Digital environment infrastructure system and method

Abstract

The invention discloses a digital environment infrastructure system and method, and relates to the technical field of the Internet, and the system comprises a demand management module which is connected with a target user terminal, and is used for generating a demand list; the supply management module is used for collecting supply information of suppliers in real time and determining the supply state of each supplier; the supply and demand decision module is used for generating and executing an optimal solution based on the demand list and the supply information of the target supplier; the data management module is used for cleaning data and converting the cleaned data into data assets by using a block chain technology, wherein the data is data acquired and generated by each module; and the digital environment intelligent support management module is used for managing the operation state of each module in the implementation process. The invention aims to solve the problems that data splitting and data collaboration are difficult and cross-platform data element circulation and capitalization are difficult to realize due to the fact that an existing digital scheme mostly focuses on a single link or a specific scene.

Description

Technical Field

[0001] This application relates to the field of Internet technology, and in particular to a digital environment infrastructure system and method. Background Technology

[0002] Digital transformation has become a core driver of socio-economic development, with market entities such as households, businesses, and merchants all having digital needs. Among existing technologies, digital solutions represented by SaaS data aggregation platforms (such as "Tianjudihe") and comprehensive life service platforms (such as "Meituan") have achieved data closure and transaction matching within specific areas (such as enterprise data access and local life services).

[0003] However, the above solutions mostly focus on a single link or specific scenario, failing to build an environment covering all entities such as families, enterprises, and merchants. Their architecture leads to data fragmentation, difficulties in data collaboration, and makes it difficult to achieve cross-platform data element circulation and assetization. Summary of the Invention

[0004] The main purpose of this application is to provide a digital environment infrastructure system and method, which aims to solve the technical problems that existing digital solutions often focus on a single link or specific scenario, resulting in data fragmentation, difficulty in data collaboration, and difficulty in realizing cross-platform data element circulation and assetization.

[0005] To achieve the above objectives, this application provides a digital environment infrastructure system, comprising: a digital environment intelligent support management module, a supply and demand decision-making module, a data management module, a demand management module, and a supply management module, all interconnected in pairs; the demand management module is connected to a target user terminal and is used to collect and mine the initial demands of the target users and generate a demand list based on the initial demands; the supply management module is used to collect supplier supply information in real time and determine the supply status of each supplier based on the supply information, wherein the suppliers include at least residential users and enterprise users, and the supply status includes at least the supplier's supply scenario; the supply and demand decision-making module is used to determine at least one target supplier based on the demand list and the supply status of each supplier, and to generate an optimal solution based on the demand list and the supply information of the target supplier, and to execute the optimal solution; the data management module is used to clean the data and use blockchain technology to convert the cleaned data into data assets, wherein the data is the data collected and generated by each module; the digital environment intelligent support management module is used to manage the operational status of each module during implementation.

[0006] Optionally, the demand management module includes a model feedback unit; the model feedback unit is used to obtain the execution result and the feedback effect of the target user after the optimal solution is executed, and transmit the execution result and the feedback effect to the supply and demand decision module so that the supply and demand decision module can optimize the optimal solution.

[0007] Optionally, the supply and demand decision-making module includes a solution generation unit and a solution implementation unit; the solution generation unit is configured with a deep reinforcement learning algorithm and a multi-objective optimization algorithm, and generates an optimal solution based on the demand list and the supply information of the target supplier, using the deep reinforcement learning algorithm and the multi-objective optimization algorithm; the solution implementation unit is connected to the solution generation unit, and is used to execute the optimal solution, and is also used to monitor the execution process of the optimal solution in real time based on robotic process automation and edge computing nodes.

[0008] Optionally, the requirement management module is configured with an NLP model; the requirement management module parses the initial requirement using the NLP model and determines whether the initial requirement is complete; if the initial requirement is complete, the requirement management module generates a requirement list based on the initial requirement; if the initial requirement is incomplete, the requirement management module uncovers hidden requirements and / or guides the target user to supplement the requirements, and generates a requirement list based on the uncovered and / or supplemented requirements.

[0009] Optionally, the demand management module is also configured with multiple API interfaces; the demand management module obtains various public data through the multiple API interfaces so that the target user can determine the initial demand based on the various public data.

[0010] Optionally, the demand management module is also configured with an LSTM model; when the target user is an enterprise user, the demand management module obtains relevant enterprise data through an API interface and predicts market demand trends based on the LSTM model, so that the target user can determine the initial demand based on the market demand trends.

[0011] Optionally, the digital environment intelligent support management module is also used for user expansion, user maintenance, and after-sales service.

[0012] Optionally, the intelligent support management module for the digital environment is further configured with multiple API interfaces; the intelligent support management module for the digital environment is also connected to the target user terminal, and the intelligent support management module for the digital environment obtains various public service information through the multiple API interfaces and sends the various public service information to the target user for confirmation and feedback; the intelligent support management module for the digital environment is also used to receive feedback information from the target user and send the feedback information to multiple public service terminals.

