Abstract: A method to provide multi-objective recommendations. The method includes receiving user input indicating a plurality of objectives, where each of the plurality of objectives indicates a desired goal for a field of interest, receiving user input indicating a plurality of actionable fields, receiving user input indicating selection of one of a plurality of records in a data set, determining, based on applying an evolutionary algorithm, one or more candidate changes to values of the plurality of actionable fields of the selected record, determining, for each of the one or more candidate changes, a multi-objective score for that candidate change, selecting one or more of the one or more candidate changes to recommend to a user based on the multi-objective scores of the one or more candidate changes, and providing, for display to the user, the selected one or more candidate changes as recommended changes.

Abstract: A method to provide multi-objective recommendations. The method includes receiving user input indicating a plurality of objectives, where each of the plurality of objectives indicates a desired goal for a field of interest, receiving user input indicating a plurality of actionable fields, receiving user input indicating selection of one of a plurality of records in a data set, determining, based on applying an evolutionary algorithm, one or more candidate changes to values of the plurality of actionable fields of the selected record, determining, for each of the one or more candidate changes, a multi-objective score for that candidate change, selecting one or more of the one or more candidate changes to recommend to a user based on the multi-objective scores of the one or more candidate changes, and providing, for display to the user, the selected one or more candidate changes as recommended changes.

Abstract: The technology disclosed determines which field values in a set of unique field values for a particular field in a fielded dataset are anomalous using six similarity measures. A factor vector is generated per similarity measure and combined to form an input matrix. A convolutional neural network processes the input matrix to generate evaluation vectors. A fully-connected network evaluates the evaluation vectors to generate an anomaly scalar for a particular unique field value. Thresholding is applied to anomaly scalar to determine whether the particular unique field value is anomalous.

Abstract: Examples are described herein that relate to determining a level of relatedness between datasets. An approximation can be made of whether an entry in a first dataset appears in a same row as an entry in a second dataset. The approximation can be made by grouping entries in the second dataset together and determining an occurrence that an entry occurs in a same row as any of the entries in a grouping of entries. A test of independence between datasets can be made based at least on the occurrence values. Datasets can be ranked according to level of independence and presented to a user as candidates to join with a dataset. Occurrence values or rankings can be precomputed and available for use so that join candidates can be presented with a little amount of perceived delay to a user. A user interface can present join candidates for a dataset and allow the user the select datasets for joining. Joining of first and second datasets can supplement entries in both of the datasets and create a third dataset.

Abstract: System and methods are described for improving automated data discovery analysis in a cloud computing environment. A method includes receiving a request to analyze a data set stored in the memory device, the data set including one or more columns, the one or more columns including one or more data values in one or more cells of each column; classify each of the one or more columns as a type of column; for a selected one of the one or more columns, if the selected column's type is an external type, join one or more columns of an external knowledge base correlated to the selected column into the data set to create an expanded data set; and execute an automated data discovery model on the expanded data set.

Abstract: The technology disclosed determines which field values in a set of unique field values for a particular field in a fielded dataset are anomalous using six similarity measures. A factor vector is generated per similarity measure and combined to form an input matrix. A convolutional neural network processes the input matrix to generate evaluation vectors. A fully-connected network evaluates the evaluation vectors to generate an anomaly scalar for a particular unique field value. Thresholding is applied to anomaly scalar to determine whether the particular unique field value is anomalous.

Abstract: The technology disclosed determines one or more field values in a set of field values for a particular field in a fielded dataset that are similar to an input value using six similarity measures. A factor vector is generated per similarity measure and combined to form an input matrix. A convolutional neural network processes the input matrix to generate evaluation vectors. A fully-connected network evaluates the evaluation vectors to generate suggestion scalars for similarity to a particular input value. Thresholding is applied to suggestions scalars to determine one or more suggestion candidates for the particular input value.

Abstract: Methods, systems, and devices supporting dynamic process orchestration are described. An orchestration server may receive a request defining a data modification process from a user device. The orchestration server may generate an execution file based on the request, and the execution file may include a set of tasks for performing the data modification process and an order for performing the set of tasks. The orchestration server may execute, for the execution file, a first set of tasks according to the order for performing the set of tasks and, in some cases, may update the execution file based on executing the first subset of tasks. For example, updating the execution file may involve modifying a second subset of tasks of the set of tasks. The orchestration server may execute, for the updated execution file, the modified second subset of tasks according to the order for performing the set of tasks.

Abstract: Examples are described herein that relate to determining a level of relatedness between datasets. An approximation can be made of whether an entry in a first dataset appears in a same row as an entry in a second dataset. The approximation can be made by grouping entries in the second dataset together and determining an occurrence that an entry occurs in a same row as any of the entries in a grouping of entries. A test of independence between datasets can be made based at least on the occurrence values. Datasets can be ranked according to level of independence and presented to a user as candidates to join with a dataset. Occurrence values or rankings can be precomputed and available for use so that join candidates can be presented with a little amount of perceived delay to a user. A user interface can present join candidates for a dataset and allow the user the select datasets for joining. Joining of first and second datasets can supplement entries in both of the datasets and create a third dataset.

Abstract: The present invention discloses an intelligent traffic safety pre-warning method, a cloud server, onboard-terminals and a system. The method comprises: a step (101): the onboard-terminal establishes a communication connection with the cloud server; a step (102): the onboard-terminal acquires data, and uploads data calculated based on the acquired data to the cloud server; a step (103): the onboard-terminal receives feedbacks from the cloud server, the feedback comprising the probability that the current vehicle has an accident within a set range of the current road segment; and a step (104): the onboard-terminal receives the probability that the current vehicle has an accident within the set range of the current road segment, and then transmits the feedback to the driver by human-computer interaction.

