Autonomous detection of compound issue requests in an issue tracking system
View Patent ↗An issue tracking system configured to determine whether an issue request submitted by a user of the issue tracking system can, or should, be subdivided into two or more issue requests. In some implementations, the issue tracking system is configured to extract a content item of the issue request (e.g., title, description, and the like) in order to perform a semantic and/or syntactic analysis of that content item. Upon determining that the content item includes two or more clauses linked by a coordinating, subordinating, or correlative conjunction, the system can provide a recommendation to the user to submit discrete two or more issue requests, each one of which corresponds to a single linked clause of the content item.
1. An issue tracking system comprising:
a host service operably coupled to a client application of a client device, the host service comprising a cooperating processor and memory configured to:
receive an issue request from the client application;
provide at least a portion of the issue request as input to a trained machine learning model;
receive as output from the trained machine learning model a divisibility score corresponding to the issue request;
in response to a determination that the divisibility score satisfies a divisibility threshold:
subdivide the issue request into two or more issue requests each at least partially populated with data extracted from the issue request; and
transmit the two or more issue requests to the client application.
2. The issue tracking system of claim 1 , wherein the at least a portion of the issue request provided as input to the trained machine learning model comprises semantic content of a content item of the issue request.
3. The issue tracking system of claim 2 , wherein:
the content item comprises an issue request description;
the semantic content comprises a set of lemmatized words extracted from the issue request description.
4. The issue tracking system of claim 3 , wherein:
the divisibility score is increased in response to a first determination that the set of lemmatized words includes at least a threshold number of lemmatized words associated with compound issue requests; and
the divisibility score is decreased in response to a second determination that the set of lemmatized words does not include the threshold number of lemmatized words associated with compound issue requests.
5. The issue tracking system of claim 1 , wherein the processor is further configured to:
identify one or more previously-received issue requests that satisfy a similarity threshold when compared to the issue request; and
populate one or more issue request templates with data extracted from the one or more previously-received issue requests.
6. The issue tracking system of claim 5 , wherein the processor is further configured to determine a likelihood that the one or more previously-received issue requests include data that is substantially similar to the issue request.
7. The issue tracking system of claim 6 , wherein:
a threshold is a first threshold; and
the processor is further configured to determine whether the likelihood satisfies a second threshold in order to identify the one or more previously-received issue requests that are substantially similar to the issue request.
8. The issue tracking system of claim 1 , wherein:
the client device is communicably coupled to the host service by a network and is configured to receive input from a user to generate the issue request;
the client device is a first client device of a group of client devices each configured to transmit at least one issue request to the processor of the host service;
each client device of the group of client devices is coupled to the host service by the network.
9. A method of subdividing an issue request received by an issue tracking system, the method comprising:
receiving the issue request from a client device;
extracting as a content item, from the issue request, at least one of:
a time to completion estimate;
an issue category;
an issue assignee;
an issue reporter; or
an issue priority;
providing the content item as input to a trained machine learning model;
receiving as output from the trained machine learning model a divisibility score corresponding to a prediction whether the issue request can be completed in less than a threshold time window;
comparing the divisibility score to a divisibility threshold; and
upon determining that the divisibility score satisfies the divisibility threshold, generating a suggestion to the client device to subdivide the issue request.
10. The method of claim 9 , wherein the content item comprises the issue assignee.
11. The method of claim 9 , wherein the content item comprise the issue priority.
12. The method of claim 9 , wherein the threshold time window is eight hours or less.
13. The method of claim 9 , wherein the content item comprises semantic content of an issue description of the issue request.
14. The method of claim 13 , wherein the semantic content comprises a word count of the issue description.