Intelligent on-demand management of ride-sharing in transportation systems
Through the distributed auction algorithm and transportation service request distribution model, the riding sharing requests are allocated in the transportation system, which solves the problems of privacy protection, fairness and high service rates in the transportation system, and realizes efficient and fair riding sharing service management. Reduces traffic congestion and resource waste.
Patent Information
- Application Number
- CN202010385104.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2019-06-03
- Filing Date
- 2020-05-09
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2040-05-09
AI Technical Summary
It is difficult for the prior art to effectively manage ride-sharing services in transportation systems, especially to find a balance between privacy protection, fairness and high service rates, while avoiding traffic congestion and resource waste.
Through distributed auction algorithms and transportation service request distribution model, ride sharing requests are intelligently distributed among multiple transportation service providers, protecting the information of each transportation service provider, optimizing vehicle allocation, ensuring fairness and privacy protection, At the same time, limit the number of vehicles, use machine learning to predict demand and adjust the number of vehicles.
It realizes efficient, fair and privacy-protected ride sharing service management in the transportation system, optimizes vehicle allocation, reduces traffic congestion and resource waste, and improves service quality and efficiency.
Smart Images

Figure CN112036676B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates generally to computing systems and, more particularly, to various embodiments for intelligent on-demand management of ride sharing in a transportation system by a processor. Background Art
[0002] In today's society, consumers, business people, educators, and others are increasingly using various computing network systems in a variety of environments. The advent of computers and networking technology has improved the quality of life and enhanced daily activities. Computing systems can include the Internet of Things (IoT), which is the interconnection of computing devices distributed around the world using existing Internet infrastructure. IoT devices can be embedded in a variety of physical devices or products.
[0003] As the great strides and advances in technology come to fruition, these technological advances can play a role in everyday life. For example, the vast amounts of data available through computing and networking technologies can then help improve transportation. Summary of the invention
[0004] Various embodiments are provided for intelligent on-demand management of ride-sharing in a transportation system by a processor. In one embodiment, by way of example only, a method is provided for providing intelligent on-demand management of ride-sharing in a transportation system by a processor. Transportation service requests may be distributed among multiple transportation service providers based on one or more transportation service request distribution models and various parameters and preferences for each user. The transportation service request distribution model may protect information related to each transportation service provider and suggest a selected order for distributing multiple transportation service requests. BRIEF DESCRIPTION OF THE DRAWINGS
[0005] In order to readily understand the advantages of the present invention, the invention briefly described above will be described in more detail by reference to specific embodiments shown in the accompanying drawings. It is to be understood that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of the scope of the invention. The invention will be described and explained with additional specificity and detail through the use of the accompanying drawings, in which:
[0006] Figure 1 is a block diagram depicting an exemplary computing node according to an embodiment of the present invention;
[0007] Figure 2 is an additional block diagram depicting an exemplary cloud computing environment according to an embodiment of the present invention;
[0008] Figure 3 is an additional block diagram depicting the abstract model layers according to an embodiment of the present invention;
[0009] Figure 4 is a diagram depicting various user hardware and computing components that function in accordance with aspects of the present invention;
[0010] Figure 5 is a block diagram of providing on-demand management of ride sharing in a transportation system according to aspects of the present invention;
[0011] Figure 6 is a block flow diagram of providing on-demand management of ride sharing in a transportation system according to aspects of the present invention;
[0012] Figure 7 is a flow chart of an additional exemplary method for protecting the privacy of an entity in a transportation system by a processor in which aspects of the present invention may be implemented; and
[0013] Figure 8 is a flow chart of an additional exemplary method for protecting the privacy of entities in a transportation system by a processor in which aspects of the present invention may be implemented. DETAILED DESCRIPTION
[0014] Computing systems may include large-scale computing known as "cloud computing," in which resources may interact and / or be accessed via a communication system, such as a computer network. Resources may be services running on one or more computing devices, such as servers, and / or simulations and / or emulations of software renderings of computing devices, storage devices, applications, and / or other computer-related devices. For example, multiple servers may communicate and / or share information that may expand and / or contract across servers, depending on the amount of processing power, storage space, and / or other computing resources required to complete a requested task. The word "cloud" implies the cloud-shaped appearance of a diagram of interconnections between computing devices, computer networks, and / or other computer-related devices that interact in such an arrangement.
[0015] In addition, the Internet of Things (IoT) is an emerging concept of computing devices that can be embedded in objects (especially appliances) and connected through a network. An IoT network can include one or more IoT devices or "smart devices", which are physical objects such as appliances with computing devices embedded in them. Many of these objects are independently operable devices, but they can also be paired with a control system or alternatively a distributed control system such as one running on a cloud computing environment.
[0016] The massive increase in the use of IoT appliances in computing systems (especially in cloud computing environments) in various environments provides users with a variety of beneficial uses. Various IoT appliances can be used for personal purposes, such as traveling or exercising, while IoT appliances can also be used in various types of vehicles or navigation systems for travel purposes. For example, many individuals use taxis or other ride-sharing services to arrange commuting travel from one place to another. Therefore, one or more IoT devices can be used to order transportation services (e.g., vehicle-for-hire and / or ride-sharing services) to help travel and quickly move to one or more desired destinations.
[0017] A rental vehicle (e.g., an automobile) is a vehicle driven by a professional driver or a self-driving vehicle (e.g., an autonomous vehicle), whose job is to pick up one or more passengers and transport them to the desired destination provided by the passenger. A common example of a rental vehicle is a taxi, also known as a "taxi". In some areas, a distinction is made between taxis and car services, where taxis are allowed to pick up passengers who call a taxi while the taxi is driving, and for car services, the pick-up location and time are pre-arranged. However, in most other areas, regardless of whether the passenger pick-up is pre-arranged or called, the car that acts as a rental vehicle is referred to as a taxi. A ride-sharing service may be a point-to-point ride-sharing service, or may be a ride-sharing service that arranges a shared ride, a carpool, or a car-sharing service. On the one hand, a vehicle may be a car, a bicycle, a motorcycle, a boat, a ship, a train, an airplane / aircraft, an autonomous vehicle, an off-road vehicle, a truck, etc.
[0018] As ride-sharing companies increase in number and size, and compete for the same customer base, there is a growing need to manage competition in an on-demand but distributed, private, and fair manner. While centralized coordination may be needed to allocate vehicles to users in an optimal manner (e.g., by service level), some entities (e.g., vehicles for rental service businesses) may not want to disclose any proprietary information about their offering policies or vehicle identifiers ("IDs") or locations. In addition, it is necessary to limit the number of operating vehicles per company in an optimized and fair manner. If resources are not limited, traffic congestion, pollution, design, and management costs may grow uncontrollably.
[0019] Thus, the present invention provides a system for intelligently ensuring high service rates of ride-sharing requests in a privacy- and fairness-focused manner while limiting the number of vehicles required. In one aspect, the mechanisms of the illustrated embodiments provide intelligent on-demand management of ride-sharing in a transportation system. Transportation service requests can be distributed via a transportation system agent (e.g., a ride-sharing agent) among multiple transportation service providers based on one or more transportation service request distribution models and various parameters and preferences for each user. The transportation service request distribution model can protect information related to each transportation service provider and suggest a selected order for distributing multiple transportation service requests.
