141 results about "Information coverage" patented technology

The invention relates to the field of intelligent transportation, and discloses a method and system for acquiring real-time traffic status information. The method includes the following steps that all road sections in a road network are traversed, so that effective links with the starting nodes and the terminal nodes being each provided with a checkpoint device are generated; the vehicle passing data of all the checkpoint devices in the current road condition period or the previous historical period within the license plate backtracking period are read in; the effective links are read one by one, and vehicle passing records corresponding to the starting nodes and the terminal nodes of the links are screened out in the vehicle passing data; the vehicle passing data matched with license plates are searched for, accordingly, the section vehicle speed and the reliability of single samples are calculated, and abnormal samples are filtered; the samples of all the effective links are distributed to all the road sections to generate the real-time traffic status information. According to the method and system, foundation road network data are processed to generate the effective links, the license recognition vehicle passing data are analyzed on this basis, the concept of the sample reliability is introduced, and the accuracy rate of the real-time traffic status information and the information coverage of the complex road network can be improved.

The invention relates to an intelligent wireless network door interlock which is used for a door lock management system adopted in occasions such as hotels, restaurants, departments and rental rooms, etc. The intelligent wireless network door interlock comprises a front desk terminal, a door lock terminal and a non-contact IC card and is characterized in that: the intelligent wireless network door interlock is also provided with a wireless network which connects and manages the front desk terminal and a plurality of door lock terminals. The intelligent wireless network door interlock of the invention has novel design and utilizes the wireless network and a short message system to control the door lock system and carry out corresponding management, thus having large information coverage area without being limited by the location; the management is convenient, intelligent and economic, therefore, the intelligent wireless network door interlock is especially suitable for the remote monitoring.

The embodiment of the invention discloses an abstract generation method and device, a server and a storage medium. The method comprises the following steps: carrying out sentence segmentation on a target text to obtain a sentence set; Obtaining a target topic corresponding to a target text, and predicting each sentence in the sentence set by using a pre-trained abstract model in combination with the target topic to obtain a probability value that each sentence is an abstract sentence; And selecting a plurality of abstract sentences from the sentence set according to the probability value, andforming an abstract of a target text according to the abstract sentences. According to the embodiment of the invention, when the abstract is generated, the abstract which has higher relevancy with thetheme and is more accurate is generated by combining the theme of the text, the important information coverage capability of the abstract is improved, and meanwhile, diversified abstracts can be generated according to different themes.

The invention discloses a video key frame selecting method. The video key frame selecting method is characterized in that video frames can be divided into n categories by adopting a clustering method, and the categories are called F; a candidate key frame set C can be calculated; video information amount Ii represented by the candidate key frame ci can be calculated; the maximum candidate key frame ci of the video information amount Ii is selected to be the first key frame set S1; according to the formula .... the next key frame set Sk+1 can be calculated in an iterative manner; the video total information amount represented by the key frame set Sk+1 can be determined; and the key frame set Sk+1 can be output. Starting from the diversity of the key frame sets and the maximum information coverage angle, the key frame sets can be quickly and effectively selected from the classified video frames, and therefore the occurrence of the redundancy frames can be well prevented, and the lengths of the key frame sets can be determined automatically; the video key frame selecting method is simple and easy to realize, and the effect is good.

The invention provides a multi-source traffic information fusion method which comprises the following steps: all kinds of traffic information is preprocessed and is on a unified processing road network; the preprocessed traffic information is fused in a weighting method, and road sections without traffic information coverage after fusion are filled to form complete traffic information; and the complete traffic information is generated and released according to a standard position. According to the invention, floating car traffic information is fused with non-structured traffic information such as micro-blog information, event information, traffic website information and the like, and historical traffic information is used as a data source and fused with real-time traffic information based on the rules of the historical traffic information.

The invention relates to big data, the invention provides a webpage labeling method. The method comprises the following steps: receiving a labeling request; determining a webpage to be labeled according to the labeling request, monitoring a trigger event on the to-be-labeled webpage; obtaining a target area, extracting information in the target area, determining the type of the information; obtaining a plurality of preset tags corresponding to the type from a configuration tag library, acquiring data corresponding to the plurality of preset tags; according to the plurality of preset labels andthe data, obtaining the data, construction of a target model, and inputting the information into the target model, generating annotation information, improving the generation efficiency of the annotation information, establishing an identifier according to the target area and the annotation information, and storing the identifier, thereby not only realizing quick annotation of the webpage, but also avoiding annotation information coverage generated when different users annotate the same area. The invention also relates to a blockchain technology, and the annotation information is stored in the blockchain.