[0013] Optionally, if the supplier includes household users, the supply information includes idle resources and / or personal skills; if the supplier includes enterprise users, the supply information includes enterprise products; if the supplier includes merchant users, the supply information includes merchant products.

[0014] Furthermore, to achieve the above objectives, this application also provides a digital environmental infrastructure method, applying the aforementioned system, comprising: collecting and mining initial needs of target users and generating a demand list based on the initial needs; collecting supply information of suppliers in real time and determining the supply status of each supplier based on the supply information, wherein the suppliers include at least residential users and enterprise users, and the supply status includes at least the supplier's supply scenario; determining at least one target supplier based on the demand list and the supply status of each supplier; and generating an optimal solution based on the demand list and the supply information of the target supplier, and executing the optimal solution.

[0015] This application also provides a controller, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the methods in any of the possible implementations described above.

[0016] This application also provides a computer-readable storage medium, comprising: storing a computer program, wherein when the computer program is executed by a processor, it implements the method in any of the above possible implementations.

[0017] This application proposes a digital environmental infrastructure system and method, which designs a five-in-one neural network collaborative architecture integrating "demand-supply-decision-data-collaboration". The demand management module and supply management module serve as the data collection antennas, the supply and demand decision-making module is the core of decision-making, the data management module realizes a closed loop of assetization of value, and the digital environment intelligent support management module provides global supervision. This distributed, adaptive collaborative architecture fundamentally solves the problems of information silos, decision-making bottlenecks, and rigid governance faced by traditional centralized platforms, forming a self-evolving and self-optimizing digital life form. Attached Figure Description

[0018] Figure 1 A structural block diagram of a digital environment infrastructure system provided in the embodiments of this application; Figure 2 A flowchart of the digital environment infrastructure method provided in the embodiments of this application; Figure 3 This is a schematic diagram of the controller provided in an embodiment of this application.

[0019] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0021] Digital transformation has become a core driver of socio-economic development, with market entities such as households, businesses, and merchants all having digital needs. Among existing technologies, digital solutions represented by SaaS data aggregation platforms (such as "Tianjudihe") and comprehensive life service platforms (such as "Meituan") have achieved data closure and transaction matching within specific areas (such as enterprise data access and local life services).

[0022] However, the above solutions mostly focus on a single link or specific scenario, failing to build an environment covering all entities such as families, enterprises, and merchants. Their architecture leads to data fragmentation, difficulties in data collaboration, and makes it difficult to achieve cross-platform data element circulation and assetization.

[0023] Furthermore, the aforementioned solutions lack intelligent multi-objective decision support and a data value allocation mechanism under privacy protection, resulting in data failing to achieve full-domain collaboration and value feedback under the premise of security and trustworthiness, thus limiting the overall effectiveness of digital transformation.

[0024] To address the aforementioned issues, this application provides a digital environmental infrastructure system and method, which will be described in detail below.

[0025] Figure 1 The following is a structural block diagram of a digital environment infrastructure system provided in an embodiment of this application. The digital environment infrastructure system 100 may include: a supply and demand decision module 110, a data management module 120, a demand management module 130, a supply management module 140, and a digital environment intelligent support management module 150, which are connected in pairs for communication. The demand management module 110 is also connected to the target user terminal (not shown in the figure). The demand management module 110 is used to collect and mine the initial demand of the target user and generate a demand list based on the initial demand. The supply management module 120 is used to collect the supply information of suppliers in real time and determine the supply status of each supplier based on the supply information. The suppliers include at least residential users and enterprise users, and the supply status includes at least the supplier's supply scenario. The supply and demand decision module 130 is used to determine at least one target supplier based on the demand list and the supply status of each supplier, and to generate an optimal solution based on the demand list and the supply information of the target supplier, and to execute the optimal solution. The data management module 140 is used to clean the data and use blockchain technology to convert the cleaned data into data assets. The data consists of data collected and generated by each module. The digital environment intelligent support management module 150 is used to manage the operational status of each module during its implementation.

[0026] It should be noted that the demand management module 110 is responsible for collecting, parsing, modeling and predicting various demands from households, enterprises and merchants, and providing intelligent decision support. The demand management module 110 can solve the problems of vague demands, information lag and high decision error rate in the traditional model.

[0027] In this embodiment of the application, the demand management module 110 is configured with an NLP model. The demand management module 110 first obtains the initial demand of the target user and parses the initial demand of the target user through the NLP model. If the initial demand is complete, a demand list is generated based on the initial demand. If the initial demand is incomplete, hidden demand is discovered and / or the target user is guided to supplement the demand, and a demand list is generated based on the discovered and / or supplemented demand.

