33 results about "Operational decision" patented technology

Examples relate to an adaptive AI coworker system for enhancing organizational operations. The system generates personalized AI coworkers based on role requirements, employing adaptive learning to understand unique organizational practices. It utilizes multi-agent coordination for complex task execution, automatically generating, prioritizing, and allocating tasks based on organizational context. The system integrates data from various sources, implementing data governance measures. Customized large language model instances are created for specific roles and organizations, incorporating organization-specific data and operational practices. The system provides explainable AI features for operational decision-making, ensuring transparency in critical tasks. Security measures and access controls are implemented to maintain data integrity and compliance with relevant regulations and standards.

The invention discloses a heat supply unit deep peak regulation and heat supply optimization operation method based on multi-mode collaboration, and particularly relates to the technical field of thermal power generation and heat supply, and the method comprises the steps of S1, system modeling and parameter identification, S2, thermoelectric load prediction, S3, multi-objective optimization solution, S4, operation decision and feedback, and S5, data agent mapping acceleration. According to the method, the thermoelectric load is accurately predicted through mechanism and data dual-drive modeling, and based on the target of maximizing the economic benefits of the whole plant, the optimal cooperation scheme of multiple operation modes such as heat supply, power supply and deep peak regulation is dynamically solved by utilizing the multi-target optimization algorithm on the premise of ensuring the safety of the unit, so that the power supply efficiency is improved. Finally, production is guided through an online decision-making and closed-loop feedback system, and safe, economical and flexible operation of the unit under the working condition of deep peak regulation is achieved.

An adaptive air intake control system and method for cooling towers, coupled with airflow diversion for energy saving, belongs to the field of adaptive control system technology. The system includes an information acquisition unit, an execution unit, and an adaptive control unit. The information acquisition unit collects environmental wind parameters and key operating parameters in real time. The execution unit includes multiple independent fan blade groups with circumferential partitioning and vertical layering for precise execution of commands. The adaptive control unit executes operational decisions, selecting the dominant operating mode from airflow diversion energy saving, anti-freezing energy saving, and anti-drip energy saving modes; it then identifies and outputs wind condition characteristics and thermal anomaly indicators through key parameter status identification, and generates control commands based on the adaptive control strategy and command generation. The system forms a closed loop, capable of adaptively adjusting the identification model and control strategy based on feedback. A corresponding control method is also disclosed, enabling intelligent and precise control of air intake in cooling towers under complex environments, improving cooling efficiency and energy saving while ensuring anti-freezing safety.

The invention discloses a thermal power enterprise operation decision result generation method, device and equipment, and relates to the technical field of energy optimization, and the method comprises the steps: collecting production operation data, fuel purchase data, inventory management data and other multi-mode operation data, and carrying out the preprocessing to obtain standardized data; and inputting the data into a preset management and control model, generating a prediction result and a scheme, and generating an operation decision result through comprehensive analysis in combination with a preset warning threshold. According to the method, the multi-modal data is input into the management and control model formed by combining multiple models, the multi-dimensional result is generated, and the final operation decision result is obtained through comprehensive analysis in combination with the threshold value, so that deep integration and analysis of the multi-modal data of the thermal power enterprise can be realized, the data utilization efficiency is improved, and the scientificity and the accuracy of operation decision are improved.

This invention provides an intelligent power distribution system and its intelligent control method based on operational decision-making and control. The method includes: S1. Standardized partitioned deployment of modular intelligent power distribution cabinets and mapping configuration of sensing-control-communication full-link units; S2. Full data entry and structured parsing of business rules and safety control boundary constraints for electricity consumption scenarios; S3. Full-link multi-source heterogeneous operational data processing based on an improved grey relational analysis preprocessing algorithm with dynamic time curvature; S4. Dynamic operational decision generation based on an improved multi-objective antlion optimization algorithm; S5. Hierarchical execution of control commands adapted to multiple scenarios and full-process status traceability. This invention realizes standardized modular deployment, full-link safety control, intelligent energy and water conservation, and closed-loop optimization of data-decision-rules in power distribution systems. It is suitable for the power distribution and energy consumption control needs of various industries such as KTVs, hotels, and restaurants, improving the intelligence, safety, and energy-saving level of power distribution systems.

