Abstract: A system and method of determining whether specific clauses in a contract have a likelihood of falling under a particular risk category is disclosed. The proposed systems and methods describe an autonomous digital assistant that accepts contract-related queries from end-users and generates conversational responses. For example, an end-user may request information about the contract's terms, and the system can automatically provide intelligent analytical responses that bypass the need to manually evaluate the various features of the document.

Abstract: This application discloses a system and method for federated collaborative machine learning model development using local training datasets that are not shared. An adaptive and evolutionary approach is used to select local training nodes that are most fit from one training round to the next training round to optimize an overall cost and performance function for the federated learning, to cross-over model architecture between local training nodes, and to perform model architecture mutation within local training nodes. The local training nodes are further clustered to account for the inhomogeneity in the local datasets. Such adaptive, evolutionary, and collaborative federated learning thus provides cost-effective and high-performance model development.

Abstract: A device may receive assessment scores for a candidate associated with an entity and performance data identifying performance metrics and time periods associated with existing members of the entity. The device may process the assessment scores and the performance data, with an attrition model, to identify attrition scores for the candidate and confidences of the attrition scores, and may calculate a final attrition score based on the attrition scores. The device may process the assessment scores and the performance data, with a performance model, to identify performance scores for the candidate and confidences of the performance scores, and may calculate a final performance score based on the performance scores. The device may calculate an overall score based on the final attrition score and the final performance score, and may perform one or more actions based on the overall score.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that leverage artificial intelligence and machine learning (ML) to forecast energy demand and to generate an energy plan for one or more facilities of an organization. For example, a system may forecast an occupancy of the facilities for use with historical demand data in forecasting the energy demand. The forecasting may be performed by one or more trained ML models. Additional ML models may be trained to select energy resources that satisfy the forecasted energy demand and that prioritize constraint(s). The system may generate an energy plan that indicates information related to the selected energy resources, such as cost, energy type, environmental impact, etc., for use in increasing an amount of renewable energy resources used at the facilities. In some implementations, the system may recommend actions to reduce a negative environmental impact associated with the selected energy resources.

Abstract: A system and method of determining whether specific clauses in a contract have a likelihood of falling under a particular risk category is disclosed. The proposed systems and methods describe an autonomous digital assistant that accepts contract-related queries from end-users and generates conversational responses. For example, an end-user may request information about the contract's terms, and the system can automatically provide intelligent analytical responses that bypass the need to manually evaluate the various features of the document.

Abstract: A device may receive assessment scores for a candidate associated with an entity and performance data identifying performance metrics and time periods associated with existing members of the entity. The device may process the assessment scores and the performance data, with an attrition model, to identify attrition scores for the candidate and confidences of the attrition scores, and may calculate a final attrition score based on the attrition scores. The device may process the assessment scores and the performance data, with a performance model, to identify performance scores for the candidate and confidences of the performance scores, and may calculate a final performance score based on the performance scores. The device may calculate an overall score based on the final attrition score and the final performance score, and may perform one or more actions based on the overall score.

Abstract: A method for predicting conditions associated with a coal stock pile is described. The method includes collecting aerial data for a site including one or more coal stock piles. Using the aerial data, the method includes performing localization of the site to identify boundaries of the coal stock piles and extracting multi-spectral features. The method also includes obtaining additional data associated with the coal stock piles from at least one data source and merging the aerial data with the additional data. Using the merged data and the extracted multi-spectral features, the method includes analyzing a status of the coal stock piles by a prediction module to predict at least one of an impending combustion event or a severe condition associated with the coal stock piles. In response to the predicted at least one impending combustion event or severe condition, the method includes implementing a response.

Abstract: A method for predicting conditions associated with a coal stock pile is described. The method includes collecting aerial data for a site including one or more coal stock piles. Using the aerial data, the method includes performing localization of the site to identify boundaries of the coal stock piles and extracting multi-spectral features. The method also includes obtaining additional data associated with the coal stock piles from at least one data source and merging the aerial data with the additional data. Using the merged data and the extracted multi-spectral features, the method includes analyzing a status of the coal stock piles by a prediction module to predict at least one of an impending combustion event or a severe condition associated with the coal stock piles. In response to the predicted at least one impending combustion event or severe condition, the method includes implementing a response.

