# US 12,002,263 B2 · Feedback and training for a machine learning algorithm configured to determine customer purchases during a shopping session at a physical store > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,002,263 B2 - Document ID: US12002263B2 - Status: Granted - Kind: B2 - Application number: 16/938,676 - Filed: 2020-07-24 - Published: 2021-04-29 - Granted: 2024-06-04 - Earliest claimed: 2019-10-25 - Assignees: 7-Eleven, Inc. - Applicants: 7-Eleven, Inc. - Inventors: Shahmeer Ali Mirza; Sailesh Bharathwaaj Krishnamurthy; Trong Nghia Nguyen; Sarath Vakacharla - Web page: https://patentgrep.com/patent/US12002263B2 ## CPC - G06V 20/10: Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59) - G06N 20/00: Machine learning - G06Q 30/0633: {Managing shopping lists, e.g. compiling or processing purchase lists (shipping orders G06Q10/083; order filling G06Q10/087)} - G06V 10/70: using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88) - G06V 20/20: in augmented reality scenes - G06V 20/49: {Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes} - G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - 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 An apparatus includes a processor. The processor receives an algorithmic shopping cart that includes a first set of items determined by an algorithm to have been selected by a person during a shopping session in a physical store, based on a set of inputs received from sensors located within the physical store. The processor also receives a virtual shopping cart that includes a second set of items. Video of the shopping session was captured by a set of cameras located in the physical store and depicts the person selecting the second set of items. The processor compares the algorithmic cart to the virtual cart and determines that a discrepancy exists between the algorithmic cart and the virtual cart. The processor determines a subset of the set of inputs associated with the discrepancy and attaches metadata explaining the discrepancy to the subset. The processor uses the subset to train the algorithm. ## Claims ### Claim 1 An apparatus comprising: a hardware processor configured to: receive an algorithmic shopping cart comprising a first set of items, the first set of items determined by an algorithm to have been selected by a first person during a shopping session in a physical store, based on a set of inputs received from sensors located within the physical store; receive a virtual shopping cart comprising a first set of virtual items, wherein each virtual item is added to the virtual shopping cart to represent a corresponding physical item selected by the first person during the shopping session; compare the algorithmic shopping cart to the virtual shopping cart; in response to comparing the algorithmic shopping cart to the virtual shopping cart: determine that the algorithmic shopping cart is consistent with the virtual shopping cart; and generate a receipt based at least in part upon the items contained in either the virtual shopping cart or the algorithmic shopping cart; receive a second algorithmic shopping cart comprising a second set of items, the second set of items determined by the algorithm to have been selected by a second person during a second shopping session in the physical store, based on a second set of inputs received from the sensors located within the physical store; receive a second virtual shopping cart comprising a second set of virtual items associated with the second shopping session; compare the second algorithmic shopping cart to the second virtual shopping cart; and in response to comparing the second algorithmic shopping cart to the second virtual shopping cart, determine that the second algorithmic shopping cart matches the second virtual shopping cart. ### Claim 2 (depends on 1) The apparatus of claim 1, wherein the receipt comprises a first price assigned to a first item and a second price assigned to a second item. ### Claim 3 (depends on 2) The apparatus of claim 2, wherein the receipt further comprises a first quantity assigned to the first item and a second quantity assigned to the second item. ### Claim 4 (depends on 1) The apparatus of claim 1, wherein the hardware processor is further configured to send the receipt to a device associated with the first person. ### Claim 5 (depends on 1) The apparatus of claim 1, wherein the virtual shopping cart is generated based at least in part upon video of the shopping session captured by a set of cameras located in the physical store, the video depicting the first person selecting the second set of items. ### Claim 6 (depends on 1) The apparatus of claim 1, wherein the sensors comprise: an array of algorithmic cameras; and a set of weight sensors, wherein each item of the first set of items is coupled to a weight sensor of the set of weight sensors. ### Claim 7 A method comprising: receiving an algorithmic shopping cart comprising a first set of items, the first set of items determined by an algorithm to have been selected by a first person during a shopping session in a