This invention discloses a method, system, equipment, and medium for predicting railway freight volume, relating to the field of railway freight technology. The method includes: acquiring target data, which includes target historical railway freight volume data and target historical railway freight-related data. The target historical railway freight-related data consists of target historical data corresponding to multiple target influencing factors related to railway freight volume, and the target influencing factors are factors that have a direct or indirect impact on railway freight volume; inputting the target data into a pre-constructed target railway freight volume prediction model to obtain the predicted railway freight volume value corresponding to the target data. This invention solves the problem that existing railway freight volume prediction methods do not consider the impact of influencing factors related to railway freight volume on railway freight volume and the relationships between these factors, resulting in low prediction accuracy and limiting and lagging operational decisions for railway freight enterprises.

Techniques for improving operational decisions of an autonomous vehicle are discussed herein. In some cases, a system may generate a lane change score based on one or more lateral metrics and one or more longitudinal metrics associated with the lane change trajectory. The system may then determine if the lane change operation is safe based on the lane change score.

This application provides an intelligent management system for integrated sports fields. By organically combining user terminals, sensing and execution devices, edge computing servers, and a cloud management platform, it constructs a full-link intelligent management system covering "user interaction - data collection - local real-time processing - cloud-based in-depth analysis." Addressing pain points in traditional sports field management such as cumbersome reservations, delayed status perception, and insufficient data support, this system utilizes edge computing and local AI model deployment to achieve real-time response to local events, avoiding response delays caused by cloud transmission latency. Simultaneously, it leverages the big data analytics capabilities of the cloud platform to provide data support for operational decisions. This combination satisfies both the immediate needs of on-site management and the decision-making requirements of macro-operation, thereby comprehensively improving the management efficiency and service quality of integrated sports fields and realizing intelligent collaboration among "people, equipment, venues, and data" in sports scenarios.

The invention relates to the technical field of bulk commodity operation, in particular to a data sharing and analysis method and system based on multi-dimensional association, and the method comprises the steps: collecting multi-source heterogeneous data through a mixed mode of interface synchronization and manual reporting, and quantifying an unstructured text into a standardized index through a bidirectional LSTM semantic analysis algorithm; a cosine similarity and grey relational degree fusion algorithm and an LSTM dynamic weight optimization model are adopted, association rules are mined in combination with an improved Apriori algorithm, and market pre-judgment is achieved through three sub-models of supply and demand, price and risk; and finally, establishing a closed-loop mechanism, and outputting an inventory adjustment scheme and a futures hedging strategy. The system correspondingly comprises four functional modules, full-process data processing and decision support are achieved, and scientificity and operability of operation decision are improved.

The invention discloses a reservoir operation data suspicious value identification method and system fusing a sliding window 3 sigma statistical criterion and physical mechanism verification. The method comprises the steps that a reservoir operation data distribution rule is deduced; trying and determining the length of a sliding window for screening suspicious values; performing suspicious value primary screening based on a sliding window; carrying out secondary screening on suspicious values based on differential characteristics; multi-source data collaborative verification based on a physical mechanism; finally confirming a suspicious value; the system comprises an acquisition module, a trial calculation module, a primary screening module, a secondary screening module, a judgment module and a confirmation module. According to the method, the quantitative relation among the reservoir inlet flow, the reservoir water level and the reservoir outlet flow is verified through the water balance principle law, so that whether the statistical suspicious data really violates the physical law or not is distinguished, the misjudgment risk caused by a pure statistical method is avoided, and the suspicious data screening accuracy and reliability are further improved; and a solid foundation is laid for subsequent data cleaning and operation decision making.

The present application relates to the technical field of low-altitude aircraft scheduling, and particularly relates to a low-altitude aircraft cluster task scheduling method and system based on big data, which comprises the following steps: generating a predicted delivery time length through a time sequence feature hybrid model based on historical data of a low-altitude aircraft distribution big data platform, wherein the time sequence feature hybrid model is constructed based on LSTM and Transformer network architecture; constructing an operational decision model with the optimization objective of minimizing the average of multiple predicted delivery time lengths and the decision variable of order allocation mode; and solving the operational decision model based on a multi-objective search strategy to determine the order allocation mode of the low-altitude aircraft cluster. The present application realizes the balance between instant response and global efficiency in low-altitude aircraft cluster scheduling, improves the adaptability of dynamic delay scheduling strategy, and improves the delivery efficiency and reduces the overtime rate.

