System and method for personalized ground transportation handling and user intent prediction

Abstract

To provide a method and a system that predict travel intent of a user or a destination while the user is traveling along a route.SOLUTION: A method comprises the steps of: (a) receiving data related to a starting geographic location of a route and identification information of a user; (b) acquiring, on the basis of at least in part on data related to the identification information of the user, a trained classifier; (c) using the trained classifier to predict, on the basis of the starting geographic location, trip intent or a destination; and (d) presenting one or more transaction options to the user on an electronic device while the user is traveling in a ground vehicle along at least a portion of the route, the one or more transaction options being identified on the basis of the predicted travel intent or the destination in (c).SELECTED DRAWING: Figure 17

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Provisional Application No. 62 / 969,472, filed February 3, 2020, which is incorporated by reference in its entirety. [Background technology]

[0002] The rapid expansion of computing power in mobile computing devices, such as smartphones, tablet computers, and other portable devices, as well as the growth in the number and sophistication of software program applications (or "apps") for mobile devices, has significantly increased individuals' reliance on the devices, apps, and associated platforms in the area of ​​personal productivity. For example, apps are widely used for scheduling meetings, determining travel routes, selecting transportation modes, and other functions.

[0003] The emergence and acceptance of mobility services, such as consumer adoption of peer-to-peer car sharing and ride hailing services (e.g., Uber® and Lyft®), is driving the combination of transportation and mobile applications. Next generation mobility is related to autonomous and automated vehicles, electric vehicles, and on-demand shared mobility and the use cases they enable. Autonomous vehicles, which can operate without human intervention, are rapidly improving. As such vehicles become autonomous or automated, commercial and transactional opportunities may be presented to passengers or users during transportation. Summary of the Invention [Problem to be solved by the invention]

[0004] Recognized herein is a need for methods and systems for providing products or services for use with vehicles, such as fully autonomous unmanned vehicles. Beneficially, such products or services can facilitate both time and resource savings for vehicle users. Additionally, such products or services can enable businesses offering those products or services to more directly engage with end consumers in a personalized manner within the vehicle transportation environment.

[0005] The present disclosure provides systems and methods for generating personalized, transportation-centric experiences with customized, monetizable driver- and / or passenger-centric services. For example, the systems and methods of the present disclosure may be used or configured to predict travel intent or destination based on limited location data. The personalized, transportation-centric experience may be provided in any transportation mode, such as, for example, autonomous vehicles, ride-hailing services, fleet-based services, microtransit (e.g., fleet-based demand-responsive transportation), rail transportation, and / or ground mass transit vehicles. The travel intent or destination may be generated, predicted, estimated, or determined using machine learning systems with minimal human intervention. The provided systems and methods may enable a set of novel use cases for unmanned / driverless vehicles in industries such as hotels and hospitality, restaurants and dining, tourism and entertainment, healthcare, and service provision. [Means for solving the problem]

[0006] In one aspect, a method is provided for predicting a travel intent or destination of a user while the user is traveling along a route. A user of the provided system / method may be a driver, a service driver such as a driver of a ride-hailing service, a passenger, or any user transported by a vehicle. The method may include (a) receiving data regarding a starting geographic location of a route and a profile of the user, (b) obtaining a trained classifier based at least in part on the data regarding the profile of the user, (c) predicting a travel intent or destination based on the starting geographic location using the trained classifier, and (d) presenting one or more transaction options to the user on an electronic device while the user is traveling in the vehicle along at least a portion of the route, the one or more transaction options being identified based on the predicted travel intent or destination in (c).

[0007] In some embodiments, the starting geographic location is received in the form of Global Positioning System (GPS) data. In some embodiments, the starting geographic location is determined in part using the geographic location of the electronic device, the geographic location being determined by Global Positioning System or signal triangulation. In some embodiments, the starting geographic location is input by a user via a graphical user interface (GUI) on the electronic device.

[0008] In some embodiments, the unsorted geospatial data includes uncorrelated GPS data. In some cases, the one or more training data sets include labeled data obtained using cluster analysis of the plurality of travel data records. In some examples, the method further includes generating the plurality of travel data records by associating the unsorted or uncorrelated GPS data with one or more personal identities. In some examples, the plurality of travel data records are augmented with social data, transportation data, or purchase data of the corresponding personal identities.

[0009] In some embodiments, training the classifier includes creating labels for the segments of the trip based on one or more labeling rules. In some embodiments, the method further includes predicting a mode of transportation for one or more portions of the travel route. In some cases, the mode of transportation includes autonomous vehicles, ride-hailing services, rail transportation, and / or ground mass transit vehicles. In some embodiments, the method further includes updating the trip intent or destination upon receiving new location data during the trip.

[0010] Another aspect of the present disclosure provides a non-transitory computer-readable medium comprising machine-executable code that, when executed by one or more computer processors, performs any of the methods described above or elsewhere herein.

[0011] Another aspect of the present disclosure provides a system for predicting a user's travel intent or destination. The system comprises one or more computer processors and a computer memory coupled thereto. The computer memory includes machine executable code that, when executed by the one or more computer processors, performs any of the methods described above or elsewhere herein. In some embodiments, the one or more processors are configured to execute a set of instructions to (a) receive data regarding a starting geographic location of a travel route and an identity of a user, (b) train a classifier based at least in part on one or more training datasets including (i) the data regarding the identity of the user, and (ii) unsorted geospatial data, (c) predict the travel intent or destination using the classifier trained in (b) based at least in part on the starting geographic location, and (d) present one or more trading options to the user on an electronic device while the user is traveling in a vehicle along at least a portion of the travel route, where the one or more trading options are identified based at least in part on the predicted travel intent or destination in (c).

[0012] In some embodiments, the starting geographic location is received in the form of Global Positioning System (GPS) data. In some embodiments, the starting geographic location is determined in part using the geographic location of the electronic device, the geographic location being determined by Global Positioning System or signal triangulation. In some embodiments, the starting geographic location is input by a user via a graphical user interface (GUI) on the electronic device.

[0013] In some embodiments, the unsorted geospatial data includes uncorrelated GPS data. In some cases, the one or more training data sets include labeled data obtained using cluster analysis of the plurality of travel data records. In some examples, the one or more processors are further configured to generate the plurality of travel data records by associating the unsorted or uncorrelated GPS data with one or more personal identities. In some examples, the plurality of travel data records are augmented with social data, transportation data, or purchase data of the corresponding personal identities. In some embodiments, the one or more processors are configured to train the classifier by creating labels for the segments of the trip based on one or more labeling rules. In some embodiments, the one or more processors are further configured to predict a transportation mode for one or more portions of the travel route. In some cases, the transportation mode includes an autonomous vehicle, a ride-hailing service, rail transportation, and / or a ground mass transit vehicle. In some embodiments, the one or more processors are further configured to update the travel intent or destination upon receiving new location data during the trip.

[0014] Additional aspects and advantages of the present disclosure will become readily apparent to those skilled in the art upon reading the following detailed description, in which only exemplary embodiments of the present disclosure are shown and described. As will be understood, the present disclosure is capable of other and different embodiments, and its several details are capable of modification in various obvious respects, all without departing from the present disclosure. Thus, the drawings and description should be regarded as illustrative in nature, and not as restrictive.

[0015] Incorporation by Reference All publications, patents, and patent applications mentioned in this specification are incorporated by reference herein as if each individual publication, patent, or patent application was specifically and individually indicated to be incorporated by reference. To the extent that the publications and patents or patent applications incorporated by reference conflict with the disclosure contained herein, the present specification is intended to supersede and / or take precedence over such conflicting material.

