60 results about "Tree diagram" patented technology

The invention discloses a large model reasoning method and system based on tree diagram and knowledge graph retrieval enhancement, and the method comprises the steps: segmenting a document into text blocks, recognizing the entities, relationships and factual descriptions of the text blocks, and forming a knowledge graph of the text blocks; constructing a factual summary of the documents based on the knowledge graph of the text blocks, and performing clustering recursion on all the documents by using a Gaussian mixture model to generate a similarity tree structure graph; the method comprises the following steps: obtaining a user problem, selecting a reasoning path from a similarity tree structure diagram through a large language model debate iteration method, obtaining a corresponding document cluster, pruning the cluster based on the user problem and a confidence score of a document, selecting a plurality of text blocks from the pruned document, and finally obtaining a knowledge graph based on the selected text blocks. And generating a reasoning result. The invention relates to the technical field of natural language processing, can realize retrieval enhancement based on a tree diagram and a knowledge graph, and accurately queries related information when a large model answers a complex multi-hop question, so that the reasoning accuracy is effectively ensured.

The invention discloses a power system scheduling and optimizing method and system based on a multi-granularity tree diagram neural network. The method comprises the following steps: step 1, constructing a power grid state sample data set; 2, performing graph representation and feature extraction on the power grid data; step 3, constructing a hierarchical multi-granularity power grid information coarsening model; 4, constructing a power grid information graph disturbance model; step 5, constructing a tree neural network adaptive path selection model; and step 6, according to the multi-granularity tree neural network model, executing explanation and scheduling decisions of the power system. According to the method, graph network structure characteristics of a power system are considered, a power grid is modeled into graph data, and on the basis of an existing graph neural network model, a multi-granularity graph coarsening module, a learnable disturbance module and a self-adaptive path selection module are introduced to construct a tree-shaped model of a multi-layer structure; therefore, the state and representation of the power system of each granularity level, such as global and local scale in different ranges, are analyzed, and the prediction accuracy of the model and the interpretability of the decision are improved.

The invention discloses an intelligent archive information security protection method and system, and belongs to the technical field of information security protection. The method is used for solving the technical problem that the reliability and interpretability of an algorithm for archive information security protection in an existing scheme cannot be actively supervised and optimized. Initial weight distribution of sensitive levels is realized through an analytic hierarchy process, the Bayesian network quantifies the influence degree of real-time risk factors, weights are dynamically adjusted in combination with time attenuation factors, finally, a multi-dimensional archive information security risk assessment model capable of being dynamically optimized is constructed, an explicit logic basis is provided through rule reasoning, and an archive information security risk assessment model is established. A machine learning model quantifies a risk probability and explains key features, multi-source information is fused through a D-S evidence theory, finally, a decision path is tracked through a visual tree diagram, and multi-dimensional improvement of risk identification accuracy-decision transparency-system adaptability is realized through adaptive parameter adjustment and closed-loop optimization of an abnormal response strategy.

The invention provides a photovoltaic power station intelligent monitoring system and method based on a dynamic weight tree diagram and edge-cloud collaboration, and relates to the technical field of photovoltaic power station intelligent monitoring, and the method comprises the steps: obtaining environment parameters such as illumination intensity and temperature of a photovoltaic power station, and equipment operation state data such as voltage and current; calculating and adjusting the dynamic weight of each monitoring index in real time according to the illumination / temperature deviation condition and the equipment health state; a multi-level tree diagram is constructed based on the dynamic weight, the upper layer represents the overall operation state of the power station, the lower layer represents a subsystem evaluation result, and the node priority and the hierarchical structure are synchronously updated; the edge computing node preliminarily processes abnormal data, uploads data conforming to a threshold value and adjusts a local control strategy; and the cloud platform issues optimization model parameters after deep diagnosis, and iteratively updates the dynamic weight calculation model. According to the invention, the fault false alarm rate is effectively reduced, and the fault detection precision and response efficiency of the photovoltaic power station in a complex environment are improved.

