116 results about "Decision quality" patented technology

The invention relates to the technical field of enterprise management, in particular to an intelligent decision support system and method based on cognitive logic and scenarized semanteme, and the method comprises the steps: obtaining enterprise decision data through multi-source data monitoring, carrying out the preprocessing, and generating cross-modal enterprise scene cognitive information; analyzing cross-modal association among the data, fusing a cognitive logical reasoning rule and a semantic understanding model, and constructing scenarized semantic decision fusion features; training an enterprise decision-making quality evaluation model based on historical cases, performing quality perception on a current decision-making scene, and outputting decision-making quality information; and an execution effect is judged in combination with an expected target, an optimization mechanism is started if the target is deviated, candidate schemes are generated by using a historical knowledge base and a multi-target optimization algorithm, an optimal solution is screened, and intelligent adjustment of a decision scheme is realized. According to the method, multi-source heterogeneous data and cognitive logic are fused, semantic understanding, dynamic evaluation and adaptive optimization capabilities of a decision system are enhanced, and scientificity and real-time performance of enterprise decision are improved.

The invention provides an intelligent emergency decision support method and device based on multi-Agent cooperation. The method comprises a task planning module, an information acquisition module, a data fusion module and an execution monitoring module. The task planning module adopts a hierarchical decision-making mechanism, performs task decomposition in a plan making stage, generates a plurality of candidate execution paths by using thinking tree reasoning in a plan execution stage, and selects an optimal scheme. The information acquisition module acquires multi-source information such as network search, knowledge graph and geographic data through a plurality of professional Agents. And the data fusion module adopts a blackboard mode to manage heterogeneous information, and realizes intelligent abstract and correlation analysis through a large language model. And the execution monitoring module realizes dynamic optimization and fault self-recovery of the system through a multi-dimensional progress evaluation and cooperative monitoring mechanism. According to the invention, the problems of insufficient information processing capability, low decision-making efficiency and poor system stability of a traditional emergency decision-making system are solved. The information collection and processing efficiency is improved through large language model multi-Agent cooperation, the decision quality and accuracy are improved through a hierarchical decision mechanism, and long-term stable operation of the system is guaranteed through self-adaptive monitoring. The method is suitable for complex emergency decision-making scenes such as natural disasters, safety accidents and public health events.

The embodiment of the invention provides a power distribution network dynamic reconstruction method based on knowledge-guided large model enhanced fine tuning and related equipment, and belongs to the technical field of smart power grids and artificial intelligence. The method comprises the following steps: constructing a power distribution network dynamic knowledge graph, and providing structured knowledge guidance for model training; subgraph sampling is carried out based on the timestamp and converted into a fine tuning sample, and a training data set is generated; utilizing the data set to supervise, finely adjust and preheat the large language model; designing a multi-dimensional reward function of fusion format accuracy, economy and security based on mechanism knowledge in the knowledge graph and expert experience; a group relative strategy optimization mechanism is adopted to carry out reinforced fine tuning on the large language model, and the large language model is guided to output a safe, reliable and economical dynamic reconstruction strategy in interaction with the environment. According to the method, the problems of lack of training data, lack of physical knowledge guidance and insufficient decision reliability of a large language model in the power grid field are solved, and the intelligent level and decision quality of dynamic reconstruction of the power distribution network are remarkably improved.

The invention discloses a carton size automatic generation method under multi-target constraint and a packaging decision-making system. The method comprises the steps of obtaining attribute information of a to-be-packaged commodity and a plurality of optimization targets; establishing a multi-objective optimization model; solving the model by adopting an evolutionary algorithm based on Pareto sorting to obtain a Pareto optimal solution set, performing multi-stage decision processing on the solution set, making a primary decision based on user preference, automatically identifying an abnormal product and starting an additional verification process, constructing a digital twin model and performing a virtual simulation test to intelligently decide a final scheme, and according to the weight of the user preference, determining the final scheme according to the weight of the user preference. The technical problems that traditional packaging design depends on artificial experience, efficiency is low, and a globally optimal solution is difficult to obtain among multiple conflict targets are solved, particularly, automatic and high-reliability verification of high-risk commodity packaging is achieved, automation and intelligentization of packaging design are achieved, and the method is suitable for large-scale popularization and application. And the decision-making quality can be improved by means of self-learning of historical data.