[0016] The novel features of the invention are set forth with particularity in the appended claims. A better understanding of the features and advantages of the present invention will be obtained by reference to the following detailed description that sets forth illustrative embodiments, in which the principles of the invention are utilized, and the accompanying drawings (herein also referred to as "Figure" and "FIG."). The present invention provides, for example, the following: (Item 1) 1. A method for predicting a user's travel intent or destination, comprising: (a) receiving data relating to a starting geographic location of a travel route and an identity of said user; (b) training a classifier based at least in part on (i) the data regarding the identities of the users, and (ii) one or more training data sets including unsorted geospatial data; (c) using the classifier trained in (b) to predict the travel intent or the destination based at least in part on the starting geographic location; (d) presenting one or more transaction options to the user on an electronic device while the user is traveling in a vehicle along at least a portion of the travel route, the one or more transaction options being identified based at least in part on the travel intent or the destination predicted in (c); A method comprising: (Item 2) 2. The method of claim 1, wherein the starting geographic location is received in the form of Global Positioning System (GPS) data. (Item 3) 2. The method of claim 1, wherein the starting geographic location is determined in part using a geographic location of the electronic device, the geographic location being determined by a global positioning system or signal triangulation. (Item 4) 2. The method of claim 1, wherein the starting geographic location is input by the user via a graphical user interface (GUI) on the electronic device. (Item 5) 2. The method of claim 1, wherein the unsorted geospatial data comprises uncorrelated GPS data. (Item 6) 6. The method of claim 5, wherein the one or more training datasets comprise labeled data obtained using cluster analysis of a plurality of travel data records. (Item 7) 7. The method of claim 6, further comprising generating the plurality of travel data records by associating the unsorted or uncorrelated GPS data with one or more personal identifying information. (Item 8) 7. The method of claim 6, wherein the plurality of travel data records are augmented with social data, transportation data, or purchase data of corresponding personally identifiable information. (Item 9) 2. The method of claim 1, wherein training the classifier comprises creating labels for the journey segments based on one or more labeling rules. (Item 10) 2. The method of claim 1, further comprising predicting a mode of transportation for one or more portions of the travel route. (Item 11) 11. The method of claim 10, wherein the transportation mode includes an autonomous vehicle, a ride-hailing service, rail transportation, and / or a ground mass transit vehicle. (Item 12) 2. The method of claim 1, further comprising updating the travel intent or the destination upon receiving new location data during the trip. (Item 13) 1. A system for predicting a user's travel intent or destination, comprising: a memory for storing a set of instructions; Executing said set of instructions (a) receiving data relating to a starting geographic location of a travel route and an identity of said user; (b) training a classifier based at least in part on (i) the data regarding the identities of the users, and (ii) one or more training data sets including unsorted geospatial data; (c) using the classifier trained in (b), predicting the travel intent or the destination based at least in part on the starting geographic location; (d) presenting one or more transaction options to the user on an electronic device while the user is traveling in a vehicle along at least a portion of the travel route, the one or more transaction options being identified based at least in part on the travel intent or the destination predicted in (c). and one or more processors configured to A system comprising: (Item 14) Item 14. The system of item 13, wherein the starting geographic location is received in the form of Global Positioning System (GPS) data. (Item 15) Item 14. The system of item 13, wherein the starting geographic location is determined in part using a geographic location of the electronic device, the geographic location being determined by a global positioning system or signal triangulation. (Item 16) Item 14. The system of item 13, wherein the starting geographic location is input by the user via a graphical user interface (GUI) on the electronic device. (Item 17) Item 14. The system of item 13, wherein the unsorted geospatial data comprises uncorrelated GPS data. (Item 18) Item 18. The system of item 17, wherein the one or more training datasets comprise labeled data obtained using cluster analysis of a plurality of travel data records. (Item 19) 20. The system of claim 18, wherein the one or more processors are further configured to generate the plurality of travel data records by associating the unsorted or uncorrelated GPS data with one or more personal identifying information. (Item 20) 20. The system of claim 18, wherein the plurality of travel data records are augmented with social data, transportation data, or purchase data of corresponding personally identifiable information. (Item 21) Item 14. The system of item 13, wherein the one or more processors are configured to train the classifier by creating labels for journey segments based on one or more labeling rules. (Item 22) 14. The system of claim 13, wherein the one or more processors are further configured to predict a transportation mode for one or more portions of the travel route. (Item 23) 23. The system of claim 22, wherein the transportation mode includes an autonomous vehicle, a ride-hailing service, rail transportation, and / or a ground mass transit vehicle. (Item 24) Item 14. The system of item 13, wherein the one or more processors are further configured to update the travel intent or the destination upon receiving new position data during the journey. [Brief description of the drawings]

[0017] [Figure 1] FIG. 1 is a schematic diagram illustrating an example of a network environment in which a personal transportation management and intent prediction system may operate, according to some embodiments. [Diagram 2] FIG. 2 illustrates a schematic diagram of a trip identification engine configured to process location data, according to some embodiments. [Diagram 3] FIG. 2 illustrates a point-of-interest (POI) assignment engine of the system, according to some embodiments. [Figure 4] FIG. 2 is a schematic diagram of a device identifier (ID) to personal identity (ID) converter according to some embodiments. [Diagram 5] FIG. 2 illustrates a schematic diagram of a personal data augmentation engine configured to augment personal data records in a personal database, according to some embodiments. [Figure 6] FIG. 2 illustrates a schematic diagram of an automatic travel labeling engine configured to further augment data stored in a personal database augmented with labels related to intent or destination, according to some embodiments. [Figure 7] FIG. 2 is a schematic diagram of a trip selector configured to group multiple trips by travel intent, according to some embodiments. [Figure 8] FIG. 2 illustrates an example of a cluster of trips, according to some embodiments. [Figure 9] FIG. 1 illustrates a labeling rules knowledge base updated with labels created for segments of a journey, according to some embodiments. [Figure 10] FIG. 2 illustrates a schematic diagram of an automatic trip labelling engine configured to label trips with labels obtained using cluster analysis; [Figure 11] FIG. 13 shows an example of an extended personal data record with different additional labels. [Figure 12] FIG. 2 is a schematic diagram of a travel abstractor of the system, according to some embodiments. [Figure 13] FIG. 2 is a schematic diagram illustrating a number of travel classifiers stored in a travel classifier knowledge base. [Figure 14] FIG. 2 illustrates a schematic diagram of a personal segmentation engine configured to segment users. [Figure 15] FIG. 13 is a diagram illustrating an example of a user segment label. [Figure 16] FIG. 1 shows an example of an expanded personal data record with all labels and organized according to user segmentation. [Figure 17] FIG. 2 is a schematic diagram illustrating a novel travel intent predictor of the system, according to some embodiments. [Figure 18] FIG. 1 illustrates an exemplary process for continually generating and updating predictions of travel destinations or intent as new data is collected during a trip. [Figure 19] FIG. 1 illustrates an exemplary process for predicting a user's travel intent. [Figure 20] FIG. 1 illustrates a computer system programmed or configured to implement a ground mobility analysis and destination / intent prediction system. [Figure 21] FIG. 2 illustrates an example of an extended travel dataset processed by the systems and methods described herein. [Figure 22] FIG. 1 illustrates an example of insight data extracted from trips associated with a user. [Figure 23] FIG. 1 illustrates an example of a system including an insight generator and a recommendation engine. [Figure 24] FIG. 2 is a schematic diagram of an insight generator. [Diagram 25] FIG. 2 is a diagram illustrating an example of a transportation ontology. [Figure 26] Examples of personal insight data include: [Figure 27]Examples of personal insight data include: [Figure 28] FIG. 2 illustrates an example of insight data regarding frequent business travelers from a particular geographic location. [Figure 29] FIG. 1 illustrates an example of inferences or insights regarding a cohort or user. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] While various embodiments are shown and described herein, it should be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous variations, changes, and substitutions may be made by those skilled in the art without departing from the present disclosure. It should be understood that various alternatives to the embodiments described herein may be used.

[0019] As used herein, the terms "autonomously controlled," "self-driving," "autonomous," and "unmanned," when used in describing a vehicle, generally refer to a vehicle that can perform all driving tasks by itself and monitor the driving environment along at least a portion of a route. An autonomous vehicle can move from one point to another without the intervention of a human aboard the autonomous vehicle. In some cases, an autonomous vehicle may refer to a vehicle that has capabilities as defined in the National Highway Traffic Safety Administration (NHTSA) definition of automated driving, specifically, Level 4 of the NHTSA definition: "An Automated Driving System (ADS) on a vehicle can perform all driving tasks by itself, monitor its driving environment, and essentially do all of the driving in certain situations. A human does not need to pay attention to those situations," or Level 5 of the NHTSA definition: "An Automated Driving System (ADS) on a vehicle can do all of the driving in all situations. A human occupant is merely a passenger and does not need to be involved in driving." In some cases, an automated vehicle may refer to a vehicle that has capabilities as defined in Level 2 of the NHTSA definition: "The on-board advanced driver assistance system (ADAS) can, under certain circumstances, actually control both steering and braking / acceleration simultaneously. The human driver must maintain full attention at all times ("must monitor the driving environment") and perform the remaining driving task" or Level 3 of the NHTSA definition: "The on-board automated driving system (ADS) can, under certain circumstances, perform all aspects of the driving task by itself. In these circumstances, the human driver must be prepared to take over driving whenever requested by the ADS. In all other circumstances, the human driver performs the driving task."Automated vehicles could also include those with Level 2+ self-driving capabilities, where AI is used to improve on Level 2 ADAS, but consistent driver control is still required.

[0020] As used herein, the term "passenger vehicle" generally refers to a vehicle used for passengers, such as a car or truck, but excluding mass transit vehicles.

[0021] As used herein, the term "mass transit vehicle" generally refers to a multi-passenger vehicle, such as a train or bus, capable of transporting one or more groups of passengers.

[0022] As used herein, the term "trip" generally refers to the total time and / or route(s) taken from a first location to a second location. A trip can include one or more routes. The term "route" generally refers to a set of one or more directions that allow a user to travel from a first location to a second location. A route can have one or more segments. A segment may refer to a portion of the route between a boarding point and a disembarking point.

[0023] As used herein, the term "context information" generally refers to any information associated with a geographic location and / or event. Context information may be derived from information indicative of or related to such geographic location and / or event.

[0024] As used herein, the term "labeled data" or "labeled dataset" generally refers to a pair of datasets used to train a model using supervised learning. The methods provided herein may utilize intents or destinations extracted by cluster analysis ground mobility analysis and destination / intent prediction systems as part of the labeled dataset. Alternatively, the methods provided herein may utilize unpaired training techniques that allow machine learning methods to train and apply existing datasets that may be available to existing systems.

[0025] Whenever the terms "at least," "greater than," or "greater than or equal to" precede a first number in a series of two or more numbers, the terms "at least," "greater than," or "greater than or equal to" apply to each number in the series. For example, 1, 2, or 3 or more equals 1 or more, 2 or more, or 3 or more.

[0026] Whenever the terms "no more than," "less than," or "less than or equal to" precede a first number in a series of two or more numbers, the terms "no more than," "less than," or "less than" apply to each number in the series. For example, 3, 2, or 1 or less is equal to 3 or less, 2 or less, or 1 or less.

[0027] As used herein, the terms "a," "an," and "the" generally refer to singular and plural referents unless the context clearly dictates otherwise.

