208results about How to "Implement automatic selection" patented technology

The invention discloses a laboratory-sheet identification method based on image processing. According to the method, a set of algorithms which can accurately divide each area of a laboratory sheet and carry out effective cleaning are designed through investigation and analysis on a laboratory-sheet structure, how to process a laboratory-sheet photograph, which is shot by a mobile phone, step by step to finally obtain a clear image is standardized and subdivided, and a mature open-source OCR engine is used for identification; in each stage of a laboratory-sheet image processing process, the method makes thorough consideration, optimizes the performance, and improves the efficiency of image processing; and after identification, a laboratory-sheet item lexicon established by utilizing a laboratory test item information database by the method realizes automatic selection for identification engine modes and intelligent error correction for an identification result, and improves the accuracy of the laboratory-sheet identification result.

The invention discloses a panoramic image fusion method based on a depth convolution neural network and depth information. The method comprises the steps of (S1) constructing a deep learning training data set, selecting overlap regions xe1 and xe2 of two fish eye images to be fused used for training and an ideal fusion area ye of a panoramic image formed after fusing the two fish eye images, and constructing a training set {xe1, xe2, ye} of the images to be fused and a panoramic image block pair, (S2) constructing a convolution neural network model, and (S3) obtaining a fusion area of a test data set based on a test data set and a trained depth convolution neural network model. According to the method, an image can be expressed more comprehensively and deeply, the image semantic representation in a plurality of abstract levels is realized, and the accuracy of image fusion is improved.

The invention provides a text classification method, a text classification device and a computer readable storage medium. The text classification method comprises the steps that text representation isconducted on a to-be-classified text to obtain a sentence set of the to-be-classified text, the sentence set is composed of word sets of all sentences in the to-be-classified text, and the word setsare composed of word vectors of words contained in corresponding sentences; based on a neural network, an attention mechanism and the word set, a feature vector of the sentence set is obtained; and the feature vectors of the sentence set is input into a text classification model to obtain a classification result of the to-be-classified text. According to the technical scheme, the text classification efficiency can be improved.

The invention discloses a batching monitoring and tracing method and system. The method has the following steps: data maintenance; order processing and recording; work order generation and processing; batching: providing work metering points, metering equipment initialization and automatic configuration, and automatic selection, work order taking and displaying, current raw material positioning and selection, raw material metering and automatic data recording, selecting metering point information or obtaining the metering point information through scanning bar codes, and taking work orders/ batching sheets from a database; and history query, statistic analysis and log report outputting, which is used for historical metering data retrieval and displaying, and analyzing consumption amount of each raw material, consumption amount of raw materials in a preset time period and actual consumption amount of each raw material in a set work order. The batching monitoring and tracing method and system help to maintain ingredient data safely and conveniently, prevent various possible non-safety factors appearing in the raw material batching process, and realize data traceability in the whole process from system operation to the end.

The embodiment of the invention discloses a desktop management method which includes the steps that information of a screen is obtained, wherein the information comprises the resolution ratio of the screen and the number of icons displayed on a desktop; according to the information, one layout style is selected from at least one preset layout styles used for managing the desktop, wherein the layout styles comprise at least one cell used for containing the icons; placing the icons displayed on the desktop in the cell of the selected layout style used for managing the desktop for display. Correspondingly, the invention further discloses a terminal device. By means of the method and the terminal device, the icons displayed on the desktop can be intelligently managed.

The invention relates to a visual-variable-based automatic classification and configuration method of map lettering, comprising the steps of: customizing a map lettering configuration rule base; inputting geographic data and carrying out mapping expression on the geographic data; calculating graphical symbol variable of single feature element; and matching the rules in the lettering configurationrule base, selecting a lettering configuration mode and finishing classification and configuration of the map lettering. In the visual-variable-based automatic classification and configuration method, the map lettering configuration is divided into seven basic configuration modes according to the substitutive characteristics and the configuration rule requirements of the feature elements needing to be lettered in the national basic scale topographic map, and simultaneously, the expansion and the combined use of the lettering configuration modes are supported; and the map lettering configuration model which is simple and is easy to realize is provided, so that automatic selection of the map lettering configuration modes in mapping of a computer map can be realized. In the visual-variable-based automatic classification and configuration method, the selection problem of lettering configuration modes of the example-level feature elements is solved, and the lettering automation level and the lettering quality in the national basic scale topographic map are improved.

