METHOD FOR DETERMINING AT LEAST ONE INDICATION OF AT LEAST ONE CHANGE

• US 20200134457A1
• Filed: 10/29/2019
• Published: 04/30/2020
• Est. Priority Date: 10/30/2018
• Status: Active Application

• Current Assignee: Siemens AG
• Original Assignee: Siemens AG
• Inventors: Montrone, Francesco, Wieghardt, Jan, Zeller, Marc, Kempter, Bernhard
• Application Number:
  US16/667,053
• Publication Number:
  US 20200134457A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 30/27 using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
• CPC Class Codes: G06F 8/65 Updates security arrangements therefor G06F21/57
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/08 Learning methods

Abstract

Provided is a method for determining at least one indication of at least one change, having the steps of receiving at least one input data record having the at least one change and associated data, and determining the at least one indication of the at least one change by applying a learning-based approach to the at least one received input data record. The invention is also directed to a determination unit and a computer program product.

Claims

1. A method for determining at least one indication of at least one change, the method comprising:

c. receiving at least one input data record having the at least one change and associated data; and

d. determining the at least one indication of the at least one change by applying a learning-based approach to the at least one received input data record.

2. The method as claimed in claim 1, wherein the change is an extension, a restriction or another change to a hardware unit or software.

3. The method as claimed in claim 1, wherein the input data record is stored in a storage unit in the form of a feature vector.

4. The method as claimed in claim 1, wherein the associated data have a description of the at least one change and/or of the further background relating to the at least one change in a natural language.

5. The method as claimed in claim 1, wherein the learning-based approach is selected from the group consisting of a neural network, reinforcement learning or another machine learning algorithm.

6. The method as claimed in claim 5, wherein the neural network is a trained neural network.

7. The method as claimed in claim 1, further comprising, after step a., filtering the input data record at least partially on a basis of at least one filter criterion.

8. The method as claimed in claim 1, also comprising determining a result value for the at least one indication of the at least one change, wherein the result value is a probability value.

9. The method as claimed in claim 8, further comprising

approving the at least one change on the basis of the determined result value;

wherein;

there is approval if the result value exceeds a predetermined threshold value;

implementing the at least one change in the case of approval; and

/or

initiating another measure in the case of approval or if the at least one change is rejected.

10. The method as claimed in claim 9, wherein the other measure is a method step selected from the group consisting of

outputting and/or transmitting a message to a unit, wherein the message comprises the at least one indication, the result value, the at least one change, the associated data, other data from the input and/or output data records;

implementing at least one further change, wherein the further change has already been approved.

11. The method as claimed in claim 10, wherein the message takes into account the result value.

12. A determination unit for carrying out the method as claimed in claim 1.

13. A computer program product, comprising a computer readable hardware storage device having computer readable program code stored therein, said program code executable by a processor of a computer system to implement a method as claimed in claim 1 when the computer program is executed on a program-controlled device.