Real-time cognitive root cause analysis (CRCA) computing
An ordered set of root cause analysis (RCA) document entry criteria is identified. RCA input segments are specified using unstructured natural language input, including at least: incident descriptive elements, a single problem statement, a set of why questions and answers, and a single cause categorization. A guided input sequence of the RCA input segments is performed interactively with a user. Quality indicators of content of user input entered during a respective RCA input segment are determined using a scoring algorithm, and the user is assisted with improving precision and consistency of the user input. Responsive to a threshold of consistent user input across the RCA input segments resulting in identification of a single cause categorization of an information technology (IT) problem, an RCA document is generated that identifies the single cause categorization of the new IT problem.
1. A computer-implemented method of generating root cause analysis (RCA) documents for information technology (IT) problems comprising:
identifying an ordered set of RCA document entry criteria, in accordance with an established computer-controlled RCA intake methodology, comprising RCA input segments specified using unstructured natural language input, the RCA input segments comprising at least: incident descriptive elements, a single problem statement, a set of why questions and answers, and a single cause categorization; and
performing, interactively with a user using cognitive natural language processing (CNLP) across a guided input sequence of the RCA input segments that result in identification of a single cause categorization of a new IT problem, each of:
determining, using a scoring algorithm that identifies keywords and causal connections of a particular type, at least two quality indicators of content of unstructured user input entered during the respective RCA input segment by (i) applying natural language processing based (NLP-based) semantic analysis to the content of the unstructured user input and (ii) applying forward logical keyword connection analysis that enforces semantic consistency of the content of the unstructured user input across completed portions of the guided input sequence of the RCA input segments; and
assisting, for any identified quality problems with the content of the unstructured user input entered during the respective RCA input segment based on the quality indicators, the user with improving precision and consistency of the content of the unstructured user input across the guided input sequence of the RCA input segments; and
the computer-implemented method further comprising: generating, responsive to determining that a threshold of consistent unstructured user inputs across the completed portions of the guided input sequence of the RCA input segments facilitates identification of the single cause categorization, an RCA document that comprises the content of the unstructured user input entered across the guided input sequence of the RCA input segments and that identifies the single cause categorization of the new IT problem,
where one of the quality indicators determined using the scoring algorithm is based on quantitative rules representing quantitative aspects of wording used during the respective RCA input segment and another of the quality indicators is based on qualitative rules representing qualitative aspects related to information technology, and where the guided input sequence of RCA input segments increases depth of investigation of the new IT problem using the forward logical connections, and further comprising ensuring that a last answer provided by the user holds a characteristic of a root cause usable to identify the single cause categorization of the new IT problem.
2. The computer-implemented method of claim 1 , where the identified quality problems are assigned a criticality level distinguishing at least between critical problems and warnings.
3. The computer-implemented method of claim 1 , where applying the forward logical keyword connection analysis that enforces the semantic consistency of the content of the unstructured user input across the completed portions of the guided input sequence of the RCA input segments comprises:
comparing the content of the unstructured user input accumulated across the completed portions of the guided input sequence of the respective RCA input segments with known-accurate RCA documents; and
identifying any deviations of semantic consistency of the content of the unstructured user input relative to known IT-related causal connections represented within the known-accurate RCA documents.
4. The computer-implemented method of claim 1 , further comprising adding to an RCA document database the RCA document that comprises the content of the unstructured user input entered across the guided input sequence of the RCA input segments and that identifies the single cause categorization of the new IT problem.
5. The computer-implemented method of claim 1 , where the identifying, the performing, and the generating are provided as a service within a cloud computing environment.
6. A system, comprising:
a memory; and
one or more processor(s) sets for generating root cause analysis (RCA) documents for information technology (IT) problems, the one or more processor(s) sets being programmed to:
identify, within the memory, an ordered set of RCA document entry criteria, in accordance with an established computer-controlled RCA intake methodology, comprising RCA input segments specified using unstructured natural language input, the RCA input segments comprising at least: incident descriptive elements, a single problem statement, a set of why questions and answers, and a single cause categorization; and
perform, interactively with a user using cognitive natural language processing (CNLP) across a guided input sequence of the RCA input segments that result in identification of a single cause categorization of a new IT problem, each of: determining, using a scoring algorithm that identifies keywords and causal connections of a particular type, at least two quality indicators of content of unstructured user input entered during the respective RCA input segment by (i) applying natural language processing based (NLP-based) semantic analysis to the content of the unstructured user input and (ii) applying forward logical keyword connection analysis that enforces semantic consistency of the content of the unstructured user input across completed portions of the guided input sequence of the RCA input segments; and
assisting, for any identified quality problems with the content of the unstructured user input entered during the respective RCA input segment based on the quality indicators, the user with improving precision and consistency of the content of the unstructured user input across the guided input sequence of the RCA input segments; and
the one or more processor(s) sets being further programmed to:
generate, responsive to determining that a threshold of consistent unstructured user inputs across the completed portions of the guided input sequence of the RCA input segments facilitates identification of the single cause categorization, an RCA document that comprises the content of the unstructured user input entered across the guided input sequence of the RCA input segments and that identifies the single cause categorization of the new IT problem,
where one of the quality indicators determined using the scoring algorithm is based on quantitative rules representing quantitative aspects of wording used during the respective RCA input segment and another of the quality indicators is based on qualitative rules representing qualitative aspects related to information technology, and where the guided input sequence of RCA input segments progressively increases depth of investigation of the new IT problem using the forward logical connections, and the one or more processor(s) sets are further programmed to ensure that a last answer provided by the user holds a characteristic of a root cause usable to identify the single cause categorization of the new IT problem.
