33 results about "Process classification" patented technology

The invention relates to the technical field of data processing, in particular to a modular task management system based on dynamic process configuration, which comprises a dynamic process configuration module, a task state circulation engine, a visual interaction interface module, a historical track tracing module and a modular expansion interface. The dynamic process configuration module dynamically binds enterprise configuration data with regional process original data through a process template ID to generate an enterprise exclusive process topological structure comprising a regional identifier, a node association relationship and a process classification label; and the task state circulation engine updates the task state data based on an event-driven and atomized transaction lock mechanism, and synchronizes the task state data to the change management general table. According to the method, flexible configuration of process logic, visual display of task states and cross-enterprise rapid adaptation are realized, and system expansibility and operation efficiency are improved.

The invention belongs to the field of deep learning and machine vision, and discloses a surface defect detection method based on YOLOX multi-scale network reconstruction, and the specific technical scheme is as follows: a surface defect detection data set is converted into a YOLO standard input format, and a reconstruction feature extraction network performs deep information mining on an image in a series connection mode; in a channel aggregation path, generating a channel attention graph through operations such as global average pooling, convolution and activation, and combining the channel attention graph with a graph after space refinement to realize multi-scale information fusion in a channel dimension; in a multi-level multi-scale space, reconstructing a multi-scale fusion network Neck based on YOLOX features, realizing a space center on the top layer of a feature pyramid, and simultaneously adjusting all previous shallow layer features by using the obtained features containing the space explicit visual center; a decoupling head is introduced to process classification and positioning tasks respectively; inputting the training set for model training, and loading the model for surface defect detection.

The invention provides a reinforcing steel bar binding point detection method based on improved YOLOv8, and the method comprises the following steps: obtaining a construction site image, carrying out the preprocessing, inputting a to-be-detected image into an improved target detection model, sequentially carrying out the local space attention calculation, depth separable convolution and channel attention weighting operation, and carrying out the detection of the to-be-detected image. Detail feature expression of reinforcing steel bar intersection points is enhanced; performing dynamic weight fusion on the top-down first feature path and the bottom-up second feature path, and embedding a lightweight residual unit in a fusion node; a classification task and a regression task are respectively processed by adopting a classification branch and a regression branch, the classification branch outputs category confidence, and the regression branch outputs coordinate positioning through depth separable convolution and a probability distribution prediction layer; and decoding output data of the target detection model, and generating a detection result containing the position and the category of the binding point. According to the method, the requirement of real-time detection can be met while the accuracy of steel bar binding point detection is improved.

The invention provides an intelligent price checking method and system for 3D drawings of parts. The method comprises the following steps: identifying a process type through a pre-trained process classification model, and matching a corresponding target equipment type according to the process type; analyzing the 3D drawing information of the part to obtain geometric machining characteristics of the part, matching a corresponding tool type from a preset tool library according to the process type and the geometric machining characteristics, and determining tool machining parameters according to equipment performance parameters corresponding to the target equipment type and tool performance parameters corresponding to the tool type; on the basis of the geometric machining features, the target equipment type and the tool machining parameters, the machining time of the part is predicted through a pre-trained time prediction model; and generating a target price checking result of the part based on the equipment use cost corresponding to the target equipment type, the material cost corresponding to the part raw material and the man-hour cost corresponding to the processing man-hour. According to the invention, the efficiency and accuracy of price checking are improved.

The invention relates to the technical field of enterprise informatization and process automation, and discloses an intelligent process construction and dynamic optimization method based on low codes, and the method comprises the steps: selecting a process category based on preset process classification; an initial process template is generated based on the process category, the initial process template is output in a visual mode, and the initial process template comprises an initial task node, an initial process branch and an initial gateway; adjusting an initial task node, an initial process branch and an initial gateway for the initial process template through visual dragging to form a basic process; executing the basic process, recording the execution condition of the basic process, and generating an optimization suggestion according to a preset optimization model; the user selects an optimization scheme according to the optimization suggestion and outputs an optimization process; and adjusting the initial process template based on a preset process adjustment strategy. The method has the advantages of reducing a process construction technical threshold, realizing process dynamic optimization and improving compliance control capability.

