Similar document identification using artificial intelligence
Implementations generally relate to processing similar documents. In some implementations, a method includes receiving a plurality of documents related to e-discovery. The method further includes determining a seed document from the plurality of documents. The method further includes receiving a search request to search at least one selection of text in the seed document. The method further includes identifying other documents from the plurality of documents based on a similarity between text in the other documents and the at least one selection of text in the seed document. The method further includes generating a graphical user interface that includes a similarity panel that provides similarity data between text in the other documents and the at least one selection of text in the seed document.
1. A method comprising:
receiving a plurality of documents;
determining, based on artificial intelligence and a type of legal issue, a seed document from the plurality of documents;
suggesting, based on the artificial intelligence and the type of legal issue, at least one selection of text in the seed document;
receiving a search request to search the at least one selection of text in the seed document;
identifying other documents from the plurality of documents based on a similarity between text in the other documents and the at least one selection of text in the seed document; and
generating a graphical user interface that includes a similarity panel that provides similarity data between text in the other documents and the at least one selection of text in the seed document;
wherein the similarity panel provides:
a number of the other documents having text that is similar to the at least one selection of text in the seed document based on a predetermined similarity threshold; and
an option to search for a subset of the other documents based on a similarity percentage between the at least one selection of text in the seed document and text in the other documents.
2. The method of claim 1 , wherein the seed document is determined based on the artificial intelligence by using pattern recognition.
3. The method of claim 1 , further comprising categorizing the other documents using pattern recognition to identify interesting trends or unusual behavior in the other documents.
4. The method of claim 1 , wherein the graphical user interface includes a list of one or more legal issues to associate with any one or more documents of the plurality of documents.
5. The method of claim 1 , further comprising:
associating one or more legal issues with the seed document;
associating one or more other documents with the one or more legal issues associated with the seed document;
receiving a filter request that includes the one or more legal issues; and
filtering one or more other documents from the plurality of documents based on the filter request.
6. The method of claim 1 , wherein the graphical user interface includes, for each document of the plurality of documents, an option to view each document of the plurality of documents in a native format, a graphical format, a text format, a production format, a translated format, or an original format.
7. The method of claim 1 , further comprising:
enabling a user to redact one or more portions of the seed document; and
automatically redacting one or more corresponding portions of one or more other documents.
8. A non-transitory computer-readable storage medium carrying program instructions thereon, the instructions when executed by one or more processors cause the one or more processors to perform operations comprising:
receiving a plurality of documents;
determining, based on artificial intelligence and a type of legal issue, a seed document from the plurality of documents;
suggesting, based on the artificial intelligence and the type of legal issue, at least one selection of text in the seed document;
receiving a search request to search the at least one selection of text in the seed document;
identifying other documents from the plurality of documents based on a similarity between text in the other documents and the at least one selection of text in the seed document; and
generating a graphical user interface that includes a similarity panel that provides similarity data between text in the other documents and the at least one selection of text in the seed document;
wherein the similarity panel provides:
a number of the other documents having text that is similar to the at least one selection of text in the seed document based on a predetermined similarity threshold; and
an option to search for a subset of the other documents based on a similarity percentage between the at least one selection of text in the seed document and text in the other documents.
9. The computer-readable storage medium of claim 8 , wherein the seed document is determined based on the artificial intelligence by using pattern recognition.
10. The computer-readable storage medium of claim 8 , wherein the instructions when executed further cause the one or more processors to perform operations comprising categorizing the other documents using pattern recognition to identify interesting trends or unusual behavior in the other documents.
11. The computer-readable storage medium of claim 8 , wherein the graphical user interface includes a list of one or more legal issues to associate with any one or more documents of the plurality of documents.
12. The computer-readable storage medium of claim 8 , wherein the instructions when executed further cause the one or more processors to perform operations comprising:
associating one or more legal issues with the seed document;
receiving a filter request that includes the one or more legal issues; and
filtering one or more other documents from the plurality of documents based on the filter request.
13. The computer-readable storage medium of claim 8 , wherein the graphical user interface includes, for each document of the plurality of documents, an option to view each document of the plurality of documents in a native format, a graphical format, a text format, a production format, a translated format, or an original format.
14. The computer-readable storage medium of claim 8 , wherein the instructions when executed further cause the one or more processors to perform operations comprising:
enabling a user to redact one or more portions of the seed document; and
automatically redacting one or more corresponding portions of one or more other documents.
15. A system comprising:
one or more processors; and
logic encoded in one or more non-transitory computer-readable media for execution by the one or more processors and when executed operable to perform operations comprising:
receiving a plurality of documents;
determining, based on artificial intelligence and a type of legal issue, a seed document from the plurality of documents;
suggesting, based on the artificial intelligence and the type of legal issue, at least one selection of text in the seed document;
receiving a search request to search the at least one selection of text in the seed document;
identifying other documents from the plurality of documents based on a similarity between text in the other documents and the at least one selection of text in the seed document; and
generating a graphical user interface that includes a similarity panel that provides similarity data between text in the other documents and the at least one selection of text in the seed document;
wherein the similarity panel provides:
a number of the other documents having text that is similar to the at least one selection of text in the seed document based on a predetermined similarity threshold; and
an option to search for a subset of the other documents based on a similarity percentage between the at least one selection of text in the seed document and text in the other documents.
16. The system of claim 15 , wherein the seed document is determined based on the artificial intelligence by using pattern recognition.
17. The system of claim 15 , wherein the logic when executed is further operable to perform operations comprising categorizing the other documents using pattern recognition to identify interesting trends or unusual behavior in the other documents.
18. The system of claim 15 , wherein the graphical user interface includes a list of one or more legal issues to associate with any one or more documents of the plurality of documents.
19. The system of claim 15 , wherein the logic when executed is further operable to perform operations comprising:
associating one or more legal issues with the seed document;
receiving a filter request that includes the one or more legal issues; and
filtering one or more other documents from the plurality of documents based on the filter request.
20. The system of claim 15 , wherein the graphical user interface includes, for each document of the plurality of documents, an option to view each document of the plurality of documents in a native format, a graphical format, a text format, a production format, a translated format, or an original format.