# US 12,118,298 B1 · Enabling secure auto-filling of information > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,118,298 B1 - Document ID: US12118298B1 - Status: Granted - Kind: B1 - Application number: 18/206,049 - Filed: 2023-06-05 - Granted: 2024-10-15 - Earliest claimed: 2023-05-22 - Assignees: Uab 360 It - Applicants: Uab 360 It - Inventors: Justinas Reigis - Web page: https://patentgrep.com/patent/US12118298B1 ## CPC - G06F 40/174: Form filling; Merging - G06F 8/75: Structural analysis for program understanding - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract An infrastructure device to analyze a source code associated with a known network element to determine a characteristic associated with an included field portion that is configured to accept a known type of input information; determine a correlation between the determined characteristic and the known type of input information; calculate, based on the correlation, a training signature that uniquely indicates a classification of the field portion as a field portion that accepts the known type of input information; train a machine learning (ML) model based on utilizing the training signature as training data; and transmit, to a user device, a trained ML model to enable the user device to utilize the trained ML model to determine, during an operation period, a given type of input information to be auto-filled in an observed field portion in an observed network element is disclosed. Various other aspects are contemplated. ## Claims ### Claim 1 An infrastructure device, comprising: a memory; and a processor communicatively coupled to the memory, wherein, during a reference period, the memory and the processor being configured to: analyze a source code associated with a known network element to determine a characteristic associated with an included field portion that is configured to accept a known type of input information; determine a correlation between the determined characteristic and the known type of input information; calculate, based at least in part on the correlation, a training signature that uniquely indicates a classification of the field portion as a field portion that accepts the known type of input information; train a machine learning (ML) model based at least in part on utilizing the training signature as training data; and transmit, to a user device, a training ML model, whereby the user device utilizes the trained ML model to determine, during an operation period, a given type of input information to be auto-filled in an observed field portion in an observed network element. ### Claim 2 (depends on 1) The infrastructure device of claim 1, wherein the memory and the processor are configured to analyze source code to determine a boundary of a form area including the field portion. ### Claim 3 (depends on 1) The infrastructure device of claim 1, wherein the memory and the processor are configured to classify a form area, that includes the field portion, as a simple form based at least in part on the field portion being structured to accept the known type of input information as a combination of alphanumerical characters and special characters. ### Claim 4 (depends on 1) The infrastructure device of claim 1, wherein the memory and the processor are configured to classify a form area, that includes the field portion, as a list form based at least in part on the field portion being structured to accept the known type of input information as a selection of an option from a list of options. ### Claim 5 (depends on 1) The infrastructure device of claim 1, wherein the memory and the processor are configured to classify a form area, that includes the field portion, as a complex form based at least in part on the field portion being structured to accept the known type of input information as upload information. ### Claim 6 (depends on 1) The infrastructure device of claim 1, wherein the known network element includes a webpage or a web application available on the Internet. ### Claim 7 (depends on 1) The infrastructure device of claim 1, wherein the known type of input information includes authentication information, contact information, or payment information. ### Claim 8 A method, comprising: analyzing, by an infrastructure device, a source code associated with a known network element to determine a characteristic associated with an included field portion that is configured to accept a known type of input information; determining, by the infrastructure device, a correlation between the determined characteristic and the known type of input information; calculating, by the infrastructure device based at least in part on the correlation, a training signature that uniquely indicates a classification of the field portion as a field portion that accepts the known type of input information; training, by the infrastructure device, a machine learning (ML) model based at least in part on utilizing the training signature as training data; and transmitting, by the infrastructure device to a user device, a trained ML model, whereby the user device utilizes the trained ML model to determine, during an operation period, a given type of input information to be auto-filled in an observed field portion in an observed network element. ### Claim 9 (depends on 8) The method of claim 8, further comprising: analyzing the source code to determine a boundary of reform area including the field portion. ### Claim 10 (depends on 8) The method of claim 8, further comprising: classifying a form area, that includes the field portion, as a simple form based at least in part on the field portion being structured to accept the known type of input information as a combination of alphanumerical characters and special characters. ### Claim 11 (depends on 8) The method of claim 8, further comprising: classifying a form area, that includes the field portion, as a list form based at least in part on the field portion being structured to accept the known type of input information as a selection of an option from a list of options. ### Claim 12 (depends on 8) The method of claim 8, further comprising: classifying a form area, that includes the field portion, as a complex form based at least in part on the field portion being structured to accept the known type of input information as upload information. ### Claim 13 (depends on 8) The method of claim 8, wherein the known network element includes a webpage or a web application available on the Internet. ### Claim 14 (depends on 8) The method of claim 8, wherein the known type of input information includes authentication information, contact information, or payment information. ### Claim 15 A non-transitory computer-readable medium configured to store instructions, which when executed by a processor associated with an infrastructure device, configure the processor to: analyze a source code associated with a known network element to determine a characteristic associated with an included field portion that is configured to accept a known type of input information; determine a correlation between the determined characteristic and the known type of input information; calculate, based at least in part on the correlation, a training signature that uniquely indicates a classification of the field portion as a field portion that accepts the known type of input information; train a machine learning (ML) model based at least in part on utilizing the training signature as training data; and transmit, to a user device, a training ML model, whereby the user device utilizes the trained ML model to determine, during an operation period, a given type of input information to be auto-filled in an observed field portion in an observed network element. ### Claim 16 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the processor is configured to analyze source code to determine a boundary of a form area including the field portion. ### Claim 17 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the processor is configured to classify a form area, that includes the field portion, as a simple form based at least in part on the field portion being structured to accept the known type of input information as a combination of alphanumerical characters and special characters. ### Claim 18 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the processor is configured to classify a form area, that includes the field portion, as a list form based at least in part on the field portion being structured to accept the known type of input information as a selection of an option from a list of options. ### Claim 19 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the processor is configured to classify a form area, that includes the field portion, as a complex form based at least in part on the field portion being structured to accept the known type of input information as upload information. ### Claim 20 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the known network element includes a webpage or a web application available on the Internet.