[0020] In another aspect, the present invention provides a solution to the vehicle-customer assignment problem (e.g., linear assignment problem "LAP") by batching ride-sharing requests (e.g., transportation service requests) within a selected time period (e.g., during a defined time window) and in a distributed / selected order, and optimally assigning one or more ride-sharing requests to one or more available vehicles. A distributed auction operation (or distributed auction algorithm) may be applied to ensure that the ride-sharing agent of the present invention is not required to obtain complete / full access to entity proprietary information. The distributed auction operation may require each transportation service provider to only communicate a bid for its vehicle, which discloses the two best prices for customers that have not yet been assigned. The distributed auction operation does not require the company to fully disclose proprietary information to the agent. Therefore, instead of obtaining all information about the ride-sharing service provider fleet and its pricing strategy, the ride-sharing agent sends a request to the ride-sharing service and obtains the top k bids. That is, the ride-sharing agent only needs the k best / optimal costs (where k is equal to or greater than 2, such as, for example, k≥2), or only needs the k best / optimal cost differences in each iteration of the distributed auction operation. In one aspect, the present invention provides a degree of fairness in the real-time available number of operating vehicles for each entity (e.g., the selected number of available transportation service providers for each company), which can be used to avoid aggressive or undesirable competition between entities for market share.
[0021] In one aspect, a distributed auction operation (or distributed auction algorithm) may be applied as follows. In a distributed implementation of the auction algorithm for allocation, the transportation service provider sends each bid for each dedicated vehicle to the ride-sharing agent. The distributed auction operation runs iteratively, and unallocated vehicles must increase their bids, which results in lower profits for the transportation service provider. After a finite number of steps, the vehicles reach a situation where no vehicle has an incentive to increase its bid. Finally, the agent communicates the vehicle allocation for the request to the transportation service provider.
[0022] On the other hand, the present invention provides a method of managing ride sharing on demand using a transportation agent that communicates with multiple ride sharing service providers in a distributed, optimal, privacy-focused manner while also providing a degree of fairness. The mechanism of the illustrated embodiment may include a transportation agent connected to multiple ride sharing services (e.g., transportation service providers). The transportation agent may receive real-time user transportation requests for transportation services (e.g., ride sharing). The transportation agent processes the user's transportation request in order to optimize the allocation of vehicles of the shared transportation provider to users / customers in a privacy-focused and fair manner. It should be noted that "optimally" providing the allocation of vehicles of the shared transportation provider may include minimizing the overall cost and time of the user / customer, maximizing one or more user-defined preferences of each user / customer, and minimizing the overall cost of operating vehicles (e.g., the total number of operating vehicles, driving time, total fuel consumption, pollution, etc.). Moreover, providing the allocation of vehicles of the shared transportation provider in a "privacy-focused manner" may include protecting selected data associated with each transportation service provider (e.g., each ride sharing company), such as, for example, each vehicle identity and location. The degree of fairness may include and / or involve the transportation agency's market share model with respect to the ride-sharing company (e.g., based on the number of permits the company pays the agency).
[0023] In one aspect, the present invention may learn user demand for ride-sharing from historical customer request data. User demand for ride-sharing may be predicted over a defined time period (e.g., over a given time range, such as, for example, over the next few hours). Embodiments of the present invention may estimate the number of vehicles required to meet the predicted user demand over a selected time period (e.g., a time range of length ΔT or the length of a time range for demand forecasting). Based on a transportation service request distribution model (e.g., a market share model), the present invention may recommend a minimum and fair number of operating vehicles over a time range of ΔT for each transportation service provider.
[0024] The present invention may receive one or more user ride-sharing requests with user preferences and batch the user ride-sharing service requests within a time window of a defined, selected and / or suitable length δT (e.g., the length of the selected time / time range for batching ride-sharing requests). The ride-sharing agent anonymizes those requests (e.g., by anonymizing the customer ID) and submits the anonymized requests to a transportation service provider. For each user request submitted to a transportation service provider, the response received from the transportation service provider may include one or more user-centric cost vectors associated with the pick-up and drop-off locations of each user request (e.g., time of pick-up, time to destination, rate, and / or deviation from user preferences). In other words, for each batch of user ride-sharing requests, the request from the transportation service provider may include one or more user-centric parameters that express user locations and preferences (e.g., pick-up and delivery time windows, maximum ride time, or arrival time). Each transportation service provider calculates the cost of allocating its dedicated vehicle to a user request. Using the cost vectors received from the transportation service provider (e.g., a list of vehicle allocation costs for customers / users / requests), the allocation problem can be solved in an optimal and fair manner. For example, ride-sharing requests can be optimally solved by using a distributed auction algorithm. For fairness in the allocation of ride-sharing requests, the distributed auction algorithm can be executed / run offline to determine the minimum number of vehicles that satisfies all requests. Then, in one implementation, the fairness operation limits the number of vehicles for each company to a minimum. The price adjustment scheme gives another implementation.
[0025] Thus, as described herein, the present invention provides intelligent on-demand management of ride-sharing in a multi-transportation service provider environment (e.g., multiple entities / companies). In one aspect, one or more batches of user ride-sharing requests for a selected time period (e.g., 10 seconds) can be collected. Each transportation service provider can determine / calculate the cost of inserting the request in each vehicle route by solving a "dial-a-ride" ("DARP") problem, and these determined costs are shared with an intelligent transportation service agent system (see Figure 4-6). The intelligent transportation service proxy system provides an optimal solution to the linear assignment problem (“LAP”) and sends a ride sharing assignment of one or more vehicles to service each ride sharing request. The intelligent transportation service proxy system can use a rebalancing strategy for one or more unserved ride sharing requests. The process is repeated for each batch of requests. In one aspect, the intelligent transportation service proxy system can provide a one-to-one assignment of each ride sharing request to a vehicle to provide very high service rates in a dynamic environment. Therefore, the LAP is solved by the intelligent transportation service proxy system, which is solved twice during each sampling period: first, finding the optimal assignment of requests to available vehicles, and then rebalancing the vehicles to satisfy the unserved requests by relaxing one or more preferences (e.g., time preferences) specified in each ride sharing request.
[0026] It should be noted that, as used herein, the term "ride sharing" may be broadly defined to include various types of transportation service providers (e.g., "ride sharing services") that provide users (e.g., customers / passengers) with travel in privately owned vehicles that are operated in an automated manner and / or by the transportation service provider's owner or driver, according to one skilled in the art. For example, "ride sharing" may include, but is not limited to, taxi services, carpooling services, ride sharing services, such as, for example, taxi services, etc. A transportation service agent (e.g., a ride sharing agent) may also be referred to as an “agent” and may be connected to one or more transportation services (e.g., “ride sharing services”). The transportation service agent may act on behalf of one or more users (e.g., represent and / or act as an agent / intermediary) to book a suitable ride with an associated connected ride sharing service. A degree of fairness (“fairness”) may involve a ride sharing service payment fee / share paid to the ride sharing agent, such as, for example, when the ride sharing agent is owned / managed by a public agency and the car sharing company pays a licensing fee to the public agency based on the number of vehicles made available. On the other hand, depending on the predicted demand, the degree of fairness may constrain or “limit” the number of vehicles per transportation service provider. In an alternative aspect, the degree of fairness may be used and / or applied in Mobility as a Service (“MaaS”) by using pricing operations, such as, for example, adjusting prices (“price adjustments”) to allocate / provide penalties to unnecessary vehicles, thereby achieving fairness in a competitive environment between one or more transportation service providers.
[0027] In such cases, it may be desirable to allocate entity / company vehicles to one or more users in a fair and appropriate manner. A "transportation service request distribution model" (e.g., a market share model) may be one or more models that determine the percentage of the total operating fleet to be allocated to each participating transportation service provider, and may be proportional to the number of licenses issued to each transportation service provider by a public entity (e.g., a government agency). Additionally, protecting information associated with each of a plurality of transportation service providers (e.g., maintaining privacy) may involve and include protecting selected data (e.g., proprietary data) of a transportation service provider (e.g., a "ride sharing service") (e.g., protecting vehicle identity and geographic location).
[0028] It should be noted that, as described herein, the term "intelligence" (or "cognitive") can relate to, be, or involve conscious intellectual activities such as, for example, thinking, reasoning, or memory, which can be performed using machine learning. On the other hand, cognitive or "cognition" can be the psychological process of knowing, including aspects such as consciousness, perception, reasoning, and judgment. A machine learning system can use artificial reasoning to interpret data from one or more data sources (e.g., sensor-based devices or other computing systems) and learn topics, concepts, and / or processes that can be determined and / or derived through machine learning.