The invention provides a large-scale knowledge graph visualization method and system, and relates to the field of knowledge graph visualization. The method comprises the following steps: acquiring knowledge graph data, and clustering the knowledge graph data through a modularity-based discovery algorithm; obtaining each sub-graph corresponding to the clustered knowledge graph data, and for each sub-graph, selecting a representative node based on a PageRank algorithm or a Leader Rank algorithm; carrying out force-oriented layout on the clustered knowledge graph data through a tree diagram space filling technology; and for the knowledge graph data subjected to the force-oriented layout, distributing priorities and use times of a Barnes-Hut algorithm and a random vertex sampling algorithm according to a preset mode, and dynamically displaying a visualization result in a layered manner through an affine transformation technology. According to the method and the device, the problem that the structural expression clarity of the drawn knowledge graph is greatly reduced due to the fact that semantic clusters and hierarchical organizations in the graph are difficult to accurately present in a traditional visualization method is solved.

The invention provides a power distribution network low-voltage transformer area topology identification method based on tree diagram coding representation, and belongs to the technical field of power distribution networks, and the method comprises the steps: S1, carrying out the identification of a user phase of a low-voltage power distribution network based on the Kirchhoff's current law, and converting the three-phase topology identification into single-phase identification; s2, expressing the topological structure of the low-voltage power distribution network through the tree diagram, and coding based on the expressed tree diagram; s3, calculating an impedance matrix based on a gradient descent method; s4, defining optimization indexes of user node voltage and prediction deviation; and S5, optimizing in the potential topological space through a genetic algorithm, and outputting an optimal low-voltage power distribution network topological structure. According to the method, the potential topological structure of the low-voltage power distribution network is represented on the basis of tree diagram coding, the deviation between the predicted value and the measured value of the user node voltage is directly used as an optimization index, complete topological identification of the low-voltage power distribution network can be achieved, and the method has high accuracy.

The embodiment of the invention discloses an operation method of a learning type index tree graph. The method is applied to a key value separation storage system, a learning type index tree graph is newly added to the key value separation storage system, each node in the tree graph comprises a linear model, a public prefix and an entry list, and the entry list is composed of empty entries, data entries and node entries. Data entries store key suffixes and positions of corresponding values in a value log area of the key-value separation storage system, and node entries are associated with child nodes. The learning type index tree graph is constructed according to a preset process. The instruction content in the operation instruction can be processed after construction; and performing addition, deletion, modification and query operations on the learning type index tree graph according to the instruction content, wherein the operations comprise point query, range query, addition, deletion and modification operations. The indexing mechanism of the key-value separation storage system has the following technical effects: firstly, the indexing mechanism has an accurate positioning capability; 2, the incremental updating capability is realized; and thirdly, the processing capability of indefinite long bonds is realized.

A text segmentation and sensitive word detection method based on matrix multiplication, comprising the following steps: obtaining an original text string and a sensitive word library; constructing a deterministic finite state automaton tree diagram of sensitive words according to the sensitive word library; converting the original text string into a text character two-dimensional matrix and recording the length of the text character two-dimensional matrix; constructing a matching two-dimensional matrix according to a horizontal matching rule, a vertical matching rule, an oblique matching rule and an inverse oblique matching rule, the length of the matching two-dimensional matrix being the same as that of the text character two-dimensional matrix; performing dot multiplication processing on the text character two-dimensional matrix and the matching two-dimensional matrix to obtain a corresponding result matrix; generating a corresponding matching text string according to the result matrix, and matching with the deterministic finite state automaton tree diagram to determine whether there is a sensitive word. The application supports interval text character information detection, improves the sensitive word detection accuracy and detection efficiency.

An information processing apparatus includes: an acquisition unit configured to acquire a plurality of tracks; a tree drawing unit configured to draw a tree diagram with the tracks as nodes; and a group editing unit configured to edit a plurality of tracks that are shared in a group including a plurality of users and are derived from a certain track in such a way that the plurality of tracks are not open to an outside of the group. The group editing unit selects one or more public tracks to be open to the outside of the group from among the plurality of tracks edited in such a way that the plurality of tracks are not open to the outside of the group, and the tree drawing unit draws the tree diagram based on the one or more public tracks selected by the group editing unit.

