Automatic Case Assignment Based on Learned Expertise of Prior Caseload
AssigneeInternational Business Machines Corporation
InventorsRichard B. Finch, Jason T. Hirst, Gerald G. Stanquist
Life of this patent
Estimating the term…
Abstract
A mechanism is provided in a data processing system for automatic case assignment. The mechanism extracts features from a machine readable form of a case to be assigned. An expertise classifier generates an initial case assignment matrix matching the case to a plurality of caseworkers based on the extracted features, a caseworker relationship graph, and an entity relationship graph. A personnel filter filters the initial case assignment matrix based on expertise, availability, and caseload of the plurality of caseworkers to form a final caseworker assignment. The mechanism assigns the case to an identified caseworker based on the final caseworker assignment.
Claims20
A method, in a data processing system, for automatic case assignment, the method comprising:
- extracting, by the data processing system, features from a machine readable form of a case to be assigned;
- generating, by an expertise classifier in the data processing system, an initial case assignment matrix matching the case to a plurality of caseworkers based on the extracted features, a caseworker relationship graph, and an entity relationship graph;
- filtering, by a personnel filter in the data processing system, the initial case assignment matrix based on expertise, availability, and caseload of the plurality of caseworkers to form a final caseworker assignment;
- and
- assigning, by the data processing system, the case to an identified caseworker based on the final caseworker assignment.
A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to:
- extract features from a machine readable form of a case to be assigned;
- generate, by an expertise classifier, an initial case assignment matrix matching the case to a plurality of caseworkers based on the extracted features, a caseworker relationship graph, and an entity relationship graph;
- filter, by a personnel filter, the initial case assignment matrix based on expertise, availability, and caseload of the plurality of caseworkers to form a final caseworker assignment;
- and
- assign the case to an identified caseworker based on the final caseworker assignment.
An apparatus comprising:
- a processor;
- and
- a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to:
- extract features from a machine readable form of a case to be assigned;
- generate, by an expertise classifier, an initial case assignment matrix matching the case to a plurality of caseworkers based on the extracted features, a caseworker relationship graph, and an entity relationship graph;
- filter, by a personnel filter, the initial case assignment matrix based on expertise, availability, and caseload of the plurality of caseworkers to form a final caseworker assignment;
- and
- assign the case to an identified caseworker based on the final caseworker assignment.
Dependencies are inferred from the claim text.