Abstract: A method for a system. The method may include receiving information regarding a plurality of nodes of the transportation network, a map associated with the transportation network, and a current demand associated with multiple nodes in the transportation network. The method may further include generating, based on the received information, a demand grid related to the transportation network. The method may also include determining a set of service zones based on the received information and the generated demand grid. The method may further include generating, based on the received information and the set of service zones, a model for route optimization. The method may also include determining, based on the model, at least one candidate path for a vehicle associated with the on-demand transportation service.

Abstract: The invention provides seamless journey experience for passenger in multimodal mobility travel using a single ticket for different trip sections and when multimodal operators provide passenger proof-of-transit, smart contracts enable automated fare disambiguation among them. The single truth of passenger travel journey on single ticket in multimodal mobility helps to also develop incentivizations/rewards for passengers, and incentivize modal operator's based on service level agreements in a consortium.

Abstract: An apparatus for providing recommended solutions for a multi-mode transportation problem associated with a multi-mode transportation network. The apparatus may include a memory and at least one processor coupled to the memory. The at least one processor may be configured to receive transportation-related data regarding a plurality of different modes of transportation. The apparatus may further be configured to generate a single-mode data set for each of the plurality of different modes of transportation. The apparatus may also be configured to generate problem-specific harmonized data for the multi-mode transportation network from the received transportation-related data. The apparatus may further be configured to provide a set of recommended solutions for the multi-mode transportation problem based on the problem-specific harmonized data.

Abstract: A method of providing optimal and personalized business decision making that leverages behavioral economics principles and machine learning techniques is discussed herein. The method may include collecting or simulating data relating to behavioral characteristics of a plurality of stakeholders and analyzing the collected data to construct behavioral economics and machine learning based models related to a business problem. These models can be used to optimize and personalize business interventions to influence consumers' purchasing behavior to achieve the best business outcome (in B2C use cases) and de-bias distorted information sharing in supply chains (in B2B use cases). By contrast, traditional consumer and supply chain analytics solutions lack behavioral insights and often lead to sub-optimal decision making because economic optimization approach alone is not adequate for decision making where behavioral biases are present.

Abstract: In example implementations described herein, person images obtained by object detection and tracking are stored in an image database. Then the system automatically samples a person image as a query of image search for past images. Filtering is performed on the search results to extract a person images having a similarity higher than certain threshold. Travel time is calculated by sorting information (camera identifier, time) attached to person images on a timeline, and the system detects gap between periods that the person appears in frame.

Abstract: Example implementations described herein involve an attribute of an inflow source that is assigned to each trajectory in the camera view, which is used for crowd analysis. The inflow source is estimated using techniques of tracking across cameras. If the inflow source is different even if the flow trajectories are the same direction, the trajectories are visualized in different styles. By using the attribute of the inflow source, it is possible to detect changes and anomalies in the crowd that were difficult to detect using the prior art.

Abstract: Example implementations are directed to eliminating or reducing the invoicing business process by using replicated states as single truth for sub-groups participating in a supply chain network involving a large number of transient partners in a low trust ecosystem. All activities of the business process such as invoicing are shared as single truth of replicated states for the subgroup. The confidential data involving terms of reference for business process is shared separately as single truth of replicated states among such partners. The validations for business process such as invoicing can be derived by executing smart contracts on such replicated states that have single truth about transactions among different sub-groups/channels in supply chain, thereby reducing/eliminating need for invoice generation that need to be manually verified, validated and acknowledged among supplier and customers for payments.

Abstract: Systems and methods described herein can involve establishing a blockchain network between a plurality of organizations, each organization representing a different mode of transport and/or transit oriented service providers; deriving multi-modal features from first data sources of the plurality of organizations in the blockchain and second data sources off the blockchain; constructing a multi-modal network that integrates the different mode of transports from the plurality of organizations from the derived multi-modal features; executing smart contracts between the plurality of organizations across the blockchain in accordance with service level agreements generated from reinforcement learning through the multi-modal model derived from the multi-modal network; and providing, through a micro-application, access to multi-modal transportation services based on the executed smart contracts.

Abstract: Example implementations described herein are directed to an asset management system configured to facilitate real-time inventory recognition with image analysis tagged with positional information. The example implementations described herein also provide the method and process to improve the accuracy of the pipe detection for counting with various approaches. Referring the expected number of the pipes, example implementations utilize the pipe detection algorithm, as well as the bounding box of the pipe stack, use the knowledge of the physical size of the pipe stack, and analyze a pipe stack from the images of two directions at the end.

Abstract: Example implementations are directed to eliminating or reducing the invoicing business process by using replicated states as single truth for sub-groups participating in a supply chain network involving a large number of transient partners in a low trust ecosystem. All activities of the business process such as invoicing are shared as single truth of replicated states for the subgroup. The confidential data involving terms of reference for business process is shared separately as single truth of replicated states among such partners. The validations for business process such as invoicing can be derived by executing smart contracts on such replicated states that have single truth about transactions among different sub-groups/channels in supply chain, thereby reducing/eliminating need for invoice generation that need to be manually verified, validated and acknowledged among supplier and customers for payments.

