43results about How to "Extensive sources of data" patented technology

A path planning method for avoiding of traffic hotspots helps to realize an intelligent path planning method with a purpose of the shortest journey time, by dynamical planning of paths with an avoiding property, based on a destination where a driving user goes. The traffic hotspot information, such as large-scale activities, traffic accidents, traffic-peak block roads, school time or commuter time of large-scale units, weather information and the like, are mined continually from a plurality of data sources comprising webpages, microblogs, real-time reported traffic information, historical regularity information and the like. By acquisition of the traffic hotspot information in real time, and combination with influences of a road maximum speed limit, road width and traffic light delay at intersections to driving as well as whether a main road containing a non-motor vehicle zone, a rapid navigation route with an avoiding function is planed, and also a dynamic path planning can be carried out in real time base on a current position. The method helps to provide a fastest path to the destination for drivers and alleviate city traffic jam in certain degree.

The invention provides a vehicle running track reconstruction method based on multiple probability matching under sparse sampling, which is characterized in that a historical data statistics sparse sampling point tolerance distribution is used, and a search area is determined; then a candidate match object (road section or intersection) is searched in a region of search, and can be divided into various types according to the characteristics of the candidate object, if no match object is in the search area, the sampling point is not considerate, if only one object is in the search area, then the sampling point couples to the only object, if various candidate objects is in the search area, a double layer probability matching model is used for further processing; the double layer probability matching model can calculate the coupling probability of each possible track according to matching probability of the sampling point and the selection probability of the reasonable path, and the track with utmost possible probability can be selected for being taken as a reconstruction track of the sparse sampling point. The vehicle running track reconstruction method can reduce the matching error of the sparse sampling data, and can effectively increase the precision and speed of reconstructed vehicle running track in a complex road net.

The invention relates to a method and device for establishing an enterprise image. The method includes the steps that data related to the enterprise image is obtained; the data related to the enterprise image is preprocessed, and preprocessed data is obtained; the preprocessed data is classified; the classified data is matched with an enterprise, and data after being successfully matched is storedin an enterprise information database corresponding to the enterprise; through data stored in the enterprise information database, the enterprise image corresponding to the enterprise is established.The data related to the enterprise image is obtained to be correspondingly preprocessed, and some useless data or repeated data or the like can be removed; then the data is classified to be matched with enterprise information so that the matched data can also be separately stored; the enterprise image is established according to the classified data, enterprise all-dimensional information is integrally depicted, and the established enterprise image is more comprehensive and objective.

The invention discloses a medical big-data analysis and processing system and method based on the IOT (Internet of Things), and belongs to the technical field of data processing. The big-data analysisand processing system mainly comprises a cloud service platform, a user terminal, a hospital database and a medical platform terminal. The medical big-data analysis and processing method of the invention comprises the steps: data acquisition and transmission, data preprocessing, prediction model constructing, and testing and optimizing of a prediction model. Therefore, the prediction model for indicating the probability of a disease of a predicted object or the probability that the predicted object has a certain disease is obtained, and the IOT transmission of the data information is achievedthrough a communication module. Moreover, the prediction model is obtained based on the convolutional neural network The data source with many correlations and wide influences is inputted, and the data has been preprocessed, which greatly improves the accurate reference value of the prediction results.

The invention provides an epidemic disease forecasting method, system and equipment, and relates to the technical field of epidemic disease forecasting. The method comprises the steps that the epidemic disease relevant data are acquired, wherein the relevant data include the internet data, the weather data and the biological information data acquired by the intelligent terminal, and the internet data include the search data and the social network data; the data cleaning is performed on the relevant data; an integrated forecasting model is established according to the relevant data after data cleaning; and forecasting is performed according to the integrated forecasting model and the forecasting result is outputted. According to the epidemic disease forecasting method, system and equipment,the data sources are wider, the forecasting effect is better, the forecasting accuracy is higher, the cost is lower and the effectiveness is higher and the possible epidemic disease outbreak can be forecasted earlier.

The invention discloses a method for optimizing a low-permeability reservoir intermittent mining working system based on a model coupling exhaustion method. Aiming at the input and output characteristics of a low-permeability and low-yield well, through the combination of the flow-in dynamic characteristics of the low-permeability reservoir, the liquid level change rule of an intermittent mining well shaft and the pump efficiency analysis, and based on the relation between the stratum liquid supply capacity and the pumping and suction capacity, a stratum flow-in dynamic model and a well shaftoutflow dynamic model are established, a coupling model is established through the coupling parameters of the bottom flow pressure and the pump efficiency, a computer solution model is established onthis basis, and the optimization of the low-permeability reservoir intermittent mining working system determination method is carried out by means of an exhaustion method. The method can accurately describe the low-permeability reservoir seepage law, realizes the real-time dynamic changes of the bottom flow pressure and the pump efficiency during the intermittent mining, and realizes the accuratequantified intermittent mining limit. The exhaustion method has better optimization precision, and the program calculation efficiency is high.

