Abstract: Methods and systems for selecting a tool for a project is described. In an example, a processor can run a machine learning model to generate a set of requirements to implement a project. The processor can identify a keyword from the set of requirements. The processor can search for the keyword on a search engine. The processor can receive a search result from the search engine corresponding to the keyword. The processor can identify, based on the search result, a tool that can be used to implement the project, where the tool can be in compliance with the set of requirements.

Abstract: In an approach for a text block recognition in a document, a processor detects characters in the document using an object detection technique. A processor identifies positions of the detected characters in the document. A processor analyzes semantic connectivity among the detected characters based on the positions and semantic connectivity of the characters. A processor recognizes text blocks of related characters based on the semantic connectivity analysis. A processor outputs the text blocks associated with the related characters.

Abstract: Example implementations of the present disclosure relate to method, apparatus, device and computer-readable storage medium for a medical assistance operation. In a method, input data is obtained from an endoscope; and information related to an operation behavior of the endoscope is determined based on the input data. According to the above method, the information related to the operation behaviors of the endoscope may be provided in real time based on the current spot of the endoscope. Accordingly, a medical assistance operation may be further provided to a doctor in real time during the endoscopic examination. Furthermore, corresponding apparatus, device and computer storage medium are also provided.

Abstract: In an approach to blockchain management of cloud service provisioning failures, one or more computer processors capture one or more application programming interface (API) calls associated with a service provision. One or more computer processors submit the captured one or more API calls to a blockchain ledger. One or more computer processors detect a system failure during the service provision. One or more computer processors extract the submitted one or more API calls from the blockchain ledger. Based on the extracted one or more API calls, one or more computer processors identify a problematic system associated with the system failure.

Abstract: A method, system, and computer program product for implementing automated cognitive software application error detection is provided. The method includes receiving data associated with model based self-learning software code. The annotated data is automatically divided with respect to specified categorization and grouping attributes and categorized groups comprising portions of the annotated data are generated and analyzed. At least one incorrect annotation associated a group of the categorized groups is detected and filtered. Likewise, a correct annotation for the group is detected and retrieved from a database. The correct annotation is appended to the group.

Abstract: The present disclosure relates to methods, devices and computer-readable storage media for model training and data processing. The method for model training comprises: determining respective degrees of influence of a plurality of augmented sample sets in a training set on a model to be trained, the plurality of augmented sample sets corresponding to a plurality of original samples; determining, based on the degrees of influence, a first group of augmented sample sets from the plurality of augmented sample sets, the first group of augmented sample sets being to have a negative influence on the model to be trained; determining a training loss function associated with the training set, in the training loss function, a first weight being allocated to augmented samples from the first group of augmented sample sets to reduce the negative influence; and training the model to be trained based on the training loss function and the training set. In this way, the performance of the trained model can be optimized.

Abstract: Embodiments of the present disclosure relate to methods, devices and computer readable storage media for data processing. The method comprises obtaining input data. The method further comprises generating, by using a neural network, a predicted label indicating a class of the input data. The neural network comprises a weighted layer that determines at least a weight applied to at least one candidate class to generate a predicted result. The input data is possibly belonging to the at least one candidate class. In this way, the predicted label may be generated more accurately.

Abstract: An electromagnetic leakage prevention device includes a bottom surface, first side walls, second side walls, a first connecting portion, and a second connecting portion. The first side walls are coupled to a side of the bottom surface. The second side walls are coupled to a side of the bottom surface opposite the first side walls. The first connecting portion is coupled to ends of the first side walls away from the bottom surface. The second connecting portion is coupled to ends of the second side walls away from the bottom surface. A distance between the first side walls and the second side walls increases along a direction away from the bottom surface.

Abstract: Embodiments of the present disclosure relate to a method, device and computer-readable storage medium for image processing. A method for image processing comprises: obtaining a first image and at least one second image, wherein each image of the at least one second image is a transformed image of the first image; and generating a first semantic segmentation label for the first image based on at least one semantic prediction result of the at least one second image. By using the first image and the first semantic segmentation label as training data to train an image semantic segmentation model, it helps to increase the precision of the trained image semantic segmentation model.

Abstract: Embodiments of the present disclosure relate to methods, devices and computer-readable storage medium for image processing. A method for image processing comprises obtaining a plurality of images, each of the plurality of images having an initial semantic segmentation label indicating a semantic class of a pixel in the each image; obtaining a plurality of image masks corresponding to the plurality of images, each of the plurality of image masks being used for selecting a target region in a corresponding image of the plurality of images; regenerating respective semantic segmentation labels of the plurality of images based on the plurality of image masks and initial semantic segmentation labels of the plurality of images; and generating a mixed image and a semantic segmentation label of the mixed image based on the plurality of images and the regenerated respective semantic segmentation labels.

