Abstract: Provided is an unbalanced sample data preprocessing method, which includes: a data acquisition request is received and initial data is acquired according to the data acquisition request, and the initial data is classified according to a preset classification rule to obtain first-class sample sets and second-class sample sets; characteristics of K first sample points extracted are analyzed to obtain a new data characteristic of the first-class sample sets; a new data label of the first-class sample sets is generated according to a first label corresponding to the first-class sample sets; a ratio between the number of first-class sample sets and the number of second-class sample sets is calculated; and new data of the first-class sample sets is generated according to the new data characteristic and the new data label, and the amount of new data is adjusted according to the ratio to increase the number of first-class sample sets.

Abstract: Disclosed is a method for preparing a rare-earth modified Keggin-type heteropolyacid-supported catalyst. Carbon nanotube is used as support, and is oxidized to form openings and cut into short tubes by an acidic solution. Under the action of metal chlorides and alcohol solvents, the end and the defect sites on the side walls of the carbon nanotubes are combined with hydroxyl groups to obtain hydroxylated carbon nanotube. In this way, the surface properties of the carbon nanotube are changed, and the active components are more easily and firmly adsorbed on the carbon nanotube, thus the stability of the catalyst is improved.

Abstract: The disclosure discloses a method of calibrating a moving region of a guide robot, including: detecting and receiving a movement instruction, and sending the received movement instruction to a controller; determining region calibration parameters corresponding to the received movement instruction according to a predetermined mapping relation between the movement instruction and the region calibration parameters, wherein the region calibration parameters include a pending moving region of the guide robot, a light display parameter in the pending moving region, and a driving parameter corresponding to the pending moving region and the light display parameter; driving the light emitting module to carry out light display calibration in the pending moving region according to the determined region calibration parameters. The disclosure further provides the guide robot and a computer storage medium. The technical solution of the disclosure enables the guide robot to display a marked region to be passed.

Abstract: The disclosure relates to an advertisement generation method and system. The advertisement generation method includes: acquiring click data of the advertisements subjected to advertisement exposure triggered by each user from various predetermined data source servers, and extracting picture style features of advertisement background pictures in the advertisement click data; during recommending of advertisements to predetermined users, analyzing the advertisement click data of the various users according to predetermined picture style features and a predetermined first analysis rule to obtain picture style features of advertisement pictures to be recommended corresponding to the various users; and generating recommended advertisements according to the obtained picture style features corresponding to the various users to recommend the recommended advertisements to the corresponding users.

Abstract: The present disclosure provides an electronic device, a method for constructing a scoring model of retail outlets, a system and a computer readable medium. The method includes: crawling POI data of a predetermined map website by a crawler system; acquiring surrounding POI data based on a location of each retail outlet, and constructing POI relevant outlet features based on the surrounding POI data; acquiring surrounding LBS information based on the location of each retail outlet, and constructing client relevant features based on the surrounding LBS information; scoring each retail outlet based on a number of new clients increased in a predetermined time period and a revenue index; and constructing the scoring model by performing supervised learning of a preset classification algorithm model using the POI relevant outlet feature, the client relevant feature, and a score of the retail outlet.

Abstract: A method, a device, a terminal and a storage medium for acquiring slant value of slant image are provided. The method for acquiring slant value of a slant image comprises: analyzing the slant image and acquiring coordinate information of a plurality of boundary lines of the slant image; acquiring first slant values of the boundary lines by analysing and calculating the coordinate information; acquiring a correction value; calculating difference values between the first slant values and the correction value respectively; determining the first slant value corresponding to the minimum difference value as the slant value of the slant image. The technical solution of the present disclosure can uniquely determine a slant value of slant image.

Abstract: An acoustic model training method, a speech recognition method, an apparatus, a device and a medium. The acoustic model training method comprises: performing feature extraction on a training speech signal to obtain an audio feature sequence; training the audio feature sequence by a phoneme mixed Gaussian Model-Hidden Markov Model to obtain a phoneme feature sequence; and training the phoneme feature sequence by a Deep Neural Net-Hidden Markov Model-sequence training model to obtain a target acoustic model. The acoustic model training method can effectively save time required for an acoustic model training, improve the training efficiency, and ensure the recognition efficiency.