[0028] Understandably, when a target user makes a vague request via voice, text, or images (for example, a family user voice-inputs "I want to start a sugar-controlled diet"), the demand management module 110 can accurately analyze their intent and, combined with a knowledge graph, intelligently guide the target user to supplement key information, such as diabetes history, lifestyle habits, and exercise frequency. The demand management module can transform fragmented, unstructured demands into structured data input, thus improving the completeness of the demand profile.

[0029] Furthermore, the demand management module 110 is also configured with multiple API interfaces. The demand management module 110 obtains various public data through these API interfaces so that target users can determine their initial requirements based on the various public data.

[0030] Understandably, the demand management module 110 connects to public data streams from government, meteorology, and disaster management systems in real time via a dedicated API interface. For example, after a rainstorm or geological disaster warning is issued, the demand management module can automatically push evacuation and relocation alerts to families in the affected areas. When a target user clicks on this information, they will receive a notification from the demand management module confirming receipt. Furthermore, the target user can provide feedback on their family's next course of action, facilitating statistical analysis of the target population's disaster relief efforts. The demand management module fundamentally solves the problem of information disconnect between families and public information, significantly improving emergency response speed.

[0031] Furthermore, the demand management module 110 is also configured with an LSTM model. When the target user is an enterprise user, the demand management module obtains relevant enterprise data through the API interface and predicts market demand trends based on the LSTM model, so that the target user can determine the initial demand based on the market demand trend. The relevant enterprise data may include market sales data, online public opinion data, and macroeconomic indicator data.

[0032] Understandably, for enterprise users, the demand management module 110 can utilize deep learning models such as Long Short-Term Memory (LSTM) networks to comprehensively analyze market sales data, online public opinion, and macroeconomic indicators, accurately predicting future market demand trends. This helps enterprises shift from passively responding to the market to proactively leading demand and shortening the new product development cycle.

[0033] It should be noted that the supply management module 120 is responsible for integrating, analyzing and optimizing supply-side resources, which can solve the problems of incomplete supply-side data and inaccurate capacity planning.

[0034] In this embodiment of the application, the supply management module 120 includes an enterprise supply subunit and a household supply subunit. The supply management module 120 collects the supply information of suppliers in real time and determines the supply status of each supplier based on the supply information. The suppliers include at least household users and enterprise users, and the supply status includes at least the supplier's supply scenario.

[0035] When suppliers include enterprise users, the enterprise supply sub-unit can collect the enterprise's supply, production, and sales data into the supply network, and combine it with public information to analyze supply scenarios, thereby enabling reliable and convenient external services and product sales.

[0036] When suppliers include household users, the suppliers' supply information includes idle resources and / or personal skills. Understandably, household users can rent or sell their idle resources (such as spare rooms, land, etc.) and personal skills (such as tutoring, design) through the platform, and realize reliable and convenient external services and asset management through smart contracts.

[0037] It should be noted that the supply management module 120 can collect enterprise production data (blockchain-based evidence storage) and idle household resources (rooms / skills) in real time via IoT / API to construct a knowledge graph of the entire industry chain. Among these, the Dynamic Graph Neural Network (DGNN) integrates the real-time status of the supply side with LSTM time-series prediction to generate supply profiles and provide early warnings of bottlenecks. Household resources are encapsulated as trusted services (such as hourly tutoring contracts) to achieve precise resource matching and flexible scheduling.

[0038] It should be further explained that the supply and demand decision module 130 includes a solution generation unit and a solution implementation unit. It can generate and execute the optimal solution through algorithms such as SHAP and DRL to achieve Pareto optimality for multiple objectives such as cost, efficiency, and risk.

[0039] In this embodiment of the application, the solution generation unit is equipped with a deep reinforcement learning algorithm and a multi-objective optimization algorithm. The solution generation unit can generate the optimal solution based on the demand list and the supply information of the target supplier, and by using the deep reinforcement learning algorithm and the multi-objective optimization algorithm.

[0040] Understandably, the solution generation unit can employ Deep Reinforcement Learning (DRL) and multi-objective optimization algorithms, combined with interpretable AI (XAI) technologies, such as SHAP (SHapley Additive exPlanations). The decision-making logic of the solution generation unit is based on a dynamic reward function, for example: R = 0.6 × Cost Optimization + 0.3 × Risk Hedging - 0.1 × Delay Probability. After receiving the demand list and the supply information of the target supplier, the DRL model explores the data space constituted by the demand list and the supply information of the target supplier to find the action plan that maximizes the reward. Finally, the solution generation unit not only outputs the optimal solution, but also quantifies the contribution of various factors (such as supplier credit, logistics timeliness, and price fluctuations) to the decision through SHAP analysis, presenting it to the user in an interpretable way, for example: "Solution A: Choose supplier X, reduce costs by 15%, and its high credit score can hedge against 30% of the price increase risk (SHAP contribution + 12%)." This greatly enhances the user's trust in the decision.

