# US 12,118,621 B2 · Hardline threshold softening > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,118,621 B2 - Document ID: US12118621B2 - Status: Granted - Kind: B2 - Application number: 17/408,797 - Filed: 2021-08-23 - Published: 2023-03-09 - Granted: 2024-10-15 - Earliest claimed: 2021-08-23 - Assignees: Paypal, Inc. - Applicants: PayPal, Inc. - Inventors: Itay Margolin - Web page: https://patentgrep.com/patent/US12118621B2 ## CPC - G06Q 40/12: Accounting - 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 ## Abstract A first schema accessed is associated with a plurality of entities that are participants of an electronic system. Each entity has a corresponding attribute. Each of a first subset of the entities has a respective attribute value below a threshold. Each of a second subset of the entities has a respective attribute value above the threshold. According to the first schema, it is determined that data and/or transactions associated with the first and second subsets of the entities are processed using a first and a second model, respectively. A second schema is generated by softening the predefined threshold such that according to the second schema, data and/or transactions associated with the first subset of the entities and data and/or transactions associated with the second subset of the entities are each processed using both the first model and the second model. The second schema is implemented in the electronic system. ## Claims ### Claim 1 A method, comprising: accessing, by one or more hardware processors of a service provider, a first schema, the first schema being associated with a plurality of entities that are participants of an electronic system, each of the plurality of entities having a corresponding attribute, wherein each of a first subset of the plurality of entities has a respective value of the attribute that is below a predefined threshold, and wherein each of a second subset of the plurality of entities has a respective value of the attribute that is above the predefined threshold; determining, by the one or more hardware processors of the service provider according to the first schema, that data and/or transactions associated with the first subset of the entities are processed using a first model and no other models, and data and/or transactions associated with the second subset of the entities are processed using a second model but no other models, wherein the second model is different from the first model; generating, by the one or more hardware processors of the service provider, a second schema at least in part by softening the predefined threshold such that according to the second schema, data and/or transactions associated with a predetermined majority of the first subset of the entities and data and/or transactions associated with a predetermined majority of the second subset of the entities are each processed using both the first model and the second model; and implementing, by the one or more hardware processors of the service provider, the second schema in the electronic system. ### Claim 2 (depends on 1) The method of claim 1, wherein: the first schema is implemented in the electronic system before generating the second schema; and the implementing the second schema comprises replacing the first schema in the electronic system with the second schema. ### Claim 3 (depends on 1) The method of claim 1, further comprising evaluating, in response to implementing the second schema, an entity of the plurality of the entities based on the second schema, and wherein the evaluating the entity further comprises predicting a performance of the entity or deciding to approve or deny a request from the entity. ### Claim 4 (depends on 1) The method of claim 1, wherein the electronic system comprises an electronic commerce platform, an electronic social media network, a digital streaming service, or a healthcare marketplace. ### Claim 5 (depends on 1) The method of claim 1, wherein the softening is performed at least in part based on a sigmoid function. ### Claim 6 (depends on 1) The method of claim 1, wherein the softening the predefined threshold comprises generating a curve that approximates the predefined threshold. ### Claim 7 (depends on 6) The method of claim 6, wherein the softening the predefined threshold further comprises calculating a slope of the curve using an optimization algorithm. ### Claim 8 (depends on 1) The method of claim 1, wherein: the softening the predefined threshold comprises generating a plurality of progressive thresholds that each have a corresponding first model involvement score and a corresponding second model involvement score; the first model involvement score indicates a weight of the first model under the second schema; the second model involvement score indicates a weight of the second model under the second schema; and the predefined threshold is greater than a first subset of the progressive thresholds and less than a second subset of the progressive thresholds. ### Claim 9 (depends on 8) The method of claim 8, wherein the generating the second schema further comprises: determining that, for the progressive thresholds below a first progressive threshold, the first model involvement score is negligible compared to the second model involvement score; and determining that, for the progressive thresholds above a second progressive threshold, the second model involvement score is negligible compared to the first model involvement score; wherein according to the second schema, only data and/or transactions associated with entities whose corresponding value of the attribute is between the first progressive threshold and the second progressive threshold are processed using both the first model and the second