[0028] The present disclosure provides systems and methods that may be used or configured to perform ground mobility analysis and predict travel destinations / intent of one or more users. The systems and methods of the present disclosure may be used or configured to predict user intent and / or destination based at least in part on location data, such as Global Positioning System (GPS) data. In some cases, the predicted destination may be used to further generate a personalized transportation plan for the user, for example instructing the user (e.g., a driver) to take a specific route to avoid accidents, to process, recommend, and / or present personalized mobility data, routing data, scheduling data, traffic data, and other forms or types of data to the user. In some examples, machine learning techniques may be utilized to predict travel intent or destination. In some examples, machine learning techniques may also be utilized to create a personalized transportation plan that includes predicted intent / destination, trip schedule (e.g., start time, end time), options for transaction-based purchase of goods, services, and content in transit, vehicle type (e.g., autonomous vehicle type such as sedan or van, brand), transportation mode type (e.g., autonomous vehicle, public transportation (such as train, tram, or city bus), shuttle, ride sharing, ride hailing, shared or private travel, walking, biking, electric scooter, taxi, etc.), etc.

[0029] The intent / destination prediction capabilities may be utilized or implemented in driver and / or passenger monetization platforms. Monetization of drivers and / or passengers may include, for example, a) transaction-based purchases of goods, e.g., gasoline, food, coffee, services, parking, and content related to the predicted intent or destination during the journey (e.g., a podcast about an artist's work that is on display at a museum that is the driver's or passenger's destination); b) subscriptions to access content, e.g., annual subscriptions to music streaming services, news services, concierge services, etc.; c) transaction-based purchases of goods, services, and content during the journey and at intermittent stops of the vehicle at fueling stations, restaurants, coffee shops, etc. (e.g., a charging station operator such as an energy company may partner with a coffee shop chain to offer a discount on a coffee drink to passengers who purchase while refueling the vehicle); and d) activities and services related to loyalty points redemption (e.g., automobile manufacturers and mobility service vehicle fleet operators may reward their customers for loyalty using a system similar to that used by airlines and hotel chains where loyalty points may be redeemed in much the same manner as these and other industries use such programs).

[0030] Artificial intelligence, including machine learning algorithms, may be used to train predictive models for predicting travel intent or destination. The machine learning algorithm may be, for example, a neural network. Examples of neural networks that may be used in the embodiments herein include deep neural networks, convolutional neural networks (CNNs), and recurrent neural networks (RNNs). In some cases, models trained by machine learning algorithms may be pre-trained and implemented in user devices or ground mobility analytics and destination / intent prediction systems, and the pre-trained models may undergo continuous re-training, which may include continuous adjustment of the predictive model or components of the predictive model (e.g., classifiers) to adapt to changes in the implementation environment over time (e.g., changes in customer / user data, sensor data, model performance, third-party data, etc.).

[0031] Method and system for ground mobility analysis and destination / intent prediction - Patents.com

[0032] The present disclosure provides systems and methods that may be used or configured to perform ground mobility analysis and predict travel destinations / intent of one or more users. The systems and methods of the present disclosure may be used or configured to predict user intent and / or destination based at least in part on location data. In some embodiments, the location data may include Global Positioning System (GPS) data. The GPS data may be unsorted data and may be uncorrelated with users (e.g., non-identified data). The presented systems and methods may process the unsorted location data and identify travel intent or destination associated with a user. The trips and corresponding users and intents may be used to generate a training data set for training a classifier to determine / infer the trip intent or destination upon deployment. The trip intent and / or destination may be predicted during the trip based on real-time location data or limited location data (e.g., location of trip start location). Alternatively or additionally, the intent and / or destination may be predicted for a new / next trip before the start of the trip.

[0033] A user may pre-register with the system described herein or subscribe to one or more mobility services provided by the system described herein. The user may be a potential requester of mobility services. The user may utilize a user mobile application to receive transaction options provided by the system during the trip. The application may provide the user with one or more transaction services or monetizable driver and / or passenger-centric service options based on a predicted intent or destination. The user may be presented with services or transaction offers related to the predicted intent or destination via the application. The user may access services or execute transactions during the trip via the application. The user may be transported from a first location to a second location while using and / or accessing one or more services including mobility services and user experience services provided by the system during the trip. A user of the provided system / method may be a driver, a service driver such as a ride-hailing service driver, a passenger, or any user transported by a vehicle, as described above.

[0034] FIG. 1 illustrates generally an example of a network environment 100 in which a ground mobility analysis and destination / intent prediction system 101 may operate. The ground mobility analysis and destination / intent prediction system 101 may interact with a plurality of user devices 103 via one or more networks 110. The ground mobility analysis and destination / intent prediction system 101 may be coupled to or part of a personal transportation platform for providing a personalized transportation experience, including providing personalized services / products during travel. In some embodiments, a user device of the plurality of user devices 103 may be a device associated with a user. In some embodiments, a user device may be used by multiple users. For example, a user device may be an embedded device or system inside or coupled to a vehicle. In some embodiments, two or more user devices may be associated with a single user.

[0035] In some embodiments, the ground mobility analysis and destination / intent prediction system 101 may be configured to provide a user interface for the user to view a travel route or interact with one or more transaction options associated with a predicted travel intent / destination during a trip via the user device 103. In some cases, the user interface may comprise a GUI rendered on the user device or on a display in the vehicle. The ground mobility analysis and destination / intent prediction system may be configured to predict a travel intent or destination based on limited location data, such as a trip start location. The travel intent or destination may be generated using a machine learning based model based on limited location data (e.g., GPS data of the trip start location) and / or personal data (e.g., personal ID). The ground mobility analysis and destination / intent prediction system may be configured to predict a travel intent / destination with improved predictive accuracy based on limited real-time data. The travel intent or destination prediction may be dynamically updated and / or improved as the trip progresses. More details regarding intent and destination prediction are described later in this specification.

[0036] In some cases, the ground mobility analysis and destination / intent prediction system may be coupled to a personal transportation planning system, which is configured to generate a personalized transportation plan including a travel route, a schedule of departure and arrival times for one or more segments or one or more stops along the journey, a transportation mode (e.g., transportation type, vehicle type / brand, vehicle configuration, etc.) for the segments of the travel route, and one or more services or monetizable driver- and / or passenger-centric services along the journey (e.g., digital services, trade events, or business activities related to the destination). In some examples, the personalized transportation plan may also include transporting the user through at least one segment using an autonomous vehicle. In some cases, the personalized transportation plan or at least a portion of the personalized transportation plan (e.g., transportation mode) may be dynamically updated based on an updated prediction of the trip intent / destination.

[0037] The personalized transportation plan may be generated based on data related to the user and / or data related to the transaction service. Data related to the user may include personal identification information (ID), user preferences, historical data such as transportation history, or purchase history. Such data may be collected from various data sources such as mobile applications (e.g., mapping applications, navigation applications, emails, text messages, social network apps, personal health apps, etc.), social network software, third party service providers such as mobility service providers (e.g., Uber® and Lyft®), vendors, business entities (e.g., fast food, restaurants, coffee shops, hospitality, convenience stores, fuel stations, theaters, etc.), content providers (e.g., Apple Music®, videos, games, etc.), digital virtual assistants, smart home devices such as Alexa®, interactive voice response (IVR) systems, social media channels and messenger APIs such as Facebook® channels, Twilio SMS channels, Skype® channels, and various other sources. Data related to the transaction service may include a user's refusal or acceptance of data from a previous transaction service or a third-party service provider. A personalized transportation plan may be generated using a machine learning-based model based at least in part on the predicted intent or destination. The input data may be data derived from various data as described above. For example, the input data may include social graphs, purchase graphs, transportation graphs, demographic information, weather data, vendor or service provider catalogs, and various others. The output of the model may be a travel route, a schedule (e.g., departure time, arrival time, etc.) of one or more segments of the travel route, a transportation mode (e.g., vehicle, type of car) for each segment, and one or more transaction options or services during the trip.In some cases, the deal offers may be provided to the user in real time by the system, for example, upon receiving user input indicating a rejection of a service offer, a new deal offer may be selected and provided to the user in real time.

[0038] As used herein, real-time generally refers to a response time of less than a second, less than a tenth of a second, less than a hundredth of a second, less than a millisecond, or less than that, such as by a computer processor. Real-time can also refer to the simultaneous or substantially simultaneous occurrence of a first event relative to the occurrence of a second event.

[0039] The ground mobility analytics and destination / intent prediction system 101 may comprise one or more servers 105 and one or more database systems 107, 109 that may be configured to store or retrieve relevant data, such as processed GPS data, trip data, augmented trip data, augmented personal data records (labeled with additional data related to travel intent, trip type, user segmentation, etc.), user profile data (e.g., personal data such as user preferences, identity, age, gender, contact information, demographic data, ratings, etc.), historical data (e.g., social graph, transportation history, transportation subscription plan data, purchase or transaction history, loyalty programs, and various other data as described elsewhere herein. In some cases, the ground mobility analytics and destination / intent prediction system 101 may include one or more location data services, ontology knowledge bases, map, weather, or traffic application program interfaces. The ground mobility analytics and destination / intent prediction system 101 may obtain data from or communicate (e.g., via one or more networks 110) with one or more external systems or data sources, such as a navigational interface, an API (application programming interface, application ...

[0040] Each of the components (e.g., servers, database systems, user devices, external systems, etc.) may be operatively connected to one another via one or more networks 110 or any type of communication link that enables transmission of data from one component to another. For example, each hardware component may be equipped with a network adapter that enables unidirectional and / or bidirectional communication with one or more networks. For example, servers and database systems may communicate with user devices 103 and / or data sources via one or more networks 110 to transmit and / or receive relevant data.

[0041] A server (e.g., server 105) may include a web server, a mobile application server, an enterprise server, or any other type of computer server, and may be a computer programmed to accept requests (e.g., HTTP, or other protocols capable of initiating data transmission) from computing devices (e.g., user devices, other servers) and provide the requested data to the computing devices. The server may be a single server, or a distributed server across multiple computers or multiple data centers. The server may be of various types, such as, but not limited to, a web server, a news server, a mail server, a message server, an advertisement server, a file server, an application server, an exchange server, a database server, a proxy server, another server suitable for performing the functions or processes described herein, or any combination thereof. Additionally, the server may be a broadcast facility, such as a free-to-air, cable, satellite, and other broadcast facility, for distributing data. The server may be a server in a data network (e.g., a cloud computing network).

