# US 12,118,634 B2 · System and method for detecting relevant potential participating entities > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,118,634 B2 - Document ID: US12118634B2 - Status: Granted - Kind: B2 - Application number: 17/124,221 - Filed: 2020-12-16 - Published: 2022-03-03 - Granted: 2024-10-15 - Earliest claimed: 2020-09-01 - Assignees: Skyline AI Ltd. - Applicants: Skyline AI Ltd. - Inventors: Or Hiltch - Web page: https://patentgrep.com/patent/US12118634B2 ## CPC - G06Q 50/167: {Closing} - G06F 16/902: {using more than one table in sequence, i.e. systems with three or more layers} - G06N 20/00: Machine learning - G06Q 30/0201: Market modelling; Market analysis; Collecting market data - 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 method and system for detecting relevant potential participating entities across different databases. A method includes retrieving transaction data related to potential participating entities by resolving each of the plurality of potential participating entities between a dataset including transaction data and a dataset indicating the plurality of potential participating entities, wherein resolving the plurality of potential participating entities further includes applying resolution rules requiring matching a plurality of features between respective instances of the potential participating entity in the transaction data and in the dataset indicating the plurality of potential participating entities; determining a plurality of relevance scores based on the retrieved transaction data and entity characteristics of a subject entity, wherein each relevance score represents a relevance of the subject entity with respect to a respective potential participating entity; and identifying, based on the plurality of relevance scores, at least one relevant potential participating entity. ## Claims ### Claim 1 A method for detecting relevant potential participating entities, comprising: retrieving transaction data related to each of a plurality of potential participating entities, wherein retrieving the transaction data further comprises resolving each of the plurality of potential participating entities between a dataset including the transaction data and a dataset indicating the plurality of potential participating entities, wherein resolving the plurality of potential participating entities further comprises applying resolution rules requiring at least matching a plurality of features between respective instances of the potential participating entity in the transaction data and in the dataset indicating the plurality of potential participating entities, wherein each potential participating entity is resolved such that different instances of the potential participating entity are determined as uniquely identifying the same potential participating entity, wherein the plurality of features between respective instances of the potential participating entity in the transaction data and in the dataset indicating the plurality of potential participating entities are determined to match when minimum requirements are met, the minimum requirements comprising partial matches rules, synonym rules, and minor error rules; determining a plurality of relevance scores based on the retrieved transaction data and entity characteristics of a subject entity, wherein each relevance score represents a relevance of the subject entity with respect to a respective potential participating entity of the plurality of potential participating entities; and identifying, based on the plurality of relevance scores, at least one relevant potential participating entity with respect to the subject entity. ### Claim 2 (depends on 1) The method of claim 1, wherein the respective relevance score for each relevant potential participating entity is above a threshold. ### Claim 3 (depends on 1) The method of claim 1, further comprising: identifying at least one redundant instance among the plurality of relevant potential participating entities, wherein identifying the at least one redundant instance further comprises resolving entities among the plurality of relevant potential participating entities; and removing the at least one redundant instance from the plurality of relevant potential participating entities to determine at least one unique relevant potential participating entity. ### Claim 4 (depends on 1) The method of claim 1, wherein the plurality of relevance scores is determined using a machine learning model trained based on training subject entity data and training transaction data. ### Claim 5 (depends on 1) The method of claim 1, wherein the resolution rules include cleaning resolution rules for cleaning data related to entities. ### Claim 6 (depends on 1) The method of claim 1, wherein the resolution rules include requirements for a minimum number of matching features. ### Claim 7 (depends on 1) The method of claim 1, further comprising: identifying supplemental data for at least one of the plurality of potential participating entities, wherein identifying the supplemental data further comprises resolving the plurality of potential participating entities between a dataset including the transaction data and at least one dataset including potential participating entity characteristics; and enriching the transaction data with the identified supplemental data, wherein the plurality of relevance scores is determined based further on the enriched transaction data. ### Claim 8 (depends on 1) The method of claim 1, further comprising: generating a notification based on the at least one relevant potential participating entity; and sending the notification to a user device. ### Claim 9 A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to