model. ### Claim 10 (depends on 1) The method of claim 1, wherein the attribute comprises a multi-dimensional attribute based on at least two different variables. ### Claim 11 A system, comprising: a non-transitory memory; and one or more hardware processors coupled to the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform operations comprising: accessing a first schema, the first schema being associated with a plurality of entities that are participants of an electronic system, each of the plurality of entities having a corresponding attribute, wherein each of a first subset of the plurality of entities has a respective value of the attribute that is below a predefined threshold, and wherein each of a second subset of the plurality of entities has a respective value of the attribute that is above the predefined threshold; determining, according to the first schema, that data and/or transactions associated with the first subset of the entities are processed using a first model but no other models, and data and/or transactions associated with the second subset of the entities are processed using a second model but no other models, wherein the second model is different from the first model; generating a second schema at least in part by softening the predefined threshold such that according to the second schema, data and/or transactions associated with a predetermined majority of the first subset of the entities and data and/or transactions associated with a predetermined majority of the second subset of the entities are each processed using both the first model and the second model; and implementing the second schema in the electronic system. ### Claim 12 (depends on 11) The system of claim 11, wherein the operations further comprise evaluating an entity of the plurality of the entities based on the second schema, and wherein the evaluating the entity further comprises predicting a performance of the entity or deciding to approve or deny a request from the entity. ### Claim 13 (depends on 11) The system of claim 11, wherein the softening the predefined threshold comprises: generating a curve that approximates the predefined threshold; and calculating a slope of the curve using an optimization algorithm. ### Claim 14 (depends on 11) The system of claim 11, wherein: the softening the predefined threshold comprises generating a plurality of progressive thresholds that each have a corresponding first model involvement score and a corresponding second model involvement score; the first model involvement score indicates a weight of the first model under the second schema; the second model involvement score indicates a weight of the second model under the second schema; and the predefined threshold is greater than a first subset of the progressive thresholds and less than a second subset of the progressive thresholds. ### Claim 15 (depends on 11) The system of claim 11, wherein the attribute comprises a multi-dimensional attribute based on at least two different variables. ### Claim 16 A non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a machine to perform operations comprising: accessing a first schema, the first schema being associated with a plurality of entities that are participants of an electronic system, each of the plurality of entities having a corresponding attribute, wherein each of a first subset of the plurality of entities has a respective value of the attribute that is below a predefined threshold, and wherein each of a second subset of the plurality of entities has a respective value of the attribute that is above the predefined threshold; determining, according to the first schema, that data and/or transactions associated with the first subset of the entities are processed exclusively using a first model, and data and/or transactions associated with the second subset of the entities are processed exclusively using a second model different from the first model; generating a second schema at least in part by softening the predefined threshold such that according to the second schema, data and/or transactions associated with a predetermined majority of the first subset of the entities and data and/or transactions associated with a predetermined majority of the second subset of the entities are each processed using both the first model and the second model; and implementing the second schema in the electronic system. ### Claim 17 (depends on 16) The non-transitory machine-readable medium of claim 16, wherein the operations further comprise evaluating an entity of the plurality of the entities based on the second schema, and wherein the evaluating the entity further comprises predicting a performance of the entity or deciding to approve or deny a request from the entity. ### Claim 18 (depends on 1) The method of claim 1, wherein the second schema comprises a sliding scale of contributions from both the first model and the second model. ### Claim 19 (depends on 16) The non-transitory machine-readable medium of claim 16, wherein the softening the predefined threshold comprises generating a curve that approximates the predefined threshold. ### Claim 20 (depends on 16) The non-transitory machine-readable medium of claim 16, wherein: the softening the predefined threshold comprises generating a plurality of progressive thresholds that each have a corresponding first model involvement score and a corresponding second model involvement score; the first model involvement score indicates a weight of the first model under the second schema; the second model involvement score indicates a weight of the second model under the second schema; and the predefined threshold is greater than a first subset of the progressive thresholds and less than a second subset of the progressive thresholds.