629results about How to "Comprehensive data" patented technology

A system and method that employs standardized data collection forms for use by health care providers and patients to enable efficient collection, storage and management of patient data for treatment of diseases, such as rheumatoid arthritis.

The invention discloses a personalized advertisement pushing method and system. The method comprises the following steps: 1) obtaining third-party external data through a crawler and calculating the behavior data of a certain user; acquiring the internal data of displaying, clicking, and interactive data of the advertisement of the user in the platform; 2) preprocessing the third-party external data and the internal data and converting the same into a data sample with accurate user information and tags; 3) using the preprocessed data for training, selecting the specific model of a user image, forming a user tag library, synchronizing the obtained user information to an advertisement platform, and storing the obtained user information in a cache tag library by the advertisement platform; 4) collecting the historical advertisement display and click data in the platform, forming a CTR advertisement pushing prediction model, and storing the CTR advertisement putting prediction model in a CTR prediction model library; and 5) pushing advertisements to a certain user accurately based on the user information and the CTR advertisement pushing prediction model.

The invention discloses a vehicle information detecting and recognizing system under the multilane condition. The vehicle information detecting and recognizing system comprises a computer system and a portal frame stretching over lanes, wherein a laser scanner and a high-definition license plate recognition device are arranged on the portal frame, a first dot matrix type wheel shaft sensor, a shaft weight sensor and a second dot matrix type wheel shaft sensor are sequentially arranged on the lane under the portal frame, and the laser scanner, the high-definition license plate recognition device, the first dot matrix type wheel shaft sensor, the shaft weight sensor and the second dot matrix type wheel shaft sensor are respectively connected with the computer system. The vehicle information detecting and recognizing system has the advantages that the two-dimension cross section size and the running position of a vehicle are detected through the laser scanner, and the vehicle three-dimension reconstitution and the vehicle separation are realized; the license plate information and the human face information are precisely collected through the license plate recognition device; the vehicle information such as the shaft distance, the shaft length, the shaft number, the shaft type, the wheel distance, the wheel width and the wheel number are measured according to signals output after a vehicle tyre presses the wheel shaft sensor; and the shaft weight and the total weight are measured through the shaft weight sensor.

In a mobile network a packet interface (103) is monitored by a tap (160-163) in a non-intrusive manner. Captured transaction data is uploaded to a probe (155-158) linked to one or more taps. The probe acts as a slave to a server (159), activating and terminating data capture. A coordinator (601) of the probe (155) manages data capture and buffering according to the server. The server (150) filters the data according to a subscriber registry (203) and loads data until there are complete protocol descriptions. These provide real time subscriber-centered QoS metrics.

The invention discloses a quality-aware edge intelligent federated learning method and a quality-aware edge intelligent federated learning system. The method comprises the following steps that: a cloud platform constructs a federated learning quality optimization problem by taking the maximum sum of aggregation model qualities of a plurality of learning tasks in each iteration as an optimization target and solves the problem: in each iteration, the learning quality of participating nodes is predicted by utilizing historical learning quality records of the participating nodes, and the learningquality of the node training data is quantified by using the reduction amount of a loss function value in each iteration; in each iteration, the cloud platform stimulates nodes with high learning quality to participate in federated learning through a reverse auction mechanism; therefore, the distribution of learning tasks and learning rewards is carried out; in each iteration, for each learning task, each participation node uploads its local model parameters to the cloud platform to aggregate to obtain a global model. According to the method and the system, richer data and more computing powercan be provided for model training under the condition of protecting data privacy so that the quality of the model is improved.

The invention discloses a vehicle remote data acquisition system based on a CAN (Controller Area Network) bus, comprising a remote server and at least one vehicle-mounted remote data acquisition device, wherein each vehicle-mounted remote data acquisition device comprises a processor module, a CAN bus communication module, a voltage comparison module and a radio communication module; input signals of the voltage comparison modules are switching value signals and pulse value signals which are output by vehicle equipment; analog value signals output by the vehicle equipment are processed by an engine ECU (Electronic Control Unit), then transmitted to the CAN bus and received by the CAN bus communication modules; the CAN bus communication module are also used for receiving equipment signals hung on the CAN bus, and the output ends of the CAN bus communication modules are connected with the processor modules through an SPI (Serial Peripheral Interface) bus; and the radio communication modules are used for carrying out radio communication with the server. The system can acquire various information of the vehicle equipment on a plurality of vehicles, data is transmitted to the server for storing through radio communication, and reliable references are provided for the maintenance and the management of the vehicles according to acquired data.

