1170results about How to "Reduce manual workload" patented technology

The invention discloses a highly automated intelligent contract formal verification system and method. The method includes the following steps: step 001, converting an intelligent contract function requirement description document into an intelligent contract function requirement specification document described in a non-natural language, wherein the content of intelligent contract function requirement specification document includes target contract function specification description and security attribute description; step 002, creating a formal validation rule model library; step 003, automatically modeling the contract source code and / or bytecode by an automated modeling tool; step 004, parsing the abstract syntax tree generated in step 003, and allocating memory addresses for constantsand variables in the code; step 005, performing formal proof. The invention is adapted to program codes written in a plurality of high-level programming languages and also adapted to a plurality of formal languages, and simultaneously provides two automatic modeling modes of source code modeling and bytecode modeling, so that modeling can be carried out according to different modeling requirements of users, and the verification efficiency is further improved.

The invention provides a text classification method and device based on transfer learning, and the method comprises the steps: S1, employing an unlabeled text to train a BERT model, and obtaining a pre-trained word representation BERT model; S2, filtering links, forwarding symbols and user name contents in the to-be-classified text; S3, inputting the filtered text into the word representation BERTmodel trained in the step S1 to obtain a semantic file of the text; and S4, inputting the semantic file of the text into a convolutional neural network for processing to obtain a category label of the sentence in the semantic file. According to the method, transfer learning is used for text classification, and a BERT word representation model trained based on large-scale unlabeled corpora is provided. The word representation model has universality, does not depend on the specific text field, and can also be used for other tasks such as entity extraction and sentiment analysis.

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 relates to a method suitable for multi-view-angle automatic global registration of ground laser point cloud data. The method involves two key modules: a module for extracting semantic feature points and a module for feature matching. The method comprises: step 1, extracting the semantic feature points: obtaining the semantic feature points in a series of modes of data slicing, distance clustering, geometric element fitting and the like; step 2, matching the semantic feature points: matching the semantic feature points by constructing a triangular geometric constraint condition and a semantic constraint condition, and removing error matching in a geometric consistency clustering mode; and finally, constructing a weighted undirected graph by taking a reciprocal of a feature point number as a weight, and finally obtaining global registration parameters of all stations by taking a minimum spanning tree of the weighted undirected graph as a registration path, thereby realizing global optimal registration. According to the invention, the method suitable for multi-view-angle automatic global registration of the ground laser point cloud data is constructed; the method can effectively resist influences of noise, point density and coverage; and the method improves the laser scanning operation efficiency, thereby having very high practical values.

The invention discloses a video-monitoring-based transformer substation tour-inspection intelligent-scheduling and control system, which comprises a tour-inspection configuration management module, a tour-inspection task scheduling module, a tour-inspection intelligent-control module and a tour-inspection result display module, wherein the tour-inspection configuration management module is used for generating tour-inspection schemes, tour-inspection tasks associated with the tour-inspection schemes and tour-inspection control strategies by configuration data; the tour-inspection task scheduling module can be used for manually or automatically scheduling the tour-inspection tasks; the tour-inspection intelligent-control module is used for intelligently controlling a tour-inspection process; the tour-inspection result display module is used for displaying tour-inspection results in diversified forms of list, statistics, report forms and the like. According to the system, a complete set of flow scheme with intelligent scheduling and control functions is formed by video tour-inspection route setting, task scheduling, control linkage and the tour-inspection results, and report forms and reports can be automatically generated, so that the working efficiency, accuracy and timeliness are improved; the system is used for the video-monitoring remote intelligent tour-inspection of a transformer substation.

The invention relates to a building point cloud model and base map aligned method based on an outline, which belongs to the technical field of computer vision. The method comprises the steps of: performing structural analysis on the building point cloud model obtained by three-dimensional reconstruction, automatically detecting the posture of the current model, ultimately realizing normalization of coordinates of the point cloud model, and obtaining a point cloud overlooking outline drawing of a current building on the basis; performing outline analysis on a remote sensing image of an area in which a reconstructed building is positioned, and automatically detecting to obtain a base map outline; estimating structure turning points of the current building according to the outline of the reconstructed building, and then realizing space alignment of the point cloud model and a satellite base map by virtue of outline matching information, so as to obtain a mapping matrix from the point cloud model to the satellite base map and automatically realize the placement of the building point cloud model on the satellite base map. Compared with the prior art, the method has the advantages that the point cloud model and the base map can be accurately and automatically aligned, manual workload required by alignment is effectively reduced, and the alignment cost is reduced.