Abstract: Disclosed is a method for identifying a user interest, including: obtaining training samples and test samples, the training samples being obtained by manually labeling after the corresponding topic models have been trained based on text data; extracting characteristics of the training samples and of the test samples, and computing optimal model parameters of a logistic regression model by an iterative algorithm based on the characteristics of the training samples; evaluating the logistic regression model based on the characteristics of the test samples and an area AUC under an ROC curve to train and obtain a first theme classifier; determining a theme to which the text data belongs using the first theme classifier, computing a score of the theme to which the text data belongs based on the logistic regression model, and computing a confidence score of the user being interested in the theme according to a second preset algorithm.

Abstract: An electronic device for identity verification includes a memory and a processor; the system of identity verification is stored in the memory, and executed by the processor to implement: after receiving current voice data of a target user, carrying out framing processing on the current voice data according to preset framing parameters to obtain multiple voice frames; extracting preset types of acoustic features in all the voice frames by using a predetermined filter, and generating multiple observed feature units corresponding to the current voice data according to the extracted acoustic features; pairwise coupling all the observed feature units with pre-stored observed feature units respectively to obtain multiple groups of coupled observed feature units; inputting the multiple groups of coupled observed feature units into a preset type of identity verification model generated by pre-training to carry out the identity verification on the target user.

Abstract: A user keyword extraction method based on a social network includes: acquiring blog posts having been posted by a target user within a preset time interval, and performing word segmentation to acquire a word list of each blog post; inputting the acquired word list corresponding to each blog post into a Word2Vec model for training to acquire a word vector model; extracting keywords corresponding to the blog posts based on a keyword extraction algorithm to form a candidate keyword set of the target user, calculating a word vector of each keyword in the candidate keyword set based on the word vector model, and constructing a semantic similarity graph; and running a Pagerank algorithm on the semantic similarity graph to score the keywords so as to acquire interest keywords of the user. This application also provides a user keyword extraction device based on a social network, and a computer-readable storage medium.

Abstract: Disclosed are a car damage picture angle correction method, an electronic device, and a readable storage medium. The method includes: after receiving a car damage picture to be classified and identified, identifying a rotation category corresponding to the received car damage picture by using a pre-trained picture rotation category identification model; determining a rotation control parameter corresponding to the identified rotation category according to a pre-determined mapping relation between rotation categories and rotation control parameters, the rotation control parameter including a rotation angle and a rotation direction; and rotating the received car damage picture according to the determined rotation control parameter, so as to generate an angle-normal car damage picture.

Abstract: The disclosure discloses a path planning system and method for a robot, the robot and a medium. The method includes: preselecting, by the path planning system for the robot, one or more position points from paths on which the robot can move in a predetermined regional map as reference positioning points; and if an instruction of moving the robot from a first position point to a second position point is received, analyzing a path from the first position point to the second position point according to the set reference positioning points and according to a predetermined path analysis rule, and controlling the robot to move to the second position point on the basis of the analyzed path.

Abstract: A system and method of controlling obstacle avoidance of a robot. The method includes acquiring current positioning data of the robot, and determining whether an obstacle, spaced from a current position at a distance shorter than a preset distance, exists in a path from the current position to a target position or not according to the current positioning data and position data of all obstacles in a predetermined moving region; if the obstacle exists, calculating the shortest distance between the robot and the obstacle according to the acquired positioning data, a predetermined 3D model of the robot and a predetermined 3D model of the obstacle; calculating a due movement direction of the current robot according to the acquired positioning data, the calculated shortest distance and the 3D model of the obstacle, and controlling a movement posture of the robot according to the calculated movement direction to avoid the obstacles.

