Digitizing industry installation documentation

90% time reduction in workflow

Meet our client

INDUSTRYManufacturing

CUSTOMERA global leader in digital solutions

How we did it

The client is a global leader in providing digital ecosystems for industries including manufacturing and infrastructure.

The challenge

To deliver a digital ecosystem, the client analyzes factory installation schematics, which are often aged and riddled with inconsistencies. Depending on the schematics’ complexity, it can take trained staff anywhere from three hours to two full days to analyze, clarify and digitalize them.

The company needs the digitalized schematics to be further used by various appliances asfully actionable data. Its database holds information about the object, its position, connections, function and detailed technical parameters. Later, the schematics are merged with 3D scans of an industrial installation to provide a real-view interactive map of the entire system, including the automated notifications about inconsistencies and potential challenges to overcome. Thus, simple scanning was not enough—manual, detailed analysis was required to extract all of the information.

The solution

deepsense.ai developed a model that recognizes and adds descriptions for all symbols used in the installation documentation. The model recognizes inconsistent symbols that differ by size, angle, and proportions.

Overcoming the numerous hurdles involved, the model delivers a fully digitalized version of the documentation.

The effect

The schematics are fully digitalized, including the technical descriptions of all components. The model reduces the work to a 30-minute review done by a specialist. It also handles the most tedious tasks, thus reducing the effort required of human specialists and the number of errors they make performing them.

Infusing retail analytics with image recognition

Nielsen Holdings 93% reduction in data gathering time by reducing the amount of manual work Learn more

#retail#computervision
Read More

Predicting CTR and spotting bots in online advertising

CTR prediction 35% CTR prediction improvement over existing heuristics. Learn more

#retail #dataanalytics
Read More

Recognizing firefighters’ actions from sensory data

University of Warsaw & Main School of Fire Service 84% accuracy in detecting firefighter activities Learn more

#publicsector#predictivemodeling
Read More

Diagnosing diabetic retinopathy

California Healthcare Foundation Human expert-level accuracy Learn more

#healthcare#computervision
Read More

We want to hear from you

Find us
  • deepsense.ai, Inc.
  • 2100 Geng Road, Suite 210
  • Palo Alto, CA 94303
  • United States of America
  • deepsense.ai Sp. z o.o.
  • Al. Jerozolimskie 162A
  • 02-342 Warsaw
  • Poland
Let us know how we can help
Fill out this quick form and we will contact you shortly




You can modify your privacy settings and unsubscribe from our lists at any time (see our privacy policy).

This site is protected by reCAPTCHA and the Google privacy policy and terms of service apply.