[0041] It should be noted that the solution generation unit combines the optimization capabilities of Deep Reinforcement Learning (DRL) with the transparency of Explainable AI (SHAP), creating a unique "dual-engine" decision-making mechanism. DRL is responsible for finding the Pareto optimal solution among multiple conflicting objectives such as cost, risk, and timeliness, while SHAP can clearly explain the causes of the decision and quantify the contribution of each factor, solving the "black box" problem of AI decision-making and significantly improving user trust and solution adoption rate.

[0042] The solution implementation unit is connected to the solution generation unit. The solution implementation unit is used to execute the optimal solution and is also used to monitor the execution process of the optimal solution in real time based on robotic process automation and edge computing nodes.

[0043] Understandably, once the optimal solution is confirmed, the implementation unit initiates an automated execution process. First, a blockchain-based smart contract is triggered, automatically executing key steps such as order payment, logistics delivery, and compensation clauses (e.g., "compensation for damage within 48 hours of receipt"), ensuring the immutability and transparency of the transaction. Second, utilizing Robotic Process Automation (RPA) and edge computing nodes, the implementation unit performs real-time automated monitoring of the fulfillment process. For example, it monitors the temperature and humidity of the cold chain logistics and the operating status of equipment on the production line. If any anomalies occur (such as exceeding temperature limits), pre-set compensation or warning processes are immediately triggered, reducing human intervention and fulfillment risks.

[0044] It should be noted that the data management module 140 is responsible for the full lifecycle management of data, building a closed loop of data assetization from collection, cleaning, desensitization, ownership confirmation, packaging to transaction and profit sharing, so as to realize the continuous appreciation of data value.

[0045] In this embodiment, the data management module 140 is used to clean the data and use blockchain technology to convert the cleaned data into data assets. The data is collected and generated by the aforementioned modules. It can be understood that the data management module 140 is applied to data collection, cleaning and de-identification scenarios, data ownership confirmation and packaging (blockchain assetization) scenarios, data trading and dynamic profit-sharing scenarios, and data interaction and value feedback scenarios.

[0046] Specifically, for data collection, cleaning, and de-identification scenarios, the data originates from multiple sources, including DNNS and SNNS. The data management module 140 employs federated learning and homomorphic encryption for "federated cleaning," meaning that model training and data cleaning can be completed without the data leaving its local environment (such as a home server or corporate firewall). In encrypted mode, the data management module 140 can remove directly sensitive identifiers such as ID numbers, but retain statistical features such as age ranges and geographical locations, thereby improving data usability by over 90% while protecting privacy.

[0047] It should be noted that the data management module 140 successfully resolves the core contradiction between "data value utilization" and "personal privacy protection" by combining privacy computing technologies such as federated learning and homomorphic encryption with blockchain smart contracts. Data can be used to extract value without leaving the local storage, and ownership and revenue distribution are achieved through an immutable blockchain. This realizes that data is "usable but not visible" and its value is "trustworthy and divisible," providing a new and feasible technological paradigm for the market-based allocation of data elements.

[0048] In data ownership confirmation and packaging (blockchain assetization) scenarios, the data management module 140 packages high-quality data, after cleaning and de-identification, into standardized "data capsules." The data management module 140 employs an enterprise-grade blockchain framework (such as Hyperledger Fabric) to generate a unique hash value and ownership certificate for each "data capsule." This certificate records metadata such as the data's source, processing procedure, and ownership, and stores it on the blockchain. This ensures the immutability of data ownership and the full traceability of the circulation process, providing a solid foundation of trust for data to be traded as an asset.

[0049] For data trading and dynamic profit-sharing scenarios, the data management module 140 has built a decentralized data asset exchange (DAE). Target users (such as research institutions and financial companies) can bid to purchase "data capsules," and the transaction proceeds are dynamically and automatically distributed through pre-set smart contracts. For example, 70% of the transaction proceeds go to the data provider (household / enterprise), 10% to the data user (such as merchants using data to optimize services), and 20% to the platform. This transparent and fair dynamic profit-sharing mechanism is expected to greatly enhance the digital participation of ecosystem participants.

[0050] In the case of data interaction and value feedback, the data management module 140 safely feeds back the data (such as market trends and changes in user preferences) after the transaction is completed to the demand management module system (DNNS) and the supply management module system (SNNS) through the value-added retraining channel. This forms a value closed loop, enabling the decision-making ability of the entire system to continuously evolve as data continues to circulate.

[0051] It should be noted that the digital environment intelligent support management module 150 is connected to the supply and demand decision module 130, the data management module 140, the demand management module 110 and the supply management module 120 respectively. The digital environment intelligent support management module 150 is used to monitor the operating status of each module.

