64results about How to "Effective and informative" patented technology

The invention discloses an information recommendation method and device. The method includes the steps of obtaining the target position region where a user is currently located, and determining the recommendation mode according to the target position region, wherein the recommendation mode is adapted to the requirements of the user in the target position region; generating a recommendation result corresponding to the recommendation mode; outputting the generated recommendation result. According to the information recommendation method and device, the recommendation mode can be determined according to the target position region where the user is currently located, and the recommendation mode is adapted to the requirements of the user in the target position region, so that the recommendation result obtained according to the recommendation mode can provide more effective information for the user, and recommendation efficiency is improved.

The invention discloses a method for estimating a separation trajectory of a stage separation wind tunnel free flight test model. The method comprises the following steps of 1, determining an attack angle-mechanical coefficient table of an aircraft model before separation and separated body models after separation; 2, setting initial launching parameters and an initial launching position of a freeflight test of the aircraft model before separation, and setting the separation position of the aircraft model before separation; 3, estimating flight trajectory data of the free flight test of the aircraft model before separation; 4, determining initial launching positions and launching parameters of the separated models; 5, estimating separation trajectory data of the separated models; and 6, judging whether the separation trajectory data of the separated body models meet the test requirements or not, and if not, resetting the initial launching parameters/launching position values in the step 2, starting execution from the step 3 again, until the separation trajectory data of the separated body models meet the test requirements; or readjusting the separation position, and starting execution from the step 4, until the separation trajectory data of the separated body model meets the test requirements.

The invention discloses a rehabilitation training motion state monitoring method and system fusing electrocardiogram and myoelectricity characteristics. The method comprises the following steps: obtaining an electrocardiogram signal and a myoelectricity signal and performing characteristic extraction respectively; performing characteristic fusion based on a random fusion coefficient vector to obtain a fusion characteristic vector; learning a multi-classification motion state recognition model based on a support vector machine by adopting the fusion characteristic vector; performing iterative optimization on the fusion coefficient vector by adopting a particle swarm algorithm to obtain an optimal fusion coefficient vector and a multi-classification motion state recognition offline model; and performing motion state recognition based on the fusion characteristic vector of the electrocardiogram signal and the myoelectricty signal collected in real time. According to the invention, electrocardiogram and myoelectricity signals are fused for motion state detection, so accuracy and reliability are greatly improved, and real-time monitoring of the motion state of rehabilitation training ofa patient is achieved; the motion state can be used as the basis for real-time adjustment of rehabilitation training task intensity and a control strategy, the rehabilitation training effect is enhanced, and secondary injuries caused by excessive training are avoided.

The invention provides a method for pre-estimating flight path of a wind tunnel free flight test model, and the method comprises the steps: 1, obtaining an attack angle - mechanics coefficient table of a flight model; 2, setting the initial attack angle value theta0 of a free flight test, a transmission position, and an initial transmission speed, obtaining the mechanics coefficient at the initial attack angle value theta0 through linear interpolation, and enabling the initial attack angle value theta0 and the corresponding mechanics coefficient to serve as an initial transmission parameter D0; 3, calculating and obtaining pre-estimated flight path data through a Runge-Kutta method after flight at the transmission position; 4, repeatedly carrying out the steps 2 and 3 when the pre-estimated flight path data does not meet the testing requirements, obtaining a new pre-estimated flight path, and carrying out step 4 till the new pre-estimated flight path meets the testing requirements. The method pre-estimates the flight path of free flight of a model in a wind tunnel, enables the flight path to stay for longer tie in an observation region, and obtains more effective information during testing.

The invention discloses a robust automatic face fusion method. The method relates to the technical field of image synthesis, and comprises the following steps: carrying out occlusion processing on a face image A and a face image B to obtain a four-channel image A and a four-channel image B, with the four-channel image A comprising identity features in a synthetic image, and the four-channel imageB comprising attribute features in the synthetic image; encoding the four-channel image A and the four-channel image B to obtain an encoding feature A and an encoding feature B; and combining the coding feature A and the coding feature B through a generative adversarial network, and outputting a face synthesis image. According to the method, a characteristic channel of a shielding mask is added, so that the synthesized characteristic has more effective information, and the method is more robust to a complex scene in practice; occlusion information is enhanced through feature reconstruction, amore complex face fusion scene can be processed, and the applicability is wider; the image segmentation is used for generating a feature mask and fusing the feature mask into original information, andthe boundary of image segmentation is expanded.