The present application discloses a method and device for detecting abnormal access data. The method includes: determining a business parameter tree diagram corresponding to the business access data of the target business; assigning values ​​to multiple dimensional features in the target branch in the business parameter tree diagram to obtain a target business parameter matrix model; extracting multiple feature values ​​of the business access data at the current moment, adapting the multiple feature values ​​to multiple target feature values, and generating an adaptation result; when the adaptation result is inconsistent with the target result, determining that the business access data has abnormal access. The present application solves the technical problem of a high false alarm rate in business access data detection caused by too few feature dimensions to be compared with the detected business access data.

The invention relates to the technical field of data analysis, and provides an error analysis method and system, electronic equipment and a storage medium, and the method comprises the steps: carrying out the preprocessing of to-be-analyzed data, and obtaining an attribute vector; based on the analysis path, identifying errors in the attribute vector to obtain an error identification result; carrying out error classification on the error identification result, analyzing true errors in an error classification result, and determining error causes; and displaying the error reasons to obtain an error map, and displaying the analysis process of the true error in the form of a tree diagram to obtain an analysis map. The method supports a user to customize an analysis path, can improve the flexibility of error analysis and meet the requirements of the user, can improve the efficiency and accuracy of error analysis by classifying error recognition results and focusing on analysis of true errors, and can improve the accuracy of error analysis by displaying an error map and an analysis map. A user can more intuitively and quickly position the error reason, so that the analysis efficiency is improved.

The present application discloses a method, device and electronic device for generating a flowchart, which can be applied to the field of big data or the field of finance. Extract key node information and the correlation relationship between key node information from target business information, connect the key node information according to the correlation relationship, obtain an initial flowchart, convert the initial flowchart into a tree diagram according to the preset flowchart conversion rule, and determine whether the nodes in the tree diagram meet the pruning rules. If so, hide all branches connected to the nodes that meet the pruning rules to obtain a flowchart. That is, the present invention can automatically connect the key node information according to the correlation relationship to obtain an initial flowchart, which can simplify manual operations and improve accuracy compared to manual methods. In addition, all branches connected to the nodes that meet the pruning rules are hidden, and branches with lower usage frequencies can be hidden, so as to optimize the flowchart and improve user experience.

The invention relates to a signal sorting method and device based on a tree diagram, and computer equipment, and the method comprises the steps: determining a father-child node relation between pulse data points based on the local density of a pulse signal and the distance measurement of a nearest pulse with a larger local density, thereby constructing a tree diagram, obtaining a clustering center in a self-adaptive manner, and carrying out the self-adaptive clustering of the clustering center; and then distribution of residual pulse data points is carried out, so that automatic clustering and sorting of pulse signals are realized. According to the method, the clustering center can be adaptively estimated, the method is suitable for any cluster shape, non-uniform-density pulse signal sorting is effectively achieved, and the sorting performance is superior to that of an existing method.

The invention discloses a hydraulic loading device multi-fault diagnosis method based on a decision tree algorithm. The method comprises the following steps: firstly, preprocessing imported data; secondly, for a multi-channel time sequence signal, extracting time domain statistical characteristics of each sample and each channel; then carrying out standardization processing on the extracted time domain statistical features; a decision tree algorithm is adopted, a Gini coefficient is used as a standard, optimal split features and threshold values are selected at each layer and divided, recursive growth is started from a root node, and a discrimination tree of various typical faults of the hydraulic loading device is obtained through training; after training is completed, tree nodes are traversed, and a complete discrimination path is formed from the root to each leaf; finally, the judgment path and the threshold condition are converted into a tree diagram, the relation between the features and the fault category is visually displayed, and the interpretability is improved. According to the method, feature construction, decision tree analysis and rule tree visualization are integrated for multi-channel time sequence data, and the interpretability of a diagnosis result is improved.