[0052] It should be noted that the scale of the Digital Environment Intelligent Support Management Module 150 can be determined by the regional scope at various levels (residential area / administrative village, community / township, district / county, provincial, national, or even global). Service stations and experience stores provide development and promotion, customer maintenance, and after-sales coordination services to customers (such as enterprises, families, merchants, and organizations) within each region. The Digital Environment Intelligent Support Management Module 150 is used for developing, promoting, and maintaining customers, monitoring operations within the permission scope of each module in the entire digital environment, and participating in complex after-sales arbitration.

[0053] Specifically, the Digital Environment Intelligent Support Management Module 150 can automatically generate a customer development priority list by analyzing regional economic data, population profiles, and digital device penetration rates, guiding service stations and shared experience stores to target customers. The Digital Environment Intelligent Support Management Module 150 can also construct a graph neural network by continuously analyzing the interaction behavior graphs of various entities within the system (families, enterprises, merchants, service stations, etc.). This graph neural network can intelligently adjust key parameters such as data access permissions, revenue distribution ratios, and dispute arbitration standards to maintain the dynamic balance of the system ecosystem. This allows governance rules to intelligently evolve with the ecosystem, rather than remaining rigid, thus ensuring the long-term fairness and adaptability of the system.

[0054] Furthermore, the digital environment intelligent support management module 150 can also build an access control system based on decentralized identity (DID) and zero-knowledge proof (ZKP) technologies. This allows each participant (individual, enterprise, device) to possess a digital identity under their own control, and any data access request must verify its permissions through ZKP without disclosing the requester's privacy information. For example, district and county-level service stations can only view aggregated statistical data that has been anonymized within their jurisdiction, and cannot access the privacy information of any individual user, thereby ensuring data security and compliance.

[0055] In addition, the digital environment intelligent support management module 150 has established a dedicated API interface with government and public welfare organizations, which enables the accurate dissemination of public services such as policies and regulations, disaster emergency response, and public welfare information. It can also report user confirmations and feedback in a closed loop, thereby seamlessly connecting social public governance capabilities to commercial infrastructure, greatly enhancing the social value of the system in this embodiment and improving the overall emergency response capability of society.

[0056] It should be noted that, in this embodiment, the digital environment intelligent support management module 150 can also build a dynamic rule engine based on graph neural networks (GNNs), abstracting ecosystem participants (individuals, enterprises) as nodes and mapping behavioral interactions as weighted edges. Incremental convolution is used to update parameters such as data permissions and revenue distribution in real time, and decentralized identity (DID) and zero-knowledge proof (ZKP) are combined to achieve privacy protection: user private keys are stored locally, and access requires ZKP verification permissions (such as "anonymized statistics for a certain area"). Furthermore, the digital environment intelligent support management module 150 seamlessly connects to government disaster early warning, policy push, and public welfare feedback through a dedicated API channel (MQTT / blockchain), achieving "rule self-evolution, permission self-verification, and service delivery in seconds."

[0057] In one embodiment, the demand management module 110 further includes a model feedback unit, which is used to obtain the execution results and the feedback effect of the target user after the optimal solution is executed, and transmit the execution results and feedback effect to the supply and demand decision module 130 so that the supply and demand decision module 130 can optimize the optimal solution.

[0058] Understandably, the demand management module 110 will continuously record the implementation effects of the solutions adopted by the target users, such as weight changes and blood pressure indicators in health management scenarios, or asset returns in family management scenarios. The demand management module 110 can use machine learning models to analyze this feedback data, thereby continuously optimizing subsequent solution recommendations, realizing dynamic decision support from "one-time recommendation" to "continuous optimization", and reducing the error rate of family decision-making.

[0059] Those skilled in the art should understand that the division of the various modules in the embodiments is merely a logical functional division. In practical applications, all or part of these modules can be integrated onto one or more actual carriers. Furthermore, these modules can be implemented entirely in software through processing unit calls, entirely in hardware, or a combination of software and hardware. The differences between the embodiments of this application and the SaaS data aggregation platform "Tianjudihe" and Meituan can be seen in Tables 1 and 2 below:

[0060] Table 1. Comparison of the differences between the embodiments of this application and the SaaS data aggregation platform "Tianjudihe".

[0061] Table 2 Comparison of the differences between the embodiments of this application and Meituan's. This application proposes and designs a five-in-one neural network collaborative architecture integrating "demand-supply-decision-data-collaboration." The demand management module 110 and supply management module 120 serve as the data acquisition points, the supply and demand decision-making module 130 is the decision-making core, the data management module 140 realizes a closed loop of value assetization, and the digital environment intelligent support management module 150 provides global oversight. This distributed, adaptive collaborative architecture fundamentally solves the problems of information silos, decision-making bottlenecks, and rigid governance faced by traditional centralized platforms.