The application discloses a kind of based on marketing text data processing method and device, the method includes: obtaining marketing text information to be processed;Utilize preset label processing rule to the marketing text information to be processed classification processing, obtain label information;Label information is related to the industry and text style of marketing text information to be processed;Utilize preset attribute processing rule to the marketing text information to be processed identification processing, obtain attribute information;Label information and attribute information are processed, and obtain first triplet information;First triplet information includes M element information;M is greater than or equal to 3 positive integer;Element information is related to label information and attribute information;First triplet information is used to construct the knowledge graph of guiding generation marketing text. Visible, the application is favorable to improve the labelization processing efficiency of marketing text, and then improve key information extraction quality, to construct effective knowledge graph.

The invention discloses a big data automatic classification and grading method, system and device based on a dynamic update feedback mechanism and a medium, and the method comprises the steps: extracting feature vectors of a field in different tables and different scenes, and determining a grading result of data in the field according to grading results of three dimensions of sensitivity, importance and use frequency, constructing a multi-dimensional scoring and grading model; performing model incremental training through data distribution detection to realize dynamic updating of the model; model retraining is carried out through grading anomaly detection, and closed-loop feedback of the model is achieved; the system, the equipment and the medium are used for realizing the method. The classification and grading method has the characteristics of full-process classification automation, dynamic updating, closed-loop feedback and big data platform adaptation, and the efficiency, safety and flexibility of data classification and grading are remarkably improved.

The application belongs to the field of intelligent construction and robot technology, and relates to a robot operation description automatic generation method, an intelligent operation method and a hardware platform, which comprises the following steps: constructing a semantic analysis engine containing a process classification dictionary and a construction process knowledge base, reading a BIM model file and screening to-be-operated components; based on the geometric topological features and volume attributes of the components, deducing and establishing a local operation space containing a grabbing coordinate system, an approaching coordinate system and an installation coordinate system; using semantic mapping technology, converting static component attributes into dynamic robot atomic action sequences, and automatically injecting dynamic constraint parameters according to material physical attributes; and finally generating a standardized robot operation description file containing timing logic and spatial information. The application can bridge the semantic gap between BIM design data and robot control data, realize precast component installation process teaching-free autonomous operation, and significantly improve construction efficiency and safety.

The invention relates to an electric power facility disaster damage monitoring method and an identification device, and belongs to the technical field of electric power facility disaster damage monitoring. The method comprises the steps of constructing a multi-dimensional feature portrait of a disaster damage identification device by collecting multi-source data, and dynamically scheduling and matching a pre-layering model for concurrent tasks based on the multi-dimensional feature portrait; performing decoupling analysis on the multi-dimensional feature portrait through the pre-layering model, and completing classification and positioning in parallel; data uploaded by all disaster damage identification devices are aggregated to train and generate a new model, a multi-dimensional feature weight is set based on a release target to calculate a comprehensive score, and a gray release target is screened. According to the method, dynamic scheduling of model resources is realized through the multi-dimensional feature portraits, and the utilization efficiency and response real-time performance of edge-side resources are improved; classification and positioning tasks are processed in parallel by adopting a decoupling architecture, so that the recognition precision is improved; a closed-loop self-evolution system is constructed by means of an intelligent gray release mechanism based on cloud edge cooperation, and the monitoring accuracy, predictability and continuous optimization capability are comprehensively improved.

The present application relates to the emerging software technology field about processing classification, and especially relates to a hull part intelligent classification method and system based on internal and external contour features. Based on the hull part drawing, a structured part object list is generated, the internal structure features and the external contour features of the part are extracted, and a multi-dimensional feature vector set is constructed; based on the preset weight configuration of each dimension, the multi-dimensional feature vector is processed by the K-means clustering algorithm based on weighted Euclidean distance, and the clustering allocation result is output; the contour coefficient of the part is calculated, the CH index is calculated, and the classification effect is output according to the contour coefficient and the CH index. By extracting the internal and external contour features of the part, constructing the multi-dimensional feature vector, and classifying based on the K-means clustering algorithm based on weighted Euclidean distance and evaluating the classification by the contour coefficient and the CH index, high-precision and high-process-fitting-degree classification is realized, and the classification efficiency and consistency are improved.

