Smart document migration and entity detection
Systems and methods include extraction of a plurality of clauses from each of a plurality of electronic documents, determination, for each of the plurality of clauses and using a machine-learned algorithm, an associated clause type, identification of one or more data privacy protection entities present within each of one or more of the plurality of clauses, determination, for each of the one or more of the plurality of clauses, of a weighted frequency for each of the one or more data privacy protection entities present within the clause based on a type of the data privacy protection entity, determination of a weighted frequency associated with each of the plurality of electronic documents based on the determined weighted frequency for each of the one or more data privacy protection entities present within clauses of the plurality of electronic documents, and storage of an identifier of each of the plurality of electronic documents in association with a respective determined weighted frequency.
1. A system comprising:
a memory storing processor-executable process steps;
a processing unit to execute the processor-executable process steps to cause the system to:
extract a plurality of clauses from each of a plurality of electronic documents;
determine an associated clause type for each of the plurality of clauses extracted from one of the documents, wherein the determination is made using a machine-learned algorithm;
identify one or more data privacy protection entities present within each of one or more of the plurality of clauses;
for each of the one or more of the plurality of clauses, determine a weighted frequency for each of the one or more data privacy protection entities present within the clause based on a type of the data privacy protection entity;
determine a weighted frequency associated with each of the plurality of electronic documents based on the determined weighted frequency for each of the one or more data privacy protection entities present within clauses of the plurality of electronic documents; and
store an identifier of each of the plurality of electronic documents in association with a respective determined weighted frequency.
2. A system according to claim 1 , the processing unit to execute the processor-executable process steps to cause the system to:
receive a request for a visualization of electronic documents associated with an entity; and
in response to the request:
determine one or more of the plurality of electronic documents associated with the request;
determine a stored weighted frequency associated with each of the determined one or more of the plurality of electronic documents; and
generate a visualization of the determined one or more of the plurality of electronic documents, the visualization representing the stored weighted frequency associated with each of the determined one or more of the plurality of electronic documents.
3. A system according to claim 2 , wherein determination of a weighted frequency for each of the one or more data privacy protection entities comprises determination of a data privacy protection entity type, a document type of a document in which a data privacy protection entity is present, and a weight associated with the data privacy protection entity type and document type.
4. A system according to claim 3 , wherein a weight associated with a first data privacy protection entity type and a first document type is different from a weight associated with a second data privacy protection entity type and the first document type.
5. A system according to claim 1 , wherein determination of an associated clause type for a clause comprises:
inputting the clause to a machine-learned algorithm to generate a predicted clause type;
presenting the predicted clause type to a reviewer;
receiving a revised clause type from the reviewer;
storing the clause and the revised clause type; and
retraining the machine-learned algorithm based at least in part on the stored clause and the revised clause type.
6. A computer-implemented method comprising:
extracting a plurality of clauses from each of a plurality of electronic documents;
determining an associated clause type for each of the plurality of clauses extracted from one of the documents, wherein the determination is made using a trained artificial neural network;
identifying one or more data privacy protection entities present within each of one or more of the plurality of clauses;
for each of the one or more of the plurality of clauses, determining a weighted frequency for each of the one or more data privacy protection entities present within the clause based on a type of the data privacy protection entity;
determining a weighted frequency associated with each of the plurality of electronic documents based on the determined weighted frequency for each of the one or more data privacy protection entities present within clauses of the plurality of electronic documents; and
storing an identifier of each of the plurality of electronic documents in association with a respective determined weighted frequency.
7. A method according to claim 6 , further comprising:
receiving a request for a visualization of electronic documents associated with an entity; and
in response to the request:
determining one or more of the plurality of electronic documents associated with the request;
determining a stored weighted frequency associated with each of the determined one or more of the plurality of electronic documents; and
generating a visualization of the determined one or more of the plurality of electronic documents, the visualization representing the stored weighted frequency associated with each of the determined one or more of the plurality of electronic documents.
8. A method according to claim 7 , wherein determining a weighted frequency for each of the one or more data privacy protection entities comprises determining a data privacy protection entity type, a document type of a document in which a data privacy protection entity is present, and a weight associated with the data privacy protection entity type and document type.
9. A method according to claim 8 , wherein a weight associated with a first data privacy protection entity type and a first document type is different from a weight associated with a second data privacy protection entity type and the first document type.
10. A method according to claim 6 , wherein determining an associated clause type for a clause comprises:
inputting the clause to a machine-learned algorithm to generate a predicted clause type;
presenting the predicted clause type to a reviewer;
receiving a revised clause type from the reviewer;
storing the clause and the revised clause type; and
retraining the machine-learned algorithm based at least in part on the stored clause and the revised clause type.
11. A non-transitory computer-readable medium storing processor-executable process steps executable by a processing unit of a computing system to cause the computing system to:
extract a plurality of clauses from each of a plurality of electronic documents;
determine an associated clause type for each of the plurality of clauses extracted from one of the documents, wherein the determination is made using a machine-learned algorithm;
identify one or more data privacy protection entities present within each of one or more of the plurality of clauses;
for each of the one or more of the plurality of clauses, determine a weighted frequency for each of the one or more data privacy protection entities present within the clause based on a type of the data privacy protection entity;
determine a weighted frequency associated with each of the plurality of electronic documents based on the determined weighted frequency for each of the one or more data privacy protection entities present within clauses of the plurality of electronic documents; and
store an identifier of each of the plurality of electronic documents in association with a respective determined weighted frequency.
12. A medium according to claim 11 , the processing unit to execute the processor-executable process steps to cause the system to:
receive a request for a visualization of electronic documents associated with an entity; and
in response to the request:
determine one or more of the plurality of electronic documents associated with the request;
determine a stored weighted frequency associated with each of the determined one or more of the plurality of electronic documents; and
generate a visualization of the determined one or more of the plurality of electronic documents, the visualization representing the stored weighted frequency associated with each of the determined one or more of the plurality of electronic documents.
13. A medium according to claim 12 , wherein determination of a weighted frequency for each of the one or more data privacy protection entities comprises determination of a data privacy protection entity type, a document type of a document in which a data privacy protection entity is present, and a weight associated with the data privacy protection entity type and document type.
14. A medium according to claim 13 , wherein a weight associated with a first data privacy protection entity type and a first document type is different from a weight associated with a second data privacy protection entity type and the first document type.
15. A medium according to claim 11 , wherein determination of an associated clause type for a clause comprises:
inputting the clause to a machine-learned algorithm to generate a predicted clause type;
presenting the predicted clause type to a reviewer;
receiving a revised clause type from the reviewer;
storing the clause and the revised clause type; and
retraining the machine-learned algorithm based at least in part on the stored clause and the revised clause type.