Aggregating procedures for automatic document analysis
This disclosure describes, in part, techniques for performing automatic document analysis. For instance, one or more computing devices may obtain a plurality of documents for analysis. The one or more computing devices may then analyze the documents to determine a respective comparative breadth score representing a breadth of each document, a respective comparative portion count score representing a number of documents portions included in each document, and a respective comparative differentiation score representing differentiation between the documents portions included in each document. In some instances, the one or more computing devices determine each of the scores based on comparing the respective breadth, respective number of document portions, and respective differentiation for each of the documents under analysis. The one or more computing devices can then determine a comprehensive score for each document using the respective scores, and generate a user interface that includes the overall scores.
1. A system comprising:
one or more processors; and
one or more computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processor to perform operations comprising:
receiving intellectual-property assets from one or more data repositories, individual ones of the intellectual-property assets including respective portions of text;
generating, for an intellectual-property asset of the intellectual-property assets, a word count score for individual ones of the portions of text based at least in part on a comparison between a word count associated with the respective portion of text and word counts associated with portions of text from at least one other intellectual-property asset of the intellectual-property assets;
identifying one or more words included in the respective portion of text;
identifying differences between the one or more words included in the respective portion of text and one or more words in the portions of text from the at least one other IP asset;
identifying similarities between the one or more words included in the respective portion of text and the one or more words in the portions of text from the at least one other IP asset;
generating a differential score for the individual ones of the portions of text, the differential score for a respective portion of text being based at least in part on the word count score, the differences between the one or more words included in the respective portion of text and the one or more words included in the portions of text from the at least one other IP asset, and the similarities between the one or more words included in the respective portion of text and one or more words in the portions of text from the at least one other IP asset;
generating an overall differentiation score for the individual ones of the intellectual-property assets based at least in part on an average of the differential scores for the individual ones of the portions of text;
generating a comparative differentiation score for the intellectual-property assets based at least in part on comparing the overall differentiation score of an individual intellectual-property asset to additional overall differentiation scores of the intellectual-property assets;
generating a ranking for the intellectual-property assets based at least in part on the comparative differentiation score for the intellectual-property assets; and
generating a user interface that includes at least the comparative differentiation scores for the intellectual-property assets, the user interface causing display of the intellectual-property assets based at least in part on the ranking.
2. The system of claim 1 , the operations further comprising:
generating the overall differentiation score for the intellectual-property asset by taking an average of the differentiation scores for the portions of text; and
generating the respective overall differentiation scores for respective intellectual-property assets of the intellectual-property assets,
wherein generating the comparative differentiation score comprises generating a percentage of intellectual-property assets from the intellectual-property assets that include a respective overall differentiation score that is less favorable or equally favorable to the overall differentiation score of the intellectual-property asset.
3. The system of claim 1 , the operations further comprising:
generating a commonness score for the individual ones of the portions of text based at least in part on a frequency in which words within the respective portion of text are found in the portions of text from the at least one other intellectual-property asset;
generating a breadth score for the individual ones of the portions of text based at least in part on the word count score and the commonness score for the respective portion of text;
generating an overall breadth score for the intellectual-property asset based at least in part on the breadth scores for the portions of text;
generating a comparative breadth score for the intellectual-property assets based at least in part on the overall breadth scores of the intellectual-property related assets; and
generating a user interface that includes at least the comparative breadth scores for the intellectual-property assets.
4. The system of claim 3 , the operations further comprising:
generating the respective overall breadth scores for respective intellectual-property assets of the intellectual-property assets,
wherein generating the comparative breadth score comprises generating a percentage of intellectual-property assets from the intellectual-property assets that include a respective overall breadth score that is less favorable or equally favorable to the overall breadth score of the intellectual-property asset.
5. The system of claim 3 , the operations further comprising:
generating a portion score for the individual ones of the intellectual-property assets based at least in part on a value corresponding to a number of portions of text that are included in the portions of text of the intellectual-property asset;
generating a comparative portion score for the intellectual-property assets based at least in part on the portion scores of the intellectual-property assets; and
generating a user interface that includes at least the comparative portion score for the intellectual-property asset.
6. The system of claim 5 , the operations further comprising:
generating the respective portion scores for respective intellectual-property related assets of the intellectual property related assets,
wherein generating the comparative portion score comprises generating a percentage of intellectual-property assets from the intellectual-property assets that include a respective value that is less favorable or equally favorable to the portion score of the intellectual property related asset.
7. The system of claim 5 , the operations further comprising:
generating a comprehensive score for the intellectual-property asset based at least in part on the overall differentiation score, the overall breadth score, and the portion score, the comprehensive score representing a favorability of the intellectual-property asset with respect to the intellectual-property assets; and
generating a user interfaces that includes at least the comprehensive score for the intellectual-property asset.
8. The system of claim 7 , wherein generating the comprehensive score for the intellectual-property asset comprises generating an average of the overall differentiation score, the overall breadth score, and the portion score.
9. The system of claim 7 , the operations further comprising:
generating a weighted differentiation score by multiplying the overall differentiation score by a first weight;
generating a weighted breadth score by multiplying the overall breadth score by a second weight, wherein the second weight is different than the first weight; and
generating a weighted portion score by multiplying the portion score by a third weight, wherein the third weight is different than at least one of the first weight or the second weight,
wherein generating the comprehensive score for the intellectual-property asset is based at least in part on the weighted differentiation score, the weighted breadth score, and the weighted portion score.