The invention discloses an abnormal monitoring and early warning method for process parameters of an annealing furnace. The abnormal monitoring and early warning method comprises the following steps: collecting product information related to product process classification, production state information related to a production process and online information of production process parameters in the annealing furnace; the collected information data is preprocessed, missing values and outliers in the information data collection process are screened, marked or eliminated, and dimension reduction processing is carried out on other process parameters; classification is carried out based on the characteristics of the process parameters, and different process parameter monitoring difference judgment methods are selected according to different types; the process parameter monitoring and difference judging method comprises a monitoring and difference judging method based on a threshold value and a monitoring and difference judging method based on a waveform; and processing the obtained monitoring result, setting different early warning information according to abnormity of different degrees, and executing corresponding operation according to different abnormity results.

The application discloses a large-scale multi-label text classification method based on label adaptive text representation. The application firstly explores label adaptive representation of the text to effectively process classification performance of head labels and tail labels under large-scale multi-label classification; a pre-trained language model is used to learn a representation pool for the text, so that different labels can focus on different representations to complete correlation discrimination. Considering the characteristics of deep models and long texts, text representation enhancement is proposed to ensure the difference and comprehensiveness of the representations in the pool. Therefore, the application can provide effective discriminative text features for large-scale labels to improve the prediction performance. Compared with current large-scale multi-label algorithms, the application can guarantee the overall classification performance of large-scale multi-labels on the one hand, and guarantee that tail labels can better focus on detailed text features on the other hand, and the performance is better than that of the current most advanced large-scale multi-label algorithm.

The invention discloses a summary approval implementation method and system, and belongs to the technical field of computer application. The method comprises the steps of creating an approval task summarization rule according to a preset summarization rule table, wherein the summarization rule table at least comprises a process classification ID; performing data extraction and analysis on the historical approval information by using a preset processing model, and constructing a summarized approval rule according to a data extraction and analysis result; adding a new field in the task table, wherein the new field is used for indicating whether the to-be-approved task is a summarized approval push task; when a new to-be-approved task exists, querying the approval task summarization rule according to a process classification ID corresponding to the to-be-approved task, and assigning a new field in the task table as yes according to a query result; and according to the approver ID and / or the process classification ID corresponding to the to-be-approved task, querying the summarizing approval rule, and according to the queried rule content, summarizing and pushing the to-be-approved task.

The invention provides an intelligent analysis method and system for operating room clinical nursing data of brain patients, and relates to the technical field of data processing. The method comprises the following steps: collecting clinical nursing record data of a plurality of patients, constructing task item structure data of each group of clinical nursing record data, obtaining operation process structure data, performing process classification on each group of task item structure data, and constructing a task item sample data set of each operation process stage; performing nursing state analysis to determine a nursing state label of each task item, and performing nursing deviation detection on a plurality of patients to generate individual deviation characteristics of each patient; stage nursing intensity analysis is carried out in combination with the nursing state labels and the individual deviation features, nursing intensity features of each operation process stage are generated, and group clinical nursing state portraits about the multiple patients are constructed. According to the invention, fine management and optimization of clinical nursing work are realized.

The application relates to a reimbursement form filling method and device based on an agent, equipment and a medium, and relates to the technical field of reimbursement processing. The method comprises the following steps: obtaining a reimbursement request input by a user through an agent assistant interface; inputting the reimbursement request into a pre-trained large language model to perform intent recognition, obtaining intent information of the reimbursement request, and determining a process classification result of the reimbursement request based on the intent information, wherein the process classification result comprises querying a business trip task sheet, generating a reimbursement form according to the business trip task sheet, and writing invoice information into the reimbursement form details; based on the process classification result, triggering a corresponding workflow branch to perform corresponding operations, obtaining an execution result of the reimbursement request, and feeding back the execution result of the reimbursement request based on the agent assistant interface, wherein the operations comprise calling a database query interface, a business plug-in interface or an external tool interface. The application realizes an intelligent reimbursement form filling process, and improves the efficiency and accuracy of the reimbursement processing.

