14 results about "Structure chart" patented technology

The invention relates to the technical field of artificial intelligence and flight training, and particularly discloses an intelligent training method and system for consciousness of a pilot. The method comprises the following steps: constructing a multi-modal flight scene and an original task structure chart, and extracting a flight task target and a semantic tag set; guiding a pilot to carry out natural language expression, collecting a voice stream and combining a task stage to align a text; comparing the language expression with task semantics by using a language model, and identifying expression differences; generating a feedback statement based on the difference, and pushing the feedback statement to the pilot; updating a task flow and reconstructing an execution script; finally, training records are counted, the capacity label weight is updated, and a capacity growth trend graph is generated. According to the method, accurate identification of pilot task understanding deviation and language expression defects can be realized, a scene training process dynamically adaptive to a cognitive state is constructed, and scene awareness and language expression ability of a pilot are remarkably improved.

The invention is suitable for the technical field of machine tool precision design, and provides a five-axis numerical control machine tool complete machine space error sensitivity analysis method, which comprises the following steps: abstracting a numerical control machine tool into a multi-body system based on a multi-body system theory, describing the incidence relation between the structure of the machine tool and each individual by using a topological structure chart and a low-sequence body array list, and calculating the overall space error sensitivity of the five-axis numerical control machine tool. The geometric error of the numerical control machine tool is analyzed, a generalized coordinate system is established, the position relation is expressed by using the characteristic matrix between adjacent bodies, the mutual relation between multiple body systems is expressed by using a homogeneous transformation matrix, and a space error model of the machine tool is established; and in combination with a space error model of the machine tool, an improved Sobol global sensitivity analysis method is provided, a first-order sensitivity coefficient and a global sensitivity coefficient are solved, and key geometric errors of the numerical control machine tool are analyzed. By establishing the space error model of the numerical control machine tool and the improved Sobol global error sensitivity analysis model, a new design and improvement concept of the numerical control machine tool is provided, and the problem of machining precision of the numerical control machine tool is solved.

The invention relates to the technical field of document processing, in particular to a multimedia document online editing method and system.The method comprises the following steps that image-text coordinates and difference values are obtained to generate a path sequence, labels and attributes are matched to construct a structure chart, paths are compared to generate offset identification, editing information is collected to extract a trigger sequence, and synchronous deviation is calculated to generate a task index. And reconstructing the sequence to generate a rearrangement result. According to the method, the logic structure is constructed through the image-text coordinate difference and the offset path, the combination state change is accurately judged in combination with the angle and distance change, the time sequence and label characteristics in the editing behavior are collected, the operation link is established, the time sequence consistency of content recombination is improved, and the task synchronization rhythm is calculated through the delay and response difference. According to the method, the rhythm control of content loading is realized, the combination sequence is reconstructed according to the logic distance, the continuity and accurate positioning after structure rearrangement are kept, and the stability and response efficiency of a multimedia document in a complex editing scene are enhanced.

The invention relates to the technical field of computers, and provides a code analysis detection method and system based on a large language model. The method comprises the following steps: deploying an analysis engine on a code detection platform, analyzing a code snippet programming normal form, and constructing a structure chart based on a code element and a context relationship; defining a detection direction according to the structure chart, and introducing gating constraints under multi-layer progressive detection; and based on the detection direction and gating constraint, performing directional distillation on the large language model, performing analysis detection in combination with the structure diagram and the code snippets, and determining a detection result. According to the method and the device, the technical problem of frequent leak detection and false alarm caused by the fact that code context and multi-level detection dimensions cannot be fully considered when code snippets are processed by a traditional code analysis method is solved, and the aim of improving the detection accuracy of the code snippets by introducing directional distillation processing based on a large language model and a gating constraint mechanism is achieved. Potential vulnerabilities and optimization points in the codes are accurately identified, and the accuracy and efficiency of code detection are improved.

The embodiment of the invention provides a community discovery method based on a structure chart. The method comprises the steps that a community graph is initialized based on a structure graph, and communities are represented by entity vertexes and have community attributes; each community is added with an atomic lock; a plurality of threads are adopted to execute a plurality of rounds of first graph iteration in parallel, and the current round of graph iteration executed by any first thread comprises the steps that for any first entity vertex processed by the first thread, all target communities to which all neighbor entity vertexes meeting a preset relation with the first entity vertex belong are determined, and after atomic locks of all the target communities are obtained, the first entity vertex is processed by the first thread; determining whether the first entity vertex needs to move or not according to the community attribute of each target community, updating the community attribute of the related community when the first entity vertex needs to move, and releasing the atomic lock after updating; and aggregating the entity vertexes in any community into a new entity vertex representing the community according to the community attribution of the entity vertexes after a plurality of rounds of first graph iteration so as to update the community graph.

The embodiment of the present invention discloses a data screening method, device, computer equipment and storage medium. The method includes obtaining multiple shopping lists, obtaining a transaction data set according to the shopping lists; finding a two-item frequent set from the transaction data set using the Apriori algorithm; calculating the support and confidence of each two-item set in the two-item frequent set, and constructing an association structure graph between commodity nodes according to the support and confidence of the two-item set; obtaining the node feature vector in the association structure graph; inputting the association structure graph and the node feature vector into a GCN model for convolution classification, and outputting the classification result. The present invention screens out commodities with an association relationship, then constructs an association structure graph between commodities, then performs high-level feature extraction on commodities with an association relationship, and then implements data screening and classification through a GCN model. It has the advantages of accurate classification, optimizes the classification process, reduces the scale of classification data, and reduces the complexity of classification calculation.

