Computer readable electronic records automated classification system
Classifying an electronic document in a computer-based system is disclosed. For each classification instance in a plurality of classification instances, a confidence data indicating a degree of confidence that the electronic document is associated with that classification instance is determined. A classification, based on a first classification instance in the plurality of classification instances, is assigned without human intervention to the electronic document if the confidence data associated with the first classification instance exceeds a first threshold.
1. A method for classifying an electronic document in a computer-based system, comprising:
generating a set of confidence data comprising for each of at least a subset of classification instances in a plurality of classification instances a corresponding determined confidence data, wherein a confidence data indicates a degree of confidence that the electronic document is associated with a corresponding classification instance;
based at least in part on a determination that at least one of the confidence data in the set exceeds a first predetermined threshold, assigning a classification to the electronic document without user input and based at least in part on a classification instance in the plurality of classification instances that is associated with the highest confidence data
based at least in part on a determination that none of the confidence data in the set exceeds the first predetermined threshold and that at least one of the confidence data in the set exceeds a second predetermined threshold that is lower than the first predetermined threshold, receiving user input and determining, based at least in part on the user input, which, if any, classification should be assigned to the electronic document; and
based at least in part on a determination that none of the confidence data in the set exceeds both the first and second predetermined thresholds, determining, without user input, that the electronic document cannot be assigned a classification.
2. The method recited in claim 1 , wherein the user input is obtained including by presenting to a user a graphical representation of at least two classification instances in the plurality of classification instances and obtaining an indication of a user selection of at least one of the at least two classification instances.
3. The method recited in claim 1 , wherein the user input is obtained including by presenting to a user a graphical representation of at least two classification instances in the plurality of classification instances if each of at least a prescribed number of classification instance(s) in the plurality of classification instances has the confidence data that exceeds a third predetermined threshold that is lower than the first threshold but higher than the second predetermined threshold.
4. The method recited in claim 1 , further comprising assigning a review classification to the electronic document to indicate that the electronic document is required to be reviewed by a user if no classification instance in the plurality of classification instances is associated with the confidence data that exceeds the first predetermined threshold and fewer than a prescribed number of classification instance(s) in the plurality of classification instances has the confidence data that exceeds the second predetermined threshold.
5. The method recited in claim 1 , wherein determining the confidence data includes using information obtained by analyzing at least one training document associated with a pre-assigned classification.
6. A system for classifying an electronic document, comprising:
a processor; and
a memory coupled with the processor, wherein the memory is configured to provide the processor with instructions which when executed cause the processor to:
generate a set of confidence data comprising for each of at least a subset of classification instances in a plurality of classification instances a corresponding determined confidence data, wherein a confidence data indicates a degree of confidence that the electronic document is associated with a corresponding classification instance;
based at least in part on a determination that at least one of the confidence data in the set exceeds a first predetermined threshold, assign a classification to the electronic document without user input and based at least in part on a classification instance in the plurality of classification instances that is associated with the highest confidence data
based at least in part on a determination that none of the confidence data in the set exceeds the first predetermined threshold and that at least one of the confidence data in the set exceeds a second predetermined threshold that is lower than the first predetermined threshold, receive user input and determine, based at least in part on the user input, which, if any, classification should be assigned to the electronic document; and
based at least in part on a determination that none of the confidence data in the set exceeds both the first and second predetermined thresholds, determine, without user input, that the electronic document cannot be assigned a classification.
7. The system recited in claim 6 , wherein the user input is obtained including by presenting to a user a graphical representation of at least two classification instances in the plurality of classification instances and obtaining an indication of a user selection of at least one of the at least two classification instances.
8. The system recited in claim 6 , wherein the user input is obtained including by presenting to a user a graphical representation of at least two classification instances in the plurality of classification instances if each of at least a prescribed number of classification instance(s) in the plurality of classification instances has the confidence data that exceeds a third predetermined threshold that is lower than the first threshold but higher than the second predetermined threshold.
9. The system recited in claim 6 , further comprising assigning a review classification to the electronic document to indicate that the electronic document is required to be reviewed by a user if no classification instance in the plurality of classification instances is associated with the confidence data that exceeds the first predetermined threshold and fewer than a prescribed number of classification instance(s) in the plurality of classification instances has the confidence data that exceeds the second predetermined threshold.
10. The system recited in claim 6 , wherein determining the confidence data includes using information obtained by analyzing at least one training document associated with a pre-assigned classification.
11. A computer program product for classifying an electronic document, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
generating a set of confidence data comprising for each of at least a subset of classification instances in a plurality of classification instances a corresponding determined confidence data, wherein a confidence data indicates a degree of confidence that the electronic document is associated with a corresponding classification instance;
based at least in part on a determination that at least one of the confidence data in the set exceeds a first predetermined threshold, assigning a classification to the electronic document without user input and based at least in part on a classification instance in the plurality of classification instances that is associated with the highest confidence data
based at least in part on a determination that none of the confidence data in the set exceeds the first predetermined threshold and that at least one of the confidence data in the set exceeds a second predetermined threshold that is lower than the first predetermined threshold, receiving user input and determining, based at least in part on the user input, which, if any, classification should be assigned to the electronic document; and
based at least in part on a determination that none of the confidence data in the set exceeds both the first and second predetermined thresholds, determining, without user input, that the electronic document cannot be assigned a classification.
12. The computer program product recited in claim 11 , wherein the user input is obtained including by presenting to a user a graphical representation of at least two classification instances in the plurality of classification instances and obtaining an indication of a user selection of at least one of the at least two classification instances.
13. The computer program product recited in claim 11 , wherein the user input is obtained including by presenting to a user a graphical representation of at least two classification instances in the plurality of classification instances if each of at least a prescribed number of classification instance(s) in the plurality of classification instances has the confidence data that exceeds a third predetermined threshold that is lower than the first threshold but higher than the second predetermined threshold.
14. The computer program product recited in claim 11 , wherein determining the confidence data includes using information obtained by analyzing at least one training document associated with a pre-assigned classification.