119 results about "Market dynamics" patented technology

A system and method for multi-scale temporal attention processing in multimodal technology deep learning systems. This system processes time-series, textual, sentiment, and structured tabular data across three hierarchically-organized temporal streams—quarterly, weekly, and intraday levels—with bidirectional cross-temporal information flow. Scale-specific attention mechanisms are optimized for respective temporal granularities, while an adaptive controller dynamically weights each temporal level based on real-time market volatility indicators. A multi-scale fusion processor integrates attention-weighted representations to generate temporally unified representations preserving both short-term market dynamics and long-term trends. This approach enables superior forecasting and risk assessment by leveraging temporal correlations across multiple time scales while automatically adapting to changing market conditions. The system facilitates interpretable AI analysis through attention visualization and enables synthetic scenario generation for model testing.

The invention relates to the technical field of asset transaction risk monitoring, and proposes an asset transaction risk monitoring system based on data analysis, and the system comprises a data obtaining module which is used for obtaining and integrating multi-source heterogeneous data, including but not limited to transaction records, market quotation data, user behavior data, legal contract texts and financial indexes, the data is preprocessed; and the risk assessment module is connected with the data acquisition module through a data transmission technology, and assesses the risk in real time based on a preset rule and a machine learning model. Through timely acquisition and analysis of latest transaction information, market dynamics and user behavior changes, a reinforcement learning technology is utilized, and according to a real-time risk assessment result and a disposal effect, risk monitoring is ensured to be always matched with a market actual condition, so that a financial institution can timely capture a risk signal and take precautionary measures in advance, and the risk monitoring efficiency is improved. And the risk loss is effectively reduced.

The invention provides a supply chain collaborative management method and system based on artificial intelligence, relates to the technical field of artificial intelligence, and quantifies collaborative, substitution and complementary relationship strength among commodities by constructing a commodity association graph network; utilizing a graph attention mechanism to identify a commodity group and calculate a demand influence coefficient, and performing time sequence analysis on historical order data to obtain basic demand prediction; meanwhile, a scene recognition model is constructed by adopting reinforcement learning, a basic prediction result is adjusted according to a current market scene, the demand conduction quantity in the commodity group is calculated in combination with a demand influence coefficient, and final demand prediction is obtained; and finally, based on a prediction result, determining a collaborative decision-making scheme of each participant by applying a cooperative game method, and generating an inventory allocation instruction. According to the method, the complex incidence relation between the commodities and the market dynamic change are accurately captured, the supply chain prediction accuracy and the cooperation efficiency are remarkably improved, and inventory optimization and cost reduction are realized.

The invention discloses a public opinion risk dynamic early-warning method and system based on a large language model, and the method and system carry out the semantic recognition, event extraction and situational reasoning of unstructured public opinion data through introducing an advanced large language model, and carry out the dynamic early-warning of the public opinion risk in combination with structured emotion indexes and market dynamics. Potential risk factors in social public opinions can be automatically identified, and risk quantitative evaluation is realized in combination with semantic tags, market behavior data and emotion intensity. The system has strong prospective perception ability and event evolution reasoning ability, can provide rapid and accurate early warning information, and further can generate personalized suggestions and decisions in combination with user risk preferences. The method can be widely applied to a plurality of public opinion sensitive fields such as enterprise brand management, government supervision, financial institutions and media transmission control, and the automation and precision capability of dealing with sudden public opinion risks is effectively improved.

The invention discloses an intelligent management system and method for cable production, and the system builds an intelligent decision-making system for demand prediction through the dynamic fusion of historical sales data and market trend information. Specifically, a time sequence feature coding and semantic embedding technology based on deep learning is adopted, cross-modal association is carried out on a local rule of a historical sales window and market dynamic semantics, and deep collaborative decision response is further carried out on historical information and market trends to obtain historical sales-market trend collaborative decision response coding features; and based on this, short-term prediction of the cable market demand is realized. In this way, the timeliness and accuracy of demand prediction are remarkably improved, the risk of supply chain imbalance caused by sudden demand change is effectively relieved, and then dual optimization of the resource utilization rate and the market response capacity is achieved.