Abstract: Presence of natural enemies has a considerable impact on pest severity in a given geo-location. However, manually estimating pest severity or population of natural enemies is cumbersome, inaccurate and not scalable. Systems and methods of the present disclosure enable estimating effective pest severity index by receiving a first set of inputs pertaining to weather associated with a geo-location under consideration; receiving a second set of inputs pertaining to agronomic information; generating a pest forecasting model and a natural enemies forecasting model based on the received first set and the second set of inputs for each pest; and estimating the effective pest severity index based on the generated models. The timing and quantity of pesticide application can be optimized based on the estimated pest severity index. The generated models can be further enhanced continually based on one or more of historical data, participatory sensing inputs, crowdsourcing inputs and management practices.

Abstract: Traceability of agricultural activities is very critical to market compliance. Mere automation of traditionally monitored agricultural activities alone may not address the challenge of providing a simple yet flexible and predictable method of effective and real time monitoring of agricultural activities around the farm that may be used to compute crop protocol for any crop under consideration. The systems and methods of the present disclosure facilitate automatic identification of crop protocol irrespective of the type of the crop and agricultural activities associated thereof. Real time monitoring of the agricultural activities also enable farm personnel to conclude on effects of dynamic changes in crop protocol thereby allowing continuous building up of the repository of agro-climatic zone based information associated with the farm. Regulating crop protocol results in a predictable increase in efficiency and sustainability of crop yield that helps farm personnel to optimize productivity.

Abstract: Presence of natural enemies has a considerable impact on pest severity in a given geo-location. However, manually estimating pest severity or population of natural enemies is cumbersome, inaccurate and not scalable. Systems and methods of the present disclosure enable estimating effective pest severity index by receiving a first set of inputs pertaining to weather associated with a geo-location under consideration; receiving a second set of inputs pertaining to agronomic information; generating a pest forecasting model and a natural enemies forecasting model based on the received first set and the second set of inputs for each pest; and estimating the effective pest severity index based on the generated models. The timing and quantity of pesticide application can be optimized based on the estimated pest severity index. The generated models can be further enhanced continually based on one or more of historical data, participatory sensing inputs, crowdsourcing inputs and management practices.

Abstract: The present invention relates to collecting and dissemination of exact and instantaneous commodity pricing information of any market from remote locations with the help of individuals present in the market by utilizing localization application loaded in their mobile phones or base station. The current prices undertaken by individuals in the market is updated in a centralized commodity database which can be queried from any remote location using mobile phone or remote computer over internet. The presence of the information provider is determined by approximating contours of the target premises which minimizes the memory required to store information in the mobile phone. In an alternative embodiment, the instantaneous price information is obtained by connecting electronic transaction payment system with the central commodity database.

Abstract: The method and system for a computer implemented agricultural activity monitoring and training is described herein. The system comprises a plurality of sensors to sense the agriculture activities and environment parameters to generate sensor data. A transceiver presents in the system transfer the sensor data to the server. The server comprises a activity detection module to detect the agriculture activities performed by an individual. A monitoring feedback generator to generate a monitoring feedback based on detected activity. A remote training module determines a performance score of the activity performed by the individual and sends training feedback to the individual based on the performance score.

Abstract: A method and system is provided for classifying plant disease in a geographical region through crowdsourcing using mobile communication device, wherein method comprising generation and distributing of a first set of task pertaining to a plurality of plant disease attributes to a first group of user via a mobile crowd sourcing application; collecting response from the first group of user against distributed first set of task and aggregating the same for generating a subsequent set of task pertaining to the plurality of plant disease attributes for distributing to a subsequent group of user; aggregating collected response of the subsequent set of task; and classifying plant disease and determining severity of the classified plant disease.

Abstract: The present invention relates to collecting and dissemination of exact and instantaneous commodity pricing information of any market from remote locations with the help of individuals present in the market by utilizing localization application loaded in their mobile phones or base station. The current prices undertaken by individuals in the market is updated in a centralized commodity database which can be queried from any remote location using mobile phone or remote computer over internet. The presence of the information provider is determined by approximating contours of the target premises which minimizes the memory required to store information in the mobile phone. In an alternative embodiment, the instantaneous price information is obtained by connecting electronic transaction payment system with the central commodity database.