72 results about "Web tables" patented technology

The invention relates to a calculation task scheduling method and system considering the uncertainty risk of a data center. The task scheduling process of the data center is modeled based on the Markov decision process to obtain the task scheduling model, the task information and the electricity price serve as uncertain parameters, the decision process of task scheduling is represented by adopting the strategy network, and the risk of too high operation cost is measured based on the conditional value-at-risk. And embedding the conditional value-at-risk as a constraint into a reinforcement learning framework, optimizing the operation cost of the data center under the condition of ensuring the controllable risk, solving a task scheduling strategy through an improved strategy gradient algorithm fused with Monte Carlo sampling, training the task scheduling model, and obtaining a task scheduling result. Outputting a task scheduling strategy of the data center through the trained task scheduling model; task scheduling can be carried out according to the time-varying electricity price, the operation cost of the data center is reduced, risks caused by uncertainty can be sensed, and potential losses are avoided.

Systems and methods for supply chain network modeling and performance prediction are disclosed. In some embodiments, a disclosed method includes: receiving, from a computing device, a query associated with a supply chain network; representing the supply chain network as at least one graph based on historical transactions in the supply chain network; obtaining at least one machine learning model that is trained based on graph data related to nodes and edges in the at least one graph; generating, using the at least one machine learning model, supply chain prediction data based on the query; and transmitting the supply chain prediction data to the computing device.

The invention relates to the technical field of weather prediction, and discloses a weather prediction method based on an improved quantum long short-term memory network, which comprises the steps of inputting weather data into a CGRU model to perform spatial feature extraction on the weather data, and then inputting an output hidden state sequence into an HAQLSTM model to perform prediction, the HAQLSTM model is an improvement of a quantum long short-term memory network model, and the quantum long short-term memory network model is an improved quantum long short-term memory network model. A parameterized variable component sub-circuit is adopted, an attention mechanism and residual connection are added, a quantum long-short-term memory network serves as a time modeler, the residual connection enhances information transmission, the attention mechanism dynamically balances the importance of different parts of input data, in the processing process, a self-attention mechanism is adopted to calculate the correlation weight of input sequence elements, and the correlation weight of the input sequence elements is calculated. Four parallel parameterized variable component sub-circuits are used for carrying out key calculation so as to improve the model performance; the problems that an existing weather prediction model network is insufficient in expression ability, and the efficiency of capturing the long-term dependency relationship in the sequence is low are solved.

In order to manage virtual private cloud (VPC) network configuration, a network topology and configuration of each network element are firstly obtained, and then a reachability intention including a target function and an intention attribute is defined. In one embodiment, a network representation is generated that describes how traffic is processed in a network element through an operable filter function, and a minimization problem is defined by converting the network representation into a MaxSAT formula that is used to minimize the number of decision variables to be modified. And according to a target function, defining a decision weight for the decision variable, and obtaining a solution of a minimization problem through a MaxSAT resolution algorithm weighted by the decision weight to generate an optimized network configuration.

The invention discloses a tower crane automatic type selection and arrangement optimization modeling method based on a generative adversarial network, and belongs to the field of engineering construction management. Aiming at the problems of low efficiency and difficulty in coping with complex construction scenes in the traditional tower crane type selection and arrangement mode, the tower crane layout scheme is directly generated by inputting the construction drawings, so that manual information extraction is avoided, and the planning burden is obviously reduced. The GAN model is trained on a high-quality data set, and the feasibility of a generation scheme and the robustness of the model are improved through hyper-parameter optimization and application of a data enhancement strategy. The generative adversarial network shows higher efficiency, the calculation time is shortest, and the transportation time is optimal. Through numerical analysis and verification of an actual construction project, the method effectively overcomes complexity limitation of a traditional method, simplifies a data processing flow, provides an accurate and efficient solution for tower crane layout planning, and comprehensively improves planning decision scientificity and execution efficiency of the construction project.