This invention discloses a mechanism- and data-driven root cause diagnosis method and system for industrial production lines. The method includes: acquiring and preprocessing multi-source heterogeneous industrial data from the production line; performing anomaly detection on the preprocessed multi-source heterogeneous industrial data, identifying abnormal time windows, and extracting multimodal anomaly data; constructing a three-level hybrid diagnostic model and generating a preliminary root cause candidate set based on the model's diagnostic output for the multimodal anomaly data; performing source tracing analysis on the preliminary root cause candidate set and generating a structured natural language diagnostic report based on the source tracing analysis results. This invention significantly improves the accuracy and generalization ability of root cause diagnosis across a wide range of scenarios by constructing a three-level hybrid model architecture. Furthermore, through source tracing analysis and natural language extension, it provides a structured report supported by clear physical logic and data evidence, thereby improving operational decision-making efficiency, reducing reliance on scarce domain experts, and significantly reducing unplanned downtime.

This application provides a drilling simulation system and method based on a desert scenario. The system establishes a data-driven relationship between environmental parameters and equipment performance models through a coupling processing module. This allows dynamic environmental data to influence the values ​​of virtual equipment performance parameters through mathematical rules, thereby simulating the continuous impact of the environment on equipment status. Addressing the issue that macroscopic environmental simulation output data cannot be used for real-time operational simulation, the data generated by the environmental simulation module is real-time and can be directly used as calculation input for the coupling processing module and the effect simulation module, achieving compatibility with operational simulation. Furthermore, through equipment performance status, the environmental impact is simultaneously transmitted to the physical interaction level and the operational decision-making level. This transforms environmental factors from isolated external conditions into core variables that drive the simulation process and shape training difficulty. Therefore, it can significantly improve the simulation effect of drilling operations in extreme desert environments.

The invention discloses a dynamic and static combined evaluation method and device for the operating efficiency of a power grid enterprise. The method comprises the following steps: constructing a power grid enterprise operating efficiency evaluation index system; constructing a power grid enterprise operation efficiency static evaluation model based on the power grid enterprise operation efficiency evaluation index system; the static evaluation model is a power grid enterprise total factor production efficiency static evaluation model based on a DEA-BCC model; calculating a comprehensive technical efficiency value of each decision-making unit in a certain period through a static evaluation model, and reflecting the resource utilization efficiency of a power grid enterprise in a given period; based on the power grid enterprise operation efficiency evaluation index system, constructing a power grid enterprise operation efficiency dynamic evaluation model; the dynamic evaluation model is a power grid enterprise total factor production efficiency dynamic evaluation model based on a Malmquist index, and the dynamic evaluation model measures the dynamic change of the power grid enterprise total factor production efficiency; the method can make up the defects of current research, and provides reference for the operation decision of a power grid enterprise.

The invention provides a supply chain toughness evaluation method and device based on an agent complex network, and the method comprises the steps: enabling each company node in a conventional supply chain network model to serve as an agent, enabling each agent to be provided with a perception sub-agent, a decision sub-agent and an execution sub-agent, enabling each node to be provided with the capability of autonomously perceiving, making a decision, and then carrying out the execution, company entities in a supply chain network are abstracted into intelligent agent models with perception, decision and execution capabilities, business exchange of the company entities is abstracted into connecting edges in a complex network, and through an interaction mechanism between intelligent agents, each company entity node in the supply chain network model has a dynamic characteristic; and the change of the operation decision of the company entity can be made according to the dynamic characteristics, so that a balance can be quickly achieved after disturbance, and the toughness evaluation can be quickly and accurately performed on the state of the supply chain network.

