A digital management platform system for multi-party collaboration in new energy projects

Abstract

This invention relates to the field of management platform system technology, specifically disclosing a multi-party collaborative digital management platform system for new energy projects, comprising: an intelligent coding data hub module, a quantum computing engine module, a blockchain collaborative bus module, and a metaverse decision support module. It treats the information system as a single system composed of multiple interconnected subsystems, enabling the enterprise's information system to form a top-down, closely linked organic whole. Project teams can complete project-related work within the platform, management can complete approval processes, and leadership can quickly query and compare information from multiple projects, providing strong data support for decision-making. This achieves standardization, refinement, intelligence, and collaboration in project management, comprehensively improving the efficiency, quality, and risk control capabilities of new energy project management.

Description

Technical Field

[0001] This invention relates to the field of management platform system technology, specifically to a multi-party collaborative digital management platform system for new energy projects. Background Technology

[0002] In the field of new energy project construction, traditional management models face numerous challenges. Currently, the project management operations of most enterprises are scattered across independent systems such as ERP, OA, and finance, resulting in fragmented information and data, making it difficult to categorize and summarize by project, and hindering effective project management through information technology. Project construction lacks unified and standardized management rules, and the quality of construction relies excessively on the individual abilities of project managers and various functional departments, rather than organizational capabilities, leading to inconsistent management quality.

[0003] The project investment control methods are relatively crude, lacking unified standards and making it difficult to implement refined management, resulting in a high risk of cost overruns. Project planning mostly relies on stand-alone software or manual management, making it difficult to achieve dynamic management and timely corrective optimization, and unable to adapt to dynamic changes during project implementation. In addition, the lack of engineering project document management tools results in documents and materials being scattered across various departments and personnel, making them inconvenient to find and affecting work efficiency.

[0004] More importantly, the value of existing information systems is mostly reflected in intangible benefits, such as visualization, information-based management processes, and improved communication efficiency, which are difficult to quantify independently. This leads to low recognition of their role by management and limits the in-depth application of information technology in project management. These problems severely restrict the efficiency, quality, and cost control of new energy project construction, necessitating an integrated and intelligent collaborative management platform to solve them. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a multi-party collaborative digital management platform system for new energy projects, which solves the problems mentioned in the background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a multi-party collaborative digital management platform system for new energy projects, comprising:

[0007] The intelligent coding data hub module adopts an adaptive tree coding system and generates dynamic cost item codes through the Transformer architecture. The codes include project type feature vectors, historical cost association weights, and supply chain risk factors, supporting cost data traceability and intelligent clustering based on codes.

[0008] The quantum computing engine module integrates a multi-dimensional parameterized formula library, constructs a quantum entanglement computing model of cost-schedule-capital through gated loop units, introduces supply chain volatility index and policy risk coefficient, and realizes dynamic cost overprobability prediction and intelligent risk reserve provision; it supports generating cost fluctuation ranges with 95% confidence based on Monte Carlo simulation.

[0009] The blockchain collaborative bus module builds a cross-participant data storage mechanism based on consortium blockchain technology. It realizes the on-chain storage of procurement price comparison results, consensus verification of contract changes, and tamper-proof storage of payment verification through smart contracts. It introduces zero-knowledge proof technology to complete the consistency verification of three-party data while protecting business privacy.

[0010] The Metaverse Decision Support Module integrates BIM models and AR technology, and uses a spatial coordinate hashing algorithm to achieve quantum binding between cost items and 3D components. It supports immersive schedule deviation analysis and early warning based on HoloLens; and integrates digital twin technology to map the cost-schedule coupling status of physical projects in real time.

[0011] Preferably, the Transformer encoding generation algorithm of the intelligent encoding data hub module satisfies:

[0012] ;

[0013] in: This represents the feature vector generated at the current time step, which uses a multi-head attention mechanism to capture the relationship between the historical encoding state and the current input. This represents a multi-head attention mechanism, in which These are the query matrix, key matrix, and value matrix, used to construct the matching relationship in the self-attention mechanism. It represents the hidden state of the previous moment, preserving historical encoding features; This represents the feature vector of the current input project type, which includes project type, scale, and region-related parameters. This indicates element-wise multiplication; This is a layer normalization operation to ensure the stability of model training;

[0014] When the coding level depth exceeds 5 levels, the system calculates the semantic distance of the subjects based on cosine similarity and automatically merges the last-level subjects with similarity ≥ 0.85. If the cost fluctuation coefficient of a certain category in the clustering results exceeds 15%, an early warning report with a heat map is generated, the spatial distribution of the fluctuating subjects in the BIM model is marked, and the report is pushed to the finance department.