The invention provides a data entry method and system of a Web table based on character recognition, and relates to the technical field of image processing. The method comprises the following steps: acquiring to-be-input image data; constructing a Web table data set according to the image data; according to the Web table data set, configuring filling fields and table styles of the Web table; selecting an anchoring field and an identification area according to a filling field and a form style of the Web form; selecting a corresponding Web table text recognition plug-in according to a filling field and a table style of the Web table; extracting text content from the recognition area of the image data through a Web table text recognition plug-in; and automatically filling the text content into corresponding fields of the Web table according to the anchoring fields to generate a filling form. According to the method, the time for manually inputting the text can be shortened, and the text inputting efficiency is improved.

The invention relates to the technical field of data query, in particular to a data query method based on a graph convolutional network. The data query method based on the graph convolutional network comprises the following steps: constructing an extraction and multi-layer semantic network of heterogeneous data; generating a multi-layer topology network conversion and layered topology sequence; performing semantic matching; matching sub-graphs embedded based on a GCN path; and carrying out structure matching and isomorphism verification. According to the method, heterogeneous data is organized into hierarchical network representation of an entity relation, an attribute relation and a time sequence relation through construction of a multi-layer semantic network, original semantic information of the data is reserved to the maximum extent, meanwhile, in combination with a semantic matching and topology verification technology based on a graph convolutional network, the method can flexibly capture complex semantic association, and the method has the advantages of being simple in structure and convenient to operate. According to the method, the expression ability and the query precision of the data are remarkably improved, and a brand new technical path is provided for efficient management and utilization of the heterogeneous data.

Systems and methods for creating chatbot-enabled web forms and workflows, the method comprising, mapping web forms and workflows to intents, wherein the web forms have required fields to be completed and the workflows have required tasks to be performed; mapping the required fields and the required tasks to entities for the intents that map to the web forms and the workflows; mapping utterances to complete the required fields and perform the required tasks to the intents and the entities that map to the web forms and the workflows; and creating chatbots configured to assist users to complete the required fields and perform the required tasks using the utterances, the intents and the entities that map to the web forms and the workflows.

Transmissions in a data center communications network are monitored at a sending computer, the transmission of data packets being controlled by control messages sent by a receiving computer. The monitor at the sending computer measures the time that a burst of data takes to be transmitted from the sending computer to the receiving computer. Based on feedback received from the receiving computer, the monitor at the sending computer calculates one of more estimated completion times for the transmission. The estimated completion times will approximately match the measured completion time if the network is not the bottleneck for communication. When there is a mismatch between the estimated and measured completion times, this is logged and the information is used to trigger analysis to detect the reason and possible causes for the network under-performing.

The invention provides a method for repairing retention time violation. The method comprises the following steps: acquiring a network list and a layout result of an FPGA (Field Programmable Gate Array); the network list comprises a connection relationship between the target sending unit and the target receiving unit, and the layout result comprises respective layout coordinates of the target sending unit and the target receiving unit; the target sending unit and the target receiving unit are driven by the same time signal; based on the respective layout coordinates of the target sending unit and the target receiving unit, evaluating the path time delay of the connection path by using a static time sequence analysis tool; and when the path time delay is smaller than a path time delay threshold value, adding an unused lookup table of at least one FPGA into the connection relation, and on the premise of not changing a layout result, determining respective layout coordinates of the at least one unused lookup table based on the layout result so as to repair retention time violation of the connection path. Therefore, the retention time violation of the connection path can be quickly repaired by adding the unused lookup table of the FPGA in the layout stage.

Insight summary and prompt generation techniques are described. In one or more examples, a plurality of insights is generated from data extracted from digital content. A network representation is produced having a plurality of nodes based on the plurality of insights and a plurality of connections between corresponding insights. A selection is received of a subset of nodes from the plurality of nodes. A prompt is formed by grouping respective insights from the subset of nodes. An insight summary of the digital content is generated based on the prompt using generative artificial intelligence as implemented using one or more machine-learning models. The insight summary is then presented for output in a user interface.

