Abstract: A method includes assigning unique symbols to pages of a website, respectively. The method includes obtaining page symbol sequences of browsing sessions, respectively. Each browsing session corresponds to a visitor of the website. For each browsing session, the page symbol sequence of the browsing session is a sequence of symbols that corresponds, respectively, to a sequence of pages of the website visited during the browsing session by the corresponding visitor. The method includes generating a master string including the page symbol sequences, generating a suffix array corresponding to the master string, and generating a longest common prefix (LCP) array corresponding to the suffix array. The method includes, based on the suffix array and LCP array, determining one or more most common n-step subsequences of pages (n is an integer greater than 1).

Abstract: A system and method in accordance with example embodiments for comprehensive sales and service data reporting. Sales and service events that take place at a front end branch of an enterprise may be input into a front end system and transmitted to a backend system where various modules then use the front end system data to generate various data and reports to display various data, such as, for example, sales incentive metrics and key performance indicators.

Abstract: A method by smart mobility platform includes a mobile application executing on a mobile device, an authentication server, a mobile application server, and a driving telemetry service. The mobile application registers and activates a user account for driving monitoring and rewards. Trip detection is enabled and raw data is transformed to driving factors by the driving telemetry service. The mobile application server converts the driving factors to a safe driving score. The score may be combined with a customer value to determine reward payout. The platform authenticates users and validates requests using electronic mail and short messaging services to ensure privacy and security.

Abstract: Systems and methods for model evaluation. A model is evaluated by performing a decomposition process for a model output, relative to a baseline input data set.

Abstract: A device may receive network data, business data, and user configuration data associated with an entity that is a candidate for a private network and may process the business data and the user configuration data, with a classification machine learning model, to determine a network hardware equipment prediction. The device may process the network data and the business data, with a first linear regression machine learning model, to determine a business output prediction and may utilize a second linear regression machine learning model to determine a data consumption prediction based on the network hardware equipment prediction. The device may process the network hardware equipment prediction, the business output prediction, and the data consumption prediction, with a machine learning model, to determine a financial profitability prediction for the private network and may perform one or more actions based on the financial profitability prediction.

Abstract: A method of imaging a turbine engine test component with a first surface and a second surface that is spaced from the first surface. The turbine engine test component includes a plurality of film holes with inlets formed in the second surface or interior that are fluidly coupled to outlets formed in the first surface or exterior. The method includes flowing airflow through the plurality of film holes of the turbine engine test component, obtaining thermographic data, determining a test dataset, and calculating a performance score.

Abstract: Systems and methods for model evaluation. A protected class model that satisfies an accuracy threshold is built by using: data sets for use by a modeling system being evaluated, and protected class membership information for each data set. A target for the protected class model is a protected class membership variable indicating membership in a protected class. Each predictor of the protected class model is a predictor of an evaluated model used by the modeling system. A target of the evaluated model is different from the target of the protected class model. Each predictor is a set of one or more variables of the data sets. For each predictor of the protected class model, a protected class model impact ranking value and a modeling system impact ranking value are determined.

Abstract: A system for road accident avoidance receives sensor data from computing devices associated with vehicles traveling on a road. The system communicates the sensor data to a blockchain network as blockchain records. The system determines that the sensor data includes an indication of a road accident. The system determines a location of the road accident from the sensor data. The system communicates, to the blockchain ledger, data that indicates the location of the road accident. The system identifies one or more vehicles within a threshold distance of the road accident that are traveling toward the road accident. The system communicates an alert signal that comprises the location of the road accident to each vehicle. The system determines a routing recommendation for each vehicle based on the location of the vehicle and the location of the road accident. The system communicates the routing recommendation to the vehicle.

Abstract: A system of orchestrating a peer-to-peer network of vehicles for data transmission comprises a peer-to-peer (p2p) network orchestrator device and a first computing device associated with a vehicle. The p2p network orchestrator device receives vehicle data that includes locations and wireless fidelity (WiFi) capability indicators of vehicles. The p2p network orchestrator device generates a security token for each vehicle. The p2p network orchestrator device establishes a blockchain ledger that includes the vehicle data and the security tokens. The first computing device receives a copy of the blockchain ledger. The first computing device receives, from a second computing device, a request to forward a data packet to a base station, the request includes a security token of a second vehicle. The first computing device determines that the security token is valid. In response, the first computing device accepts the data packet and forwards it to the base station.

Abstract: Systems and methods for model evaluation. A protected class model that satisfies an accuracy threshold is built by using: data sets for use by a modeling system being evaluated, and protected class membership information for each data set. A target for the protected class model is a protected class membership variable indicating membership in a protected class. Each predictor of the protected class model is a predictor of an evaluated model used by the modeling system. A target of the evaluated model is different from the target of the protected class model. Each predictor is a set of one or more variables of the data sets. For each predictor of the protected class model, a protected class model impact ranking value and a modeling system impact ranking value are determined.

