Modern, cutting-edge developments are not reflected in current patent classification systems, which tend to catalogue established technologies. Identifying patent portfolios in such emerging fields proves a challenging job for patent and technology experts.
Going beyond the mere identification of new IP, additional value may be added using a regional geographic weighting combined with consolidated portfolio owner information.
Effective monitoring of the technological field is achieved by training active-learning search engines to hunt for highly relevant patent documents, thus keeping IP portfolios for emerging technologies up to date. The system we have developed permits extremely accurate updates with drastically reduced noise and with low workload which have proven to be invaluable in a world of drastically increasing data blur.
II-SV 2017: How to effectively monitor Technological Developments in IP
1. How to effectively analyse and monitor
Technological Developments in IP
Sample study: Industry 4.0, Factory 4.0
• Technology fields: Quantitative & qualitative,
business related analysis.
• Making use of technology field analysis to get the
decisive competitive advantage by being faster and
by having the right informations at hand .
• Example studies of Industry 4.0 technology
aspects
• Actively monitoring technology fields, using the
Averbis machine learning engine to keep ahead of
time and ahead of the competition.
SDV-II, 25.04.2017
2. Technology fields today: Patent Informations from and for a
business perspective.
Technology fields today: Patent Informations from and for a
business perspective.
•
• Smart House
• Process Automation
• Fintec
• Autonomous Driving
• Li-Batteries
• 3D Printing
materials
• Wearables
• ..
1. Define, collect and
categorise the patent
data
Examples out of 40 cutting edge technology
fields and up to 200 geographic regions,
elaborated together with
Added value information, delivered
by
• Patent owner consolidation
• Ownertyp identification
(University, Company)
• Legal situation (only active
patent families)
• Quality indexing over the
full database
• Geographical indication
2. Adding business-relevant
Parameters, normalize factors
SDV-II, 25.04.20172
3. Analysis
• Visualisation
• Identification of
trends, targets
and
opportunities
• Benchmarking
• Developing
decision
ground
4. Active Monitoring
• Updating the
selection with
high efficiency
using machine
learning and
text mining
• Easy assessing
and evaluating
of the data
• Re-assessing,
and re-
adjusting the
learned target
3. SDV-II, 25.04.20173
Source: Roland&Berger
Industry 4.0: from global buzz to reality
Definition of Industrial application of Industry
4.0: «Factory 4.0»
But what about
«Factory 4.0» in
the Patent
Landscape??
USE CASE: Industry 4.0 or Factory 4.0 and the
patent landscape
4. Worlds Average
SDV-II, 25.04.20174
Patent Landscape of Industrial application of Industry 4.0: «Factory 4.0»
Technology Fields of interest: Total 1.109 Mio active patent families
AverageQuality
CompetitiveImpact™
Forward Citation count (weighed and normalized)
Technology Relevance
Technology Fields
Process Automation
Sensors
Digital Communication
Ceramics
Additive Manufacturing
Advanced Manufacturing
Blockchain/Bitcoin
Predictive Maintenance
Artifical Intelligence
IoT Smart House
IoT Smart City
Autonomous Driving
Robotics
Nanomaterials
Carbon&Graphene
and further to cross sector
overlapping technologies
Robotic&ArtIntelligence
Sensors&ArtIntelligence
Sensors&Robotic
DigiCom&Robotic
DigiCom&Sensor
Bitcoin
to advanced technologies
Autonomous Driving
IoT Smart House / IoT Smart City
Add.Manufact Adv.Manufact
Robotic
Art.Intelligence
Carbon&Graphene
Nanomaterial Increasing quality due to forward citations:
From basic technologies
Digital Communication
Sensors
Ceramics
Process Automation
Factory 4.0 Patents: From basic to advanced
technology
5. Factory 4.0 Patent Players in 4 Regions*: Which
players and regions are prepared?
(*only EP and some WO publications, based in inventors adress)
5
Factory 4.0 Basics:
Sensors
Add. Manuf.
Nanomaterial
Robotik
Autonomous
Adv. Manuf.
MET Region Zürich /CH 1101 active
MET Region Munich/DE 3202 activeMET Region Ile de France /1537 active
MET Region SF/USA 4275 active
SDV-II, 25.04.2017
6. Worlds Average
SDV-II, 25.04.20176
Patent Landscape of Industrial application of Industry 4.0: «Factory 4.0»
Target Technology fields for Active Monitoring
AverageQuality
CompetitiveImpact™
Forward Citation count (weighed and normalized)
Technology Relevance
Technology Fields
Process Automation
Sensors
Digital Communication
Ceramics
Additive Manufacturing
Advanced Manufacturing
Blockchain/Bitcoin
Predictive Maintenance
Artifical Intelligence
IoT Smart House
IoT Smart City
Autonomous Driving
Robotics
Nanomaterials
Carbon&Graphene
and further to cross sector
technologies
Robotic&ArtIntelligence
Sensors&ArtIntelligence
Sensors&Robotic
DigiCom&Robotic
DigiCom&Sensor
Bitcoin
to advanced technologies
Autonomous Driving
IoT Smart House / IoT Smart City
Add.Manufact Adv.Manufact
Robotic
Art.Intelligence
Carbon&Graphene
Pred./Prev. Maintenance
Nanomaterial Increasing quality due to forward citations:
From basic technologies
Digital Communication
Sensors
Ceramics
Process Automation
Factory 4.0 Patents: Keeping in touch with the
development -> Active Monitoring
7. SDV-II, 25.04.20177
Advanced Technology fields choosen as examples for Active Monitoring:
Advanced Manufacturing
Additiv Manufacturing
Predictive / Preventive Maintenance
Bitcoin
8. SDV-II, 25.04.20178
Advanced Technology fields choosen as examples for Active Monitoring:
Advanced Manufacturing
Additiv Manufacturing
Predictive / Preventive Maintenance
Bitcoin
Top15 Player for the 4 technologiesTop 10 Countries
9. SDV-II, 25.04.20179
The question is: How to actively keep technology
fields up to date, without doing a search always
and again?
Automatic patent categorization
10. • is a machine-learning based document classification software
• automatically classifies documents into customer-specific categories
• continuously learns from and imitates the behavior of IP professionals
Our Solution
11. Our Approach in a NutshellDefine Categories1
Provide Examples & Train2
Let the System Categorize
Documents
3
Review Results4
Active
Learning
GO
Our Approach in a Nutshell
19. • Split the (manually) labeled document collection into training set
(90%) and into test set (10%)
• Train the classifier on the 90%
• Test the classifier on the 10% (already labeled)
• Count true positives, false positives and false negatives
• Repeat 10 times
19Cross-Evaluation
24. 24Summary
• Actively monitor technology field developments using automatic
patent categorization
• Based on machine learning by training on document collections
provided by experts
• Reliable even with few training examples
• Technology fields are valuable patent collections with multiple use
benefits (if they are collected by experts)
• Combination of data, normalized, weighted and enriched with
business information is the base for competitive advantage
25. Dr. Jochen Spuck
• Chemist, Expert in polymer chemistry
• Head of Product Development at ip-
search
• Patent Professional at the Swiss
Federal Institute of Intellectual
Property since 9 years
Dr. Kornél Markó
• Computer Scientist, Natural Language
Processing
• Co-Founder of Averbis GmbH, 2007
Questions?
SDV-II, 25.04.2017