The invention relates to an optimized scheduling method for a production and assembly process of an automobile air conditioner air outlet, and belongs to the technical field of intelligent optimized scheduling in production workshops. An optimization objective and a scheduling model in the production and assembly process of the automobile air conditioner air outlet are determined, and the optimized scheduling method for an adaptive hybrid distribution estimation algorithm is used for optimizing the optimization objective, wherein the scheduling model is built according to the processing time of parts of the automobile air conditioner air outlet on each machine and the final assembly completion time, and the minimum average completion time is used as the optimization objective. The optimized scheduling method has the advantages that the expression of the production and assembly process of the automobile air conditioner air outlet is clear and accurate, and high-quality regions found through global searching are subjected to intensive local searching, so that better balance is achieved between the global searching and the local searching.

The invention relates to a data recording and U disk exporting method of a digital flat regulation system. Locomotive equipment packs data of shunting operation and then writes into a permanent memory plug-in Flash memory chip to store during communication according to the agreement on recording; the packed data content comprises real-time time, type, a frequency group, direction and an ID (Identifier); the reliability and the accuracy are guaranteed through data check; during operation of an application program of the locomotive equipment, the locomotive equipment detects whether a U disk is accessed constantly, and reads a configuration file in the U disk and determines to dump all or a part of recorded content if detecting that the U disk is accessed; the data which are transferred out by the locomotive equipment are written into the U disk in the form of a file. The method has the beneficial effects that both the communication and the user operation between the locomotive equipment and a handset can be recorded, the recorded effective information is rich, a working process is convenient to reduce, a part of or all the data can be selectively exported according to the configuration file when the U disk exports the data, and the method is flexible in dumping, convenient, quick and easy to operate.

The invention relates to an optimized scheduling method for the LCTV (Liquid Crystal Television) production and assembly process, belonging to the technical field of intelligent optimized scheduling of production lines in workshop. An optimization target is optimized by determining a scheduling model and the optimization target in the LCTV production and assembly process and utilizing the optimized scheduling method with improved estimation of distribution algorithm; the scheduling model is established according to the processing time and final assembly completion time of LCTV components on machines; and the optimization target is to minimize the average completion time. The optimized scheduling method enables clear and accurate expression of the LCTV production and assembly process, and enhances the global search capability of algorithms.

The invention provides a solar radio interference filtering method, a readable storage medium and electronic equipment. The method comprises the following steps: collecting intensity data in a set time period before and after a solar burst event, and screening out frequency channels where eligible radio signals are located according to radio flux value data of all frequency channels at a certain moment in a non-burst time period; preprocessing the acquired eligible radio station signal data, and establishing a data set; establishing a recurrent neural network, training the recurrent neural network by using the preprocessed radio station signal data, and predicting the signal value of a radio station in a solar burst area by using the trained recurrent neural network; and according to the linear additive property of the signal, subtracting the predicted radio station value from the original radio flux value of the burst area at the corresponding moment to obtain a value of a clean puresolar burst event. Radio station interference signals can be predicted more accurately, and more solar burst information can be reserved. The final solar burst observation effect of the method is obviously superior to that of a common image filtering method.

A method for relay - tracking light image of auxiliary video camera in virtual studio system includes setting auxiliary video camera on rotary table, tripod, swinging arm or other accessory of foreground video camera , adding light image with different color or different lightness above or around foreground video camera to let image shot by auxiliary video camera have inconsistence color or brightness at each pixel on image , obtaining movement parameter of auxiliary video camera by calculating shot image with tracking server and then obtaining foreground video camera movement parameter according to auxiliary video camera movement parameter and location relation of two video cameras .

