171 results about "Category attribute" patented technology

A system and method that enhances the “focus” of information exchanged between sellers and buyers. Buyers identify potential sources for goods and services that are desirable to the buyer. Buyers can focus their access to listings of seller information by identifying desirable attributes, including but not limited to: geography attributes relating to the location(s) of the seller; and category attributes relating to the various categories of offerings that interest to the buyer. The use of geographical and categorical attributes is not limited to their inclusion as part of the search terms. Instead, seller listings can be organized into hierarchies of geography-based and category-based attributes in a highly normalized fashion to enhance the ability of a buyer focus on the most desirable listings. The system can be configured to limit, order, or otherwise prioritize the information viewed by the buyer on the basis of the desired attributes identified by the buyer.

The invention discloses a video structured processing method based on target behavior attributes. The method comprises the steps that the basic attributes of the target are acquired by using a YOLO target detection algorithm; the trajectory information of the detected target is acquired by using a multi-target tracking algorithm; abnormal video frames are extracted by using an abnormal behavior analysis algorithm based on the motion light flow characteristics; the corresponding target category attributes and the target trajectories and other characteristic information are acquired by using themethod according to the meta-data structure constructed by customization; the false detection data existing in the extracted meta-data are corrected by using a weighted judgment method; and the acquired data are uploaded to the rear-end server to be further processed. With application of the mode, the unstructured video data can be converted into the structured data having practical value so thatthe network transmission efficiency of the video monitoring system can be enhanced and the load rate of the rear-end server can be reduced. The invention also provides a real-time processing system based on the target behavior attributes and a real-time processing device based on the target behavior attributes.

The invention relates to an interactive method of image semi-automatic annotation, comprising S1 dividing an initial sample into three different types of annotation samples according to different category attributes; labeling the three types of labeling samples manually to get different kinds of labeling results, and then using three models of Mask-RCNN, Fast-RCNN and FCN to train separately; S2 processing the data set of the picture to be annotated in an offline manner, wherein the annotating process is that the data set of the picture to be annotated passes through the three depth learning models in turn to output the json format files of all types and coordinate points of the data samples; S3 calling the relevant attribute tag value and coordinate point value of the json format file according to the name of the annotated image; S4 displaying the corresponding automatic marking result in the marking software, and judging whether the category and area marking of the target object arestandardized and reasonable by manpower; S5 carrying out data augmentation on the correctly labeled labeling samples and feeding back the augmented data to the model for retraining.

The invention provides a synthetic aperture radar target identification method based on diagonal subclass judgment analysis, which mainly solves the problem that the prior synthetic aperture radar has poor target identification performance. The method comprises the following processes: the self-adapting threshold segmentation, the morphological filtering, the geometric clustering operation and the pretreatment of image enhancement are carried out for an original image; the optimal subclass division to each target after pretreatment is carried out by adopting a two-dimension rapid global K-means clustering algorithm; the diagonal subclass judgment analysis or the diagonal subclass judgment analysis and two-dimension subclass judgment analysis are used for finding out an optimal projection matrix; training and testing images after pretreatment are projected towards the projection matrix to obtain characteristic matrixes of the training and testing images; the Euclidean distance between a testing target and the characteristic matrix of each training target is calculated, and the category attribute of the testing target is determined by adopting a nearest neighbor rule. Simulation experiments show that the invention has the advantages of good effect of inhibiting background clutter, high quality of the target image and low characteristic dimensionality and can be used in a remote sensing system.

The invention provides a method for classifying documents in a mass document library. The method includes: determining keywords of each document in the document library and correspondence between each keyword and the document that the keyword belongs to; matching the keywords one by one in a term base, using industry category attribute of a term matching with each keyword as the industry category attribute of the keyword belonging to the corresponding document; determining same maximum industry category attributes in each document according to the correspondence; and using the industry category attribute with the maximum attribution as the category of the corresponding document. Documents in a reference library are subjected to term retrieval according to the idea of backward matching. The term base is a set with a character sequence index structure, string matching by dichotomy in the term base needs 1+log2n times of matching calculation at most, and accordingly matching times are decreased greatly, the matching process is simplified and efficiency in document classification is improved.

