144results about How to "Convenient labeling" patented technology

Antifungal polypeptides, isolated from Medicago plants, are shown to control fungal damage to plants. DNA encoding the polypeptides was cloned into vectors for transformation of plant-colonizing microorganisms or plants, thereby providing a method of inhibiting fungal growth on plants. The polypeptides can be formulated into compositions useful in controlling undesired fungi.

The invention provides a medical field-oriented named entity identifying method based on deep learning and relates to a named entity identifying method. The invention mainly aims at solving the problems that semantic information is not considered in a CRF model and a large amount of unmeaning labelling results can appear in labelling results under the condition that training corpus is extremely scarce. The method provided by the invention is realized by the following steps of: firstly, obtaining a vocabulary voc supplementing medical field corpus and a term vector vec corresponding to the vocabulary voc; secondly, carrying out short and long term memory (LSTM) unit network training by utilizing training corpus in labelled corpus; and thirdly, carrying out path finding of labelling results according to an updated neural network parameter theta in the step two, so that the labelling results with labelled corpus; and evaluating labelling result of test corpus in the labelled corpus by utilizing a named entity identification and evaluation criteria value F. The method provided by the invention is applied to the named entity identification field.

The invention belongs to the technical field of image marking and particularly provides an interactive method for processing image marking tasks based on a crowdsourcing platform. Firstly, an on-line crowdsourcing work mode is established to make taste demand parties and crowdsourcing members complete marking tasks on the platform; secondly, image marking tasks are used as main research and entry points to design and achieve the interactive method. The interactive method specifically comprises the steps that an image marking task classifying system is established, and the crowdsourcing platform is established; the design criteria and design process of the interactive method are established; the specific operating steps of the interactive method for processing image marking tasks based on the crowdsourcing platform are designed. By adopting the method, the marking efficiency and user experience of crowdsourcing workers are improved, accordingly image data training sets are more quickly provided for the scientific research fields of machine learning and the like, image data marking work is completed by utilizing a network crowdsourcing work mode, and new employment and income increasing opportunities are provided for vulnerable groups such as the disabled.

The invention relates to an electronic map, in particular to an electronic map provided with roadside panoramic view picture strips, a method for manufacturing the same, and a method for marking interested places. The invention is dependent on road information of the prior electronic map and the correlation between the road information and the panoramic view picture strips for the overlay of the panoramic view picture strips showing both roadsides on roads displayed on the electronic map. Each panoramic view picture strip is a narrow picture which records all the scenes on a section of road, and users can comprehensively, continuously and intuitively know the conditions on both sides of a street through the panoramic view picture strip and determine the actual position of a place in the panoramic view picture strip on the electronic map.

The invention discloses a method and device for marking electronic documents, and relates to the field of electronic document processing in the computer application technology. The method of the invention comprises: presetting an electronic document, an marking shortcut icon, a note bar and an marking edit box, displaying a first document page on a screen and loading the marking shortcut icon, detecting the activation of the marking shortcut icon, displaying the note bar, editing the electronic document page by invoking a document-editing engine, and acquiring a second document page, detecting an operation action executed in the note bar and displaying the marking edit box, and completing the marking of the document content and saving the marked content in a preset directory. The device of the invention arranges the marking, remarks and note by setting the note bar and displays and hides the note bar by zooming the electronic document page, preventing reading trouble caused by directly marking on the reading interface of the electronic document, facilitating the marking and the recording of the reading note and improving user experience.

The invention discloses a geological map database establishing device based on a geological database. The geological map database establishing device comprises a grid map vectorization module, an automatic attribute content acquisition and improvement module, a vector data mapping expression and map face finishing module and a quality inspection working module. The core characteristics of the process technology are as follows: a geological database management model, attribute recording and automatic acquisition, object-oriented vectorization, geological lettering and automatic code generation and updating, symbol management and mapping expression and quality inspection software. The geological map database establishing device disclosed by the invention has the advantages that the technical problems of low database establishing efficiency and difficult application of the geological mineral map are solved, the data quality of the geological map is improved, and the storage space of result data is less than the original storage space; the problem of disconnection between data acquisition of the geological mineral map at the earlier period and management of a relational database at the later period is solved, so that the database of the geological mineral map has good succession and integrity; and the current situation of low-efficiency management of the current geological special map data set by the traditional document type database is broken through, high-efficiency management of the relational database is realized, and the current situation that the geological special map data set is large so as to be difficult to manage is changed.