[0029] On the other hand, intelligence or "cognition" can refer to the mental activity or process of acquiring knowledge and understanding through one or more sensing of thought, experience, and the use of machine learning (which can include the use of sensor-based devices or other computing systems including audio or video devices). Intelligence or "cognition" can also refer to the recognition of patterns of behavior, resulting in "learning" of one or more events, operations, or processes. Thus, over time, the intelligent model can develop semantic labels to apply to observed behaviors and use knowledge domains or ontologies to store learned observed behaviors. In one embodiment, the system provides progressive levels of complexity in what can be learned from one or more events, operations, or processes.
[0030] On the other hand, the term intelligence can refer to an intelligent system (e.g., a cognitive system). An intelligent system can be a dedicated computer system or a group of computer systems configured with hardware and / or software logic (combined with hardware logic on which software is executed) to simulate human intelligence / cognitive functions. These intelligent systems apply human-like characteristics to convey and manipulate ideas that, when combined with the inherent advantages of digital computing, can solve problems with a high degree of accuracy (e.g., within a defined percentage range or above an accuracy threshold) and large-scale elasticity. An intelligent system can perform one or more computer-implemented artificial intelligence ("AI") operations that approximate human thought processes and enable users or computing systems to interact in a more natural way. An intelligent system can include artificial intelligence logic (such as, for example, logic based on natural language processing (NLP)) and machine learning logic, which can be provided as dedicated hardware, software executed on hardware, or any combination of dedicated hardware and software executed on hardware. The logic of an intelligent system can implement (one or more) intelligent operations, examples of which include, but are not limited to, question answering, identification of related concepts within different parts of content in a corpus, and intelligent search algorithms, such as Internet web page search.
[0031] In general, such intelligent systems are able to perform the following functions: 1) navigate the complexity of human language and understanding; 2) ingest and process large amounts of structured and unstructured data; 3) generate and evaluate hypotheses; 4) weigh and evaluate responses based only on relevant evidence; 5) provide situation-specific advice, insights, estimates, determinations, assessments, calculations, and guidance; 6) improve knowledge through machine learning processing and learn with each iteration and interaction; 7) enable decisions to be made at the point of impact (contextual guidance); 8) scale proportionally to the task, process, or operation; 9) extend and amplify human expertise and cognition; 10) identify resonant human-like attributes and traits from natural language; 11) infer a variety of language-specific or agnostic attributes from natural language; 12) remember and recall relevant data points (images, text, speech) (e.g., highly relevant recollection (memory and recall) from data points (images, text, speech); and / or 13) predict and sense through context-aware operations that mimic human cognition based on experience.
[0032] Additional aspects and attendant benefits of the present invention are further described below.
[0033] First, it should be understood that although the present disclosure includes a detailed description about cloud computing, the implementation of the technical solutions recorded therein is not limited to a cloud computing environment, but can be implemented in combination with any other type of computing environment now known or later developed.
[0034] Cloud computing is a service delivery model for convenient, on-demand network access to a shared pool of configurable computing resources. Configurable computing resources are resources that can be quickly deployed and released with minimal management cost or interaction with the service provider, such as networks, network bandwidth, servers, processing, memory, storage, applications, virtual machines, and services. This cloud model can include at least five characteristics, at least three service models, and at least four deployment models.
[0035] Features include:
[0036] On-demand self-service: Cloud consumers can unilaterally and automatically deploy computing capabilities such as server time and network storage on demand without human interaction with the service provider.
[0037] Broad network access: Computing power can be accessed over the network through standard mechanisms that facilitate the use of the cloud through different types of thin-client or thick-client platforms (e.g., mobile phones, laptops, personal digital assistants (PDAs)).
[0038] Resource pool: The computing resources of the provider are grouped into resource pools and serve multiple consumers through a multi-tenant model, where different physical and virtual resources are dynamically allocated and reallocated on demand. Generally, consumers cannot control or even know the exact location of the provided resources, but can specify the location (such as country, state or data center) at a higher level of abstraction, so it is location-independent.
[0039] Rapid elasticity: The ability to quickly and elastically (sometimes automatically) deploy computing power to scale up quickly, and quickly release it to scale down quickly. To consumers, the computing power available for deployment often appears to be unlimited, and any amount of computing power can be accessed at any time.
[0040] Measurable services: Cloud systems automatically control and optimize resource usage by leveraging metering capabilities at a level of abstraction appropriate to the type of service (e.g., storage, processing, bandwidth, and active user accounts). Resource usage can be monitored, controlled, and reported, providing transparency to both service providers and consumers.
[0041] The service model is as follows:
[0042] Software as a Service (SaaS): The capability provided to consumers is to use the provider's applications running on a cloud infrastructure. Applications can be accessed from a variety of client devices through a thin client interface such as a web browser (e.g., web-based email). Aside from limited user-specific application configuration settings, consumers neither manage nor control the underlying cloud infrastructure including networks, servers, operating systems, storage, or even individual application capabilities.
[0043] Platform as a Service (PaaS): The capability provided to consumers is to deploy applications created or acquired by consumers on the cloud infrastructure, which are created using programming languages and tools supported by the provider. Consumers neither manage nor control the underlying cloud infrastructure including networks, servers, operating systems or storage, but have control over the applications they deploy and may also have control over the configuration of the application hosting environment.
[0044] Infrastructure as a Service (IaaS): The capabilities provided to consumers are processing, storage, network, and other basic computing resources on which consumers can deploy and run arbitrary software including operating systems and applications. Consumers neither manage nor control the underlying cloud infrastructure, but have control over the operating system, storage, and applications they deploy, and may have limited control over selected network components (such as host firewalls).
[0045] The deployment model is as follows:
[0046] Private Cloud: Cloud infrastructure is run solely for an organization. The cloud infrastructure can be managed by the organization or a third party and can exist inside or outside the organization.
[0047] Community Cloud: A cloud infrastructure is shared by several organizations and supports a specific community with common interests (e.g., mission, security parameters, policies, and compliance considerations). A community cloud can be managed by multiple organizations within the community or by a third party and can exist inside or outside the community.
[0048] Public cloud: Cloud infrastructure is provided to the public or to large industry groups and is owned by an organization that sells cloud services.
[0049] Hybrid cloud: A cloud infrastructure consisting of two or more clouds (private, community or public) in a deployment model that remain distinct entities but are bound together by standardized or proprietary technologies (such as cloud burst sharing for load balancing between clouds) that enable data and application portability.
[0050] The cloud computing environment is service-oriented, with characteristics centered on statelessness, low coupling, modularity, and semantic interoperability. The core of cloud computing is the infrastructure that includes a network of interconnected nodes.
[0051] Reference now Figure 1 , which shows an example of a cloud computing node. Figure 1 The cloud computing node 10 shown is only an example of a suitable cloud computing node and should not bring any limitation to the functions and scope of use of the embodiments of the present invention. In short, the cloud computing node 10 can be used to implement and / or perform any of the functions described above.
[0052] The cloud computing node 10 has a computer system / server 12, which can operate with many other general or special computing system environments or configurations. As is well known, examples of computing systems, environments and / or configurations suitable for operating with the computer system / server 12 include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, etc.
[0053] Computer system / server 12 may be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. In general, program modules may include routines, programs, object programs, components, logic, data structures, etc. that perform specific tasks or implement specific abstract data types. Computer system / server 12 may be implemented in a distributed cloud computing environment where remote processing devices linked through a communication network perform tasks. In a distributed cloud computing environment, program modules may be located on local or remote computing system storage media including storage devices.
[0054] like Figure 1 As shown, the computer system / server 12 in the cloud computing node 10 is presented in the form of a general-purpose computing device. The components of the computer system / server 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).