The invention provides a selection method and equipment of site locations, and a selection method and equipment of grids. The method comprises the steps that a to-be-analyzed area in which the site locations are arranged is divided into a plurality of grids, signal sampling is carried out on sampling points in each grid, the grids which need the site locations to be arranged are confirmed according to collected signal index values, and the site locations needing to be arranged are arranged in the grids which need the site locations to be arranged. The selection method and the equipment of the site locations, and the selection method and the equipment of the grids can achieve automatic selection of the site locations.

The invention discloses a WIFI band selection method and device, a memory medium and electronic equipment. The method comprises the steps of detecting whether a WIFI connection establishment request of an opposite end with to-be-established WIFI connection is received or not; obtaining parameter information if it is detected that the WIFI connection establishment request is received; selecting a WIFI working band according to the parameter information, wherein the WIFI working band comprises a 2.4G band and a 5G band; and establishing WIFI connection with the opposite end with the to-be-established WIFI connection, based on the selected WIFI working band. The WIFI working band can be automatically selected according to the parameter information, the WIFI band is automatically selected, andthe WIFI band selection flexibility is improved.

The invention provides a turbulent boundary layer flow field velocity measurement method based on boundary tracing and belongs to the field of fluid computing. The method is used for acquiring velocity vector distribution of turbulent boundary layer fluid with hydrogen bubbles being tracing particles under a single-phase condition. The method comprises the steps that a hydrogen bubble image is acquired through a special experimental facility, the obtained experimental image is subjected to image input processing, processing through a histogram equalization algorithm, image feature extraction processing, FCM cluster partitioning processing, boundary recognition and tracking processing, local velocity distribution processing, velocity maximum value extraction processing, setting of an optimal detection window of a fast Fourier transformation cross-correlation algorithm, processing through the fast Fourier transformation cross-correlation algorithm, velocity vector distribution processingand other processing processes in sequence, and finally the velocity vector distribution is obtained. The method is simple, easy to implement, high in application value, high in operability and convenient to realize; and quantitative analysis is performed on a large-scale structure existing in a turbulent boundary layer, and the blank of quantitative research about a turbulent boundary layer quasi-order structure with the hydrogen bubbles being the tracing particles is filled up.

The invention provides an automatic and moderate orthographic projection correction method of a satellite remote sensing image. The method is formed by the organic combination of control point automatic match, control point automatic optimization, control point gross error automatic detection, correction model moderate solving and the like. The method solves the problem that the control points in the control point automatic selection are not uniformly distributed and the problems of detecting control point observed value gross error and improving model solving precision. As the method has the advantages of moderation, precision and high degree of automation, the method is suitable for the production of orthographic projection correction products of the satellite remote sensing image on a large scale.

The invention discloses an information collection method, a mobile terminal and a computer readable storage medium. The information collection method comprises the steps of preprocessing page information in a current display interface according to an information collection instruction when the information collection instruction triggered based on a displayed collection suspension control is monitored, thereby obtaining to-be-collected information; extracting keywords from the to-be-collected information, and according to a keyword quantity, determining a collection folder of the to-be-collected information; and storing the to-be-collected information in the collection folder, and uploading the to-be-collected information to a cloud end for performing synchronization. The collection of thepage information of the current display interface is realized through the collection suspension control, so that information collection in APPs is effectively realized; and meanwhile, the collected information is not a conventional webpage link but specific contents corresponding to the webpage link, so that the situation that the collected information cannot be obtained because the contents of the webpage link are deleted by a releaser is avoided.

The invention discloses a region growth ultrasound image automation segmentation method based on energy constraint. The method comprises the following steps: (1) preprocessing is performed on an original ultrasound image, (2) automatic selection of a seed point is performed on the ultrasound image after the preprocessing, and (3) the seed point obtained in the step (2) is used to be taken as a start point of region growth, constrained growth is performed under an energy function, the growth stops when a constraint condition is reached, and then a final segmentation result is obtained. The obtained segmentation result is accurate, the segmentation process needs no artificial participation, fully automatic ultrasound image segmentation is really achieved, and subsequent processing such as focal region characteristic extraction is facilitated.

The invention discloses an industrial data nonlinear cause and effect analysis method based on a sparse deep neural network. The method comprises the following steps of (1) collecting the process output signals of all control loops in an industrial process to be detected; (2) selecting one process output signal as an output variable and taking each order lag of all variables as an input variable to construct the sparse deep neural network; (3) through successively deleting the input variables, completing Granger causality testing one by one, and acquiring all the Granger causes of the output signal of the process; (4) repeating the steps (2) and (3), and acquiring a causal relationship among the output signals of all the process; and (5) integrating the causal relationship among the outputsignals of all the process, and positioning a fault source location and fault propagation path. In the invention, nonlinear causal analysis can be performed on the control loop signal of the industrial process, and fault source positioning and fault propagation path analysis are completed.