The present application relates to the field of petroleum engineering, and provides a method for classifying the working conditions of conventional workover operations in oil and gas fields. It uses data processing technology based on deep learning to decompose and semantically encode the text descriptions of conventional workover operations in oil and gas fields. Then, the process semantic feature corresponding to the i-th process is extracted from the set of encoded process semantic features as the process semantic feature to be recognized, and the entire set is divided into the sets of the process semantic features of the previous text and the subsequent text with this as the dividing line. Then, the process semantic feature to be recognized is contextually encoded with the sets of the process semantic features of the previous text and the subsequent text respectively, so as to intelligently judge the operation category of the process to be recognized according to the positive and negative attention responses between the context semantic features of the previous text and the subsequent text of the process to be recognized. In this way, the efficiency and accuracy of process classification can be effectively improved.

To provide a machine learning device, method, and program capable of improving the reliability of labels used to train deep learning models that process classification problems. [Solution] The machine learning device according to the embodiment includes a learning unit, a determination unit, and an update unit. The learning unit obtains a first model output including inference probabilities and / or feature vectors output from a first deep learning model by applying a first sample to a first deep learning model that processes a classification problem. The determination unit determines whether or not it is necessary to update the labels used as teachers for training the first deep learning model, based on the first model output and / or labels. If it is determined that a label update is necessary, the update unit updates the labels based on the first model output and the current update count of the labels; if it is determined that a label update is not necessary, it terminates the label update.

The invention relates to the technical field of drug production data monitoring, in particular to a drug production data analysis system based on cloud computing, which acquires environmental parameters of equipment such as a reaction kettle, constructs a process section parameter fluctuation index, identifies a fluctuation overlapping interval to divide trend blocks, extracts a same-direction trend path of temperature and humidity parameters and marks a repetition mode. And positioning the cache structure offset intensity in combination with a task calling record, collecting a parameter track of a high-frequency offset section, mapping a process type, constructing a stable trend classification set, and generating a drug production parameter clustering analysis result. According to the method, a multi-dimensional parameter fluctuation index is constructed, the classification precision is improved through a process paragraph label, abnormality is detected through trend coincidence and interference marks, a parameter linkage map is established, load change is positioned in combination with task frequency, a stable process classification system is formed through a mapping track, data analysis is enhanced, and quality evaluation, process optimization and risk early warning efficiency are improved.

Systems and methods for processing classification field values in machine learning applications, particularly neural networks, are disclosed. Classification field values are typically converted to vectors prior to being passed to the neural network. However, low-dimensional vectors limit the ability of the network to understand correlations between contextually, semantically, or featured similar values. On the contrary, the high-dimensional vector may suppress the neural network, resulting in the network finding a correlation with respect to individual dimension values, which may be false. The disclosure relates to a hierarchical neural network comprising a primary network and one or more secondary networks. Classification field values are processed in the secondary network to reduce the dimensions of the values prior to being processed by the primary network. This enables contextual, semantic and feature dependencies to be identified without overloading the entire network.

The invention provides a wind speed early warning method and system based on weather forecast and topographic features, and relates to the field of meteorological disaster early warning technologies. The method comprises the following steps: S1, carrying out fusion and gridding preprocessing operation on meteorological data; s2, performing dynamic correction operation on the wind speed according to the terrain effect; s3, based on historical disaster data analysis of a specific area, establishing a typical weather process classification system, and realizing weather adaptation optimization; and S4, dividing risk levels and carrying out partition response. The system provided by the invention comprises a data fusion module, a dynamic calculation module, a weather process adaptation optimization module and an early warning output module. The method has the beneficial effects that the spatial scale limitation of weather forecast data is broken through, and refined wind speed distribution mapping of a complex terrain region is realized; the wind speed modulation effect of the typical terrain under different meteorological conditions is quantified, and a dynamically adaptive calculation model is established; and resource configuration is optimized through a space partition response mechanism, and the protection efficiency is improved.