[0055] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.
[0056] Computer system / server 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer system / server 12, including volatile and nonvolatile media, removable and non-removable media.
[0057] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer system / server 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 1 not shown, usually called a "hard drive"). Although Figure 1 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.
[0058] A program / utility 40 having a set (at least one) of program modules 42 may be stored in the system memory 28, such program modules 42 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.
[0059] The computer system / server 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the computer system / server 12, and / or any device that enables the computer system / server 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. In addition, the computer system / server 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the computer system / server 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may operate with the computer system / server 12, including, but not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0060] In the context of the present invention, and as will be appreciated by those skilled in the art, Figure 1 The various components depicted in the drawings may be located in a moving vehicle. For example, some of the processing and data storage capabilities associated with the mechanisms of the illustrated embodiments may occur locally via local processing components, while the same components are connected via a network to remotely located distributed computing data processing and storage components to accomplish the various objects of the invention. Again, as will be appreciated by those of ordinary skill in the art, this description is intended to convey only a subset of the entire connected network of distributed computing components that may collectively accomplish various inventive aspects.
[0061] Reference now Figure 2 , in which an exemplary cloud computing environment 50 is shown. As shown, the cloud computing environment 50 includes one or more cloud computing nodes 10 with which a local computing device used by a cloud computing consumer can communicate, and the local computing device can be, for example, a personal digital assistant (PDA) or a mobile phone 54A, a desktop computer 54B, a laptop computer 54C and / or an automobile computer system 54N. The cloud computing nodes 10 can communicate with each other. The cloud computing nodes 10 can be physically or virtually grouped in one or more networks including but not limited to private clouds, community clouds, public clouds or hybrid clouds, or a combination thereof as described above (not shown in the figure). In this way, cloud consumers can request infrastructure as a service (IaaS), platform as a service (PaaS) and / or software as a service (SaaS) provided by the cloud computing environment 50 without having to maintain resources on local computing devices. It should be understood that Figure 2The various types of computing devices 54A-N shown are merely illustrative, and the cloud computing node 10 and the cloud computing environment 50 may communicate with any type of computing device on any type of network and / or network-addressable connection (eg, using a web browser).
[0062] Reference now Figure 3 , which shows a cloud computing environment 50 ( Figure 2 ) provides a set of functional abstraction layers. First of all, it should be understood that Figure 3 The components, layers, and functions shown are only exemplary and the embodiments of the present invention are not limited thereto. Figure 3 As shown, the following layers and corresponding functions are provided:
[0063] The device layer 55 includes physical and / or virtual devices that embed and / or have independent electronics, sensors, actuators, and other objects to perform various tasks in the cloud computing environment 50. Each device in the device layer 55 combines networking capabilities with other functional abstraction layers so that information obtained from the device can be provided to other functional abstraction layers, and / or information from other abstraction layers can be provided to the device. In one embodiment, the various devices including the device layer 55 can be combined with a network of entities collectively referred to as the "Internet of Things" (IoT). As will be appreciated by those of ordinary skill in the art, such a network of entities allows for the mutual communication, collection, and distribution of data to achieve a variety of purposes.
[0064] The device layer 55 shown includes sensors 52, actuators 53, a "learning" thermostat 56 with integrated processing, sensor and networking electronics, a camera 57, a controllable household outlet / receptacle 58, and a controllable electrical switch 59, as shown. Other possible devices may include, but are not limited to, various additional sensor devices, networking devices, electronic devices (such as remote control devices), additional actuator devices, so-called "smart" appliances (such as refrigerators or washers / dryers), and a wide variety of other possible interconnected objects.
[0065] The hardware and software layer 60 includes hardware and software components. Examples of hardware components include: host 61; server 62 based on RISC (Reduced Instruction Set Computer) architecture; server 63; blade server 64; storage device 65; network and network components 66. Examples of software components include: network application server software 67 and database software 68.
[0066] The virtualization layer 70 provides an abstraction layer that can provide examples of the following virtual entities: virtual servers 71 , virtual storage 72 , virtual networks 73 (including virtual private networks), virtual applications and operating systems 74 , and virtual clients 75 .
[0067] In one example, the management layer 80 may provide the following functions: Resource provisioning function 81: providing dynamic acquisition of computing resources and other resources for performing tasks in a cloud computing environment; Metering and pricing function 82: tracking the cost of resource usage within the cloud computing environment and providing bills and invoices for this purpose. In one example, the resource may include an application software license. Security function: providing identity authentication for cloud consumers and tasks, and providing protection for data and other resources. User portal function 83: providing access to the cloud computing environment for consumers and system administrators. Service level management function 84: providing allocation and management of cloud computing resources to meet the required service levels. Service level agreement (SLA) planning and fulfillment function 85: providing pre-arrangement and provision for future demand for cloud computing resources predicted according to the SLA.
[0068] The workload layer 90 provides an example of the functionality that may be implemented in a cloud computing environment. In this layer, examples of workloads or functions that may be provided include: mapping and navigation 91; software development and lifecycle management 92; virtual classroom teaching provision 93; data analysis processing 94; transaction processing 95; and in the context of the illustrated embodiment of the present invention, various workloads and functions 96 for intelligent on-demand management of ride-sharing in a transportation system. In addition, the workloads and functions 96 for intelligent on-demand management of ride-sharing may include operations such as data analysis (including data collection and processing from various vehicle or environmental sensors), collaborative data analysis, and predictive data analysis functions. Those skilled in the art will recognize that the workloads and functions 96 for intelligent on-demand management of ride-sharing in a transportation system may also work in conjunction with other parts of various abstraction layers (such as those in hardware and software 60, virtualization 70, management 80, and other workloads 90 (such as data analysis processing 94, for example)) to achieve the various purposes of the illustrated embodiment of the present invention.
[0069] As previously described, the mechanisms of the illustrated embodiments provide a new approach to intelligent transportation service management in a transportation system by a processor. Transportation service requests may be allocated among multiple transportation service providers based on one or more transportation service request distribution models and various parameters and preferences for each user. The transportation service request distribution model may protect information associated with each transportation service provider and suggest a selected order for distributing multiple transportation service requests.
[0070] In one aspect, ride-sharing services may involve a "trip" or "journey". What is called a "trip" or "journey" may be very subjective and context-dependent. In the broadest possible sense, a trip may simply be the entire / full travel experience from point A to point B. For example, a trip may encompass the user's entire travel experience (e.g., commuting from home to the office). In a more restrictive context, a trip may include one or more actions or movements of traveling from one location to another. A trip may also include travel-related operations, one or more actions, events, or decisions related to one or more actions of moving from one location to one or more alternative locations. A trip may include every decision, experience, action, and / or movement inside and outside the vehicle. A trip may include one or more routes and destinations. A trip may also include one or more actions, movements, stops (temporary or permanent), travel information, reservations, transportation options, modes of travel, and / or one or more operations related to a navigation system, an entertainment system, and / or a telecommunications system.
[0071] Now go to Figure 4 , a block diagram depicting exemplary functional components of a system 400 depicting various mechanisms in accordance with the illustrated embodiments is shown. Figure 4 Illustrated is a system 400 for providing an intelligent transportation service agent system 410 in a transportation system / computing environment according to an example of the present technology.
[0072] As will be seen, in contrast to the previous Figure 1-3 Many functional blocks can also be considered "modules" or "components" of functionality in the same descriptive sense already described in . For example, Figure 1 The computer system / server 12 may be included in Figure 4 The system may be connected to other computing nodes (such as a vehicle's computer system or non-vehicle systems such as traffic cameras, cloud computing networks, global positioning satellite ("GPS") devices, vehicle-to-vehicle ("V2V") systems, smart phones, etc., and / or one or more Internet of Things (IoT) devices) via a distributed computing network, where additional data collection, processing, analysis, and other functions may be implemented.