The present invention discloses an IoT (Internet of Things)-based water supply equipment management method. The IoT based water supply equipment management method adopts a plurality of groups of water supply equipment management units. Each group of water supply equipment management units is used for managing and controlling a set of water supply equipment; each data of each group of water supply equipment management units is sent to a data acquiring and sending server by an information acquisition and data transmission module and is transmitted to a stream data server cluster for data processing by the data acquiring and sending server; the IoT-based water supply equipment management method has the functions of secondary data storage and data archiving; meanwhile, by a service server, real-time data or stored data of the water supply equipment is subjected to operations of inquiry and the like according to requests of an external client; by a system management client, faults of a system and faults of the water supply equipment can be processed and judged and corresponding maintenance personnel is assigned to carry out maintenance so as to implement intelligent and uniform management of each set of water supply equipment.

The invention discloses an original article influence analysis system based on collection of media information. The system comprises a media article data acquisition module, an update module for article page views, comments and likes, an original article clustering analysis module and an original article influence calculation module. The media article data acquisition module is used for acquiringarticle information issued by a media platform in the internet, extracting content text from article information and storing the content text. The update module for article page views, comments and likes is used for obtaining dissemination feedback data of the article information and storing the dissemination feedback data of the article information. The original article clustering analysis moduleis used for clustering all content texts stored in a text database in order to obtain original articles. The original article influence calculation module is used for calculating influence of the original articles in the media platform and used for calculating influence of the original articles in all media platforms. The invention further discloses an original article influence analysis method based on collection of media information. By quantitative analysis of original article influence, analysis efficiency is high and accuracy of analysis is great.

The embodiment of the invention provides an interactive television network IPTV service quality detection method and system, and relates to the technical field of communication. The problem that when the IPTV service quality is detected at present, the device operation information of a node device in an IPTV network cannot be detected, resulting in that the detection range is incomplete and that a fault position cannot be accurately judged. The scheme is as follows: the IPTV service quality detection system comprises an IPTV centralized detection platform, probes and a node management center, the probes are deployed on the layers of links in the IPTV network, the probes detect data quality indexes of IPTV service on the links where the probes are located through detection instruction, initiate a dialing test of the node device and feed back detection result to the IPTV centralized detection platform, the node management center is connected with the IPTV centralized detection platform and feeds back the device operation information to the IPTV centralized detection platform, and the IPTV centralized detection platform analyzes the received information and determines the fault position.

The invention discloses a full-function flight simulator. A flight simulation system is arranged in a simulation cockpit, the flight simulation system comprises an instrument table board, a signal device, a control device and an optical device. A movable platform comprises a working table top and a hydraulic actuator cylinder, the working table top is mounted on the hydraulic actuator cylinder, the simulation cockpit is mounted on the working table top, and the hydraulic actuator cylinder is connected with a hydraulic generating device. A view generating device is connected with the optical device in the simulation cockpit. An instructor commanding and controlling table is connected with the flight simulation system in the simulation cockpit, and a computer system is connected with the flight simulation system in the simulation cockpit, the movable platform, the hydraulic generating device, the view generating device and the instructor commanding and controlling table respectively. The full-function flight simulator improves the exercise and training naturalness, and represents the almost true flight environments and the flight motion states of an air vehicle under various flight conditions in real time.

The invention discloses an autonomous underwater vehicle (AUV) track predicating method based on marine environment information. According to the method, the current track data of an AUV are acquired in real time, the current track data of the AUV are input into an AUV track predicting model for prediction, and then the predicated track of the AUV is obtained. The predicating method of the AUV track predicating model comprises the steps of forming a training sample of the AUV track predicating model, conducting principal component analysis on input data to obtain simplified input data, determining calculating parameters and establishing the AUV track predicating model of the BP neural network, and conducting BP neural network training on the simplified input data to obtain the weight values and threshold values of all layers of the AUV track predicating model. According to the method, measured AUV position data and marine environment data serve as the input of the track predicating model together, so that data are more complete, and then track predicting precision is improved.

