144 results about "Taxonomic database" patented technology

The invention puts forward an image intelligent mode identification search method. The method can establish an image sample training set database and combine with basic text search engine technology and basic image content inquiry technology, so that a network creeper can perform Internet image search and URL information resolution, so as to catch the image URL and relevant information into a local primary database; perform such pre-processes as preliminary filtration, decompression and image pre-classification and etc for the images; then, calculate color characteristics, grain characteristics and shape characteristics of the extraction images, so as to gain corresponding characteristic vector sets; combine with the image URL information before saving the images into the image basic database and establishing an index for the images; perform characteristic vector similarity calculation for images in the image basic databases and sample training sets, and then, save the classified images into an image classification database; accept key words or image description that are input by the user, create the index vector, perform similarity calculation with the image characteristic vectors in the image classification database, and then, return the index results to the user.

There is disclosed a method and system for tracking purchasing data for an individual consumer of a product or service. The method includes assembling a database of purchasing data and preferences for an individual consumer, extracting the purchasing data and preferences from the individual database by a terminal device, analyzing the extracted purchasing data and preferences at a collection center, and communicating customized information to the individual consumer based on the analysis of the extracted purchasing data and preferences.

The present invention relates to a storage device comprising an antenna for transmission of data to and/or from a radio frequency identification (RFID) tag. More specifically, the invention relates to a low or ultra-low temperature storage device comprising an antenna for transmission of data between a radio frequency identification (RFID) tag and an RFID tag transceiver and its use for item identification, organization, classification, databasing, tracking or locating.

An intelligent search and retrieval system and method is provided to allow an end-user effortless access yet most relevant, meaningful, up-to-date, and precise search results as quickly and efficiently as possible. The method may include providing a query profiler having a taxonomy database; receiving a query from a user; accessing the taxonomy database of the query profiler to identify a plurality of codes that are relevant to the query; augmenting the query using the codes to generate feedback information to the user for query refinement, the feedback information including a plurality of query terms associated with the query and to be selected by the user; presenting the feedback information to the user; receiving one of the query terms from the user; and identifying a source of the query term and presenting to the user. The system may include a query profiler having a taxonomy database to be accessed upon receiving a query from a user, which identifies a plurality of codes that are relevant to the query; means for augmenting the query using the codes to generate feedback information to the user for query refinement, the feedback information including a plurality of query terms associated with the query and to be selected by the user; and means for identifying a source of the query term, upon receiving one of the query terms from the user.

A system and method for categorizing documents with the aid of an external knowledge database. In an exemplary embodiment of the invention, an external knowledge database is used to provide concepts related to the documents of a categorized database and an input document in order to improve the ability of correctly categorizing input documents. Additionally, the above system and method can be implemented to search for documents related to an input document.

A specific clothing image identification and detection method based on machine learning is provided. The invention relates to an image identification and detection method. The purpose of the invention is to solve the problems of the prior art that a manual detection way cannot realize searching of images of specific kinds of clothing because of a large quantity. The method includes the following processes: firstly, identifying image contents, and obtaining identified image contents; constructing an image classification database, processing images in the image classification database through a self-service sampling method, and obtaining processed images; obtaining an optimized convolution neural network; carrying out model integration; obtaining N individual learning devices, and combining the N learning devices through a simple ballot way; and secondly, utilizing a Faster R-CNN method to detect the identified image contents obtained in the first step. The specific clothing image identification and detection method is applied to the clothing image identification and detection field.

The invention further provides a method for providing workforce management and collaborative support amongst a plurality of entities comprising; aggregating in a comprehensive database a set of data, documentation, instructions and tools for the performance of at least one task, loading the comprehensive database onto at least one computer for the performance of the tasks, performing the at least one task, creating a record of the execution of the at least one task, adding entities through the process comprising; requesting assistance from at least one support entity by any of the plurality of entities, wherein requesting assistance includes; creating a classification database of resource classifications, sharing the database among a plurality of resources and resource users, registering an address and resource classification for each of the plurality of resources, receiving a request for at least one resource from the resource user, searching for at least one matching resource, and returning the resource to the resource user, creating an electronic communication link from the support entity to the entity, providing the record from the entity to the support entity, and sharing control of the executing of the at least one task.

The invention discloses the user classification methods, targeted ads methods, devices and systems. In which users classified in the following ways: access to the user clicks on the link, described by the links users determine the content of information of interest from Preferences classification for users to find the distinction between categories of users with the information referred to the users most interested in information matching categories of users; users will be referred to above categories of users join. Directional ads include: user login classification from the user database users find described in the respective categories of users; classification, in accordance with user preferences according to the rules described in users inject targeted advertising. Use of this invention to provide a method of directional ads, ads can be directed to the targeted advertising really interested surfers before.