According to the automatic software development method and device and the computer program, intelligent demand analysis is achieved through a natural language processing technology, dynamic task arrangement is conducted through a finite state automaton, collaborative development is completed by means of a multi-specialized role agent, intelligent verification is implemented based on a template matching mechanism, and the development efficiency is improved. And a complete automatic closed loop from demand to delivery is constructed. According to the scheme, full-process automation is realized, manual intervention is greatly reduced, and the development efficiency is remarkably improved; through division and cooperation of multiple agents, the professionality and decision-making quality of each link are ensured, and the capability limitation of a single agent is overcome; flexible and reliable process control is provided based on state machine management, and development state changes are dynamically adapted; and the standard consistency of the delivery result is ensured by combining template verification. According to the method, the problems of long development period, large quality fluctuation and the like caused by chain splitting, low intelligent level and excessive dependence on manpower of an existing development tool are effectively solved, and a feasible path is provided for comprehensive intelligence of software development.

The invention relates to the technical field of glass hot working control, and discloses a rapid prototyping control system and a rapid prototyping control method for tempered glass production. Comprising a thermal coupling module, a temperature control decision module, a flow field solving module, a photoelastic stress analysis module, a quantum annealing optimization module and a time domain synchronous control module. According to the system, a three-dimensional thermal-stress field is constructed on the basis of physical properties and thermal boundaries of glass, heating power is predicted through reinforcement learning, flow field simulation and stress image analysis are combined, control parameter self-adaptive adjustment is achieved through quantum annealing optimization, beats of all subsystems are coordinated through a synchronization module, and an efficient closed-loop control structure is formed. By introducing the quantum annealing optimization module, parameter adjustment in the control system is optimized, the technical effect of improving the precision of complex control decisions is achieved, and the optimization speed and the decision quality of the system are improved.

The invention relates to the technical field of artificial intelligence multi-agents, in particular to a proposal review method and system based on evidence verification and multi-agent cooperation. A cross validation mechanism based on a review information pool is introduced. The cross validation mechanism is a multi-agent round table cooperation mechanism, and a preliminary review result generated by an agent is not directly output, but passes multiple rounds of mutual verification, supplementation and correction until a preset convergence condition is met. According to the evidence verification process, cognitive deviation and knowledge blind areas possibly existing in a single agent are effectively eliminated, and the omission ratio and the misjudgment rate of the review result are remarkably reduced, so that the accuracy, the integrity and the reliability of a final review report are ensured; the technical problems of low efficiency and low accuracy caused by insufficient review depth, single angle and lack of verification in the prior art are effectively solved, and the review efficiency and decision quality of enterprise project proposals are remarkably improved.

The invention discloses a space-time cooperative scheduling method for an intelligent sky rail and an AGV in an automatic container terminal, and the method comprises the steps: determining the scheduling constraint conditions of an SMV and the AGV based on an SMV and AGV dual-cycle strategy, and constructing a model and constraint conditions which take the minimization of the completion time of all tasks as a target; using an LBBD algorithm to decompose the mixed integer linear programming model into a main problem and a sub-problem, constructing three acceleration strategies based on SMV and AGV dual-cycle strategies, embedding acceleration cut into the main problem as a constraint condition, solving the main problem and the sub-problem under the constraint condition, and generating Benders cut; embedding the Benders into the main problem, and solving again to obtain a scheduling optimization result; the scheduling decision quality is fundamentally improved, a set of scientific and efficient SMV-AGV collaborative operation method is provided for an intelligent air rail system, the equipment utilization rate can be remarkably improved, the operation completion time can be shortened, the optimal collaborative scheduling scheme can be rapidly and accurately obtained in a large-scale task scene, and the unloaded driving cost, the energy consumption cost and the operation cost are synchronously reduced.

