim 24, wherein the first inference model comprises at least one of:

a face detector and an object detector.

27. The method of claim 18, wherein the first result comprises spatial information.

28. The method of claim 18, wherein the first result comprises temporal information.

29. The method of claim 18, wherein the first result comprises a mapping, the mapping associates points in time with values.

30. The method of claim 18, wherein the performance information comprises at least part of the first result.

31. The method of claim 18, wherein the performance information comprises at least part of the first input data.

32. The method of claim 18, wherein the update comprises at least part of the second inference model.

33. The method of claim 18, wherein the first inference model comprises a plurality of components;

wherein the update comprises at least one updated component; and

wherein obtaining the second inference model comprises replacing at least one of the plurality of components with the at least one updated component.

34. The method of claim 18, further comprising:

receiving, using the at least one communication device, a data request, the data request is based, at least in part, on the performance information;

selecting a portion of the first input data based, at least in part, on the data request; and

transmitting, using the at least one communication device, the selected portion of the first input data.

35. A software product stored on a non-transitory computer readable medium and comprising data and computer implementable instructions for carrying out the method of claim 18.