Method and system for augmenting a question path graph for technical support

A technical support (TS) system, comprising:

• a storage configured to store a plurality of question path graphs (QPGs) and a likelihood of success information (LSI);
• a processor, wherein the processor is configured to:
• receive, as part of a technical support session (TSS), a technical support correspondence (TSC), wherein the TSC is converted into a text format and is cleaned to obtain a cleaned TSC, wherein the cleaned TSC is classified as a first question;
• determine, using a machine learning algorithm evaluating the TSS in real-time, a technical support issue (TSI) for the TSS technical,
• wherein the TSI is used to identify a historical TSS, wherein a second question is identified from the historical TSS,
• wherein, based on the TSI, a ranking request comprising the first question and the second question is sent to a technical support person (TSP), wherein, in response to the ranking request, a ranking of the first question and the second question is received from the TSP, wherein, based on the ranking, the question is determined as useful in resolving the TSI, wherein the first question and the second question are referred as a question sequence, wherein, based on at least the first question sequence, a QPG is generated;
• identify that the QPG of the plurality of QPGs is associated with the TSI, wherein the QPG comprises a plurality of nodes and a plurality of directed edges connecting the plurality of nodes;
• identify a first node of the plurality of nodes in the QPG corresponding to the first question;
• identify a portion of the QPG, wherein the portion of the QPG only comprises the first node and one or more nodes of the plurality of nodes that are downstream of the first node;
• and
• display on a graphical user interface the portion of the QPG and the LSI to the TSP during the TSS, wherein the LSI indicates a likelihood that a specific question path will result in a successful resolution of the TSI.

A non-transitory computer readable medium comprising computer readable program code to:

• receive, as part of a technical support session (TSS), a technical support correspondence (TSC), wherein the TSC is converted into a text format and is cleaned to obtain a cleaned TSC, wherein the cleaned TSC is classified as a first question;
• determine, using a machine learning algorithm evaluating the TSS in real-time, a technical support issue (TSI) for the TSS,
• wherein the TSI is used to identify a historical TSS, wherein a second question is identified from the historical TSS,
• wherein, based on the TSI, a ranking request comprising the first question and the second question is sent to a technical support person (TSP), wherein, in response to the ranking request, a ranking of the first question and the second question is received from the TSP, wherein, based on the ranking, the first question is determined as useful in resolving the TSI, wherein the first question and the second question are referred as a question sequence, wherein, based on at least the question sequence, a question path graph (QPG) is generated;
• identify that the QPG is associated with the TSI, wherein the QPG comprises a plurality of nodes and a plurality of directed edges connecting the plurality of nodes;
• identify a first node of the plurality of nodes in the QPG corresponding to the first question;
• identify a portion of the QPG, wherein the portion of the QPG only comprises the first node and one or more nodes of the plurality of nodes that are downstream of the first node;
• and
• display on a graphical user interface the portion of the QPG and a likelihood of success information (LSI) to the TSP during the TSS, wherein the LSI indicates a likelihood that a specific question path will result in a successful resolution of the TSI.