The invention discloses a task planning-based material information processing method and device. The method comprises the steps of obtaining a multi-modal material information file; dividing the material information file according to the target content of the material information file to generate a plurality of analysis sub-tasks; according to a processing cluster resource state, dynamically distributing the analysis subtasks to cluster nodes, and giving structured information corresponding to the analysis subtasks; substituting the structured information into the information processing model to obtain processing result data corresponding to the structured information, the processing result data including a processing score, a risk probability and a supplier order; and carrying out AB test weight adjustment voting fusion on the processing result data to generate a material information report comprising multi-modal evidence. By dividing the multi-modal material information file, synchronous processing of multi-type data of the bid invitation file is realized, the data processing efficiency and accuracy are improved, a reliable data basis is provided for bid evaluation, and the intelligent level and decision quality of a bid invitation process are comprehensively improved.

The invention discloses an internet-based ship port entering and leaving scheduling system and method, and relates to the technical field of ship management, and the system comprises an initial ship scheduling unit; and the optimal ship scheduling unit is used for constructing a multi-target reward tensor in combination with a multi-target scheduling constraint condition, processing the multi-target reward tensor by using a sequence based on Monte Carlo tree search, constructing a strategy to generate an initial scheduling set, obtaining a candidate scheduling set through a denoising path optimization mechanism dynamically guided by a target condition, and performing ship scheduling. Selecting an optimal ship scheduling sequence; the multi-ship collaborative network unit is used for constructing a multi-dimensional space-time cascade atlas to identify implicit resource conflicts among ships, and generating a collaborative track by using a multi-ship collaborative track generation algorithm to form a multi-ship collaborative network; and a dispatching instruction generating and pushing unit. According to the invention, balance and accuracy of ship scheduling among multiple targets are ensured, scheduling errors and delay are reduced, and scheduling efficiency and decision quality are improved.

The invention discloses a large-model multi-agent task scheduling method with memory and retrieval capabilities, and the method comprises the steps: carrying out the cognitive analysis of a complex task based on task scheduling agents, and carrying out the distribution of subtasks through combining the functional attributes of all task execution agents and an integrated tool; each task execution agent completes execution work of a specific task through an integration tool, a task result is returned to the task scheduling agent for integration, and execution of a next link subtask or completion of the task is determined according to a task condition; maintaining task context information and a task entity information base by adopting a dynamic memory pool; and cross-agent and cross-task node multi-dimensional information sharing is realized by using cross-agent search. According to the method, the problem of state loss of a multi-agent system is solved by introducing a memory enhancement mechanism, and the context sensing capability in the task execution process is remarkably improved; cross-task and cross-agent knowledge reuse is realized through a cross-agent search mechanism, and the decision quality of the system is improved; the method is compatible with multi-source heterogeneous task requirements, breaks through the limitation of a traditional multi-agent system on task complexity, cross-agent collaboration and knowledge reuse capability, and can be widely applied to the field of intelligent scheduling of complex scenes such as emergency rescue, industrial automation and urban public management.

The invention relates to the technical field of artificial intelligence, multi-agent systems and natural language processing, in particular to a multi-agent collaborative decision-making and communication system with a body based on a large language model, and the system comprises a sensing module which is used for obtaining environment and self state information; the large language model core processing module is integrated to each agent, comprises a multi-modal perceptual representation and semantic mapping system, a semantic-structured information bidirectional conversion network and a self-adaptive multi-path decision generation system, and is used for generating individual action decision suggestions and natural language communication contents oriented to other agents; the cooperative communication network is used for supporting efficient and semantic-rich interaction between intelligent agents based on natural language communication content; the environment coordination module is used for analyzing communication content and generating a global or local coordination instruction, a large language model is integrated into the multi-agent system, efficient communication and collaborative decision-making between agents based on natural languages are achieved, and the adaptability and decision-making quality of the system in a complex and dynamic environment are improved.