The invention discloses a Chinese lexical analysis method. The Chinese lexical analysis method comprises the following steps of (1) obtaining a characteristic function and a weight from a given training corpus; (2) segmenting an input Chinese text: segmenting the input Chinese text into multiple statements, wherein one statement is a word sequence; (3) calculating a conditional probability of all possible lexical information tagging sequences of the word sequences corresponding to the input Chinese text; (4) determining a final lexical information tagging sequence of the word sequences corresponding to the input Chinese text; (5) carrying out Chinese word segmenting, Chinese POS (Part-of-Speech) tagging and Chinese named entity recognizing, and thus obtaining a final Chinese lexical analysis result. According to the Chinese lexical analysis method disclosed by the invention, three subtasks of Chinese lexical analysis are realized by being unified in a word sequence tagging framework, the defects that error is upwards transmitted, amplified and accumulated, and multiple classes of information are difficult to integrate and utilize are overcome, the calculation is simple, and the operation amount is small; a dictionary is not needed at all, and unknown words can also be better segmented and tagged.

The invention provides a wireless interaction electronic whiteboard conference system. The wireless interaction electronic whiteboard conference system comprises an electronic whiteboard and user side communication equipment, wherein a point-to-point wireless network connection is realized through the electronic whiteboard and the user side communication equipment based on a p2p protocol; the electronic whiteboard is compatible with at least two wireless transmission protocol standards; the user side communication equipment automatically searches for and is connected with the electronic whiteboard according to the p2p protocol; the user side communication equipment sends a message to the electronic whiteboard after the connection; and the electronic whiteboard determines a protocol standard supported by the user side communication equipment according to a content format of the message, and calls a protocol standard which is matched with the user side communication equipment to realize wireless connection access. Through adoption of the wireless interaction electronic whiteboard conference system, real-time content sharing among a plurality of pieces of equipment can be realized in a projection-video conference system anytime and anywhere, and display content of equipment of corresponding different types can be received and directly displayed on the electronic whiteboard, so that real-time annotation and explanation can be realized, and sharing, communication and discussion of a conference become more convenient and effective.

The invention relates to a multifunctional pipeline detection device which comprises a detection rod, a detector, a driving mechanism, a left positioning frame and a right positioning frame. One end of the detection rod is rotatably connected with the left positioning frame; the other end of the detection rod axially penetrates through an inner cavity of a pipeline to be detected so as to be rotatably connected with the right positioning frame; the left positioning frame or the right positioning frame is provided with the driving mechanism; the detector is arranged in the middle of the detection rod; a detecting instrument capable of detecting the flatness of the inner wall of the pipeline to be detected, the precision of a welding seam and the concentricity of the welded pipeline is arranged on the detector; the detecting instrument is connected with detection equipment located outside the pipeline to be detected through signals; a left adjusting device capable of moving up and down to adjust the height of the left end of the detection rod is arranged on the left positioning frame; and a right adjusting device capable of moving up and down to adjust the height of the right end ofthe detection rod is arranged on the right positioning frame. The multifunctional pipeline detection device provided by the invention has the advantages that the detection function is diversified, thedevice can be applied to detection of pipelines with different pipe diameters, and installation and detection are conducted conveniently and efficiently.

The invention relates to a construction method and application of a lightweight gesture detection convolutional neural network model, and the method comprises the steps: constructing a lightweight gesture detection convolutional neural network framework based on a SquezeNet convolutional neural network framework and an SSD multi-target detection convolutional neural network framework; Acquiring agesture picture and a background picture, and performing image data enhancement and picture synthesis processing on the gesture picture based on the background picture to obtain a gesture data set; And based on the public data set and the gesture data set, training a lightweight gesture detection convolutional neural network framework to obtain a lightweight gesture detection convolutional neuralnetwork model. According to the invention, a small amount of gesture data is expanded into the gesture data set containing a large amount of picture data at a high speed; The technical problem that alarge amount of high-quality gesture picture data is difficult to obtain is solved, in addition, by combining the SquezeNet convolutional neural network architecture and the SSD multi-target detectionconvolutional neural network architecture, the constructed lightweight gesture detection convolutional neural network model occupies few computing resources, and can be applied to various detection platforms.