The invention discloses a wall painting information extraction method based on hyperspectral imaging. The method comprises the following steps of: 1, acquiring original hyperspectral image information of a wall painting in a preset region; and 2, extracting draft information of the wall painting, pigment information of the wall painting and disease information of the wall painting according to the original hyperspectral image information. According to the wall painting information extraction method based on the hyperspectral imaging, the wall painting information is extracted and analyzed according to the advantages of a hyperspectral technology, so that the shortcomings of large working amount, large error, multiple manmade factors and the like of the conventional wall painting information investigation and analysis method are overcome; the wall painting information extraction method has the characteristics of quickness and effectiveness; the shortcoming of insufficient spectral information in dispersion wave band in a multi-spectrum technology is overcome; and the wall painting information extraction method has the advantages of spectrum continuity and rich data and is favorable for quick, effective and scientific analysis of wall painting information, so that instruction and basis are supplied to deep research and protective repair on the wall painting information.

The invention discloses a robot-based intelligent road detection method, which comprises the steps of: S1, determining a road detection region; S2, and automatically planning a path according to the road detection region and executing a road detection task by means of an autonomous detection robot, acquiring real-time positioning information of the robot in the process of executing the road detection task, acquiring road surface data by means of a high-precision camera and a round penetrating radar, correlating the acquired road surface data with the positioning information corresponding to the time when the data is acquired, and storing the data and the information. The robot-based intelligent road detection method utilizes the autonomous detection robot to perform path automatic planningand execute the road detection task, utilizes the positioning equipment to acquire the positioning information of the robot in real time and utilize the data acquisition sensor to acquire the road surface data, and associates the acquired road surface data with the corresponding positioning information, thus the effect of completing the road detection task autonomously by means of the robot is realized, the operating efficiency is high, the detection data is complete, the detection data and the position information are precise, and the diseases can be precisely positioned.

The invention provides a three-dimensional vibration stress relief multitask acquisition and control system which comprises at least one workpiece, at least one vibration exciter, a sensor matched with each workpiece, a mainframe device and a vibration exciter drive unit, wherein, the sensor acquires a three-dimensional signal of each workpiece; the mainframe device classifies and selects distribution of the inherent frequency and the resonant frequency of each workpiece according to the maximum energy absorption principle and the multi-vibration mode principle and drives the vibration exciter drive unit; and the vibration exciter drive unit drives the vibration exciter to vibrate according to the frequency selected by a mainframe so as to eliminate the stress of each workpiece through vibration. The system and a method thereof provided by the invention have the following advantages of achieving more simplified and more convenient acquisition, ensuring that the distribution of the resonant frequency with different vibration patterns of each workpiece is wider and data is more perfect without omission in Fourier spectrum analysis, ensuring that the obtained result is more accurate while classifying and selecting the resonant frequency for Fourier spectrum analysis, and ensuring that vibration ageing treatment effect is better.

A method based on wavelet transform for diagnosing the age state of electric machine's insulation includes beating the main insulating surface of stator bar of large electric generator, receiving the radiated sound wave by sound sensor, wavelet transforming to find out the modular maximum, and determining its age state. Its apparatus is composed of impact source, signal detector, sound sensor, data processing and display unit and software.

The invention relates to a big data-based collage students' psychological behavior abnormal change system scheme design method. According to the method, multidisciplinary theories such as system science, information science, medicine and psychology are comprehensively applied; based on multi-source heterogeneous information fusion, virtual-reality space psychological behavioral representation information is pooled; by means of big data association analysis, a mapping relationship model between college students' psychological behaviors and behavioral representation information is established; through pooling smart campus big data, appropriate image processing, text mining, deep learning, incremental learning and other algorithms are selected to mine and establish a psychological behavior abnormal change monitoring and early warning model; and based on a Hadoop and Tensorflow big data analysis platform, college students' psychological behavior abnormal change monitoring and early warningsoftware is researched and developed. Compared with an existing system, the system of the invention scientifically detects individual students with psychological behavior abnormal changes, and has the advantages of high accuracy, good dynamic performance and the like.

The invention discloses an HTML5 webpage based user behavior analysis method and device. The method includes: collecting user operation information at an HTML5 mobile webpage end when a user accesses a product service system, wherein the user operation information is operation information that the user operates a product service; matching the user operation information through a JavaScript based user behavior rule, recording the user operation information if matching succeeds, and filtering out the user operation information if matching fails; counting, analyzing and processing all the recorded user operation information, and acquiring a user behavior analysis result. The method can improve the accuracy of user behavior analysis.

