Machine learning labeling platform for enabling automatic authorization of human work assistance
AssigneeState Farm Mutual Automobile Insurance Company
InventorMatthew Aaron Mifflin
Life of this patent
Estimating the term…
Abstract
Systems and methods for dynamically assessing property damage by determining whether and how to leverage a crowdsourcing marketplace are provided. According to certain aspects, a server computer may receive a set of media depicting property damage, and may analyze the set of media using a machine learning model to estimate a type and amount of the property damage. The server computer may also determine whether and how to leverage a set of additional individuals to provide a set of assessments for the property damage and, based on the set of assessments provided by the set of additional individuals, the server computer may automatically facilitate a work order request to address the property damage.
Claims20
A computer-implemented method for dynamically assessing property damage, the method comprising:
- receiving, by a processor and from an electronic device, image data depicting a property;
- executing, by the processor, a machine learning model to determine a first damage assessment of the property based on the image data, the first damage assessment being characterized by a confidence level;
- determining, by the processor, that the confidence level is below a threshold level;
- based on determining that the confidence level is below the threshold, transmitting, by the processor, to a computing device via a network, the image data, and a request executable by the computing device, the request causing the computing device to:
- generate a second damage assessment, and
- provide the second damage assessment to the processor via the network;
- updating, by the processor, the machine learning model using the second damage assessment;
- and
- transmitting, by the processor, the second damage assessment to a service provider.
A system for dynamically assessing property damage, comprising:
- a non-transitory computer-readable memory storing a set of instructions;
- and
- a processor configured to execute the set of instructions to cause the processor to perform actions including:
- receiving, from an electronic device, image data depicting a property;
- executing a machine learning model to determine a first damage assessment of the property based on the image data, the first damage assessment being characterized by a confidence level;
- determining that the confidence level is below a threshold level;
- based on determining that the confidence level is below the threshold, transmitting, to a computing device via a network, the image data, and a request executable by the computing device, the request causing the computing device to:
- generate a second damage assessment, the second damage assessment, and
- provide the second damage assessment to the processor via the network;
- updating the machine learning model using the second damage assessment;
- and
- transmitting the second damage assessment to a service provider.
A non-transitory computer-readable storage medium storing computer-readable instructions for dynamically assessing property damage, that when executed by a processor, cause the processor to perform actions comprising:
- receiving, from an electronic device, image data depicting a property;
- executing a machine learning model to determine a first damage assessment of the property based on the image data, the first damage assessment being characterized by a confidence level;
- determining that the confidence level is below a threshold level;
- based on determining that the confidence level is below the threshold, transmitting, to a computing device via a network, the image data, and a request executable by the computing device, the request causing the computing device to:
- generate a second damage assessment, the second damage assessment, and
- provide the second damage assessment to the processor via the network;
- updating the machine learning model using the second damage assessment;
- and
- transmitting the second damage assessment to a service provider.
Dependencies are inferred from the claim text.