[0042] A server may include various computing components such as one or more processors, one or more memory devices that store software instructions executed by the processor(s), and data. A server may have one or more processors and at least one memory for storing program instructions. The processor(s) may be a single or multiple microprocessors, field programmable gate arrays (FPGAs), or digital signal processors (DSPs) that can execute a set of specific instructions. The computer-readable instructions may be stored on a tangible, non-transitory computer-readable medium such as a floppy disk, a hard disk, a CD-ROM (Compact Disk-Read Only Memory), an MO (Magneto-Optical), a DVD-ROM (Digital Versatile Disk-Read Only Memory), a DVD RAM (Digital Versatile Disk-Random Access Memory), or a semiconductor memory. Alternatively, the methods may be implemented in hardware components such as, for example, an ASIC, a special purpose computer, or a general purpose computer, or a combination of hardware and software.

[0043] The one or more databases 107, 109 may utilize any suitable database technique. For example, structured query language (SQL) or “NoSQL” databases may be utilized to store predictive models or algorithms used to predict processed / raw GPS data, user profile data, historical data, travel intent / destinations, maps, or other data. Some of the databases may be implemented using various standard data structures such as arrays, hashes, (linked) lists, structures, structured text files (e.g., XML), tables, JavaScript Object Notation (JSON), NOSQL, and / or similar. Such data structures may be stored in memory and / or in (structured) files. In another alternative, an object-oriented database may be used. An object database may contain several object collections that are grouped and / or linked together by common attributes, which may in turn be related to other object collections by some common attributes. An object-oriented database works similarly to a relational database, except that objects are not just pieces of data, but may have other types of functionality encapsulated within a given object. In some embodiments, the database may include a graph database that uses a graph structure for semantic queries with nodes, edges, and properties to represent and store data. When the database of the present invention is implemented as a data structure, the use of the database of the present invention may be integrated into another component, such as a component of the present invention. The database may also be implemented as a mix of data structures, objects, and relational structures. The database may be consolidated and / or distributed by standard data processing techniques. Parts of the database, such as tables, may be exported and / or imported, thereby distributing and / or consolidating.

[0044] In some embodiments, the ground mobility analysis and destination / intent prediction system 101 may build a database to efficiently deliver data to users. For example, the ground mobility analysis and destination / intent prediction system 101 may provide customized algorithms to extract, transform, and load (ETL) data. In some embodiments, the ground mobility analysis and destination / intent prediction system 101 may build a database using a proprietary database architecture or data structure to provide an efficient database model that is adapted to large databases, is easily scalable, is efficient in queries and data retrieval, or has reduced memory requirements compared to using other data structures.

[0045] One or more databases (e.g., an extended personal database) may be accessed by various applications or entities that may be related to the transaction, although in some circumstances such various applications or entities may not be related to the transaction. In some cases, data stored in the extended personal database may be utilized or accessed by other applications via application programming interfaces (APIs). Data accessed by various applications may include data managed by the system, such as predicted intent / destination, predicted mode of transport, and / or personal data records. Access to the databases may be granted per API level, per data level (e.g., type of data), per application level, or according to other authorization policies.

[0046] The ground mobility analysis and destination / intent prediction system 101 may be implemented anywhere in the network. The ground mobility analysis and destination / intent prediction system 101 may be implemented on one or more servers in the network, one or more databases in the network, one or more electronic devices incorporated in or coupled to a vehicle, or one or more user devices. For example, the ground mobility analysis and destination / intent prediction system 101 may be implemented in a distributed architecture (e.g., multiple devices that collectively function together to implement or perform the ground mobility analysis and destination / intent prediction system 101 or its operations) or in a replicated manner (e.g., multiple devices that each implement or perform the ground mobility analysis and destination / intent prediction system 101 or its operations as a standalone system). The ground mobility analysis and destination / intent prediction system 101 may be implemented using software, hardware, or a combination of software and hardware in one or more of the above-mentioned components in the network environment 100.

[0047] A user device of the plurality of user devices 103 may be an electronic device. A user device may be a computing device configured to perform one or more operations consistent with the disclosed embodiments. Examples of user devices include, but are not limited to, a mobile device, a smart phone / cell phone, a tablet, a personal digital assistant (PDA), a smart wearable device, a smart watch, a laptop or notebook computer, a desktop computer, a media content player, a television set, a video game station / system, a virtual reality system, an augmented reality system, a microphone, or any electronic device configured to enable a user to view a travel route, interact with transaction or service related information, and display other information related to the travel. A user device may be a handheld object. A user device may be portable. A user device may be carried by a human user. In some cases, a user device may be located remotely from a human user, and the user may control the user device using wireless and / or wired communication. A user device may be a computing device that communicates with a wearable device worn by the user. In some cases, the wearable device may be configured to monitor the user's activity, the user's vital signs (e.g., blood pressure and heart rate), or health conditions. In some cases, the user device may be an electronic device coupled to or mounted on a vehicle.

[0048] In some embodiments, the user device may be capable of detecting the location of the device / user. The user device may have one or more sensors on board the device to provide the instantaneous location or location information of the user device. In some embodiments, the instantaneous location information may be provided by sensors such as position sensors (e.g., Global Positioning System (GPS)), inertial sensors (e.g., accelerometers, gyroscopes, inertial measurement units (IMUs)), altitude sensors, attitude sensors (e.g., compasses), pressure sensors (e.g., barometers), field sensors (e.g., magnetometers, electromagnetic sensors), and / or other sensor information (e.g., Wi-Fi data). The location of the user device may be used to identify the origin of a travel route. Additionally or alternatively, the location of a place of interest (e.g., the origin of a trip, a stop during a trip) may be provided by the user via the user device 103, such as by manually inputting the location via a user interface.

[0049] The user device may include a communication unit that may enable communication with one or more other components in the network. In some examples, the communication unit may include a single communication module, or multiple communication modules. In some examples, the user device may be capable of interacting with one or more components in the network environment using a single communication link or multiple different types of communication links. The user device 103 may interact with the ground mobility analysis and destination / intent prediction system 101 by requesting and obtaining the above-mentioned data via the network 110.

[0050] A user device may include one or more processors capable of executing a non-transitory computer-readable medium that may provide instructions for one or more operations consistent with the disclosed embodiments. A user device may include one or more memory storage devices that include a non-transitory computer-readable medium that includes code, logic, or instructions for performing one or more operations.

[0051] In some embodiments, a user may utilize a user device 103 to interact with the ground mobility analysis and destination / intent prediction system 101 through one or more software applications (i.e., client software) executed on and / or accessed by the user device, and the user device 103 and the ground mobility analysis and destination / intent prediction system 101 may form a client-server relationship. For example, the user device 103 may run a dedicated mobile application provided by the ground mobility analysis and destination / intent prediction system 101.

[0052] In some embodiments, the client software (i.e., software application installed on the user device 103) may be available as a downloadable mobile application for various types of mobile devices. Alternatively, the client software may be implemented in one or more combinations of programming and markup languages ​​for execution by various web browsers. For example, the client software may run in a web browser that supports JavaScript and HTML rendering, such as Chrome, Mozilla Firefox, Internet Explorer, Safari, and any other compatible web browser. Various embodiments of the client software application may be compiled for various devices across multiple platforms and optimized for each native platform. In some cases, third-party user interfaces or APIs may be integrated into the mobile application and integrated into the front-end user interface (e.g., within a graphical user interface). The third-party user interface may be hosted by a third-party server. The third-party server may be provided by a range of third-party entities, such as original equipment manufacturers (OEMs), hotels and hospitality, restaurants and dining, tourism and entertainment, service delivery, and various other entities as described elsewhere herein. In some cases, APIs or third party resources (e.g., map service providers, mobility service providers, digital service providers, Starbucks, McDonalds, Ticketmaster, etc.) may be used to provide and execute transactions with users.In some cases, one or more third-party services may be invoked by the ground mobility analysis and destination / intent prediction system 101 and integrated into the user application so that the user can access such services with a familiar front-end user experience. In some cases, one or more of the above-mentioned services may be built-in components of the ground mobility analysis and destination / intent prediction system 101 and may be provided to the user without outsourcing a third-party entity. In some cases, data obtained from third-party service providers may be organized and stored by the ground mobility analysis and destination / intent prediction system 101 to form a vendor / service catalog that may be used to determine trade offers related to the predicted intent for the user while in transit. In some cases, the ground mobility analysis and destination / intent prediction system 101 may provide a graphical user interface (GUI). The GUI may enable the user to access, accept, reject, and select one or more trade offers / options, information, services related to the predicted destination by interacting with graphical elements and viewing information such as travel route and travel schedule while in transit.

[0053] The user device may include a display. The display may be a screen. The display may be a touch screen. Alternatively, the display may not be a touch screen. The display may be a light-emitting diode (LED) screen, an OLED screen, a liquid crystal display (LCD) screen, a plasma screen, or any other type of screen. The display may be configured to display a user interface (UI) or graphical user interface (GUI) rendered via an application (e.g., via an application programming interface (API) running on the user device). For example, the GUI may show graphical elements that allow the user to accept or reject a trade offer and view information related to a predicted intent / destination, travel route, and trade options.