The invention discloses an intelligent switch fault diagnosis method based on multilayer data reasoning, which relates to the field of switches, collects and fuses multi-source data of a switch, converts entities, attributes and relationships in a multi-source fusion data set into an RDF triple based on a predefined network operation and maintenance ontology model, and performs fault diagnosis on the RDF triple. The method comprises the steps of constructing a switch fault diagnosis knowledge graph, dynamically generating an SPARQL query statement based on real-time monitoring data, performing graph traversal and logical reasoning on the switch fault diagnosis knowledge graph, and outputting a switch fault diagnosis conclusion. According to the method, comprehensive upgrading of switch fault diagnosis from passive response to active prevention is achieved, the network operation and maintenance efficiency and decision quality are remarkably improved, equipment monitoring, topological relations and service data are integrated through a unified semantic framework, a structured knowledge graph is constructed, and fault diagnosis has semantic interpretability.

The invention relates to the technical field of electronic data processing, and discloses a micro-service concurrent scheduling method and system based on DAG (Directed Acyclic Graphics) drive, which comprises the following steps: acquiring a directed acyclic graph, identifying a strong dependency side and a weak dependency side to carry out topological layering on the directed acyclic graph, and calculating a global parallelism factor; determining a prediction range, analyzing nodes in a subsequent main service layer in the prediction range, and generating a predictive resource demand vector; determining a target number of various service instances in the preheating pool; when the health degree attenuation value is lower than an activity threshold value, marking the idle instance as a to-be-refreshed state; calculating the scheduling affinity of each matching pair, and selecting the matching pair with the highest affinity to execute the task; if the execution time consumption exceeds the statistical standard, recording the type of the service node and the timeout amplitude as a path blocking event; the historical path blocking degree is updated and used for feeding back and adjusting the target number of the follow-up preheating pools. According to the method, the task can be matched to the optimal execution instance, and the scheduling decision quality is improved.

The invention relates to a discrete industrial agent-based production management method and system, and relates to the field of production management, and the method comprises the steps: collecting a production prediction sample data set and a quality inspection decision sample data set, carrying out the data weight division of the two data sets, and obtaining two sample weight sets; obtaining a production prediction and quality inspection decision path array, a first prediction accuracy rate set and a decision accuracy rate set after integrated training; combining the two path arrays to obtain a discrete industrial agent array, carrying out joint optimization training, and testing to obtain a second prediction and decision accuracy set; obtaining current production basic data, inputting the current production basic data into the agent array, outputting a predicted production yield and a decision quality inspection parameter, performing compensation according to an error between the second prediction and decision accuracy set and the first prediction and decision accuracy set, and obtaining a predicted production yield and decision quality inspection parameter interval for production management. The technical problem that data interaction and business collaboration of a plurality of complex and independent scenes in the discrete manufacturing industry are difficult to realize in production management is solved.

The application discloses a kind of robot autonomous exploration mapping system and method, system includes perception module, decision module, planning module and control module, the output of perception module is connected with the input of decision module, and perception module transmits front point candidate set to decision module, the output of decision module is connected with the input of planning module, and decision module transmits optimal target point to planning module, the output of planning module is connected with the input of control module, and planning module transmits motion instruction to control module, and the output of control module is connected with the input of perception module, and control module state information is fed back to perception module, and forms closed loop control system. It can be adapted to diversified industrial scene, with the advantages of efficient completion of autonomous exploration, balancing decision quality and real-time, self-adapting different structure environment, improving decision stability and the like.

The application discloses a power-hydrogen-doped gas network combined scheduling method and relates to the field of energy scheduling. The application proposes a power and hydrogen-doped gas network combined scheduling framework based on graph neural network embedding optimization. Firstly, the hydrogen doping ratio in the pipe network is accurately modeled based on the graph neural network, and then the graph neural network inference process is equivalently embedded in the optimization problem, so that the energy scheduling decision can accurately and efficiently consider the hydrogen doping ratio. The application can improve the decision quality of the combined scheduling operation of the power grid-hydrogen-doped gas pipe network system, thereby improving the safety and economy of the operation, and can be deployed and migrated in batches at low cost.