Abstract: Systems and methods for providing a user interface that facilitates application development. The applications may utilize one or more underlying machine-learning models to perform application functions. Exemplary implementations may: effectuate presentation of an application development interface to developers through client computing platforms associated with the developers; receive, from client computing devices, input information indicating feature values entered and/or selected by the developers via the user interface fields; responsive to receipt of first input information, configure a first application in accordance with the feature values included in a first feature values set; provide the configured application for user by one or more users; and/or other exemplary implementations.

Abstract: Systems and methods for generating and processing modeling workflows are disclosed. In some examples, a reference distribution of scores generated by a model is determined. The reference distribution of scores is recorded in a structured database. One or more unexpected scores are detected during execution of the model. To detect the one or more unexpected scores, a production distribution of scores is compared with the reference distribution of scores recorded in the structured database. The production distribution of scores is generated by the model for a production input data set. An alert is then provided to an external system, when an alert condition is determined to be satisfied based on the comparison. The alert indicates detection of the one or more unexpected scores.

Abstract: Disclosed are example embodiments of systems, method, and devices for generating audio assets. The example method includes receiving an input including at least one of audio, text, video, Java Script Object Notation (JSON), Extensible Markup Language (XML), Really Simple Syndication (RSS). The example method includes receiving configuration inputs including at least one of configure language, gender, and persona. The example method includes preparing for processing based on the at least one of configure language, gender, and persona. The example method includes processing the input based on the configuration inputs, the processing including at least one of transcribing, translating, brand safety, enrichment, generating custom Speech Synthesis Markup Language (SSML), and including generating an audio clip. The example method includes delivering the audio clip.

Abstract: A method includes assigning unique symbols to pages of a website, respectively. The method includes obtaining page symbol sequences of browsing sessions, respectively. Each browsing session corresponds to a visitor of the website. For each browsing session, the page symbol sequence of the browsing session is a sequence of symbols that corresponds, respectively, to a sequence of pages of the website visited during the browsing session by the corresponding visitor. The method includes generating a master string including the page symbol sequences, generating a suffix array corresponding to the master string, and generating a longest common prefix (LCP) array corresponding to the suffix array. The method includes, based on the suffix array and LCP array, determining one or more most common n-step subsequences of pages (n is an integer greater than 1).

Abstract: An example system can include: at least one processor; and non-transitory computer-readable storage storing instructions that, when executed by the at least one processor, cause the system to: provide an individualized contextual module programmed to capture individual information associated with a user, the individual information including personal information about the user; provide an artificial intelligence module programmed to use artificial intelligence to tailor an experience for the user based upon the personal information; and provide a sub-component assembly module programmed to select sub-components based upon the experience to generate a contextual interface for the user.

Abstract: A control system for controlling vehicle door movement along a door sweep trajectory between a first position and a second position, can include one or more controllers, the control system configured to: receive a sensor signal; based on the sensor signal, generate an obstacle detection map of a sensor region in the vicinity of the vehicle, the obstacle detection map comprising a location of an obstacle if present; determine an overlap of the obstacle detection map and a projected door sweep region defined by the door sweep trajectory; and generate an output signal based on the determined overlap.

Abstract: A computer-implemented method comprises identifying an audio playback device configured to reproduce audio content based on an audio input signal, wherein the audio playback device has a previously measured characteristic frequency response; retrieving the previously measured characteristic frequency response associated with the audio playback device; generating, based on the previously measured characteristic frequency response and a preferred frequency response curve for a plurality of users, a frequency response filter that modifies the previously measured characteristic frequency response of the audio playback device to a modified frequency response; processing the audio input signal with the frequency response filter to generate a filtered audio signal that differs in relative amplitude from the audio input signal in one or more frequency bands; and causing the audio playback device to play back the filtered audio signal.

Abstract: Embodiments of systems and methods for automated real-time routing within a fleet of geographically distributed drivers are disclosed. Embodiments may operate to dispatch orders and determine routing in real-time in a geographic area through application of rule-based filtering of drivers and selective application of optimal or non-optimal routing solutions utilizing the real-time locations of drivers, real-time conditions within the geographic area and the locations for the set of orders being routed by the system.

Abstract: A drone comprises at least one propeller for generating lift and an article containment area for containing an article to be carried by the drone. The floor of the article containment area comprises a dynamic support surface for supporting the article and allowing the article to move into, out of and through the article containment area. The dynamic support surface may be a conveyor belt forming the floor of the article containment area.

Abstract: Described herein are techniques for efficiently upgrading product information stored on a client device to the latest version that reflects the current products offered by a particular establishment. Product information changes frequently, which could result in large upgrade packages. Yet, the time available for downloading the packages onto a device may be severely limited. To improve download time, upgrade packages may be shard based on product commonality within different predefined scopes. For instance, information related to products common across chain-wide establishments may be upgraded using one set of upgrade packages, and information related to products common across region-wide establishments may be upgraded using another set. This upgrade framework helps reduce file size and leverage the edge-caching capabilities of content delivery networks to reduce the time needed to transmit upgrade packages to client devices.