A system and method that enhances the “focus” of information exchanged between sellers and buyers. Buyers identify potential sources for goods and services that are desirable to the buyer. Buyers can focus their access to listings of seller information by identifying desirable attributes, including but not limited to: geography attributes relating to the location(s) of the seller; and category attributes relating to the various categories of offerings that interest to the buyer. The use of geographical and categorical attributes is not limited to their inclusion as part of the search terms. Instead, seller listings can be organized into hierarchies of geography-based and category-based attributes in a highly normalized fashion to enhance the ability of a buyer focus on the most desirable listings. The system can be configured to limit, order, or otherwise prioritize the information viewed by the buyer on the basis of the desired attributes identified by the buyer.

The invention provides a KNN (K-Nearest-Neighbor) text classification method based on improved K-Medoids and relates to the field of computer text data processing. The method comprises the following steps: pre-processing a training text set and a testing text set, wherein preprocessing comprising removal of participles and stop words, DF feature selection and vector representation, so as to obtain a training text vector space and a testing text vector space; carrying out training sample clipping on the basis of an improved K-Medoids method, namely, optimizing from the points of initial center point selection and replacement of center point search strategy, and applying optimization to the training sample clipping so as to obtain a new training text space; and finally, carrying out KNN classification, defining a representative function and applying the representative function to class attribute functions for KNN classification so as to obtain a final result. Experimental results show that compared with a conventional KNN method and a KNN method based on the K-Medoids, the KNN text classification method provided by the invention has higher classification accuracy and classification efficiency.

The invention provides a multi-classifier combined weak annotation image object detection method. The method comprises the steps that M weak annotation image sets with different labels are input, objective analysis is conducted on all images in the image sets, and an objective region set is generated; image features are generated for the region set, and clustering is conducted on different label feature sets; a middle region classifier is trained for each clustered region set according to a clustering result; a category attribute is calculated for each classifier; a test image is input, objective analysis is conducted to obtain a region block, and region features are generated. A multi-classifier is used for conducting combined detection, and the region containing the category object is judged. The multi-classifier combined weak annotation image object detection method has good performance on the aspect of multi-category image object combined detection and can be applied to fields of image object automatic annotation, image object identification and the like.

The invention discloses a map production method and device based on laser point cloud, and relates to the technical field of computers. A specific embodiment of the method comprises: collecting laserpoint cloud of a target area, and performing semantic analysis on the laser point cloud to determine a category attribute of each point cloud point in the laser point cloud and a serial number of an instance to which the point cloud point belongs; combining the point cloud points with the same category attribute under the same instance number to obtain a point cloud cluster, and determining the shape of the point cloud cluster according to the corresponding relationship between the category attribute and the shape; and determining a vectorization rule corresponding to the shape to perform vectorization processing on the point cloud cluster to obtain a vectorization map of the target area. The laser point cloud acquired in the embodiment has the advantages of multiple angles and multiple positions, the integrity and consistency of an object can be better kept compared with a perspective drawing, and the condition that a small part is shielded can be avoided; and three-dimensional vectorization is carried out on point clouds of different shapes, element types can be enriched, and generation of a three-dimensional high-precision map is completed.

The invention discloses a risk control system and method and belongs to the field of risk control. The system comprises a storage unit, a reception unit, a first filter unit, a second filter unit, a calculating unit and a processing unit. The method comprises the following steps: obtaining operation data continuously; filtering all the operation data according to the corresponding category attributes and based on risk control rules to obtain corresponding first filtering data of a first class; filtering the first filtering data according to individual attribute of the risk control rules to obtain corresponding second filtering data; carrying out calculation on the second filtering data to obtain corresponding calculation result and outputting the result; comparing the calculation result with a trigger threshold value and outputting a corresponding comparison result; and carrying out processing on the operation data and / or follow-up operation associated with the operation data when the calculation result reaches the trigger threshold value according to the comparison result. The beneficial effects of the technical scheme are that the setting and processing process of the risk control rules is simplified, and efficiency is improved.

The disclosure describes systems and methods that pertain to interactions between a vehicle and an occupant within the vehicle. More specifically, various systems and methods for enhancing the decisions of automated vehicle applications (collectively “decision enhancement system”) are disclosed. In a safety restraint embodiment, a sensor is used to capture various sensor readings. Sensor readings are typically in the form of images. Occupant information, such as location attributes, motion attributes, and occupant category attributes can be obtained from the sensor readings. Such information can then used by the system to enhance the decisions made by various automated applications.

