ADD: PATSTAT CPC taxonomy and AI/ML/DB related groupsearch based on WOS keywords

PATSTAT/patstat_cpc_parse.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 60,
    "id": "a8be6839",
    "metadata": {},
    "outputs": [],
@@ -19,7 +19,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 61,
    "id": "211ba466",
    "metadata": {},
    "outputs": [],
@@ -39,7 +39,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 62,
    "id": "f878b151",
    "metadata": {},
    "outputs": [],
@@ -59,7 +59,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 63,
    "id": "95ea20da",
    "metadata": {},
    "outputs": [],
@@ -103,7 +103,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 63,
    "id": "907d9c3e",
    "metadata": {},
    "outputs": [],
@@ -111,7 +111,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 64,
    "id": "1be8971a",
    "metadata": {},
    "outputs": [
@@ -134,7 +134,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 65,
    "id": "b1274c34",
    "metadata": {},
    "outputs": [],
@@ -145,7 +145,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 66,
    "id": "2a7e39ee",
    "metadata": {},
    "outputs": [],
@@ -164,7 +164,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 67,
    "id": "e31a013f",
    "metadata": {},
    "outputs": [
@@ -172,7 +172,7 @@
      "data": {
       "text/plain": "[('A', 'HUMAN NECESSITIES'),\n ('A01',\n  'AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING'),\n ('A01B',\n  'SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS, DETAILS, OR ACCESSORIES OF AGRICULTURAL MACHINES OR IMPLEMENTS, IN GENERAL (making or covering furrows or holes for sowing, planting, or manuring A01C5/00; soil working for engineering purposes E01, E02, E21; {measuring areas for agricultural purposes G01B})'),\n ('A01B1/06',\n  'Hoes; Hand cultivators {(rakes A01D7/00; forks A01D9/00; picks B25D)}'),\n ('A01B1/065', '{powered}')]"
      },
-     "execution_count": 10,
+     "execution_count": 67,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -183,7 +183,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 68,
    "id": "f09a616c",
    "metadata": {},
    "outputs": [
@@ -192,7 +192,7 @@
       "text/plain": "     cpc_id                                           cpc_name section class   \n0         A                                  HUMAN NECESSITIES       A  None  \\\n1       A01  AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTI...       A    01   \n2      A01B  SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS...       A    01   \n3  A01B1/00  Hand tools (edge trimmers for lawns A01G3/06  ...       A    01   \n4  A01B1/02  Spades; Shovels {(hand-operated dredgers E02F3...       A    01   \n\n  subclass group main_group  cpc_version   \n0     None  None       None         2023  \\\n1     None  None       None         2023   \n2        B  None       None         2023   \n3        B     1         00         2023   \n4        B     1         02         2023   \n\n  version https://git-lfs.github.com/spec/v1   \n0                                        NaN  \\\n1                                        NaN   \n2                                        NaN   \n3                                        NaN   \n4                                        NaN   \n\n                                        cpc_taxonomy  \n0                           [(A, HUMAN NECESSITIES)]  \n1  [(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...  \n2  [(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...  \n3  [(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...  \n4  [(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...  ",
       "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>cpc_id</th>\n      <th>cpc_name</th>\n      <th>section</th>\n      <th>class</th>\n      <th>subclass</th>\n      <th>group</th>\n      <th>main_group</th>\n      <th>cpc_version</th>\n      <th>version https://git-lfs.github.com/spec/v1</th>\n      <th>cpc_taxonomy</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>A</td>\n      <td>HUMAN NECESSITIES</td>\n      <td>A</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES)]</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>A01</td>\n      <td>AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTI...</td>\n      <td>A</td>\n      <td>01</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>A01B</td>\n      <td>SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS...</td>\n      <td>A</td>\n      <td>01</td>\n      <td>B</td>\n      <td>None</td>\n      <td>None</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>A01B1/00</td>\n      <td>Hand tools (edge trimmers for lawns A01G3/06  ...</td>\n      <td>A</td>\n      <td>01</td>\n      <td>B</td>\n      <td>1</td>\n      <td>00</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>A01B1/02</td>\n      <td>Spades; Shovels {(hand-operated dredgers E02F3...</td>\n      <td>A</td>\n      <td>01</td>\n      <td>B</td>\n      <td>1</td>\n      <td>02</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
      },
-     "execution_count": 12,