1. The name of the design product: graphical user interface of electronic device management decision. 2. The use of the design product: the design product is used for electronic device. 3. The design points of the design product: the graphical user interface content in the screen, the display screen panel is the existing design; the "XX" area in the interface is the editable text content, and the single color block in the interface is the variable content picture. 4. The picture or photo that best shows the design points: front view. 5. The electronic device is a common design, and the rear view, left view, right view, top view and bottom view are omitted. 6. The use of the graphical user interface: the design product is used for information display. 7. The human-computer interaction mode of the graphical user interface: in the front view, clicking any one row of specific index name can enter the interface change state diagram.

This invention provides a method and equipment for park operation decision analysis, relating to the field of smart park operation management technology. The invention constructs a candidate solution scenario library through structured definitions of covariates and intervention variables, covering various operational intervention scenarios to be evaluated; relying on generative causal Bayesian networks to integrate causal inference and generative modeling capabilities, it achieves reliable causal prediction of counterfactual solutions without historical observation data; it outputs predicted effect values ​​and uncertainty indicators to quantify prediction credibility and decision risk; in high-uncertainty hypothetical scenarios, through proactive surveys and incremental updates, it achieves effect prediction of counterfactual and hypothetical solutions to assist decision analysis, reduce investment risk and decision costs, and improve the robustness and efficiency of operational decisions. This invention addresses the problem of unreliable prediction and difficulty in proactive decision-making for counterfactual and hypothetical solutions without historical data in park operations, achieving a closed-loop, end-to-end park operation decision analysis.

The invention discloses a financial institution customer value hierarchical operation system and method based on big data, particularly relates to the field of financial customer operation management, and is used for solving the problem that structural association and multi-cycle behavior change among customers are difficult to reflect due to static hierarchical results in the existing customer value hierarchical management process. According to the method, the client association network with the time sequence weight among the clients is constructed, the potential communities of the clients are identified, the community structure vulnerability is evaluated, and the network structure risk is mapped to the client level to obtain the client network value gain; meanwhile, trend decomposition is carried out on the multi-cycle transaction behaviors of the clients, and behavior stability indexes are constructed. On this basis, a two-dimensional customer value layering matrix is constructed, dynamic layering of customer values is realized, and a targeted operation strategy is generated according to historical operation benefits of adjacent layered customer groups, so that the accuracy of financial institution customer value identification and the scientificity of operation decision are improved.

The invention relates to the technical field of big data analysis and supply chain capacity management, in particular to an enterprise intelligent operation decision support system based on big data, which is characterized in that a supply chain data acquisition unit acquires a one-week capacity decrease value and a fluctuation period identifier caused by raw material delay in real time; a fluctuation characteristic analysis unit generates a fluctuation amplitude grade identifier through continuous interval threshold matching, analyzes a period identifier to obtain a continuous period characteristic, and packages the continuous period characteristic into structured data; the dynamic fusion processing unit fuses real-time productivity, same-period historical fluctuation and global historical productivity mean data according to two dimensions of grades and periods, and distributes differentiation weights; and the reference capacity generation unit is based on real-time data, superposes historical capacity change trend coefficients, and outputs a dynamic reference capacity value retaining instantaneous fluctuation characteristics through global mean smooth calibration, so that reliable support is provided for an enterprise to formulate a distribution plan matched with the actual capacity of the current week, and the operation decision scientificity is improved.

An Enterprise-Oriented Cloud Control System is disclosed for providing time-sensitive, vehicle-specific guidance and control instructions to autonomous vehicles (AVs) in long-tail corner cases. The system operates through an enterprise-oriented cloud intelligent unit (E-CIU) that integrates service, management, communication, sensing, prediction, planning, control, and support subsystems. Automated driving scenarios are classified by a traffic fence based on demand and supply characteristics. The E-CIU receives multi-source event and non-event data from vehicles, roads, clouds, and centers, offers various “as-a-service” functions, and employs event models to convert macroscopic event data into microscopic operational data. These models generate cooperative sensing, prediction, planning, and control solutions and produce customized, real-time instructions for longitudinal / lateral motion and operational decisions. An onboard unit exchanges information with the E-CIU and executes cloud-generated commands, providing effective management of AVs in rare and complex scenarios.