The application discloses a multi-knowledge base fusion deduction method based on collaborative decision-making, comprising: performing semantic analysis on a deduction request input by a user to extract key semantic features; activating a target knowledge base in a multi-knowledge base cluster based on the features and retrieving preliminary knowledge fragments; performing semantic alignment and conflict resolution on the preliminary knowledge fragments to generate a fusion knowledge graph; performing cross-library joint reasoning on the fusion knowledge graph, and performing a multi-step deduction cycle with the preliminary reasoning conclusion as a starting point, wherein a hypothesis generation and verification mechanism is introduced; and finally performing confidence evaluation, sorting and synthesis on each conclusion in the final deduction conclusion chain to output an optimal deduction result. The application realizes a leap from "information retrieval" to "knowledge deduction", has advantages such as cross-library joint reasoning, multi-step deduction cycle, hypothesis verification and interpretability, and improves reasoning capability, dynamic adaptability and decision quality in a complex decision-making scenario.

This application discloses a hierarchical obstacle avoidance method and system based on collaborative training of the PPO-TD3 algorithm. This application utilizes a dynamically adaptive hierarchical decision-making system, namely a collaborative architecture of the PPO and TD3 algorithms, to achieve intelligent obstacle avoidance in dynamic environments through a hierarchical reinforcement learning framework. In simple environments, only the high-frequency control network of the underlying TD3 algorithm is run to improve response speed, while in complex scenarios, the complete hierarchical architecture is activated to ensure decision quality. Simultaneously, a semantic instruction interface is innovatively designed, enabling the abstract instructions output by the high-level PPO decision-making layer policy network to be intelligently parsed into executable actions by the underlying TD3 execution layer control network in conjunction with real-time physical constraints. Combined with a hybrid training framework integrating simulation training, human demonstration, and real-world learning, and a resilient safety mechanism based on dynamic risk assessment, this achieves synergistic optimization of safety and operational efficiency in complex dynamic environments.

The present disclosure provides a self-driving control method and device, electronic equipment and storage medium, the method comprising: scoring a plurality of candidate trajectories according to evaluation dimensions defined according to a preset rule, the evaluation dimensions including safety, efficiency and / or comfort, the plurality of candidate trajectories being generated based on inputting driving information at the same time during self-driving into different prediction algorithms; if the deviation of the score of at least one candidate trajectory from the highest score is less than a first preset threshold, obtaining self-vehicle information, self-vehicle interaction object information and environmental information within a preset past time at the current time; inputting the obtained information, the highest score candidate trajectory and the at least one candidate trajectory into a pre-trained arbitration model to enable the arbitration model to output a target candidate trajectory based on expert driving behavior; and controlling the self-vehicle to drive according to the target candidate trajectory. Accordingly, the arbitration model focuses on processing situations that are difficult to distinguish by rules, ensuring decision quality.

The invention discloses a multi-constraint-condition-based dynamic cross-layer path planning method, which belongs to the technical field of indoor navigation, and comprises the following steps of: constructing a real-time constraint set containing a plurality of quantitative constraint conditions through multi-source data fusion, multi-constraint comprehensive decision and dynamic weight updating, continuously updating a'dynamic weighted multilayer topological graph 'representing an indoor space, and performing multi-source data fusion, multi-constraint comprehensive decision and dynamic weight updating. An optimal cross-layer navigation path is generated and dynamically adjusted in real time, and search efficiency and decision quality are considered based on a two-stage optimization processing mechanism (edge weight real-time updating and path evaluation screening), so that path planning can intelligently adapt to an indoor environment which changes in real time, and individual requirements of users are fully met; the critical defect that a static path library cannot adapt to a dynamic environment in the prior art is effectively overcome, and the accuracy, adaptability and user experience of path planning in a complex multi-layer indoor environment are remarkably improved.