The invention relates to the technical field of data processing, in particular to a log data analysis method and device, computer equipment and a storage medium. The method comprises the following steps: collecting a plurality of log files, calling a preset log matching table, obtaining an extractor name, calling a field extractor corresponding to the extractor name, and analyzing fields in the log files through the field extractor to obtain a plurality of pieces of effective field information; And converting the effective field information through a field converter to obtain corresponding data information, and storing the data information after the data information is added into a log file. collecting log files in each subsystem; By calling the log configuration table, different extractors are adopted to extract information in the log file to obtain effective field information, data in the original log file are enriched through further processing of re-conversion of the analyzed effective field information, and valuable log data are provided for subsequent analysis of the log file.

The invention provides a method for testing producing profiles of a horizontal well through a coiled tubing optical fiber technology. The method comprises the following steps of type selection of coiled tubings and optical fibers, mounting of the optical fibers penetrating through the coiled tubings, testing operation, mounting and pressure testing operation of the continuous oil pipes, debuggingand rectifying of a data collecting system, putting down of the continuous oil pipes to target positions, determining of testing schemes and relevant parameters, testing of the optical fiber producingprofiles and collecting of data, extracting, dividing, fitting, rectifying and treatment of the data, and analyzing and explaining of the data. According to the method provided by the invention, no logging instrument is arranged, the continuous oil pipes are applied to put down the testing optical fibers to target layers, real-time monitoring of a whole shaft for 24 h is achieved accordingly, theproducing profiles of all tested well sections of the horizontal well and the producing contribution of all the producing layers are obtained, the well diameter limitation of putting down of producing oil pipes or large-drift-diameter bridge plugs in the well shaft can be overcome, or the problem of large construction difficulty of testing of the producing profiles of the large-slope horizontal well is solved.

The invention relates to a method of transfer learning from a long text to a short text. The method of the transfer learning from the long text to the short text is characterized by comprising step 1, obtaining data of a source domain according to tags extracted from a short text of an target domain, and extracting a seed feature set of the source domain; step 2, creating an undirected graph of social media according to a tag set of the short text of the target domain and the seed feature set of the source domain, and extracting subgraphs containing all the nodes of the tag set and the seed feature set of the target domain from the undirected graph; step 3, obtaining a new feature representation of the data of the source domain on the basis of a Laplacian Eigenmap algorithm; step 4, classifying the data of the source domain according to the new feature representation of the data of the source domain.

The invention relates to an automatic fish sorting system based on image recognition, and belongs to the technical field of sorting systems. The automatic fish sorting system comprises a sorting system and a cloud server; the cloud server is in communication connection with the sorting system; and the sorting system comprises an image recognition module, a weighing module, a measuring module, an image collecting module, a warehouse, a sorting module, an image searching module and a communication module. The image recognition technology and the sorting system are combined for identifying and sorting fish, fish can be subjected to classification and identification, length measurement, width measurement, weight measurement, video recording, photo shooting, position positioning and traceability of data simultaneously, digital conversion of fish sorting is conducted, the operating cost is reduced, the operation efficiency is high, the error rate is low, data are more complete, through satellite and 5G automatic switching, the communication stability is ensured, and the communication cost is reduced.

The invention provides a neural network-based college students' psychological behavior abnormal change monitoring and early warning method. The method includes the following steps that: 1) the multi-information source data of students are acquired, a data pre-processing algorithm is adopted to obtain the psychological behavior data of the students on the basis of the multi-information source data,the depression psychological test self-evaluation forms of the students are obtained, the psychological health states of the students are labeled with labels through the results of the psychologicaltest self-evaluation forms, and features related to the psychological health states are extracted through the psychological behavior data, and a PCA algorithm is adopted to extract the main feature components of the data through the features; 2) after the psychological behavior data of the students are obtained, and the main feature components are extracted, and a neural network algorithm is utilized to establish and train a depression psychological early warning model; and 3) the multi-information source data of new students are obtained, and the depression states of the new student individuals are evaluated according to the depression psychological early warning model.

The present invention provides an information system and a method of public security criminal technical inspection and identification. The method has the following procedures: authorizing identification, accepting the authorized identification, delegation of inspection of cases, implementing identification, professional verification, administrative examination and approval, returning the cases, picking up documents, keeping material evidences, filing the documents, integrated modification, integrated inquiry, integrated statistics, working out statistical forms, personnel management, managing the assets, attendance management, network office operation, and system management. The system comprises three levels, wherein, a first level is application, comprising application of dual-server clustering and WEB server dual-clustering; a second level is database which takes two highly functional servers as the database clustering servers and uses independent exchanger equipment; a third level is data storage, adopting an EMC high-end array. The present invention can meet the needs of the criminal technical inspection and identification for a public security system.