[0054] The network 110 may be a communication pathway between the personal transportation management system 101, the user device 103, and other components of the network. The network may include any combination of local and / or wide area networks using both wireless and / or wired communication systems. For example, the network 110 may include the Internet and cellular networks. In one embodiment, the network 110 uses standard communication technologies and / or protocols. Thus, the network 110 may include links using technologies such as Ethernet, 802.11, worldwide interoperability for microwave access (WiMAX), 2G / 3G / 4G or Long Term Evolution (LTE) mobile communication protocols, infrared (IR) communication technologies, and / or Wi-Fi, and may be wireless, wired, asynchronous transfer mode (ATM), InfiniBand, PCI Express Advanced Switching, or combinations thereof. Other network protocols that may be used on network 110 include multiprotocol label switching (MPLS), transmission control protocol / Internet protocol (TCP / IP), User Datagram Protocol (UDP), hypertext transport protocol (HTTP), simple mail transfer protocol (SMTP), file transfer protocol (FTP), and the like.Data exchanged over the network may be represented using technologies and / or formats, including image data in binary format (e.g., Portable Networks Graphics (PNG)), hypertext markup language (HTML), extensible markup language (XML), and the like. Additionally, all or part of the links may be encrypted using conventional encryption technologies, such as secure sockets layers (SSL), transport layer security (TLS), Internet Protocol security (IPsec), and the like. In alternative embodiments, entities on the network may use custom and / or proprietary data communications technologies in place of or in addition to those listed above. The network may be wireless, wired, or a combination thereof.

[0055] A system for predicting travel destination or intent may comprise multiple components as described and illustrated herein. Figures 2-18 illustrate various components of a system configured to perform functions and operations of collectively predicting destination or intent based on limited location data. In some embodiments, the various components of the system may comprise a trip identification engine, a point of interest (POI) assignment engine, a device ID to personal ID converter, a personal data augmentation engine, an automatic trip labeling engine, a machine learning (ML) clustering system, a personal segmentation engine, a database, and various other components.

[0056] In some embodiments, one or more components of the system (e.g., a trip classifier) ​​may be deployed using unsorted or uncorrelated location data. In some embodiments, personal data records generated and managed by the ground mobility analysis and destination / intent prediction system may include data extracted from the unsorted or uncorrelated location data. In some cases, the unsorted or uncorrelated location data may be processed by a trip identification engine of the system to output multiple individual trips. FIG. 2 illustrates a schematic of a trip identification engine 210 for processing location data, according to some embodiments.

[0057] In some embodiments, the location data 201 may include GPS data. In some cases, the GPS data may include multiple records or data sets that include corresponding GPS information. For example, a table may be maintained with an entry for each record that includes corresponding coordinate data (e.g., latitude, longitude), a timestamp, a name match, and other information such as a device ID. The data entries of the location records may include any suitable data structure. For example, the data structure may include multiple data fields as described above. The data structure may depend on the raw data format or the data source from which the data is obtained.

[0058] The location data 201 may be obtained from one or more data sources. The location data may be obtained using any suitable location-based technology, such as Global Navigation Satellite System (GNSS), cellular triangulation, assisted-GPS (A-GPS), differential global positioning system (DGPS), etc.

[0059] In some embodiments, the location data may include at least geographic location information and an identifier, such as a device ID. Depending on the data source, the identifier may be, for example, an Identifier for Advertising (IDFA) or an Android Advertising ID (AAID).

[0060] The records of location data may be obtained from one or more data sources in a stream or batch. The location data may be time series data, such as space-time point measurements. In some cases, the records or datasets of location data may be unsorted, which may not be streamed or organized in time series. The records or datasets may be associated with multiple trips associated with one or more devices / individuals. In some cases, the records or datasets of location data may not include explicit information about individuals or trips.

[0061] The location data may be processed by the trip identification engine 210 to identify one or more individual trips 221-1, 221-2, 221-3. In some cases, the one or more individual trips may be stored in the trip database 220. A trip may include an ordered sequence of location data records including at least a location data set corresponding to a strip origin and a location data set corresponding to a trip destination. A trip may be identified from the multiple location data sets using any suitable method such that trip information including a trip origin geographic location / start time, a trip destination geographic location / end time, and a device ID with which the trip is associated is identified. One or more unique trips may be identified and associated with a device ID. For example, different trips 221-1, 221-2 at different start / end times may be identified and associated with the same device ID.

[0062] In some embodiments, the geographic locations of the origin and / or destination of a trip may be assigned location context data, such as points of interest (POI). FIG. 3 illustrates a POI assignment engine 303 of the system, according to some embodiments. The POI assignment engine 303 may be coupled to a trip database 301 to assign location context data to at least the origin and destination of each trip. In some cases, location context data may be assigned to one or more intermediate location points (e.g., stops along the way) during a trip. Such location context data may be associated with an identity of a destination, origin, or stop along the trip. Location context data may include, for example, coffee shops, airports, venues, restaurants, stadiums, theaters, dental clinics, etc. The trip database 301 may be the same as the trip database described in FIG. 2.

[0063] In some cases, the POI assignment engine can retrieve one or more trips from the trip database 301 and assign location context data collected using crowdsourcing techniques. For example, the POI assignment engine can be coupled to one or more third-party data sources 307-1, 307-2, 307-3 to collect local business, landmark, and point of interest (POI) data. As an example, the POI data can have a geotag associated with it, and the POI assignment engine can search the POI data to find a good match with the geographic coordinates of the trip origin or destination (e.g., trip start latitude / longitude, trip end latitude / longitude). The POI data of the best match (e.g., trip start POI, trip end POI) can be returned.

[0064] In some cases, one or more third-party data sources 307-1, 307-2, 307-3 may be selected over other data sources to provide POI data. For example, if multiple candidate POIs are associated with the same location or address, the system may select one POI from the multiple candidate POIs based on a selection criterion. In some cases, the selection criterion may be user-specific. For example, a POI may be selected from the multiple candidate POIs based on historical user data (e.g., the user's transportation, purchase, and / or transaction history, the user's social activities, etc.). Alternatively or additionally, the POI data may be a combination of multiple candidate POIs. For example, the POI data may be aggregate information (e.g., street names, landmark references, area names, etc.) regarding all POIs belonging to the same geographic point. In other examples, POIs with unstructured addresses that do not follow any format, such as "suite number, street name, area code," may be supplemented with information of other POIs belonging to the same geographic location.

[0065] In some cases, the location context data may be extended by various other data sources, such as an ontology knowledge base 305. For example, some POIs may be supplemented with additional attributes provided by an ontology knowledge base (e.g., an airport has a terminal number, an airline in a terminal). The ontology knowledge base 305 may be manually deployed by one or more individuals, organizations, imported from an external system or resource, or partially trained using a machine learning system working with users (e.g., extracting transportation terms from natural language text). The travel dataset 310 supplemented with POI data 311, 313 may then be back-populated into the travel database 301.

[0066] As mentioned above, the original / raw location data may not be associated with an individual. In some embodiments, a device ID-to-personal ID converter of the system may be used to correlate the location data with an individual based on the device ID. Figure 4 illustrates a schematic of a device ID-to-personal ID converter 401, according to some embodiments.

[0067] The device ID-personal ID converter 401 may be configured to match one or more device IDs with a personal ID. The device ID-personal ID converter 401 may process the device ID data and correlate the device ID with a personal identifier. The personal identifier 413 may correspond to a personal identity, which may be obtained using an appropriate identity resolution method. The resolution method may encompass different identity attributes and matching algorithms. For example, identity-related data, such as personal identity attributes, social behavior attributes, and social relationship attributes, may be processed by matching algorithms, such as pairwise comparison, transitive closure, and collective clustering, to extract the personal identity. The identity-related data and the device ID may be further processed and associated to form a personal data record 411. An entry 413 of the personal data record may include multiple data fields, such as a personal ID and a device ID. The personal data record 411 may then be stored in the personal database 410. In some cases, the unrecognized device ID 403 may be stored in a separate database.

[0068] In some embodiments, the personal data records may be extended with additional personal data. Figure 5 illustrates a personal data augmentation engine 500 configured to augment the personal data records to form an extended personal database 420. In some embodiments, the personal data augmentation engine may obtain user data (e.g., demographic data, purchase data, social graph, etc.) from multiple data sources and travel data from the travel database 301 to augment the personal data records.

[0069] User data may include personal data about an individual, such as identity, age, gender, contact information, demographic data, etc. Such data may be extracted from other data sources or third-party applications. In some cases, personal data may also include user preferences. User preferences may include both travel preferences and transaction / service preferences. Travel preferences may be derived from one or more of various parameters acquired by the system and used to generate personalized travel routes or to predict transportation modes. For example, a travel preference, such as a "fastest route" preference, may indicate a preference for the quickest route (in time) between two points. A "shortest route" preference may indicate a preference for the shortest (distance) route between two points. A "most fuel-efficient route" preference may indicate a preference for fuel savings. A travel preference may indicate a preference for "effort," which may be particularly relevant for cyclists, walkers, runners, hikers, and swimmers, who may desire large changes in gradient (e.g., hills) or small changes in gradient (e.g., flats). Travel preferences may indicate a preference for routes with various scenic points, greenery over city views, etc., a preference for museums, theaters, playhouses, etc., a preference for routes that include shopping opportunities, a preference for food, a preference by the user to avoid traffic congestion even if a busy route is the quickest route to the destination, and various other preferences. Travel preferences may include the user's preferred mode of transportation (e.g., autonomous vehicles, public transportation (e.g., trains, trams, or city buses), shuttles, ride sharing, ride hailing, shared or private travel, walking, bicycles, electric scooters, taxis, etc.), or in-vehicle user experiences (e.g., access to music, games), etc. Travel preferences may be used to determine travel routes, route segments, transport modes for segments, and / or stops along the travel route (e.g., beautiful views, restaurants, coffee shops, etc.). Such user preferences may be input by the user and / or extracted from other data sources or historical data.

