# US 2019/0378136 A1 · Programmatic approvals of corporate spend and employee expense > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0378136 A1 - Document ID: US20190378136A1 - Status: Published application - Kind: A1 - Application number: 16/436,938 - Filed: 2019-06-11 - Published: 2019-12-12 - Earliest claimed: 2018-06-11 - Assignees: Custodia Inc. - Applicants: Custodia Inc. - Inventors: Elad EFRAIM; Jonathan HELLER; James HACKETT - Web page: https://patentgrep.com/patent/US20190378136A1 ## CPC - G06Q 20/405: {Establishing or using transaction specific rules} - G06N 3/09: Supervised learning - G06N 20/00: Machine learning - G06N 20/20: Ensemble learning - G06Q 10/06312: {Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling} - G06Q 20/2295: {Parent-child type, e.g. where parent has control on child rights} - G06Q 20/4093: {Monitoring of device authentication} - G06N 3/08: Learning methods - G06N 20/10: using kernel methods, e.g. support vector machines [SVM] - 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 - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method of approving expenditures in real-time, comprising receiving an expenditure request initiated by a user associated with an organization for transferring funds of the organization in exchange for one or more products and/or services, identifying request attribute(s) relating to the user, the value, the funds, the product, the service, a time of reception of the expenditure request and/or a geographical location of the user, analyzing scheduling data obtained from one or more online data sources which is indicative of one or more activity attributes of activity(s) scheduled for the user, automatically determining compliance between the request attribute(s) and one or more expenditure rules predefined for the product(s) and/or service(s) with respect to the activity attribute(s) and transmitting a response to the expenditure request according to the determination which includes approval of the expenditure request in case of compliance and rejection in case of incompliance. ## Claims ### Claim 1 A method of approving expenditures in real-time, comprising: using at least one processor for: receiving an expenditure request initiated by a user associated with an organization for transaction of a value of funds of the organization in exchange for at least one product and/or service; identifying at least one request attribute relating to at least one of: the user, the value, the funds, the product, the service, a time of reception of the expenditure request and a geographical location of the user; analyzing scheduling data obtained from at least one online data source, the scheduling data is indicative of at least one activity attribute of at least one activity scheduled for the user; determining automatically compliance between the at least one request attribute and at least one expenditure rule predefined for the at least one product and/or service with respect to the at least one activity attribute; and transmitting a response to the expenditure request according to the determination which includes approval of the expenditure request in case of compliance and rejection in case of incompliance. ### Claim 2 (depends on 1) The method of claim 1, wherein the transaction of the funds value includes at least one of: an electronic card transaction and a cryptocurrency transaction. ### Claim 3 (depends on 1) The method of claim 1, wherein the at least one request attribute relating to the user includes at least one member of a group consisting of: identity of the user, a relation of the user to the organization, an expense budget approved for the user, a rank of the user, a position of the user and a seniority of the user, a seniority of the user, a team the user belongs to and a department the user belongs to. ### Claim 4 (depends on 1) The method of claim 1, wherein the at least one request attribute relating to the value includes at least one member of a group consisting of: the value, a maximal value per product and a maximal value per service. ### Claim 5 (depends on 1) The method of claim 1, wherein the at least one request attribute relating to the funds includes at least one member of a group consisting of: a maximal value of organization funds available for expenditures, a maximal value of organization funds available for expenditures per period of time, a maximal value of funds available per user, a maximal value of funds available per product and a maximal value of funds available per service. ### Claim 6 (depends on 1) The method of claim 1, wherein the at least one request attribute relating to the at least one product includes at least one member of a group consisting of: a type of the product, a category of a vendor of the product and an identity of the vendor. ### Claim 7 (depends on 1) The method of claim 1, wherein the at least one request attribute relating to the at least one service includes at least one member of a group consisting of: a type of the service, a category of a vendor of the service and an identity of the vendor. ### Claim 8 (depends on 1) The method of claim 1, wherein the at least one activity attribute includes at least one member of a group consisting of: a type of the activity, a time of the activity, a location of the activity and an authorization for the user to engage in the activity. ### Claim 9 (depends on 1) The method of claim 1, wherein the online data source is a member of a group consisting of: an electronic calendar, an electronic task list, an electronic itinerary, an email record, a text message record, a voice message record, an automated system of the organization and an online service of the organization. ### Claim 10 (depends on 1) The method of claim 1, wherein the at least one expenditure rule includes at least one member of a group consisting of: a minimal value of funds available in an expense budget of the organization, a maximal funds value approved for a single expenditure, a maximal funds value approved for a plurality of expenditures, a maximal funds value approved per time period, authorization of purchase per product, a maximal funds value approved per product, authorization of purchase per service, a maximal funds value approved per service, a maximal funds value approved per activity, a maximal funds value approved for an event consisting of a plurality of activities and a maximal expense value approved for the user. ### Claim 11 (depends on 1) The method of claim 1, wherein the at least one expenditure rule includes at least one member of a group consisting of: a rule specifically defined for the user and a general rule defined for a group of users associated with the organization. ### Claim 12 (depends on 1) The method of claim 1, wherein the at least one expenditure rule is defined by the organization according to at least one expense policy of the organization defining at least one member of a group consisting of: an expense policy for a user who is part of the organization, an expense policy for a sub-contractor and an expense policy for a customer. ### Claim 13 A system for approving expenditures in real-time, comprising: at least one processor executing a code, the code comprising: code instructions to receive an expenditure request initiated by a user associated with an organization for a transaction of a value of funds of the organization in exchange for at least one product and/or service; code instructions to identify at least one request attribute relating to at least one of: the user, the value, the funds, the product, the service, a time of reception of the expenditure request and a geographical location of the user; code instructions to analyze scheduling data obtained from at least one online data source, the scheduling data is indicative of at least one activity attribute of at least one activity scheduled for the user; code instructions to determine automatically compliance between the at least one request attribute and at least one expenditure rule predefined for the at least one product and/or service with respect to the at least one activity attribute; and code instructions to transmit a response to the expenditure request according to the determination which includes approval of the expenditure request in case of compliance and rejection in case of incompliance. ### Claim 14 A method of approving expenditures in real-time, comprising: using at least one processor for: receiving an expenditure request initiated by a user associated with an organization for a transaction of a value of funds of the organization in exchange for at least one product and/or service; identifying at least one request attribute relating to at least one of: the user, the value, the funds, the product, the service, a time of reception of the expenditure request and a geographical location of the user; applying at least one trained machine learning model to the at least one request attribute, the at least one machine learning model is trained to identify at least one approval pattern by analyzing a plurality of expenditure request evaluation sessions conducted by at least one authorized user of the organization for approving or rejecting respective expenditure requests received from at least one user associated with the organization; and transmitting a response to the expenditure request which includes approval or rejection of the expenditure request determined according to an outcome of the at least one machine learning model. ### Claim 15 A system for approving expenditures in real-time, comprising: at least one processor executing a code, the code comprising: code instructions to receive an expenditure request initiated by a user associated with an organization for a transaction of a value of funds of the organization in exchange for at least one product and/or service; code instructions to identify at least one request attribute relating to at least one of: the user, the value, the funds, the product, the service, a time of reception of the expenditure request and a geographical location of the user; code instructions to apply at least one trained machine learning model to the at least one request attribute, the at least one machine learning model is trained to identify at least one approval pattern by analyzing a plurality of expenditure request evaluation sessions conducted by at least one authorized user of the organization for approving or rejecting respective expenditure requests received from at least one user associated with the organization; and code instructions to transmit a response to the expenditure request which includes approval or rejection of the expenditure request determined according to an outcome of the at least one machine learning model.