The invention relates to the technical field of electric power systems, in particular to an electric power spot market risk prevention and control method and system considering market subject behaviors. Acquiring operation data of generating capacity, electricity demand, market price and power grid state of the electric power spot market; on the basis of the acquired operation data, a coupling degree evaluation index and a stability evaluation index are introduced to carry out prediction and anomaly detection on a market trend, and influence factors of connection of a large-scale generator set and a small-scale power grid are particularly concerned; analyzing a market subject behavior pattern through transaction frequency, price volatility and market participation degree characteristic quantitative indexes, and identifying market manipulation and violation operation risks; market dynamics are monitored in real time, a risk threshold value is set, and an alarm is triggered when a risk index exceeds a set standard; early warning information of different levels is automatically sent out according to the risk degree, and corresponding countermeasures and suggestions are provided; and a supervision mechanism is helped to make a quick response through a visual interface.

The invention discloses a coal market analysis and purchase decision-making method and system based on big data, and belongs to the technical field of coal market data analysis, and the method comprises the steps: generating an integrated market analysis data set through multi-source data collection and data integration and cleaning; based on the integrated market analysis data set, data analysis and mining are carried out through index calculation, correlation analysis and trend prediction, and an analysis result containing market dynamics, price trend and supply conditions is obtained; displaying a preset report template based on the market analysis, the purchase suggestion and the data; and based on an analysis result, generating a coal purchase decision support report in combination with a report template and an automatic filling technology, and outputting the report in a specified format. According to the invention, factors in multiple aspects such as coal quality, purchase cost, transportation mode and supplier capability are comprehensively considered, and accurate and reliable coal market analysis and purchase decisions are provided for users through data acquisition and integration, data analysis and mining and automatic analysis report generation.

The invention provides a supply chain cost anomaly AI positioning system based on multi-mode depth tracing, and relates to the technical field of cost anomaly tracing. According to the supply chain cost anomaly AI positioning system based on multi-modal depth tracing, a three-layer architecture is adopted, a dynamic threshold algorithm and a multi-level association map are combined, real-time detection and root positioning of cost anomaly are achieved, and the three-layer structure is data acquisition, dynamic modeling and visual tracing. The system has the advantages that dynamic adaptability is improved, reasonable fluctuation and abnormal risks are accurately distinguished, the system breaks through the rigid limitation of a traditional static rule, the judgment threshold value is dynamically adjusted by fusing market dynamics (such as bulk commodity prices and policy adjustment) and real-time service data, and a supplier-production-logistics-storage association graph is constructed, so that the risk of abnormal risks is accurately distinguished. And the conduction path of the cost abnormity in each link of the supply chain is visually displayed.

The invention belongs to the technical field of advertisement putting management, and particularly relates to an intelligent precise advertisement putting optimization method and system based on dynamic strategy adjustment. The system comprises a user behavior deep insight module, a market dynamic perception module, an advertisement effect intelligent evaluation module, a strategy dynamic generation module, an advertisement intelligent putting execution module and an advertisement putting management end. Various behavior data of users in a network environment are collected and analyzed through the user behavior deep insight module, the market dynamic sensing module monitors and analyzes changes of the market environment in real time, and the advertisement effect intelligent evaluation module evaluates the actual effect of advertisement putting. And the strategy dynamic generation module dynamically generates and adjusts the advertisement putting strategy, the advertisement is accurately put to the target user according to the advertisement putting strategy, the advertisement putting is comprehensively upgraded from multiple dimensions of accuracy, timeliness, effect optimization and user experience, and the increasingly complex and variable advertisement putting requirements are met.

The invention relates to the technical field of agricultural product sales management, in particular to an agricultural product intelligent sales management system based on AI digital humans, and aims to solve the problems that in the prior art, sales volume, price and environmental factors cannot be comprehensively analyzed to construct a sales trend prediction model, a comprehensive view cannot be provided to improve prediction accuracy, and the sales trend cannot be predicted. And enterprises cannot quickly respond to market dynamics. According to the method, the sales trend prediction model is constructed by using historical sales and meteorological data, the method has significant advantages, the sales volume, price and environmental factors are comprehensively analyzed, a comprehensive perspective is provided to improve prediction accuracy, the sales trend prediction feature vector is generated, the module can predict future sales volume change in real time, and the prediction accuracy is improved. And enterprises are supported to quickly respond to market dynamics, and inventory, pricing and marketing strategies are optimized.