The invention provides an intelligent vertical search method and an intelligent vertical search system, and relates to the technical field of networks. The method comprises the following step of: according to matching results of query words of a user and items which have been classified in the industry in a classified database, acquiring items related with the query words in various classes, displaying the items of the various classes and related information according to classes, wherein the items which have been classified in the industry are acquired by the following steps of: acquiring all items of all webpages of the industry and related information; performing weighted analysis on morphological matching results of key words of various items and key words corresponding to various classes of the industry to determine the classes to which the various items belong; and/or determining the classes to which the various items belong according to the similarity of the appearance frequency rate of various key words of unclassified items and the appearance probability of various key words of the classified items, which is acquired through statistics in advance. By the invention, information related to focuses of users can be displayed more accurately, comprehensively and quickly.

The invention discloses a spatial index establishing method, a spatial index use method and a spatial index use device. The spatial index establishing method includes using classes set in a classification database for classifying spatial objects in a spatial database; aiming at the spatial objects of each class and according to distribution of the spatial objects of the class in a spatial region, continuously dividing the spatial region by the aid of a quadtree mode until distribution of the spatial objects of the class in each divided sub-region satisfies set conditions; and establishing spatial indexes for the spatial objects of the class in each divided sub-region by the aid of an R-tree mode. Probability of interlapping of various spatial objects can be decreased by establishing the spatial indexes for the spatial objects of each class, and since spatial regions dense in spatial object distribution are divided into smaller regions according to distribution characteristics of all classes of spatial objects when the spatial indexes are established for each class of spatial objects, spatial overlapping probability is further decreased, and speed of using the established spatial indexes for searching is increased while accuracy of using the established spatial indexes for searching is improved.

A system and associated method for automatically controlling a hospital equipment of in-patient care environment is performed by a module coupled to a classification database, an Inference Engine (IE), a Truth Maintenance System (TMS), and the hospital equipment. Upon admitting a patient, a patient record related to the patient is created and events for the patient are recorded. Based on inference rules of the IE, inferred event data is generated and subsequently control data to manipulate the hospital equipment is generated. Pursuant to new event affecting truth of the inferred event data, the inferred event data may be renewed and new control data based on the renewed inferred event data is created to ensure that the control data is based on the latest event related to the patient.

An advertising/revenue generation system for use with telecommunication systems. A database can be organized or sorted on parameters relating to telecommunication, such as caller demographics, time and place of a call, and the services of the initially dialed number. Advertisers can submit advertisements to the advertising system. When a caller submits a communication request, for example by entering a telephone number into a communication device, the advertising system recognizes the request and accesses the database. The advertising system determines advertisements that are related to the caller's communication request and telecommunicates relevant advertising content to the caller. The content can be provided before, during, and/or after the caller establishes communication as initially requested. The advertising system can provide incentives to callers to select ads, can collect fees from advertisers for submitting their ads to callers, and can pay commissions to telecommunications carriers for supporting communication.

The invention provides a method and a system for interactive display of a cultivation culture virtual scene. The method comprises the steps of acquiring cultivation knowledge and performing classified storage; respectively establishing a plurality of classified databases and three-dimensional models; respectively forming a correspondence between the plurality of classified databases and a correspondence between the plurality of classified databases and the three-dimensional model; displaying the three-dimensional model with a triggering condition, triggering and playing the cultivation knowledge which corresponds with the triggering condition in the classified database that corresponds with the three-dimensional model; inputting the triggering information for triggering a preset event in the three-dimensional model, and playing the related agricultural knowledge in the classified database which corresponds with the three-dimensional model. The method and the system realizes reproduction of the traditional cultivation scene. Three-dimensional modeling technology is utilized for reproducing an object for obtaining a 3D model and improving a stereo perception, so that the picture is more enriched. Furthermore vividness and trueness which are realized by interaction technology are added, thereby greatly improving interest of audiences, making the audiences understand and search a scene content and improving availability and timeliness of the system.

The invention discloses an incoming call prompt method and device as well as an incoming call classifying method and device. The incoming call prompt method comprises the following steps: acquiring characteristic attributes of an incoming call, and prompting the incoming call according to the category, to which the characteristic attributes of the incoming call belong, in a category database. As the category database is dynamically updated and perfected according to a training sample set and updating of user communication data, different classification results are generated for different users; use habits and interpersonal connections of users are met; the method has the characteristics of high classification quality, high classification speed and low misjudgment rate.