[0073] In one embodiment, the computer system / server 12 includes an intelligent transportation service agent system 410, which can communicate with one or more transportation service providers (e.g., rental vehicle providers) such as, for example, transportation service provider 440 via a network or communication link 475, and / or communicate with users 406 via one or more user equipment ("UE") 412 (e.g., IoT devices such as smart phones, computers, tablets, smart watches, etc.).
[0074] In one aspect, the intelligent transportation service agent system 410 may be composed of one or more computing systems and servers (not shown for ease of illustration, but may be included in Figure 1-4 An independent computing service provided by one or more components, modules, services, applications and / or functions of the transport service provider 402 and the UE 412 and is external to the transport service provider 402 and the UE 412.
[0075] In additional embodiments, the intelligent transportation service agent system 410 may be located and locally installed within a computing system associated with the transportation service provider 402 and / or the UE 412. The transportation service provider 402 and the UE 412 may be associated with the intelligent transportation service agent system 410 via one or more pre-authorization operations, and / or may be instantaneously joined to the intelligent transportation service agent system 410 via a series of authentication operations to join the intelligent transportation service agent system 410 and grant permission to the intelligent transportation service agent system 410 to obtain access to one or more IoT devices and / or computing systems of the transportation service provider 402 and the UE 412, thereby requesting a rental vehicle and / or protecting the privacy of the user 406 in the transportation system / rental vehicle system.
[0076] In addition, the intelligent transportation service agent system 410 can be combined with, for example, Figure 1 The processing unit 16 (“processor”) and memory 28 of the present invention may be used to perform various computations, data processing, and other functions according to various aspects of the present invention. The intelligent transportation service agent system 410 may also include a privacy protection component 420, a rental vehicle service component 430 (e.g., a ride sharing component), an allocation component 440, and a machine learning component 450, each of which may be controlled and communicated with the processing unit 16 and the memory 28.
[0077] The rental vehicle service component 430 (e.g., a ride-sharing service) can enable a user (such as, for example, user 406) to order, subscribe to, and / or request and / or dispatch a ride-sharing service / rental vehicle (e.g., a taxi, a peer-to-peer ride-sharing service, etc.). The rental vehicle service component 430 can identify one or more available vehicles for rent, such as, for example, a taxi, a peer-to-peer ride-sharing service, or a transportation service that charges a fee for transporting a passenger from one location to another. The rental vehicle service component 430 can provide and / or assist in providing a map from a mapping service to a rental vehicle (e.g., transportation service provider 402) associated with a requesting party (e.g., user 406).
[0078] In one aspect, the rental vehicle service component 430 associated with the allocation component 440 can receive one or more transportation service requests from one or more users (e.g., user 406) during a selected time period, and each transportation service request can include one or more parameters and preferences of the one or more users (e.g., user 406). The rental vehicle service component 430 associated with the allocation component 440 can allocate the transportation service requests among various transportation service providers such as, for example, transportation service provider 402 according to one or more transportation service request distribution models and one or more parameters and preferences for each user (such as, for example, user 406). In one aspect, the privacy protection component 420 can use the transportation service request distribution model to protect information related to each transportation service provider (e.g., transportation service provider 402) and suggest a selected order for distributing the one or more transportation service requests.
[0079] The machine learning component 450 can forecast the demand for transportation service requests of a plurality of users over a selected time period and estimate the number of transportation service providers required to service the forecasted number of transportation service requests.
[0080] The machine learning component 450 can learn parameters and preferences of one or more users, learn transportation service request requirements of one or more users based on historical transportation service request data, and / or learn one or more contextual factors related to a journey associated with one or more transportation service requests, wherein the one or more contextual factors include traffic data, weather data, road conditions, road types, or a combination thereof.
[0081] The rental vehicle service component 430 can suggest both a selected order for distributing the plurality of transportation service requests and a minimum number of transportation service providers (e.g., transportation service providers 402) for servicing one or more transportation service requests. The rental vehicle service component 430 can maintain a degree of fairness among the plurality of transportation service providers for servicing the one or more transportation service requests within a selected time period. Additionally, in another aspect, the rental vehicle service component 430 can maintain a degree of fairness among the plurality of transportation service providers for servicing the one or more transportation service requests within a selected time period by prioritizing one or more parameters and preferences of one or more users and minimizing the time and cost associated with transportation.
[0082] The machine learning component 450 can collect and / or learn one or more user preferences, rental vehicle parameters, one or more events, daily living activities (ADL) and / or other events associated with the user. One or more machine learning modules for providing one or more functions of the intelligent transportation service agent system 410 can be developed, learned and / or constructed, such as, for example, one or more transportation service request distribution models. For example, the machine learning component 450 can apply the following multiple combinations to the machine learning model for intelligent privacy protection transportation operations: factors, parameters, user preferences, user's ADL, travel preferences, travel data (e.g., ride sharing data), shopping preferences, behavioral characteristics, vehicle operator profiles, vehicle operation or behavior standards / values, learned behavioral parameter data, temperature data, historical data, traffic data, weather data, road conditions, operator's health status, operator's biometric data, longitude location data, latitude location data, longitude / latitude location data and / or other contexts related to the vehicle or a combination thereof.
[0083] For example, the machine learning component 450 can cognitively predict, estimate, and / or provide an approximate location within the selected location of the user 406. In one aspect, the machine learning component 450 can collect feedback information from the UE 406 and / or the transportation service provider 402 to learn, identify, and / or predict one or more privacy protection parameters, user preferences, and / or events (recorded and / or unrecorded) associated with the user to perform intelligent privacy protection services using the intelligent transportation service agent system 410. The machine learning component 450 can also learn and / or suggest privacy protection factors for each user based on user profiles, behavior patterns, preferences, feedback, etc.
[0084] In one aspect, as described herein, the machine learning operations of the machine learning component 450 can be performed using a variety of methods or combinations of methods, such as supervised learning (e.g., MCMC filters, Kalman filters, particle filters, etc.), unsupervised learning, temporal difference learning, reinforcement learning, etc. That is, machine learning modeling can learn parameters of one or more physical models. Machine learning modeling can be used in the category of parameter estimation of state-space models, which can be accomplished by unsupervised learning techniques, particularly learning context and / or indicators.
[0085] Some non-limiting examples of supervised learning that can be used with the present technology include Kalman filters, particle filters, MCM filters, AODE (averaged one-dependence estimator), artificial neural networks, back propagation, Bayesian statistics, naive Bayes classifier, Bayesian networks, Bayesian knowledge base, case-based reasoning, decision trees, inductive logic programming, Gaussian process regression, gene expression programming, grouping method for data processing (GMDH), learning automata, learning vector quantization, minimum message length (decision trees, decision diagrams, etc.), lazy learning, instance-based learning, nearest neighbor algorithms, analogy modeling, probably approximately correct (PAC) learning, ripple down) rules, knowledge acquisition methodology, symbolic machine learning algorithms, sub-symbolic machine learning algorithms, support vector machines, random forests, classifier ensembles, guided aggregation (bagging), boosting (meta-algorithms), ordinal classification, regression analysis, information fuzzy networks (IFNs), statistical classification, linear classifiers, Fisher linear discriminators, logistic regression, perceptrons, support vector machines, quadratic classifiers, k nearest neighbors, hidden Markov models, and boosting. Some non-limiting examples of unsupervised learning that can be used with the present technology include artificial neural networks, data clustering, expectation maximization, self-organizing maps, radial basis function networks, vector quantization, generative topographic maps, information bottleneck methods, IBSEAD (interaction based on distributed autonomous entity systems), association rule learning, prior algorithms, eclat algorithms, FP growth algorithms, hierarchical clustering, single link clustering, concept clustering, partition clustering, k-means algorithms, fuzzy clustering, and reinforcement learning. Some non-limiting examples of temporal difference learning can include Q learning and learning automata. The specific details of any of the examples of supervised, unsupervised, temporal difference, or other machine learning described in this paragraph are known and are within the scope of this disclosure. Moreover, when deploying one or more machine learning models, computing devices can be tested first in a controlled environment before being deployed in a public environment. Moreover, even when deployed in a public environment (e.g., outside a controlled test environment), computing devices can be monitored for compliance.