The invention particularly relates to a hybrid cell type identification method based on fine granularity identification, comprising the following steps: a fine granularity identification convolutionalneural network model and a cell image database are established in advance; the cell image database comprises a hybrid cell image; the hybrid cell image is an image including a plurality of types of cells; the hybrid cell type identification method comprises the following steps of: 1, collecting mixed cell images; 2, inputting the mixed cell image into a fine-grained recognition convolution neuralnetwork model to obtain a cell type thermogram; 3, performing threshold that mixed cell image to obtain a binary image of the cell region; 4, combined with binary image of cell region and thermogramof cell species, the cell species identification results being obtained. The invention accurately identifies cell species according to the specificity of cell morphological characteristics, and avoidsthe shortcomings of the traditional cell species identification method that takes a long time and the process is tedious. The model can learn the morphological characteristics of fine-grained cells and identify cell types through texture information, which has high recognition accuracy and robustness.

The invention discloses a big data O2O drawing reviewing cloud platform management system used for construction project construction drawing reviewing. A construction organization drawing paper upload module comprises a network server and a database server assembly. A construction unit data terminal is connected with the input end of the network server. The data output end of the network server is connected with the database server assembly. A firewall is connected on the port of the database server assembly through a switch I. The firewall is divided into three paths to be connected with a reviewing organization drawing reviewing management terminal, a storage unit and a CAD electronic signature authentication system. The whole course of paperless drawing reviewing of construction drawing reviewing can be realized, the drawing reviewing efficiency and the installation performance can be enhanced, and the cost can be greatly saved and the project period can be shortened.

A computerized method of the invention includes software having instructions loaded on a computer system including a database populated with item information associated with owner, leasee and / or lien holder information. The CPU executes the instructions for, in a first step, registering user, in a second step, associating items and, in a third step, making registered item information available for updating and interrogation by users with the requisite permissions.

The invention provides a text recognition method and device, electronic equipment and a storage medium. The text recognition method comprises the steps of acquiring a text set of multiple texts; extracting theme keywords of the text in the text set, and obtaining actual theme keywords extracted from at least one text in the text set; determining first distribution of the theme keywords in each text in the text set and second distribution of the practical theme keywords in each text in the text set; inputting the texts in the text set carrying the first distribution and the second distributioninto a classifier for recognition, and obtaining key sentences and non-key sentences of the texts in the text set. Through the text recognition method, the key sentences and the non-key sentences of the text can be rapidly and accurately obtained according to the technical scheme. The non-key sentences of the text are cleaned, the key sentences of the text are conveniently marked. Construction efficiency of a knowledge graph is improved. The key sentences of the text are reserved, so that a user can rapidly know the main content of the text when looking up the text.

The invention discloses a three-dimensional point cloud labeling method, a device, equipment and a storage medium, and belongs to the technical field of artificial intelligence. According to the quickthree-dimensional point cloud labeling method provided by the embodiment of the invention, the three-dimensional point clouds are displayed in the three-dimensional scene, and the three-dimensional point clouds are selected and labeled by utilizing the detected contour selection operation, so that a labeling person draws the contours of the objects in the three-dimensional scene, and the three-dimensional scene can automatically select the three-dimensional point clouds needing to be labeled. Thus, the tedious process that a labeler triggers selection operation on each point in the point cloud one by one is omitted, so that the labor cost and time expenditure for labeling the three-dimensional point cloud are saved, and the labeling efficiency of the three-dimensional point cloud is improved. Moreover, since the three-dimensional point clouds are displayed in the same three-dimensional scene, the spatial position relationship among different points in the three-dimensional point clouds can be intuitively reflected by utilizing the three-dimensional space provided by the three-dimensional scene, so that a labeler can label conveniently.

The invention discloses an MIL-based medical image lesion point accurate marking method. The MIL-based medical image lesion point accurate marking method comprises the following steps: a step 1: acquiring a medical image data set which is divided into a positive sample set and a negative sample set; a step 2: performing initialization of a classification model; a step 3: acquiring S instances foreach sample in the positive sample set, and inputting each instance into the classifier model; recording an instance with the maximal lesion point probability value, and then adding the instance to adata set D; a step 4 : acquiring S instances for each sample in the negative sample set, inputting each instance into the classifier model, recording an instance which is less likely to have a lesionpoint, and adding the instance into the data set D; a step 5: performing iterative training in the neural network classifier model to obtain a training model; and a step 6: detecting and marking new samples according to the classification model. The method can accurately mark the lesion point samples in large quantities, is fast in speed and low in cost, and is extremely efficient.

The invention provides a drawing method for showing a three-dimensional figure of underground pipelines by using a plane figure, which can be realized by a 2D figure processor. A road plane figure, aroad section cutting plane figure, a vertical pipe position figure, a ground datum line and a pipeline vertical view are integrated according to an underground pipeline figure drawn according to the invention so that the three-dimensional relationship between the underground pipelines is clear at a glance and has strong visibility to be convenient for error detection. The invention can accuratelyand simply label the horizontal and vertical sizes of the pipelines, the pipelines with same distances on the figure have same actual distances, and the figure can be used as an engineering construction figure so that the construction precision and the construction speed are greatly improved.