[0062] Furthermore, this system overturns the traditional platform's profit model based on information asymmetry and traffic commission, reconstructing the logic of commercial value distribution. Through data assetization and intelligent profit-sharing mechanisms, every participant in the ecosystem transforms from a mere "user" into a "value co-creator." Families can earn thousands of yuan annually by contributing data, businesses can significantly improve their capacity utilization, and merchants can drastically reduce customer acquisition costs.

[0063] The embodiments of this application use the following two specific examples to further illustrate the above embodiments: Example 1: Scenario: Mr. Zhang's father has a history of hypertension and chronic gastritis, and recently his physical activity has decreased, while his diet has become more salty. Mr. Zhang hopes to obtain a scientific health management plan for his father through this system.

[0064] Requirements Management Module: Mr. Zhang entered "Create a blood pressure control and health plan for my father" into the family app (user terminal). DNNS immediately initiated multimodal data collection and analysis: First, the system automatically accessed authorized smart bracelet data (daily average steps <3000), electronic medical records (systolic blood pressure >140mmHg), and dietary logs (sodium intake exceeding the recommended level by 30%). Subsequently, the NLP semantic parsing engine proactively guided the user: "We detected that your father is deficient in potassium. Does he need to supplement with high-potassium foods?" After the user confirmed, the system ultimately generated a structured health profile, including tags such as "hypertension," "low exercise," and "high-sodium diet," and uncovered hidden needs such as "blood pressure control devices," "low-sodium diets," and "rehabilitation guidance."

[0065] Supply Management Module: Upon receiving structured demands, the supply management module immediately matches them within the supply network. The system uses a full-supply chain analyzer to access digital twin models of suppliers, filtering out qualified suppliers such as medical device company A (blood pressure monitor accuracy ±2mmHg, sufficient inventory) and health food company B (low-sodium meals ≤400mg / serving, cold chain coverage radius 20km). Simultaneously, its dynamic capacity simulation, using the TCN model, predicts that company B's inventory of a key ingredient (such as spinach) is only sufficient for 48 hours, immediately triggering a supply bottleneck warning and automatically recommending backup supplier D (whose products have higher potassium content).

[0066] Supply and demand decision-making module: The supply and demand decision-making module's solution generation unit begins multi-objective decision optimization. The DRL algorithm calculates based on the reward function R = 0.5 × health matching degree + 0.3 × timeliness - 0.1 × cost - 0.1 × risk. Ultimately, the engine generates a comprehensive solution, explained using SHAP (SHapley Additive exPlanations): "Recommended solution: Purchase Company A's smart arm blood pressure monitor (¥199, accuracy +10%), Restaurant D's high-potassium, low-sodium meals (¥40 / day, guaranteed inventory), and Rehabilitation Institution C's in-home physiotherapy (¥150 / session, available today or tomorrow). Restaurant D was chosen because its potassium content exceeds the average by 20% (contributing +35% to health weight), while excluding another institution with a credit score below 80 (risk weight -15%)." Supply and demand decision-making module and digital environment intelligent support management module: After Mr. Zhang confirmed the plan, the implementation unit of the supply and demand decision-making module triggered the smart contract, automatically pre-freezing the account funds and issuing instructions to each supplier (such as requiring Company A to deliver the goods within 1 hour). At the same time, the digital environment intelligent support management module monitored the performance process in real time: it automatically monitored the temperature of the cold chain truck carrying the food through robotic processes, and automatically triggered compensation if the temperature exceeded 8°C; it also verified the delivery location of the blood pressure monitor through GPS to ensure accurate delivery.

[0067] Data Management Module: All performance data generated during this service (such as delivery temperature, receipt status, blood pressure changes, and dietary feedback) was collected by the data management module. After federated cleaning and anonymization, this data was packaged into an anonymous "Hypertension Health and Wellness Data Capsule" and listed on the Data Asset Exchange (DAE). A pharmaceutical company purchased this data capsule (containing thousands of similar data sets) for 100,000 yuan for the purpose of developing sustained-release potassium tablets. After the transaction was completed, the smart contract automatically executed profit sharing, and Mr. Zhang's family received the data revenue. At the same time, the blood sugar control demand trend data for the region was fed back to the data management module to optimize the next solution recommendation.

[0068] It should be noted that in this example, Mr. Zhang's father's blood pressure control rate improved by 90%; the health catering company D expanded its production due to the acquisition of precise orders, resulting in a 25% increase in quarterly revenue; the pharmaceutical company's R&D efficiency improved by 50%; and Mr. Zhang's family also upgraded from pure consumers to data producers and value sharers, realizing continuous returns on data assets.

[0069] Example 2: Scenario setting: Company A needs to sell 5 million self-developed flagship mobile phones (each priced at 2,000 yuan). The system will verify the effectiveness of the shared experience store channel in stages and dynamically adjust the sales strategy.