[0086] in addition, Figure 4 The computing system 12 / computing environment can perform one or more calculations based on mathematical operations or functions, which may involve one or more mathematical operations (for example, solving differential equations or partial differential equations analytically or computationally using addition, subtraction, division, multiplication, standard deviation, mean, average, percentage, statistical modeling using statistical distributions by finding the minimum, maximum, or similar threshold of combined variables, etc.).
[0087] Now go to Figure 5, depicting a method for implementing an intelligent transportation service agent system 550 (eg, Figure 4 A block diagram of exemplary functionality for providing on-demand management of ride sharing in a transportation system, as used throughout the context of an intelligent transportation service agent system 410 of FIG. 4 . As shown, various functional blocks are depicted with arrows that specify the relationship of blocks 500 to one another and illustrate the process flow. In one aspect, Figure 1-4 One or more of the components, modules, services, applications and / or functions described in Figure 5 For the sake of brevity, repeated descriptions of similar elements, components, modules, services, applications and / or functions used in other embodiments described herein are omitted.
[0088] In addition, descriptive information associated with each functional block 500 is also seen. As will be seen, in the same manner as previously described in Figure 4 Many of the functional blocks 500 may also be considered "modules" of functionality in the same descriptive sense already described in . With the foregoing in mind, the module blocks 500 may also be incorporated into various hardware and software components of a system for providing on-demand management of ridesharing in a transportation system according to the present invention. Many of the functional blocks 500 may be executed as background processing in a distributed computing component or on a user device or on various components elsewhere.
[0089] In one aspect, the intelligent transportation service broker system 550 may include a customer demand learner 510, customer request and context data 512, a learned model 518, a broker request processor 514, an allocation component 516, a customer demand forecaster 520, a vehicle fleet estimator 522, and a market share model 524. The intelligent transportation service broker system 550 may communicate with one or more transportation service providers such as, for example, ride sharing company 1, ride sharing company 2, and ride sharing company N.
[0090] In one aspect, the customer demand learner 510 can learn one or more models 518 (e.g., "learned models", such as, for example, customer demand models) to predict customer demand. The customer demand learner 510 can use customer requests and context data 512 (e.g., historical customer requests, historical context data associated with customer requests (e.g., weather, events, time of day, day of week)). The output of the model learned by the customer demand learner 510 may include one or more prediction models (e.g., statistical models, neural networks), which can be implemented using time series operations, deep learning operations (e.g., recursive neural networks, long short-term memory "LSTM" networks, multi-layer perceptron networks), etc.
[0091] The customer demand predictor 520 can predict customer demand 530 for the ride-sharing service for a selected time period (e.g., a given time range, such as, for example, the next 6 hours) (e.g., demand forecast within a time window / range of length δT). The customer demand predictor 520 can use as input data the forecast time range, one or more learned models 518 (e.g., one or more customer demand prediction models learned from the customer demand learner 510), current context data (e.g., time of day, day of the week, weather, events of the day), current and previous customer demand data. The customer demand predictor 520 can generate as output a forecast (or prediction) of customer demand within a selected time period (e.g., input time range), which can be implemented using time series operations, deep learning operations (e.g., recursive neural networks, long short-term memory "LSTM" networks, multi-layer perceptron networks), etc.
[0092] The vehicle fleet estimator 522 can estimate the minimum number of operating vehicles for each transportation service provider (such as, for example, ride-sharing company 1, ride-sharing company 2, and ride-sharing company N) based on the customer demand forecast generated from the customer demand forecaster 520 and one or more market share models (e.g., transportation service request distribution models) to establish a degree of fairness in vehicle allocation. The vehicle fleet estimator 522 can use the forecast time horizon, the predicted customer demand from the customer demand forecaster 520, and each market share model 524 received from each transportation service provider (such as, for example, ride-sharing company 1, ride-sharing company 2, and ride-sharing company N) as input data.
[0093] The market share model 524 can be a function of determining a percentage of the total operating fleet (e.g., a fleet of vehicles) to be allocated to each participating transportation service provider (such as, for example, ride sharing company 1, ride sharing company 2, and ride sharing company N) and can be proportional to the number of licenses issued to each transportation service provider by a legal or administrative agency.
[0094] For example, if there are three transportation service providers involved, such as, for example, ride-sharing company 1, ride-sharing company 2, and ride-sharing company N, and they have 30, 15, and 5 licenses, respectively, then their market shares may be 60%, 30%, and 10%, respectively. The market share model 524 generates an output that provides the minimum number of operating vehicles for each ride-sharing company within the input time range. Based on the predicted customer demand via the customer demand predictor, the vehicle fleet estimator 522 can estimate the minimum total number of operating vehicles required, which can be achieved by offline learning the number of vehicles required to meet a 100% service rate for a given estimated number of requests. Based on the total number of vehicles and the market share model 524, the vehicle fleet estimator 522 can recommend a minimum number of operating vehicles for each transportation service provider (such as, for example, ride-sharing company 1, ride-sharing company 2, and ride-sharing company N), which can be based on the following model: the recommended number of vehicles for each transportation service provider is proportional to the market share of the transportation service provider.
[0095] In one aspect, one or more ride service requests 502 may be received (as input) via the proxy request processor 514, where the ride service requests 502 may be a batch of requests within a selected time period (e.g., a time window of length δT). That is, the one or more ride service requests 502 (e.g., customer requests) may be pre-processed by batching real-time customer requests within a predefined and selected time period (e.g., a time window of length δT) and preparing relevant request data for other system components (dispatching components, historians, etc.).
[0096] The one or more ride service requests 502 may be a real-time stream / log of customer requests over a predefined and selected time period (e.g., a time window of length δT). The one or more ride service requests 502 may be processed via a proxy request processor 514 to generate / output a batch of pre-processed anonymous requests including anonymized identifiers (“IDs”), pick-up and drop-off locations and times, and one or more customer preferences (e.g., vehicle type, preference for whether to share a ride with other passengers, etc.).
[0097] The one or more ride service requests 502 may be associated and stored with the client request and context data 512 via the proxy request processor 514. In one aspect, the proxy request processor 514 may extract any relevant non-private information from the one or more ride service requests 502 (e.g., ride sharing requests) and submit the one or more ride service requests 502 to an allocation component 516 (e.g., an allocation solver / optimizer), and may group one or more similar requests (e.g., requests from passengers traveling from similar origins to similar destinations and indicating a willingness to share a ride with other users) for input to the allocation component 516. The proxy request processor 514 may concatenate the one or more ride service requests 502 and the context data and store them as the client request and context data 512.
[0098] The allocation component 516 can receive one or more cost matrices 526 from one or more transportation service providers, such as, for example, ride sharing company 1, ride sharing company 2, and ride sharing company N. That is, the one or more cost vectors received from the transportation service providers can be used to allocate one or more transportation service requests among the transportation service providers according to a degree of fairness while maintaining protected data of the transportation service providers.
[0099] The allocation component 516 can dispatch one or more anonymized ride-sharing requests to one or more transportation service providers, and can then receive a cost matrix (which can be anonymized) associated with one or more top / best k ride-sharing options for each ride service request 502. The allocation component 516 can calculate / determine the optimal allocation by solving a linear allocation problem. Thus, the allocation component 516 can output 504 one or more allocations for servicing the ride-sharing request by one or more transportation service providers.
[0100] The allocation component 516 can submit the anonymized ride service request 502 to one or more transportation service providers, such as, for example, ride sharing company 1, ride sharing company 2, and ride sharing company N. That is, the allocation component 516 can allocate one or more vehicles from various transportation service providers (such as, for example, ride sharing company 1, ride sharing company 2, and ride sharing company N) to the one or more ride service requests 502 in an optimal, privacy-focused, and fair manner.