7. The system of claim 6 , where the identified quality problems are assigned a criticality level distinguishing at least between critical problems and warnings.
8. The system of claim 6 , where, in being programmed to apply the forward logical keyword connection analysis that enforces the semantic consistency of the content of the unstructured user input across the completed portions of the guided input sequence of the RCA input segments, the one or more processor(s) sets are programmed to:
compare the content of the unstructured user input accumulated across the completed portions of the guided input sequence of the respective RCA input segments with known-accurate RCA documents; and
identify any deviations of semantic consistency of the content of the unstructured user input relative to known IT-related causal connections represented within the known-accurate RCA documents.
9. The system of claim 6 , where the one or more processor(s) sets being programmed to identify, perform, and generate is provided as a service within a cloud computing environment.
10. A computer program product, comprising:
a computer readable storage medium having computer readable program code for generating root cause analysis (RCA) documents for information technology (IT) problems embodied therewith, where the computer readable storage medium is not a transitory signal per se and where the computer readable program code when executed on a computer causes the computer to:
identify an ordered set of RCA document entry criteria, in accordance with an established computer-controlled RCA intake methodology, comprising RCA input segments specified using unstructured natural language input, the RCA input segments comprising at
least: incident descriptive elements, a single problem statement, a set of why questions and answers, and a single cause categorization; and
perform, interactively with a user using cognitive natural language processing (CNLP) across a guided input sequence of the RCA input segments that result in identification of a single cause categorization of a new IT problem, each of:
determining, using a scoring algorithm that identifies keywords and causal connections of a particular type, at least two quality indicators of content of unstructured user input entered during the respective RCA input segment by (i) applying natural language processing based (NLP-based) semantic analysis to the content of the unstructured user input and (ii) applying forward logical keyword connection analysis that enforces semantic consistency of the content of the unstructured user input across completed portions of the guided input sequence of the RCA input segments; and
assisting, for any identified quality problems with the content of the unstructured user input entered during the respective RCA input segment based on the quality indicators, the user with improving precision and consistency of the content of the unstructured user input across the guided input sequence of the RCA input segments; and
the computer readable program code when executed on the computer further causing the computer to:
generate, responsive to determining that a threshold of consistent unstructured user inputs across the completed portions of the guided input sequence of the RCA input segments facilitates identification of the single cause categorization, an RCA document that comprises the content of the unstructured user input entered across the guided input sequence of the RCA input segments and that identifies the single cause categorization of the new IT problem,
where one of the quality indicators determined using the scoring algorithm is based on quantitative rules representing quantitative aspects of wording used during the respective RCA input segment and another of the quality indicators is based on qualitative rules representing qualitative aspects related to information technology, and where the guided input sequence of RCA input segments progressively increases depth of investigation of the new IT problem using the forward logical connections, and where the computer readable program code when executed on the computer further causes the computer to ensure that a last answer provided by the user holds a characteristic of a root cause usable to identify the single cause categorization of the new IT problem.
11. The computer program product of claim 10 , where the identified quality problems are assigned a criticality level distinguishing at least between critical problems and warnings.
12. The computer program product of claim 10 , where, in causing the computer to apply the forward logical keyword connection analysis that enforces the semantic consistency of the content of the unstructured user input across the completed portions of the guided input sequence of the RCA input segments, the computer readable program code when executed on the computer causes the computer to:
compare the content of the unstructured user input accumulated across the completed portions of the guided input sequence of the respective RCA input segments with known-accurate RCA documents; and
identify any deviations of semantic consistency of the content of the unstructured user input relative to known IT-related causal connections represented within the known-accurate RCA documents.
13. The computer program product of claim 10 , where the computer readable program code when executed on the computer further causes the computer to add to an RCA document database the RCA document that comprises the content of the unstructured user input entered across the guided input sequence of the RCA input segments and that identifies the single cause categorization of the new IT problem.
14. The computer program product of claim 10 , where the computer readable program code when executed on the computer causing the computer to identify, perform, and generate is provided as a service within a cloud computing environment.