The invention relates to a remote sensing image target detection method and device. The method comprises the following steps: firstly, establishing a depth full-convolution neural network; the depth full-convolution neural network comprises a main network used for feature extraction and a sub-network used for target detection; training the main network through an image classification database; after the main network is trained, adding the sub-network; fine-adjusting the network parameters by means of the remote sensing target detection database to obtain a trained depth full-convolution neuralnetwork; and finally inputting the remote sensing image to be detected into the depth full-convolution neural network to obtain a final target detection result. Compared with a conventional way of directly using a remote sensing target detection database to train the established depth all-convolution neural network, the generalization ability and accuracy can be improved, and the rapid, high-precision and high-robustness automatic target detection can be realized in a complex background.

The invention relates to an intelligent product classification method, which includes the following steps of building a classification database which comprises multiple product categories respectively including at least one classification keyword, traversing data of products required to be classified and extracting at least one product keyword for different products, matching product keywords of different products with the classification keyword of the classification database, and using the product category with the matched classification keyword as the current product category and adding the same into the classification property of the product. By the intelligent product classification method, category tags of products can be added more quickly. Workload of manual operation can be released greatly by utilizing machines to analyze description words of products and then judge categories thereof.

One embodiment of the present invention provides a system for automatically classifying data in a database. During operation, the system receives and executes a database operation. Next, the system automatically determines if any data was modified as a result of executing the database operation. If so, for each data item that was modified, the system automatically determines if the data item is associated with a classification-rule. If so, the system automatically reclassifies the data item according to the classification-rule. If not, the system leaves a classification of the data item unchanged.

The invention relates to an information classification and retrieval system, which comprises a stock name classification database, an index association module and a news index database. The stock name classification database stores at least one stock name classification. The stock name classification also comprises a stock name, a stock code and a stock classification. The index association module is used for analyzing the key words related to stock in the news, finding out the stock classification corresponding to the key words in the stock name classification database, and building the index association between the news and the stock name classification. Afterwards, the news and the corresponding index association are stored in the news index database and the system can find out the consistent news in the news index database and transmit to the user terminal, thus having the advantages of shortening the time for news search, decreasing the calculation load of the user terminal and reducing the data transmission bandwidth.

The invention belongs to the technical field of embedded computers, and discloses a design method for missing alarm prevention for switch machine gap monitoring. The method is realized through an industrial computer processing module, a data receiving and storing module and a machine learning identification module. The industrial computer processing module uploads the collected conventional data packet, video data and gap data packet of an industrial computer to an NVR server, and simultaneously updates the display information of an upper computer. The data receiving and storing module receives the data uploaded by the industrial computer, displays the data on the upper computer, and stores the data in the NVR server. The machine learning identification module establishes an image classification database, introduces a convolutional neural network, and establishes a classifying and sampling learning unit for the image classification database. Finally, a video frame is output through Fast R-CNN. The video frame is processed. An alarm type is output. Finally, the detected alarm type is compared with the alarm type of the industrial computer to acquire alarm information. According to the invention, missing alarm and false alarm of a switch machine can be effectively prevented, and the reliability of gap video monitoring of the switch machine is improved.

The invention discloses a method and a device for detecting database blockage. The method includes the steps: receiving database detection commands, reading stored current data acquired from databases according to a preset time period, and acquiring detection and analysis results and detected database response time information from the read current data; determining classified databases of the detection and acquisition results according to pre-stored classified database information, inquiring pre-stored classified database response time information and acquiring the corresponding database response time information of the classified databases; and determining the database blockage if the detected database response time exceeds acquired database response time by means of inquiry. By the aid of the method and the device, the detection efficiency of the databases at the HANG state can be improved.

A method and system for of fusing the outputs of multiple sensors. The output of each sensor including a sensor class probability vector based on each sensor's classification database is input to a fusion engine which estimates a base class probability vector based on the sensor class probabilities output by the sensors and a preconfigured base database including base classes.

The invention discloses a method, system and device automatically conducting sorting operation based on data types. The method comprises the steps of extracting sorting information from received file data or existing file data, establishing a sorting catalogue with the sorting information as the name, classifying corresponding file data into the corresponding sorting catalogue, forming a temporary sorting set with the sorting catalogue and the corresponding file data as elements, and merging the temporary sorting set to a set sorting data base. If the number of the file data contained in the sorting catalogue of the elements in the merged set is larger than or equal to a set parameter, displaying the sorting catalogue. The sorting method involves no manual operation, collating sorting time is saved, during later use, a user only needs to search information in a corresponding catalogue and can find out the information quickly and conveniently, and searching time is further saved.