# US 10,311,440 B2 · Context-aware deterrent and response system for financial transaction device security > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,311,440 B2 - Document ID: US10311440B2 - Status: Granted - Kind: B2 - Application number: 15/162,880 - Filed: 2016-05-24 - Published: 2017-11-30 - Granted: 2019-06-04 - Earliest claimed: 2016-05-24 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Osamuyimen Stewart; Komminist Weldemariam - Web page: https://patentgrep.com/patent/US10311440B2 ## CPC - G06Q 20/405: {Establishing or using transaction specific rules} - G06Q 20/3224: {Transactions dependent on location of M-devices} - G06Q 20/4016: {involving fraud or risk level assessment in transaction processing} - G06Q 40/02: Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03) - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract The disclosure provides systems and methods for increasing the security of financial transaction devices and other places of value. Increased security is provided by analysis of a plurality of sensor and other inputs, and formulation of context-sensitive response plan involving the most probably effective response agents. ## Claims ### Claim 1 A method comprising: receiving a sensor reading from a sensor positioned proximal to a financial transaction device, the sensor reading pertaining to an incident; receiving a contextual data item pertaining to the financial transaction device; calculating an expected risk profile based on the sensor reading and contextual data item, wherein the expected risk profile comprises a probability that a detected behavior is related to a theft incident and an expected incident description that includes a number of perpetrators, a type of attack, weaponry used in the attack and amount of money in the financial transaction device; determining an appropriate response element and response plan selected from among multiple possible response options based on the financial transaction device and the expected risk profile, wherein the determining includes evaluating similar historical responses and predicting a behavior of the response element; and initiating a response from the response element. ### Claim 2 (depends on 1) The method of claim 1, wherein the sensor reading and contextual data item are received by a server via a network, the server positioned remote from the financial transaction device, and wherein the initiating a response comprises transmitting, by the server, an instruction configured to initiate the response from the response element. ### Claim 3 (depends on 1) The method of claim 1, wherein the sensor reading and contextual data item are received by a local device proximal to or integral with the financial transaction device. ### Claim 4 (depends on 1) The method of claim 1, wherein the contextual data item is selected from a status of the financial transaction device, financial transaction device ID, a geo-location of the financial transaction device, the time, a traffic report, and an activity report. ### Claim 5 (depends on 1) The method of claim 1, wherein the appropriate response element is selected from a private security detail and a public law enforcement detail, and is determined based on the location of the response element and the capabilities of the response element. ### Claim 6 (depends on 1) The method of claim 1, further comprising determining an appropriate response plan based on the geo-location of the financial transaction device and the expected risk profile. ### Claim 7 (depends on 1) The method of claim 1, further comprising determining an appropriate response plan based on the geo-location of the financial transaction device and the expected risk profile, wherein the response plan comprises initiating an audio message from a device proximal to the financial transaction device, changing a status of the financial transaction device. ### Claim 8 (depends on 1) The method of claim 1, wherein the determining the appropriate response element comprises accepting input from a human operator. ### Claim 9 A system comprising: a processor; a memory coupled to the processor, the memory configured to store program instructions for instructing the processor to carry out the steps of: receiving a sensor reading from a sensor positioned proximal to a financial transaction device, the sensor reading pertaining to an incident; receiving a contextual data item pertaining to the financial transaction device; calculating an expected risk profile based on the sensor reading and contextual data item, wherein the expected risk profile comprises a probability that a detected behavior is related to a theft incident and an expected incident description that includes a number of perpetrators, a type of attack, weaponry used in the attack and amount of money in the financial transaction device; determining an appropriate response element and response plan selected from among multiple possible response options based on the financial transaction device and the expected risk profile, wherein the determining includes evaluating similar historical responses and predicting a behavior of the response element; and initiating a response from the response element. ### Claim 10 (depends on 9) The system of claim 9, wherein the program instructions are configured to initiate a reasoning engine, the reasoning engine configured to calculate the expected risk profile and appropriate response element. ### Claim 11 (depends on 9) The system of claim 9, wherein the program instructions are configured to initiate an engine selected from an image and video engine; a language engine; a mapping engine; a counting engine; a distance engine; a pattern engine; and a risk assessor engine. ### Claim 12 (depends on 9) The system of claim 9, wherein the program instructions are configured to identify similar historical responses, apply probabilistic algorithms to find the most likely optimal response plan, and predicted behavior of response elements. ### Claim 13 (depends on 9) The system of claim 9, wherein the program instructions are configured to determine incident severity based on past incident patterns, the sensor reading, and the contextual data item.