168results about How to "Improve the matching success rate" patented technology

The invention discloses a block chain-based online taxi-hailing service system. The system includes a traffic cloud database, a traffic cloud artificial intelligence system (TAI) and a mobile client. With the block chain-based online taxi-hailing service system adopted, a decentralized, trustless, collectively maintained, asymmetric cryptography reliable database basic infrastructure and underlying internet protocol can be provided for traffic cloud; and a mobile SaaS (Software-as-a-Service) application pattern, a distributed computing normal form and a group intelligence model which can establish high-degree connections for travelers based on time stamp, achieve travel resource allocation consensuses and provide services according to demands can be realized.

The invention relates to a fuzzy Chinese address geographic evaluation method based on a matching rule, which belongs to the field of the address evaluation of a geographic information system. The method comprises the following steps: firstly, reading in an address character string and a standard address base; inquiring and dividing administrative division parts in the address character string and filtering reduced target data sets; then realizing the segmentation and the matching of an address by means of a matching rule tree and a rule base in allusion to the fuzzy problems of address element incompletion, address ambiguity and the like frequently appearing in the address character string, and returning a matching record meeting requirements. The invention integrates two important links of address segmentation and database matching in geographic evaluation, realizes that the database matching of the address is completed while in segmentation, effectively solves the address matching problem of the fuzzy Chinese address and improves the accuracy and correctness of address matching.

The invention discloses an automatic license plate character recognition method. The method includes following steps: inputting color vehicle images; pretreating the images; choosing different algorithms for license plate positioning under different light conditions; subjecting a license plate to horizontal tilt correction and vertical tilt correction; adopting a method based on cluster connection and vertical projection to perform character segmentation to the license plate obtained in step d; using an improved template matching method to perform character recognition to characters obtained in step e; and outputting recognition results of step f. By the automatic license plate character recognition method, using performance of a whole automatic license plate character recognition system is evidently improved, in the step of license plate positioning, license plate positioning can be realized by choosing different algorithms under different light conditions and utilizing characteristics of license plate areas, and accurate positioning of license plate area positions can be guaranteed even under the circumstance that interferences occur.

The invention discloses a method for automatically matching multisource space-borne SAR (Synthetic Aperture Radar) images based on an RFM (Rational function model). The method comprises the following steps of: calculating respective RPC (Rational Polynominal Coefficient) parameter of images; performing forecast of initial positions of points to be matched, matching of approximate epipolar line geometric establishment constraints and geometric rough correction of matched window images by using the RPC parameters of the images on every pyramid image layer, deleting wrong matching points from the image matching result of every layer of pyramid by adopting regional computer network error compensation based on an RFM model; refining the RPC parameters of the images and calculating the object space coordinates of the matching points; refining the matching result to the original image layer by layer; and refining a matching result by using a least square image matching method to realize automatic and reliable matching of common points of multisource space-borne SAR images. In the method, the RFM model is introduced into automatic matching of the multisource space-borne SAR images, and the regional computer network error compensation of the RFM model is blended into the image matching process of every layer pyramid, so that wrong matching points in the matching process can be effectively deleted, and the workload of manual measurement of common points is effectively lowered.

The invention discloses a steady automatic matching method for high-resolution satellite image connecting points. The method comprises the following steps of: A, performing automatic enhancement by using Wallis filter technology, generating pyramid images of each layer and extracting the images by using feature extraction operators; B, forecasting an initial point position of identical points by using satellite image orientation parameters and upper pyramid matching results of characteristic points, establishing an epipolar geometric constraint equation, and performing geometric coarse correction on matched window images; C, removing error matched points in the matching result of the pyramid images of each layer by using an RFM model-based block adjustment method; and D, repeating the steps B, C and D till the primary image layer, and finally refining the matching result by using a double-sheet least square matching method. The method can greatly reduce the artificial editing workload of connecting point measurement and improve the automation degree of satellite image data processing by combining block adjustment and satellite image matching, and has remarkable economic benefit and social benefit.

The invention provides a visual guiding-based robot workpiece grabbing method, and belongs to the field of robot visual recognition and positioning. The method comprises the following steps of (1) establishing templates of target workpieces in advance, collecting images of the target workpieces, and acquiring edge feature images of the templates and edge feature images of the target workpieces; (2) acquiring the deflection angle of each target workpiece relative to the corresponding template by utilizing the minimum enclosing rectangle of the edge feature image of the target workpiece, and establishing a compensation template set by utilizing the deflection angles and the edge feature images of the templates; (3) matching the edge feature images of the target workpieces and the compensation template set, and recognizing the target workpieces and acquiring the center coordinates of the target workpieces under a visual coordinate system; (4) converting the visual coordinate system to a robot user coordinate system; and (5) selecting a reference point, and uniquely identifying the same target workpiece by utilizing the time and the position to complete positioning grabbing. The targetworkpieces can be accurately recognized by utilizing the method.