Abstract: In example implementations described herein, person images obtained by object detection and tracking are stored in an image database. Then the system automatically samples a person image as a query of image search for past images. Filtering is performed on the search results to extract a person images having a similarity higher than certain threshold. Travel time is calculated by sorting information (camera identifier, time) attached to person images on a timeline, and the system detects gap between periods that the person appears in frame.

Abstract: Example implementations described herein are directed to a solution to the problem of accurate real-time inventory counting and industrial inspection. The solution, involves a device such as a mobile device that assists a human operator on the field to quickly achieve high quality inspection results. The example implementations detect objects of interest in individual image snapshots and use location and orientation sensors to integrate the snapshots to reconstruct a more accurate virtual representation of the inspection area. This representation can then be reorganized in various ways to derive inventory counts and other information that are not planned originally.

Abstract: Example implementations described herein are directed to a tag using a color/pattern coding scheme for better use in industrial settings which may involve curved objects such as pipes. The tag can include one or more anchors indicative of an orientation of the tag; a calibration pattern mapping each of a plurality of colors/patterns to one or more values; and encoded information provided on the tag in one or more of the plurality of colors/patterns. The tag may be printed directly on the object to ensure longevity and readability, or attached as a sticker or printed label depending on the desired implementation.

Abstract: Example implementations described herein are directed to a tag using a color/pattern coding scheme for better use in industrial settings which may involve curved objects such as pipes. The tag can include one or more anchors indicative of an orientation of the tag; a calibration pattern mapping each of a plurality of colors/patterns to one or more values; and encoded information provided on the tag in one or more of the plurality of colors/patterns. The tag may be printed directly on the object to ensure longevity and readability, or attached as a sticker or printed label depending on the desired implementation.

Abstract: Example implementations described herein are directed to the projection of two dimensional (2D) image recognition results to three dimensional (3D) space by using 3D reconstructed data to realize accurate object counting, identification, scene re-organization, and so on in accordance with the desired implementation. Through the example implementations described herein, more accurate objection detection can be provided than regular 2D object detection.

Abstract: Example implementations described herein are directed to a solution to the problem of accurate real-time inventory counting and industrial inspection. The solution, involves a device such as a mobile device that assists a human operator on the field to quickly achieve high quality inspection results. The example implementations detect objects of interest in individual image snapshots and use location and orientation sensors to integrate the snapshots to reconstruct a more accurate virtual representation of the inspection area. This representation can then be reorganized in various ways to derive inventory counts and other information that are not planned originally.

Abstract: Example implementations described herein are directed to an asset management system configured to facilitate real-time inventory recognition with image analysis tagged with positional information. The example implementations described herein also provide the method and process to improve the accuracy of the pipe detection for counting with various approaches. Referring the expected number of the pipes, example implementations utilize use the pipe detection algorithm as well as the bounding box of the pipe stack, use the knowledge of the physical size of the pipe stack, and analyze a pipe stack from the images of two directions at the end.

Abstract: In some examples, a system may receive log data including a depth-series of data for a sensed parameter. The system may determine a parameter value of the depth series data for individual subunits of depth corresponding to a larger unit of depth. The system may further determine a scale of graphic effects corresponding to parameter values for the depth-series data. The system may present, on a display, a visualization of the depth-series data. For instance, the visualization may include a plurality of cells arranged in a plurality of rows, with each cell corresponding to the larger unit of depth and including a plurality of subcells corresponding to the subunits of depth. Additionally, each subcell may be presented with a respective graphic effect corresponding to the parameter value determined at a corresponding depth, and the graphic effect may correspond to the parameter value on the scale of graphic effects.

Abstract: In some examples, a system may receive log data including a depth-series of data for a sensed parameter. The system may determine a parameter value of the depth series data for individual subunits of depth corresponding to a larger unit of depth. The system may further determine a scale of graphic effects corresponding to parameter values for the depth-series data. The system may present, on a display, a visualization of the depth-series data. For instance, the visualization may include a plurality of cells arranged in a plurality of rows, with each cell corresponding to the larger unit of depth and including a plurality of subcells corresponding to the subunits of depth. Additionally, each subcell may be presented with a respective graphic effect corresponding to the parameter value determined at a corresponding depth, and the graphic effect may correspond to the parameter value on the scale of graphic effects.

Abstract: Systems and methods are directed to oil and gas management. In example implementations, data relating to oil and gas management is aggregated and placed in a cube along several cube dimensions, which can include scalar, temporal and spatial dimensions. The dimensions can be structured as a hierarchy, such that output can be generated as a roll up or roll down along the hierarchy.