System and method for providing technology assisted data review with optimizing features
Embodiments may provide a document system that receives a responsiveness call from a user through the task/queue framework regarding a machine call document. Theses responsiveness calls may be used to refining the scoring algorithm used by the document system of to generate a desired confidence score for the document system.
1. A method, comprising:
controlling automated assisted review of a plurality of documents within a data store of a document system by:
initiating generation of a document map for the plurality of documents using a topic-related generative model for the plurality of documents;
initiating transmission of a control set of documents from the plurality of documents to a user, the control set of documents determined based on selected documents, based on selecting the selected documents from a first strata of the plurality of documents and a second strata of the plurality of documents; and
based on a control set metric regarding the control set of documents provided by the user, the control set metric including an indicator of responsiveness for each of the documents of the control set of documents, initiating:
determining a responsiveness score for each of the plurality of documents based on a scoring algorithm;
determining a set of responsive documents and a set of non-responsive documents of the plurality of documents based on the responsiveness score determined for each of the plurality of documents and a decision boundary score;
determining a confidence score for the document system using the responsiveness score for each of the documents of the control set and the indicator of responsiveness for each of the control set documents provided by the user;
selecting one or more of the plurality of documents based on the responsiveness scores of the plurality of documents, wherein the responsiveness score of each of the one or more selected documents is at or near the decision boundary score;
providing a presentation of the one or more selected documents to the user;
based on an indicator of responsiveness by the user for each of the selected documents, refining the scoring algorithm based on the indicator of responsiveness for each of the selected document; and
generating a desired confidence score for the document system, and providing a presentation of the set of responsive documents to the user when the desired confidence score for the document system is achieved, wherein the confidence score for the document system is an F1 score determined based on a comparison of the responsiveness score for the documents of the control set with the indicator of responsiveness for the documents of the control set received from the user.
2. The method of claim 1 , wherein initiating generation of the document map includes initiating determination of a document-topic relation based on a soft clustering of the plurality of documents, the clustering based on a plurality of topics, the generation of the document map including utilizing a distributed filing system parallel processing unit in conjunction with the topic-related generative model.
3. The method of claim 1 , wherein the decision boundary score is determined as a median score of the responsiveness scores for each of the plurality of documents.
4. The method of claim 1 , wherein relative positioning of document map documents in the document map provides an indicator of similarities of respective pairs of the document map documents, based on a determined similarity of content in the document map documents.
5. The method of claim 1 , further comprising initiating an update of the document map based on a comparison of a first responsiveness score of a selected document map document, selected based on a predictive responsiveness of the selected document map document, compared with the control set metric.
6. The method of claim 5 , wherein initiating the update of the document map includes initiating a reordering of indicators of document map documents included in the document map based on a determined mathematical distance of each of the document map documents from the decision boundary.
7. The method of claim 1 , further comprising initiating a categorization of the plurality of documents based on the document map.
8. A system, comprising:
a processor; and
a non-transitory computer readable medium, storing instructions for:
controlling automated assisted review of a plurality of documents within a data store of a document system by:
initiating generation of a document map for the plurality of documents using a topic-related generative model for the plurality of documents;
initiating transmission of a control set of documents from the plurality of documents to a user, the control set of documents determined based on selected documents, based on selecting the selected documents from a first strata of the plurality of documents and a second strata of the plurality of documents; and
based on a control set metric regarding the control set of documents provided by the user, the control set metric including an indicator of responsiveness for each of the documents of the control set of documents, initiating:
determining a responsiveness score for each of the plurality of documents based on a scoring algorithm;
determining a set of responsive documents and a set of non-responsive documents of the plurality of documents based on the responsiveness score determined for each of the plurality of documents and a decision boundary score;
determining a confidence score for the document system using the responsiveness score for each of the documents of the control set and the indicator of responsiveness for each of the control set documents provided by the user;
selecting one or more of the plurality of documents based on the responsiveness scores of the plurality of documents, wherein the responsiveness score of each of the one or more selected documents is at or near the decision boundary score;
providing a presentation of the one or more selected documents to the user;
based on an indicator of responsiveness by the user for each of the selected documents, refining the scoring algorithm based on the indicator of responsiveness for each of the selected document; and
generating a desired confidence score for the document system, and providing a presentation of the set of responsive documents to the user when the desired confidence score for the document system is achieved, wherein the confidence score for the document system is an F1 score determined based on a comparison of the responsiveness score for the documents of the control set with the indicator of responsiveness for the documents of the control set received from the user.
