Inspection and assessment based on mobile edge-computing
Methods, computer-readable media, software, and apparatuses may receive, at a field vehicle, field data from one or more unmanned autonomous vehicles, where the field data may be indicative of an item for assessment. Edge-computing, based on machine learning techniques, may be performed at the field vehicle to identify one or more characteristics of the assessment, and a projected cost may be determined. An estimate may be sent to a consumer. In some aspects, the projected costs may be based on local data related to a geographical location of the item. In another aspect, underwriting tasks may be performed at the field vehicle, and a quote may be sent to a consumer.
1. A method comprising:
receiving, by a computing device at a field vehicle, field data from one or more unmanned autonomous vehicles, wherein the field data is indicative of an item for assessment;
identifying, by the computing device and in real-time based on a machine learning model, one or more characteristics of the assessment;
determining, by the computing device at the field vehicle and in real-time based on the machine learning model, a projected cost for the assessment without communicating with a central server; and
sending, to a user associated with the item, an estimate for the assessment.
2. The method of claim 1 , wherein the identifying the one or more characteristics of the assessment comprises:
analyzing the field data to determine one or more of a type of material, an amount of material, an amount of labor, and an estimated time to complete a repair or a replacement.
3. The method of claim 1 , further comprising:
training the machine learning model to identify the one or more characteristics based on an analysis of the item.
4. The method of claim 1 , wherein the determining the projected cost for the assessment comprises:
determining, based on local data related to a geographical location of the item, a projected cost of material and a projected cost of labor.
5. The method of claim 4 , further comprising:
dynamically updating, by the computing device, the local data.
6. The method of claim 1 , further comprising:
causing, in real-time and based on the one or more characteristics of the assessment, the one or more unmanned autonomous vehicles to collect additional field data.
7. The method of claim 1 , further comprising:
performing, in real-time and by the computing device at the field vehicle, an underwriting task associated with the assessment.
8. The method of claim 7 , further comprising:
training the machine learning model to perform the underwriting task.
9. An apparatus, comprising:
a processor;
a memory unit storing computer-executable instructions, which when executed by the processor, cause the apparatus to:
receive, at a field vehicle, field data from one or more unmanned autonomous vehicles, wherein the field data is indicative of an item for assessment;
identify, in real-time based on a machine learning model, one or more characteristics of the assessment;
determine, at the field vehicle, in real-time based on the machine learning model, a projected cost for the assessment without communicating with a central server; and
send, to a user associated with the item, an estimate for the assessment.
10. The apparatus of claim 9 , wherein the computer-executable instructions, when executed by the processor, further cause the apparatus to identify the one or more characteristics of the assessment by causing the apparatus to:
analyze the field data to determine one or more of a type of material, an amount of material, an amount of labor, and an estimated time to complete a repair or a replacement.
11. The apparatus of claim 9 , wherein the computer-executable instructions, when executed by the processor, cause the apparatus to:
train the machine learning model to identify the one or more characteristics based on an analysis of the item.
12. The apparatus of claim 9 , wherein the computer-executable instructions, when executed by the processor, further cause the apparatus to determine the projected cost for the assessment by causing the apparatus to:
determine, based on local data related to a geographical location of the item, a projected cost of material and a projected cost of labor.
13. The apparatus of claim 12 , wherein the computer-executable instructions, when executed by the processor, cause the apparatus to:
dynamically update the local data.
14. The apparatus of claim 9 , wherein the computer-executable instructions, when executed by the processor, cause the apparatus to:
cause, in real-time and based on the one or more characteristics of the assessment, the one or more unmanned autonomous vehicles to collect additional field data.
15. The apparatus of claim 9 , wherein the computer-executable instructions, when executed by the processor, cause the apparatus to:
perform, in real-time at the field vehicle, an underwriting task associated with the assessment.
16. The apparatus of claim 15 , wherein the computer-executable instructions, when executed by the processor, cause the apparatus to:
train the machine learning model to perform the underwriting task.
17. One or more non-transitory computer-readable media storing instructions that, when executed by a computing device, cause the computing device to:
receive, at a field vehicle, field data from one or more unmanned autonomous vehicles, wherein the field data is indicative of an item for assessment;
identify, in real-time based on a machine learning model, one or more characteristics of the assessment;
determine, at the field vehicle, in real-time based on the machine learning model, a projected cost for the assessment without communicating with a central server; and
send, to a user associated with the item, an estimate for the assessment.
18. The one or more non-transitory computer-readable media of claim 17 , storing further instructions that, when executed by the computing device, cause the computing device to:
analyze the field data to determine one or more of a type of material, an amount of material, an amount of labor, and an estimated time to complete a repair or a replacement.
19. The one or more non-transitory computer-readable media of claim 17 , storing further instructions that, when executed by the computing device, cause the computing device to:
determine, for the one or more characteristics and based on the machine learning model, a projected cost for the assessment; and
wherein the estimate is based on the projected cost.
20. The one or more non-transitory computer-readable media of claim 17 , storing further instructions that, when executed by the computing device, cause the computing device to:
perform, in real-time at the field vehicle, an underwriting task associated with the assessment.