25results about How to "Realize intelligent identification" patented technology

The invention relates to an overseas website access encrypted traffic detection method based on multi-scale information entropy modeling, and belongs to the technical field of communication. The method comprises the following steps: collecting and preprocessing network traffic, and extracting a data packet byte sequence, a length sequence and a time interval sequence; calculating a multi-scale information entropy matrix of the traffic sequence based on different time scales and packet window scales; inputting the information entropy matrix into a convolutional neural network and attention mechanism fusion method for feature extraction; a long-time dependency relationship is modeled through a self-attention mechanism by using a Transform model, so that the accuracy of flow analysis is further improved; model training optimization is carried out through a cross entropy loss function and an Adam optimization algorithm, and the generalization ability is improved by adopting regularization and data enhancement methods. According to the invention, intelligent identification of Chinese websites and non-Chinese websites is realized in an encrypted traffic environment.

The present disclosure relates to a method and device for identifying tectonic coal based on borehole gamma data. The method comprises: acquiring gamma curve data and mechanical drilling speed data collected in real time during the process of logging while drilling; preprocessing the gamma curve data and the mechanical drilling speed data to obtain depth sequence data; performing segmentation processing on the depth sequence data to obtain a plurality of data sample units; for each data sample unit, extracting a plurality of sample features for representing the response mode of tectonic coal from the data sample unit, fusing the plurality of sample features to obtain a multi-parameter fusion feature vector; and inputting the multi-parameter fusion feature vector into a trained machine learning classification model to obtain a classification result output by the machine learning classification model. The present scheme improves the accuracy and efficiency of tectonic coal identification.

The application discloses a novel end device of a surgical robot system, which comprises a parent control module and a child tool module detachably installed on the parent control module; a plurality of positioning holes are arranged on the end face of the parent control module towards the child tool module; a plurality of positioning pillars for identifying the model of a surgical tool are arranged on the end face of the child tool module towards the parent control module; when the plurality of positioning pillars on the child tool module are inserted into the plurality of positioning holes on the parent control module, the parent control module identifies the model of the surgical tool of the child tool module by judging the layout style and / or length of the inserted positioning pillars. The end device of the application can be installed on the mechanical arm of the surgical robot to realize intelligent identification.

This invention provides a deep learning-based intelligent analysis method for cardiovascular medical images, comprising the following steps: S1, heterogeneous data fusion and acquisition of multimodal medical images and physiological signals; S2, intelligent extraction and quantitative analysis of vascular structural features based on deep learning; S3, hemodynamic parameter modeling and risk region segmentation based on fused structural features; S4, texture feature mining and intelligent identification of lesion types in high-risk areas; S5, cardiovascular disease risk stratification prediction based on multi-dimensional feature fusion; S6, federated learning optimization and closed-loop update of the model. This invention's deep learning-based intelligent analysis method for cardiovascular medical images achieves, for the first time, heterogeneous fusion of medical images, millimeter-wave radar-PPG physiological signals, and clinical molecular data, and achieves precise spatiotemporal alignment through GPS-controlled crystal oscillators, overcoming the limitations of single image analysis and providing a more comprehensive feature foundation for subsequent feature extraction and risk prediction.

This invention discloses a neural network-based anti-disassembly identification system and method for data center equipment, belonging to the field of neural network technology. Based on the data center equipment management backend, it obtains equipment structural assembly information, constructs a set of detachable components and corresponding structural nodes and their connections, introduces connection attribute parameters, establishes a structural connection constraint matrix for detachable components, constructs a baseline state model of equipment structural connections, calculates structural differences, and generates component-level abnormal state identifiers. The structural differences and abnormal states of each detachable component are used as structural state feature vectors input to the disassembly behavior identification neural network model, outputting a disassembly risk score to determine whether illegal disassembly of the data center equipment exists. When illegal disassembly is detected, the system generates corresponding alarm information and triggers warning and handling operations, achieving intelligent identification and risk assessment of data center equipment disassembly behavior, improving the accuracy and real-time performance of equipment structural safety supervision.