Abstract: Embodiments of the present disclosure relate to an image processing method, a device and a computer-readable storage medium. The method includes obtaining a first reference image and a second reference image of a reference object. The method further includes determining a first constraint and a second constraint based on the first reference image and the second reference image. The first constraint is related to a difference between different depth maps of the same reference images, and the second constraint is related to a depth consistency of different reference images. The method further includes training a depth estimation model at least based on the first constraint and the second constraint. In this way, an obtained trained depth estimation model may provide more accurate depth information.

Abstract: A computer includes a chassis, a circuit board installed in the chassis, and a support member. The support member includes a support portion, a first clamping portion, and a second clamping portion. The first clamping portion and the second clamping portion are respectively located at two ends of the support portion. The first clamping portion is configured to clamp the circuit board. The second clamping portion is configured to clamp the chassis.

Abstract: A computer-implemented method, computer system, and computer program product for blockchain enabled service reservation and delegation. The present invention may include receiving one or more first or second trigger conditions defined by a user, detecting an occurrence of the one or more first trigger conditions, deploying a smart contract based on the received one or more first trigger condition, detecting an occurrence of the one or more second trigger conditions, and deactivating the smart contract based on the received one or more second trigger conditions. The present invention may include receiving a subject registration, the subject is the user, a service, or a device. The one or more first trigger conditions may be a condition that upon its occurrence may initiate the deployment of the smart contract. The one or more second trigger conditions may be a condition that upon its occurrence may initiate the deactivation of the smart contract.

Abstract: Embodiments of the present disclosure relate to a method, a device and a computer storage medium for data analysis. The method comprises: obtaining a prediction model, a processing layer of the prediction model comprising a plurality of processing units, parameters of each of the a plurality of processing units satisfying an objective parameter distribution, an output of the prediction model being determined based on a plurality of groups of parameters determined from the parameter distribution; and applying model input data to the prediction model, so as to obtain a prediction for the model input data. In this way, a more accurate prediction result may be obtained.

Abstract: A method for applying compensation to a display screen to reduce MURA effects in the display includes: collecting a display image of the display panel and obtaining panel parameters, the panel parameters comprising a greyscale level values and a luminance value of each pixel in the display image. Regions containing a foreign object are recognized and removed, the blanked regions being infilled. A Gramma value of the display panel is calculated according to the panel parameters and a Gamma curve determined, luminance value of each region of the display panel being obtained according to the Gamma curve. An ideal quadric surface for the display panel is obtained according to the luminance value of each region, a compensation parameter is calculated according to the ideal quadric surface, and compensation applied accordingly. A system and electronic device are also disclosed.

Abstract: An outer case includes an upper case, a lower case, and a plurality of guiding structures. The lower case includes a bottom wall defining a plurality of through holes. The guiding structures are arranged on the bottom wall. Each of the guiding structures includes a first guiding plate and a second guiding plate, the first guiding plate includes a first connecting part and a first blocking part connected with the first connecting part, the second guiding plate includes a second connecting part and a second blocking part connected with the second connecting part, the first connecting part and the second connecting part face each other. The first blocking part is suspended on the bottom wall through the first connecting part, the second blocking part is suspended on the bottom wall through the second connecting part, the first blocking part and the second blocking part are staggered.

Abstract: Filtering incoming calls according to predicted preferences of a user. User preferences are predicted by analysis of user behavior, online activity, oral queues, and purchasing history. Data analysis includes weighting caller and user attributes according to a scheme that is dynamically updated by applying user feedback and/or machine learning processes.

Abstract: In an approach for a text block recognition in a document, a processor detects characters in the document using an object detection technique. A processor identifies positions of the detected characters in the document. A processor analyzes semantic connectivity among the detected characters based on the positions and semantic connectivity of the characters. A processor recognizes text blocks of related characters based on the semantic connectivity analysis. A processor outputs the text blocks associated with the related characters.

Abstract: In an approach to blockchain management of cloud service provisioning failures, one or more computer processors capture one or more application programming interface (API) calls associated with a service provision. One or more computer processors submit the captured one or more API calls to a blockchain ledger. One or more computer processors detect a system failure during the service provision. One or more computer processors extract the submitted one or more API calls from the blockchain ledger. Based on the extracted one or more API calls, one or more computer processors identify a problematic system associated with the system failure.

Abstract: A method, system, and computer program product for reconstructing training data and building a new incremental learning model with the reconstructed training data that can be further trained. The method may include receiving new data to be inputted into a previously trained machine learning model, where the previously trained machine learning model has inaccessible training data. The method may also include generating simulated training data using a reverse form of the previously trained machine learning model. The method may also include verifying the simulated training data. The method may also include creating a new machine learning model using the simulated training data, where the new machine learning model includes a same structure as the previously trained machine learning model. The method may also include inputting the new data into the new machine learning model, where the new machine learning model is further trained with the new data.