# US 2022/0044199 A1 · AUTOMATIC GENERATION Of A TWO-PART READABLE SUSPICIOUS ACTIVITY REPORT (SAR) FROM HIGH-DIMENSIONAL DATA IN TABULAR FORM > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2022/0044199 A1 - Document ID: US20220044199A1 - Status: Published application - Kind: A1 - Application number: 16/986,289 - Filed: 2020-08-06 - Published: 2022-02-10 - Earliest claimed: 2020-08-06 - Assignees: Actimize Ltd. - Applicants: Actimize LTD. - Inventors: Debabrata PATI; Danny BUTVINIK - Web page: https://patentgrep.com/patent/US20220044199A1 ## CPC - G06Q 10/10: Office automation; Time management - G06F 40/56: Natural language generation - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/045: Combinations of networks - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/0475: Generative networks - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06Q 10/06316: {Sequencing of tasks or work} - G06Q 30/018: Certifying business or products - G06Q 40/02: Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03) - G06Q 50/26: Government or public services (business processes related to the transportation industry G06Q50/40) - G06N 3/047: Probabilistic or stochastic networks - 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 ## Abstract A computerized-method for automatically generating a two-part readable Suspicious Activity Report (SAR) from high-dimensional data in tabular form is provided herein. The computerized-method may include receiving high-dimensional data in tabular form of evidence financial transactions to be reported under Anti Money Laundering (AML) regulations. Then, displaying the received data to a Subject Matter Expert (SME) for ordering each displayed transaction in a predefined construction; Then, training one or more Natural Language Generation (NLG) translation models, for each transaction type, according to a deep learning model. Then, operating the one or more NLG translation models on each transaction e to generate for each transaction type a narrative of SAR; Then, operating a prebuilt summary model on the generated narrative of SAR of each transaction type to generate a summary of the narrative of SAR; and combining the narrative of SAR and the summary of narrative of SAR to one SAR. ## Claims ### Claim 1 A computerized-method for automatically generating a two-part readable Suspicious Activity Report (SIR) from high-dimensional data in tabular form, said computerized-method comprising: in a computerized-system comprising a processor and a memory, receiving by the processor, high-dimensional data in tabular form of evidence financial transactions to be reported wider Anti Money Laundering (AML) regulations, performing by the processor: displaying the received high-dimensional data in tabular form of evidence financial transactions to a Subject Matter Expert (SME) for ordering each displayed evidence financial transaction in a predefined construction; training one or more Natural Language Generation (NLG) translation models on the evidence financial transactions in the predefined construction, wherein each NLG model of the one or more NLG translation models is trained for a different preconfigured transaction type, according to a deep learning model; operating the one or more NLG translation models on the different preconfigured transaction type of the evidence financial transaction to generate for each transaction type a narrative of SAR; operating a prebuilt summary model on the generated narrative of SAR of each transaction type to generate a summary of the narrative of SAR; and combining the narrative of SIR and the summary of narrative of SAR to one SAR. ### Claim 2 (depends on 1) The computerized-method according to claim 1, wherein the deep learning model is a convolutional Seq2Seq model that is configured to operate a hierarchical attention mechanism, and wherein the prebuilt summary model is using NLGSimple model. ### Claim 3 (depends on 1) The computerized-method according to claim 1, wherein each one of the different preconfigured transaction type is at least one of: international, domestic, Automated Clearing House (ACH) and Peer to Peer (P2P) transfers, and wherein each one of the different preconfigured transaction types is performed via a channel, said channel is selected from: web, mobile, phone, branch, Application Programming Interface (API), Automated Teller Machine (ATM) and Point Of Sale (POS). ### Claim 4 (depends on 1) The computerized-method according to claim 1, wherein the summary is generated according to key features. ### Claim 5 (depends on 4) The computerized-method according to claim 4, wherein said key features are selected from: a total amount of transferred money from a first preconfigured bank to a second preconfigured bank, a total number of transfers from the first preconfigured bank to the second preconfigured bank or any other aggregated data. ### Claim 6 (depends on 2) The computerized-method according to claim 2, wherein the Seq2Seq model further implements a copying mechanism to handle Out Of Vocabulary (OOV) words. ### Claim 7 (depends on 1) The computerized-method according claim 1, wherein the summary of the narrative of SAR is implemented with a hierarchical attention mechanism to operate on keywords and key sentences level. ### Claim 8 (depends on 1) The computerized-method according claim 1, wherein each evidence financial transaction is having fields categorized as high changing fields and low changing fields. ### Claim 9 (depends on 8) The computerized-method according claim 8, wherein high changing fields are tokenized by an attribute name, and low changing fields are tokenized by a value thereof.