# US 12,217,141 B2 · Creating a machine learning policy based on express indicators > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,217,141 B2 - Document ID: US12217141B2 - Status: Granted - Kind: B2 - Application number: 18/428,299 - Filed: 2024-01-31 - Published: 2024-05-23 - Granted: 2025-02-04 - Earliest claimed: 2018-11-19 - Assignees: ZixCorp Systems, Inc. - Applicants: ZixCorp Systems, Inc. - Inventors: Daniel Joseph Potkalesky; Mark Stephen DeMichele - Web page: https://patentgrep.com/patent/US12217141B2 ## CPC - G06N 20/00: Machine learning - G06Q 10/107: Computer-aided management of electronic mailing [e-mailing] - G06F 21/602: {Providing cryptographic facilities or services} - 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 - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract According to some embodiments, a method performed by a classification scanner comprises receiving an electronic message and determining a classification that applies to the electronic message. The classification is determined based on an express indication from a user. The method further comprises providing a machine learning trainer with the electronic message and an identification of the classification that applies to the electronic message. The machine learning trainer is adapted to determine a machine learning policy that associates attributes of the electronic message with the classification. ## Claims ### Claim 1 A method for creating a machine learning policy for a classification type, comprising: receiving at least one electronic message, the at least one electronic message associated with a sender and a recipient; determining at least one classification type that applies to the at least one electronic message, the at least one classification type determined based on at least one or more express indications associated with the message prior to a sending of the at least one electronic message to the recipient, wherein determining the at least one classification type comprises scanning the at least one electronic message based on a plurality of classification types; providing the at least one electronic message and at least one identification of the at least one classification type that applies to the at least one electronic message to a machine learning trainer adapted to determine a machine learning policy that associates attributes of electronic messages with the at least one classification type; receiving a second electronic message, the second electronic message comprising one or more of the attributes that the machine learning policy associates with the at least one classification type; determining, at a classification scanner, that the at least one classification type applies to the second electronic message based on the machine learning policy; and based on the determination, instructing, by the classification scanner, an enforcer to apply the at least one classification, wherein the application of the at least one classification comprises taking an action associated with the second electronic message based on the determination that the at least one classification type applies to the second electronic message, the action associated with the classification type. ### Claim 2 (depends on 1) The method of claim 1, wherein the action comprises enforcing a compliance criteria. ### Claim 3 (depends on 2) The method of claim 2, wherein the compliance criteria is associated with the machine learning policy or the classification type. ### Claim 4 (depends on 1) The method of claim 1, wherein the machine learning policy is applicable to a domain, premise, company, or department. ### Claim 5 (depends on 4) The method of claim 4, wherein the domain, premise, company, or department is associated with the sender or the recipient. ### Claim 6 (depends on 5) The method of claim 5, wherein the action is specific to the domain, premise, company, or department. ### Claim 7 (depends on 6) The method of claim 6, wherein the second electronic message is an attachment to a third electronic message. ### Claim 8 A non-transitory computer readable medium, comprising instructions for: receiving at least one electronic message, the at least one electronic message associated with a sender and a recipient; determining at least one classification type that applies to the at least one electronic message, the at least one classification type determined based on at least one or more express indications associated with the message prior to a sending of the at least one electronic message to the recipient, wherein determining the at least one classification type comprises scanning the at least one electronic message based on a plurality of classification types; providing the at least one electronic message and at least one identification of the at least one classification type that applies to the at least one electronic message to a machine learning trainer adapted to determine a machine learning policy that associates attributes of electronic messages with the at least one classification type; receiving a second electronic message, the second electronic message comprising one or more of the attributes that the machine learning policy associates with the at least one classification type; determining, at a classification scanner, that the at least one classification type applies to the second electronic message based on the machine learning policy; and based on the determination, instructing, by the classification scanner, an enforcer to apply the at least one classification, wherein the application of the at least one classification comprises taking an action associated with the second electronic message based on the determination that the at least one classification type applies to the second electronic message, the action associated with the classification type. ### Claim 9 (depends on 8) The non-transitory computer readable medium of claim 8, wherein the action comprises enforcing a compliance criteria. ### Claim 10 (depends on 9) The non-transitory computer readable medium of claim 9, wherein the compliance criteria is associated with the machine learning policy or the classification type. ### Claim 11 (depends on 8) The non-transitory computer readable medium of claim 8, wherein the machine learning policy is applicable to a domain, premise, company, or department. ### Claim 12 (depends on 11) The non-transitory computer readable medium of claim 11, wherein the domain, premise, company, or department is associated with the sender or the recipient. ### Claim 13 (depends on 12) The non-transitory computer readable medium of claim 12, wherein the action is specific to the domain, premise, company, or department. ### Claim 14 (depends on 13) The non-transitory computer readable medium of claim 13, wherein the second electronic message is an attachment to a third electronic message. ### Claim 15 A system for creating a machine learning policy for a classification type, comprising: a processor; and a non-transitory computer readable medium comprising instructions for: receiving at least one electronic message, the at least one electronic message associated with a sender and a recipient; determining at least one classification type that applies to the at least one electronic message, the at least one classification type determined based on at least one or more express indications associated with the message prior to a sending of the at least one electronic message to the recipient, wherein determining the at least one classification type comprises scanning the at least one electronic message based on a plurality of classification types; providing the at least one electronic message and at least one identification of the at least one classification type that applies to the at least one electronic message to a machine learning trainer adapted to determine a machine learning policy that associates attributes of electronic messages with the at least one classification type; receiving a second electronic message, the second electronic message comprising one or more of the attributes that the machine learning policy associates with the at least one classification type; determining, at a classification scanner, that the at least one classification type applies to the second electronic message based on the machine learning policy; and based on the determination, instructing, by the classification scanner, an enforcer to apply the at least one classification, wherein the application of the at least one classification comprises taking an action associated with the second electronic message based on the determination that the at least one classification type applies to the second electronic message, the action associated with the classification type. ### Claim 16 (depends on 15) The system of claim 15, wherein the action comprises enforcing a compliance criteria. ### Claim 17 (depends on 16) The system of claim 16, wherein the compliance criteria is associated with the machine learning policy or the classification type. ### Claim 18 (depends on 15) The system of claim 15, wherein the machine learning policy is applicable to a domain, premise, company, or department. ### Claim 19 (depends on 18) The system of claim 18, wherein the domain, premise, company, or department is associated with the sender or the recipient. ### Claim 20 (depends on 19) The system of claim 19, wherein the action is specific to the domain, premise, company, or department. ### Claim 21 (depends on 20) The system of claim 20, wherein the second electronic message is an attachment to a third electronic message.