+     "execution_count": 68,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -204,7 +204,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 69,
    "id": "f3fa8bf3",
    "metadata": {},
    "outputs": [
@@ -226,7 +226,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 70,
    "id": "58701721",
    "metadata": {},
    "outputs": [],
@@ -244,13 +244,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 71,
    "outputs": [
     {
      "data": {
       "text/plain": "'neural network|machine learn|deep learn|remote sensing|convolutional neural|internet of things|feature extraction|genetic algorithm|big data|artificial intelligence|data driven|support vector machine|logistic regression not p=|optimization algorithm|principal component analysis|artificial neural network|swarm optimization|regularization|linear regression not p=|optimization algorithm|random forest|cloud computing|reinforcement learning|computer vision|kalman filter|image processing|data mining|evolutionary algorithm|edge computing|supervised learning|computational modeling|pattern recognition|image classification|long short-term memor|robotics|image segmentation|convex optimization|covariance matri|attention mechanism|markov chain|object detection not brain|clustering algorithm|recurrent neural network|data augmentation|transfer learning|adversarial network|decision tree|multi agent system|fuzzy set|convolutional network|image reconstruction|data analytic|smart grid|autoencoder|fuzzy logic|radial basis function|bayesian network|dimensionality reduction|face recognition not brain|gaussian process|anomaly detection|k-nearest neighbor|natural language processing|monte carlo method|large dataset|gradient descent|support vector regression|extreme learning machine|perceptron|model selection|ensemble learning|representation learning|recommender system|target tracking|singular value decomposition|feature learning|smart city|sentiment analy|markov decision process|k-means clustering|independent component analysis|brain computer interface|human-computer interaction|markov chain monte carlo|hierarchical clustering|semantic web|semi-supervised learning|human-robot interact|knowledge graph|speech recognition not brain|ensemble model|fog computing|mapreduce|evolutionary computation|data science|text mining|generative model|active learning|swarm intelligence|multi-task learning|language model|collaborative filtering|backpropagation|machine vision|computer-aided diagnosis|gated recurrent unit|lagrange multiplier|expert system|learning rate|hadoop|markov process|nonlinear optimization|learning system|self-organizing map|smart manufacturing|smart home|few shot learning|few-shot learning|meta-learning|meta learning|adversarial training|zero-shot learning|word embedding|expectation maximization algorithm|stochastic gradient descent|ridge regression|deep belief network|non-negative matrix factorization|affective computing|latent dirichlet allocation|kernel method|kernel learning|feature engineering|variational inference|image representation|manifold learning|adversarial example|knowledge distillation|time series forecast|variational autoencoder|lasso regression|smart energy|dbscan|multi-label classification|intelligent robot|ubiquitous computing|gaussian mixture models|smart technolog|boltzmann machine|smart buildings|predictive analytic|pervasive computing|smart agriculture|capsule network|human-in-the-loop|intelligent agent|ai applications|word vector|transformer model|facial recognition|unstructured data|restricted boltzmann machine|albert|lifelong learning|autonomous agents|chatbot|cholesky decomposition|nosql|nosql|explainable ai|seq2seq|probabilistic graphical model|qr decomposition|unsupervised deep learning|data warehouse|quantum machine learning|continual learning|smart environment|multimodal learning|smart health|artificial immune system|swarm robotics|kernel machine|latent factor model|eigendecomposition|adversarial machine|adversarial machine learning|smart mobility|sequence-to-sequence model|eigen decomposition|adversarial robustness|smart parking|adversarial neural|roberta|bidirectional encoder representations from transformer|locally linear embedding|hebbian learning|one-shot learning|multimodal representation|smart tourism|entity extraction|adaptive moment estimation|ontology learning|topic modeling|relational database'"
      },
-     "execution_count": 49,
+     "execution_count": 71,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -269,19 +269,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": null,
+   "outputs": [],
+   "source": [],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
    "outputs": [
     {
      "data": {