The invention discloses an address matching method for sorting. The method includes the steps of obtaining address information of an email, carrying out data cleaning according to the address information, analyzing and processing the address information after data cleaning by means of a Chinese word segmentation algorithm, obtaining a segmentation result, and carrying out email dress matching according to the segmentation result. By means of the method, automatic matching of email addresses can be achieved, the workload of workers in the sorting process is lowered, and matching efficiency and the success rate are improved.

The invention relates to a service network station matching method and system. The method comprises the following steps of: obtaining the position of a customer; matching the position with a service area of each to-be-selected network station, wherein the service area is a geographic area formed by a plurality of service boundary points of the to-be-selected network station; and when the position is located in the service area of one of the to-be-selected network stations, determining the to-be-selected network station as a service network station of the customer. According to the method and system, geographic position matching is carried out on the longitudes and latitudes of customers and the service areas, the problem of matching failure caused by nonstandard address information or incomplete service network station information for matching when only address information obtained by text input is matched is avoided, and the success rate of matching between the customers and the service network stations is effectively improved.

The invention provides an infrared matching method with a feedback function. The method comprises the steps: storing and transmitting an infrared code by adopting a cloud server, automatically transmitting the infrared code to an infrared matching device after the cloud server receives a mobile terminal matching instruction, transmitting an infrared signal to an electric appliance after the infrared matching device receives an infrared code instruction set, and monitoring a power-on situation of the household electric appliance by virtue of an electric appliance state monitoring device, wherein whether the matching is succeeded or not can be remotely confirmed. According to the infrared matching method, the automation is completely realized, the infrared matching can be realized only by pressing a starting button, and the operation is easy and convenient; according to the entire infrared code matching process, only a power-on instruction needs to be matched by simplifying the instruction set, so that the matching time is shortened, the matching success rate is increased, and the user experience is improved. The invention also provides an infrared matching system utilizing the method. The infrared matching system comprises the mobile terminal, the cloud server, the infrared matching device and the electric appliance state monitoring device.

The invention relates to an assisting image matching method by means of airborne lidar point cloud data. The assisting image matching method by means of the airborne lidar point cloud data includes the steps of obtaining a reference image, searching image and the cut out airborne lidar point cloud data, abstracting a feature point from the reference image as a point to be matched, generating regularized digital surface model (DSM) information corresponding to an image overlapped region by means of the lidar point cloud data, converting point of sale (POS) data into elements of exterior orientation of the reference image, working out object space coordinates of corresponding ground points of the feature point to be matched by means of the DMS information and the elements of exterior orientation of the reference image, reversely calculating object space coordinates of the corresponding ground points to the searching image, obtaining the initial position of a corresponding matching point of the searching image, and matching by means of the correlation index to obtain a final matching result. The assisting image matching method provides good object space restraint for image matching by means of the lidar point cloud data, can effectively avoid complicated search strategies, achieves the purpose of the image matching and is high in matching success rate, short in consumed time and effective.

The invention discloses an address similarity calculation method and device, equipment and a storage medium. Aiming at the problems that address matching has complex rules, an existing matching algorithm is not high in retrieval speed and accuracy, and the address matching efficiency is low, a solution is proposed. Input address information is expressed by a proper initial vector; an address similarity calculation model based on a twin neural network is used, a gradient descent algorithm of a ternary loss function is combined, thus obtaining a feature vector of the initial address vector; finally, the cosine distance or L2 distance between the feature vector and an address vector in a standard address data set is calculated, the known address vector closest to the input address vector is obtained, so that the address matching rule is simplified, the preferred accuracy of the same address is improved, and the retrieval speed and accuracy of the matching algorithm are further improved.

The present invention relates to an information transmission method, a video playing device and a video display device. The information transmission method includes: sending an information read instruction to a video display device; acquiring EDID according to a preset acquisition rule, and extracting display parameters from the EDID; judging whether the display parameters successfully match playing parameters of a video playing device; transmitting video data matching the EDID to the video display device if the display parameters successfully match the playing parameters; and reacquiring the EDID according to the preset acquisition rule if the display parameters unsuccessfully match the playing parameters, wherein versions of the EDID acquired by the video playing device each time are different. The information transmission method, video playing device and video display device in the technical solution provided in the present invention enable the video playing device to read EDID matching playing capabilities thereof, so that video data can be successfully transmitted to the video display device.

