# US 11,308,473 B2 · Device for determining a transactional device, corresponding method and computer program > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,308,473 B2 - Document ID: US11308473B2 - Status: Granted - Kind: B2 - Application number: 17/048,765 - Filed: 2019-04-11 - Published: 2021-05-20 - Granted: 2022-04-19 - Earliest claimed: 2018-04-20 - Assignees: Banks and Acquirers International Holding - Applicants: Banks and Acquirers International Holding - Inventors: Thierry Marsaud - Web page: https://patentgrep.com/patent/US11308473B2 ## CPC - G06Q 20/20: Point-of-sale [POS] network systems - G06F 9/451: Execution arrangements for user interfaces - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06Q 20/204: {comprising interface for record bearing medium or carrier for electronic funds transfer or payment credit} - G06Q 20/34: using cards, e.g. integrated circuit [IC] cards or magnetic cards - G06Q 20/356: {Aspects of software for card payments} - G06V 10/22: by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition - G06V 30/40: Document-oriented image-based pattern recognition - G06V 40/107: {Static hand or arm} - G07F 7/0873: {Details of the card reader} - G07F 7/088: {the card reader being part of the point of sale [POS] terminal or electronic cash register [ECR] itself} - G07F 7/0893: {the card reader reading the card in a contactless manner} - G06N 3/02: Neural networks - G06N 5/04: Inference or reasoning models - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06Q 20/3278: {RFID or NFC payments by means of M-devices} - G06Q 20/341: {Active cards, i.e. cards including their own processing means, e.g. including an IC or chip} - G06Q 20/352: {Contactless payments by cards} - G06V 2201/09: Recognition of logos - 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 - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G07F: COIN-FREED OR LIKE APPARATUS (coin sorting G07D3/00; coin testing G07D5/00; {handling coins or paper currencies apart from payment activated apparatus G07D; payment architectures, schemes or protocols G06Q20/00}) ## Abstract A device and a method for determining a transactional device used for a transaction. More particularly, the device includes a data processor, a memory, an optical sensor, and a set of transactional interfaces. The method includes: obtaining at least one recording coming from the optical sensor), the recording being obtained when a user holds the transactional device in hand; determining at least one confidence score, the at least one confidence score being associated with at least one corresponding input of a structure of data for activating transactional interfaces present within the electronic device; and activating at least one transactional interface associated with the at least one input as a function of the at least one confidence score. ## Claims ### Claim 1 A method for determining a type of transactional device used to carry out a transaction, wherein the method is implemented by an electronic device comprising a data processor, a memory and an optical sensor, and a set of transactional interfaces, and the method comprises: obtaining at least one recording coming from the optical sensor, said recording being obtained when a user holds said transactional device in hand; determining at least one confidence score, said at least one confidence score being associated with at least one corresponding input of a structure of data for activating transactional interfaces of the set of transactional devices of said electronic device; and at least one act of activating at least one transactional interface associated with said at least one input of the structure of data for activating at least one transactional interface of the set of transactional devices of the electronic device as a function of a descending order of value of score of said at least one confidence score. ### Claim 2 (depends on 1) The method according to claim 1, wherein the at least one confidence score is a value representative of a probability of using a given transactional interface on the part of the user holding said transactional device in hand. ### Claim 3 (depends on 1) The method according to claim 1, wherein the determining of at least one confidence score associated with at least one input of the structure of decision data comprises at least one of the following: determining a confidence score associated with a number of finger portions present on at least one recording coming from the optical sensor; determining a confidence score associated with the transactional device in hand. ### Claim 4 (depends on 3) The method according to claim 3, wherein the determining at least one confidence score comprises the following for a current image and for a current input of the structure of data for activating transactional interfaces: determining a number of finger portions present on said current image, delivering a first value of number of finger portions; determining a position of finger portions present on said current image, delivering a second value of position of finger portions; assigning a score to the current input of the structure of data for activating transactional interfaces as a function of the first and second previously determined values. ### Claim 5 (depends on 3) The method according to claim 3, wherein the determining of a confidence score associated with the number of finger portions present on at least one recording coming from the optical sensor implements at least one previously trained neural network. ### Claim 6 (depends on 3) The method according to claim 3, wherein the determining of the confidence score associated with the number of finger portions present on at least one recording coming from the optical sensor implements at least one recognition template. ### Claim 7 (depends on 2) The method according to claim 2, wherein the determining at least one confidence score comprises, for a current image: pre-processing the current image delivering a pre-processed image; obtaining, from amongst a set of characteristics, at least one characteristic to be searched for; searching for said at least one characteristic on said processed image delivering at least one value representing the presence of said at least one characteristic within said current image. ### Claim 8 An electronic device for determining a type of transactional device used to carry out a transaction, the electronic device comprising: a data processor; a memory; an optical sensor; and a set of transactional interfaces, wherein the memory stores instructions which when executed by the data processor configure the electronic device to: obtain at least one recording coming from the optical sensor, said recording being obtained when a user holds said transactional device in hand; determine at least one confidence score, said at least one confidence score being associated with at least one corresponding input for activating at least one transactional interface of the set of transactional interfaces of said electronic device; and activating at least one transactional interface associated with said at least one input of the structure of data for activating transactional interfaces of the set of transactional devices of the electronic device, as a function of a descending order of value of score of said at least one confidence score. ### Claim 9 (depends on 8) The electronic device according to claim 8, wherein the electronic device is comprised in a payment terminal. ### Claim 10 A non-transitory computer-readable medium comprising program code instructions stored thereon, which when executed by a processor of an electronic device configure the electronic device to: determine a type of transactional device used to carry out a transaction by: obtaining at least one recording coming from an optical sensor of the electronic device, said recording being obtained when a user holds said transactional device in hand; determining at least one confidence score, said at least one confidence score being associated with at least one corresponding input of a structure of data for activating transactional interfaces of a set of transactional devices of said electronic device; and at least act of activating at least one transactional interface associated with said at least one input of the structure of data for activating at least one transactional interface of the set of transactional devices of the electronic device as a function of a descending order of value of score of said at least one confidence score.