The invention provides a video recommendation method and device based on dynamic bipartite network representation, and relates to the technical field of data processing. The method comprises the following steps: intercepting a plurality of bipartite network snapshots according to a set time interval in a set time period, and filling virtual nodes in other bipartite network snapshots according to the bipartite network snapshot with the maximum scale; acquiring a processed bipartite network snapshot and an adjacent matrix formed by splicing user nodes and project nodes, and capturing explicit features of the nodes; wherein the user node is a user account in the social media platform; the project nodes are videos in the social media platform; obtaining the processed bipartite network snapshots and the explicit features of the nodes, and capturing the implicit features of the nodes in the bipartite network snapshots; the explicit features and the implicit features of the nodes are expressed through low-dimensional vectors, and the low-dimensional vectors are partially stored in a cache region; and generating a video recommendation scheme for the user based on the low-dimensional vector representation of the node. The accuracy of the recommendation result can be improved.

The invention discloses an intelligent fault tree generation method based on cooperation of a multi-modal large model and a large language model, and relates to the field of fault tree analysis. In order to solve the defects of low tree building efficiency, insufficient cross-modal information processing and incomplete fault causal chain reasoning in the prior art, the technical scheme provided by the invention comprises the following steps: carrying out topological structure analysis on a system flow chart by adopting a multi-modal large model to obtain an equipment network table; taking the equipment network list as input, and performing fault mode directional retrieval on the equipment information base by adopting a large language model to obtain a fault mode list; taking the equipment network list and the fault mode list as input, performing failure reason reasoning by adopting a large language model, and establishing a fault causal chain from a system layer to an equipment layer; and taking the fault causal chain as input, constructing a fault tree by adopting a large language model, and generating a complete fault tree structure from a system top event to an equipment basic event. The method is suitable for safety and reliability analysis work of a complex industrial system.

Disclosed in the present application are a supply chain planning method, an apparatus, a computer device and a storage medium. Specifically, the disclosed supply chain planning method comprises: receiving information of an stock keeping unit and information of facilities; receiving information of activities, the information of the activities comprising the information of the stock keeping unit and the information of the facilities; and, according to the information of the stock keeping unit, the information of the facilities and the information of the activities, generating nodes and arcs to form a supply chain planning network, the nodes and the arcs respectively containing the number of the activities and decision variables of a traffic. In this way, supply chain planning can be abstracted into three different object layers and then, according to actual service requirements, constraint and object configuration are performed so as to form a network expression of the supply chain planning, such that a subsequent supply chain planning optimization result can be calculated as a reference for actual decision making.

Examples of the present disclosure describe systems and methods for state-based entity behavior analysis. In an example, entities of a computing environment may be represented using a hierarchical entity web. In some examples, an entity may have a state associated with it, which may be modeled using a place / transition (PT) network. Events within the computing environment may be evaluated by transitions of a PT network to determine whether an entity should change state. If an entity transitions from one state to another, one or more actions may be performed, including, but not limited to, taking a remedial action, generating a recommendation, and updating the state of one or more associated entities. Thus, aspects disclosed herein may provide a high-level overview of the state of entities of a computing environment, but may also be used to view in-depth information of entities at lower levels of the hierarchical entity web.

The present invention provides, for example, a highly convenient manufacturing network processing system. A manufacturing network processing system (100) is provided with a processing unit (51) that causes a terminal device (60) to display a manufacturing network in which a process by which components are assembled or materials are processed sequentially to complete a prescribed product is represented by a tree-structured network. Each node of the manufacturing network is associated with an item code for a component or material serving as a constituent element of the product. Each branch of the manufacturing network is associated with a drawing code of a drawing used for assembling the components or processing the materials. When there is a prescribed inconsistency in the manufacturing network, the processing unit (51) causes the terminal device (60) to display a notification screen (601) for the inconsistency.

Embodiments of the present application provide a representation method, a speech recognition method, a device and an electronic device. The representation method comprises: obtaining to-be-processed data, wherein the to-be-processed data is one of the following: to-be-processed speech data, to-be-processed text data, and to-be-processed image data; obtaining a feature vector generated after feature extraction is performed on a data vector corresponding to the to-be-processed data; performing conversion processing on the feature vector by using a filter to obtain a triple used for self-attention calculation, wherein the triple comprises a query vector, a key vector, and a value vector; and performing self-attention calculation according to the query vector, the key vector, and the value vector to obtain a corresponding network representation. Through the technical solution provided in the embodiments of the present application, the number of parameters corresponding to the self-attention mechanism can be directly reduced, and then the number of parameters of the neural network using the self-attention mechanism can be reduced, that is, the memory occupied by the neural network is reduced, which is conducive to the popularization of the neural network.