The embodiment of the invention discloses a power grid equipment transportation method and device, electronic equipment and a computer readable medium. A specific embodiment of the method comprises the steps of obtaining a power grid equipment data set; generating at least one power grid equipment association structure chart; performing structure chart verification on each power grid equipment association structure chart to generate a verification result; in response to determining that the verification result represents that the verification is correct, storing the at least one power grid equipment association structure chart and the at least one query element in a predetermined format; in response to the received target query demand information, performing information analysis on the query demand information to generate a query element information set; screening out a power grid equipment association structure graph set; generating a summarized power grid equipment association structure chart; displaying the target demand map; a power transport operation is performed. According to the embodiment, at least one piece of corresponding power grid equipment information can be inquired rapidly and efficiently according to the equipment inquiry requirement of the target user, so that efficient transportation of electric power is realized.

The invention provides an information detection method, device and equipment, a medium and a program product, which can be applied to the technical field of artificial intelligence. The information detection method comprises the following steps: acquiring a social network structure chart and to-be-detected information; performing feature extraction on the to-be-detected information to obtain a semantic feature vector; constructing multiple groups of cue words based on the to-be-detected information and the social network structure chart, and performing propagation graph simulation based on the multiple groups of cue words to obtain a propagation graph representing a propagation path of the to-be-detected information; feature extraction is carried out on the propagation graph to obtain a propagation graph feature vector, and the propagation graph feature vector represents structure information of the propagation graph and behavior information of the user nodes; and inputting the semantic feature vector and the propagation graph feature vector into a trained prediction neural network to obtain a detection result of the to-be-detected information.

To provide a system.SOLUTION: A system comprises: means for receiving and analyzing organization chart data of a company; means for arranging in each section, a generative AI coping with each section in the company indicated by the analyzed organization chart data; means for connecting the arranged generative AI through a network for sharing information in the respective section; means where the generative AI processes the data in the respective sections of which the generative AI takes charge, for generating information related to management of the company; and means for summarizing the generated information related to management and outputting the same.SELECTED DRAWING: Figure 1

The invention provides an intelligent manufacturing digital twinning whole process management and control method and platform based on a swan gap system, and the method comprises the steps: constructing a process structure chart according to a manufacturing process, and collecting operation parameters through a state collection port; and constructing a current state vector of each node according to the operation parameters, and obtaining an operability mark of each node according to the precursor node set, the current state vector and a state linkage rule. The node of the operable mark is defined as a target node. And generating a plurality of candidate control strategies of each target node according to the strategy parameter template, the current state vector and the current equipment margin. And obtaining a cost evaluation value of each candidate control strategy according to the cost function. The candidate control strategy corresponding to the minimum cost evaluation value is defined as a target control strategy. And sending the target control strategy to a controller for execution. The whole-process modeling capability with the process dependency relationship as the framework is achieved, and when the production line rhythm or the equipment load changes, the scheduling logic can also be automatically adapted accordingly.

The invention relates to a circuit layout method and device, equipment, a storage medium and a program product. The circuit layout method comprises the following steps: searching a repetitive unit group with the same topological structure as that of a layout template in a circuit topological structure chart, wherein the repetitive unit group comprises a plurality of circuit units; multiple repetitive unit groups corresponding to the same layout template are aggregated into independent layout units, and the multiple repetitive unit groups corresponding to the same layout template have the same relative position relation between circuit units after layout; and carrying out layout on the independent layout units. The layout design efficiency is remarkably improved, layout errors caused by manual operation are avoided, and the layout design accuracy is improved.

The application discloses a kind of ship structure standardization design data analysis methods based on AI, comprising the following steps: using unlabeled data to carry out bimodal self-supervised pre-training to HGT, through geometric attribute cover prediction and edge existence prediction, loss is optimized jointly;Obtain the labeled ship structure chart data;Parallelly embed error transmission module in pre-training model, obtain final cumulative error;The labeled data is input into the HGT after embedding error transmission module, calculate size prediction loss, assembly constraint loss, and obtain fine-tuning model by optimizing jointly;Target structure chart data is input into fine-tuning model, and each node design size prediction value and tolerance band are output;Standardized design data is generated.The application realizes the efficient reuse and construction process cooperation of ship structure design data, and improves the design standardization degree and engineering adaptability.

The invention belongs to the technical field of computers, and discloses a software development project management method and system based on an incremental model, and the method comprises the steps: receiving external change data, mapping the external change data into a target node in a structure chart based on the structure chart of a preset software system, and calculating the structural stability parameter of the target node, judging whether a preset structure change threshold value is reached or not, if so, marking the node as a fission trigger node, and outputting an identifier and adjacency information; fission trigger nodes and adjacency information are received, based on the structure diagram, a structure splitting function is used for executing sub-diagram cutting operation on the affected area, different structure sub-diagrams are constructed, and a structure sub-diagram set and corresponding sub-diagram function information are output; mapping the sub-graph function information to a unified function expression space through a preset function semantic mapping rule, and outputting a unified function expression vector group and a corresponding cooperative relationship matrix; and the overall execution efficiency of the project and the resource use efficiency are improved.

The invention relates to the technical field of software engineering, in particular to a source code fault positioning method based on heterogeneous decoupling and gating fusion, which comprises the following steps of: establishing a unified coverage graph based on a to-be-tested program code, a test code and a result of performing automatic test by utilizing the test code; decoupling the unified coverage graph to obtain a code structure graph and a test coverage graph; encoding the test coverage graph and the code structure graph by adopting a heterogeneous graph neural network, and performing dynamic test embedding and static structure embedding on each node; dynamic test embedding and static structure embedding of the nodes are spliced, and final comprehensive embedding of the code nodes is obtained through gating information spreading; performing full-connection linear layer processing on the final comprehensive embedding of each code node, and outputting a suspicious degree score; the suspicious degree scores of all the nodes are arranged in a descending order to serve as a fault positioning result; the method can improve the fault positioning effect of the graph neural network.