[0070] The company inputs a sales target: "Sell 5 million flagship phones in one quarter." The system responds: "Verify the feasibility of selling out in a single week by conducting a trial sale of 100 units. If the target is achieved, expand the quantity to 10,000 units, and ultimately strive for 5 million units."

[0071] Requirements Management Module: The demand management module initiates multimodal analysis: analyzing historical data (only 5% of models in the same price range sold out in the first week), social media buzz (the popularity of the keyword "5G flagship" increased by 180% month-on-month), and competitor dynamics (Brand B released a price war announcement on the same day). It proactively asks users and completes the parameters: "Do we need to test the penetration rate of installment payments? Please specify the key verification areas." After confirmation, demand tags are generated: "High-price market elasticity verification", "Shared experience store density optimization", and "Financial instrument coupling".

[0072] Supply Management Module: The supply management module schedules shared experience store units within the digital environment intelligent support management module. Specifically, it matches 10 high-potential stores within a 3-kilometer radius (historical conversion rate >25%, customer traffic >50 people / day) and generates a profit-sharing smart contract template (base 12% + excess bonus 3%). Furthermore, the supply management module triggers dynamic bottleneck warnings: detecting that the density of competitors surrounding 3 stores in the Shanghai area exceeds a threshold (>5 stores / square kilometer), triggering a "red zone breakthrough" protocol. The supply management module also calls upon the financial module for integration, automatically linking to a bank's installment service API (12-month interest-free period with a 4.5% fee).

[0073] Supply and Demand Decision Module: The solution generation unit of the supply and demand decision module generates three-stage solutions and interprets them through SHAP (SHapley Additive exPlanations). Phase 1 (Trial Sales): Allocate 100 units to 10 shared experience stores, with a target of selling out 80 units within 7 days; The decision-making criteria included: high-conversion stores had a customer acquisition cost that was 52% lower than online (SHAP+28%), and installment payments could increase impulse purchase rates by 37% (SHAP+19%). Phase 2 (Expansion): Once the target is met, sales of 10,000 units will commence, covering 2,000 shared experience stores.

[0074] The dynamic strategy is as follows: additional "trade-in" subsidies will be provided to stores in the red zone (up to 800 yuan off, SHAP+22%). Phase 3 (Final Offensive): 5 million units were fully distributed, and a hybrid channel of "90% shared stores + 10% online KOCs" was adopted; Among them, stores with a conversion rate consistently below 5% are excluded (risk weight -30%).

[0075] Supply and demand decision-making module and digital environment intelligent support management module: The supply and demand decision-making module's implementation unit automatically executes the above plan, sets up an on-chain contract to freeze a trial sales deposit of 200,000 yuan, opens up sample machine application permissions to 10 stores, and automatically loads subsidy contracts for stores in the red zone (the old machine valuation model calculates the discount in real time).

[0076] During the implementation of the plan, the digital environment intelligent support management module controls the plan in real time. Specifically, the digital environment intelligent support management module monitors the store sales video stream (which has been de-identified) through robotic process automation. On the third day, it identifies that a store in Beijing is sold out (triggering expansion preparation). When it detects that the sales of the second store in Shanghai are 0 on the first day, it automatically activates the "breakthrough package": 1) targeted advertising within a 3-kilometer radius; 2) temporary increase in profit sharing to 18%.

[0077] Data Management Module: Federated cleaning of trial sales data: Encapsulation of "high-end machine decision funnel" capsules (including installment payment conversion rate, competitor confrontation threshold, and store location gain coefficient).

[0078] Data capsule transactions:

[0079] Feedback and optimization: Input the characteristics of high-conversion stores into SNNS, and the site selection accuracy will be improved to 95% in the next stage.

[0080] It's worth noting that in this example, 10 stores sold out 102 units within 72 hours (a 127% success rate), shortening the verification cycle by 5.8 times compared to traditional channels. The conversion rate for stores in Shanghai's high-risk areas increased from 0% to 35% (the subsidy strategy reduced price sensitivity by 22 percentage points). Furthermore, this example avoided the 28.6 million RMB sunk cost incurred from blindly stocking up, ensured that trial sales data covered 23% of marketing costs, and boosted the model, increasing the first-week sell-through rate of 5 million units to 19% (compared to the industry average of 7%).

[0081] Figure 2A flowchart of a digital environment infrastructure method provided in an embodiment of this application is shown below. Figure 2 As shown, the method may include: S21. Collect and analyze the initial needs of target users and generate a requirements list based on the initial needs; S22. Collect supplier supply information in real time and determine the supply status of each supplier based on the supply information. Suppliers include at least residential users and enterprise users, and the supply status includes at least the supplier's supply scenario. S23. Based on the demand list and the supply status of each supplier, determine at least one target supplier, and generate an optimal solution based on the demand list and the supply information of the target supplier, and execute the optimal solution.