       "text/plain": "               cpc_id                                           cpc_name   \n12725    A61B1/000096                    {using artificial intelligence}  \\\n13764      A61B5/7264  {Classification of physiological signals or da...   \n13897        A61B6/52  {Devices using data or image processing specia...   \n14016        A61B8/52  {Devices using data or image processing specia...   \n15252   A61B2018/0069                                {using fuzzy logic}   \n...               ...                                                ...   \n250685  Y10S707/99946         Object-oriented database structure network   \n250686  Y10S707/99947       Object-oriented database structure reference   \n250687  Y10S707/99948  Application of database or data structure, e.g...   \n250688  Y10S707/99951                       File or database maintenance   \n250703    Y10S715/968      interface for database querying and retrieval   \n\n       section class subclass group main_group  cpc_version   \n12725        A    61        B     1     000096         2023  \\\n13764        A    61        B     5       7264         2023   \n13897        A    61        B     6         52         2023   \n14016        A    61        B     8         52         2023   \n15252        A    61        B  2018       0069         2023   \n...        ...   ...      ...   ...        ...          ...   \n250685       Y    10        S   707      99946         2023   \n250686       Y    10        S   707      99947         2023   \n250687       Y    10        S   707      99948         2023   \n250688       Y    10        S   707      99951         2023   \n250703       Y    10        S   715        968         2023   \n\n       version https://git-lfs.github.com/spec/v1   \n12725                                         NaN  \\\n13764                                         NaN   \n13897                                         NaN   \n14016                                         NaN   \n15252                                         NaN   \n...                                           ...   \n250685                                        NaN   \n250686                                        NaN   \n250687                                        NaN   \n250688                                        NaN   \n250703                                        NaN   \n\n                                             cpc_taxonomy  \n12725   [(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...  \n13764   [(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...  \n13897   [(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...  \n14016   [(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...  \n15252   [(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...  \n...                                                   ...  \n250685  [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...  \n250686  [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...  \n250687  [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...  \n250688  [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...  \n250703  [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...  \n\n[317 rows x 10 columns]",
       "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>cpc_id</th>\n      <th>cpc_name</th>\n      <th>section</th>\n      <th>class</th>\n      <th>subclass</th>\n      <th>group</th>\n      <th>main_group</th>\n      <th>cpc_version</th>\n      <th>version https://git-lfs.github.com/spec/v1</th>\n      <th>cpc_taxonomy</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>12725</th>\n      <td>A61B1/000096</td>\n      <td>{using artificial intelligence}</td>\n      <td>A</td>\n      <td>61</td>\n      <td>B</td>\n      <td>1</td>\n      <td>000096</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...</td>\n    </tr>\n    <tr>\n      <th>13764</th>\n      <td>A61B5/7264</td>\n      <td>{Classification of physiological signals or da...</td>\n      <td>A</td>\n      <td>61</td>\n      <td>B</td>\n      <td>5</td>\n      <td>7264</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...</td>\n    </tr>\n    <tr>\n      <th>13897</th>\n      <td>A61B6/52</td>\n      <td>{Devices using data or image processing specia...</td>\n      <td>A</td>\n      <td>61</td>\n      <td>B</td>\n      <td>6</td>\n      <td>52</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...</td>\n    </tr>\n    <tr>\n      <th>14016</th>\n      <td>A61B8/52</td>\n      <td>{Devices using data or image processing specia...</td>\n      <td>A</td>\n      <td>61</td>\n      <td>B</td>\n      <td>8</td>\n      <td>52</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...</td>\n    </tr>\n    <tr>\n      <th>15252</th>\n      <td>A61B2018/0069</td>\n      <td>{using fuzzy logic}</td>\n      <td>A</td>\n      <td>61</td>\n      <td>B</td>\n      <td>2018</td>\n      <td>0069</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>250685</th>\n      <td>Y10S707/99946</td>\n      <td>Object-oriented database structure network</td>\n      <td>Y</td>\n      <td>10</td>\n      <td>S</td>\n      <td>707</td>\n      <td>99946</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n    </tr>\n    <tr>\n      <th>250686</th>\n      <td>Y10S707/99947</td>\n      <td>Object-oriented database structure reference</td>\n      <td>Y</td>\n      <td>10</td>\n      <td>S</td>\n      <td>707</td>\n      <td>99947</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n    </tr>\n    <tr>\n      <th>250687</th>\n      <td>Y10S707/99948</td>\n      <td>Application of database or data structure, e.g...