The invention provides a real-time commodity price prediction system based on multi-source data fusion, and the system comprises a data integration module which is used for obtaining multi-source heterogeneous data, carrying out the alignment processing of the multi-source heterogeneous data according to the commodity types and timestamps, and generating a standardized fusion data set; the dynamic weight distribution module is used for dynamically calculating the weight coefficient of each data source according to the relevance between each data source in the standardized fusion data set and the commodity category; the model integration module is used for performing weighted fusion on the price trend prediction result output by the time sequence prediction model and the game correction output by the market game model based on the weight coefficient to generate initial price prediction; and the optimization output module is used for performing periodic rule correction and strategy collaborative analysis on the initial price prediction according to the real-time market dynamic data to obtain a predicted commodity price trend. By adopting the system, the commodity price trend can be dynamically predicted based on multi-source big data, an enterprise is helped to optimize a purchasing strategy, and the inventory overstock risk is reduced.

The invention provides an automobile after-service pricing model optimization method under dynamic supply and demand balance, and relates to the technical field of pricing model optimization. The pricing model optimization method comprises the following steps of accessing a government policy issuing platform and an industry association database, capturing related policies and macroeconomic indicators of automobile post-service in real time, performing semantic analysis on financial news and policy interpretation articles, extracting potential factors, and performing classification and analysis on the potential factors. A competitor official website, an e-commerce platform and a social media account are monitored for 7 * 24 hours, a real-time feedback module is embedded in a service platform, customers are encouraged to evaluate services, prices and new product demands in time, a market signal threshold model is established, and the market quality is improved. And early warning thresholds are set for the policy change frequency, the competitor price fluctuation amplitude and the customer demand growth rate index. Through real-time market dynamic monitoring, scientific quantitative analysis, intelligent and accurate decision making and rapid iteration strategies, the enterprise pricing ability and market competitiveness are effectively improved.

According to the intelligent inventory management and automatic replenishment e-commerce operation method, sales data, inventory data, return data, commodity attributes, supply chain data and market environment data (such as social media, weather data, economic indicators and the like) of an e-commerce platform are integrated, and a data preprocessing method is adopted for cleaning and denoising, so that the quality and integrity of the data are ensured. A multi-dimensional data fusion and deep learning algorithm is adopted, multiple factors such as commodity historical sales data, seasonal fluctuation, market dynamics, user behaviors and the like can be fully considered, and therefore compared with a traditional single prediction model, the demand prediction accuracy can be greatly improved, the inventory overstock or stockout risk caused by prediction errors can be avoided, and the user experience can be improved. By designing a mechanism for monitoring and analyzing external events in real time, emergency situations (such as emergency promotion, market demand fluctuation, weather change and the like) can be quickly responded, a replenishment strategy can be timely adjusted, and inventory crisis caused by the fact that the system fails to quickly respond to external changes is avoided.

The invention relates to the technical field of commercial financial information processing, and provides a commodity market dynamic prediction method and system, a medium and electronic equipment. Acquiring real-time market information data of the target commodity and submitting the real-time market information data to a market information staring system; verifying the real-time market data, generating a data set hash value based on the target data passing the verification, aggregating the target data in a distributed hash table, and storing the aggregated data in a block chain based on the data set hash value; formulating a transaction strategy based on the target data, encoding the transaction strategy into a smart contract, and deploying the smart contract on the block chain; and when the market dynamic condition of the target data is predicted to meet the triggering condition of the smart contract, automatically executing the transaction. On the basis of ensuring the data accuracy and security, the transaction is automatically executed when the market information dynamically accords with the intelligent contract, so that the intelligence, automation and high efficiency of transaction decision making are realized, and the response speed and execution precision of commodity transaction are greatly improved.

The invention relates to a differential privacy-based competitive intelligence analysis system and method. The differential privacy-based competitive intelligence analysis system comprises a differential privacy processing and budget management module, a differential privacy feature engineering module, a privacy protection analysis and prediction module and a differential privacy synthetic data generation module. According to the design of the invention, an end-to-end advanced analysis framework with mathematics provable privacy protection capability is constructed, so that accurate, timely and reliable insight of market dynamics and competitor strategies is realized on the premise of strictly protecting enterprise sensitive commercial confidentials.

The invention relates to the technical field of intelligent pricing, in particular to an intelligent pricing management system based on machine learning and data analysis, and aims to improve the purity and consistency of data and lay an accurate data foundation for subsequent analysis through cleaning and format unified processing of market original data and elimination of redundant information. Through a non-dominated sorting genetic algorithm, the influence weight of each data point is analyzed, comprehensive quantitative modeling of price influence factors is realized, a model basis with better interpretation and adaptability is provided for price prediction, and market changes and competition patterns are dynamically captured by combining a linear regression model, so that the price prediction accuracy is improved. And the price is ensured to be dynamically and accurately adjusted along with the market through a fine adjustment strategy, the dynamic matching capability between the price and the market fluctuation is realized, the adaptability of the strategy under different market conditions is verified and optimized through a multi-scene simulation test and market feedback monitoring, and the high efficiency and stability of the price adjustment strategy in practical application are ensured.