The invention relates to electronic equipment capable of switching work statuses and a switching method thereof. The method comprises the steps: when the electronic equipment is in a first status, acquiring parameters of a connected network of the electronic equipment; identifying the category attribute of the acquired parameters of the connected network; executing a first-level password security strategy when first predetermined conditions are met, so as to switch the electronic equipment to a second status from the first status; executing a second-level password security strategy when second predetermined conditions are met, so as to switch the electronic equipment to the first status from the second status, wherein a security level corresponding to the execution of the first-level password security strategy and a security level corresponding to the execution of the second-level password security strategy are different.

The invention provides a spectrogram feature-based radar target high-resolution distance image identification method for mainly solving the problems of poor identification performance and high memory demand and calculated quantity in the conventional radar aircraft target identification technology. The method comprises the following processes of: preprocessing radar training target distance echo data; extracting spectrogram features from the preprocessed radar training target distance echo data and the radar test target distance; training a multi-task hidden Markov model for the spectrogram features of each frame of the radar training target echo data along the time dimensions of the spectrogram features, determining parameters of the model, and calculating the posterior probability values of the radar test target echo data by using a forward algorithm; and taking the category attribute of the radar training target echo data corresponding to the maximum posterior probability value as the category attribute of the radar test target echo data. The method has the advantages of high identification performance and low memory demand and calculation burden, and can be used for identification of an aircraft target.

A method for autonomic computing using a relational grammar represented in a mark-up language. In response to a system input change, the autonomic relational grammar and the autonomic system input is parsed to form an autonomic derivation tree representing autonomic system tokens, categories, attributes and relationships. An action is taken as defined by the relational grammar according to the input changes sensed.

The invention discloses a radar target identification method based on a label maintaining multitask factor analyzing model and mainly solves the problem that the prior art is poor in target identification performance under a small sample condition. The radar target identification method includes the steps of firstly, performing normalization and alignment pretreatment on a radar high range resolution profile; secondly, using the preprocessed high range resolution profile to build a label maintaining multitask factor analyzing model; thirdly, performing Gibbs sampling on the parameters of the model, and saving sampling average of the model parameters; fourthly, performing normalization and alignment pretreatment on a to-be-tested sample; fifthly, calculating the frame probability density function value of the to-be-tested sample according to the sampling average, learned by the training steps, of the parameters of the label maintaining multitask factor analyzing model; sixthly, judging the category attribute of the to-be-tested sample according to the frame probability density function value. The radar target identification method has the advantages that supervised learning of the model is achieved, the identification performance under the small sample condition is increased, and the method is applicable to the radar target identification under the small sample condition.

The invention discloses a remote sensing image scene classification system. The system comprises an acquisition step, a grayscale processor, a fitting step, an edge detection step, a remote sensing image pixel classification step and a neural network trainer, wherein the acquisition step is used for acquiring original remote sensing images and transmitting the original remote sensing images to thegrayscale processor as samples; the grayscale processor is used for carrying out grayscale processing on the original remote sensing images transmitted in the acquisition step by adoption of a component method; the fitting step is used for fitting a grayscale histogram by adoption of a low-order spline function; the edge detection step is used for finding zero cross points, obtained by the images, of second derivatives by adoption of a zero cross-based method, so as to position edges; the remote sensing pixel classification step is used for judging surface feature category attributes expressed by pixels by adoption of pixel-based classification and carrying out classification to obtain a classified thematic map; and the neural network trainer is used for inputting the images into a convolutional neural network model to carry out training, so as to obtain a classification results, achieving requirement precision, of remote sensing image scenes. The system is high in classification correctness.

The invention discloses a crowd type identification method based on the mobile phone signaling data, and belongs to the technical field of the crowd type identification. According to the method, the mobile phone signaling data and the basic attribute information of the mobile phone users are combined, and the crowd travel related characteristics are mined and extracted. The method comprises the following steps of calculating the total distance entropy among all samples, and sorting all features according to the importance degree by utilizing a backward elimination method so as to select the features; and based on the screened features, performing clustering analysis on the mobile phone signaling data by utilizing a k-means clustering method, and dividing the clustering clusters; and performing the crowd type identification on each clustering cluster in combination with the distribution condition of each crowd in the corresponding feature. Compared with the prior art, the method has the advantages that the information in the mobile phone signaling data can be more fully mined, and the category attributes of the crowd are analyzed from the global perspective by utilizing a machine learning method, the dependence and requirements on the priori experience knowledge are reduced, the applicability of the method is improved, and the subjectivity brought by a rule discrimination method can be avoided.

