Abstract: The present disclosure relates to the field of vehicle technology and provides an energy recovery control method, a system, and a vehicle. The method is applied in a vehicle, and the vehicle comprises a drive motor and a battery electrically connected to the drive motor; a first energy recovery torque curve with respect to the drive motor is pre-configured in the vehicle, and the first energy recovery torque curve is used to indicate a correspondence relationship between vehicle speed and energy recovery torque of the drive motor. The present disclosure performs reduction on a first energy recovery torque curve by means of utilizing a reduction ratio, allowing energy recovery in accordance with a relatively low torque strength when a usable charge power of the battery is unable to satisfy a preset power requirement corresponding to the first energy recovery torque curve.

Abstract: Disclosed are a product inspection method and device, producing system and a computer storage medium. The method comprises: conducting image acquisition on a product assembly line to obtain a production line image; extracting a product image including a product to be inspected from the production line image; extracting an inspection point image in a part inspection area in the product image; inputting the inspection point image into an inspection model to obtain an inspection result; and determining that the product to be inspected in the product image has defects under the condition that the inspection result meets any of the following conditions.

Abstract: The invention relates to a hair care composition comprising a) a cationic surfactant selected from stearamidopropyl dimethylamine, behentrimonium chloride, stearyl trimethyl ammonium chloride or mixtures thereof; b) from 15 to 30% by weight of glycerin; and c) from 0.1 to 2.0% by weight of fatty alcohol based on the total weight of the composition.

Abstract: A model predictive virtual synchronous generator inverter control method considering a frequency-movement direction includes: obtaining a current frequency absolute value based on fundamental frequency of an inverter and a steady-state absolute value based on the fundamental frequency of the inverter; determining a frequency-movement state by comparing the above two absolute values: in a state of deviating from the fundamental frequency or a state of regressing to the fundamental frequency; setting a corresponding prediction output horizon according to the frequency-movement state, and constructing a cost function considering the frequency-movement state; and calculating an optimal virtual power increment value based on the cost function, then calculating an optimal virtual power, inputting the optimal virtual power to a swing equation of a virtual synchronous generator, and performing frequency adjustment according to an output value.

Abstract: A brushless direct-current (BLDC) motor is provided. The motor includes a stator including a stator core, stator teeth, and windings; a rotor shaft disposed within the stator and extending along a longitudinal axis; and a rotor. The rotor includes a rotor core including an inner body mounted on the rotor shaft and radial projections projecting outwardly from the inner body, a permanent magnet mounted on an outer end of the radial projections, and a mold structure formed in contact with the radial projections and configured to secure the permanent magnet to the rotor core.

Abstract: A computer-implemented method, system and computer program product for detecting Unicode injection in text. A language model is trained to determine if text data (e.g., text fragment) conforms with human writing habits using negative and positive samples. Negative samples include samples of text that are not classified as being suspect for containing Unicode characters. Such negative samples include text written by humans. Positive samples include samples of text that are to be classified as being suspect for containing Unicode characters. Such positive samples may be formed by randomly inserting Unicode characters into the corpus of negative samples. After training the language model, the language model is able to determine whether the received text data (e.g., text fragment) is suspect for containing Unicode characters based on whether the text data conforms with human writing habits.

Abstract: The present disclosure discloses a method, apparatus and device for detecting obstacles, and a computer storage medium, which belong to the field of security monitoring. The method includes: by performing object detection and pedestrian detection on a monitored image of a monitored region, an object identification group including an object identification box and a pedestrian identification box are acquired, and upon removing an object identification box associated with the pedestrian identification box, that an obstacle is present in the monitored region based on the object identification box in the object identification group is determined. False warning caused by presence of pedestrians in the monitored region can be avoided. The problem of low accuracy of methods for detecting obstacles in the related art can be solved, and the effect of improving the accuracy of the method for detecting obstacles can be achieved.

Abstract: Embodiments of the present disclosure provide a method of matching image, an apparatus of matching image, a device, and a computer-readable storage medium. The method includes: acquiring an image to be matched; determining a key point feature similarity between any image in an image library and the image to be matched, and determining a color feature similarity between the any image and the image to be matched; determining a fusion similarity between the any image and the image to be matched according to the key point feature similarity and the color feature similarity; and determining whether an image matching the image to be matched exists in the image library or not according to the fusion similarity between each of at least one image in the image library and the image to be matched.

Abstract: Apparatus and method for polishing objects uses a layer of diamond slurry on a polishing surface of a polishing structure that is formed by dispensing a set amount of diamond slurry onto the polishing surface. The thickness of the layer of diamond slurry is maintained by periodically dispensing another set amount of diamond slurry onto the polishing surface of the polishing structure.