The present invention discloses a precast beam process identification system and method, which solves the problem that the progress of precast beam processes mainly relies on manual inspections in the prior art, and has the beneficial effect of being able to identify precast beam processes more economically and efficiently. The specific solution is as follows: A precast beam process identification system includes a gantry crane. The two sides of the gantry crane are supported by traveling rails, and the gantry crane can move along the traveling rails; a process identification mechanism, the process identification mechanism is installed on the main beam of the gantry crane, the main beam is provided with a first rail, and the process identification mechanism includes a collection unit, a communication unit and a control unit connected in sequence. The control unit is also connected to a movement control unit, and the movement control unit is used to control the process identification mechanism to move along the first rail; a control unit, the control unit matches the classification result with the process classification model built in the control unit, so as to identify the precast beam process corresponding to the image information transmitted by the collection unit.

The present invention provides a low-density-high-density dual-branch cell division process classification system, including a cell division degree classification module, a video interpolation module, a feature extraction module and a classification prediction module; the cell division degree classification module obtains the degree of division change intensity; the video interpolation module is used to interpolate the original low-density real embryo image set to obtain a high-density embryo image set with high information density; when interpolating, different numbers of frames are inserted between two adjacent embryo images according to the degree of division change intensity; the feature extraction module is used to extract the features of the low-density real embryo image set and the high-density embryo image set respectively and fuse them; the classification prediction module is used to input the fused features into a fully connected layer for prediction to obtain a classification result. Extract the rules that change over time and space and use the current rules to improve the classification accuracy of different division modes.

The invention provides a double-branch cell division process classification system based on low density and high density. The system comprises a cell division degree classification module, a video frame insertion module, a feature extraction module and a classification prediction module. The cell division degree classification module is used for obtaining a division change intensity degree grade; the video frame insertion module is used for performing frame insertion on the original low-density real embryo image set to obtain a high-density embryo image set with high information density; when frame insertion is carried out, different frame numbers are inserted between two adjacent embryo images according to fission change intensity levels; the feature extraction module is used for respectively extracting features of the low-density real embryo image set and the high-density embryo image set and fusing the features; and the classification prediction module is used for inputting the fused features into a full connection layer for prediction to obtain a classification result. And laws changing along with time and space are extracted, and the classification accuracy of different splitting modes is improved by using the current laws.

To provide an information processing device, information processing method and information processing program for improving accuracy of classifying and organizing natural language used in business processes.SOLUTION: An information processing device includes: an acquisition unit for acquiring a document; an extraction unit that extracts, from the document, at least any of natural language, an item name with which the natural language is extracted, a business process and a document type; a reading unit that searches a document information table to determine whether information identical to and / or similar to at least any of the natural language, the item name, the business process and the document type is present in the document information table, and reads information from the document information table on the basis of a result of the determination; a registration unit that registers, in a data set, data of the natural language, the item name, the business process, the document type, a process classification and items having a dependency-correlation and / or an attribute-correlation with the item; and a document information storage unit for storing the document information table.SELECTED DRAWING: Figure 1

The present invention provides a method, a system and a rail vehicle for the management of outsourcing production of product processes, which are used for the outsourcing production of parts of the rail vehicle. The method includes: obtaining production orders of a plurality of the rail vehicles; querying the process based on the production orders to obtain outsourcing data; obtaining all process numbers based on the outsourcing data, wherein different process numbers are adopted for any different processes in terms of process description, process content and processing part; calculating the outsourcing standard price of each process based on the process classification and process parameters corresponding to all the process numbers; and forming the total outsourcing price based on the outsourcing standard prices of all processes. By numbering the outsourcing processes in the process, the present invention can quickly predict all the processes used in the outsourcing manufacturing in the process, and further quickly determine the total price of the outsourcing processes in combination with the process classification and process parameters, so as to provide a reference for the tendering work and reduce the outsourcing manufacturing cost.

