Patent Application
20180122160
The present disclosure relates generally to a techniques for providing a predictive outcome and more particularly to techniques for generating a predictive outcome in operation of a vehicle.
This section is intended to introduce the reader to various aspects of art, which may be related to various aspects of the present invention that are described and/or claimed below. This discussion is believed to be helpful in providing the reader with background information to facilitate a better understanding. Accordingly, it should be understood that these statements are to be read in this light, and not as admissions of prior art.
There is an emerging trend to automate many of the components of navigational vehicles such as cars and boats. In this regard, computers have been incorporated in such vehicles to increase reliability and improve operational facility. Many of the manual and mechanical components of these vehicles have been replaced by electronic counterparts. This allows for reduction in number of controls and overall simplicity through automation. For example, an electric starter has replaced a clank, and pedals that were physically linked to such systems as the braking mechanism and throttle are also being increasingly replaced by electronic controls.
Recently, more and more of the vehicles functions and safety operations are being automated sometimes by use of an on-board diagnostic (OBD) system or device. Early versions of OBD were simple in that they would only alert a user of a malfunction simply by a light indicator. While the current versions are more sophisticated, they are still limited in how they provide information. In addition, OBD's are tied in to a particular vehicle and therefore any alerts are issued only when that particular vehicle is in use.
Technology advancements have provided many users instant and cheap access to processors such as through the use of mobile devices. This allows the potential of using these processing devices in place or in conjunction with OBDs to improve the safety and reliability of vehicles ahead of time. Consequently, it is desirous to have improvements in the area of vehicle management that can take full advantage of recent processor capability and availability.
A method and apparatus implemented by at least one processor comprising receiving operational information of a vehicle and monitoring driving information of a driver driving the vehicle during a time period. This information is updated based on the operational information of the vehicle being monitored. Finally, a predictive outcome is generated for at least one future event relating to the operation of the vehicle. This is generated based on the initial and new operational history and information and the captured driving habits.
Additional features and advantages are realized through the techniques of the present disclosure. Other embodiments and aspects of the invention are described in detail herein and are considered a part of the claimed invention. For a better understanding of the invention with advantages and features, refer to the description and to the drawings.
The present disclosure will be better understood and illustrated by means of the following embodiment and execution examples, in no way limitative, with reference to the appended figures on which:
Wherever possible, the same reference numerals will be used throughout the figures to refer to the same or like parts.
It is to be understood that the figures and descriptions of the present invention have been simplified to illustrate elements that are relevant for a clear understanding of the present principles, while eliminating, for purposes of clarity, many other elements found in typical digital multimedia content delivery methods and systems. However, because such elements are well known in the art, a detailed discussion of such elements is not provided herein. The disclosure herein is directed to all such variations and modification. In addition, various inventive features are described below that can each be used independently of one another or in combination with other features. Moreover, all statements herein reciting principles, aspects, and embodiments of the disclosure, as well as specific examples thereof, are intended to encompass both structural and functional equivalents thereof. Additionally, it is intended that such equivalents include both currently known equivalents as well as equivalents developed in the future, i.e., any elements developed that perform the same function, regardless of structure.
In one embodiment, each electronic or mobile device 230 can have its own displays, processors and other components as can be appreciated by those skilled in the art. In addition, the server 210 and other components may be directly connected, or connected via the network 250 which may include one or more private networks, the Internet or others.
In one embodiment, the system 100/200 provides support for the management and delivery of over the top content (OTT). As known to those skilled in the art, in broadcasting OTT provides for delivery of audio, video, and other media over the Internet without the involvement of a multiple system operator in the control or distribution of the content. In one embodiment, OTT can also include content from a third party that is delivered to an end-user, by simply transporting IP packets. In another embodiment, text messaging can also be provided. In one embodiment, OTT messaging can also be provided throughout the same system such as one using one or more instant messaging services (as an alternative to text messaging) such as one provided by a mobile network provider. In one embodiment, one or more users may access the OTT service provider via the server and use their companion devices (e.g., the electronic devices such as smartphones, tablets, or PCs) to manage their subscription and purchased content. In addition, a navigation system can be provided as part of vehicle infotainment system 220 or as part of the network 250 or through the server 210. The navigation system, for example can include one or more positioning device(s) such as a global positioning system (GPS).