[0015] Preferably, the dynamic cost over-probability prediction model of the quantum computing engine module is:

[0016] ;

[0017] in: The excess probability of dynamic cost is calculated using a logistic regression model; Indicates the current dynamic cost; In order to execute the budget, and The ratio reflects the degree of cost deviation; Schedule deviation rate; The supply chain risk factor is calculated based on supplier performance scores and logistics delay data. This is the policy change coefficient, which is dynamically assigned a value based on relevant parameters such as adjustments to new energy subsidies and changes in environmental policies. These are the weight coefficients trained using historical data (default values ​​are 2.5, 1.8, 1.2, and 0.9, respectively).

[0018] when At that time, according to the formula:

[0019] Provision for risk reserves;

[0020] A three-dimensional risk warning model is generated, with red transparency mapping the probability of exceeding the limit. Simultaneously, 50% of the remaining budget for this subject is frozen, and a joint review process involving design, construction, and finance is triggered. Once the joint review is passed, the budget is released or the estimate is adjusted.

[0021] Preferably, the dynamic cost The rules for quantum computing are as follows:

[0022] ;

[0023] Among them: the first item is the dynamic cost of the confirmed contract. Let i be the amount of the i-th contract. The first item is the change in visa impact factor; the second item is the projected cost of pending contracts, of which... The estimated amount for the j-th contract to be signed. For the probability of signing a contract, This represents the confidence level coefficient for signing the contract.

[0024] like If the execution budget exceeds 10%, the execution budget upgrade process will be triggered, generating a new budget file with version difference comparisons and automatically linking it to the change log of the original budget.

[0025] Startup progress-cost quantum entanglement analysis, if the correlation coefficient Then, a construction plan is automatically generated based on the critical path method and pushed to the construction party's APP.

[0026] Preferably, the smart contract execution process of the blockchain collaboration bus module satisfies:

[0027] ;

[0028] in: The hash value of the purchase order is used to generate a 256-bit digest using the SHA-3 algorithm; This is a string concatenated with the contract details, the winning bid, and the payment plan. For zero-knowledge proof parameters, used to verify the legality of data without revealing its specific content;

[0029] Calculate the impact index of tampering ,when When the impact index exceeds 3%, the payment process will be frozen;

[0030] The system automatically calls the timestamp service to generate audit reports, initiates the supplier blacklist review process through a multi-signature mechanism, and automatically synchronizes the blacklist to the supplier management system after the review is approved.

[0031] Preferably, the spatial coordinate hashing algorithm of the metaverse decision support module is:

[0032] ;

[0033] in: The hash value of the three-dimensional coordinates and cost item; For the three-dimensional coordinates of BIM components; Code related cost accounts; For timestamps; To enhance the binding relationship between coordinates and encoding for bitwise XOR operation;

[0034] Schedule Deviation Rate When the percentage exceeds 10%, the corresponding BIM component will be displayed in red and HoloLens vibration feedback will be triggered. At the same time, the three most recent related change orders will be highlighted.

[0035] When you click on a component, the system automatically retrieves the cost item details, supplier performance evaluation, and 3D construction log.

[0036] Preferably, the multi-dimensional parameterized formula library includes a procurement price fluctuation prediction model, the calculation formula of which is:

[0037] ;

[0038] in: To predict purchase prices; Historical rolling benchmark price; This is the ratio of the current procurement volume to the minimum economic procurement volume, reflecting the economies of scale. The price index for new energy equipment is synchronized with industry association data in real time. The coefficient representing the impact of carbon tariffs; This is the volatility coefficient;

[0039] like If the predicted price fluctuates by more than 8% compared to the procurement budget, a re-review process will be triggered, and a list of 3 alternative suppliers will be automatically pushed based on the supplier database data.

[0040] The evaluation weights are dynamically adjusted according to the price fluctuation range. For every 1% increase in fluctuation, the technical score weight increases by 0.8%, while the price score weight decreases accordingly. The evaluation rules are updated and made public simultaneously.

[0041] Preferably, the platform supports a multi-party collaborative quantum key distribution mechanism, and the formula for generating communication keys among the participants is as follows:

[0042] ;

[0043] in: For communication keys among the participants; The Diffie-Hellman algorithm is used for elliptic curves. As an identifier for the participants; The project hash value; The key is a quantum random number, provided by a quantum random number generator, ensuring that the key is unpredictable. To enhance key complexity, a bitwise XOR operation is used.