Abstract: The present application relates to a shelf interaction method and a shelf. The shelf is provided with at least one image capturing device. The method includes: capturing an image of the shelf through the at least one image capturing device; in response to detecting that a first position on the shelf is changed from presence of a first item of goods to absence of the first item of goods according to the image, identifying a first category of the taken-away first item of goods; in response to that a second goods category associated with the first position is the same as or different from the first category of the taken-away first item of goods, sending first prompt information to indicate that the first item of goods is taken away.

Abstract: A system and method for field extraction including determining a key position of a key in an electronic file, isolating candidate key values based on a distance from the key position, selecting a key value from the candidate key values based on an output of a trained neural network, and extracting the key and the key value from the electronic file, regardless of a key-value structure.

Abstract: A system, method, and computer program product for implementing cognitive natural language processing software framework optimization is provided. The method includes receiving instructions associated with an audible user input of a user. An AI input intention of the user is determined and key information is extracted from the audible user input. The key information is inputted into a generated database table and additional key information is retrieved from a dialog table. A supplementary database table comprising the additional key information is generated and the key information is spliced with the additional key information. A resulting spliced data structure is merged into a final database table and natural language is converted into a request code structure within an SQL structure and an interactive AI interface presenting results of the converting is generated. Operational functionality of an AI device is enabled for audibly presenting results of the conversion.

Abstract: In an approach for using an open source of existing text labeling models to label sentences that need to be clustered with multiple external tags and then to use the tags as auxiliary information to perform the clustering at a dual level, a processor receives a set of text, wherein the set of text contains one or more sentences. A processor tags each sentence of the set of text with one or more tags using a plurality of open-source text classification models. A processor performs a preliminary clustering of one or more nodes under strict conditions using a canopy clustering algorithm.

Abstract: The present invention provides a method for separation and recovery of boron trifluoride and complexes thereof in an olefin polymerization reaction.

Abstract: A method and related system detail a split of an architecture of a monolithic application into an architecture of a micro service application. The method receives source code for the monolithic application, and maps the source code into a directed graph. The graph is split into subgraphs and optimized. The method further provides the detailing of the micro service application split, based on the subgraphs.

Abstract: A computer-implemented process for modifying a training dataset includes the following operations. The training dataset is benchmarked using a State Of The Art (SOTA) neural network to determine a benchmark for the training dataset. The training set is divided into a plurality of slices. A sequence of a plurality of atomic operations are selected using a selection strategy generator operating on one of the plurality of slices. The sequence of the plurality of atomic operations is applied to modify the one of the plurality of slices to generate a revised one of the plurality of slices. Reverse reinforcement learning is performed on the revised one of the plurality of slices using the benchmark and the SOTA neural network. The training dataset is modified by replacing the one of the plurality of slices with the revised one of the plurality of slices to generate a modified training dataset.

Abstract: Training data models using machine learning can include training a computer data model of data distribution using a training data set. The training data set includes training data and additional training data, and the training data and the additional training data being represented by layers of data representing the data distribution of the training data set. The computer data model using the additional training data is iteratively trained for each of the layers of the training data set. Statistical noise is added randomly to each of the layers of the training data set. Data variations are detected in each of the layers of the additional training data. The data variations are diluted in each of the additional layers of the training data, and the computer data model is retrained for the training data set using the diluted data variations in each of the layers of the additional training data.

Abstract: A method, a computer program product, and a computer system compare images for content consistency. The method includes receiving a first image including a first document and a second image including a second document. The method includes performing a visual classification analysis on the first image and the second image. The visual classification analysis generates an overlap of the first image with the second image. The method includes determining whether a region of the overlap is indicative of a content inconsistency. As a result of the region of the overlap being indicative of a content inconsistency, the method includes performing a character recognition analysis on a first area of the first image and a second area of the second image corresponding to the region of the overlap to verify the content inconsistency.

Abstract: Systems, methods and/or computer program products for automating evaluations of code deliveries for software projects. Automated evaluations are generated by selecting software projects and dividing a project into a plurality of code blocks by analyzing the code, build file and build log. Attributes of code blocks are extracted and correlations between code blocks are calculated. Dynamic distance between code blocks is calculated by the correlation and code delivery history, to create a Dynamic General Distance Map and Dynamic User Distance Map for the code blocks. Code delivery distance indicating the code delivery behavior is generated by the Dynamic User Distance Map while the delivery assessment criteria is generated to evaluate code delivery and assess levels of risk associated with delivery of the code. High-level risk indicates that a code delivery may not follow best practices and users are alerted to pay more attention to the code delivery during review.

Abstract: Aspects include determining a coding intention and a dimension of interest to a user. A plurality of relevant projects that each include a logical code block that meets the coding intention are located. The locating includes searching a plurality of code repositories based at least in part on the coding intention. A score is assigned to each of the plurality of logical code blocks based at least in part on properties associated with the logical code blocks and on the dimension of interest to the user. A logical code block with the highest score is promoted to the user.