[0101] The allocation component 516 can estimate the minimum number of vehicles for each transportation service provider using a batch of pre-processed and anonymized customer requests (e.g., ride service requests 502) as input. The allocation component 516 can generate an optimal vehicle allocation for the ride service requests 502 as output by submitting the anonymized request data (from the batch) to transportation service providers (such as, for example, ride sharing company 1, ride sharing company 2, and ride sharing company N).
[0102] Each transportation service provider may match requests with locations in the transportation service provider's fleet of vehicles and return a (user-centric) cost vector for each of the k best / optimal ride-sharing service request matches. The result may be a cost matrix / tensor 575, where each request or combination of similar requests (rows) may be associated with a cost vector associated with the best k allocations, such as Figure 5 As shown, depicting the Figure 4-5 The cost vector may include, for example, the indicated pickup time, the route time to the destination, the rate (e.g., the monetary value and / or rate associated with the customer request may be considered as the route time to the customer), deviations from user preferences, etc. The allocation component 516 may perform the linear allocation using a distributed auction algorithm that solves the linear allocation problem to an optimal solution in a privacy-conscious manner.
[0103] It should be noted that the allocation component 516 does not require complete / full access to the cost matrix C ij. The allocation component 516 and / or the proxy request processor 514 can coordinate cooperation between various transportation service providers (such as, for example, ride sharing company 1, ride sharing company 2, and ride sharing company N) via a distributed auction operation, where auction bids can be used to help provide a degree of fairness. In a distributed implementation, entities participating in the auction (i.e., transportation ride sharing providers) can send only the information required to calculate the bid B(i, j) of each dedicated vehicle i for customer request j to the allocation component 516 and / or the proxy request processor 514. Winning an iteration of the auction means having the vehicle allocated to the customer. Transportation service providers participating in the auction with one or more unallocated vehicles can increase their bids in the next iteration, resulting in a decrease in the profit of the transportation service provider. After a finite or defined number of steps, the vehicles reach a state of "almost equilibrium", in which case no transportation service provider has an incentive to increase its bid. This state corresponds to a feasible allocation of vehicles for the request, which is communicated to the company by the agent. In other words, the cooperative protocol provides an allocation solution in which no firm has any incentive to unilaterally seek out another user / customer (by bidding higher). The almost-equilibrium situation is formally represented by Equation 1, where M is the set of user ride-sharing requests at time t, C i is the capacity of each vehicle, C ij YesR ij The duration of each time, where R ij is the optimal route for vehicle i, and B is the bid:
[0104]
[0105] This ensures that each vehicle i is within ∈ (a sufficiently small constant) of the best current bid price estimate for customer j i Provides a service, C is a set of vehicles, and represents each vehicle i. It should be noted that in this context, "profit" is expressed as an allocation cost with an opposite sign. In one aspect, the present invention does not require vehicles to disclose their best prices to the allocation component 516 and / or the proxy request processor 514, but only to disclose bids. Specifically, in order to calculate the bids in each iteration, the allocation component 516 and / or the proxy request processor 514 needs to receive the difference between the two best returns of the unallocated vehicles, rather than the entire allocation cost matrix (as a centralized protocol would require).
[0106] To further illustrate, consider the following example of providing intelligent transportation service management in a transportation system by solving the allocation of ride-sharing requests in a collaborative protocol with a degree of fairness. First, all available vehicles for each transportation provider are considered unallocated and the initial vehicle bid is set to zero. In each iteration, locally, each transportation service provider with unallocated vehicles calculates the difference between the two best possible net returns obtained by serving (i.e., being allocated to) the user / customer. In order to participate in the auction, each transportation service provider with unallocated vehicles i can increase its bid by a selected amount and increase the disturbance ∈ by a selected amount (i.e., the difference between the two best possible net returns obtained by serving the customer and the disturbance ∈). The disturbance is included to achieve an almost balanced state. Vehicles allocated to users / customers in previous iterations do not need to update their bids. The bid prices can be collected by each transportation service provider and sent to the allocation component 516 and / or the proxy request processor 514, which can allocate each user / customer to the highest vehicle bidder / transportation service provider. The auction can continue until all vehicles of each transportation service provider are allocated or the maximum number of iterations is reached. The allocations returned by the auction operation require a feasibility interpretation, where a vehicle allocated to a request with infinite cost will not have the associated user / customer added to its route.
[0107] In one aspect, the allocation component 516 can have one or more attributes: (1) a privacy-focused attribute, and (2) a fairness attribute. With respect to the privacy-focused attribute, when forwarding one or more transportation service requests to one or more transportation service providers, the allocation component 516 can forward one or more anonymous transportation service requests that do not disclose the identity of the user / customer, the exact location of the user and / or transportation service provider, or all preferences (e.g., a complete list of customer preferences). In this manner, the allocation component 516 only forwards the selected data required to calculate the allocation cost. When a cost matrix / tensor is sent from a transportation service provider to a transportation service request proxy, the submitted matrix is anonymous in the sense that the location or all cost information of the user and / or transportation service provider is not disclosed. Instead, the allocation component 516 only assigns the k best / optimal costs to the anonymous requests previously sent by the proxy request processor 514.
[0108] For the fairness attribute, the allocation module can enforce fairness by a constraint on a minimum number of vehicles for each transportation service provider. The allocation component 516 can solve the following linear allocation problem using one or more decision variables, which can be binary variables indicating that the request is allocated to a transportation service provider vehicle (e.g., matching one of the k costs in the cost matrix). One or more constraints can be used on fairness, where each request can be allocated to a vehicle if the vehicle is feasible for the customer preference, and there is only one allocation per request. In one aspect, multiple ride-sharing requests can be allocated to each transportation service provider, depending on (e.g., ≤) the minimum number of vehicles calculated for the selected transportation service provider, so as to minimize the overall allocation cost and the number of vehicles for all allocations.
[0109] Now go to Figure 6 , depicting a method for providing a Figure 4 and Figure 5 A block diagram of exemplary functionality 600 associated with providing on-demand management of ridesharing as used throughout the context of an intelligent transportation service agent system of FIG. As shown, the various functional blocks are depicted with arrows that specify the relationship of the blocks 600 to each other and illustrate the process flow. In addition, descriptive information associated with each functional block 600 is also seen. As will be seen, in the context of the previously described intelligent transportation service agent system of FIG. Figure 4-5 Many of the functional blocks may also be considered "modules" of functionality in the same descriptive sense as has been described in . In view of the foregoing, the module blocks 600 may also be incorporated into various hardware and software components of a system for an intelligent transportation service agent system according to the present invention. Many of the functional blocks 600 may be executed as background processing in a distributed computing component or on a user device or on various components elsewhere, and may not be typically noticed by a user performing a general task of taking a photo using the user's camera (e.g., illustrated in 501).
[0110] Beginning at block 610, the proxy request processor 514 may receive one or more ride service requests ("requests") and group them into batches. The batches may be submitted to an assignment component 516 (eg, an assignment solver / optimizer) and may be stored in a database.
[0111] In block 620, the allocation component 516 can dispatch one or more anonymized rideshare requests to one or more transportation service providers and can then receive a cost matrix (which can be anonymized) associated with one or more top / best k rideshare options for each rideshare request 502. The allocation component 516 can compute / determine the optimal allocation by solving a linear allocation problem.
[0112] As in block 630, the customer demand learner 510 may learn customer demand based on historical context and transportation service request data. As in block 640, customer ride-sharing demand may be predicted by the customer demand predictor 520 based on historical data (e.g., historical ride-sharing requests) and contextual data (e.g., weather, events, time of day, day of the week / month, etc.).