The invention is a method for public resource navigation, based on the computer system for public traffic resources databank, it designs data structure storage and searching data joint, the storing mode of data structure for point in databank is, the point data in the databank is mainly stored in two data tables, namely the point basic attributes table and information table of relative station, the attributes stored in the point basic information table has: point name, searching key word, point sketch map, type and other basic attributes; the joint is bonded with point data, and arranges with ordering joint, the ordering joint is made up of three parts: the number of this joint, the weight of the distance between the two joints from this joint to the next joint and the next joint; acquires all the relative information from the two data tables, and they are displayed on the web.

The invention discloses an effective method and system for context information transmission in intelligent robot chatting. The method can help the chat robot to realize accurate multi-round conversation. Context information stored in the system is updated in each round of chatting in real time by simulating a human dialogue process. Under the appropriate condition, the current round input of chatting combined with the current preceding text information, an instruction is generated, namely a function and parameters which can be executed by software are generated, and therefore the system synchronously updates the preceding text information which can be used by the chatting below while generating the current round reply. According to the method, a certain amount of training data is marked, namely part of training corpora is changed, a deep neural network model is indicated in an explicit mode, and when a user asks for questions, a robot replies and when there is the preceding text information, how to answer and reserve the preceding text information is achieved. The invention provides a plurality of practical data annotation schemes and a method for annotating corpora by using the data annotation schemes. Meanwhile, some sample application scenarios and related technical details are also provided.

The invention provides a medical field oriented named entity recognition method based on deep learning. The method comprises the steps of S1, carrying out long short-term memory (LSTM) training through utilization of training corpuses in labeled corpuses in the medical field; S2, carrying out labeling result path searching according to neural network parameters theta updated in the S1, thereby obtaining labeling results of the labeled corpuses, and evaluating labeling results of test corpuses in the labeled corpuses through utilization of a named entity recognition evaluative criteria F value;and S3, within a training process in the S1, carrying out the long short-term memory (LSTM) training through utilization of the labeled corpuses in the journalism field, carrying out medical field model training according to a trained model and the labeled corpuses in the medical field, and evaluating the labeling results of the test corpuses in the labeled corpuses through utilization of the named entity recognition evaluative criteria F value. The method is applied to the field of named entity recognition.

The invention discloses a robot autonomous navigation control method and system based on deep learning. The method comprises the following steps: setting a starting point and an end point of a robot in an environment map, and calculating the optimal path that the robot can drive; adopting a positioning algorithm for determining the position of the robot at the moment in the driving process, stopping movement when arriving at the end point, and otherwise continuing navigation; acquiring an environment information image in front of the robot by using a camera, inputting the environment information image into the trained convolutional neural network model, judging whether an obstacle with an unknown environment map influences the normal movement of the robot or not, if not, continuing navigation according to the optimal route, and if yes, generating a corresponding control instruction by using the network model, enabling the robot to avoid an unknown obstacle, and at the same time, replanning the optimal route, determining the position at the moment, and judging whether an end point is reached or not is judged. The system is based on a deep learning technology, can avoid various obstacles on a route planned by a global path, and is high in applicability.

The invention relates to a drawing processing method and device based on a hull structure three-dimensional model and a storage medium. The method comprises the steps: recognizing and displaying large-assembly-base-plane jointed board parts, marking design information, and generating large-assembly-base-plane jointed board subgraphs; identifying and displaying large-assembly longitudinal bone parts, marking design information and generating large-assembly longitudinal bone sub-graphs; identifying medium-assembly parts, displaying the medium-assembly parts step by step according to the assemblysequence, labeling design information for the medium-assembly parts corresponding to each step, and generating corresponding middle-assembly sub-graphs; identifying small-assembly parts, displaying the small-assembly parts step by step according to the assembly sequence, marking design information for the small-assembly parts corresponding to each step, and generating corresponding small-assemblysub-graphs; and conducting identifying to obtain a part which is not drawn, and labeling design information to generate a residual sub-graph. Compared with the prior art, design information is displayed and marked in batches according to the assembling sequence, and meanwhile assembling personnel can be clearly guided to assemble parts in sequence.

