Abstract: Methods and systems for monitoring use, determining risk, and pricing insurance policies for a vehicle having autonomous or semi-autonomous operation features are provided. According to certain aspects, with the insurance customer's permission, operation of an autonomous (or semi-autonomous vehicle) by a vehicle operator may be monitored. Based upon vehicle and/or other data analysis, an identity of the operator may be determined, and operating data regarding the autonomous or semi-autonomous vehicle while the operator at least partially controls the autonomous vehicle may be monitored. A vehicle operator profile that includes information regarding an operating style of the vehicle operator based upon the operating data may be determined. Risk levels associated with operation of the autonomous vehicle based upon the information regarding the vehicle operator's operating style may be determined.

Abstract: The present invention discloses a picture book recognition method applied to an apparatus with a camera, comprising: acquiring an image of the picture book with the camera at a preset acquisition frequency; uploading the image to a server; receiving a first audio link corresponding to the image returned from the server and, if the image is an image of a cover of the picture book, receiving a picture book ID corresponding to the cover image; and connecting to a first audio stream in the server and playing the audio according to the first audio link. The present invention further provides a picture book recognition apparatus, system and electronic device. The picture book recognition method, apparatus, system and electronic device provided by the present invention solve the problem of high error rate in picture book recognition in the prior art.

Abstract: Methods and systems for monitoring use, determining risk, and pricing insurance policies for a vehicle having one or more autonomous or semi-autonomous operation features are provided. According to certain aspects, with the customer's permission, it may be detected by sensors that an occupant of the autonomous or semi-autonomous vehicle is experiencing a medical emergency. A nearby medical facility may be determined based upon the vehicle location and the detected medical emergency. A route from the current vehicle location to the medical facility may be determined, and the autonomous or semi-autonomous vehicle may be automatically directed or routed to the medical facility. A message may also be generated and transmitted to the medical facility to alert them that a person in need of timely medical assistance is on the way. Life and auto insurance discounts may be generated for risk averse customers based upon their vehicles having the emergency response functionality.

Abstract: A computer-implemented method of enhancing safe vehicle operation may include, one or more processors, (1) determining a preferred parking spot for an autonomous or semi-autonomous vehicle; (2) determining a route to the preferred parking spot from a driver drop off point; and (3) causing the autonomous or semi-autonomous vehicle to travel from the driver drop off point to the preferred parking spot following the route controlled by one or more autonomous operation features. The preferred parking spot may be a covered parking spot, a parking spot in a parking structure, or a parking spot in a residential garage. An autonomous vehicle owner may remotely direct the autonomous vehicle to autonomously return to the driver drop off point, such as via their mobile device. Insurance discounts may be provided to autonomous vehicle owners having the self-parking functionality that mitigates or prevents risk of damage to, or theft of, the vehicle.

Abstract: Methods and systems for monitoring use, determining risk, and pricing insurance policies for a vehicle having autonomous or semi-autonomous operation features are provided. In certain aspects, with the customer's permission, a computer-implemented method for updating an autonomous operation feature may be provided. An indication of a software update associated with the autonomous operation feature may be received, and several autonomous or semi-autonomous vehicles having the feature may be identified. The update may be installed within the several vehicles, such as via wireless communication. Also, a change in a risk level associated with the update to the autonomous operation feature may be determined, and an insurance discount may be determined or adjusted.

Abstract: A knowledge base (KB) is generated and used to classify images. The knowledge base includes a number subcategories of a specified category. Instead of obtaining images just based on a category name, structured and unstructured data sources are used to identify subcategories of the category. Subcategories that are determined to not be relevant to the category may be removed. The remaining data may be used to generate the KB. After identifying the relevant subcategories, representative images are obtained from one or more image sources based on the subcategories identified by the KB. The obtained images and the KB are then used to train an image classifier, such as a neural network or some other machine learning mechanism. After training, the neural network might, for example, classify an object within an image of a car, as a car, but also as a particular brand and model type.