International Business Machines Corporation

Huawei Technologies Co., Limited

Petal Cloud Technology Co., Ltd.

Weicai Zhong

Jing-Yun Shyr

Yea Jane Chu

Wenjie Zhang

Jane Y Chu

Dong Chen

Jing Jing Zhang

Min Wang

Liang Hu

Yu Wang

Songcen Xu

Sier Han

Long Jiao

Lei Hao

Zhenhua Zhao

In one example method, a first image including M objects is obtained. For N objects in the M objects, when N is greater than or equal to 2, arrangement orders of the N objects is determined, where an arrangement order of any one of the N objects is determined based on at least one of a scene intent weight, a confidence score, or an object relationship score. The scene intent weight is used to indicate a probability that the any object is searched in a scene corresponding to the first image, the confidence score is a similarity between the any object and an image in an image library, and the object relationship score is used to indicate importance of the any object in the first image. Search results of some or all of the N objects are fed back according to the arrangement orders of the N objects.

Search result feedback method and apparatus, and storage medium

This application relates to the field of digital image processing technologies, and discloses an image-text fusion method and apparatus, and an electronic device, to minimize blockage of a saliency feature in an image by a text when the text is laid out in the image, and obtain a higher visual balance degree after the text is laid out in the first image, thereby achieving a better layout effect. According to the method of this application, first, a plurality of candidate text templates and layout positions of a plurality of corresponding texts in an image can be determined, so that a text laid out in the image does not block a visually salient object having a greater feature value, such as a human face or a building. Then based on magnitudes of feature values of pixels blocked by the text, a balance degree of feature value distribution of pixels in each region in the image in which the text is laid out, and the like when the text is laid out in the image at corresponding layout positions in the image by using different text templates, a final text template of the text and a layout position of the text in the image are determined.

Image-text fusion method and apparatus, and electronic device

A theme icon generation method includes obtaining an application icon, where the application icon includes a transparent region and an opaque region, and the opaque region includes an icon background and a first logo graphic; segmenting a first logo graphic from the opaque region; adjusting a size of the first logo graphic to generate a second logo graphic; and fusing the second logo graphic with a theme template to generate a theme icon.

Theme icon generation method and apparatus, and computer device

Techniques are described for automatic interval metadata determination for intermittent time series data. In one example, a method for determining intermittent time series interval metadata includes detecting one or more time variables in a time series data set. The method further includes determining whether the one or more time variables are intermittently regular. The method further includes determining one or more respective time intervals for the one or more time variables. The method further includes determining the parameters of intermittency for the one or more time variables. The method further includes generating an output comprising information about the one or more time variables based on the one or more respective time intervals and the parameters of intermittency for the time variable.

Automatic time interval metadata determination for business intelligence and predictive analytics

Updating a prediction model, where the prediction model is used for time series data, a computer selects a first prediction time window in an order from a plurality of prediction time windows associated with the prediction model, and predicts predicted values of the time series data at time points within the first prediction time window. The computer calculates a prediction error associated with the first prediction time window based on the one or more predicted values and one or more actual measured values of the time series data at the plurality of time points. The computer determines whether the prediction error is larger than a predefined error threshold associated with the first prediction time window, and in response to determining the prediction error is larger than the predefined error threshold, provides a notification of updating the prediction model.

Updating prediction model

Techniques are described for automated selection of components for a generalized linear model. In one example, a method includes determining a candidate set of distributions, a candidate set of link functions, and a candidate set of predictor variables, based at least in part on a dataset of interest. The method further includes selecting a distribution from the initial candidate set of distributions and a link function from the initial candidate set of link functions, based at least in part on the candidate set of predictor variables; and selecting predictor variables from the candidate set of predictor variables, based at least in part on the selected distribution and the selected link function. The method further includes reiterating the selecting processes until a stopping criterion is fulfilled, and generating a generalized linear model output comprising the selected distribution, the selected link function, and the selected predictor variables.

Automated selection of generalized linear model components for business intelligence analytics

Techniques for presenting insight into classification trees may include performing a grouping analysis to group leaf nodes of a classification tree into a significant group and an insignificant group, performing influential target category analysis to identify one or more influential target categories for the leaf nodes of the classification tree in the significant group, and presenting one or more insights into the classification tree based on the grouping analysis and the influential target category analysis. Techniques for presenting insight into regression trees may include performing a grouping analysis to group leaf nodes of a regression tree into a high group and a low group, performing unusual node detection analysis to detect one or more outlier nodes in the high group and in the low group, and presenting one or more insights into the regression tree based on the grouping analysis and the unusual node detection analysis.

Growing community of inventors

Xi'an, China

Weicai Zhong