The invention discloses a protocol-independent network redundant flow eliminating method. According to the method, a certain number of data packets are grabbed from a network in advance, the data packets are grouped according to the magnitudes of loads, statistics of the data size cumulative probability of grouping is conducted, a corresponding load threshold value is determined, and a sending end conducts redundant flow elimination on the data packet the load of which is larger than the load threshold value; the loads are partitioned according to the weak Hash values, the strong Hash value of each data block is taken as a fingerprint to be matched with a fingerprint in a fingerprint base, the fingerprint which is not matched with the fingerprint in the fingerprint base and the corresponding data block are updated to the fingerprint base and a data block base, the sending end takes the initial positions of all the data blocks in the data packets and the positions of all the data blocks in the data block base as loads to regenerate data packets and sends the data packets to a receiving end, and the receiving end conducts recovery on the data packets after receiving the data block information in the data packets. The method is used for processing redundant data among the data packets without being affected by the application layer communication protocol and has a good redundant flow elimination effect and a good processing time effect.

The present invention belongs to the field of the radar simulation technology, and discloses an intelligent acquisition and intelligence automatic generation system on the basis of Agent radar real-equipment data and a method thereof. The system provided by the invention comprises a radar intelligence generation server and embedded acquisition devices. The first end of the radar intelligence generation server is connected with a plurality of embedded acquisition devices through a local area network, and each embedded acquisition device is connected with a real-equipment radar through the local area network or a RS485 netting twine and a RS232 netting twine; and the first end of the radar intelligence generation server is connected with a simulation application system of a radar data output device through the local area network or the RS485 netting twine and the RS232 netting twine, and the embedded acquisition devices are acquisition Agent hardware architectures. According to the invention, a plurality of real-equipment radar data may be acquired to realize radar real-equipment data mining and derivation of radar target track data, obtain optimal track truth values and noise models and synthesize the optimal track truth values and noise models to be a new radar simulation intelligence, therefore the application scope of the automatic generation technology of radar target tracks is further developed.

Novel automatic aero-triangulation software is disclosed. With wide application of unmanned aerial vehicles, responses to emergencies can be carried out by means of the unmanned aerial vehicles as a platform to perform photogrammetry. The software aims to aerial images, especially to aerial image treatment in the unmanned aerial vehicles. In the software, a feature extraction algorithm of large data is employed for treating the aerial images and a block adjustment of the large data is treated in a manner of internal and external memories, and meanwhile camera parameters are calculated.

The invention discloses a digital television and a searching method for external input channels thereof. The searching method comprises the steps that the digital television controls external input equipment to switch channels, and displays a channel list or related channel information; the digital television captures a television picture and identifies channel names and channel numbers in the captured picture; the digital television interacts with a server so as to confirm the channel name and the channel number matched with the identified channel name and the channel number in a channel list database stored in the server; and the digital television outputs the matched channel name and the channel number so as to generate a channel list. According to the searching method, the digital television can confirm the corresponding relation of the external input channel name and channel number, and provides the corresponding relation for a user; when automatic identification is not correct, the user is allowed to input a correct channel number manually to correct the channel list, so as to realize right channel switching; and the invention provides users with a convenient solution for television channel direct switching in television applications, so that the users avoid unnecessary operations and prevent mistakes.

The invention discloses an emergency calling method and electronic equipment. The method is applied to the electronic equipment and comprises steps as follows: initiating a call request carrying a call number in the absence of a card; acquiring the call request, analyzing the call number, performing inquiry according to the mapping relation between the call number and a current national emergency number, and feeding back an inquiry result; judging whether the received and fed inquiry result is that the call number is matched with the current national emergency number, if yes, allowing the call number to be called as the current national emergency number; otherwise, forbidding calling. With the adoption of the emergency calling method, problems of wrong matching and the heavy maintenance workload caused by adoption of existing emergency calls in the absence of cards are solved at least, numbers can be matched quickly, emergency calls are realized, and the calling success rate is increased.

The invention relates to a space-borne synthetic aperture interferometer radar image registration method with feature point Voronoi diagram optimization. The method is mainly characterized in that the deployment strategy of a matching reference point is novel, the attribute information of statistical information, thematic information, topological information, metric information and the like of a feature point is fully considered. The method comprises the steps of (1) obtaining the space-borne InSAR complex image pair of a measured area, (2) calculating the energy image of one complex image in the image pair and carrying out filtering processing, (3) using a Forstner operator to extract a feature point in the filtered energy image, (4) constructing a Voronoi diagram for the extracted feature point and optimizing the feature point by using the Voronoi diagram, (5) using the optimized feature point and adopting a method related to maximum spectrum to search a same name point, (6) calculating a model parameter between two images according to the searched same name point pair, and (7) unifying the two images in the same image coordinate system by using the calculated model parameter. According to the method, the same name point search success rate and related coefficient value are raised, thus the optimized feature point is more reasonable in the distribution, the calculation precision of the model coefficient is raised, and thus the registration precision of the image pair is raised.