The invention discloses an intelligent monitoring method and device, computer equipment and a storage medium, and the method comprises the steps: collecting the basic information and target address ofa floating person and the MAC address of portable electronic equipment; generating an action path and an activity space according to the target address; collecting real-time data, performing structured processing on the real-time data to obtain structured data, storing the structured data in an acceleration processing layer, and storing historical data in a batch processing layer; carrying out correlation analysis on the space-time relationship of the real-time data, and outputting a behavior space track of the floating person and residence time at each monitoring point; and outputting the probability of track abnormality through a classification model based on supervised learning, and giving an alarm outwards when the probability exceeds a threshold value. According to the invention, therelated information of the floating personnel is collected, and the plurality of monitoring points are combined to monitor the floating personnel, so that the information coverage of the floating personnel is improved, the trajectory tracking of the floating personnel is enhanced, and the interests of community residents are guaranteed.

The invention discloses a book automatic classification method. The method comprises the steps of S10: through shooting or scanning, obtaining image sources of book covers, and identifying book covertexts to obtain cover text information; S20: according to the cover text information, performing matching in a book database to obtain book attribute information; and S30: according to information carried in the book attribute information, outputting book classification information, wherein the classification information includes one or more of book theme classification information, book price classification information, book audience classification information and book evaluation grade classification information. According to the method, the effect of quickly and automatically performing corresponding classification on books can be achieved; furthermore, a user can perform corresponding retrieval according to inclined retrieval classification items to quickly find the books which the userplans to retrieve; and the classification types are rich, the information coverage is wide, the classification accuracy is high, and the classification efficiency is high.

The invention discloses an infrared target robustness recognition method in combination with multi-feature dimensionality reduction and transfer learning. The method comprises: firstly providing, in view of the incomprehensive information coverage of a traditional infrared human target feature extraction method extracting a single feature, heterogeneous features for extracting different types of targets, including the shape feature and the brightness feature of the target image, so as to fully excavate the features of an infrared human target; secondly, using a principal component analysis method to reduce the dimensionality of the fused heterogeneous feature; and finally, designing an effective infrared human target classifier based on transfer learning to maximize the generalization performance and target recognition accuracy. Compared with the traditional infrared human target recognition method, the method provided by the invention improves the infrared human target recognition performance in a complex background.

A system for dynamically offloading data and video traffic to a broadcast offload core network from a cellular network or to the cellular network from the broadcast offload core network is provided. The system includes an analytics engine, a load manager, and a radio access network (RAN). The analytics engine captures geographical radio frequency (RF) information from a geographical RF information database. The geographical RF information includes an operator infrastructure information, a physical terrain information, a subscriber information, a coverage information, a signal quality information, and telecom traffic patterns. The analytics engine determines whether to offload the data and the video traffic to at least one of a unidirectional downlink network from a unicast network or the unicast network from the unidirectional downlink network by analyzing a hybrid cellular user equipment from a particular geographical location trying to access the data or video content.

An information storage apparatus recognizes a traffic sign on a road expressed by a road surface image, and stores recognized traffic sign in association with its position information in a hard disk drive. By recognizing and storing information on the traffic sign in combination with the position information for the sake of traffic safety, information coverage in terms of traffic safety is updated to the most up-to-date condition for roads in the entire country.

The embodiment of the present invention provides a picture generating method, a display method and corresponding devices. The picture generating method comprises: acquiring image resources and voice data, and generating voice pictures according to the image resources and the voice data. Through the adoption of the technical scheme, the generated novel voice pictures not only comprise image information, but also comprise voice information. The picture representing forms can be enriched, the picture information coverage is increased, and the picture browsing experience of users is improved.