The invention discloses a binocular vision system-based image defogging method. The method comprises the steps of calibrating the lens of a binocular camera, shooting and acquiring two original images by the binocular camera, acquiring a disparity image according to the two original images, and obtaining a defogged image through subjecting the two original images to bilateral filtering treatment. The disparity image is adopted as a limiting condition for the bilateral filtering treatment. According to the invention, the effective information of left image and right images is combined. Compared with the conventional defogging means based on a single image, resulted images are clearer and more abundant in effective information.

The invention discloses a simulator system, a live broadcast method and device, and a storage medium, and relates to the technical field of live broadcast of offline events. The system comprises a server and at least one observer terminal; the server is used for reading card wall information from automatic card stacking equipment; generating n packs of hand card information according to acquired starting point information and the card wall information, wherein the hand card information is arrangement information of mahjong tiles distributed to player accounts, and n is greater than or equal to1; the server is further used for sending the n packs of hand card information to the observer terminal; and the observer terminal is used for outputting a live broadcast picture to a live broadcastsystem according to the n packs of hand card information. According to the simulator system provided by the invention, the card wall information sent by a Mahjong machine is received by the server, and then the hand card information corresponding to each player account is generated; the hand card information corresponding to each player account can be displayed in the live broadcast picture, therefore, more effective information is carried in the live broadcast picture, and audiences can intuitively know card face information corresponding to each player account from the live broadcast picture.

The invention provides a method and system for establishing three-dimensional images based on multi-aperture imaging and multi-polarization imaging. The method comprises the steps that a broad-spectrum light source generates a broad-band broad-spectrum light, a spectral imaging device acquires a plurality of narrow-band spectral images formed by the broad-spectrum light reflected by a surgical region at multiple angles, a multi-aperture stereo vision algorithm is utilized to construct primary three-dimensional reconstruction images of the surgical region, a multi-polarization imaging device collects a plurality of narrow-band polarization images formed by a polarization light reflected by the surgical region to obtain body fluid coverage images of human body organs in the surgical region,and a processing system obtains the three-dimensional reconstruction images of the surgical region according to the primary three-dimensional reconstruction images and the body fluid coverage images of the human body organs and outputs to a display device.

The embodiment of the invention discloses a method, a device and a client for processing the information recommendation. The method comprises the following steps of determining an acquired search termto be a broad search term, and expanding the broad search term to be at least one search sentence based on a preset information corpus; intensively acquiring the recommending information matched withthe search sentence from a selected information set; and displaying at least one piece of recommended information. By means of the method or device, the recommended information matched with the search sentence can be recommended to users. The recommendation information can enrich the space selected by users. Meanwhile, the further search and guide service can be provided for users.

The embodiment of the invention provides a human body key point recognition method and a device, and electronic equipment, and is applied to the field of image processing. The method comprises the steps of obtaining a target video frame of a to-be-identified human body key point in a video; performing human body image extraction processing on the target video frame to obtain a to-be-utilized target human body image; performing key point information identification on the target human body image by using a pre-trained neural network model and taking predetermined human body image information ofa video frame before the target video frame as auxiliary information to obtain key point information of each human body key point in the target human body image; and determining coordinates of each human body key point in the target video frame based on the key point information of each human body key point in the target human body graph. Through the method, the purpose of improving the accuracy of human body key point recognition can be achieved.

The invention discloses a weak fault feature extraction method based on selective integration and improved local feature decomposition. The method specifically comprises the steps that collecting vibration signals and carrying out normalization processing; adopting a boundary continuation method based on mirror image continuation symmetric points to carry out continuation on two ends of the normalized signal; decomposing the extended signal into a plurality of ISC components by adopting an SEILCD method; estimating the energy of each ISC component at the confidence of 95% and 99%; judging whether each ISC component belongs to noise or not, if yes, denoising the ISC by adopting a minmax threshold denoising method, and otherwise, denoising the ISC by adopting an AWOGS method; and normalizingand orthogonalizing the denoised ISC and carrying out time-frequency analysis. According to the method, the LCD interpolation mean value curve and the adaptive signal denoising can be adaptively selected, the complex vibration signal processing capability is improved, the fault characteristics are effectively enhanced, and the accuracy and interpretability of fault diagnosis are further improved.

