Abstract: A tool is provided with which a user in need of a service may use to select a service provider based on user-set metrics. A request for a service to be performed is received, a set of metrics are extracted from the request, a database of service provider profiles is searched in accordance with the metrics, and a service provider profile that matches the metrics is displayed. Upon selection of the service provider profile, a first message is communicated to a service provider corresponding to the service provider profile. Upon acceptance by the service provider, a second message is communicated to a client device.

Abstract: Systems and methods are provided for predicting the effects of acceleration on a probability of a successful completion of a project. Specifically, one or more machine learning algorithms can be trained to predict the success of a project from a plurality of features, including at least one feature that is a function of an end date of the project. A set of projects can be selected from projects having expected end dates that do not fall within a desired window of time, each project having a first probability of success given the current end date. A second probability is calculated for each project at a machine learning platform that quantifies a chance that the project will be successful if completed within the window of time. A difference between the first probability and the second probability is determined for each project, and the projects are selected according to the difference.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving an electronic text document. Identifying a context of the document based on mapping text from the document to entries in a plurality of concept libraries. Determining an intersection between a first entry in a first of the plurality of concept libraries and a second entry in a second of the plurality of concept libraries. Identifying a relationship between at least two concepts included in the document based on the intersection between the first entry and the second entry. Determining an intent of the document based on the context and the relationship between the at least two concepts. Automatically routing the document for further processing based on the determined intent.

Abstract: A system and method for a protocol to identify patterns among caregivers and predict the root cause of burnout, whereby the system leverages proprietary data and data collected form third party sources to assess the risk of caregivers and then adjusts accordingly based on previous data of the caregivers as well as other similar caregivers.

Abstract: The disclosed embodiments provide a system for performing activity-based inference of title preferences. During operation, the system determines features and labels related to first title preferences for jobs sought by a first set of candidates. Next, the system inputs the features and the labels as training data for a machine learning model. The system then applies the machine learning model to additional features for a second set of candidates to produce predictions of second title preferences for the second set of candidates. Finally, the system stores the predictions in association with the second set of candidates.

Abstract: Provided are systems, methods, and software for determining a probability of selling to a consumer an automotive commodity associated with a vehicle of interest to the consumer. The software retrieves individual consumer data indicating at least one of present or future needs of the consumer, historical behavior of the consumer, and demographics of the consumer. The software retrieves dealer management system (DMS) data indicating transactional data relating to automotive commodities associated with the vehicle. Deal data indicating transactional terms relating to at least one of current acquisition of the vehicle of interest by the consumer, and past acquisition of the vehicle of interest or vehicles similar to the vehicle of interest by other consumers, is retrieved. The software predicatively analyzes the individual consumer data, DMS data, and deal data and computes a probability of selling at least one of the automotive commodities to the consumer based on the predictive analysis.

Abstract: A business analytics conversational tool comprising: a device comprising a communication channel, a natural language processor (NLP), a fulfillment application program interface (F-API), a database application program interface (D-API), and a business management database; wherein: the NLP receives a user-input from a user through the communication channel; the NLP deduces an intent of the user-input; the NLP communicates the intent to the F-API; the F-API communicates a request for data associated with the intent to the database via the D-API; the D-API communicates the data associated with the intent to the F-API; the F-API converts the data associated with the intent to conversational form and sends the conversational form for voice output through the communication channel.

Abstract: Logistical operations (e.g., warehouses) may use a voice-enabled workflow to facilitate the work tasks of a staff (i.e., population) of workers. Typically, it is necessary for a worker to travel from location-to-location to complete assigned work tasks. As such, a worker's time spent travelling often correlates with the worker's overall work performance. Understanding the worker's travel performance is highly desirable, but computing a fair and accurate travel-performance metric is difficult. One reason for this is that the distance a worker travels is often unknown. The present invention embraces a system and method for accurately and fairly assessing a worker's travel performance by analyzing the worker's voice dialog.

Abstract: Embodiments of the present invention provide systems and methods for constructing a plan for creating a cloud service. In one embodiment, a configurator receives a request for one or more services making up a cloud service, and a preliminary plan for the requested services is generated. A service provider determines that it is able to fulfill a requested service, and inserts a sub plan for fulfilling the requested service into the preliminary plan. A final plan is generated, which includes a sub plan from each service provider inserted into the preliminary plan.

Abstract: Methods and systems are provided for automatically creating and displaying an action plan generated from an action plan template. An action plan template is created by a template owner, who can then add tasks to the action plan template until all tasks to be included as part of the template have been created. After it has been published, action plan owners can use it during an action plan creation process. An action plan owner can select a particular target record to be associated with a new action plan and specify other action plan details. An application platform can then automatically populate the new action plan with information indicating: a name of the action plan owner, a plurality of tasks a corresponding task owner who is assigned to each task, and a corresponding task deadline that was automatically calculated for each task by the action plan creation module.

Abstract: Improved energy conservation, including realization of a ZNET (Zero Net Energy including Transportation) paradigm, can be encouraged by providing energy consumers with a holistic view of their overall energy consumption. Current energy consumption in terms of space heating, water heating, other electricity, and personal transportation can be modeled by normalizing the respective energy consumption into the same units of energy. In addition, the passive always-on electricity consumption caused by inactive devices that contributes to the baseload of a building can be identified and addressed by the consumer, as appropriate by expressing baseload as a compound value that combines constant always-on loads and regularly-cycling loads. The baseload is estimated as the peak occurrence in a frequency distribution of net load data, after which the always-on load can be determined by subtracting out any regularly-cycling loads.