[0113] As in block 650 , the vehicle fleet estimator may estimate the number of vehicles required to service one or more transportation service requests in a batch, and may also estimate the number of operating vehicles for each transportation service provider based on a market share model.
[0114] In block 660 , one or more cost matrices that may be received from one or more transportation service providers may be anonymized (eg, to protect vehicle details, location, and / or position of the vehicle).
[0115] Now go to Figure 7 , depicts a method 700 for providing intelligent transportation service management (e.g., rental vehicle service, ride sharing service) in a transportation system by a processor, in which various aspects of the illustrated embodiments may be implemented. Function 700 may be implemented as a method executed on a machine as instructions, wherein the instructions are included on at least one computer-readable medium or on a non-transitory machine-readable storage medium. Function 700 may start in block 702.
[0116] As in box 704, one or more transportation service requests (e.g., for a rental vehicle or ride-sharing service) including one or more parameters and preferences may be received from one or more users within a selected time period. As in box 706, a number of transportation service providers required to service the one or more transportation service requests may be determined. As in box 708, the one or more transportation service requests may be allocated among multiple transportation service providers based on one or more transportation service request distribution models and one or more parameters and preferences for one or more users. The transportation service request distribution model may protect information associated with each transportation service provider and suggest a selected order for distributing the multiple transportation service requests. As in box 710, functionality 700 may end.
[0117] Now go to Figure 8 , depicts a method 800 for providing intelligent transportation service management (e.g., rental vehicle service, ride sharing service) in a transportation system by a processor, in which various aspects of the illustrated embodiments may be implemented. Function 800 may be implemented as a method executed on a machine as instructions, wherein the instructions are included on at least one computer-readable medium or on a non-transitory machine-readable storage medium. Function 800 may start in block 802.
[0118] As in block 804, user / customer demand for ride-sharing may be learned and / or predicted from historical customer request data. As in block 806, user / customer demand for ride-sharing may be learned and / or predicted within a selected time frame. As in block 808, the number of vehicles required to satisfy the predicted amount of transportation service provider demand within the selected time frame may be estimated.
[0119] As in block 810, a minimum number of operating vehicles may be allocated to each transportation service provider while maintaining a degree of fairness between each transportation service provider for providing services within the time frame while prioritizing one or more parameters and preferences of one or more users and minimizing the time and cost associated with transportation for the user / customer. As in block 812, functionality 800 may end.
[0120] On the one hand, combined Figure 7-8 At least one box and / or as Figure 7-8 As part of at least one block of , operations 700 and / or 800 may include each of the following. The operations of 700 and / or 800 may receive one or more transportation service requests from one or more users within a selected time period, wherein each transportation service request includes one or more parameters and preferences of the one or more users.
[0121] The operations of 700 and / or 800 may predict / forecast the demand for transportation service requests of a plurality of users over a selected time period, and / or estimate the number of transportation service providers required to service the forecasted number of transportation service requests.
[0122] The operations of 700 and / or 800 can learn parameters and preferences of one or more users, learn transportation service request requirements of one or more users based on historical transportation service request data, and / or learn one or more contextual factors associated with a journey associated with one or more transportation service requests, wherein the one or more contextual factors include traffic data, weather data, road conditions, road types, or a combination thereof.
[0123] The operations of 700 and / or 800 can both suggest a selected order for distributing multiple transportation service requests and a minimum number of transportation service providers for servicing one or more transportation service requests, maintain a degree of fairness among multiple transportation service providers for servicing one or more transportation service requests within a selected time period, and / or maintain a degree of fairness among multiple transportation service providers for servicing one or more transportation service requests within a selected time period by prioritizing one or more parameters and preferences of one or more users and minimizing time and costs associated with transportation.
[0124] The present invention may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present invention.
[0125] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.
[0126] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.
[0127] The computer program instructions for performing the operation of the present invention may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and procedural programming languages, such as "C" language or similar traditional programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present invention.
[0128] Various aspects of the present invention are described herein with reference to the flow charts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each box of the flow chart and / or block diagram and the combination of each box in the flow chart and / or block diagram can be implemented by computer-readable program instructions.
[0129] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0130] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0131] The flowcharts and block diagrams in the accompanying drawings show the architecture, functions and operations of the possible implementations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram may represent a part of a module, segment or instruction, which contains one or more executable instructions for implementing (one or more) specified logical functions. In some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two boxes shown as continuous may actually be executed substantially in parallel, or the boxes may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, may be implemented with a dedicated hardware-based system that performs a specified function or action, or may be implemented with a combination of dedicated hardware and computer instructions.
Claims
1. A method for providing intelligent transportation service management in a transportation system by a processor, comprising: receiving a plurality of data representing transportation service information associated with a plurality of transportation service providers and a plurality of users, wherein the plurality of transportation service providers are ride-sharing entities including a plurality of vehicles; performing machine learning operations to generate one or more transportation service request distribution models based on the plurality of data, wherein performing the machine learning operations includes analyzing and correlating historical transportation service request data, one or more parameters and preferences of each of the plurality of users, and one or more contextual factors associated with journeys involving a plurality of transportation service requests submitted by the plurality of users; and allocating, via a transportation agent, a plurality of transportation service requests among the plurality of transportation service providers based on the one or more transportation service request distribution models and one or more parameters and preferences for each of the plurality of users, wherein the one or more transportation service request distribution models protect information about pricing policies associated with each of the plurality of transportation service providers and recommend a selected order for distributing the plurality of transportation service requests to the plurality of transportation service providers and a minimum number of operating vehicles for each transportation service provider, wherein the transportation service requests provided to the transportation service providers include only data required to calculate allocation costs, wherein the plurality of transportation service requests are allocated in batches among the plurality of transportation service providers within a selected time period according to a distributed auction operation, the distributed auction operation iteratively providing one of the transportation service request batches having a predetermined number of the transportation service requests to each of the transportation service providers using the transportation agent, receiving the highest k bids for providing services from the transportation service providers for each iteration, performing allocation of the received bids for the plurality of transportation service requests, and requiring unallocated transportation service providers to increase their bids during the next iteration to reduce profits of the unallocated transportation service providers, The transportation service request allocated to each transportation service provider is no greater than the minimum number of operating vehicles recommended by the transportation service provider, so as to minimize the overall allocation cost and the number of all allocated vehicles.
2. The method of claim 1, further comprising receiving the plurality of transportation service requests from the plurality of users within a selected time period.
3. The method of claim 1, further comprising: Forecasting the transportation service request needs of the plurality of users within a selected time period; as well as The number of transportation service provider vehicles required to service the forecasted number of transportation service requests is estimated.
4. The method of claim 1, further comprising: learning parameters and preferences of the plurality of users; Based on the historical transportation service request data, learning the transportation service request needs of the plurality of users; as well as One or more contextual factors associated with the journeys related to the plurality of transportation service requests are learned, wherein the one or more contextual factors include traffic data, weather data, road conditions, road types, or a combination thereof.
5. The method of claim 1, further comprising suggesting both a selected order for distributing the plurality of transportation service requests and a minimum number of transportation service providers for servicing the plurality of transportation service requests.
6. The method of claim 1, further comprising maintaining a degree of fairness among the plurality of transportation service providers for servicing the plurality of transportation service requests within the selected time period.
7. The method of claim 1 , further comprising maintaining a degree of fairness among the plurality of transportation service providers for servicing the plurality of transportation service requests within a selected time period by prioritizing the one or more parameters and preferences of the plurality of users and minimizing time and costs associated with transportation.
8. A system for providing intelligent transportation service management in a transportation system, comprising: One or more computers having executable instructions which, when executed, cause the system to perform the steps of the method according to any one of claims 1-7.
9. A computer program product for providing intelligent transport service management in a transport system by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions causing the processor to perform the steps of the method according to any one of claims 1-7 when executed.
10. A system comprising modules individually configured to perform each step of the method according to any one of claims 1-7.