execute a process, the process comprising: retrieving transaction data related to each of a plurality of potential participating entities, wherein retrieving the transaction data further comprises resolving each of the plurality of potential participating entities between a dataset including the transaction data and a dataset indicating the plurality of potential participating entities, wherein resolving the plurality of potential participating entities further comprises applying resolution rules requiring at least matching a plurality of features between respective instances of the potential participating entity in the transaction data and in the dataset indicating the plurality of potential participating entities, wherein each potential participating entity is resolved such that different instances of the potential participating entity are determined as uniquely identifying the same potential participating entity, wherein the plurality of features between respective instances of the potential participating entity in the transaction data and in the dataset indicating the plurality of potential participating entities are determined to match when minimum requirements are met, the minimum requirements comprising partial matches rules, synonym rules, and minor error rules; determining a plurality of relevance scores based on the retrieved transaction data and entity characteristics of a subject entity, wherein each relevance score represents a relevance of the subject entity with respect to a respective potential participating entity of the plurality of potential participating entities; and identifying, based on the plurality of relevance scores, at least one relevant potential participating entity with respect to the subject entity. ### Claim 10 A system for detecting a relevant potential participating entities, comprising: a processing circuitry; and a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to: retrieve transaction data related to each of a plurality of potential participating entities, wherein retrieving the transaction data further comprises resolving each of the plurality of potential participating entities between a dataset including the transaction data and a dataset indicating the plurality of potential participating entities, wherein resolving the plurality of potential participating entities further comprises applying resolution rules requiring at least matching a plurality of features between respective instances of the potential participating entity in the transaction data and in the dataset indicating the plurality of potential participating entities, wherein each potential participating entity is resolved such that different instances of the potential participating entity are determined as uniquely identifying the same potential participating entity, wherein the plurality of features between respective instances of the potential participating entity in the transaction data and in the dataset indicating the plurality of potential participating entities are determined to match when minimum requirements are met, the minimum requirements comprising partial matches rules, synonym rules, and minor error rules; determine a plurality of relevance scores based on the retrieved transaction data and entity characteristics of a subject entity, wherein each relevance score represents a relevance of the subject entity with respect to a respective potential participating entity of the plurality of potential participating entities; and identify, based on the plurality of relevance scores, at least one relevant potential participating entity with respect to the subject entity. ### Claim 11 (depends on 10) The system of claim 10, wherein the respective relevance score for each relevant potential participating entity is above a threshold. ### Claim 12 (depends on 10) The system of claim 10, wherein the system is further configured to: identify at least one redundant instance among the plurality of relevant potential participating entities, wherein identifying the at least one redundant instance further comprises resolving entities among the plurality of relevant potential participating entities; and remove the at least one redundant instance from the plurality of relevant potential participating entities to determine at least one unique relevant potential participating entity. ### Claim 13 (depends on 10) The system of claim 10, wherein the plurality of relevance scores is determined using a machine learning model trained based on training subject entity data and training transaction data. ### Claim 14 (depends on 10) The system of claim 10, wherein the resolution rules include cleaning resolution rules for cleaning data related to entities. ### Claim 15 (depends on 10) The system of claim 10, wherein the resolution rules include requirements for a minimum number of matching features. ### Claim 16 (depends on 10) The system of claim 10, wherein the system is further configured to: identify supplemental data for at least one of the plurality of potential participating entities, wherein identifying the supplemental data further comprises resolving the plurality of potential participating entities between a dataset including the transaction data and at least one dataset including potential participating entity characteristics; and enrich the transaction data with the identified supplemental data, wherein the plurality of relevance scores is determined based further on the enriched transaction data. ### Claim 17 (depends on 10) The system of claim 10, wherein the system is further configured to: generate a notification based on the at least one relevant potential participating entity; and send the notification to a user device.