The invention discloses a data index customized display system and method based on a graph editing engine, and relates to the technical field of data visualization and management, and the system comprises a business map module which is used for macroscopically displaying the process classification of company data assets and providing an entrance for jumping to a data map; the data map module is used for displaying a data asset structure and an association relationship in a specific business process in detail and supporting deep navigation and data viewing; and a graph editing engine module. According to the data index customized display system and method based on the graph editing engine, the problems that in an existing data asset visualization technology, a data asset panoramic structure cannot be visually displayed, data navigation and retrieval are inconvenient, interaction experience is poor, data dynamic updating is not timely and the like are solved, asset panoramic display is achieved, and the user experience is improved. The user can conveniently and quickly carry out data navigation and retrieval, the interaction experience of the user is improved, and deep data management and operation work of the system user is supported.

The application proposes a multi-target domain adaptive method based on contrast learning and self-correlation incremental learning, comprising: using a feature extractor to obtain contrast loss of source domain data and first target domain data respectively, and using a classifier to obtain cross-entropy loss of the source domain data; optimizing the contrast loss and the cross-entropy loss to align the source domain data and the first target domain data; based on the feature extractor after alignment, sharing weight parameters are performed to obtain the trained feature extractor and the classifier; a classification model for single-source target domain adaptive image classification is constructed to ensure the classification performance and classify the target domain. In each domain, the positive samples of the samples are obtained through data enhancement, and the other samples are negative samples, the source domain and the target domain are pulled closer by minimizing the contrast learning loss, the incremental learning module is added to ensure the domain-invariant knowledge learned to multiple target domains, and the self-correlation loss obtained from the source domain ensures the accuracy of the one-to-many process classification.

To provide an information processing device, information processing method and information processing program for improving accuracy of classifying and organizing natural language used in business processes.SOLUTION: An information processing device includes: an acquisition unit for acquiring a document; an extraction unit that extracts, from the document, at least any of natural language, an item name with which the natural language is extracted, a business process and a document type; a reading unit that searches a document information table to determine whether information identical to and / or similar to at least any of the natural language, the item name, the business process and the document type is present in the document information table, and reads information from the document information table on the basis of a result of the determination; a registration unit that registers, in a data set, data of the natural language, the item name, the business process, the document type, a process classification and items having a dependency-correlation and / or an attribute-correlation with the item; and a document information storage unit for storing the document information table.SELECTED DRAWING: Figure 1

The invention discloses a medical anomaly detection method based on graph language feature guidance. The method comprises the following steps: S1, acquiring medical image data and associated text description data; s2, extracting visual features of the medical image through a visual encoder of the CLIP model; extracting text features of the text description through a text encoder of the CLIP model; s3, segmenting the medical image into a plurality of image blocks, and constructing an image structure; graph structure features are extracted through a Vision GNN graph neural network, and local and global features are layered and aggregated by adopting a pyramid architecture; s4, the visual features and the graph structure features are aligned through a multi-stage feature adapter, and fusion features are generated; respectively processing the classification features and the segmentation features by adopting a double-branch architecture; and S5, in a zero sample mode and a few sample mode, a final anomaly detection result is obtained through weighted fusion.

The invention provides an out-of-distribution detection method and device of an image, electronic equipment and a storage medium. The method comprises the following steps: acquiring a to-be-detected image; extracting an embedded vector of the to-be-detected image; determining a detection result of each to-be-detected picture in the to-be-processed classification task according to the embedded vector, the classification list corresponding to the data in the text distribution and the classification list corresponding to the data outside the text distribution; wherein the classification list corresponding to the data in the text distribution and the classification list corresponding to the data outside the text distribution are constructed based on the data set in the distribution and the data set in the distribution respectively. According to the invention, the category of the to-be-detected image can be accurately judged according to the set judgment rule, and the over-confidence prediction of the traditional deep neural network on the out-of-distribution data is avoided, so that the reliability and accuracy of the model in a complex environment are improved. According to the method, the data in the text distribution and the data outside the text distribution are comprehensively considered, the data distribution characteristics are better captured, and a rich judgment basis is provided for out-of-distribution detection.