The invention discloses a method and a system for automatically generating an article based on a description text. The method comprises the following steps: receiving a description text of a to-be-generated article; determining a theme of the description text, and taking the theme as the theme of the to-be-generated article; constructing a thematic word graph according to a text corpus corresponding to the theme; and generating an article corresponding to the theme according to the constructed thematic word graph. The method and the system which are disclosed by the invention have the advantage that article generating efficiency and accuracy can be improved.

The invention discloses a method and device for updating an online map by using an unmanned vehicle. The method comprises one specific implementation method: a sensor mounted on the unmanned vehicle is used for scanning a road where the unmanned vehicle is located currently to acquire real-time road information; a map information acquisition request is sent to a backstage server of the online map, wherein the map information acquisition request includes position information of the unmanned vehicle; whether the real-time road information is consistent to map information returned by the backstage server is detected; in an inconsistent case, detected map distinguishing information is sent back. The implementation method can reduce the manual updating and maintaining workload required during map data change, and also greatly improves the efficiency of map data updating.

The embodiment of the invention discloses a panel defect analysis method, a device and a storage medium. The method comprises: obtaining a panel image corresponding to a panel to be analyzed; detecting defects in the panel image to obtain positions and types of defects; performing circuit region segmentation on the panel image according to a preset strategy to obtain a circuit segmented image including a plurality of circuit regions; according to the position of the defect, the circuit region where the defect being located is cut from the circuit segmentation image to obtain an image to be analyzed. A machine learn model is used to analyze that effect of the defect on the circuit in the panel based on the image to be analyzed and the type of the defect, and a defect analysis result is obtain. This scheme realizes the automatic detection and analysis of panel defects without the participation of workers, which not only reduces the manual workload, but also improves the accuracy and efficiency of panel defects analysis.

The application discloses a method and a device for marking point cloud data. According to a specific implementation, the method includes the following steps: using a laser radar and a sensor different from the laser radar to collect the data of the same scene to obtain point cloud data and sensor data; segmenting and tracking the point cloud data to obtain a point cloud segmenting and tracking result; identifying and tracking the features in the sensor data to obtain a feature identifying and tracking result; using the feature identifying and tracking result to correct the point cloud segmenting and tracking result to obtain the confidence of the point cloud segmenting and tracking result; and determining a point cloud segmenting and tracking result of which the confidence is greater thana confidence threshold as a point cloud marking result. The implementation reduces the manual workload of point cloud data marking and reduces the cost of marking.

The invention discloses a method and system for achieving automatic voice classification. The method includes the steps of receiving to-be-classified voice data, carrying out voice recognition on the to-be-classified voice data to obtain recognition texts, carrying out acoustic analysis on the to-be-classified voice data to obtain classification characteristics in acoustics, carrying out content analysis on the recognition texts to obtain classification characteristics in content, classifying the to-be-classified voice data by means of the classification characteristics in acoustics, the classification characteristics in content and a pre-built voice classification model to obtain the type of the to-be-classified voice data. By means of the method and system, workloads of workers can be reduced, and classification accuracy of the voice data is improved.

The invention discloses a method and device for creating a data warehouse table blood relationship graph and belongs to the field of computers. The method comprises the steps of analyzing each data warehouse operational statement which has access to a data warehouse to obtain the name of a data warehouse destination table to which each data warehouse operational statement has access, storing the corresponding relationship between the statement identification of each data warehouse operational statement and the name of the corresponding data warehouse destination table in a corresponding relationship table, obtaining the name of a data warehouse source table corresponding to each data warehouse destination table in the corresponding relationship table, and creating the data warehouse table blood relationship graph according to the name of each data warehouse destination table and the name of the data warehouse source table corresponding to each data warehouse destination table. The device comprises an analyzing module, a first storage module, a first obtaining module and a creating module. According to the method and device, a server can automatically create the data warehouse table blood relationship graph.

The invention discloses a super high-rise core tube horizontal direction and vertical direction synchronous construction top formwork system which comprises a truss platform system, a hanger enclosure system, a supporting system, a formwork system and a hydraulic control system. The formwork system is an aluminum alloy formwork system. The aluminum alloy formwork system comprises vertical wall formworks and horizontal formworks. Each vertical wall formwork comprises a plurality of aluminum alloy standard unit plates spliced transversely, and C-shaped aluminum alloy grooves located in the aluminum alloy standard unit plates. Each horizontal formwork is formed by splicing a plurality of aluminum alloy bulk slicing plates. The horizontal formworks on the different layers are formed by splicing the aluminum alloy bulk slicing plates different in quantity. The horizontal formworks are connected with the vertical wall formworks through the C-shaped aluminum alloy grooves. According to the super high-rise core tube horizontal direction and vertical direction synchronous construction top formwork system provided by the invention, synchronous construction of horizontal structures and vertical structures of a core tube is achieved.

