# US 12,008,025 B2 · Method and system for augmenting a question path graph for technical support > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,008,025 B2 - Document ID: US12008025B2 - Status: Granted - Kind: B2 - Application number: 17/502,197 - Filed: 2021-10-15 - Published: 2023-04-20 - Granted: 2024-06-11 - Earliest claimed: 2021-10-15 - Assignees: EMC IP Holding Company LLC - Applicants: EMC IP Holding Company LLC - Inventors: Shelesh Chopra; Parminder Singh Sethi; Akanksha Goel; Kanika Kapish - Web page: https://patentgrep.com/patent/US12008025B2 ## CPC - G06F 16/3329: Natural language query formulation - G06F 16/3326: {using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages} - G06F 16/3346: {using probabilistic model} - G06F 16/9024: {Graphs; Linked lists (G06F16/9027 takes precedence)} - H04L 41/5074: Handling of user complaints or trouble tickets - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract In general, embodiments relate to a method for managing a technical support session, comprising: determining a technical support issue (TSI) for a technical support session; identifying a question path graph (QPG) associated with the TSI; and displaying at least a portion of the QPG to a technical support person (TSP) during the technical support session. ## Claims ### Claim 1 A method for managing a technical support session (TSS), comprising: receiving, as part of the 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; determining, 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; identifying 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; identifying a first node of the plurality of nodes in the QPG corresponding to the first question; identifying 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 displaying 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. ### Claim 2 (depends on 1) The method of claim 1, wherein the QPG is a directed graph, wherein each node in the QPG corresponds to a different question. ### Claim 3 (depends on 2) The method of claim 2, wherein a directed edge connects the first node and a second node, wherein the directed edge is one of the plurality of directed edges, and wherein the first node and the second node are each one of the plurality of nodes. ### Claim 4 (depends on 3) The method of claim 3, wherein the first node is associated with the LSI. ### Claim 5 (depends on 4) The method of claim 4, wherein the LSI specifies a third node that is downstream of the second node and the likelihood that the question sequence of the first node, the second node, and the third node will lead to successful resolution of the TSS. ### Claim 6 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. ### Claim 7 (depends on 6) The TS system of claim 6, wherein the QPG is a directed graph, wherein each node in the QPG corresponds to a different question. ### Claim 8 (depends on 7) The TS system of claim 7, wherein a directed edge connects the first node and a second node, wherein the directed edge is one of the plurality of directed edges, and wherein the first node and the second node are each one of the plurality of nodes. ### Claim 9 (depends on 8) The TS system of claim 8, wherein the first node is associated with the LSI. ### Claim 10 (depends on 9) The TS system of claim 9, wherein the LSI specifies a third node that is downstream of the second node and the likelihood that the question sequence of the first node, the second node, and the third node will lead to successful resolution of the TSS. ### Claim 11 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. ### Claim 12 (depends on 11) The non-transitory computer readable medium of claim 11, wherein the QPG is a directed graph, wherein each node in the QPG corresponds to a different question. ### Claim 13 (depends on 12) The non-transitory computer readable medium of claim 12, wherein a directed edge connects the first node and a second node, wherein the directed edge is one of the plurality of directed edges, and wherein the first node and the second node are each one of the plurality of nodes. ### Claim 14 The non-transitory computer readable medium of 17, wherein the first node is associated with the LSI. ### Claim 15 The non-transitory computer readable medium of 18, wherein the LSI specifies a third node that is downstream of the second node and the likelihood that the question sequence of the first node, the second node, and the third node will lead to successful resolution of the TSS.