[0082] It should be noted that each step in the digital environment infrastructure method in this embodiment corresponds one-to-one with each module in the digital environment infrastructure system in the aforementioned embodiment. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned digital environment infrastructure system, and will not be repeated here.

[0083] Based on the above embodiments, Figure 3 This is a schematic diagram of the controller according to one embodiment of this application, as shown below. Figure 3 As shown, the controller may include a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute the aforementioned digital environment infrastructure method.

[0084] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0085] Based on the above embodiments, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute a digital environment infrastructure method provided by the above methods.

[0086] Based on the above embodiments, in another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform a digital environment infrastructure method provided in the above embodiments.

[0087] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A digital environmental infrastructure system, characterized in that, The system includes: a digital environment intelligent support management module, a supply and demand decision-making module, a data management module, a demand management module, and a supply management module, all of which are connected in pairs for communication. The demand management module is connected to the target user terminal. The demand management module is used to collect and mine the initial demand of the target user and generate a demand list based on the initial demand. The supply management module is used to collect the supply information of suppliers in real time and determine the supply status of each supplier based on the supply information. The suppliers include at least household users and enterprise users, and the supply status includes at least the supplier's supply scenario. The supply and demand decision module is used to determine at least one target supplier based on the demand list and the supply status of each supplier, and to generate an optimal solution based on the demand list and the supply information of the target supplier, and to execute the optimal solution. The data management module is used to clean the data and use blockchain technology to convert the cleaned data into data assets. The data is the data collected and generated by each module. The digital environment intelligent support management module is used to manage the operational status of each module during its implementation.

2. The system according to claim 1, characterized in that, The demand management module includes a model feedback unit; The model feedback unit is used to obtain the execution result and the feedback effect of the target user after the optimal solution is executed, and transmit the execution result and the feedback effect to the supply and demand decision module so that the supply and demand decision module can optimize the optimal solution.

3. The system according to claim 1, characterized in that, The supply and demand decision-making module includes a scheme generation unit and a scheme implementation unit; The solution generation unit is equipped with a deep reinforcement learning algorithm and a multi-objective optimization algorithm. The solution generation unit generates the optimal solution based on the demand list and the supply information of the target supplier, using the deep reinforcement learning algorithm and the multi-objective optimization algorithm. The solution implementation unit is connected to the solution generation unit. The solution implementation unit is used to execute the optimal solution. The solution implementation unit is also used to monitor the execution process of the optimal solution in real time based on robotic process automation and edge computing nodes.

4. The system according to claim 1, characterized in that, The demand management module configures the NLP model; The requirement management module parses the initial requirement using an NLP model and determines whether the initial requirement is complete. If the initial requirements are complete, the requirements management module generates a requirements list based on the initial requirements. If the initial requirements are incomplete, the requirements management module will uncover hidden requirements and / or guide the target user to supplement the requirements, and generate a requirements list based on the uncovered and / or supplemented requirements.

5. The system according to claim 4, characterized in that, The demand management module is also configured with multiple API interfaces; The demand management module obtains various public data through multiple API interfaces, enabling the target user to determine the initial demand based on the various public data.

6. The system according to claim 5, characterized in that, The demand management module is also configured with an LSTM model; When the target user is an enterprise user, the demand management module obtains relevant enterprise data through the API interface and predicts market demand trends based on the LSTM model, so that the target user can determine the initial demand based on the market demand trends.

7. The system according to claim 1, characterized in that, The digital environment intelligent support management module is also used for user expansion, user maintenance, and after-sales service.

8. The system according to claim 7, characterized in that, The digital environment intelligent support and management module is also configured with multiple API interfaces; The digital environment intelligent support management module is also connected to the target user terminal. The digital environment intelligent support management module obtains various public service information through the multiple API interfaces and sends the various public service information to the target user for the target user to confirm and provide feedback. The digital environment intelligent support management module is also used to receive feedback information from the target user and send the feedback information to multiple public service terminals.

9. The system according to claim 1, characterized in that, In cases where the supplier includes household users, the supply information includes idle resources and / or personal skills; In the case where the supplier includes enterprise users, the supply information includes enterprise products; In the case where the supplier includes merchant users, the supply information includes merchant products.

10. A method for digital environmental infrastructure, characterized in that, Applied to the system according to any one of claims 1-9, the method comprises: Collect and analyze the initial needs of target users and generate a needs list based on the initial needs; The system collects supply information from suppliers in real time and determines the supply status of each supplier based on the supply information. The suppliers include at least residential users and enterprise users, and the supply status includes at least the supplier's supply scenario. Based on the demand list and the supply status of each of the suppliers, at least one target supplier is determined, and an optimal solution is generated based on the demand list and the supply information of the target supplier, and the optimal solution is executed.

Images