10. The system of claim 9 , wherein generating the comprehensive score for the intellectual-property asset comprises generating an average of the weighted differentiation score, the weighted breadth score, and the weighted portion score.
11. A method comprising
receiving, by one or more processors, intellectual-property assets from one or more data repositories, individual ones of the intellectual-property assets including respective portions of text;
generating, by the one or more processors and for an intellectual-property asset of the intellectual-property assets, a word count score for individual ones of the portions of text based at least in part on a comparison between a word count associated with the respective portion of text and word counts associated with portions of text from at least one other intellectual-property asset of the intellectual-property assets;
identifying, by the one or more processors, one or more words included in the respective portion of text;
identifying, by the one or more processors, differences between the one or more words included in the respective portion of text and one or more words in the portions of text from the at least one other IP asset;
identifying similarities between the one or more words included in the respective portion of text and the one or more words in the portions of text from the at least one other IP asset;
generating, by the one or more processors, a differential score for the individual ones of the portions of text, the differential score for a respective portion of text being based at least in part on the word count score, the differences between the one or more words included in the respective portion of text and the one or more words included in the portions of text from the at least one other IP asset, and the similarities between the one or more words included in the respective portion of text and one or more words in the portions of text from the at least one other IP asset;
generating, by the one or more processors, an overall differentiation score for the individual ones of the intellectual-property assets based at least in part on an average of the differential scores for the individual ones of the portions of text;
generating, by the one or more processors, a comparative differentiation score for the intellectual-property assets based at least in part on comparing the overall differentiation score of an individual intellectual-property asset to additional overall differential scores of the intellectual-property assets;
generating, by the one or more processors, a ranking for the intellectual-property assets based at least in part on the comparative differentiation score for the intellectual-property assets; and
generating, by the one or more processors, a user interface that includes at least the comparative differentiation scores for the intellectual-property assets, the user interface causing display of the intellectual-property assets based at least in part on the ranking.
12. The method of claim 11 , further comprising:
generating the overall differentiation score for the intellectual-property asset by taking an average of the differentiation scores for the portions of text; and
generating the respective overall differentiation scores for respective intellectual-property assets of the intellectual-property assets,
wherein generating the comparative differentiation score comprises generating a percentage of intellectual-property assets from the intellectual-property assets that include a respective overall differentiation score that is less favorable or equally favorable to the overall differentiation score of the intellectual-property asset.
13. The method of claim 11 , further comprising:
generating a commonness score for the individual ones of the portions of text based at least in part on a frequency in which words within the respective portion of text are found in the portions of text from the at least one other intellectual-property asset;
generating a breadth score for the individual ones of the portions of text based at least in part on the word count score and the commonness score for the respective portion of text;
generating an overall breadth score for the intellectual-property asset based at least in part on the breadth scores for the portions of text;
generating a comparative breadth score for the intellectual-property assets based at least in part on the overall breadth scores of the intellectual-property related assets; and
generating a user interface that includes at least the comparative breadth scores for the intellectual-property assets.
14. The method of claim 13 , further comprising:
generating the respective overall breadth scores for respective intellectual-property assets of the intellectual-property assets,
wherein generating the comparative breadth score comprises generating a percentage of intellectual-property assets from the intellectual-property assets that include a respective overall breadth score that is less favorable or equally favorable to the overall breadth score of the intellectual-property asset.
15. The method of claim 13 , further comprising:
generating a portion score for the individual ones of the intellectual-property assets based at least in part on a value corresponding to a number of portions of text that are included in the portions of text of the intellectual-property asset;
generating a comparative portion score for the intellectual-property assets based at least in part on the portion scores of the intellectual-property assets; and
generating a user interface that includes at least the comparative portion score for the intellectual-property asset.
16. The method of claim 15 , further comprising:
generating the respective portion scores for respective intellectual-property related assets of the intellectual property related assets,
wherein generating the comparative portion score comprises generating a percentage of intellectual-property assets from the intellectual-property assets that include a respective value that is less favorable or equally favorable to the portion score of the intellectual property related asset.
17. The method of claim 15 , further comprising:
generating a comprehensive score for the intellectual-property asset based at least in part on the overall differentiation score, the overall breadth score, and the portion score, the comprehensive score representing a favorability of the intellectual-property asset with respect to the intellectual-property assets; and
generating a user interfaces that includes at least the comprehensive score for the intellectual-property asset.
18. The method of claim 17 , wherein generating the comprehensive score for the intellectual-property asset comprises generating an average of the overall differentiation score, the overall breadth score, and the portion score.
19. The method of claim 17 , further comprising:
generating a weighted differentiation score by multiplying the overall differentiation score by a first weight;
generating a weighted breadth score by multiplying the overall breadth score by a second weight, wherein the second weight is different than the first weight; and
generating a weighted portion score by multiplying the portion score by a third weight, wherein the third weight is different than at least one of the first weight or the second weight,
wherein generating the comprehensive score for the intellectual-property asset is based at least in part on the weighted differentiation score, the weighted breadth score, and the weighted portion score.
20. The system of claim 19 , wherein generating the comprehensive score for the intellectual-property asset comprises generating an average of the weighted differentiation score, the weighted breadth score, and the weighted portion score.