The invention discloses a merging unit error self-monitoring method, system and device, a storage medium and a program product, and relates to the technical field of data processing, and the merging unit error self-monitoring method comprises the steps: obtaining high-frequency sampling data; performing error related feature extraction based on the high-frequency sampling data to obtain error evaluation features; and performing error classification and trend prediction based on the error evaluation features to obtain an error type and an error trend. According to the method, error related feature extraction is carried out by acquiring high-frequency sampling data, so that inherent calculation errors caused by insufficient sampling are reduced, and meanwhile, the problem of low recognition precision caused by simple threshold comparison is avoided; through prediction of the error trend, advanced risk prediction of the error condition is realized, and richer and more predictive information support is provided for operation and maintenance decisions. By constructing a progressive perception decision-making system, high-precision and real-time self-monitoring of various errors is realized in a merging unit, and the use cost of the system is reduced.

This invention relates to a substation comprehensive situational awareness and fault simulation system and method, belonging to the field of substation safe operation technology. The technical solution involves: first, constructing a refined digital twin of the substation connected to real-time / historical data streams; second, importing the twin model into the GE GridOS platform to form a data-simulation hybrid closed loop synchronized with the physical station; and finally, based on this hybrid closed-loop system, achieving real-time, dynamic, and cross-scale panoramic awareness of the substation's operating status, as well as immersive simulation, intelligent diagnosis, and recovery plan verification for pre-set or sudden faults. This invention moves from post-event presentation to pre-event prediction, enhancing the initiative and depth of situational awareness, constructing a simulation environment with primary-secondary-grid panoramic interaction, achieving realistic reproduction and in-depth diagnosis of fault processes, optimizing the scientific nature of operational decisions and emergency response, and establishing a dynamic calibration mechanism for models and data to ensure the long-term accuracy of the digital twin.

Methods and systems are presented for assisting the making of operational decisions for an aircraft, the method being performed by three computers during a current task. The first computer (C1) automatically determines a technical state of the aircraft, a minimum equipment list, one or more affected MEL items, and one or more applicable scheduling conditions for each item from the fault information. The second computer (C2) automatically determines the proposed scheme (including selection of scheduling conditions for each affected MEL item in the case of scheduling according to one or more MEL items) from previous items provided by the first computer and a set of future tasks to be allocated in the aircraft fleet. A third computer (C3) receives a decision from the pilot to accept or reject the proposed scheme and, in the event of acceptance, triggers the completion of some tasks in the aircraft and updates the log.

This invention discloses a device and method for real-time intelligent parsing of NOTAMs. The device is used to: continuously receive real-time NOTAM messages from an upstream system or gateway interface and store them in their original form, ensuring uninterrupted reception through 24 / 7 monitoring; perform preliminary and detailed decomposition of the NOTAM messages, wherein the detailed decomposition process utilizes targeted algorithms based on various rules mined from NLP annotation training results to achieve refined structure parsing of the messages; store the structured parsing results and provide them to other business systems through an interface; and simultaneously perform route impact analysis on target type messages to extract the value of the notification data. This invention, through intelligent NOTAM message parsing and deep processing, significantly improves the efficiency and value of aviation intelligence utilization, providing auxiliary support for airline operational decision-making and safety management.

This invention discloses an enterprise-side situational awareness method based on distributed dynamic data processing using AI agents. Distributed AI agents collect and preprocess multi-source dynamic data from the enterprise, then break down complex situational awareness tasks into executable sub-tasks and send them to the AI ​​Agent task routing module. The AI ​​Agent task routing module deeply interacts with a large language model to complete sub-tasks such as semantic understanding and risk rating, inference decision-making and rule optimization, knowledge alignment and graph generation. The inference results are returned to the distributed AI Agent and synchronized to a multi-AI Agent collaboration and situational fusion module for distributed data fusion. Finally, through multi-AI Agent collaborative situational awareness analysis, enterprise-side situational awareness results are generated and output, achieving efficient processing and accurate situational awareness of multi-source dynamic data, providing real-time support for enterprise operational decisions.