The embodiments of this specification provide a method and a device for sequence processing using a neural network. In the sequence processing method, in the generation layer, the original vector sequence corresponding to the indicator sequence formed by the business indicator values ​​sorted by time is obtained, and multi-level vector aggregation is iteratively performed on the original vector sequence to obtain multi-level processing vector sequences corresponding to different time scales. The original vector sequence and each vector in each processing vector sequence form a multi-level tree relationship diagram. In the attention layer, according to the tree relationship diagram, the association vector of any input target vector is determined, and the target vector is subjected to weighted comprehensive processing based on the attention mechanism according to the association vector to obtain the corresponding update vector; the update vector is used to determine the feature representation of the indicator sequence.

The present disclosure relates to a bridge information processing method, device, equipment and storage medium. The method comprises: determining a plurality of structure information corresponding to a plurality of bridge structures in the bridge, and a plurality of component positions corresponding to a plurality of bridge components in each bridge structure; for each bridge structure, generating a component identifier corresponding to each component type in the bridge structure according to the assembly information and the component detail information, and assigning the component identifier to the corresponding bridge component according to the component type and the component position; determining a plurality of component models according to the component types corresponding to a plurality of bridge components, and adding the plurality of component models to the corresponding component positions to obtain a bridge model corresponding to the bridge; establishing a component tree diagram of the bridge according to the component identifier, and associating and displaying the component tree diagram and the bridge model. Thus, the belonging relationship of the bridge components is intuitively displayed through the component tree diagram, and the unified collaborative management of information is realized.

The invention discloses a method for automatically checking the integrity of a command receiving point of a dispatching command based on a tree diagram, which is applied to the technical field of rail transit and comprises the following steps of: constructing a tree diagram model of a sub-diagram through a retrieval method, a pruning method and a branching method in combination with a connection relationship of the sub-diagram (namely a dispatching sub-section); after a dispatching command is received, command receiving point information and a station sequence are analyzed, an expected station sequence is determined in combination with sub-graph connection relation information provided by the tree diagram model and the command receiving point information, integrity verification is carried out on the analyzed station sequence, the verification process is not limited by a dispatching command template any more, and the verification efficiency is improved. While the verification accuracy is improved, a train dispatcher is allowed to respond to emergencies more quickly, errors caused by human factors such as fatigue, negligence or subjective judgment are reduced, and technical support is provided for safe and compliant operation of a train dispatching system.

This invention discloses a preoperative risk prediction method for cerebral aneurysms based on multimodal deep learning. To address the problems of time-consuming computational fluid dynamics simulations and difficulty in quickly obtaining individualized hemodynamic indicators, this invention reconstructs vascular geometry and a tree diagram by aligning computed tomography angiography, magnetic resonance angiography, and blood pressure and heart rate time series. It employs a graph network that satisfies Kirchhoff conservation and connects differentiable Wendt-Kessel impedance learning boundary conditions. Combining physical constraints of cardiac phase conditional neural operators, Helmholtz projection, and signed distance function boundary embedding, it approximates the flow field, calculates and closes the loop to correct wall shear stress, oscillatory shear exponent, and pressure gradient. Then, it fuses the risk features of the imaging branch, clinical branch, and text branch through expert product to output lesion-level and patient-level risks and confidence levels. This achieves the technical effect of rapidly estimating hemodynamics and performing interpretable preoperative risk assessment under physically consistent constraints.

The application discloses a network slice method based on data clustering, and comprises the following steps: firstly, a plurality of user data are acquired, the characteristics in the user data are normalized, and corresponding threshold values are set; it is judged whether the characteristic values are greater than the corresponding threshold values; if yes, 1 is assigned; if no, 0 is assigned; secondly, the characteristic frequent occurrence times of each characteristic are defined as the total times of the characteristic values being 1 in single user data, and the characteristic frequent occurrence times of each characteristic are obtained by scanning the user data; then, the minimum characteristic frequent occurrence time is set, the characteristics with the characteristic frequent occurrence times less than the minimum characteristic frequent occurrence time are deleted, and the remaining characteristics are arranged according to the characteristic frequent occurrence times; a tree diagram is constructed according to the arranged characteristics, frequent item sets are found in the tree diagram, and a normalized hypergraph is made; finally, the strong correlation between the characteristics is judged by using the obtained hypergraph, and a network slice resource allocation scheme is made. The application can reasonably, efficiently and fairly allocate the network slice resources.