physical store, based on a set of inputs received from sensors located within the physical store; receiving a virtual shopping cart comprising a first set of virtual items, wherein each virtual item is added to the virtual shopping cart to represent a corresponding physical item selected by the first person during the shopping session; comparing the algorithmic shopping cart to the virtual shopping cart; in response to comparing the algorithmic shopping cart to the virtual shopping cart: determining the algorithmic shopping cart is consistent with the virtual shopping cart; and generating a receipt based at least in part upon the items contained in either the virtual shopping cart or the algorithmic shopping cart; receiving a second algorithmic shopping cart comprising a second set of items, the second set of items determined by the algorithm to have been selected by a second person during a second shopping session in the physical store, based on a second set of inputs received from the sensors located within the physical store; receiving a second virtual shopping cart comprising a second set of virtual items associated with the second shopping session; comparing the second algorithmic shopping cart to the second virtual shopping cart; and in response to comparing the second algorithmic shopping cart to the second virtual shopping cart, determining that the second algorithmic shopping cart matches the second virtual shopping cart. ### Claim 8 (depends on 7) The method of claim 7, wherein the receipt comprises a first price assigned to a first item and a second price assigned to a second item. ### Claim 9 (depends on 8) The method of claim 8, wherein the receipt further comprises a first quantity assigned to the first item and a second quantity assigned to the second item. ### Claim 10 (depends on 7) The method of claim 7, wherein the hardware processor is further configured to send the receipt to a device associated with the first person. ### Claim 11 (depends on 7) The method of claim 7, wherein the virtual shopping cart is generated based at least in part upon video of the shopping session captured by a set of cameras located in the physical store, the video depicting the first person selecting the second set of items. ### Claim 12 (depends on 7) The method of claim 7, wherein the sensors comprise: an array of algorithmic cameras; and a set of weight sensors, wherein each item of the first set of items is coupled to a weight sensor of the set of weight sensors. ### Claim 13 A system comprising: a set of sensors located within a physical store, the set of sensors comprising: an array of algorithmic cameras; and a set of weight sensors; and a processor configured to: receive an algorithmic shopping cart comprising a first set of items, the first set of items determined by an algorithm to have been selected by a first person during a shopping session in the physical store, based on a set of inputs received from the set of sensors; receive a virtual shopping cart comprising a first set of virtual items, wherein each virtual item is added to the virtual shopping cart to represent a corresponding physical item selected by the first person during the shopping session; compare the algorithmic shopping cart to the virtual shopping cart; in response to comparing the algorithmic shopping cart to the virtual shopping cart: determine that the algorithmic shopping cart is consistent with the virtual shopping cart; and generate a receipt based at least in part upon the items contained in either the virtual shopping cart or the algorithmic shopping cart; receive a second algorithmic shopping cart comprising a second set of items, the second set of items determined by the algorithm to have been selected by a second person during a second shopping session in the physical store, based on a second set of inputs received from the set of sensors; receive a second virtual shopping cart comprising a second set of virtual items associated with the second shopping session; compare the second algorithmic shopping cart to the second virtual shopping cart; and in response to comparing the second algorithmic shopping cart to the second virtual shopping cart, determine that the second algorithmic shopping cart matches the second virtual shopping cart. ### Claim 14 (depends on 13) The system of claim 13, wherein the receipt comprises a first price assigned to a first item and a second price assigned to a second item. ### Claim 15 (depends on 14) The system of claim 14, wherein the receipt further comprises a first quantity assigned to the first item and a second quantity assigned to the second item. ### Claim 16 (depends on 13) The system of claim 13, wherein the hardware processor is further configured to send the receipt to a device associated with the first person. ### Claim 17 (depends on 13) The system of claim 13, wherein the virtual shopping cart is generated based at least in part upon video of the shopping session captured by a set of cameras located in the physical store, the video depicting the first person selecting the second set of items.