The invention discloses an operation decision optimization and insurance charging method under multiple disaster risks of a wind power plant, and particularly relates to the technical field of new energy risk management and intelligent operation and maintenance. Mapping the real-time prediction output of the physical field evolution model as a dynamic load to an equipment vulnerability curved surface, calculating the damage probability of a unit, carrying out spatial interpolation and topological aggregation in combination with geographic coordinates and electrical topology, generating a unit-level dynamic risk map, identifying a risk unit, splitting and reconstructing a power transmission channel, and carrying out power transmission. Performing power adaptive redistribution on the online unit according to the reconstruction capacity and the predicted wind speed to form an operation strategy; and aggregating the unit-level damage probability into a comprehensive risk exposure index, fitting an expected loss cost in combination with a historical power generation efficiency baseline, dynamically adjusting a basic insurance rate, and generating a differentiated insurance billing factor linked with an operation strategy.

The invention discloses an enterprise resource dynamic allocation method based on reinforcement learning, and relates to the technical field of enterprise resource management and dynamic scheduling, and the method comprises the following steps: S1, collecting and preprocessing resource state data in real time; s2, extracting a real-time hidden state feature vector based on an RNN model; s3, constructing a PPO model, and initializing a PPO strategy network and a value function network; s4, calculating a dominant function value according to an improved GAE algorithm, and updating parameters of the PPO strategy network and the value function network by using the dominant function value; s5, dynamically generating a resource allocation decision scheme; and S6, performing real-time feedback and iterative optimization. According to the method, the limitations of dependence on manual decision, insufficient distribution precision and response delay in a traditional enterprise resource dynamic distribution method are overcome, and an efficient and accurate solution is provided for enterprise intelligent resource optimization and operation decision.

This invention relates to an operational decision-making system for determining the process mode and regulating parameters of a biological treatment pond, comprising: a parameter input module for acquiring operational parameters; a parameter processing module for acquiring first data based on the operational parameters; a process mode determination module for acquiring the actual internal carbon source denitrification rate and the theoretical maximum internal carbon source denitrification rate of the biological treatment pond under test and determining the process mode of the biological treatment pond under test; an internal carbon source denitrification relationship analysis module for acquiring all permutations and combinations of operational regulation parameters under the target internal carbon source denitrification rate when the process mode tends to undergo denitrification mainly based on enhanced internal carbon source denitrification and has optimization space; and a first scenario parameter regulation module for acquiring the suitable process mode for the biological treatment pond under test under the current water quality and the regulation range of the optimal permutation and combination of operational regulation parameters under the mode; this invention effectively improves the precision and intelligence level of wastewater treatment.

The invention discloses an operation decision prediction method, device and equipment based on multi-modal time sequence data, relates to the technical field of intelligent monitoring, and can solve the technical problems of low prediction efficiency and low accuracy of manual operation decision at present. The method comprises the following steps: determining historical equipment monitoring data and historical real operation decisions corresponding to each preset historical time point; training an initial operation decision prediction model according to historical equipment monitoring data and the historical real operation decision to obtain a trained operation decision prediction model; equipment monitoring data corresponding to a current time point of a current time period and each non-current time point and a real operation decision corresponding to each non-current time point are obtained, and a target operation decision is obtained through prediction according to the equipment monitoring data, the real operation decision and the operation decision prediction model, the current time period comprises the current time point and all the non-current time points.

This invention discloses a data processing method and system based on a business management platform, specifically relating to the field of advertising placement business management technology. It addresses the problems of difficulty in anomaly attribution and low decision-making efficiency caused by isolated dimensional data in existing systems. The method involves synchronously acquiring channel-level click volume and touchpoint-level blacklist interception volume. When channel click volume abnormally decreases, it extracts the corresponding channel-related blacklist interception logs and product-level conversion rates. Based on the interception logs, it verifies the intensity of user behavior path topology distortion and decision manifold tightness caused by the blacklist strategy. When the distortion intensity exceeds a threshold or the tightness falls below a threshold, it backtracks the advertising exposure user path of the corresponding channel product. It analyzes the temporal correlation between blacklist interception nodes and product exposure nodes in this path to generate a candidate root cause set. It detects the direction of product conversion rate fluctuations during abnormal periods and determines the root cause from the candidate set accordingly, significantly improving the efficiency and accuracy of operational decision-making.