The invention discloses a soft measurement method of a coal slurry flotation cleans ash based on date-driven, which establishes a hardware platform and a flotation cleans ash. Flotation feeding concentration, flow, flotation medicament dosage and tailings flashboard position are used as auxiliary variables, the flotation cleans ash is used as a master variable, the auxiliary variables are used as input and the flotation cleans ash is used as model output so as to carry out soft measurement modeling, and calibration and parameter correction are carried out to a model so as to estimate the ash content of the current flotation cleans in real-time. The method has simple application and low cost, can realize the soft measurement of the flotation cleans ash by only needing a small quantity of samples, thus improving the measurement timelessness, and being beneficial to realizing the optimized control of the flotation procedure.

A rice fine processing and cold polishing technique includes a vertical paddy entering silo-a primary screen-a permanent magnet drum-a vibration cleaning screen-a stone removing machine-a main scouring machine-a secondary scouring machine-a fine mesh screen-a gravity paddy slug separator-a first paddy pounder-a second paddy pounder-a third paddy pounder-a rice grading screen-an abrasive finishing machine-a color selector-a rice grading screen-a length grading machine-a vertical silo for finished product-an electric flow scale-a package. The present invention is characterized in that a vertical rice cooling silo used for cooling the temperature of the rice is arranged before the abrasive finishing machine. The present invention changes the defect of the traditional thermal polishing technique. The present invention adopts the mode of combining natural cooling and mechanical cooling, thus greatly improving the cooling effect, increasing the rice yield by 4 percent, greatly reducing the rate of cracked rice and subliming the rice quality not only from the appearance, but also from the inner quality.

The embodiment of the invention provides a generation method of a question and answer knowledge base, a training method and equipment of a neural network. The generation method of the question and answer knowledge base comprises the steps of splitting document data and obtaining multiple knowledge fragments; conducting mapping on each knowledge fragment through the neural network, obtaining questions corresponding to each knowledge fragment, and thus generating and obtaining the question and answer knowledge base. Through the generation method of the question and answer knowledge base, the training method and equipment of the neural network, the difficulty of question and answer knowledge acquirement can be effectively reduced, and the manual workload is greatly reduced.

The embodiment of the invention provides an anomaly detection method and device. The method comprises the following steps: acquiring the target time sequence data of a power grid system, and converting the target time sequence data to a first matrix; and inputting the first matrix to a pre-trained coding and decoding model to acquire a second matrix, calculating a first error of the second matrix with respect to the first matrix, and determining that the target time sequence data is the abnormal sequence data when the first error exceeds the preset error range. By adopting the anomaly detection method and device provided by the embodiment of the invention, the anomaly is detected by using the pre-trained coding and decoding model, and thus the manual workload in the anomaly detection of power systems can be reduced, and the efficiency of anomaly detection can be increased.

The invention provides a method for measuring track corrugation by utilizing axle box vibration and impact information. A vibration and impact information acquisition device contains a rotating speed sensor S arranged on a wheel set shaft of an operating vehicle, a vibration and impact detection sensor A1 and a vibration and impact detection sensor A2 which are arranged on an axle box bearing block at the two ends of a wheel set, an online monitoring device JKQ and a corrugation ground analysis system DMXT, wherein the rotating speed sensor S, the vibration and impact detection sensor A1 and the vibration and impact detection sensor A2 are connected with the online monitoring device JKQ, and detection, acquisition, diagnosis, analysis and decision of vehicular corrugation information of the operating vehicle are realized by virtue of the online monitoring device JKQ or by downloading data of the online monitoring device JKQ to the corrugation ground analysis system DMXT. The method for measuring the track corrugation by utilizing the axle box vibration and impact information has the advantages that the axle box vibration and impact information of the operating vehicle are acquired, based on a generalized resonance measurement principle, vehicular real-time track corrugation wave length and wave depth measurement and analysis or track corrugation wave length and wave depth measurement and analysis after downloading is completed are realized, and the manual workload is greatly reduced.

The invention belongs to the textile fabric anti-crease performance measuring instrument field, in particular relates to a textile fabric crease elasticity tester which is characterized in that: the tester also comprises a camera, a microcomputer and a display unit, wherein the camera, which is arranged above a clamping device and can slide, is used to shoot the image when a textile fabric sample restores from bending; the microcomputer is used to process the image shot by the camera and to measure and calculate the numeric value of the crease recovery angle of the textile fabric sample in the image; the display unit is used to display the numeric value calculated by the microcomputer, and the numeric value is equal to the numeric value of the practical crease recovery angle of the textile fabric sample. The tester shoots the image after the textile fabric sample restoring from bending through adopting the camera with the image processed by the microcomputer, and the crease recovery angle of the textile fabric sample is automatically calculated by program, thereby ensuring the accuracy of measurement; in addition, because the tester does not adopt manual measurement basis, manual workload is also reduced.