</td>\n      <td>Y</td>\n      <td>10</td>\n      <td>S</td>\n      <td>707</td>\n      <td>99948</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n    </tr>\n    <tr>\n      <th>250688</th>\n      <td>Y10S707/99951</td>\n      <td>File or database maintenance</td>\n      <td>Y</td>\n      <td>10</td>\n      <td>S</td>\n      <td>707</td>\n      <td>99951</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n    </tr>\n    <tr>\n      <th>250703</th>\n      <td>Y10S715/968</td>\n      <td>interface for database querying and retrieval</td>\n      <td>Y</td>\n      <td>10</td>\n      <td>S</td>\n      <td>715</td>\n      <td>968</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n    </tr>\n  </tbody>\n</table>\n<p>317 rows × 10 columns</p>\n</div>"
      },
-     "execution_count": 54,
+     "execution_count": 72,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "#dummy search\n",
     "scope_df = cpc_ids[cpc_ids[\"cpc_name\"].str.lower().str.contains(\"machine learn|neural network|deep learn|deep network|artificial intel*| big data|database|recommender system|computer vision|image processing|language model|language processing|fuzzy logic|principal component|image classification|video classification\", regex=True, na=False)]\n",
     "scope_df"
    ],
@@ -291,7 +301,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 58,
+   "execution_count": 73,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "              cpc_id                                           cpc_name   \n12725   A61B1/000096                    {using artificial intelligence}  \\\n13746       A61B5/72  {Signal processing specially adapted for physi...   \n13764     A61B5/7264  {Classification of physiological signals or da...   \n13897       A61B6/52  {Devices using data or image processing specia...   \n14016       A61B8/52  {Devices using data or image processing specia...   \n...              ...                                                ...   \n246159   Y10S128/924                      using artificial intelligence   \n246160   Y10S128/925                                     Neural network   \n248454   Y10S323/909                                     Remote sensing   \n250570    Y10S706/00           Data processing: artificial intelligence   \n250571    Y10S706/90                                        Fuzzy logic   \n\n       section class subclass group main_group  cpc_version   \n12725        A    61        B     1     000096         2023  \\\n13746        A    61        B     5         72         2023   \n13764        A    61        B     5       7264         2023   \n13897        A    61        B     6         52         2023   \n14016        A    61        B     8         52         2023   \n...        ...   ...      ...   ...        ...          ...   \n246159       Y    10        S   128        924         2023   \n246160       Y    10        S   128        925         2023   \n248454       Y    10        S   323        909         2023   \n250570       Y    10        S   706         00         2023   \n250571       Y    10        S   706         90         2023   \n\n       version https://git-lfs.github.com/spec/v1   \n12725                                         NaN  \\\n13746                                         NaN   \n13764                                         NaN   \n13897                                         NaN   \n14016                                         NaN   \n...                                           ...   \n246159                                        NaN   \n246160                                        NaN   \n248454                                        NaN   \n250570                                        NaN   \n250571                                        NaN   \n\n                                             cpc_taxonomy  \n12725   [(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...  \n13746   [(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...  \n13764   [(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...  \n13897   [(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...  \n14016   [(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...  \n...                                                   ...  \n246159  [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...  \n246160  [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...  \n248454  [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...  \n250570  [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...  \n250571  [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...  \n\n[358 rows x 10 columns]",