The invention discloses a sow obstetric table which comprises a base plate (1) and supporting feet (2) arranged on the base plate (1). Two main arch frames (3) dividing the obstetric table into sow chambers are arranged on the base plate (1), piglet chambers defined by fences (4) and the main arch frames (3) are arranged on the base plate (1), front doors (5) are arranged at the front ends of the main arch frames (3), and rear doors (6) are arranged at the rear ends of the main arch frames (3). The sow obstetric table is characterized in that buffer rods (7) are arranged on the main arch frames (3), and the distance between the two main arch frames (3) is 50-80cm. The sow obstetric table is simple in structure and low in cost, the speed that sows lie down can be reduced through the buffer rods arranged on the main arch frames so that the situation that piglets are crushed down to be hurt and even die due to the fact that the sows lie down too forcefully can be prevented, and therefore the sow obstetric table is suitable for popularization and use.

The embodiment of the invention discloses an audio file processing method, and the audio file processing method comprises the following steps: obtaining an audio set which includes a plurality of audio files, the audio set being divided according to audio attributes; segmenting each of the audio files into M audio frames, wherein M is a positive integer greater than or equal to 2; extracting a plurality of feature combinations of each of the audio frames, wherein each of the feature combinations includes a first energy value corresponding to a frequency spectrum brightness, a second energy value corresponding to a first frequency spectrum roll-off, and a third energy value corresponding to a second frequency spectrum roll-off; inputting the plurality of feature combinations of each of theaudio frames into a preset model to obtain a ranking value of each of the audio files; and determining a target audio file from the audio set according to the ranking value of each of the audio files.For a group of audio files with the same content and different tone quality, the tone quality of the audio files can be identified accurately and rapidly, which is beneficial to the optimization of amusic library.

The invention discloses a touch blackboard capable of being used for writing. The touch blackboard mainly comprises a piece of blackboard glass and intelligent touch equipment, wherein the blackboard glass is used for writing and has good light transmission. The intelligent touch equipment comprises a touch display, a mainboard module, a power module and a calculation display unit and a supporting shell of another module. The intelligent interactive blackboard integrates the advantage of an ordinary blackboard that writing is convenient and the advantages of an intelligent interactive all-in-one machine, so that writing and annotating are more convenient, faster and more freely for children and various exchange activities in work, writing with chalk can be achieved, and multimedia presentation can also be conducted; and the touch blackboard is easy to move, and the randomness of application scenes is improved.

The invention discloses a video marking method and device, and a video conference system. The method comprises the steps of obtaining first video data sent by a terminal device which accesses a video conference; forming second video data containing marking information according to the first video data; and sending the second video data to a remote conference system which accesses the video conference through the video conference, thereby sharing the second video data. According to the technical scheme provided by the embodiment of the invention, the first video data and the marking information are combined to form the second video data, the second video data is displayed on a display interface, so conference participants can mark on the display interface conveniently, and the efficiency of the video conference is improved.

The invention discloses an audio and video synchronized driving method used for online learning and relates to computer online education. The method comprises the first step of timing triggering of audio and video, the second step of checking of a synchronization time point, the third step of mapping and triggering of the synchronization time point and a teaching material, the fourth step of mapping and triggering of the synchronization time point and a note, the fifth step of mapping and triggering of the synchronization time point and a sign, the sixth step of mapping and triggering of the synchronization time point and an outline, and the seventh step of synchronization of a non-audio-or-video entity. The scene of traditional course teaching is reproduced, so that the learning process is immersive; in addition, after the course teaching material is separated from the audio and video, a learner can conveniently learn the note and mark key points / difficulties / doubtful points / and the like, and the note and the sign are also synchronously linked with the audio and video.

The invention provides detachable interval-adjustable parallel bars for physical education. The parallel bars comprise bottom supporting rods, lifting adjusting drums and a scaling ladder cross bar, alifting rotating bearing is fixed on the top side of each bottom supporting rod through a bolt, each lifting adjusting drum is fixedly arranged on the top side of the corresponding lifting rotating bearing through a bolt, and a threaded structure is arranged on the inner side of each lifting adjusting drum; a lifting supporting rod is embedded on the inner side of each lifting adjusting drum through a thread, and an outer-wall threaded structure of each lifting supporting rod is matched with the threaded structure arranged on the inner side of the corresponding lifting adjusting drum. Pedalsare symmetrically and equidistantly welded and mounted on the outer wall of the bottom supporting rod, the structural design brings convenience to part of people with low body height or beginners to climb the parallel bars by stepping on the pedals, so that convenience in use of the parallel bars is improved effectively.