The invention discloses a method for clearing message items of a cell phone, which comprises the following steps: a multi-selection list of all candidate message items is established; a selection or a plurality of selections among the candidate message items in the multi-selection list are received; and all selected message items are deleted according to a deleting instruction. Meanwhile, the invention provides a device for clearing the message items of the cell phone, which comprises a multi-selection list establishing unit that reads the appointed message items stored in the cell phone according to a user instruction, thus forming a multi-selection list that contains all candidate message items; a selecting and receiving unit that receives selected messages of the candidate message items in the multi-selection list and marks the corresponding candidate message items according to the selected messages; a deleting unit that is used for receiving deleting instructions of a user and deleting the selected message items recorded in the multi-selection list according to the deleting instruction. The user can select a plurality of the message items at one time and then wholly delete a plurality of the selected message items by using the method and the device.

A semiconductor integrated circuit and its operating method are provided. The present circuit has first and second supply terminals capable of supplying first and second power supply voltages respectively, an input voltage selection circuit coupled to the first and second supply terminals, and first and second power supply switches. The input voltage selection circuit includes a power-on reset circuit, an input voltage detection circuit and a control circuit. When the supply of the first or second power supply voltage to one of both supply terminals is detected upon completion of a power on reset operation, one of both power supply switches and the other thereof are controlled to on and off respectively. When the supply of both power supply voltages to both supply terminals is detected, the one thereof and the other thereof are respectively controlled to on and off according to the preset order of precedence.

The invention provides a method and device for selecting an audio output channel and terminal equipment. According to the invention, by a set of algorithm, a target priority level is automatically determined, and by an audio output channel corresponding to the target priority level, an audio is output, so that automatic selection of a plurality of audio output channels is implemented. Various human-computer interaction interfaces and channel control algorithms do not need to be designed, and thus, a computation burden and operation time of a television terminal program can be reduced. Moreover, when a new audio output channel is added according to actual demands, only a priority level and a connection state of the newly added audio output channel need to be determined, thereby benefiting for improving flexibility in program design. According to the method, in a mode of setting various priority levels, various combination modes of the audio output channels can be provided; when the priority level and the connection state of each audio output channel are changed, the target priority level can be changed accordingly. According to the method for dynamically selecting the audio output channel, operability and flexibility of selecting the audio output channels can be improved.

The present invention provides a method and apparatus of generating browsing paths for data, a method for browsing data and a computer program product. According to one aspect of the invention, there is provided a method of generating browsing paths for data. Firstly, a plurality of candidate browsing paths based on a data model describing the data structure is generated; next for each of the plurality of candidate browsing paths, importance of the browsing path based on a portion of data corresponding to the browsing path in the data is calculated; and at least one of the plurality of candidate browsing paths based on the importance is selected.

The invention belongs to the technical field of serial communication, and particularly relates to an implementation method for achieving self-adaption of the baud rate. The method includes the following steps of setting the format of a serial communication data package, detecting the baud rate and automatically adjusting the baud rate. The method solves the technical problem that an existing technology can meet different design requirements for the baud rate unless external equipment is provided and cannot achieve self-adaption of the baud rate. The method has the advantages that when the method is utilized to carry out serial communication with other subsystems, labor hardware jumper arrangement or program selection is needless, and plug and play performance is achieved; the baud rate used at present can be automatically analyzed according to the serial communication data package, the baud rate of a system is automatically adjusted to be baud rate used at present, and thus the system is universally used for different baud rate systems.

The invention discloses a characteristic recommendation method and a characteristic recommendation device. The characteristic recommendation method comprises the following steps: according to an output textual characteristic estimation model, determining target values of textual characteristics in sample data, wherein the output textual characteristic estimation model is obtained according to the optimal combined characteristics selected from training data; according to the target values, sorting the textual characteristics in the sample data and according to a sequence of the target value from high to low, carrying out recommendation on the textual characteristics in the sample data. The characteristic recommendation method and the characteristic recommendation device can realize automatic selection of the effective combined characteristics, are time-saving and labor-saving, effectively solve the difficult problems of time waste and labor waste in the existing manual characteristic selecting process and can improve effectiveness of a recommendation system.