The application relates to a power data attack tracking and tracing method and system. The method comprises the following steps: acquiring an abnormal node of a power system, determining an initial attack path of the power system according to the abnormal node, determining a tree diagram corresponding to the initial attack path, wherein the tree diagram comprises at least one tree diagram node, modifying the tree diagram according to a node parameter of the tree diagram node, and determining a target attack path of the power system according to the modified tree diagram. The method can improve the accuracy of power data attack tracking and tracing.

The invention belongs to the technical field of data processing, and particularly relates to an automatic generation method for a construction information description file of a port and a storage medium. S2, a parameter extraction stage; s3, a parameter filling and file generating stage; s4, a similarity calculation and tree diagram generation stage; according to the method for automatically generating the construction information description file for the port, parameters are extracted from different target files by using corresponding extraction algorithms, and then the parameters are automatically filled into corresponding positions of a set template, so that the workload of manually inputting the parameters is reduced in the process, the information processing efficiency is improved, and the workload of manual operation is reduced. Meanwhile, the extracted parameters are automatically filled into a template to generate a descriptive file, so that the information is presented in a structured form, subsequent storage, query and management are facilitated, and in addition, the structured information organization mode is beneficial to improving the readability and availability of the information.

The invention provides a community detection method and system based on a probability distribution hierarchical graph clustering network, and the method comprises the steps: carrying out the preprocessing of to-be-processed graph data based on a graph convolution network, extracting the node features of all nodes in the to-be-processed graph data, and determining the similarity between all nodes based on the node features; determining the probability distribution of each node based on the similarity, clustering each node to a corresponding affiliation community based on the probability distribution, and constructing a multi-level community tree diagram based on a clustering result; and carrying out refined division on communities of the multi-level community tree diagram based on the model loss function, and completing community detection on each node in the to-be-processed diagram data based on a refined division result. According to the community detection method and device, accurate and reliable community detection is carried out on each node, the accuracy of community detection is guaranteed, the community detection effect is greatly improved, and great convenience is provided for understanding of functions and characteristics of a network.

To easily present information on content included in composite content.SOLUTION: The content management device includes an acquisition unit that acquires content posted by a user and system information indicating a system of a plurality of pieces of content connected in a tree shape, and a display composition unit that generates a display screen including a tree diagram visually indicating the system of the content connected in the tree shape to be displayed when the content or the composite content is distributed to the user on the basis of the system information. A content management device includes an acquisition unit that acquires content posted by a user and additional information related to the content, a statistics unit that performs statistics of the additional information for each user and outputs the additional information as performance information of the user, and a display composition unit that generates a display screen including the performance information.SELECTED DRAWING: Figure 12

The application discloses a tree diagram and knowledge graph retrieval enhanced large model reasoning method and system, which comprises the following steps: cutting a document into text blocks, identifying entities, relationships and factual descriptions of the text blocks to form a knowledge graph of the text blocks; constructing a factual summary of the document based on the knowledge graph of the text blocks, recursively clustering all documents using a Gaussian mixture model to generate a similarity tree structure diagram; obtaining a user question, selecting a reasoning path from the similarity tree structure diagram through a large language model debate iteration method, obtaining a corresponding document cluster, then pruning the cluster based on the user question and the confidence score of the document, and selecting a plurality of text blocks from the pruned document, and finally generating a reasoning result based on the knowledge graph of the selected text blocks. The application relates to the technical field of natural language processing, and can realize retrieval enhancement based on a tree diagram and a knowledge graph, accurately query relevant information when a large model answers a complex multi-hop question, and effectively guarantee reasoning accuracy.