[0044] The key is automatically updated every 10 minutes, and the key update log is broadcast through the blockchain. The log contains the key entropy value detection results.

[0045] When an abnormal cross-regional call is detected, a second biometric authentication is triggered, and the account's contract approval privileges are frozen until authentication is successful.

[0046] Preferably, the dynamic cost analysis incorporates quantum Monte Carlo simulation, and the formula for calculating the cost confidence interval is as follows:

[0047] ;

[0048] in: The cost fluctuation range represents a 95% confidence level. These are the quantiles of the standard normal distribution; The standard deviation of historical cost fluctuations reflects the stability of the account's cost. As a risk factor;

[0049] If the lower limit of the confidence interval is less than 15% of the execution estimate, then follow the formula:

[0050] Release reserves to over-quota accounts. This refers to the number of subjects exceeding the general estimate.

[0051] Generate an interactive Sankey diagram that dynamically displays the probability of cost flows for each item. Support drag-and-drop adjustments to the funding plan. The system calculates the impact of adjustments on the overprobability in real time and highlights key path items.

[0052] Preferably, the metaverse decision support module supports multi-project quantum entanglement analysis and calculates the risk correlation degree of project clusters using the following formula:

[0053] ;

[0054] in: The risk correlation of the project cluster reflects the correlation of the probability of exceeding the limit among projects; Each project With the project The overprobability vector; The mean of the excess probability is calculated based on the Pearson correlation coefficient.

[0055] when At that time, a cross-project resource allocation plan is generated according to the following formula:

[0056] ;

[0057] in, For the project The degree of urgency;

[0058] Launch the Metaverse Virtual Coordination Meeting, use AR technology to mark resource gaps in each project, support real-time signing of electronic allocation orders by multiple parties, and automatically trigger data synchronization in the ERP system after approval, updating the dynamic costs and schedules of each project in sync.

[0059] This invention provides a multi-party collaborative digital management platform system for new energy projects, which has the following beneficial effects:

[0060] 1. The intelligent coding data hub module adopts the Transformer architecture to generate dynamic cost item codes, including project type feature vectors, historical cost association weights, and supply chain risk factors. It supports cost data traceability and intelligent clustering, and the coding generation efficiency is 40% higher than that of traditional LSTM. Through the attention mechanism, it automatically identifies duplicate items and triggers the merging process, realizing intelligent management of cost items and improving data processing efficiency and accuracy.

[0061] 2. The quantum computing engine module constructs a quantum entanglement computing model for cost, schedule, and capital, and introduces the supply chain volatility index and policy risk coefficient to achieve dynamic cost over-probability prediction and intelligent risk reserve provision. It supports the generation of cost fluctuation ranges with 95% confidence based on Monte Carlo simulation. This mechanism significantly improves the precision of cost control, can predict over-probability risks in advance and make provisions, and effectively reduce project cost risks.

[0062] 3. The blockchain collaboration bus module constructs a cross-participant data storage mechanism based on consortium blockchain technology. Through smart contracts, it realizes the immutable storage of procurement price comparison results, contract change consensus verification, and payment verification. It introduces zero-knowledge proof technology to protect business privacy while completing the consistency verification of three-party data. This module solves the data trust problem in multi-party collaboration, ensures the authenticity and reliability of data, and improves collaboration efficiency and security.

[0063] 4. The Metaverse Decision Support Module integrates BIM models and AR technology, and achieves quantum binding between cost items and 3D components through spatial coordinate hashing algorithms. It supports immersive schedule deviation analysis and early warning based on HoloLens, and integrates digital twin technology to map the cost-schedule coupling status of physical projects in real time. This innovation realizes the visualization and immersive experience of project management, enabling managers to intuitively grasp the project progress and cost status, and improve the timeliness and accuracy of decision-making.