The application discloses a dense pedestrian target detection method based on an improved YOLOv11, and realizes efficient detection of dense pedestrians by constructing an improved YOLOv11 model. The method first collects a dense pedestrian dataset and performs image preprocessing, and then constructs the improved YOLOv11 model. The specific improvement steps are as follows: the GhostConv module is used to replace the ordinary convolution in the backbone network, the redundant information in the feature map is reduced, and the calculation cost is reduced, so that the model is lightweight; the C3K2 module is replaced by C3K2-WTConv, the convolution receptive field is expanded, the low-frequency information in the image is effectively captured, and the dense target detection effect is significantly improved; the lightweight MLCA attention mechanism is introduced into the C2PSA module to form a new C2PSA-MLCA module, and the local and global information are combined to enhance the network expression ability. After the model construction is completed, training, testing and performance evaluation are performed. The application realizes model lightweight, improves the accuracy of target detection, and is suitable for traffic monitoring and safety monitoring in public places.

The embodiment of the invention discloses a network sub-health state simulation method and device, a distributed storage system, a distributed storage node, a storage medium and a computer program product. Receiving a simulation type for network sub-health state simulation input by a user and a first simulation parameter corresponding to the simulation type; performing simulation processing corresponding to the simulation type on a data transmission link aiming at a second node based on the first simulation parameter through a second module deployed in the second node of the distributed storage cluster; wherein the second node is a node needing network sub-health state simulation; through a third module deployed in the second node, collecting a simulation result generated by the second module in the processing process; wherein the simulation result represents the network performance of the distributed storage cluster.

The invention belongs to the technical field of artificial intelligence, and relates to an artificial intelligence-based risk assessment method and device, computer equipment and a storage medium, and the method comprises the steps: carrying out the preprocessing of collected face image data of a user, and obtaining standardized face data; performing feature extraction on the standardized face data to obtain visual features and semantic features, and fusing the visual features and the semantic features to obtain target face feature representation; processing the target face feature representation based on a contour expert network, an expression expert network and a comprehensive expert network to obtain a first risk assessment result, a second risk assessment result and a third risk assessment result; and based on the gating network and the target face feature representation, performing comprehensive calculation on the first risk assessment result, the second risk assessment result and the third risk assessment result, and generating a Parkinson risk assessment result of the user. The Parkinson risk assessment method can be applied to a Parkinson risk assessment scene in the medical field, and the accuracy of Parkinson risk assessment is effectively improved through the Parkinson risk assessment method.

Machine learning systems and methods for computer modeling and optimization of telecommunications networks are provided. The system processes information relating to a telecommunications network, such as a cellular telephone network, and generates a directed network graph that represents the network as a series of connected edges and nodes with associated attributes such as transmitter power, antenna tilt, radio resource control information, handover attempts, collisions, and other parameters. The network graph is stored in a graph database, and is processed by one or more network graph model inference modules which apply one or more specially-trained artificial intelligence (AI) models to the network graph to generate an optimized version of the network graph that can be utilized to improve the telecommunications network. A modeling visualization interface is also provided, and allows users of the system to visualize modeling and optimization performed by the system.

Examples of the present disclosure describe systems and methods for state-based entity behavior analysis. In an example, entities of a computing environment may be represented using a hierarchical entity web. In some examples, an entity may have a state associated with it, which may be modeled using a place / transition (PT) network. Events within the computing environment may be evaluated by transitions of a PT network to determine whether an entity should change state. If an entity transitions from one state to another, one or more actions may be performed, including, but not limited to, taking a remedial action, generating a recommendation, and updating the state of one or more associated entities. Thus, aspects disclosed herein may provide a high-level overview of the state of entities of a computing environment, but may also be used to view in-depth information of entities at lower levels of the hierarchical entity web.