The invention discloses a multi-agent collaborative optimization scheduling method and device based on peak regulation market dynamic rule formulation, and the method comprises the steps: carrying out the refined classification of resources in multiple agents according to the physical characteristics and adjustment flexibility of the resources, building a multi-dimensional classification system, and providing a data basis for the dynamic design of rule parameters; an accurate description model is established for each type of resources, and feasible regions and cost characteristics of the resources in a peak regulation market are quantified; establishing dynamic association between resources and peak regulation market rules, embedding rule parameters into the optimization model, and constructing a power market optimal rule model containing multiple agents; and constructing a double-layer collaborative optimization strategy, solving the model and outputting an optimal rule of the current peak regulation market, and realizing market rule dynamic optimization and resource collaborative scheduling. According to the method, the static limitation of a traditional peak regulation market rule is broken through, dynamic matching of rule parameters and resource characteristics is achieved through multi-agent collaborative optimization, and the new energy consumption capacity and the market operation efficiency are effectively improved.

The invention relates to the technical field of product oil management, and discloses a product oil purchase-sale-stock multi-modal data analysis method and system. The method comprises the following steps: acquiring real-time inventory data, transportation state data and sales terminal data in a product oil supply chain to form a multi-modal data set; performing data cleaning on the data, and extracting key inventory characteristics to generate a cleaned data subset; obtaining associated historical purchase data, regional demand prediction data and market price fluctuation data based on the gas station identification information to form a multi-dimensional auxiliary data set; inputting the features into an inventory feature extraction model, generating a multi-feature vector set, and fusing the multi-feature vector set; inputting the fused feature vectors into an inventory state evaluation model set, and outputting inventory early warning level and abnormal type information; and finally, a dynamic allocation scheme is generated by combining real-time inventory data and the like. According to the method, multi-modal data are integrated, so that the comprehensiveness and accuracy of data analysis are improved, and the purchase-sales-stock management of the product oil is assisted to be more suitable for market dynamics.

The invention discloses a power distribution network material cost dynamic calculation system construction method based on multi-dimensional sensitivity analysis. The method comprises the following steps: fusing multi-source heterogeneous data and standardizing business characteristics; carrying out single-factor sensitivity modeling based on dynamic demand elasticity; performing multi-factor coupling sensitivity analysis; constructing a dynamic cost calculation system; and performing economic influence prediction and dynamic verification. According to the method, the problem that a traditional method is insufficient in processing complex multi-source data and coping with market dynamic changes is solved, accurate cost prediction and intelligent decision support are achieved, and the efficiency and economic benefits of power distribution network material management are improved.

The present invention discloses a smart marketing management method and system based on AI artificial intelligence. The smart marketing management system includes a data collection and preprocessing module, a market dynamics prediction module, a competitive product analysis module, an advertising strategy generation module, and a strategy execution and feedback module. The smart marketing management system collects relevant data on marketing advertisements in the market, collects market dynamics data, monitors and updates the advertising strategies and market performance of competitive products in real time, and automatically adjusts advertising delivery strategies through AI artificial intelligence technology based on competitive product analysis results and real-time advertising effect data. Through the introduction of AI technology, market and competitive product data can be analyzed in real time, advertising strategies can be automatically adjusted, advertising content and delivery channels can be optimized, and advertising budgets and time frequencies can be dynamically adjusted. This system is not only highly intelligent and automated in advertising decision-making, but also achieves a reasonable allocation of marketing resources through multi-dimensional optimization strategies, significantly improving the overall effectiveness of advertising and the rate of return on investment.

The invention provides a reinforcement learning dynamic pricing method based on game feedback, and relates to the technical field of online data market dynamic pricing. Through combination of leader-follower strategy interaction of the Stackelberg game and the exploration-utilization balance principle of the dobby machine, the problems of price adjustment lag, large income fluctuation and insufficient strategy stability in a non-stable environment are solved. By introducing a data freshness evaluation mechanism, data weight is dynamically adjusted by integrating data timeliness attenuation and market correlation analysis, it is ensured that data input into a model always has high real-time performance and strong correlation, and the problem of decision lag caused by static data input in a comparison scheme is avoided; the exploration-utilization balance principle and the reinforcement learning model of the dobby machine are fused, the exploration rate is dynamically adjusted, a historical optimal strategy can be fully utilized in a non-stationary environment, a potential better scheme can be explored, and the static optimization bottleneck that a game model is limited to a preset objective function in a comparison scheme is broken through.