The invention relates to a credit assessment technology, and aims to provide a personal credit assessment method and system based on fusion neural network feature mining. The method comprises the steps that behavior data of an individual user are preprocessed and checked and then subjected to matrix processing, and the obtained data serve as input of an LSTM model and a CNN model at the same time; in the LSTM model, sequentially processing by an embedding layer, a bidirectional long short-term memory neural network and an attention mechanism layer, and outputting a time sequence behavior feature vector extracted from the data; in the convolutional neural network model, processing is carried out through a convolutional layer and a pooling layer in sequence, and local behavior feature vectors extracted from the data are output; and carrying out vector splicing on the two types of feature vectors, taking the spliced feature vectors as input of an XGBoost classifier, and carrying out training to finally obtain a personal credit evaluation result. Compared with the prior art, the method has the characteristics of comprehensive index coverage, wide processing index source, advanced modeling mode, flexible model expansion, complete and effective feature extraction and accurate result.

The invention provides a relational network construction method, a device and electronic equipment. The method includes the steps of acquiring locked suspects in a target case; acquiring target data related to the locked suspects, wherein the target data include communication text data and also include person relationship data and/or consumption record data; carrying out data analysis of the target data and determining target persons; determining person association information corresponding to a specified dimension among the locked suspects and the target persons according to the target data;and establishing the relational network of the target case according to the locked suspects and the target persons as well as the person association information. Data sources in the relational networkconstruction method, the device and the electronic equipment are extensive and are not limited to the communication text data, and also relate to the person relationship data and/or the consumption record data. Based on these data, the relational network is constructed, a single data source problem is solved, and the reliability and practicality of the relationship network are improved.

The invention relates to a real-time traffic safety index dynamic comprehensive evaluation system and a construction method thereof. The construction method is characterized by comprising the following steps: step 1, collecting related data influencing traffic accidents and extracting characteristics of various data; step 2, establishing an accident risk assessment and prediction model by taking the characteristics of the collected related data as independent variables and taking a traffic safety index formed by the number and the grade of historical traffic accidents as dependent variables, and solving model parameters; step 3, according to the accident risk assessment and prediction model obtained in the step 2, calculating expectation of the number of traffic accidents occurring in different areas in combination with real-time road conditions, road structure attributes and driving safety coefficients, and obtaining real-time traffic safety indexes of the different areas through calculation according to a pre-established safety index model; and step 4, establishing a visual display platform for displaying the real-time traffic safety indexes of different areas. The system and method can be widely applied to the field of traffic safety evaluation.

The invention relates to the technical field of information, and discloses a rail transit platform door remote fault diagnosis method and system. The method comprises the steps that the platform doordata are collected, the platform door data are from at least two platforms, and the platform door data include the state parameters of each device; when a hardware fault report is received, the faultcause of the hardware is diagnosed according to the platform door data; the feature parameters, the purchasing information and the logistics information of the hardware are extracted, and the diagnosis report is acquired through combination of the fault cause of the hardware; and the diagnosis report is transmitted to a remote terminal. The diagnostic basis of the remote fault diagnosis technologyis abundant and the feedback is rapid so that the common maintenance personnel can remotely determine the fault and eliminate the fault through the remote terminal with no requirement for the manufacturer to send professional research and development technicians for field maintenance when the fault of the platform door occurs, and thus the fault maintenance speed can be enhanced and the labor cost can be reduced.

The present invention relates to a suspicious threat index active validation method and system based on source-opening information. The method comprises the following steps of: 1) designing a specialquery statement, wherein the special query statement is combination of suspicious threat indexes and special scenes; 2) collecting and crawling result information obtained through retrieval on the internet according to the special query statement; 3) performing structuring processing of the related source-opening information in the result information to obtain structural data; 4) employing the structural data to fully learn the hidden features and train a corresponding classification model; and 5) employing the classification model to verify the malevolence of the suspicious threat indexes inthe special scenes so as to identify the network threat. The system comprises a query design module, an information collection module, a data processing module, a model training module and an index verification module. The suspicious threat index active validation method and system based on source-opening information can efficiently and accurately complete the verification of the suspicious threatindexes to help users with identification of high-class threat attack so as to ensure network safety.

The invention discloses a method for evaluating the safety drilling probability of ultra-high temperature and high pressure development based on a Weibull function. The method comprises the followingsteps: collecting a pore pressure data sample of an ultrahigh-temperature high-pressure stratum and a vertical well fracture pressure data sample; obtaining probability density distribution of the pore pressure of each section and the fracture pressure of a vertical well according to the occurrence frequency of the pore pressure of each section and the fracture pressure of the vertical well; determining a dual-parameter Weibull function expression of pore pressure and vertical well fracture pressure probability density; integrating to obtain a cumulative probability function expression of thepore pressure and the vertical well fracture pressure; determining a cumulative probability expression of the vertical well safety pressure; determining a cumulative probability expression of the safety pressure of a directional well; and calculating a safe drilling probability value of the ultrahigh-temperature and high-pressure directional well. By means of the method, the safe drilling probability can be evaluated before drilling of a development well, high-risk operation is avoided, cost and safety accidents are reduced, and the method has important significance in development of an ultra-high-temperature and high-pressure oil and gas field.