The application discloses a Web table abnormal data discovery method based on a text semantic mapping relationship. The application aims at discovering abnormal data with fuzzy or even wrong semantic information in a Web table. The method mainly comprises three parts: a semantic representation module, a column type inference module and an error discovery module. First, the semantic representation module represents the meaning of cell text. For a cell in a table, the string text in the cell is represented as a semantic vector according to context information. Then, the column type inference module infers the type of the column where the cell is located, and obtains the mode information of the column. Finally, based on the mapping relationship between the column type and the semantic vector of the cell text of the main column cell and the target cell, abnormal data in the table is discovered and labeled.

The invention provides an information detection method and device, electronic equipment, a computer readable storage medium and a computer program product. The information detection method and device are applied to various mold penetrating detection scenes such as cloud technology, artificial intelligence, intelligent transportation and games. The information detection method comprises the steps that attention processing is carried out on initial image features of a to-be-detected image, to-be-detected image features are obtained, and the to-be-detected image is an image of a virtual object model; performing through-mold detection on the to-be-detected image features to obtain a first through-mold detection result; based on the image semantic information of the to-be-detected image, an element graph network is constructed, and the element graph network represents a semantic relationship between image elements in the to-be-detected image; performing mold penetrating detection on the element graph network to obtain a second mold penetrating detection result; and combining the first mold penetrating detection result and the second mold penetrating detection result to obtain a target mold penetrating detection result of the to-be-detected image. According to the invention, the accuracy and efficiency of mold penetration detection can be improved.

Embodiments of the present application disclose an information display method and apparatus. The main technical solutions include: displaying a media playback page on which media content is being played; a first entry is displayed in the media playback page, and the first entry is an entry for viewing the full picture of an event. By triggering the entry for viewing the full picture of the event, a set of full picture information corresponding to the media content is displayed; the set of full picture information includes: the context development information of the event, the online attitude information of the event, and the hot meme creative information of the event. The present application can directly trigger the display of the set of full picture information of the event corresponding to the media content in the media playback page, and the user does not need to leave the current media playback page or jump to other pages, which simplifies the user operation, improves the user's instant experience, and enhances the interactivity between the user and the media content.

The present application belongs to the field of computer and online social network, and particularly relates to a propagation network reconstruction and prediction method combined with multiple types of dynamic social relationship. A social relationship representation method is provided in the present application, which represents social relationship by using a multi-layer social network, and the multi-layer social network G includes a relationship topology network corresponding to multiple relationship types one by one; the relationship topology network includes network nodes corresponding to users one by one, and edges of the relationship topology network are used to represent relationship strength between users. The social relationship representation method provided in the present application uses a multi-layer graph neural network to describe various different types of social interaction features. The present application comprehensively considers multi-level, multi-type social relationship and information propagation characteristics, and is suitable for various different complex social networks.

Systems and methods are disclosed for identifying a set of internal edges on a representation of a network that satisfy a set of demands on the network. The disclosed systems and methods perform a multi-step process of selecting the internal edges. In a first step, an initial set of internal edges can be selected using a clique graph (or in another suitable manner). In a second step, a second set of internal edges can be selected using stream graph(s) (or in another suitable manner). The second set of internal edges can be used when determining network paths that satisfy the demands. When the representation of the network has a cut of two, the disclosed systems and methods can identify a set of internal edges providing a degree of protection against link failure.

Systems and methods for diversifying k-shortest path computation results for multiple vertices as destination or as inclusion constraint include receiving a request for k paths, in a network from a source port at a source node to a node, wherein the node includes a plurality of ports; representing the network as a graph with vertices representing ports, edges representing connections between the ports, and with weights assigned to each of the edges; assigning a dummy destination vertex to connect to each of the plurality of ports and associated edges between each of the plurality of ports and the dummy destination vertex having a same weight; determining up to the k paths between the source port and the dummy destination vertex, and, subsequent to the determining each of the k paths, assigning a corresponding edge of the associated edges in each of the k paths a predetermined value.