The invention provides a method is for recognizing rain-wind induced vibration waterline of a stayed cable based on computer vision. The method is characterized in that non-contact measurement is realized for evolution of the form of the waterline through an image recognition algorithm. With the method, a measurement region is arranged on the surface of the stayed cable, a coordinate grid system is drawn, the movement pictures of the waterline in the measurement region are shot through a high-speed CCD camera, and first, according to color difference contrasting, the water line is recognized from an original picture; then through grayscale correction and a gray threshold method, a binary image of the coordinate grid system is obtained, and all coordinate lines are expressed through equations based on Hough conversion and least square fit; finally, the distribution position of the waterline on the surface of the cable is determined through the coordinate grid system. With the method, the movement pictures of the waterline shot constantly are recognized, and then the evolution process of the form of the waterline can be reconstructed. The method has the advantages of being wide in measurement range, obtaining much waterline information and being high in precision, and a device is simple, convenient and rapid to operate and easy to transplant to application of actual bridge engineering.

The invention discloses a heterogeneous graph-based virtual article time sequence recommendation method and device, a medium and equipment. The method comprises the following steps: firstly, using GCN on a heterogeneous graph comprising three nodes of users, virtual articles and article attributes to obtain user representations and article representations; and then, respectively extracting a social sub-graph and an article association sub-graph from the heterogeneous graph, respectively obtaining user representation and article representation through GCN, and fusing the user representation and the article representation with user representation and article representation obtained in the heterogeneous graph to obtain final user representation and article representation. Inputting the obtained article representations into a sequential network according to a purchase time sequence to obtain candidate virtual articles; and finally, performing dot product on the user representation and the candidate virtual article representation to obtain a recommendation probability of each candidate article. According to the virtual article recommendation method, the relationship between the user and the virtual article in the spatial dimension and the relationship of purchase of the virtual article in the time dimension can be fully considered in the virtual article recommendation task, so that more accurate virtual article recommendation is realized.

The invention discloses a shuffled frog leaping solving method for a multi-target backpack problem. The method comprises the steps: (1) reading problem information, which comprises the value and weight information of each goods of each backpack and the weight limitation information of each backpack; (2) initializing algorithm parameters; (3) calculating target values of all individuals in the population, determining a non-dominated solution set and putting the non-dominated solution set into an external memory; (4) entering a quick convergence stage, dividing the population into subgroups by using an S-type grouping mode according to a quick non-dominated sorting result, performing local search based on a discrete jump rule and greedy generation on each subgroup, shuffling each subgroup, updating an external memory, judging whether the target evaluation frequency meets a quick convergence stage termination condition; and if not, continuing iteration; and if yes, entering the next stage; (5) entering an exploration expansion stage; and (6) entering an extreme value mining stage. The method has the advantages of high search speed, high search capability and high profit of the planned backpack.

The invention discloses a new method for online detecting crude tobacco chemical components through an AOTF near-infrared spectroscopy, and mainly relates to the technical field of the analytical chemical instrument. The method comprises the following steps: step one, mounting an online window module on an outer frame of a conveyor belt; step two, enabling crude tobacco samples to fall to the window module from the conveyor belt, and sliding to a subsequent conveyor belt through a quartz window; step three, fixing the AOTF near-infrared spectroscopy behind the window module so that a lens of the AOTF near-infrared spectroscopy is aimed at a center of circle of the quartz window and the optical distance remains stationary; and step four, when online work is carried out, all crude tobacco samples pass through the window module, wherein the AOTF near-infrared spectroscope collects the data of the crude tobacco samples through the quartz window. By detecting multi-group of data, the obtained near-infrared spectrum information is more comprehensive, the effective information is more plentiful, and the spectral analysis difficulty is reduced.