This application discloses a programmable data processing method and system for multi-level users, involving power plant scheduling and data processing technologies. The method includes: constructing a tree diagram based on collected multi-source data; configuring the displayable node range for users at each user level; and dividing the displayable node range into the smallest data elements according to the tree diagram; setting default display methods and associated operations for any data element based on the semantic tag set for users with different permissions; monitoring changes in user permissions or node status to trigger corresponding decision scenarios, thereby instantiating a view within the decision scenario. The VDF is a set of data element query and assembly rules to achieve view instantiation after VDF execution. By introducing a semantic tag set, decision scenarios, and dynamic VDF execution, the method solves the problems of event flow situation awareness and the balance between permission security and user experience in existing technologies.

The invention discloses a zero-sample Chinese character recognition method based on radical structure tree graph level representation, and belongs to the technical field of Chinese character recognition. The method comprises the following steps: establishing a Chinese character database and constructing a directed radical structure tree of each Chinese character from top to bottom; adding direction position codes to nodes in the tree to distinguish the spatial relationship of brother nodes; inputting the radical structure tree with the direction and position codes into a GraphSAGE-based tree encoder to obtain normalized vector representation of the Chinese characters; extracting vector representation of the sample image by using ResNet; aligning the Chinese character vector and the image vector through comparative learning; and finally, zero sample recognition is realized by calculating the similarity between the to-be-recognized image and all candidate Chinese character vectors, and the highest similarity is selected as a recognition result. According to the method, the structure perception capability is improved through the directed tree, fine-grained spatial differences are perceived through directional coding, and the recognition capability of the model on unseen Chinese characters is effectively improved.

A method for modeling a digital power generation and transformation equipment includes the following steps: Step 1: Establishing an instantiated power plant structure model: referencing KKS coding rules and dictionaries, and automatically generating an equipment KKS coding tree based on the selected plant template; Step 2: Associating with physical equipment; Step 3: Configuring equipment information; Step 4: Configuring the tree diagram; Step 5: Determining whether to update the instantiated data based on notifications of new standards and standard changes; Step 6: Importing and exporting the power plant system equipment coding table. This invention provides a digital modeling method for power generation and transformation equipment that is open and extensible, allowing for flexible expansion based on the characteristics of different power generation and transformation equipment. It is applicable to digital model calculation and analysis fields such as power generation and transformation equipment status trend prediction and fault diagnosis.

The invention provides a method and system for automatically generating a movie script and a movie abstract, and relates to the technical field of computers. After a target movie video is obtained, a key frame set, a voice transcription text and a character action recognition result are extracted from the target movie video, a visual feature vector is extracted from the set, a scene segmentation scheme with the minimum total bit cost is searched in combination with a preset scene division principle, and the target movie video is segmented into a plurality of scenes; extracting a target actor information image from the video clip containing the actor table to generate a first corresponding relation and a second corresponding relation, and further generating a target format script and a scene list of each target scene; generating a tree diagram according to the scene, and processing to obtain a plot summary and a database; based on the target format script and the database, the story outline is generated, and the movie script and the movie abstract are generated in combination with the scene list, so that the movie script and the plot abstract which are logically coherent, rich in information and matched with the visual content are automatically generated.

The invention relates to the technical field of medical research and development, in particular to a cost-reducing and efficiency-increasing drug development scheduling system, which comprises a data classification module, a data analysis module and a development scheduling optimization module, the time sequence features and the data features are deeply fused to construct multi-dimensional distribution features, development data of the same type are judged, a distributed storage technology is adopted for classification, and a hash value is allocated to each storage node; the data analysis module performs standardized processing on different types of development data, defines the development data as standard data, and judges whether the standard data have correlation or not; the development scheduling optimization module perceives the standard data with correlation to construct a standard tree diagram; and perceiving the development tree diagram, mapping and comparing the standard tree diagram, and if difference nodes exist in the development tree diagram and the standard tree diagram, calculating the influence degree.

The invention relates to a power data attack tracking and tracing method and system. The method comprises the following steps: acquiring an abnormal node of a power system, and determining an initial attack path of the power system according to the abnormal node; determining a tree diagram corresponding to the initial attack path; the tree diagram comprises at least one tree diagram node; according to the node parameters of the tree diagram nodes, correcting the tree diagram; and determining a target attack path of the power system according to the corrected tree diagram. By adopting the method, the accuracy of power data attack tracing can be improved.