1. Machine Learning Assisted IPC-based Sorting at IP Australia
Abhinay Mukunthan
Senior Examiner of Patents
IP Australia

2. Examination Work-flow at IP Australia
New Application Filed
Technology Sorting
Classification
Examination
Sub-class level classification to select examination section
Sub-group level classification in IPC (and CPC if AU original)

3. IP Australia’s Patent Examination Structure
14 Examination workgroups
Work allocated to each exam group based on IPC sub-class, in rare occasions by main-group or sub-group
Example: Medical devices examines A61B,C,D,F,G,H,J,M,N and C12M
Example: Bio-technology examines A01H, A01K67, C12N,Q,R,S, C04B20 and G01N33/48-52 and G01N33/566-98

4. Technology Sorting – Existing Practice
Currently performed by examiners to allocate an IPC sub-class to all incoming non-national phase applications
where required, a main-group or sub-group are also allocated
Estimated time spent: average of 2.5 minutes per application with around cases per year, equating to roughly 64 working days per year

5. Technology Sorting – Machine Learning Trial
PAC (Patent Auto-Classifier) – a machine learning based system to perform technology sorting of PCT applications by allocating IPC main-group level information
PAC is built around a training database of applications from including:
All IP Australia classified national, convention and PCT applications
All AU national phase applications with existing IPC symbols from other offices
Results from a three month trial (late 2018)
86% accuracy when sorting to the right examination workgroup

6. Overview of the System
Sits outside existing case-management and other IT systems
Uses a hierarchical training and prediction model - mirroring the IPC structure
Always selects the top three results at each level of the hierarchy before traversing to the next level
Once a selection of results are available at a particular level of detail, the top three overall results are selected

7. A Simplified Example of the Algorithm
Claim being classified: An unmanned aerial vehicle based wireless sensor network using satellite positioning.
Required level of detail: IPC Main-group A B
B60
B62
B64
B64B
B64C
B64C27
B64C29
B64C39
B64D C D E F G
G01
G01P
G01R
G01S
G01S7
G01S11
G01S19
G05
G06 H
H01
H03
H04
H04B
H04L
H04W
H04W4
H04W40
H04W84

8. Training the Algorithm – an overview
Symbol
Document
Terms
Each symbol has a cluster of representative documents and each document has a cluster of weighted terms
Terms in a document are weighted based on:
Frequency within the same document
Inverse-frequency across different documents
Example: Terms like “Encryption”, “Transmission” occur frequently within the same document but not across many documents  Higher weighting
Example: Terms like “Figure”, “Abstract” occur frequently within all documents  Lower weighting
H04L 1/00
H04L 5/00
H04L 7/00
H04L 9/00 AU
Encryption
Encode
Cipher AU AU AU
Transmission
Authentication
Token
Secret AU
H04L 12/00
H04L13/00
H04L 15/00

9. Training the Algorithm – looking a bit deeper
Each node (symbol) in the IPC is trained with a sample of documents with that particular symbol using an extreme gradient boosting (XGBoost) algorithm
Term similarities are measured using pre-trained word embedding over IPA patent documents (using the word2vec algorithm)
The combination of term weighting and word embedding is used to measure the distance between patent documents
When a new application is classified, each IPC node runs its own customised algorithm to provide a probability score for that application belonging to that node

10. Future Work
Integrate PAC with existing IT systems using process automation tools (PEGA Robotics)
Run trials with an expanded training data set including USPTO and EPO applications and classifications
Trial predictions at full IPC Sub-group level to provide suggestions to examiners
Expand the system to work with USPTO and EPO CPC data sets and provide CPC suggestions
Collaborate with other offices on their efforts in AI and ML-assisted classification

11. Thank you Abhinay Mukunthan Senior Examiner of Patents IP Australia