Abstract: Improved energy conservation, including realization of a ZNET (Zero Net Energy including Transportation) paradigm, can be encouraged by providing energy consumers with a holistic view of their overall energy consumption. Current energy consumption in terms of space heating, water heating, other electricity, and personal transportation can be modeled by normalizing the respective energy consumption into the same units of energy. Options for reducing energy that can include traditional energy efficiencies, such as cutting down on and avoiding wasteful energy use and switching to energy efficient fixtures, and improving the thermal efficiency and performance of a building, can be modeled. Additional options can also include non-traditional energy efficiencies, such as replacing a gasoline-powered vehicle with an electric vehicle, fuel switching from a water heater fueled by natural gas to a heat pump water heater, and fuel switching from space heating fueled by natural gas to a heat pump space heater.

Abstract: Methods, systems, and media for providing direct and hybrid data acquisition approaches are provided. In accordance with some embodiments of the disclosed subject matter, a method of data acquisition for construction of classification models that incorporates multiple human reviewing resources is provided, the method comprising: receiving a cost structure for constructing a classification model using a data set; instructing human reviewing resources to search through the data set and select instances of a class that satisfy a criterion, providing the human reviewing resources with a definition of the class; training the classification model with the instances from the human reviewing resources; determining when an expected gain for performing additional searches by the human reviewing resources as a function of the cost structure is lower than a given threshold; and, instructing the human reviewing resources searching through the set to label one or more examples from the data set.

Abstract: A method for generating a communicable disease policy plan by using machine learning. The process identifies a number of workplace policies for a number of business entities. The workplace policies comprise a number of dimensions of data collected from a number of sources. The process collects employment data for each of the business entities. The employment data includes sick leave data about employees of the plurality of business entities. The process determines metrics for the sick leave data during a given time interval; simultaneously models the workplace policies and the metrics for the sick leave data to identify correlations among the number of dimensions of data and generalize rules for predicting effective workplace policies; predicts a number of effective workplace policies for a particular business entity; and generates a communicable disease policy plan for the particular business entity based on the number of effective workplace policies.

Abstract: To increase the efficiency of a used vehicle data processing process while still tailoring to an individual user's unique specifications on a used vehicle, at least some pre-calculations are performed by a backend process before a request for data for a specified vehicle is received through a web site or a web server on the Internet. A user can be presented with an interface where the user can make a variety of determinations. After the user requests data on a specific vehicle configuration, a frontend process handles user-provided data in conjunction with the data calculated in the backend process to ensure that the results are better tailored to the user's specific vehicle attributes. The results can include pricing data such as a trade-in price, a list price, an expected sale price or range of sale prices, market low sale price, market average sale price, market high sale price, etc.

Abstract: Methods and systems for forecasting demand for a plurality of items are provided. In particular, the demand forecasting system and methods described herein are useful for predicting demand of products in a retail context. Forecast models are built and used to score incoming sales data to predict future demand for items. Forecast models are validated by evaluating actual demand against predicted demand and using that information to inform how future ensemble forecast will be generated. Forecasts may be broken down into smaller components to satisfy a variety of requests for data from client applications.

Abstract: Embodiments relate to storing farming activity values into geospatial containers associated with a spatial grid system, and generating data analytics therefrom. Pulse data collected by a data collection device and associated with a swath width of a farming implement can be obtained. A pulse polygon can be generated based on the swath width and location information included in the pulse data. The pulse polygon can be translated into at least one grid cell of a plurality of grid cells of a spatial grid system, such that the at least one grid cell geographically corresponds to the pulse polygon. Relevant data points extracted from the pulse data can be stored into a geospatial container generated for each grid cell of the at least one grid cell. Any of the geospatial containers can thus be selectively analyzed, independently or in combination with other geospatial containers, to derive accurate insights therefrom.

Abstract: A system and method for interactively evaluating energy-related investments affecting building envelope with the aid of a digital computer are provided. Obtained is a total amount of fuel purchased for a building over a set period from which an existing amount of the fuel consumed for space heating is derived. Characteristics including thermal performance and furnace and delivery efficiencies of the building for both existing and proposed equipment are obtained, including remotely controlling a heating source inside the building. The thermal performance and furnace and delivery efficiencies characteristics of the existing and proposed equipment are expressed as interrelated ratios. An amount of fuel to be consumed for space heating is evaluated as a function of the existing amount of the fuel consumed for space heating and the ratios of the existing and proposed equipment.

Abstract: Gross energy load can be determined by combining periodic net load statistics, such as provided by a power utility or energy agency, with on-site power generation, such as photovoltaic power generation, as produced over the same time period. The gross energy load provides an indication upon which other types of energy investment choices can be evaluated. These choices can include traditional energy efficiencies, such as implementing electrical efficiency measures, which includes cutting down on and avoiding wasteful energy use and switching to energy efficient fixtures, and improving the thermal efficiency and performance of a building. The choices can also include non-traditional energy efficiencies, such as replacing a gasoline-powered vehicle with an electric vehicle, fuel switching from a water heater fueled by natural gas to a heat pump water heater, and fuel switching from space heating fueled by natural gas to a heat pump space heater.

Abstract: Various embodiments relate generally to computer science, data science, software, and computer program and platform architectures, including receiving from a device geolocation data and input data, parsing the input data, evaluating the event data and the location data to generate shipment data, parsing the account to identify subscription data, selecting a sample associated with another item, the sample being selected by an adaptive distribution platform, transmitting other data to the device that renders an electronically-displayed message on an interface on the device, calling one or more data services to retrieve item data associated with the item, and generating a retrieval option associated with the item if the threshold, the query, and the additional input data indicates the device is within a numerical range of the first location or an alternative location and retrieval of the item from the first location is indicated.