The embodiment of the invention discloses an analysis processing method and device for teaching big data. The method comprises the steps of acquiring structured teaching data and semi-structured log files in all regional servers; analyzing the semi-structured log file, extracting an entity relationship in the semi-structured log file, and converting the semi-structured log file into structured feature data according to the entity relationship; and establishing an analysis model according to the structured teaching data and the structured feature data, and analyzing teaching big data accordingto the analysis model. Structured teaching data and semi-structured log files in all regional servers are acquired, so that the data source is relatively wide; by analyzing the semi-structured log file into structured feature data, the data structure is consistent, an analysis model is conveniently established, scientific modeling and analysis of teaching big data are achieved, monitoring, evaluation and diagnosis can be conducted on all aspects of student learning, and a teacher is guided to be continuously adjusted into a better teaching mode.

The invention discloses a driving behavior data acquisition and analysis method and system. The invention relates to the technical field of traffic big data analysis, and solves the problem of high data acquisition and analysis cost caused by a traditional driving behavior data acquisition mode. According to the invention, data contents are selected as positioning data, speed data, urgent acceleration and deceleration data, lane departure data, license plate image data and front road video data, the data source can be an automobile data recorder or a vehicle-mounted mobile phone of any vehicleon the road. More than 90% of road vehicles can be basically covered on the premise of not increasing extra construction cost. The method has the advantages of wide data source, simple data acquisition, simple analysis method and low analysis equipment performance requirement, greatly reduces the construction, operation and maintenance cost on the whole, and is more beneficial to the realization,popularization and promotion of driving behavior analysis.

The invention discloses a big data-oriented potential adverse drug reaction data mining system and method. The system comprises a plurality of acquisition terminals, an electronic medical record acquisition module, a specific drug data mining module, a cloud terminal adverse event data processing module, a cloud generation module, a main control computer, a human-computer interaction interface anda data switch, the method comprises the following steps: S1, networking electronic medical record systems of hospitals; S2, capturing a patient who takes the specific medicine in the electronic medical record system; S3, establishing a database of related drugs and adverse reactions after the drugs are used; S4, screening data; and S5, performing feature classification. According to the invention, adverse reactions of specific drugs are analyzed by integrating electronic medical records of various hospitals, the data source is wider, various populations exist, and the analysis of reactions ofdrugs relative to various populations is facilitated. Useless data can be eliminated in the analysis process, analysis is facilitated, the data analysis workload is reduced, and the sample accuracy is improved.

The invention belongs to the technical field of machine vision, and discloses a non-contact respiration detection method and device. The detection method comprises the following steps: acquiring a breathing image of a chest and abdomen area of a human body; the breathing image is converted into a gray level image, and the movement speed of each pixel point in each frame of gray level image in the X-axis direction and the movement speed of each pixel point in the Y-axis direction are obtained through an optical flow method; and obtaining the sum of the movement speeds of all the pixel points in the X-axis direction and the sum of the movement speeds in the Y-axis direction of each frame of gray level image to obtain a breathing oscillogram. The method has the advantages that the breathing oscillogram is obtained through the breathing image of the chest and abdomen area of the human body, the breathing image can be collected through the camera, and therefore data sources are wide, and the method can adapt to breathing detection in more application scenes.

The invention provides a general ledger-based supervision index configuration implementation method and device, a medium and equipment. The method comprises the steps of inputting general ledger basic index data; calculating to obtain an R index according to the general ledger basic index data and a calculation engine; according to the demand of the off-site supervision report and the R index, calculating to obtain a derived index of which the hierarchy is higher than the R index; obtaining different off-site supervision reports according to derived indexes of which the levels are higher than the R index; and performing consistent data submission on different off-site supervision reports. On the basis of the basic indexes, a set of R indexes is configured and generated according to 1104 off-site supervision requirements, and report filling is performed on the basis of the R indexes to meet the requirements of consistent submission calibers and high accuracy requirements. And when the index caliber changes, the effect can be taken in all related reports only by modifying the configuration, so that the submission pressure is greatly reduced.

The invention discloses an article alias mining method and system, electronic equipment and a readable storage medium. The article alias mining method comprises the steps of performing reverse association to obtain all retrieval keywords of an accessed article in a preset time period; obtaining the retrieval amount of each retrieval keyword in the preset time period; judging whether the retrievalamount of each retrieval keyword is larger than a preset threshold value, and if so, taking the retrieval keywords larger than the preset threshold value as the candidate words; obtaining comment dataof the article; for each candidate word, obtaining the association degree of the candidate word and the article according to the comment data; and judging whether the association degree is greater than a preset threshold, and if so, taking the candidate words of which the association degree is greater than the preset threshold as another name of the article. According to the article alias miningmethod, the user comments and the user retrieval data are used as mining data sources, and the data cost is low, and the data sources are wide, meanwhile, the data comes from users, and the mining precision is higher, and the user experience is better.