STAB: smart triaging assistant bot for intelligent troubleshooting

{
  "publication_number": "US10733037B2",
  "country": "US",
  "kind": "B2",
  "title": "STAB: smart triaging assistant bot for intelligent troubleshooting",
  "abstract": "In one embodiment, a server in a network reports one or more symptoms of a monitored device that is malfunctioning to a user interface via a particular chatbot session. The server receives, via the particular chatbot session, a triage request to enter a triage mode regarding the one or more reported symptoms. The server predicts a corrective action using the one or more reported symptoms as input to a machine learning model. The machine learning model is trained using a history of observed symptoms in the network, a history of corrective actions initiated via chatbot sessions and associated with the observed symptoms, and a history of feedback regarding the corrective actions received via the chatbot sessions. The server provides the predicted corrective action to the user interface via the particular chatbot session as a suggested corrective action, in response to the received triage request.",
  "claims": [
    "1. A method comprising: reporting, by a server in a network, one or more symptoms of a monitored device that is malfunctioning to a user interface via a particular chatbot session using a natural language processing; receiving, at the server and via the particular chatbot session, a triage request to enter a triage mode regarding the one or more reported symptoms; predicting, by the server, a corrective action using the one or more reported symptoms as input to a machine learning model, wherein the machine learning model is trained using a history of observed symptoms in the network, a history of corrective actions initiated via chatbot sessions and associated with the observed symptoms, and a history of feedback regarding the corrective actions received via the chatbot sessions; generating, by the server, a plurality of feature vectors, wherein each feature vector comprises one or more of the observed symptoms, corrective actions initiated via the chatbot sessions, and feedback regarding the corrective actions received via the chatbot sessions; providing, by the server, the predicted corrective action to the user interface via the particular chatbot session as a suggested corrective action, in response to the received triage request; and providing, by the server, a triage mechanism summary to an external storage system or code version management system.",
    "2. The method as in claim 1, further comprising: receiving, at the server, a request to implement the suggested corrective action via the chatbot session; and causing, by the server, performance of the suggested corrective action in response to receiving the request to implement the suggested corrective action.",
    "3. The method as in claim 2, further comprising: providing, by the server, an indication of a result of the performed corrective action via the particular chatbot session; and receiving, at the server, feedback from the user interface regarding the result of the performed corrective action via the particular chatbot session.",
    "4. The method as in claim 1, wherein the feedback comprises a request to exit the triage mode regarding the one or more reported symptoms.",
    "5. The method as in claim 1, further comprising: receiving, at the server, an indication of the one or more symptoms for an agent executed by the monitored device.",
    "6. The method as in claim 1, wherein the monitored device comprises one of: a router or switch.",
    "7. The method as in claim 1, further comprising: receiving, at the server, a rule from the user interface via the particular chatbot session, wherein the rule associates a set of one or more symptoms to an automatic corrective action to be initiated by the server.",
    "8. The method as in claim 7, further comprising: initiating, by the server, the automatic corrective action in response to receiving an indication from the monitored device that the monitored device is exhibiting the one or more symptoms of the rule.",
    "9. The method as in claim 1, further comprising: providing, by the server, a triage mechanism summary to an external storage system or code version management system.",
    "10. An apparatus, comprising: one or more network interfaces to communicate with a computer network; a processor coupled to the one or more network interfaces and configured to execute a process; and a memory configured to store the process executable by the processor, the process when executed configured to: report one or more symptoms of a monitored device that is malfunctioning to a user interface via a particular chatbot session using a natural language processing; receive, via the particular chatbot session, a triage request to enter a triage mode regarding the one or more reported symptoms; predict a corrective action using the one or more reported symptoms as input to a machine learning model, wherein the machine learning model is trained using a history of observed symptoms in the network, a history of corrective actions initiated during chatbot sessions and associated with the observed symptoms, and a history of feedback regarding the corrective actions received during the chatbot sessions; generate a plurality of feature vectors, wherein each feature vector comprises one or more of the observed symptoms, corrective actions initiated via the chatbot sessions, and feedback regarding the corrective actions received via the chatbot sessions; provide the predicted corrective action to the user interface via the particular chatbot session as a suggested corrective action, in response to the received triage request; and provide a triage mechanism summary to an external storage system or code version management system.",