The invention relates to the technical field of gas leakage early warning, in particular to a gas leakage early warning method and system based on Internet of Things pressure monitoring, and the method comprises the steps: carrying out the node detection of a target pipeline, obtaining a distributed monitoring network, carrying out the monitoring data collection of the target pipeline, obtaining a monitoring information set, and carrying out the monitoring data analysis of the monitoring information set. A monitoring feature vector set is obtained, leakage judgment is carried out, a leakage judgment result is obtained, if the leakage judgment result is that no leakage event exists, a monitoring report is constructed according to the leakage judgment result and the monitoring feature vector set, and if the leakage judgment result is that the leakage event exists, leakage positioning analysis is carried out on the target pipeline, and a leakage position set is obtained; and obtaining a monitoring report and an early warning instruction according to the leakage judgment result, the monitoring feature vector set and the leakage position set. According to the invention, the problems of low early warning real-time performance and weak leakage position positioning capability in the current gas leakage monitoring process can be solved.

The application discloses a fallen pineapple righting device and a harvesting method, which are arranged on a harvesting vehicle and comprise a righting frame, a clamping mechanism arranged on the righting frame and used for clamping the pineapple, a vertical driving mechanism used for driving the clamping mechanism to move vertically, a horizontal driving mechanism used for driving the clamping mechanism to move horizontally, and a visual recognition positioning module used for recognizing and positioning the fallen pineapple. The clamping mechanism comprises two oppositely arranged clamping claws and a clamping driving mechanism used for driving the two clamping claws to open and close. The clamping mechanism is connected with the driving end of the vertical driving mechanism, the vertical driving mechanism is connected with the driving end of the horizontal driving mechanism, and the driving direction of the horizontal driving mechanism is perpendicular to the direction in which the harvesting vehicle advances to harvest. The righting device and the harvesting method can intelligently recognize the posture of the fallen pineapple, accurately clamp the crown bud and right the fallen pineapple.

The application discloses a kind of energy-saving control method of frequency conversion speed regulation and energy recovery cooperation rig plunger pump, and relates to industrial control technical field.The method includes: monitoring the current working power of rig plunger pump at first working frequency, when power exceeds preset first working power interval, first working power time sequence is collected;According to the time sequence data, the geological adaptability coefficient is calculated using the pre-trained geological adaptability analyzer;Determine whether the working frequency needs to be adjusted, and determine the second working frequency and the corresponding second working power interval accordingly;Based on the second working frequency, frequency converter, energy storage device and energy recovery device are cooperatively controlled.The application realizes intelligent perception and self-adaptive adjustment to formation change, and significantly improves the energy efficiency and operation economy of rig plunger pump under complex geological conditions through the collaborative management of energy.

This invention relates to the field of expense reimbursement management technology, and in particular to a centralized management system and method for expense reimbursement documents based on financial sharing. The management system includes a financial sharing module, an interaction management module, and an expense reimbursement document interaction module. The financial sharing module pushes expense reimbursement document data to the interaction management module in real time. The interaction management module controls and monitors the entire interaction process of expense reimbursement documents. The expense reimbursement document interaction module implements the entire interaction process of expense reimbursement documents. A first machine learning model is established in the financial sharing module as its generator network; a second machine learning model is established in the interaction management module as its generator network; a discriminant network for the interaction management module is established in the financial sharing module; and a discriminant network for the financial sharing module is established in the interaction management module. This management system and method effectively solve the problems of risk and time-consuming / labor-intensive processes in expense reimbursement document interaction.

The application discloses a sintering machine tail state monitoring method based on machine vision. The method comprises the following steps: S1, preprocessing of the input sintering machine tail image; S2, color gamut conversion of the original image to extract the combustion area in the image; S3, image processing after extracting the combustion area and extraction of the machine tail area; S4, feature value calculation of the extracted machine tail area; and S5, sintering state judgment and monitoring according to the feature value. The application constructs a sintering machine tail state monitoring system through machine vision and image processing related technologies, realizes real-time monitoring of the sintering machine, gives a prompt and a warning to the abnormal part, further realizes intelligent production of the sintering process section, improves the production efficiency of the steel enterprise, reduces the labor cost, and further promotes the intelligent manufacturing transformation and upgrading and intelligent development of the steel metallurgy field in China.