9. The system of claim 8 , wherein initiating generation of the document map includes initiating determination of a document-topic relation based on a soft clustering of the plurality of documents, the clustering based on a plurality of topics, the generation of the document map including utilizing a distributed filing system parallel processing unit in conjunction with the topic-related generative model.
10. The system of claim 8 , wherein the decision boundary score is determined as a median score of the responsiveness scores for each of the plurality of documents.
11. The system of claim 8 , wherein relative positioning of document map documents in the document map provides an indicator of similarities of respective pairs of the document map documents, based on a determined similarity of content in the document map documents.
12. The system of claim 8 , wherein the instructions are further for initiating an update of the document map based on a comparison of a first responsiveness score of a selected document map document, selected based on a predictive responsiveness of the selected document map document, compared with the control set metric.
13. The system of claim 12 , wherein initiating the update of the document map includes initiating a reordering of indicators of document map documents included in the document map based on a determined mathematical distance of each of the document map documents from the decision boundary.
14. The system of claim 8 , wherein the instructions are further for initiating a categorization of the plurality of documents based on the document map.
15. A non-transitory computer readable medium, storing instructions for:
controlling automated assisted review of a plurality of documents within a data store of a document system by:
initiating generation of a document map for the plurality of documents using a topic-related generative model for the plurality of documents;
initiating transmission of a control set of documents from the plurality of documents to a user, the control set of documents determined based on selected documents, based on selecting the selected documents from a first strata of the plurality of documents and a second strata of the plurality of documents; and
based on a control set metric regarding the control set of documents provided by the user, the control set metric including an indicator of responsiveness for each of the documents of the control set of documents, initiating:
determining a responsiveness score for each of the plurality of documents based on a scoring algorithm;
determining a set of responsive documents and a set of non-responsive documents of the plurality of documents based on the responsiveness score determined for each of the plurality of documents and a decision boundary score;
determining a confidence score for the document system using the responsiveness score for each of the documents of the control set and the indicator of responsiveness for each of the control set documents provided by the user;
selecting one or more of the plurality of documents based on the responsiveness scores of the plurality of documents, wherein the responsiveness score of each of the one or more selected documents is at or near the decision boundary score;
providing a presentation of the one or more selected documents to the user;
based on an indicator of responsiveness by the user for each of the selected documents, refining the scoring algorithm based on the indicator of responsiveness for each of the selected document; and
generating a desired confidence score for the document system, and providing a presentation of the set of responsive documents to the user when the desired confidence score for the document system is achieved, wherein the confidence score for the document system is an F1 score determined based on a comparison of the responsiveness score for the documents of the control set with the indicator of responsiveness for the documents of the control set received from the user.
16. The non-transitory computer readable medium of claim 15 , wherein initiating generation of the document map includes initiating determination of a document-topic relation based on a soft clustering of the plurality of documents, the clustering based on a plurality of topics, the generation of the document map including utilizing a distributed filing system parallel processing unit in conjunction with the topic-related generative model.
17. The non-transitory computer readable medium of claim 15 , wherein the decision boundary score is determined as a median score of the responsiveness scores for each of the plurality of documents.
18. The non-transitory computer readable medium of claim 15 , wherein relative positioning of document map documents in the document map provides an indicator of similarities of respective pairs of the document map documents, based on a determined similarity of content in the document map documents.
19. The non-transitory computer readable medium of claim 15 , wherein the instructions are further for initiating an update of the document map based on a comparison of a first responsiveness score of a selected document map document, selected based on a predictive responsiveness of the selected document map document, compared with the control set metric.
20. The non-transitory computer readable medium of claim 19 , wherein initiating the update of the document map includes initiating a reordering of indicators of document map documents included in the document map based on a determined mathematical distance of each of the document map documents from the decision boundary.
21. The non-transitory computer readable medium of claim 15 , wherein the instructions are further for initiating a categorization of the plurality of documents based on the document map.