Verifying sensor data using embeddings

Abstract

A network system analyzes data samples using embeddings based on, for example, symbolic representations of the data samples or representations in latent dimension space. The network system coordinates providers who provide geographical location-based services to users. The network system may receive data samples from the client device of a provider. For instance, a sensor of the client device captures the data samples during a transportation service along a particular route. To verify that the data samples accurately indicate the location or movement of the provider, the network system can generate a test embedding representing the data samples and compare the test embedding with a reference embedding. The reference embedding is generated based on data samples captured for other similar services, e.g., corresponding to providers who also provided transportation services along the same particular route.

Description

BACKGROUND1. Field of Art[0001]The present disclosure generally relates to verifying sensor data, and more specifically to comparing embeddings that represent sensor data.2. Description of the Related Art[0002]In a system, providers provide geographical location-based services to users, for example, a provider uses a vehicle to transport a user or to deliver an item. Providers have client devices that provide information about the location or movement of the client devices. For example, the provider carries a smartphone client device in the provider's vehicle during services. The smartphone has a global positioning system (GPS) sensor that provides sensor data such as location information to the system. The system may use the sensor data to verify that a provider provided a service. However, providers may try to spoof the system by using their client devices to provide fictitious sensor data and simulate providing the service. If the system cannot differentiate fictitious sensor dat...

AI Technical Summary

Benefits of technology

This approach efficiently verifies sensor data authenticity at scale, reducing computational costs and preventing data spoofing by ensuring accurate representation and comparison of sensor data across varying trip lengths and characteristics.

Problems solved by technology

However, providers may try to spoof the system by using their client devices to provide fictitious sensor data and simulate providing the service.

If the system cannot differentiate fictitious sensor data from proper sensor data, the system will not be able to verify whether a provider actually provided a service.

Additionally, it may also be particularly challenging to verify sensor data at a large scale because processing large amounts of raw sensor data can be computationally expensive.

Images