This invention belongs to the field of natural language processing and engineering cost estimation technology, specifically involving an automatic process segmentation method for engineering bills of quantities that integrates semantic understanding and sequence labeling. It achieves automatic bill of quantities segmentation by deeply integrating engineering domain knowledge and deep learning. Through atomized process segmentation and BIOA sequence labeling, process-level granularity is achieved, accurately separating different processes and providing a favorable premise for subsequent cost item matching. By introducing the BERT+CRF sequence labeling model, the semantic logic of construction is understood, and through the B-I tagging mechanism, the main process and its supplementary descriptions are automatically merged, maintaining the semantic integrity of the process. This overcomes the dual defects of existing technologies, namely, "illusion in overall prediction" and "unintelligent mechanical segmentation."

The application discloses a scheme for automatically discovering the similarity between different table data of a relational database based on a Bloom filter algorithm, reads all table information from the relational database, forms a table information dictionary and stores the table information dictionary; a filter is established based on a unique value set of N by using the Bloom filter algorithm; the established Bloom filter is transmitted to a unique value set of M, the value is filtered, and a return result set {R1, R2, R3, … Rn: R epsilon (True, False)} is counted; a probability W is counted: ∑R{true} / (R{true|false}); when W>ɑ (ɑ is a given threshold value), it is determined that M and N are similar, otherwise, M and N are not similar. The application can analyze all tables and all fields, and judge the data similarity between tables without relying on any artificial rules, artificial judgment or predefined instructions, and can be used for main data discovery, data reference relationship generation and data table relationship construction in a data management process, so that the traditional data management process is changed from manual to intelligent, and the management accuracy and management efficiency are effectively improved.

The application discloses a kind of reciprocating compressor fault early warning method, system, equipment and storage medium, the method includes: to the pre-processing of multi-source sensor data, obtain standardized data frame sequence set;Standardized data frame sequence set is based on time domain feature extraction, frequency domain feature extraction, angle domain order feature extraction and displacement feature extraction;To the multi-source feature fusion normalization of extracted time domain feature, frequency domain feature, angle domain order feature and displacement feature;Fusion normalized multi-source feature vector is input into fault diagnosis model, and outputs fault diagnosis report, carries out fault early warning to reciprocating compressor, and fault diagnosis model is based on mechanism rule engine and CNN-LSTM attention network combination construction.The application effectively integrates the vibration, displacement, key phase and other multi-source sensor data of reciprocating compressor, overcomes the technical bottleneck of single sensor information deficiency and poor adaptability of traditional diagnostic method, and improves the accuracy of fault diagnosis.

This utility model relates to the field of food production technology and discloses an automatic food carton sealing machine, including an operating table. A loading platform and a unloading platform are respectively provided at both ends of the operating table. A pressing component is fixedly installed on the loading platform, and a carton body is placed on the loading platform. A transmission component and a sealing component are provided on the operating table, and an adhesive tape body is provided on the top of the sealing component. In this utility model, by setting up the pressing component, the two short tongues of the carton body are flattened and the two long tongues are pre-shaped, while the height of the carton body can be measured. After receiving the height data, the remote control center adjusts the overall height of the sealing component. By setting up the transmission component to clamp and transmit the carton body, the width of the carton body can also be measured. After receiving the height data, the remote control center adjusts the auxiliary clamping and feeding distance of the sealing component, thereby realizing intelligent identification of carton data.

The application discloses a rural land consolidation potential intelligent identification method and device, obtains a rural land object to be consolidated through spatial range vector data and high-resolution remote sensing image data of the rural land to be consolidated, extracts image features of the rural land object to be consolidated, establishes a rural land consolidation potential identification model, realizes automatic identification of the rural land consolidation potential, and corrects the identified potential land block through a participatory survey. The application fully utilizes the advantages of rich and diverse ground object information of high-resolution remote sensing images, realizes intelligent identification of the rural land consolidation potential land block in a manner that random forest classification identification is combined with participatory survey, and makes the identified consolidation potential land block more accurate in scale, more accurate in spatial position and higher in available degree.