[0070] The purchase data may include any purchases or transactions made by the user during or at the end of the trip. The purchases or transactions may be performed anywhere (e.g., at the destination) that may not be on the vehicle. The purchases or transactions may be in-vehicle or in-cabin transactions.

[0071] In some cases, the social data can depict relationships between various users or vehicles to facilitate in-vehicle sharing, among other things. In some cases, the social data can indicate relationships between the user and other individuals and entities (e.g., family, businesses, friends, etc.), road networks, and potential meeting places within the community. In some cases, the social data can be used to facilitate car sharing, provide recommended rides and locations, and suggest car sharing partners based on common interests and mobility activities. In some cases, the social data can be used to predict or recommend locations and / or schedules for trips. For example, if a user is scheduled to meet with someone with whom the user has a business relationship, the arrival time may be scheduled based on business meeting preferences. The social data can be obtained from social networks (e.g., Facebook, Twitter, LinkedIn, etc.), past communications (e.g., email, SMS, video chat, etc.), common memberships in clubs, common memberships in organizations, common memberships and societies, family relationships, common employers, common workplaces, etc.

[0072] In some cases, additional user data may be used to predict the transportation mode for at least a segment of the trip. For example, the user data may include transportation modes (e.g., autonomous vehicles, public transportation (such as trains, trams, or city buses), shuttles, ride sharing, ride hailing, shared or private travel, walking, biking, electric scooters, taxis, etc.) collected from historical transportation data associated with the user.

[0073] The personal data augmentation engine 500 may be configured to augment personal data records in the personal database 410 with user data (e.g., demographic data, purchase data, social graph, etc.) and travel data obtained from the travel database 301, thereby generating an augmented personal data record. In some embodiments, the travel data and personal data may be integrated based on a device ID. In some embodiments, the personal data augmentation engine 500 may employ a suitable technique to integrate different databases (i.e., a travel database, a personal database). For example, a travel database may be integrated with multiple records in a personal database by incorporating travel data into one of the multiple personal data records based on a matched device ID. The integrated personal data record may then be stored in the augmented personal database 420 as an augmented personal data record. For example, the augmented personal data record may include data fields such as a personal ID, a device ID, and corresponding travel data (e.g., a set of location data tagged with POIs).

[0074] In some embodiments, the extended personal data record may be further updated and extended with additional intent or destination related information. Figure 6 illustrates a schematic of an automated travel labeling engine 600 configured to further extend the data stored in the extended personal database 420 with intent or destination related labels.

[0075] In some embodiments, the destination intent may be an intent inferred from the contextual information associated with the activity or the destination. For example, a supermarket intent may be food shopping, an intent associated with a weekday morning trip may be a daily commute, an intent associated with food, gas, etc. may be shopping, and an intent associated with a sports arena, theater may be entertainment. Such intents may be obtained from a labeling rules knowledge base 610 that stores a list of intent labels. The automatic trip labeling engine 600 may label each trip destination with the intent labels provided by the labeling rules knowledge base 610. The extended personal data record may then be updated by incorporating the destination intents associated with each trip.

[0076] In some embodiments, the expanded personal data records may be processed by a trip selector of the system to group trips by intent. The group of trips may be further processed by a machine learning based clustering system and further clustered by destination. Figure 7 illustrates a trip selector 700 configured to group multiple trips retrieved from the expanded personal database 420 based on intent. For example, trips with the same intent label may be grouped together. Trips with the same intent (e.g., communicate to work) may or may not have the same destination.

[0077] In some cases, the trips grouped by intent are further processed by a machine learning based clustering system. The machine learning based clustering system can perform cluster analysis on the trips to determine natural groupings of trips for a set of intents. For example, trips in the same cluster can have the same destination and can have different origins, stops along the way, or start / end times. In some cases, a set of trips belonging to the same cluster can have one or more characteristics in common in addition to the intent (e.g., origin, mode of transportation, stops along the way). In some cases, one or more common characteristics can be identified and used as a label for the trip or trip segment.

[0078] In some cases, the labels associated with the clusters may be used as part of a training dataset to train the classifier. The labels may be used as part of a training dataset to pair with the travel data. The labels may be created manually by one or more individuals, organizations, or may be imported from an external system or resource. The labels (e.g., personal car, morning trip, direct commute, etc.) may be identified based on natural clustering generated by a machine learning based clustering system, as described above.

[0079] Figure 8 shows an example of a cluster of trips. A set of trips may be included in the "commuting with personal car" cluster. The set of trips may have the same destination and the same intent, but may have different stops along the way.

[0080] In some embodiments, trip segments may be labeled with the augmented data. FIG. 9 shows that the labeling rules knowledge base is updated with labels created for trip segments. The labels may be created manually by one or more individuals, organizations, or imported from an external system or resource. The labels (e.g., personal car, morning trip, direct commute, etc.) may be identified based on natural clustering generated by a machine learning based clustering system, as described above.

[0081] In some embodiments, the labels created for a trip or a segment of a trip may be used to supplement the extended personal data record. FIG. 10 illustrates a schematic of an automatic travel labeling engine 1000 configured to label a trip with a label obtained using cluster analysis as described above. The automatic travel labeling engine 1000 may be the same as the automatic travel labeling engine described in FIG. 6. The automatic travel labeling engine 1000 may automatically label a trip or one or more segments of a trip. In some cases, the labeling may be performed based on labeling rules obtained from the labeling rules knowledge base 610. The labeling rules may be manually deployed by one or more individuals, organizations, imported from an external system or resource, or partially learned using a machine learning system working with a user (e.g., extracting transportation terms from natural language text). The following are exemplary rules stored in the labeling rules knowledge base 610:

[0082] Rule 1: If trip_start_time is after 5:00 AM and trip_end_time is before 12:00 PM, then label="morning_trip" (here, AM and PM are calculated in the local time zone)

[0083] Rule 2: IF trip_type="daily commute" AND intermediate_stop_duration is > 5 minutes and < 20 minutes AND in_trip_POI_type="coffee shop" THEN label="coffee shop on commute"

[0084] The trips extended with the additional labels may be stored in an extended personal database. As shown in Figure 10, the extended personal data record includes additional labels (e.g., morning, direct commute, from home, to office, personal car, etc.) compared to the extended personal data record shown in Figure 6.

[0085] Figure 11 shows an example of an extended personal data record with different additional labels. The two extended personal data records shown in the example have the same intent, one character difference (e.g., direct commute, coffee on commute) and multiple common characteristics (e.g., morning, from home, to office, personal car).

[0086] In some embodiments, the multiple augmented personal data records may be used to train a machine learning based travel abstractor. FIG. 12 illustrates a schematic of a travel abstractor 1200 of the system, according to some embodiments. The travel abstractor may be a classifier trained using the augmented personal data records including additional labels. The travel abstractor may process the travel data and predict the intent associated with the travel destination. Artificial intelligence, such as a machine learning algorithm, may be used to train the travel abstractor. The machine learning algorithm may be, for example, a neural network. Examples of neural networks include deep neural networks, convolutional neural networks (CNNs), and recurrent neural networks (RNNs). In some cases, models trained by machine learning algorithms may be pre-trained and implemented in the system, and the pre-trained models may undergo continuous re-training, including continuous adjustment of the predictive model or components of the predictive model (e.g., classifiers), to adapt to changes in the implementation environment over time (e.g., changes in customer / user data, available labeled data, model performance, third-party data, etc.).

[0087] In some embodiments, the travel classifier may correspond to travel intent. FIG. 13 illustrates a schematic of a plurality of travel classifiers stored in the travel classifier knowledge base 1300. In some cases, training the model may include selecting a model type (e.g., CNN, RNN, gradient boosting classifier, or repressor, etc.), selecting the model's architecture (e.g., number of layers, nodes, ReLU layers, etc.), setting parameters, creating training data (e.g., pairing data, generating input data vectors), and processing the training data to create the model. The trained model may be tested and optimized using test data obtained from the travel classifier knowledge base. The test results may be compared to the performance characteristics to determine whether the predictive model meets the performance requirements. If the performance is good, i.e., the performance requirements are met, the model may be inserted into the travel classifier knowledge base.

[0088] 21 illustrates an example of an augmented trip dataset 2100 processed by the systems and methods as described above. In the illustrated example, the augmented trip dataset 2100 may be generated using at least uncorrelated GPS data. One or more augmented trips may be associated with a device, such as a device ID 2101. Each extended trip may include, for example, a device ID 2101, predicted or extracted information about the origin of the trip such as the POI / name of the origin of the trip (e.g., one stop foods, Galter LifeCenter) 2103, the category of the POI (e.g., grocery store, office building, guy, restaurant) 2105, the origin address 2107, predicted or extracted information about the destination of the trip such as the destination POI (e.g., home, CTA-Harrison, etc.) 2109, the predicted category of the POI (e.g., home, subway station, etc.) 2111, the destination address 2113, the predicted modality of the trip (e.g., car, ride sharing, etc.) 2115, the start time of the trip, and various information. In the illustrated example, an entry / row in the list of extended trip data may be a trip or a segment of a trip.

[0089] In some embodiments, individuals / users may be segmented and organized into segments / clusters. FIG. 14 illustrates a personal segmentation engine 1400 configured to segment individuals in a personal database. Personal segmentation may enable the system to target specific segments of users with offers that may be relevant to those users (e.g., found to be most relevant). Individuals or users may be segmented (or organized into one or more segments) using any suitable segmentation technique. For example, the segmentation technique may be based on fixed segmentation rules 1410. Users may be grouped based on one or more attributes, such as geography (or geographic location), social graph(s), purchasing graph(s), transportation graph(s), demographic information, user preference(s), installed mobile application(s), or other user attribute(s) or characteristic(s) extracted from user profile data, as described above. Users in the same group may share one or more user attributes or characteristics (e.g., age, gender, geographic location, social graph, frequent flyer, frequent food shopper, etc.). An individual may belong to one or more segments. In some cases, segments may be automatically expanded and updated continuously as new data is collected. In some embodiments, new segments may be created as new users (or categories of users) join or subscribe to the system. In some cases, segments may be discrete. In other cases, two or segments may overlap and share a commonality or set of characteristics.