The embodiment of the invention discloses an information rendering method and device, equipment and a medium, and relates to the field of image processing, in particular to an intelligent traffic technology. According to the specific implementation scheme, the method comprises the following steps: identifying a live-action road image acquired from an image collector, and determining a road surfacearea in the live-action road image and a target object position included in the road surface area; and avoiding the position of the target object, and rendering the auxiliary driving information to the road surface area. The embodiment of the invention provides an information rendering method and device, equipment and a medium. Rendered auxiliary driving information is prevented from covering traffic sign information of vehicles, pedestrians or roads ahead.

The invention discloses a method for estimating precise circumferences of target boundaries based on gray level information. The estimating method comprises the following steps of (1) introducing concepts covering digitization to process synthetic target images, thereby acquiring the images retaining gray level information and covering digitization; (2) to the acquired images covering digitization, defining the internal and external boundaries of the target object in the images, and acquiring the target object of the internal or external boundary with the pixel width by tracking the boundary; (3) calculating the boundary slope of the local configuration region on one pixel-width image boundary, and acquiring the circumference of the configuration region according to an arc length calculation formula; (4) accumulating the obtained circumferences of the boundaries in the local configuration region by browsing the boundaries, thereby respectively obtaining the circumferences of the internal and external boundaries in all target objects; (5) according to the obtained circumferences of the internal and external boundaries, finally obtaining the precise circumferences of the target objects by adopting a certain strategy. According to the method, the circumference calculation process cannot be affected by fuzzy image boundaries, boundary discontinuity, boundary noise and various complex factors, and the problem that the target circumference cannot be precisely estimated by other algorithms under discontinuous and fuzzy target boundaries can be better solved, thus the accuracy, effectiveness and robustness of the circumference calculation process is greatly improved and the method can be widely used for extracting actual image characteristics.

The invention discloses a resource monitoring method and device for an artificial intelligence server, and the method comprises the steps: obtaining a first operation state of a predefined target process and a second operation state of a GPU application program, and judging whether the target process exists or not according to the first operation state and the second operation state; in response to the existence of the target process, using a performance monitoring counter to automatically collect feature information from the server, wherein the feature information comprises a real-time communication link transmission bandwidth, a control equipment working state, a GPU working state, equipment temperature and equipment power consumption; formatting the feature information into a format stored in a database to be written into the database; and constructing a webpage, periodically reading the feature information from the database by using javascript, and filling the feature information into the webpage in a covering manner so as to visually display and refresh the feature information. According to the invention, graphical display can be supported, sufficient statistical information can be provided to execute performance analysis, automatic resource monitoring is realized, and system problems are solved.

The invention is applicable to the technical field of data extraction, and provides a method and device for extracting information of working spaces and living spaces and a computer readable storage medium. The residence location of each resident individual is obtained through whole sample demographic data. The working site location of each resident individual is obtained through social security payment data and commercial subject data. The residence location and the working site location are put in a spatial basic grid. The residence location and the working site location of each resident individual are connected through encrypted keywords. The actual commuting distance of each resident individual is calculated according to the connected residence location and working site location. The method and device for extracting the information of the working spaces and the living spaces have comprehensive information coverage, can accurately extract the residence location and the working sitelocation of each resident individual, and improve the extraction accuracy of the information of the working spaces and the living spaces.

The invention discloses a signal coverage analysis method integrated with ADS-B measured signals and line-of-sight transmission analysis. The method comprises the following content: 1. ADS-B measured signal coverage analysis based on a concave packet model; 2. segment coverage analysis based on a ADS-B signal reliability grade; and 3, ADS-B signal multiple fusion information coverage analysis integrated into a geographic information system. The method provided by the invention is applied to civil aircraft ADS-B surveillance and operation analysis and site selection recommendation. The signal coverage analysis method improves the accuracy of an existing ADS-B surveillance scope and solves the problem of future location and siting of an ADS-B base station.

The embodiment of the invention discloses a traffic information quality monitoring method and device, which relate to the field of traffic information processing, improve the accuracy of real-time traffic information quality monitoring, and reduce the cost of real-time traffic information quality evaluation and testing. The method includes: acquiring information files containing statistical information of traffic road condition quality in real time; analyzing the information file to obtain the statistical information of traffic road condition quality; calculating the travel time information coverage according to the statistical information of traffic road condition quality rate; compare the travel time information coverage with the monitoring standard travel time information coverage; if the travel time information coverage is lower than the monitoring standard travel time information coverage, the travel time information coverage Output of comparison with monitoring standard travel time information coverage. The invention is suitable for the online monitoring process of traffic information processing process data.