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>cpc_id</th>\n      <th>cpc_name</th>\n      <th>section</th>\n      <th>class</th>\n      <th>subclass</th>\n      <th>group</th>\n      <th>main_group</th>\n      <th>cpc_version</th>\n      <th>version https://git-lfs.github.com/spec/v1</th>\n      <th>cpc_taxonomy</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>12725</th>\n      <td>A61B1/000096</td>\n      <td>{using artificial intelligence}</td>\n      <td>A</td>\n      <td>61</td>\n      <td>B</td>\n      <td>1</td>\n      <td>000096</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...</td>\n    </tr>\n    <tr>\n      <th>13746</th>\n      <td>A61B5/72</td>\n      <td>{Signal processing specially adapted for physi...</td>\n      <td>A</td>\n      <td>61</td>\n      <td>B</td>\n      <td>5</td>\n      <td>72</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...</td>\n    </tr>\n    <tr>\n      <th>13764</th>\n      <td>A61B5/7264</td>\n      <td>{Classification of physiological signals or da...</td>\n      <td>A</td>\n      <td>61</td>\n      <td>B</td>\n      <td>5</td>\n      <td>7264</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...</td>\n    </tr>\n    <tr>\n      <th>13897</th>\n      <td>A61B6/52</td>\n      <td>{Devices using data or image processing specia...</td>\n      <td>A</td>\n      <td>61</td>\n      <td>B</td>\n      <td>6</td>\n      <td>52</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...</td>\n    </tr>\n    <tr>\n      <th>14016</th>\n      <td>A61B8/52</td>\n      <td>{Devices using data or image processing specia...</td>\n      <td>A</td>\n      <td>61</td>\n      <td>B</td>\n      <td>8</td>\n      <td>52</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A61, MEDICAL OR VETE...</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>246159</th>\n      <td>Y10S128/924</td>\n      <td>using artificial intelligence</td>\n      <td>Y</td>\n      <td>10</td>\n      <td>S</td>\n      <td>128</td>\n      <td>924</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n    </tr>\n    <tr>\n      <th>246160</th>\n      <td>Y10S128/925</td>\n      <td>Neural network</td>\n      <td>Y</td>\n      <td>10</td>\n      <td>S</td>\n      <td>128</td>\n      <td>925</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n    </tr>\n    <tr>\n      <th>248454</th>\n      <td>Y10S323/909</td>\n      <td>Remote sensing</td>\n      <td>Y</td>\n      <td>10</td>\n      <td>S</td>\n      <td>323</td>\n      <td>909</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n    </tr>\n    <tr>\n      <th>250570</th>\n      <td>Y10S706/00</td>\n      <td>Data processing: artificial intelligence</td>\n      <td>Y</td>\n      <td>10</td>\n      <td>S</td>\n      <td>706</td>\n      <td>00</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n    </tr>\n    <tr>\n      <th>250571</th>\n      <td>Y10S706/90</td>\n      <td>Fuzzy logic</td>\n      <td>Y</td>\n      <td>10</td>\n      <td>S</td>\n      <td>706</td>\n      <td>90</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n    </tr>\n  </tbody>\n</table>\n<p>358 rows × 10 columns</p>\n</div>"
+     },
+     "execution_count": 73,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "scope_df = cpc_ids[cpc_ids[\"cpc_name\"].str.lower().str.contains(keywords, regex=True, na=False)]\n",
+    "scope_df"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
    "id": "6c3baa5b",
    "metadata": {},
    "outputs": [],
@@ -303,13 +335,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
+   "execution_count": 75,
    "outputs": [
     {
      "data": {
       "text/plain": "'WESTERN_CH_scope'"
      },
-     "execution_count": 59,
+     "execution_count": 75,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -323,14 +355,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": 76,
    "outputs": [
     {
      "data": {
       "text/plain": "              cpc_id                                           cpc_name   \n0                  A                                  HUMAN NECESSITIES  \\\n1                A01  AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTI...   \n2               A01B  SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS...   \n3           A01B1/00  Hand tools (edge trimmers for lawns A01G3/06  ...   \n4           A01B1/02  Spades; Shovels {(hand-operated dredgers E02F3...   \n...              ...                                                ...   \n260486  Y10T483/1873                                    Indexing matrix   \n260487  Y10T483/1882                                        Rotary disc   \n260488  Y10T483/1891                                      Chain or belt   \n260489    Y10T483/19                                      Miscellaneous   \n260490           NaN                                                NaN   \n\n       section class subclass group main_group  cpc_version   \n0            A  None     None  None       None         2023  \\\n1            A    01     None  None       None         2023   \n2            A    01        B  None       None         2023   \n3            A    01        B     1         00         2023   \n4            A    01        B     1         02         2023   \n...        ...   ...      ...   ...        ...          ...   \n260486       Y    10        T   483       1873         2023   \n260487       Y    10        T   483       1882         2023   \n260488       Y    10        T   483       1891         2023   \n260489       Y    10        T   483         19         2023   \n260490     NaN   NaN      NaN   NaN        NaN         2022   \n\n               version https://git-lfs.github.com/spec/v1   \n0                                                     NaN  \\\n1                                                     NaN   \n2                                                     NaN   \n3                                                     NaN   \n4                                                     NaN   \n...                                                   ...   \n260486                                                NaN   \n260487                                                NaN   \n260488                                                NaN   \n260489                                                NaN   \n260490  oid sha256:f138d6bdf2939ba576b96b633d81366123b...   \n\n                                             cpc_taxonomy  data_scope  \n0                                [(A, HUMAN NECESSITIES)]       False  \n1       [(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...       False  \n2       [(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...       False  \n3       [(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...       False  \n4       [(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...       False  \n...                                                   ...         ...  \n260486  [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...       False  \n260487  [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...       False  \n260488  [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...       False  \n260489  [(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...       False  \n260490                                                 []       False  \n\n[260491 rows x 11 columns]",
       "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>cpc_id</th>\n      <th>cpc_name</th>\n      <th>section</th>\n      <th>class</th>\n      <th>subclass</th>\n      <th>group</th>\n      <th>main_group</th>\n      <th>cpc_version</th>\n      <th>version https://git-lfs.github.com/spec/v1</th>\n      <th>cpc_taxonomy</th>\n      <th>data_scope</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>A</td>\n      <td>HUMAN NECESSITIES</td>\n      <td>A</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES)]</td>\n      <td>False</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>A01</td>\n      <td>AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTI...</td>\n      <td>A</td>\n      <td>01</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...</td>\n      <td>False</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>A01B</td>\n      <td>SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS...</td>\n      <td>A</td>\n      <td>01</td>\n      <td>B</td>\n      <td>None</td>\n      <td>None</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...</td>\n      <td>False</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>A01B1/00</td>\n      <td>Hand tools (edge trimmers for lawns A01G3/06  ...</td>\n      <td>A</td>\n      <td>01</td>\n      <td>B</td>\n      <td>1</td>\n      <td>00</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...</td>\n      <td>False</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>A01B1/02</td>\n      <td>Spades; Shovels {(hand-operated dredgers E02F3...</td>\n      <td>A</td>\n      <td>01</td>\n      <td>B</td>\n      <td>1</td>\n      <td>02</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(A, HUMAN NECESSITIES), (A01, AGRICULTURE; FO...</td>\n      <td>False</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>260486</th>\n      <td>Y10T483/1873</td>\n      <td>Indexing matrix</td>\n      <td>Y</td>\n      <td>10</td>\n      <td>T</td>\n      <td>483</td>\n      <td>1873</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n      <td>False</td>\n    </tr>\n    <tr>\n      <th>260487</th>\n      <td>Y10T483/1882</td>\n      <td>Rotary disc</td>\n      <td>Y</td>\n      <td>10</td>\n      <td>T</td>\n      <td>483</td>\n      <td>1882</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n      <td>False</td>\n    </tr>\n    <tr>\n      <th>260488</th>\n      <td>Y10T483/1891</td>\n      <td>Chain or belt</td>\n      <td>Y</td>\n      <td>10</td>\n      <td>T</td>\n      <td>483</td>\n      <td>1891</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n      <td>False</td>\n    </tr>\n    <tr>\n      <th>260489</th>\n      <td>Y10T483/19</td>\n      <td>Miscellaneous</td>\n      <td>Y</td>\n      <td>10</td>\n      <td>T</td>\n      <td>483</td>\n      <td>19</td>\n      <td>2023</td>\n      <td>NaN</td>\n      <td>[(Y, GENERAL TAGGING OF NEW TECHNOLOGICAL DEVE...</td>\n      <td>False</td>\n    </tr>\n    <tr>\n      <th>260490</th>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>2022</td>\n      <td>oid sha256:f138d6bdf2939ba576b96b633d81366123b...</td>\n      <td>[]</td>\n      <td>False</td>\n    </tr>\n  </tbody>\n</table>\n<p>260491 rows × 11 columns</p>\n</div>"
      },
-     "execution_count": 56,
+     "execution_count": 76,
      "metadata": {},
      "output_type": "execute_result"
     }