SVM/RBF training and prediction outcomes by percentage across 11 significant regions and decision groups of invalidation re-examination
| Applicant region | Patent set | Patents | Classification accuracy (%) | ||
|---|---|---|---|---|---|
| Claims fully or partly valid (Group 1) | Claims all invalid (Group 0) | Overall | |||
| 1 (US) | Training set | 474 | 95.95% | 14.04% | 65.19% |
| Prediction set | 277 | 94.62% | 12.09% | 67.51% | |
| 2 (JP) | Training set | 463 | 96.03% | 18.01% | 68.90% |
| Prediction set | 246 | 92.22% | 8.86% | 65.45% | |
| 3 (Guangdong) | Training set | 416 | 98.33% | 6.90% | 72.84% |
| Prediction set | 225 | 93.63% | 10.29% | 68.44% | |
| 4 (Shenzhen) | Training set | 404 | 97.64% | 17.76% | 76.49% |
| Prediction set | 220 | 95.06% | 10.34% | 72.73% | |
| 5 (Jiangsu) | Training set | 420 | 98.99% | 2.46% | 70.95% |
| Prediction set | 193 | 97.14% | 1.89% | 70.98% | |
| 6 (Zhejiang) | Training set | 391 | 99.63% | 2.50% | 69.82% |
| Prediction set | 221 | 99.36% | 1.54% | 70.59% | |
| 7 (Beijing) | Training set | 397 | 100.00% | 0.00% | 73.05% |
| Prediction set | 156 | 100.00% | 0.00% | 69.87% | |
| 8 (DE) | Training set | 236 | 98.68% | 0.00% | 63.14% |
| Prediction set | 126 | 97.62% | 0.00% | 65.08% | |
| 9 (Shanghai) | Training set | 211 | 100.00% | 1.32% | 64.45% |
| Prediction set | 113 | 98.61% | 0.00% | 62.83% | |
| 12 (CN-others) | Training set | 1,039 | 99.17% | 3.51% | 70.36% |
| Prediction set | 555 | 99.50% | 0.66% | 72.43% | |
| 13 (Overseas-others) | Training set | 852 | 96.01% | 23.55% | 72.54% |
| Prediction set | 436 | 90.78% | 12.59% | 65.14% | |
| Average | Training set | 5,303 | 98.05% | 9.87% | 70.43% |
| Prediction set | 2,768 | 95.96% | 6.20% | 68.75% | |
| Total | 8,071 | 97.33% | 8.64% | 69.86% | |
| Average difference | (Training-test) | 2.09% | 3.68% | 1.68% | |
| Applicant region | Patent set | Patents | Classification accuracy (%) | ||
|---|---|---|---|---|---|
| Claims fully or partly valid (Group 1) | Claims all invalid (Group 0) | Overall | |||
| 1 (US) | Training set | 474 | 95.95% | 14.04% | 65.19% |
| Prediction set | 277 | 94.62% | 12.09% | 67.51% | |
| 2 (JP) | Training set | 463 | 96.03% | 18.01% | 68.90% |
| Prediction set | 246 | 92.22% | 8.86% | 65.45% | |
| 3 (Guangdong) | Training set | 416 | 98.33% | 6.90% | 72.84% |
| Prediction set | 225 | 93.63% | 10.29% | 68.44% | |
| 4 (Shenzhen) | Training set | 404 | 97.64% | 17.76% | 76.49% |
| Prediction set | 220 | 95.06% | 10.34% | 72.73% | |
| 5 (Jiangsu) | Training set | 420 | 98.99% | 2.46% | 70.95% |
| Prediction set | 193 | 97.14% | 1.89% | 70.98% | |
| 6 (Zhejiang) | Training set | 391 | 99.63% | 2.50% | 69.82% |
| Prediction set | 221 | 99.36% | 1.54% | 70.59% | |
| 7 (Beijing) | Training set | 397 | 100.00% | 0.00% | 73.05% |
| Prediction set | 156 | 100.00% | 0.00% | 69.87% | |
| 8 (DE) | Training set | 236 | 98.68% | 0.00% | 63.14% |
| Prediction set | 126 | 97.62% | 0.00% | 65.08% | |
| 9 (Shanghai) | Training set | 211 | 100.00% | 1.32% | 64.45% |
| Prediction set | 113 | 98.61% | 0.00% | 62.83% | |
| 12 (CN-others) | Training set | 1,039 | 99.17% | 3.51% | 70.36% |
| Prediction set | 555 | 99.50% | 0.66% | 72.43% | |
| 13 (Overseas-others) | Training set | 852 | 96.01% | 23.55% | 72.54% |
| Prediction set | 436 | 90.78% | 12.59% | 65.14% | |
| Average | Training set | 5,303 | 98.05% | 9.87% | 70.43% |
| Prediction set | 2,768 | 95.96% | 6.20% | 68.75% | |
| Total | 8,071 | 97.33% | 8.64% | 69.86% | |
| Average difference | (Training-test) | 2.09% | 3.68% | 1.68% | |
Note(s): Classifying parameters: all indicators of significance for each region
Training set: patents issued in months excluding March, June, September and December
Prediction set: patents issued in March, June, September and December
Source(s): Authors’ own work
As a benefit of your subscription, you can share temporary access to restricted articles.
Each link will stop working after 30 days or 10 uses. You may create up to 10 links in a 30 day period.
Please sign in to your personal account to gift article access.
As a benefit of your subscription, you can share temporary access to restricted articles.
Each link will stop working after 30 days or 10 uses. You may create up to 10 links in a 30 day period.
Gift articles remaining: --
Each link will stop working after 30 days or 10 uses. You may create up to 10 links in a 30 day period.
Gift articles remaining: --
As a benefit of your subscription, you can share temporary access to restricted articles.
Each link will stop working after 30 days or 10 uses.
You have reached the limit of 10 links within a 30 day period.
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.