The invention discloses a full-automatic coagulate blood analytical instrument and a using method thereof. The instrument comprises a sample position module, a reagent position module, an incubation detection module, a gripper module, a cupping module, a needle movement module, a light source module, a pump station module, a consumable module, a power source module and a cuboid-shaped frame body composed of six faces of a front face, back face, left side face, right side face, top face and bottom face, wherein the center in the frame body is provided with a main cavity, the sample position module, the reagent position module, the incubation detection module, the gripper module and the needle movement module are all located in the main cavity, the left side face of the frame body is provided with a left side cavity, the pump station module is located in the left side cavity, the right side face of the frame body is provided with a right side cavity, the consumable module and the light source module are located in the right cavity, the cupping module is located in the right side cavity and penetrates into the main cavity, the back face of the frame body is provided with a back cavity, the power source module is located in the back cavity, and through the synergy of the modules, the full-automatic coagulation analysis is achieved.

The invention relates to a device and a method for carrying out on-line detection of the biochemical oxygen demand (BOD) in a water body sample by utilizing a microbiological fuel cell. The detection device has the advantages of real-time and on-line continuous detection function, simple operation, long continuous working time, and lower use and maintenance costs. The upwelling microbiological fuel cell is taken as the core, a BOD sample enters the microbiological fuel cell directly or after being diluted, and a linear relation exists between the coulomb yield of the microbiological fuel cell and the BOD content of the sample, thereby obtaining the BOD content of the sample through detecting the electrical signal generated by the microbiological fuel cell and through analyzing the obtained data by a computer control system. The detection method includes detecting the oligotrophic BOD concentration with the BOD concentration value in the sample less than critical value, and the eutrophic BOD concentration with the BOD concentration value in the sample larger than critical value; the detection of the eutrophic BOD concentration can be completed by adopting a buffer solution dilution method or a pulse integration method.

Embodiments of the present invention provide an indoor multipath error determining method and apparatus. The method comprises the steps of acquiring a to-be-positioned region covered by multiple base stations; dividing the to-be-positioned region into multiple preset grids; determining grid tops of each grid of the multiple preset grids as multiple reference points; measuring TOA Measure at when a signal of each base station of the multiple base stations arrives at the multiple reference points; for each reference point among the multiple reference points, comparing the TOA Measure with preset ideal TOA at when the signal of each base station arrives at each reference point, so as to obtain a multipath error of signal transmission between each reference point and each base station; and according to the multipath error of each reference point and pre-acquired position information of the multiple reference points, using a interpolation algorithm to obtain multipath errors of all points achieving the preset distance accuracy in the to-be-positioned region, wherein the preset distance accuracy specifically refers to a distance between every two points of all the points in the to-be-positioned region.

The invention discloses an intelligent vehicle safety belt detection method and an intelligent detection system. The method comprises steps that, in-vehicle members are detected, and a body area of each in-vehicle member is determined; edge detection on image data of each body area is carried out; whether a parallel straight line pair exists in each body area is determined, if yes, the in-vehicle members in the image are equipped with safety belts; if not, X body areas having no parallel straight line pairs are determined, image data of the X body areas is respectively filtered, and evaluation parameters and classification characteristic vectors are extracted; the classification characteristic vectors corresponding to the X body areas are respectively input into a training-over classifier, and wear results corresponding to the X body areas are determined; whether the X body areas respectively correspond to the safety belt wear results is determined, if yes, that the in-vehicle members in the picture respectively wear a safety belt is determined. Through the method, accuracy and efficiency are high, an operation speed is fast, and work load is greatly reduced.

The invention discloses a fixed-length cutting control device, comprising a conveyor unit, a length measuring unit, a cutting unit and a control unit, wherein the length measuring unit is used for measuring whether an object to be cut reaches preset fixed-length, wherein the object is conveyed by the conveyor unit; the cutting unit is used for cutting the object to be cut when the object to be cut reaches the preset fixed-length; and the control unit is used for controlling the conveying process of the conveyor unit for the object to be cut, the measuring process of the length measuring unit and the cutting process of the cutting unit. The invention also discloses a fixed-length cutting control method. According to the invention, by automatically conveying the object to be convey with the conveyor unit, by automatically judging cutting points with the length measuring unit, and by automatically cutting the object to be cut with the cutting unit, workload of labors is reduced, and production efficiency is improved. In addition, a rotary encoder is used to measure the length of a material to be cut, thus improving measuring accuracy, and reducing post-cutting error.