Abstract: System and methods are described for visual data cleaning in a cloud computing environment. A method includes receiving a request for transformation of data values in cells of a selected column of a data set stored in a memory, applying the transformation on the selected column, if the selected column exists in a hierarchical relationship graph, determining zero or more columns of the data set affected by the transformation on the selected column according to the hierarchical relationship graph, and if there are one or more affected columns, predicting expected values for cells in the one or more affected columns according to a knowledge base.

Abstract: System and methods are described for improving automated data discovery analysis in a cloud computing environment. A method includes receiving a request to analyze a data set stored in the memory device, the data set including one or more columns, the one or more columns including one or more data values in one or more cells of each column; classify each of the one or more columns as a type of column; for a selected one of the one or more columns, if the selected column's type is an external type, join one or more columns of an external knowledge base correlated to the selected column into the data set to create an expanded data set; and execute an automated data discovery model on the expanded data set.

Abstract: The present invention discloses an intelligent traffic safety pre-warning method, a cloud server, onboard-terminals and a system. The method comprises: a step (101): the onboard-terminal establishes a communication connection with the cloud server; a step (102): the onboard-terminal acquires data, and uploads data calculated based on the acquired data to the cloud server; a step (103): the onboard-terminal receives feedbacks from the cloud server, the feedback comprising the probability that the current vehicle has an accident within a set range of the current road segment; and a step (104): the onboard-terminal receives the probability that the current vehicle has an accident within the set range of the current road segment, and then transmits the feedback to the driver by human-computer interaction.

Abstract: An online system manages data by determining relevance of data dimensions to users. The online system determines which data dimensions a user is likely to be interested in. If a user requests to access a data set that includes data of different dimensions, the online system analyzes the dimensions' relevance to the user before providing the data set to the user. The online system provides the data to the user by prioritizing data dimensions that are more relevant to the user. As such, the online system improves the user experience by allowing users to conveniently and quickly locate relevant data and minimizing the distraction caused by irrelevant data. The online system may create and provide a user interface to present data dimensions that are determined to be relevant.

Abstract: The present application relates to a service battery charging management device and method for power supply of a recreational vehicle, wherein, the service battery charging management device for power supply of recreational vehicle includes: a vehicle generator, a solar cell panel, a MCU main control unit, an input automatic switching unit, a charging main converting DC/DC circuit, a service battery, a PWM mode charging unit, and a load. The MCU main control unit controls the input automatic switching unit according to an output voltage of the solar cell panel and an output voltage of the vehicle generator, which enables the solar cell panel and the vehicle generator to selectively serve as a charging power supply of the service battery to enable the service battery to be kept in an alternative-charging state, so that normal power supply of household electricity consumption of the recreational vehicle can be guaranteed.

Abstract: The present application relates to a service battery charging management device and method for power supply of a recreational vehicle, wherein, the service battery charging management device for power supply of recreational vehicle includes: a vehicle generator, a solar cell panel, a MCU main control unit, an input automatic switching unit, a charging main converting DC/DC circuit, a service battery, a PWM mode charging unit, and a load. The MCU main control unit controls the input automatic switching unit according to an output voltage of the solar cell panel and an output voltage of the vehicle generator, which enables the solar cell panel and the vehicle generator to selectively serve as a charging power supply of the service battery to enable the service battery to be kept in an alternative-charging state, so that normal power supply of household electricity consumption of the recreational vehicle can be guaranteed.

Abstract: An online system manages data by determining relevance of data dimensions to users. The online system determines which data dimensions a user is likely to be interested in. If a user requests to access a data set that includes data of different dimensions, the online system analyzes the dimensions' relevance to the user before providing the data set to the user. The online system provides the data to the user by prioritizing data dimensions that are more relevant to the user. As such, the online system improves the user experience by allowing users to conveniently and quickly locate relevant data and minimizing the distraction caused by irrelevant data. The online system may create and provide a user interface to present data dimensions that are determined to be relevant.

Abstract: The technology disclosed determines one or more field values in a set of field values for a particular field in a fielded dataset that are similar to an input value using six similarity measures. A factor vector is generated per similarity measure and combined to form an input matrix. A convolutional neural network processes the input matrix to generate evaluation vectors. A fully-connected network evaluates the evaluation vectors to generate suggestion scalars for similarity to a particular input value. Thresholding is applied to suggestions scalars to determine one or more suggestion candidates for the particular input value.

Abstract: The technology disclosed determines which field values in a set of unique field values for a particular field in a fielded dataset are anomalous using six similarity measures. A factor vector is generated per similarity measure and combined to form an input matrix. A convolutional neural network processes the input matrix to generate evaluation vectors. A fully-connected network evaluates the evaluation vectors to generate an anomaly scalar for a particular unique field value. Thresholding is applied to anomaly scalar to determine whether the particular unique field value is anomalous.

Abstract: Disclosed are a method for searching a cross-regional power supply area based on a common information model (CIM) and a system thereof. In the method, a hash function is first created according to a size of a power grid in which a power source is located; identification numbers of all devices in the power grid are mapped to a discrete hash table according to the hash function, and a collision is solved by using separate chaining; and a hash topological graph of the power grid is formed by using the discrete hash table; and a power supply area of a designated device is searched by using the hash topological graph. According to the present invention, devices in a power supply area are located rapidly and accurately by creating a discrete hash table for all device resources, so that the amount of computation is greatly reduced, and the efficiency of searching the power supply area is significantly improved.