The invention discloses a radar range profile statistics and recognition method based on a FA model in the strong noise background, which relates to the technical field of radar automatic target recognition and mainly solves the problem that the current statistics and recognition methods based on the FA model are not robust to noises. The training phase comprises the following steps: framing, translating, aligning and strength-normalizing radar HPPR continuously, learning the parameters of each azimuth frame of the FA model by adopting the processed HRRP and storing a template. The test phase comprises the following steps: first strength-normalizing, translating and aligning the samples to be tested and then estimating the range of the signal-to-noise ratios (SNR) of the samples; computing the distance value of each frame of each target and deciding the category attribute if the SNR is more than 30dB, and rewriting the distance value, solving the noise energy under SNR condition by minimizing the distance value, finally computing the distance value of each frame of each target and deciding the category attribute if the SNR is less than 30dB. The method has the advantages of robustness to noises and less computation and is applied to identifying radar targets.

The invention discloses a data discretization method based on category-attribute relation dependency, belonging to the field of data mining. The method is characterized by comprising: first, based on CAIM algorithm, comprehensively considering about the influence of attribute importance and inconsistent rate of a decision table for discretization result, and providing an improved CAIM algorithm; and second, adopting a lambda correlation coefficient as discretization discriminant for evaluating category-attribute relation, and providing a new monitor discretization algorithm which does not need artificial input parameters and can automatically select discretization points. The method has the advantages that the method can maintain the high efficiency of extracting information for an original data set, balances the consideration of accuracy, and can obtain higher accuracy when in machine learning.

Distribution displays for categories are provided which illuminate the distribution of continuous attributes over all cases in a category, and which provide a histogram of the population of the different states of categorical attributes. An array of such displays by attribute (in one dimension) and category (in another dimension) may be provided. Category diagram displays are also provided for visualizing the different categories, and their distributions, populations, and similarities. These are displayed through different shading of nodes and edges representing categories and the relationship between two categories, and through proximity of nodes.

The invention discloses a sending method, a sending system and a sending device for category information. The main content is as follows: the category information in a central data memory is stored into a category server in the form of a file, consequently, when receiving the category identifier of a terminal and a request for category attribute information during commodity information issue, the category server can locally and directly query and return the category information requested by the terminal without needing to query the category information in the central data memory any more, as a result, the operation pressure of the central data memory is decreased, and the commodity information issue efficiency can be effectively increased.

The invention provides a picture retrieval method and system and relates to the technical field of picture retrieval. In the embodiment, a picture data set is first built; feature data of each picture is extracted and processed to achieve a feature data matrix; then a category matrix and a category-attribute matrix are built according to category information where the picture belongs to; the feature data matrix is divided into a training matrix and a test matrix and further a Hash transferring function is gained; the training matrix and the test matrix are encoded via the Hash transferring function; a preset number of pictures is extracted from the training encoding matrix and the test encoding matrix to form a retrieval base; at last, a picture is selected from the test encoding matrix; a Hamming distance between a Hash code of the picture and a Hash code of a picture in the retrieval base is calculated; and retrieval results are orderly output according to the Hamming distance. The embodiment can effectively improve picture retrieval efficiency and reduce picture retrieval cost.

The invention discloses a tumour early-screening method, a tumour early-screening device and tumour early-screening terminal equipment based on deep learning and a computer-readable storage medium. The method comprises the following steps: acquiring a gene sequence of a sample after gene sequencing; carrying out data analysis on the gene sequence to acquire valid expression levels of target genes;predicting class attributes of the sample through a tumor classification model according to the expression levels of the target genes; and acquiring probability of each class attribute to generate adisease risk recommendation according to a class attribute of highest probability. Costs are low, a cycle is short, and the method is suitable for use on various groups of people.