The invention relates to the technical field of construction informatization application, and discloses a constructional engineering budgeting system and a working mechanism thereof. The constructional engineering budgeting system comprises a computer system operating module. The constructional engineering budgeting system is characterized by further comprising a system maintaining module used for maintaining system operating, a graphic interacting module used for providing a graphic interacting function, a three-dimensional displaying module used for carrying out 3D processing and / or displaying on graphs and an engineering business module used for providing at least one constructional engineering business template. According to the constructional engineering budgeting system and the working mechanism thereof, the manpower workload can be further lowered, an engineering budgeting result can be rapidly obtained, the accuracy of engineering budgeting can be assured, the automation degree of the constructional engineering budgeting system is improved, and the follow-up construction of the constructional engineering is convenient.

A post-treatment method after character is identified includes identifying characters in file to obtain candidate character of said character and similarity of candidate character, confirming misidentified character by comparing said similarity with preset threshold, forming seek word to carry out search in known text databank to obtain measurement value of said word, using said value to calculate out weight value of misidentified character seek word, confirming correct character being used to correct misidentified character by comparing weight values of all misidentified character seek words.

The invention discloses a fully automatic system and a method of data preparation based on a financial IC card, and relates to the technical field of financial IC card personalization. The system comprises a foreground, a data base and a background, wherein the foreground includes a portal displaying module used for providing a manual configuration interface; a WEB management module used for importing a public template, configuring various templates and systematic parameters, and storing the templates and parameters in the data base; the background includes a card-making data processing module used for acquiring card-making data and generating a card-making request task; a task scheduling module used for splitting each card-making request task into atomic tasks; an atomic task processing module used for acquiring at least IC card secret-key certificate information from a secret-key management server to generate personalization data; and a data preparation file generating module used for merging personalization data to generate data preparation files, and delivering the data preparation files into different personalization servers according to target addresses. According to the invention, manual copy operation is not needed, workload and cost are reduced, man-made risks are reduced, and data security of a bank IC card is strengthened.

The invention discloses a numerical control machine tool operation state health diagnosis system and diagnosis method. The system comprises an edge data acquisition module, a cloud platform and a client, the cloud platform is connected with the edge data acquisition module and the client. The cloud platform comprises a predictive diagnosis module, an information management and storage module and an application server; and the predictive diagnosis module comprises a real-time diagnosis module, a post-processing diagnosis module and a comprehensive diagnosis module. According to the system, a cloud platform with a diagnosis function is used for replacing an upper computer, the expandability is greatly improved, the diagnosis and prediction tasks can be completed only by deploying corresponding sensors on the machine tool and connecting the sensors to the cloud platform, the real-time state data of the machine tool are managed in a centralized mode through the cloud platform, and the health condition of the machine tool is evaluated and predicted through the diagnosis technology based on the neural network. The diagnosis method is simpler, and the health diagnosis accuracy is high.

The invention provides an image data augmentation method. The method comprises: S1000, acquiring image data corresponding to category information of a to-be-screened image set; S2000, according to a preset screening strategy and a sample image corresponding to the category information, identifying the image data; S3000, classifying the image data based on the identification result to obtain an image data set; and S4000, carrying out adversarial training on the image data set to obtain a sample data set. The preset screening strategy includes one or more of similarity screening, hash value filtering, and keyword filtering. Therefore, the manual sample data set screening is reduced; the screening efficiency and screening reliability are improved; and the accuracy of the neural network is enhanced.

The invention relates to a method for optimizing 2D (two-dimensional) to 3D (three-dimensional) conversion of a video work. In the technical scheme, firstly, an original image is reduced and a low resolution depth map is artificially generated, wherein the workload can be greatly reduced when the depth map is generated under the condition of low resolution; and then the depth map is amplified to the size of the original image and a high resolution depth map is generated by utilizing a signal processing method. The method comprises the following steps of: firstly, carrying out filtering treatment on the amplified depth map by utilizing a bilateral filter; carrying out image gradient computation on the original image and the amplified depth map and judging whether important differences exist between the depth map and the original image; then selecting the bilateral filter or a trilateral filter to carry out optimization treatment on the amplified depth map according to a judging result and generating a depth map with high quality; and finally, generating a 3D stereo image by utilizing a depth-based image rendering algorithm. According to the method, on the premise of ensuring the quality of the depth map, the speed of generating the depth map can be quickened. The method can be used for making the 3D video work with high quality and low cost and at high speed.