This invention discloses a naming entity recognition method for aviation equipment models that integrates multi-source knowledge, comprising the following steps: S1: constructing a corpus for recognizing flat and nested entities of aviation equipment models; S2: establishing a naming entity recognition model integrating multi-source knowledge based on the corpus constructed in step S1; S3: using the naming entity recognition model established in step S2 to recognize the named entities of aviation equipment models. The naming entity recognition model integrating multi-source knowledge generally adopts an MRC model, integrating naming rule information into the query information in the input text, and combining RoBERTa and domain dictionary enhancement methods to extract semantic information during text encoding. The recognition method in this invention achieves F1 scores of 89.26% and 85.53% for flat entities and nested entities, respectively, realizing intelligent recognition of naming entities for aviation equipment models.

The utility model relates to a kind of battery management system control shell size detection equipment, belong to battery production technical field.The equipment includes casing, detection component, conveying mechanism, multiple placing pieces and replenishment component, conveying mechanism extends to the inside of casing, placing piece equidistance is set on the surface of conveyer belt, every placing piece includes placing seat, its top is set inlaid battery shell inner cavity, replenishment component is set above conveying mechanism, including replenishment box, fixed frame, baffle, stop plate, guide ring and connecting shaft etc., placing piece is also equipped with auxiliary strip, when placing seat is vacant, auxiliary strip naturally droops and contacts stop plate, and pushing connecting shaft rotates, through guide ring and connecting frame drive baffle transverse movement, so that the battery shell in replenishment box falls into vacant placing seat.The equipment is automatically identified empty position and completes replenishment by mechanical structure, avoids false triggering, ensures that detection process is continuously carried out, effectively improves production efficiency.

This invention relates to the field of computer-aided design technology, specifically disclosing a system for automatic extraction and cost calculation of drawing dimensions based on DXF files. The system includes: a main interface interaction module, a file management module, a DXF parsing and dimension extraction module, a cost calculation module, a log and progress management module, and a version and permission management module. The system achieves a closed-loop process for DXF drawings, from batch import, integrated automatic extraction of geometric and process information, automatic cost calculation with compensation in multiple modes, batch fault-tolerant processing, to commercial authorization control. This invention constructs a fully automated closed-loop process from batch import of DXF drawings, integrated automatic extraction of geometric and process information, automatic cost calculation in multiple modes, and automatic export of results, completely replacing the traditional method of manually processing drawings one by one.

The invention relates to the technical field of grain quality detection, discloses an intelligent identification method and system for broken spherical grains, and aims to solve the problems of poor efficiency and accuracy of the existing method, and the scheme mainly comprises the following steps: continuously conveying spherical grains to be detected to pass through an imaging area one by one without overlapping; transmission light is applied to the single grain passing through the imaging area from the upper portion and the lower portion, and a transmission image of the grain under the transmission light is collected from the upper portion; segmenting an instance region of a single particle from the continuously acquired transmission images by adopting an image instance segmentation algorithm; for each instance area, gray level distribution characteristics in the transmission image are analyzed; and identifying a region with enhanced light transmission caused by reduction of local thickness based on the gray level distribution characteristics, and judging whether the grain particles are broken particles or not according to the region. The broken grain detection efficiency and accuracy are improved through the intelligent imaging technology, and the method is suitable for intelligent identification of quality indexes of spherical grains such as rapeseeds and soybeans.

The invention provides a sensitive information detection method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining to-be-detected candidate data, and carrying out the preprocessing of the candidate data, so as to generate target data; performing feature extraction on the target data based on a 40-point feature extraction model to generate multi-level pose features; processing the multi-level pose features to generate a rule matching score, a pose score, a skin exposure score and a scene score; and determining a confidence value based on the rule matching score, the posture score, the skin exposure score and the scene score, and judging whether sensitive information exists or not. Through a technical path of 40-point refined pose modeling-multi-dimensional sensitivity scoring-dynamic confidence fusion, the method realizes structured, quantifiable, adjustable and controllable intelligent recognition of potential sensitive information in complex human body postures, effectively makes up for the defects of a traditional keyword or simple image recognition method, and improves the recognition accuracy of the human body postures. And a key technical support is provided for constructing safe and compliant network ecology.

