# US 2013/0159787 A1 · Methods and systems for predicting a fault > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2013/0159787 A1 - Document ID: US20130159787A1 - Status: Published application - Kind: A1 - Application number: 13/330,847 - Filed: 2011-12-20 - Published: 2013-06-20 - Earliest claimed: 2011-12-20 - Assignees: NCR Corporation - Inventors: Harold R. Yingling, JR.; Cynthia Hill Evans; Larry D. Bass - Web page: https://patentgrep.com/patent/US20130159787A1 ## CPC - G06F 11/008: {Reliability or availability analysis} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Disclosed is a fault prediction system and method that uses non-fatal event data received from a terminal to make predictions concerning future fatal faults for the terminal. A complex fault pattern associated with a fault is applied to the non-fatal event data to predict the fault. A corrective action is provided for each predicted fault and historical data is used to predict a time to the predicted fault to govern the type of service response to create to prevent the fault. ## Claims ### Claim 1 A method for predicting a fatal fault in a terminal using non-fatal event data, the method comprising the steps of: receiving a plurality of event data from the terminal where the plurality of event data includes non-fatal event data; identifying non-fatal event data associated with a fault from the plurality of event data; comparing the identified non-fatal event data to a predetermined fault pattern associated with the fault; and generating a fault predicted signal for the terminal when the predetermined fault pattern is found within the non-fatal event data. ### Claim 2 (depends on 1) 2) The method of claim 1, further comprising: receiving historical event data associated with the fault from a plurality of terminals where the historical event data includes fatal and non-fatal event data; and processing the historical event data to identify the predetermined fault pattern associated with the fault where the identified fault pattern is based on non-fatal event data. ### Claim 3 (depends on 1) 3) The method of claim 1 further comprising: receiving configuration data for the plurality of terminals; and refining the identified predetermined fault pattern based on the configuration data. ### Claim 4 (depends on 1) 4) The method of claim 1, further comprising: repeating the receiving, identifying and comparing steps when the predetermined fault pattern is not identified within the non-fatal event data. ### Claim 5 (depends on 1) 5) The method of claim 1, wherein the predetermined fault pattern includes a first pattern wherein during a first predetermined period of time the number of events exceeds a first threshold and wherein the predetermined fault pattern includes a second pattern wherein the first pattern is repeated a predetermined number of times. ### Claim 6 (depends on 1) 6) The method of claim 1, wherein the event data includes an environmental parameter. ### Claim 7 (depends on 6) 7) The method of claim 6, wherein the environmental parameter is a temperature. ### Claim 8 (depends on 1) 8) The method of claim 1, wherein the event data include an operational parameter. ### Claim 9 (depends on 8) 9) The method of claim 8, wherein the operational parameter is a recoverable magnetic stripe card operation. ### Claim 10 (depends on 8) 10) The method of claim 8, wherein the operational parameter is an RPM value for a fan. ### Claim 11 (depends on 1) 11) The method of claim 1, further comprising: receiving tally data from the terminal; and adjusting the predetermined fault pattern when the tally data associated with the fault exceeds a predetermined threshold for the tally data where the predetermined threshold for the tally data is a life limit value. ### Claim 12 (depends on 11) 12) The method of claim 11, wherein adjusting the predetermined fault pattern includes adjusting at least one predetermined value in the predetermined fault pattern lower. ### Claim 13 (depends on 11) 13) The method of claim 11, wherein the tally data is a total operating time. ### Claim 14 (depends on 11) 14) The method of claim 11, wherein the tally data is a total cycle count. ### Claim 15 (depends on 1) 15) The method of claim 1, further comprising: capturing event data at the terminal; and transferring the event data from the terminal. ### Claim 16 (depends on 1) 16) The method of claim 1, wherein the terminal is an automatic teller machine. ### Claim 17 (depends on 1) 17) The method of claim 1, wherein the terminal is a point of sale terminal. ### Claim 18 (depends on 1) 18) The method of claim 1, further comprising: generating a predictive service next visit call request to a first location where the terminal is located in response to the predicted fault signal wherein the predictive service next visit call request includes a first service time period during which a predictive service call associated with the request is not scheduled. ### Claim 19 (depends on 18) 19) The method of claim 18, wherein a reactive service call is scheduled to the first location during the first service time period and the predictive service next visit call is combined with the reactive service call. ### Claim 20 (depends on 18) 20) The method of claim 18, wherein generating the predictive service next visit call request includes predictive part service advice. ### Claim 21 (depends on 18) 21) The method of claim 18, wherein generating the predictive service next visit call request includes predictive parts replacement advice. ### Claim 22 (depends on 1) 22) The method of claim 1, further comprising: generating a predictive action request for the terminal in response to the predicted fault signal. ### Claim 23 23) A fault predicting system for predicting a fault in a terminal, the system comprising: a computer memory wherein a plurality of computer programs and data are stored; and a computer processor in communication with the computer memory wherein when the computer programs are executed by the computer processor operations are performed, the operations comprising: receiving a plurality of event data from the terminal where the plurality of event data includes non-fatal event data; identifying non-fatal event data associated with a fault from the plurality of event data; comparing the identified non-fatal event data to a predetermined fault pattern associated with the fault; and generating a fault predicted signal for the terminal when the predetermined fault pattern is found within the non-fatal event data. ### Claim 24 (depends on 23) 24) The system of claim 23, the operations further comprising: receiving historical event data associated with the fault from a plurality of terminals where the historical event data includes fatal and non-fatal event data; and processing the historical event data to identify the predetermined fault pattern associated with the fault where the identified fault pattern is based on non-fatal event data. ### Claim 25 (depends on 23) 25) The system of claim 23, the operations further comprising: determining that the predictive failure date is less than 24 hours away and converting the predictive service next visit call request to a predictive imminent service request; and scheduling a predictive service call in response to the predictive imminent service request. ### Claim 26 (depends on 23) 26) The system of claim 23, the operations further comprising: receiving configuration data for the plurality of terminals; and refining the identified predetermined fault pattern based on the configuration data. ### Claim 27 (depends on 23) 27) The system of claim 23, the operations further comprising: repeating the receiving, identifying and comparing steps when the predetermined fault pattern is not identified within the non-fatal event data. ### Claim 28 (depends on 23) 28) The system of claim 23, wherein the predetermined fault pattern includes a first pattern wherein during a first predetermined period of time the number of events exceeds a first threshold and wherein the predetermined fault pattern includes a second pattern wherein the first pattern is repeated a predetermined number of times.