The invention provides a magma contact metamorphic zone coal quality prediction method based on organic geochemical data, and relates to the technical field of coal quality prediction. The magma contact metamorphic zone coal quality prediction method based on the organic geochemical data comprises the following steps that S1, at least two sampling sections are arranged in the direction perpendicular to a contact zone of a magma rock mass and a coal seam, one sampling section is perpendicular to a coal seam sedimentary layer, the other sampling section is parallel to the coal seam sedimentary layer, coal samples are collected on the sampling sections at equal intervals, and coal samples are obtained; and obtaining organic geochemical data of the critical control points. Through sparse sampling and transition point recognition algorithms, data requirements are greatly reduced, the prediction period is shortened, complex simulation is replaced by template matching, the prediction process is intuitive and explainable, a multi-source verification and reliability grading mechanism ensures that the result is stable, the overall method is high in practicability and easy to deploy and apply in a resource limited scene, and the prediction efficiency is improved. And the decision-making quality and benefit are improved.

The invention relates to the technical field of power systems, and discloses a hybrid multi-target coordination control system based on SVG and a synchronous phase modifier, which significantly improves the decision quality and foresight of an intelligent agent by fusing a real-time state and future prediction, and improves the decision efficiency compared with a single system state vector. The enhanced state characterization not only comprises real-time parameters such as voltage deviation and reactive power difference, but also integrates future uncertainty probability information predicted by the random forest, so that the intelligent agent can simultaneously sense the current state and the expected evolution trend of the system, and the enhanced environment sensing capability enables the Q learning algorithm to make a more predictable decision, so that the method is more suitable for popularization and application. According to the method, the coordination strategy of the SVG and the phase modifier is adjusted in advance before voltage fluctuation occurs, state characterization is enhanced, comprehensive environment information is provided, an intelligent agent can better balance the relation between quick response and steady state support, the voltage stability is guaranteed, the economical efficiency of system operation is improved, and finally multi-target collaborative optimization in the true sense is achieved.

The invention provides a supply chain demand prediction optimization method and system, and the method comprises the steps: obtaining a multi-frequency time series data set through collecting and preprocessing historical supply chain data; performing demand prediction calculation through the dual-frequency fusion network model to obtain a future demand prediction result; a cost minimization supply chain optimization model is established and solved, and a supply chain decision scheme is obtained; and performing multi-scene simulation analysis on the decision scheme to obtain an index evaluation result. According to the method, time sequence data of different frequencies can be effectively fused, the demand prediction precision is improved, the supply chain decision quality is optimized, the reliability of the scheme is ensured through simulation verification, and scientific decision support is provided for enterprise supply chain management.

This invention discloses a method, device, and electronic device for intelligent identification of network attacks, relating to the field of network security technology. The method includes: acquiring security log data and identifying threat logs within the security log data; performing address-perspective analysis and attack event-perspective analysis on the threat logs; clustering the threat logs based on the address-perspective analysis results and attack event-perspective analysis results to obtain attack activity log clusters, and statistically analyzing key indicators within the attack activity log clusters; calculating scores for network attack sources in four dimensions—threat level, resource utilization capability, attack intent, and technical complexity—based on the address-perspective analysis results, attack event-perspective analysis results, and key indicators; and classifying the network attack sources into corresponding profile types based on the scores in the four dimensions and preset threshold comparison rules. This invention achieves effective noise reduction and accurate identification, as well as in-depth attacker profiling, improving security operation efficiency and decision-making quality.

This invention discloses a resume screening and display method and system for human resource management. It constructs a keyword-dimension mapping table based on job description text using a natural language processing engine; analyzes keyword frequency, syntactic position, modification strength, and semantic relevance to generate a job requirement intensity vector; retrieves historical recruitment data based on job meta-information to generate a historical weight vector; adaptively calculates a smoothing coefficient based on the amount of historical data; and integrates dual-source weights to generate a dynamic weight vector; standardizes the scoring of each dimension of the resume, using a normalized formula based only on valid dimensions to calculate the matching degree, avoiding score distortion caused by missing fields; and finally displays the results sorted by matching degree. This invention abandons the preset weight mode, achieving dynamic screening with a tailored approach for each job, improving matching accuracy, operational efficiency, and the quality of human-machine collaborative decision-making, providing a scientific, efficient, and transparent intelligent solution for human resource management.