This invention belongs to the field of image analysis and visual recognition. It discloses an intelligent identification system and method for engineering safety hazards based on image recognition. The system obtains multi-source engineering hazard image features by collecting, processing, and fusing engineering monitoring images, and also acquires environmental and meteorological features, engineering personnel features, and constructs a knowledge structure graph. It obtains engineering safety association tags and calculates the risk relationship features between the environment and engineering personnel. After feature embedding and fusion processing of the above images and relationship features, it constructs an engineering safety hazard identification and prediction model based on corresponding engineering safety hazard prediction and identification methods. The model is used for risk monitoring of engineering construction safety hazards. The system achieves intelligent identification of engineering safety hazards by constructing a knowledge graph network representing the attribute feature vectors of the environment and personnel, and relying on a voting multi-value fusion classification neural network model for end-to-end fusion feature processing.

The invention relates to the technical field of intelligent manufacturing and industrial robots, in particular to an intelligent welding method based on deep learning and three-dimensional reconstruction. Comprising the steps that point cloud data of a to-be-welded workpiece is obtained, a welding seam area is recognized through preprocessing and a point cloud segmentation network, and welding seam track information including welding seam space coordinates and a welding gun posture is obtained; optimizing the motion track of the robot through a global optimization algorithm and a local obstacle avoidance algorithm, and generating a planned track; welding seam position information is obtained in real time in the welding process, the real-time welding seam position is obtained through filtering of a state estimation algorithm and compared with a planned track, and position deviation is obtained and dynamically corrected; performing defect detection on the weld seam image, and combining process parameter analysis and case matching to generate a quality evaluation result; and closed-loop self-adaptive control is carried out based on the real-time welding seam position and the quality evaluation result. By means of the method, high-precision automatic extraction of the welding seam track, optimal planning of the movement track, real-time accurate tracking of the welding seam position and intelligent evaluation of the welding quality can be achieved.

This utility model relates to an intelligent identification blood collection tube cap device, including a device housing, a cover plate installed at the rear end of the device housing, multiple fixing blocks installed at the bottom of the device housing, and limiting grooves provided on the top of the multiple fixing blocks. Multiple blood collection tubes with caps of different colors are placed in different limiting grooves. The inner wall of the limiting groove is provided with an installation groove, and a moving component is provided inside the installation groove. An intelligent identification component is provided on the top of the device housing. This utility model can place multiple blood collection tubes with caps of different colors into multiple limiting grooves respectively. When different types of blood collection tubes are needed, the operator can use the buttons corresponding to the multiple blood collection tube types on the surface of the industrial control computer to start the drive motor on the corresponding fixing block, thereby driving the corresponding blood collection tube to move and rise, so that the corresponding blood collection tube can be directly removed, making it convenient for the operator to accurately pick up different types of blood collection tubes.

The invention provides a BIM (Building Information Modeling)-based rigid concrete structure collision-free construction method, which relates to the technical field of rigid concrete construction and comprises the steps of BIM model construction, intelligent detection of collision points, open pore parameterization design, deepened drawing export, steel skeleton prefabrication processing, field installation and rechecking and the like. According to the invention, collision detection automation, trepanning design precision and construction process visualization can be realized, the rework rate is greatly reduced, and the construction quality and efficiency are guaranteed.

The application discloses a metallurgical furnace condition recognition method based on a streaming multimodal graph neural network, which extracts visible light image features of a furnace material surface by using a convolutional neural network, extracts time series data features by using a multilayer Transformer encoder, deeply fuses double-mode features through a bidirectional cross-attention mechanism, constructs a dynamic memory bank, stores historical sample features by using a first-in-first-out strategy, takes current sample features as a query vector, filters neighbor nodes based on double-mode similarity, constructs a dynamic topology graph through an adaptive edge weight fusion module, and outputs a furnace condition recognition result by using a lightweight graph neural network to weight, aggregate and update node features. The application adopts a semi-supervised learning strategy, combines cross-entropy loss, Laplace loss and consistency loss for joint optimization, realizes high-precision furnace condition recognition under the condition of only a small amount of labeled samples, has the advantages of lightweight, low latency and support for streaming incremental reasoning, and is suitable for edge deployment in a metallurgical industrial field.