    "11. The apparatus as in claim 10, wherein the process when executed is further operable to: receive a request to implement the suggested corrective action via the chatbot session; cause performance of the suggested corrective action in response to receiving the request to implement the suggested corrective action; provide an indication of a result of the performed corrective action via the particular chatbot session; and receive feedback from the user interface regarding the result of the performed corrective action via the particular chatbot session.",
    "12. The apparatus as in claim 10, wherein the feedback comprises a request to exit the triage mode regarding the one or more reported symptoms.",
    "13. The apparatus as in claim 10, wherein the process when executed is further operable to: receive an indication of the one or more symptoms for an agent executed by the monitored device.",
    "14. The apparatus as in claim 10, wherein the process when executed is further operable to: receive a rule from the user interface via the particular chatbot session, wherein the rule associates a set of one or more symptoms to an automatic corrective action to be initiated by the apparatus.",
    "15. The apparatus as in claim 14, wherein the process when executed is further operable to: initiate the automatic corrective action in response to receiving an indication from the monitored device that the monitored device is exhibiting the one or more symptoms of the rule.",
    "16. A tangible, non-transitory, computer-readable medium storing program instructions that cause a computer in a network to execute a process comprising: reporting one or more symptoms of a monitored device that is malfunctioning to a user interface via a particular chatbot session using a natural language processing; receiving, via the particular chatbot session, a triage request to enter a triage mode regarding the one or more reported symptoms; predicting a corrective action using the one or more reported symptoms as input to a machine learning model, wherein the machine learning model is trained using a history of observed symptoms in the network, a history of corrective actions initiated during chatbot sessions and associated with the observed symptoms, and a history of feedback regarding the corrective actions received during the chatbot sessions; generating a plurality of feature vectors, wherein each feature vector comprises one or more of the observed symptoms, corrective actions initiated via the chatbot sessions, and feedback regarding the corrective actions received via the chatbot sessions; providing the predicted corrective action to the user interface via the particular chatbot session as a suggested corrective action, in response to the received triage request; and providing a triage mechanism summary to an external storage system or code version management system.",
    "17. The tangible, non-transitory, computer-readable medium as in claim 16, the process further comprising: receiving, at the server, a request to implement the suggested corrective action via the chatbot session; and causing, by the server, performance of the suggested corrective action in response to receiving the request to implement the suggested corrective action.",
    "18. The tangible, non-transitory, computer-readable medium as in claim 17, the process further comprising: providing, by the server, an indication of a result of the performed corrective action via the particular chatbot session; and receiving, at the server, feedback from the user interface regarding the result of the performed corrective action via the particular chatbot session.",
    "19. The tangible, non-transitory, computer-readable medium as in claim 16, wherein the feedback comprises a request to exit the triage mode regarding the one or more reported symptoms.",
    "20. The tangible, non-transitory, computer-readable medium as in claim 16, wherein the monitored device comprises one of: a router or switch."
  ],
  "cpc": [
    "G06F 11/0709",
    "G06F 11/0787",
    "G06F 11/0793",
    "G06N 20/00",
    "H04L 51/02"
  ],
  "assignees": [
    "CISCO TECH INC"
  ],
  "filing_date": "2016-11-03",
  "publication_date": "2020-08-04",
  "grant_date": "2020-08-04",
  "priority_date": "2016-11-03",
  "application_number": "US-201615342340-A",
  "family_id": "62021562",
  "citations": [
    "US2008109683A1",
    "US2014098949A1",
    "US2016094492A1",
    "US2016350173A1",
    "US2017235629A1",
    "US7003560B1",
    "US9036805B2",
    "US9401989B2"
  ]
}