System and Method Providing Specific Insights into Data-Confidentiality-Preserving Applications in Case of Deviations

A data processing apparatus for providing insights into confidential company data in case of data deviations in an industrial plant context, the data processing apparatus comprising a processor being configured to carry out a method for providing insights into confidential company data in case of data deviations in an industrial plant context, the method comprising:

• processing company data by a calculation module in a first processing state and obtaining key performance indicator (KPI) values from the processing;
• wherein the company data are secured by first IT security means and are associated with a process related to a first company;
• wherein the calculation module is secured by second IT security means and is associated with a second company;
• determining data deviations by determining whether a predetermined KPI threshold is violated by the obtained KPI values;
• and
• based on a result of the determining:
• using an a-posteriori method comprising providing action recommendations for data deviation reduction based on a confidential machine learning model and/or switching the calculation module into a second processing state, wherein the second processing state enables the calculation module to perform additional processing related to the company data and to provide additional information related to the company data as compared with the first processing state;
• and/or
• using an a-priori method comprising applying a zero-knowledge proof method and/or a remote attestation method related to the company data.

A computer program product comprising instructions which, when executed by a computing system, enable and/or cause the computing system to perform a method for providing insights into confidential company data in case of data deviations in an industrial plant context, comprising:

• instructions for processing company data by a calculation module in a first processing state and obtaining key performance indicator (KPI) values from the processing;
• wherein the company data are secured by first IT security means and are associated with a process related to a first company;
• wherein the calculation module is secured by second IT security means and is associated with a second company;
• instructions for determining data deviations by determining whether a predetermined KPI threshold is violated by the obtained KPI values;
• and
• based on a result of the determining:
• instructions for using an a-posteriori method comprising providing action recommendations for data deviation reduction based on a confidential machine learning model and/or switching the calculation module into a second processing state, wherein the second processing state enables the calculation module to perform additional processing related to the company data and to provide additional information related to the company data as compared with the first processing state;
• and/or
• instructions for using an a-priori method comprising applying a zero-knowledge proof method and/or a remote attestation method related to the company data.