The invention discloses a container connection transportation path planning method based on deep reinforcement learning, and the method comprises the steps: building a mixed integer nonlinear programming model with the minimization of the total fuel consumption of all trucks as a target according to a container connection transportation system, performing linearization processing on the mixed integer nonlinear programming model to obtain a mixed integer linearization programming model; the method comprises the following steps: taking a container connection transportation path planning problem as a Markov decision process, and carrying out reinforcement learning training on a deep reinforcement learning network based on Transform in a container connection transportation simulation environment based on a deep reinforcement learning algorithm of Transform to obtain an optimal deep reinforcement learning network; and realizing container connection transportation path planning through the optimal deep reinforcement learning network. The method solves the problem that the existing method cannot effectively capture the structural features of the transportation process, limits the decision-making quality and generalization ability in high-dimensional and other complex scenes, and further causes the low container connection transportation efficiency.

The embodiment of the invention discloses a model optimization method for long task decision and a related device. When one round of interaction meets one dialogue paragraph, generating a historical dialogue abstract according to the environment input of the dialogue paragraph and the corresponding response action, and generating a decision sub-track of the language model in the dialogue paragraph according to the historical dialogue abstract of the dialogue paragraph, and outputting a behavior strategy of a response action based on a given context according to the decision sub-trajectory optimization language models of the plurality of dialogue paragraphs, and generating an abstract strategy of a historical dialogue abstract according to the decision sub-trajectory optimization language models of the plurality of dialogue paragraphs. By dynamically managing the context history and adjusting the strategy of abstract generation and task execution according to long-term return, the problems of information loss and memory decline in long-sequence tasks are effectively solved. By means of a cross-time-period reward return mechanism, effective credit distribution between early information and a final task processing result is achieved, and the decision-making quality and stability of the model in a long-term task are improved.

This application provides a method for optimizing the drying process parameters of insulating paper in power transformer manufacturing, belonging to the field of process parameter optimization technology. The method includes: constructing a first initial state vector and a corresponding first drying state vector of the insulating paper at a first historical time; obtaining a first drying process index set at the first historical time; and constructing a drying process model; adjusting the parameters of the first drying process index set; inputting a first decision variable set into the drying process model to obtain a first decision quality set; collecting a first deviation quality set based on the first decision quality set; and performing drying processing through the first decision variable set. This application can solve the technical problem in the prior art where the drying process lacks a dynamic adjustment mechanism, resulting in the inability to flexibly adjust process parameters, thereby achieving real-time adjustment of the drying process and improving drying efficiency.

The invention provides an intelligent soft package recommendation method and system based on big data analysis, and relates to the technical field of big data, and the method comprises the steps: recognizing an imagination dimension set of life experience imagination of a selected soft package combination by a user; analyzing the soft-loading life experience big data, and determining a life experience imagination dimension complete set corresponding to the soft-loading combination; based on the life experience imagination dimension complete set and the imagination dimension set, life experience imagination guidance is carried out on the user; and when the user generates negative feedback in the guiding process, carrying out replacement recommendation of the soft installation combination on the user based on the negative feedback. According to the intelligent soft decoration recommendation method, through multi-modal behavior data analysis and a dynamic guiding mechanism, the soft decoration recommendation accuracy and the user satisfaction degree are remarkably improved. Compared with a traditional recommendation system, the method can comprehensively recognize the life experience imagination dimension of the user, makes up for the deficiency of autonomous imagination of the user, and guides the user to pay attention to key dimensions such as functionality, durability and environmental protection, thereby improving the decision quality.