The invention discloses an album classification method and apparatus, so as to distinguish and determine attributes of audio and video files in an album to achieve the objective of fast determining a type the album. The method comprises steps of: step A: obtaining all audio and video files of a to-be-classified album, and extracting titles and keywords of all the audio and video files, wherein the keywords are used to identify a language type, a music type and a singer of each audio and video file; step B: performing word segmentation operation on the titles and keywords of all the audio and video files, so as to obtain decomposed titles and decomposed keywords after the word segmentation; step C: performing clustering operation on the decomposed titles and decomposed keywords according to a word meaning feature after the word segmentation; and step D: using the word meaning feature that corresponds to a greatest quantity of word clusters as a category attribute of the to-be-classified album, and determining the category of the to-be-classified album according to the obtained category attribute and performing classification on the album.

The invention relates to a network construction management and control method and platform based on big data analysis. The method comprises the following steps that: receiving data information input by a user, and storing the data information in a database of a corresponding data interface according to the category attribute of the data information; receiving a data analysis instruction sent from a data analysis processor, wherein the data analysis instruction comprises data interface identification; according to the interface identification, determining the data information in a called interface; and according to a preset algorithm, generating statistical data, and storing the statistical data in the corresponding data analysis processor which sends the data analysis instruction. The method also comprises the following steps that: receiving a functional assessment instruction, wherein the functional assessment instruction comprises the identification of the data analysis processor; and according to the identification of the data analysis processor, determining the called statistical data in the data analysis processor, and generating a functional assessment result. By use of the method, the mutual calling of various classes of data information is realized, data resources are fully utilized, big data analysis is realized on the basis of the comprehensive utilization of a plurality of database resources, the big data analysis is realized, and the accuracy of the functional assessment result is guaranteed.

The invention provides a service contrast method, which comprises the steps that the service is generated and issued on the basis of attribute value inputted in a preset service category attribute template; a benchmark industry is determined according to the service category of the service in the contrast, and the preset attribute of the benchmark industry is acquired; and the service in the contrast is contrasted with the attributed value corresponding to attribute of the benchmark industry to generate a contrast result; and the invention also provides a service contrast system. According to the technical scheme, the contrast of the service can be high efficiently realized.

Systems, methods, and computer program products for validating billing data and detecting anomalies in billing data are provided. In one embodiment a method is provided, the method comprising: receiving historical billing data for a customer, the historical billing data organized into a plurality of historical data sets; calculating a plurality of statistical representations of each of the plurality of historical data sets; generating a historical profile for the customer based on the plurality of statistical representations of the historical billing data; receiving current billing data for the customer; generating a current profile for the customer; comparing the current profile to the historical profile, the current profile and the historical profile being associated with the same at least one category attribute; and, based at least in part on the result of the comparison, determining whether one or more anomalies are present in the current billing data for the customer.

The invention discloses an object-based remote sensing image super-resolution charting method. Object-based soft classification is carried out by aiming at a mixed object problem with which an object-based remote sensing classification process is faced so as to obtain the category ratio of each object on the basis of the object-based soft classification; and a spatial relationship between the mixed object and a neighborhood object thereof is utilized, on the basis of the first law of geography, i.e., a spatial correlation principle, the spatial correlation feature of each sub pixel in the mixed object is estimated by virtue of a deconvolution and surface to point kriging interpolation technology in statistics, and an object-based linear optimization model is constructed under the ratio constraint of each category of the mixed object to determine the optimal category attribute of the sub-pixel so as to finish the remote sensing image super-resolution charting. The method has the advantages of high practicality, high simulation accuracy and the like and is suitable for ground surface information extraction and geoscience data mining works including remote sensing data classification, land coverage / utilization, change detection and the like.

The invention provides an automatic classification method based on Chinese privacy policy terms, which belongs to the technical field of natural language processing, and comprises the following steps:data processing: obtaining privacy policies of a plurality of applications as a data set, manually labeling to obtain a data set with labels, and then cleaning the data set to obtain a training sample data set; data training: performing feature selection on the training sample data set, selecting effective features capable of identifying different clause categories, and establishing a detection model; and judging whether the privacy policy text has integrity or not. According to the automatic classification method based on the Chinese privacy policy terms, through automatic classification based on the privacy policy terms, the privacy policy content is quickly classified to each classification category attribute, so that a user can read and understand conveniently, and integrity detectionof the privacy policy terms is realized; and the user can quickly identify whether the privacy policy is complete or not.