The invention belongs to the technical field of virtual power plants, and relates to a power spot market oriented virtual power plant resource dynamic aggregation method. The method comprises the following steps: extracting a distributed resource feature vector and mapping the distributed resource feature vector into a response type label; determining a price fluctuation period according to a spot price sequence, calculating a time sequence matching degree between each resource and a market rhythm by combining the feature vector, and constructing a comprehensive distance by fusing a clustering weight and a response type label; dividing the resource cluster into dynamic aggregation units by taking the variance of the minimum comprehensive distance as a target; a resource aggregation strategy is generated based on the aggregation unit, a control instruction is issued, and clustering weights and aggregation parameters are iteratively updated according to the clearing deviation rate fed back by market clearing. According to the method, the technical problems that the market dynamics is ignored, the clustering model is easy to merge heterogeneous resources and the closed-loop optimization is lacked in the existing static division are solved, and the effects of improving the market response capability of the virtual power plant, the control consistency of the aggregation unit and the adaptive optimization of continuous transactions are achieved.

The invention provides an enterprise cooperation and competition simulation method and system based on a large language model, and the method comprises the steps: 1, carrying out the modeling of a market environment, constructing a comprehensive model of supply and demand, consumer behaviors, market structure and policy intervention, and generating a dynamic and real market background; 2, performing multi-agent intervention, combining a large language model and reinforcement learning to realize dynamic strategy generation and natural language interaction of competitor agents, and adjusting pricing, advertisement and capacity layout; 3, dynamic game decision making, wherein non-cooperative, cooperative and mixed games are carried out between players and intelligent agents; 4, multi-agent debate and task disassembly are carried out, alliance negotiation and resource allocation are supported, task disassembly is realized through multi-round debate, and multi-party benefit balance is guaranteed; and 5, performing data analysis and feedback, recording market dynamics in real time, and providing visual analysis and strategy optimization suggestions. According to the invention, new technical support is provided for enterprise game simulation.

The invention relates to the technical field of electric power market bidding decision making, and discloses a market dynamic game bidding decision making method based on multi-stage deep reinforcement learning. According to the method, a market participant bidding behavior data set is obtained through an electricity market data center, and a reference bidding strategy is obtained through historical data trend analysis; according to market subject types, quotation elasticity and market power characteristics of each type are extracted; performing multi-stage deep reinforcement learning training on the features by using a reference bidding strategy to generate an initial bidding strategy matrix; and in combination with the matrix and the corresponding subject type, controlling the bidding decision agent to generate a dynamic bidding sequence in the feasible strategy set. And during market clearing, real-time data is collected to determine a feedback value, and an intelligent agent bidding strategy is adjusted according to the feedback value and the initial strategy value. According to the method, multi-stage learning and dynamic gaming are fused, main body features and real-time states are accurately captured, the adaptability and pertinence of a bidding strategy are improved, and participants are assisted in coping with complex market competition.

The invention belongs to the technical field of computer application, and discloses an anticipated price rolling matchmaking transaction aided decision-making method based on a big data algorithm, which integrates microscopic transaction data, mesoscopic market dynamics and macroscopic environment variables through a system, enables price prediction to more comprehensively fit the actual operation logic of the market, and improves the efficiency of price prediction. The deep forest model has a strong cross-modal feature learning ability, and can deeply mine hidden associations between different types of data, such as indirect influences between international situation changes and bulk commodity prices, conduction effects of upstream and downstream price linkage of an industrial chain on transaction varieties, and the like. A more three-dimensional and more reliable expected basis is provided for transaction decision making, so that a prediction result can better reflect the complex full view of the market, and prediction deviation caused by one-sided information is reduced; through a prediction framework combining a dynamic sliding window and incremental learning, subtle changes of the market can be tracked in real time, and it is ensured that the model is always kept synchronous with the market rhythm.