[0090] In some cases, the segmentation technique may be based on patterns extracted from historical data (e.g., user profile data). The patterns may be extracted using machine learning algorithms. In some cases, a set of patterns may be initially generated and an algorithm may be utilized to identify optimal assignments of patterns to segments that are feasible and maximize the desired outcome. The desired outcome may be providing a small number of services or transaction options related to a predicted destination that are sent to appropriately selected customers (e.g., a group of customers) at appropriate times and / or locations such that the selected customers are most likely to accept the service. The initial set of patterns may be generated using any suitable method, such as a decision tree or other pattern identification algorithm. In some cases, the algorithm for identifying optimal assignments of patterns to segments may be a trained machine learning algorithm (e.g., a support vector machine or a neural network).

[0091] In some embodiments, labels may be created for user segments. FIG. 15 shows examples of user segment labels (e.g., likes driving, frequent flyer, likes Italian food, likes sports, etc.). The labels may be created manually by one or more individuals, organizations, or may be imported from an external system or resource. Alternatively or additionally, labels for user segmentation (e.g., likes driving, frequent flyer, likes Italian food, likes sports, etc.) may be identified using machine learning techniques as described above. In some cases, the labels for user segmentation may be used to supplement the expanded personal data records in the expanded personal database.

[0092] FIG. 16 illustrates an exemplary augmented personal data record 1600 with all labels and organized according to user segmentation. The augmented personal data record may be managed, maintained, and updated by the system periodically (e.g., hourly, daily, weekly, etc.) or upon detection of new data being added to the database. The augmented personal data record may be used to form a training data set for continually training the classifier and thereby improving performance. As mentioned above, the training data set may be labeled data including intent or destination obtained using a clustering system.

[0093] The system may be capable of predicting future travel intent without relying on user planning / scheduling data (e.g., calendar, email, etc.). The system may be capable of predicting likely destinations of a current trip based on real-time location data or limited location data. For example, trained classifiers may be deployed to make intent and / or transportation mode predictions based on real-time location data. In some cases, predicted intent and / or transportation mode may be generated based on location data of the trip origin. In some cases, predicted intent and / or transportation mode may be generated during the trip and updated as new location data flows in.

[0094] 17 illustrates a schematic of a novel travel intent predictor 1700 of the system, according to some embodiments. The novel travel intent predictor 1700 can make predictions of travel destinations and / or intents based on real-time location data using one or more trained classifiers downloaded from the travel classifier knowledge base 1300. The novel travel intent predictor 1700 can be coupled to the augmented personal database 420 and the travel classifier knowledge base 1300 to download appropriate classifiers and obtain corresponding augmented personal data records to form an input data set together with the real-time location data. In some cases, upon receiving real-time data such as a personal ID, trip start location (e.g., origin GPS location), updated location data as the trip progresses, or transportation mode, the novel travel intent predictor 1700 can retrieve corresponding extended personal data records from the extended personal database 420 and extract data such as customer segment, trip type, etc. to supplement the real-time data, thereby forming an input data set that is processed by the classifier downloaded from the travel classifier knowledge base 1300.

[0095] FIG. 18 illustrates an exemplary process for continually generating and updating predictions of trip destinations or intents as new data is collected during a trip. As shown in the example, upon receiving origin location data (e.g., trip start location), a new trip intent predictor may initially generate three predicted intents, e.g., a morning trip to work, a trip to the airport, and a morning trip for food shopping. In some cases, as new location data is collected during the trip, the predicted intents may be refined and updated. For example, as the trip progresses and location data is collected indicating a stop at a coffee shop, the predicted intent is updated as food shopping and the predicted destination is a supermarket.

[0096] In some embodiments, the provided system may employ an edge intelligence paradigm in which at least a portion of the data processing may be performed at the edge. For example, data processing and inference may be performed by a novel travel intent predictor deployed on a user device. In some examples, machine learning models or classifiers may be built and trained on the cloud, stored and maintained in the travel classifier knowledge base 1300, and executed on an edge device or edge system (e.g., hardware accelerator). The systems and methods of the present disclosure may provide an efficient and highly scalable intent prediction platform that enables real-time, on-the-spot travel destination and intent prediction.

[0097] The predicted intent or travel destination may be used in various applications. For example, the predicted intent or destination may be used to provide deal offers, services to facilitate travel, offers related to the predicted destination, and various others. For example, the predicted intent or destination may be used to facilitate the user travel to the intended destination by providing information on fast routes, parking, or available transportation modalities. In another example, the predicted intent or destination may be used to provide offers related to the destination, such as discounts on products offered by the predicted destination (e.g., a supermarket) or services near the destination (e.g., a coffee shop at the supermarket). In a further example, the predicted intent or destination may be used to influence the user's original intent to divert the user from the predicted destination (e.g., offers of discounts, services offered by a competing service provider).

[0098] FIG. 19 illustrates an example process 1900 for predicting a user's travel intent. In the illustrated example, location data, such as GPS data, may be acquired and analyzed to create a plurality of individual trips (operation 1901). Real-time location data may be acquired from a user device (e.g., sensors on the user device) or a user application, such as a mapping and navigation application, running on the user device. POIs may be identified and assigned to trip end and / or trip start locations (operation 1903). Personal trip data may be created by associating one or more individual trips with a personal ID (operation 1905). The personal trip data may be augmented with additional user data (operation 1907). The augmented personal trip data is clustered to identify travel intent (operation 1909). One or more trip classifiers are trained using the augmented personal trip data (operation 1911). The trip classifiers may be run to predict travel intent, destination, or transportation mode before a new trip, at the start of a trip, or during a trip (operation 1913). In some cases, one or more offers / services related to the predicted intent / destination may be displayed to the user on a user interface.

[0099] While FIG. 19 illustrates a method according to some embodiments, one skilled in the art would recognize that there are many adaptations to various embodiments. For example, the operations may be performed in any order. Some of the operations may be omitted, some of the operations may be performed simultaneously in one step, some of the operations may be repeated, and some of the operations may include sub-steps of other operations. In some cases, the timing of providing one or more commerce options may be based on the user's current geographic location and / or travel time. The method may also be modified according to other aspects of the disclosure provided herein.

[0100] An individual's travel data may be analyzed to extract various insight information. Such insight information may be extracted based at least in part on the predicted intent of each trip associated with the individual. FIG. 22 illustrates an example of insight data extracted from trips associated with a user. For example, multiple predicted travel intents associated with an individual may be analyzed based on the city or location where the trip occurred. For example, the individual's trips that occurred in the city of residence may be analyzed and a diagram 2210 may be generated showing the number of trips organized by travel intent. Similarly, a diagram 2220 may be provided to show the number of trips in visited cities organized by travel intent. Such a diagram may beneficially provide insight into the individual's mobility patterns in different cities. In some embodiments, a plot showing the modalities of trips associated with the individual may also be generated. For example, a plot 2230 may show the number of trips using different modalities (e.g., private vehicle, rental car, ride hailing, walking, combined, etc.) in the city of residence, and another plot 2240 may show the number of trips using different modalities in visited cities. This insight can beneficially provide measurements of mobility as a function of service effort at a town, city, state, country, or any level. For example, such measurements can be used by automobile manufacturers, vehicle insurance companies, city, state, and national governments, retailers (e.g., supermarkets, home improvement centers, department stores, etc.), hospitality service companies (e.g., hotels, restaurants, coffee shop chains), and / or mobility service companies / organizations to understand how well mobility and other types of transportation-related services are being received by consumers.

[0101] In some embodiments, the personal database may be further extended with predicted insights (e.g., travel preferences) about the individual and / or predicted recommendations based on the insights. FIG. 23 illustrates an example of a system including an insight generator 2305 and a recommendation engine 2307. The traveler database 2301 may be the same as the personal database as described above. For example, the traveler database may store an extended personal data record including user segment labels, trips, demographic characteristics, trip types, and various other data generated by ingesting third party data 2301 and performing trip creation and user segmentation 2303 as described above. The extended personal data record may further include insight data generated by the insight generator 2305 and recommendation engine 2307. The insight generator 2305 and recommendation engine 2307 may include models trained with one or more machine learning algorithms to predict a set of recommendations related to an individual's preferences and transportation services.

[0102] FIG. 24 illustrates an insight generator 2405 in a schematic manner. In some cases, the insight generator 2405 may be trained to predict insights regarding one or more user preferences. The one or more user preferences may relate to personal travel preferences, such as preferred modalities, preferred destination types, accommodation types, or various other preferred services, such as preferred restaurants, price points, brand preferences, and the like. For example, the insight generator 2405 may comprise one or more machine learning based models 2407 and a transportation ontology 2403, process personal data records from a traveler database 2401 to predict user preferences, augment the personal data records with the predicted user preferences, and store the augmented personal data records in a traveler database 2409. FIG. 25 illustrates an example of the transportation ontology 2403. In some cases, the insight generator may utilize one or more machine learning based models or machine learning techniques, as described in user segmentation to predict segmentation labels associated with individuals. In some cases, the insight generator can make inferences based on the segmentation labels, other personal data, and different ontologies to generate additional insights about the user.

[0103] In some cases, the recommendation engine may be trained to generate recommendations based at least in part on the individual's predicted preferences and the individual's predicted travel intent. For example, the recommendation engine may be trained to generate recommendations during a trip (e.g., recommendations for restaurants, modalities for the next trip segment, etc.).