The invention discloses a power distribution method of a non-ideal millimeter wave wireless power supply communication unmanned aerial vehicle network. The invention discloses a wireless power supplycommunication unmanned aerial vehicle network based on considered non-ideal millimeter waves. The method comprises the steps of firstly obtaining an energy coverage probability expression and an information coverage probability expression of a model, then obtaining an optimization problem of a power distribution coefficient according to an actual demand problem, then solving the optimization problem, and finally obtaining an optimal power distribution coefficient meeting requirements. The invention provides a method for solving the optimal power division coefficient of the millimeter wave unmanned aerial vehicle wireless energy supply communication network under the conditions of non-ideal hardware and non-ideal wave beams, and the efficiency of the network is improved.

The invention discloses a hidden structure learning-based image digest generation method. The method comprises the following steps: (1) extracting the HSV (Hue, Saturation and Value) color histogram characteristic, visual word characteristic and orientation histogram characteristic of a picture; (2) performing normalization preprocessing on the three characteristics extracted in the previous step and combining the three characteristics into a characteristic vector after normalization; (3) constructing a structural support vector machine with a hidden variable, selecting training sets from a database for many times, and performing weight coefficient learning on picture sets related to different subjects in a training set; (4) selecting picture sets related to different subjects from the database by using the weight coefficient obtained by the learning in the previous step, predicting hidden characteristic selection preferences of the picture sets and generating a digest picture set corresponding to the hidden characteristic selection preferences. The method has higher information coverage and lower redundancy, can implicitly learn the different preferences of the picture sets related to the different subjects in characteristic selection and has a better effect compared with the conventional method.

The invention discloses a method for reserving multimedia programs, a server and a terminal, and belongs to the technical field of Internet. The method comprises the following steps: acquiring a plurality of first multimedia programs of which the playing moments are later than a current moment according to the current moment; transmitting a program reservation interface including program reservation options of the plurality of first multimedia programs to the terminal; acquiring at least one second multimedia program reserved by the terminal in the program reservation interface; and giving a playing starting prompt to the terminal before arrival of the playing moment of any second multimedia program in order to realize a way of intelligently reserving the multimedia programs. Reservation of any first multimedia program can be provided, so that the information coverage percentage is high. The second multimedia programs can be reserved as required, and a playing starting prompt can be given specific to any second multimedia program, so that user requirements can be met to the maximum extent.

The application relates to the intelligent traffic technical field, and especially relates to a traffic flow information monitoring equipment setting method and system; the method comprises the following steps: a, determining primary areas-of-interest, and calculating contiguous relations between the primary areas-of-interest; b, gradually merging the primary areas-of-interest according to the contiguous relations, thus obtaining novel interested units; c, calculating the monitoring equipment number needed by vehicle information monitoring between the novel interested units, and setting the monitoring equipment according to the calculation result. The traffic flow information monitoring equipment setting method and system can reduce the areas-of-interest finess degree so as to reduce the monitoring equipment demands, thus providing the maximum vehicle information coverage ability between the areas-of-interest, and preventing the conditions in which the needed equipment number exceeds the present budget.

The invention provides a metering detection service collaboration system and method based on a cloud platform. Aiming at the problems that the on-site metering detection business service time is long,and the efficiency is low, a metering detection service cooperation system based on a cloud platform is established, so that a plurality of working links of on-site testers are seamlessly connected;the waiting time is greatly shortened, the on-site service efficiency is effectively improved. Moreover the system enables all personnel participating in the metering service to obtain the concerned service information in time, cover all links from the work new construction, the certificate generation, the application submission, the certificate audit, the certificate issuing, the certificate downloading and the client feedback management, carries out the efficient and rapid off-site business collaboration based on the Internet, realizes the transparent progress state of metering detection business, timely data transmission, tight business collaboration and high standardization degree, shortens the metering time greatly, and improves the service efficiency and the service quality effectively.