The invention discloses a machine learning-based cross-border e-commerce self-operation product selection dynamic adjustment method and system, relates to the technical field of e-commerce product selection adjustment, and aims to construct a product selection adsorption quantity model, evaluate the sales attraction of different products in different market situations, analyze the market response condition of each product and improve the product selection efficiency. After the commodities are screened in combination with the output result of the commodity selection adsorption quantity model, the commodities are adaptively adjusted, the racking sequence is determined, the market response condition analysis result is sent to the dynamic optimization module, and based on the market response condition analysis result of the commodities, the discount strength of the commodities is dynamically adjusted by simulating the market dynamic state; according to the analysis of commodity sales data and market feedback, the shelf sequence and marketing promotion strategy of commodities are optimized. According to the adjustment method, through introduction of a machine learning technology and combination of a data driving mode, commodity sales data and market environment changes can be analyzed from multiple dimensions, and commodity selection and adjustment efficiency of a cross-border e-commerce platform is significantly improved.

The invention belongs to the technical field of self-media operation and business decision, and particularly relates to a self-media account business intelligent quotation method and system, and the method comprises the following specific steps: S1, collecting self-media account basic data, user portrait data, commercial value data and market dynamic data; s2, encrypting and storing the sensitive data through AES-256; s3, adopting a random forest algorithm to construct a basic quotation model, and combining account operation fluctuation and market nodes to realize dynamic adjustment; s4, displaying quotation composition details to the account party and supporting parameter adjustment preview; and S5, generating a multi-format personalized quotation list, and negotiating and recording full-link data based on the quotation and the cooperation effect. According to the method and the system, through integrating the self-media account basic data, the user portrait data, the commercial value data and the market dynamic data, the key information influencing the quotation is covered in multiple dimensions, the quotation association factors are comprehensively considered, the deviation caused by single data limitation is reduced, and the quotation accuracy is improved.

The invention relates to the technical field of data processing, in particular to a project application competitiveness analysis system which comprises an acquisition module, a preliminary screening module, a judgment module, a determination module, an adjustment module and an output module. According to the method, multi-dimensional data is acquired in real time, firstly, project keywords are matched with policy keywords, and then key projects are judged by utilizing technology integration density and task dependency density; then, a priority list is determined by integrating the competitive strength, the technical optimization rate and the policy matching degree, in addition, according to the dynamic optimization threshold value of the approval rate, self-adaption policy change and market dynamics, not only is the scientificity of analysis improved, but also the practicability and reliability of the system are enhanced, and finally, by outputting an analysis report, a decision basis of data support is provided for a user, and the user experience is improved. The problems of low project screening accuracy and response lag caused by excessive dependence on models and incapability of adapting to changeable markets and policy environments are effectively solved.

The invention discloses a mobile terminal security quotation analysis system, which relates to the technical field of finance, and comprises a back-end server and a system architecture design module, and the back-end server interacts with a value-added service access module, a real-time data synchronization and updating module and a quotation analysis integrated module. According to the method, the same-screen display of time-sharing and K-line data is realized through the up-down split interface layout, the screen utilization rate is improved, the user experience is optimized, and frequent view switching is avoided; multiple functions such as market quotation, historical query and index analysis are integrated, integrated market analysis is realized, and the depth deficiency in the prior art is made up; market data are synchronized and updated in real time, it is ensured that the user follows the market dynamic state closely, and the delay problem is solved; a value-added service interface is reserved, future expansion is supported, architecture design is flexible, new function integration is facilitated, and market adaptability is enhanced; the convenience and efficiency of security quotation analysis of the mobile terminal are remarkably improved, the user experience is comprehensively improved, and the rapid change requirement of the market is met.

The invention discloses a carbon trading market analysis method and system based on market data, and relates to the technical field of artificial intelligence, and the method comprises the steps: initializing a solver through a four-order Runge-Kutta method, employing symbolic regression and pi-net forward propagation, generating a predicted carbon price curve, calculating the TBPPT truncation length, and employing EMA for smoothing. A time-space gating mechanism is combined with a smooth length to update a hidden state of a starting point, a triangular membership function parameter is randomly set by initializing a particle swarm, Levy flight is used for position updating, Morlet wavelet mutation is used for position mutation, and adjustment is performed by combining a smell concentration mechanism. The Pi-net network is combined with the PNODE differential equation to improve the precision of carbon price prediction, the dynamic characteristics of the carbon market are adaptively captured through the time-space gating mechanism and ST-ODE modeling, and the efficiency and accuracy of transaction instructions are improved through fuzzy rule generation of the triangular membership function and particle swarm optimization.