Deep learning based object identification and/or classification
US-2023360385-A1 · Nov 9, 2023 · US
US12560910B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12560910-B2 |
| Application number | US-202318174801-A |
| Country | US |
| Kind code | B2 |
| Filing date | Feb 27, 2023 |
| Priority date | Feb 27, 2023 |
| Publication date | Feb 24, 2026 |
| Grant date | Feb 24, 2026 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Various embodiments relate to mapping hierarchical reference data associated with industrial assets and contextualizing raw streaming data generated by the industrial assets. Embodiments are configured to receive an application programming interface (API) call request to map hierarchical reference data comprised in a digital twin system that digitally represents assets within an industrial environment. In response to the API call request, embodiments can generate flattened asset data objects associated with the hierarchical reference data, where the flattened asset data objects comprise respective mappings of data attributes for the hierarchical reference data. Embodiments can correlate raw streaming data related to the assets with the flattened asset data objects to generate contextualized asset data for the one or more assets. Embodiments can also update, based on the contextualized asset data, the digital twin system to facilitate asset data queries for the one or more assets via the digital twin system.
Opening claim text (preview).
What is claimed is: 1 . A system, comprising: one or more processors; a memory; and one or more programs stored in the memory, the one or more programs comprising instructions configured to: receive an application programming interface (API) call request to map one or more portions of hierarchical reference data comprised in a digital twin system that digitally represents one or more assets within an industrial environment; in response to the API call request, generate one or more flattened asset data objects associated with the one or more portions of the hierarchical reference data, wherein the one or more flattened asset data objects comprise respective mappings of one or more data attributes for the one or more portions of the hierarchical reference data; correlate one or more portions of raw streaming data related to the one or more assets with at least one flattened asset data object of the one or more flattened asset data objects to generate contextualized asset data for the one or more assets, wherein at least one portion of the one or more portions of raw streaming data comprises identifier data associated with one or more component parts of the one or more respective assets, sensor data captured by one or more sensor points associated with the one or more respective assets, calculation data computed by one or more processors associated with the one or more respective assets, or measurement data captured by one or more measurement devices associated with the one or more respective assets; join the one or more portions of raw streaming data with the at least one of the one or more flattened asset data objects; and update, based on the contextualized asset data, the digital twin system to facilitate one or more asset data queries for the one or more assets via the digital twin system. 2 . The system of claim 1 , wherein the one or more portions of the hierarchical reference data comprised in the digital twin system are structured in a knowledge graph associated with the one or more assets within the industrial environment. 3 . The system of claim 2 , wherein the one or more programs comprising the instructions configured to generate the one or more flattened asset data objects associated with the one or more respective portions of the hierarchical reference data are further configured to: traverse one or more data nodes associated with the knowledge graph to parse the one or more portions of the hierarchical reference data associated with the one or more respective assets, wherein traversing the knowledge graph comprises sequentially executing one or more knowledge graph API calls. 4 . The system of claim 2 , wherein the one or more data attributes are associated with respective parsed nodes of the knowledge graph. 5 . The system of claim 1 , wherein the one or more data attributes comprised by the one or more flattened asset data objects related to the one or more assets comprise at least one of: an asset identifier, an asset role, an asset manufacturer identifier, a corresponding engineering unit identifier, an asset location, an asset sensor point identifier, an asset sensor type, an asset sensor measurement value, a user identifier, a change event identifier, or a timestamp. 6 . The system of claim 1 , wherein the one or more programs further comprise instructions configured to: identify a change event with respect to the hierarchical reference data, wherein the change event is associated with an alteration to the one or more portions of the hierarchical reference data associated with the one or more respective assets; and reconfigure, based on the change event, the one or more respective flattened asset data objects associated with the one or more portions of the hierarchical reference data. 7 . The system of claim 1 , wherein the instructions configured to correlate the one or more portions of raw streaming data related to the one or more assets with the at least one flattened asset data object of the one or more flattened asset data objects to generate the contextualized asset data are further configured to: join the one or more portions of raw streaming data with the at least one of the one or more flattened asset data objects. 8 . The system of claim 1 , wherein the one or more portions of raw streaming data are associated with one or more respective industrial processes executed at least in part by the one or more assets. 9 . The system of claim 1 , wherein the one or more programs further comprise instructions configured to: cause storage of the one or more portions of raw streaming data related to the one or more assets in a database configured as a data lake. 10 . A computer-implemented method, the computer-implemented method comprising: receiving an application programming interface (API) call request to map one or more portions of hierarchical reference data comprised in a digital twin system that digitally represents one or more assets within an industrial environment; in response to the API call request, generating one or more flattened asset data objects associated with the one or more portions of the hierarchical reference data, wherein the one or more flattened asset data objects comprise respective mappings of one or more data attributes for the one or more portions of the hierarchical reference data; correlating one or more portions of raw streaming data related to the one or more assets with at least one flattened asset data object of the one or more flattened asset data objects to generate contextualized asset data for the one or more assets, wherein at least one portion of the one or more portions of raw streaming data comprises identifier data associated with one or more component parts of the one or more respective assets, sensor data captured by one or more sensor points associated with the one or more respective assets, calculation data computed by one or more processors associated with the one or more respective assets, or measurement data captured by one or more measurement devices associated with the one or more respective assets; joining the one or more portions of raw streaming data with the at least one of the one or more flattened asset data objects; and updating, based on the contextualized asset data, the digital twin system to facilitate one or more asset data queries for the one or more assets via the digital twin system. 11 . The system of claim 1 , wherein the one or more programs further comprise instructions configured to: generate an interactive tabular representation of the contextualized asset data for rendering via a graphical user interface. 12 . A computer-implemented method, the computer-implemented method comprising: receiving an application programming interface (API) call request to map one or more portions of hierarchical reference data comprised in a digital twin system that digitally represents one or more assets within an industrial environment; in response to the API call request, generating one or more flattened asset data objects associated with the one or more portions of the hierarchical reference data, wherein the one or more flattened asset data objects comprise respective mappings of one or more data attributes for the one or more portions of the hierarchical reference data; correlating one or more portions of raw streaming data related to the one or more assets with at least one flattened asset data object of the one or more flattened asset data objects to generate contextualized asset data for the one or more assets; and updating, based on the contextualized asset data, the digital twin system to facilitate one or more asset data queries for the one or more
characterised by the network communication · CPC title
characterised by data acquisition, e.g. workpiece identification · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.