To aid understanding, examples will be used to explore some situations. In one example, a driver of an electric car notices that the car's range prior to it needing recharging is a range of 30 miles. The problem is that the driver does not know if this range is sufficient for an immediate trip to a particular store 10 miles away. While the mileage to the store round trip is only 20 miles on paper, the driver realizes that the numerical distance is not the only important factor for consideration. Other factors that will affect car performance and fuel usage will include weather conditions, traffic conditions, road conditions, driving habits. In one embodiment, as will be presently discussed, an intelligent management system is provided that gathers all necessary data from the car and from other sources such as the environment. This data or information may include machine-learning algorithms to provide the necessary recommendations to the driver in one embodiment.
In another embodiment, the intelligent management system 300 can be used to improve the driving habits of a driver. Some of these habits may be in advertent and pose safety concerns. For example, a driver that drives too close to a curb or takes a certain corner too fast can become mindful of these concerns. Beyond, the safety concerns the system can be used to also address other convers. In a different example, a driver may like to find out as how to improve his/her driving habits to reduce fuel consumption on a periodical basis, such as on a daily, monthly or yearly time period. Acquiring good driving habits not only improves road safety but also it can help reducing fuel consumption. But most people are unaware of their habits that may be unintentional unless they hire an experts to frequently share and monitors their driving. Therefore, opportunities for improvement are missed. In one embodiment, machine-learning algorithms can be used in conjunction with the present intelligent system to further enable the development of personal assistants.
In addition, in one embodiments the intelligent system 300 can provide an anticipatory report or generate alerts prior to a problem occurring based on the condition of the car, similar experiences of other users, or the driving habits and other things detected and observed. In one embodiment, a periodical report can be generated that provides the most likely problems anticipated for the car for a future time period such as over the next few months. While a precise guess as what may go wrong is difficult, a good estimate can be made of potential upcoming issues based studies of similar cars and car conditions, driving habits, and similar experience with similar cars driven by other users. In this way, an automatic expert system can be built that provides this type or other customized services for one or more users.
Referring back to
In the exemplary embodiment of
In one embodiment, system 300 collects the raw data from a variety of sources such as OBD 305 and aggregates it as shown at 309. External data 308 can be also provided such as weather and road conditions as shown. It will then store the raw data in a database 310 and aggregates and stores it as “refined data” such as in a database as shown at 320. External data aggregators as will be discussed and shown at 315 can also provide aggregate data to the refined database. The term refined data here represents highly structured linked data that can be used for machine-learning operations 330. It can additionally, it can be used for decision making 340 as the basis for the personalized experts and recommenders. However, as can be appreciated by those skilled in the art, in alternate embodiments other similar arrangements can be used.
In another embodiment, the data will be highly structured and grouped so as to serve the purpose of capturing historic descriptions of trajectory segments for drivers while driving by the system 300. In this embodiment, refined data can be described as a linked graph because it aggregates data from multiple sources.
In addition, a refined data set can be generated and described similarly and data and information can be organized in a relational database in pieces such as a collection of trajectory segments. To aid understanding, for a current example, trajectory is defined as the route a driver takes to go from an initial location to a final location (but it can be defined otherwise in alternate embodiments). The route trajectory in this example can be divided into smaller segments. A segment can represent a certain distance in the trajectory (e.g. 2 miles), or it may represent a certain time interval in the trajectory (e.g. first 10 minutes).
Referring back to
To aid understanding, in an example a trajectory segment of 2 miles is provided for a particular user at a given time in
In one embodiment a suite of machine learning algorithms can be used to identify (and continuously learn) patterns from the data. Other methods are used in alternate embodiments. When machine-learning algorithms are used data that includes both supervised and unsupervised methods of collection can be incorporated. Unsupervised methods can be used, for example, to classify drivers that drive during winter conditions into: ‘extremely careful’, ‘careful’, ‘average’, ‘careless’, ‘extremely careless’. Supervised methods can be used, for example, to predict the impact of traffic congestion and weather conditions on fuel consumption for urban and rural settings. Supervised learning methods can include deep learning algorithms where a neural network is trained to identify patterns like driving habits based on collected car data and environment data.
In one embodiment, these machine-learning algorithms can be used for the deployment of classifiers, recommenders, decision engines, and expert systems. These machine-learning algorithms may be able to use data from different but similar drivers (persons) to classify, predict, or find patterns for a single driver. These machine-learning algorithms may be highly dynamic. They may be able to change their outcome (classification, prediction, pattern recognition) based on dynamic changes to the environment. For example, if the system is used to predict energy consumption for a trip from A to B, the system can dynamically compute new estimates in case of sudden nearby accidents.
This application claims the benefit of U.S. Provisional Application No. 62/414,122 dated Oct. 28, 2016.
| Number | Date | Country | |
|---|---|---|---|
| 62414122 | Oct 2016 | US |