Abstract: A method of training a random forest model, an electronic device and a storage medium. The method of training the random forest model includes analyzing, by a system of controlling model training, whether model training conditions are met or not; if the model training conditions are met, determining whether reconstructive training needs to be carried out on the random forest model or not; if the reconstructive training needs to be carried out on the random forest model, carrying out the reconstructive training on the random forest model by using sample data; if the reconstructive training does not need to be carried out on the random forest model, carrying out corrective training on the random forest model by using the sample data.

Abstract: Disclosed are a speech recognition method, apparatus, computer device and storage medium. The method includes: performing a framing and an acoustic feature extraction of a speech-information-to-be-tested according to a default rule to obtain a frame-level speech feature sequence; dividing the frame-level speech feature sequence into n blocks sequentially; inputting all blocks into a preset bidirectional LSTM-RNN model parallelly to obtain an output result of the corresponding neuron in an output layer of the preset bidirectional LSTM-RNN model corresponding to the forward recognition result and backward recognition result of each block to obtain a speech recognition result of the speech-information-to-be-tested. The present application can improve the speech recognition effect significantly and reduce the time delay of the speech decoding effectively.

Abstract: The preset application is applied to the field of information processing technologies, and a method and a device for generating a medical report are provided. The method includes: receiving a medical image to be recognized; importing the medical image into a preset visual geometry group VGG neural network to acquire a visual feature vector and a keyword sequence of the medical image; importing the visual feature vector and the keyword sequence into a preset diagnostic item recognition model to determine diagnostic items corresponding to the medical image; constructing a paragraph for describing each of the diagnostic items respectively based on a diagnostic item extension model; generating a medical report for the medical image based on the paragraph, the keyword sequence and the diagnostic items.

Abstract: Disclosed is a method for identifying a user interest, including: obtaining training samples and test samples, the training samples being obtained by manually labeling after the corresponding topic models have been trained based on text data; extracting characteristics of the training samples and of the test samples, and computing optimal model parameters of a logistic regression model by an iterative algorithm based on the characteristics of the training samples; evaluating the logistic regression model based on the characteristics of the test samples and an area AUC under an ROC curve to train and obtain a first theme classifier; determining a theme to which the text data belongs using the first theme classifier, computing a score of the theme to which the text data belongs based on the logistic regression model, and computing a confidence score of the user being interested in the theme according to a second preset algorithm.

Abstract: An information retrieval precision evaluation method and device and a computer-readable storage medium. The method includes: retrieving, by virtue of a first predetermined retrieval system, at least one first retrieval result corresponding to a predetermined keyword, and retrieving, by virtue of a second predetermined retrieval system, at least one second retrieval result corresponding to the keyword; generating a first retrieval sequence number corresponding to the first retrieval result and a second retrieval sequence number corresponding to the second retrieval result according to a preset sequence number generation rule; and analyzing the generated first retrieval sequence number and second retrieval sequence number according to a predetermined precision analysis rule to obtain precision of the first retrieval system and the second retrieval system.

Abstract: This invention disclosure reported here a supported metal hydroxide adsorbent and a method for its preparation as well as a method for its oxidative regeneration. The supported metal hydroxide adsorbent comprises metal hydroxide and support with a mass ratio of 5-30:100. The adsorbent disclosed in present invention exhibited outstanding adsorption capacity and high selectivity to sulfur impurity in gasoline. The method of oxidative regeneration provides an efficient way for the recovery of the saturated adsorbent.

Abstract: A method for data distribution includes: receiving a request for data distribution sent from a terminal; searching for raw association network data, wherein the raw association network data includes a set of nodes and a set of edges existing between the nodes; searching for a corresponding user grade according to a user identifier carried in the request for data distribution, and determining a privacy budget parameter corresponding to the user grade; determining the distributing probability distribution corresponding to the raw association network data to be distributed according to a pre-constructed Laplace Model and the determined privacy budget parameter; selecting an arbitrary value within the distributing probability distribution as a distributing probability for each network edge of the set of edges, generating a random number between 0 to 1 for each network edge, comparing the random number to the distributing probability, and distributing the corresponding network edge when the distributing probabilit