[0104] 26 and 27 show examples of insight data about an individual. The insight data may be extracted from the augmented trips 2601, 2603 associated with the individual. The insight data may be generated by an insight generator and / or a recommendation engine, as described above. For example, the augmented trips associated with the individual in different cities (city of residence 2601, cities visited 2603) may be processed to extract further insights about the individual. For example, based on the predicted intent, modality, or other information in the augmented trip data, insights of user preferences such as preferred modality 2605 (e.g., personal vehicle, ridesharing, walking), preferred hotel price range 2607 (e.g., mid-price range), preferred cuisine 2609, persona 2611 (e.g., active lifestyle traveler, food lover, health and fitness, etc.), preferred restaurant price range 2613, top brands (e.g., Peets, Target, etc.), and various other insights may be inferred. Inferred user preferences may also include POI preferences such as preferred days to dine out 2601, preferred modalities to restaurants in a particular city 2703, 2705 (e.g., ridesharing in Denver, car in Chicago), preferred days for business travel 2707, preferred travel stays, preferred travel restaurants 2711, or preferred travel modalities 2713. In some cases, such insight data may make further predictions 2715 of recommended restaurants, hotels, services offered in a particular city or predicted trip, etc.

[0105] In some cases, insights regarding cohorts of travelers may be provided. Figure 28 shows an example of insight data regarding frequent business travelers from a particular geographic location. The insight data may include frequent business travelers from a particular location 2801, number of trips from a particular location associated with each individual 2805, and device IDs associated with the individual 2803. Such insights may be generated using the methods and systems described above, such as associating uncorrelated trips with an individual and predicting travel intent.

[0106] The provided methods and systems may also be utilized to make inferences regarding trips associated with a cohort of users. FIG. 29 illustrates an example of inferences or insights regarding a cohort or user. For example, a diagram 2601 may be generated showing category frequencies (e.g., restaurants, national parks, gyms) of trips associated with a cohort of users (e.g., travelers in a particular city). In some cases, a distribution diagram may be generated regarding modalities of trips associated with a cohort of users, such as cities of residence 2920 or cities visited 2930.

[0107] Computer Systems The systems, various components of the systems, or processes described herein may be implemented by one or more processors. In some embodiments, the processor may be a processing unit of a computer system. FIG. 20 illustrates a computer system 2001 programmed or configured to implement a ground mobility analysis and intent prediction system. The computer system 2001 may coordinate various aspects of the present disclosure. The computer system 2001 may be a user's electronic device or a computer system located remotely relative to the electronic device. The electronic device may be a mobile electronic device.

[0108] The computer system 2001 includes a central processing unit (CPU, also referred to herein as "processor" and "computer processor") 2005, which may be a single-core or multi-core processor, or multiple processors for parallel processing. The computer system 2001 also includes a memory or memory locations 2010 (e.g., random access memory, read-only memory, flash memory), an electronic storage unit 2015 (e.g., hard disk), a communication interface 2020 (e.g., network adapter) for communicating with one or more other systems, and peripheral devices 2025, such as cache, other memory, data storage, and / or electronic display adapters. The memory 2010, storage unit 2015, interface 2020, and peripheral devices 2025 communicate with the CPU 2005 via a communication bus (solid lines), such as a motherboard. The storage unit 2015 may be a data storage unit (or data repository) for storing data. The computer system 2001 may be operatively coupled to a computer network ("network") 2030 with the aid of a communication interface 2020. The network 2030 may be the Internet, an Internet and / or an extranet, or an intranet and / or an extranet in communication with the Internet. In some cases, the network 2030 is a telecommunications network and / or a data network. The network 2030 may include one or more computer servers, which may enable distributed computing, such as cloud computing. In some cases, the network 2030 may implement a peer-to-peer network, which may enable devices coupled to the computer system 2001 to operate as clients or servers with the aid of the computer system 2001.

[0109] The CPU 2005 can execute a series of machine-readable instructions, which may be embodied in a program or software. The instructions may be stored in a memory location, such as the memory 2010. The instructions may be directed to the CPU 2005, which may then program or configure the CPU to perform the methods of the present disclosure. Examples of operations performed by the CPU 2005 include fetch, decode, execute, and writeback.

[0110] The CPU 2005 may be part of a circuit, such as an integrated circuit. One or more other components of the system 2001 may also be included in the circuit. In some cases, the circuit is an application specific integrated circuit (ASIC).

[0111] The storage unit 2015 may store files such as drivers, libraries, and saved programs. The storage unit 2015 may store user data, such as user preferences and user programs. In some cases, the computer system 2001 may include one or more additional data storage units that are external to the computer system 2001, such as located on a remote server that communicates with the computer system 2001 via an intranet or the Internet.

[0112] The computer system 2001 can communicate with one or more remote computer systems via the network 2030. For example, the computer system 2001 can communicate with a remote computer system of a user (e.g., a user device). Examples of remote computer systems include a personal computer (e.g., a portable PC), a slate or tablet PC (e.g., an Apple® iPad®, a Samsung® Galaxy Tab), a phone, a smartphone (e.g., an Apple® iPhone®, an Android-enabled device, a Blackberry®), or a personal digital assistant. A user can access the computer system 2001 via the network 2030.

[0113] The methods described herein may be implemented by machine (e.g., computer processor) executable code stored in an electronic storage location of the computer system 2001, such as the memory 2010 or the electronic storage unit 2015. The machine executable or machine readable code may be provided in the form of software. In use, the code may be executed by the processor 2005. In some cases, the code may be retrieved from the storage unit 2015 and stored in the memory 2010 for easy access by the processor 2005. In some situations, the electronic storage unit 2015 may be omitted and the machine executable instructions are stored in the memory 2010.

[0114] The code may be pre-compiled and configured for use on a machine having a processor adapted to execute the code, or it may be compiled during run-time. The code may be provided in a programming language that may be selected to allow the code to be executed pre-compiled or as compiled.

[0115] Aspects of the systems and methods provided herein, such as computer system 2001, may be embodied in programming. Various aspects of the technique may be considered "products" or "articles of manufacture," typically in the form of machine (or processor) executable code and / or associated data carried on or embodied in some type of machine-readable medium. The machine-executable code may be stored in an electronic storage unit, such as a memory (e.g., read-only memory, random access memory, flash memory) or a hard disk. A "storage" type medium may include any or all of the tangible memory of a computer, processor, etc., or associated modules that may provide non-transitory storage at any time for software programming, such as various semiconductor memories, tape drives, disk drives, etc. All or part of the software may be communicated over the Internet or various other telecommunications networks. Such communication may, for example, enable loading of the software from one computer or processor to another, for example, from a management server or host computer to a computer platform of an application server. Thus, other types of media that may bear software elements include light waves, electrical waves, and electromagnetic waves, such as those used across physical interfaces between local devices, through wired and optical terrestrial networks, and through various air links. The physical elements that carry such waves, such as wired or wireless links, optical links, etc., may also be considered media that bear the software. As used herein, unless limited to non-transitory, tangible "storage" media, terms such as computer or machine "readable medium" refer to any medium that participates in providing instructions to a processor for execution.

[0116] Thus, a machine-readable medium such as a computer executable code can take many forms, including but not limited to a tangible storage medium, a carrier wave medium, or a physical transmission medium. Non-volatile storage media include optical or magnetic disks, such as any of the storage devices of any computer(s), such as may be used to implement, for example, the databases shown in the drawings. Volatile storage media include dynamic memory, such as the main memory of such a computer platform. Tangible transmission media include coaxial cables, copper wire and optical fibers, including the wiring that comprises a bus within a computer system. Carrier wave transmission media can take the form of electric or electromagnetic signals, or acoustic or light waves, such as those generated during radio frequency (RF) and infrared (IR) data communications. Thus, common forms of computer readable media include, for example, floppy disks, flexible disks, hard disks, magnetic tape, any other magnetic media, CD-ROMs, DVDs or DVD-ROMs, any other optical media, punch cards paper tape, any other physical storage media with a pattern of holes, RAM, ROM, PROMs and EPROMs, FLASH-EPROMs, any other memory chips or cartridges, carrier waves carrying data or instructions, cables or links carrying such carrier waves, or any other medium from which a computer can read programming code and / or data. Many of these forms of computer readable media can be involved in carrying one or more sequences of one or more instructions to a processor for execution.

[0117] The computer system 2001 may include or be in communication with an electronic display 2035 that includes a user interface (UI) 2040 for providing, for example, a graphical user interface as described elsewhere herein. Examples of UIs include, but are not limited to, graphical user interfaces (GUIs) and web-based user interfaces.

[0118] The methods and systems of the present disclosure may be implemented by one or more algorithms. The algorithms may be implemented by software when executed by the central processing unit 2005. For example, the algorithms may be trained models such as a transportation planning engine.

[0119] Although preferred embodiments of the present invention have been illustrated and described herein, it should be apparent to those skilled in the art that such embodiments are provided by way of example only. It is not intended that the present invention be limited by the specific examples provided herein. Although the present invention has been described with reference to the above specification, the description and illustration of the embodiments herein are not meant to be construed in a limiting sense. Numerous variations, changes, and substitutions will now occur to those skilled in the art without departing from the present invention. Furthermore, it should be understood that all aspects of the present invention are not limited to the specific depictions, configurations, or relative proportions described herein which depend upon a variety of conditions and variables. It should be understood that various alternatives to the embodiments of the present invention described herein may be used in carrying out the present invention. It is therefore contemplated that the present invention shall encompass any such alternatives, modifications, variations, or equivalents. It is intended that the following claims define the scope of the present invention, and that methods and structures within the scope of these claims and their equivalents are covered thereby.

Claims

[Claim 1] The invention described in this specification.

Images