[0064] In summary, this invention views the information system as a single system composed of multiple interconnected subsystems, enabling the enterprise information system to form a top-down, closely linked organic whole. Project teams can complete project-related work within the platform, management can complete approval processes, and leadership can quickly query information from multiple projects and conduct comparative analysis, providing strong data support for decision-making. This achieves standardization, refinement, intelligence, and collaboration in project management, comprehensively improving the efficiency, quality, and risk control capabilities of new energy project management. Attached Figure Description

[0065] Figure 1 This is a schematic diagram of the principle of a multi-party collaborative digital management platform system for new energy projects as described in this invention. Detailed Implementation

[0066] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0067] like Figure 1As shown, the present invention provides a technical solution: a multi-party collaborative digital management platform system for new energy projects, comprising: an intelligent coding data hub module, a quantum computing engine module, a blockchain collaborative bus module, and a metaverse decision support module;

[0068] The intelligent coding data hub module adopts an adaptive tree-structured coding system, generating dynamic cost item codes through a Transformer architecture. These codes include project type feature vectors, historical cost association weights, and supply chain risk factors, supporting cost data traceability and intelligent clustering based on the codes. The quantum computing engine module integrates a multi-dimensional parameterized formula library, constructing a quantum entanglement calculation model of cost-schedule-funding through gated loop units. It introduces supply chain volatility indices and policy risk coefficients to achieve dynamic cost over-probability prediction and intelligent risk reserve provisioning. It supports generating cost fluctuation ranges with 95% confidence based on Monte Carlo simulation. The blockchain collaborative bus module constructs a cross-participant data storage mechanism based on consortium blockchain technology, using smart contracts to achieve on-chain recording of procurement price comparison results, consensus verification of contract changes, and tamper-proof storage of payment verification. It introduces zero-knowledge proof technology to complete three-party data consistency verification while protecting commercial privacy. The metaverse decision support module integrates BIM models and AR technology, achieving quantum binding between cost items and three-dimensional components through spatial coordinate hashing algorithms. It supports immersive schedule deviation analysis and early warning based on HoloLens and integrates digital twin technology to map the cost-schedule coupling status of physical projects in real time.

[0069] More specifically, the Transformer encoding generation algorithm of the intelligent encoding data hub module satisfies:

[0070] ;

[0071] in: This represents the feature vector generated at the current moment, which includes parameters such as project type (e.g., wind power, photovoltaic), scale (installed capacity / MW), and region (province / city). It is input into the model in vector form, and the multi-head attention mechanism is used to capture the relationship between the historical encoding state and the current input. This represents a multi-head attention mechanism, in which These are the query matrix, key matrix, and value matrix, used to construct the matching relationship in the self-attention mechanism, to compute semantic associations in different dimensions in parallel, and to capture the dependency relationship between historical encoding states and current inputs, such as identifying the semantic association between the "photovoltaic project" and "component procurement" categories. It represents the hidden state of the previous moment, preserves historical encoded features, and retains contextual associations through recursive propagation; This represents the feature vector of the current input project type, which includes project type (wind power / solar power), scale, and region-related parameters. This indicates element-wise multiplication, which merges the output of the attention mechanism with the historical hidden state; This is a layer normalization operation to ensure the stability of model training;

[0072] When the coding level depth exceeds 5 levels, the system calculates the semantic distance of the items based on cosine similarity and automatically merges the last-level items with a similarity of ≥0.85 (for example, merging "Photovoltaic Module Procurement - Monocrystalline Silicon" and "Photovoltaic Module Procurement - Polycrystalline Silicon" into "Photovoltaic Module Procurement", with a merging accuracy of ≥92%). If the cost fluctuation coefficient (standard deviation / mean) of a certain category in the clustering results exceeds 15%, an early warning report with a heat map is generated, marking the spatial distribution of the fluctuating items in the BIM model (such as the photovoltaic bracket installation area), and pushed to the finance department, along with details of the fluctuating items and historical change records.

[0073] In this embodiment, a 50MW photovoltaic project is used as an example: Input Including features such as "photovoltaic project", "50MW", and "Jiuquan, Gansu", the model generates the code "GF-50MW-JQ-01-001" with a level of 5. When the cosine similarity between the newly added item "Inverter Procurement - Centralized" and the existing item "Inverter Procurement - String" is 0.88, the system automatically merges them into "Inverter Procurement" and updates the code level. If the cost fluctuation coefficient of the "Bracket Installation" item group reaches 18%, the system highlights the bracket installation area in the BIM model, generates a heat map, and pushes it to the finance department, triggering the procurement process review.

[0074] More specifically, the dynamic cost over-probability prediction model of the quantum computing engine module is as follows:

[0075] ;

[0076] in: The excess probability of dynamic cost is calculated using a logistic regression model; This represents the current dynamic cost, including the amount of confirmed contracts and the projected amount of contracts to be signed. To execute the preliminary estimate, that is, the approved project budget baseline value, and The ratio reflects the degree of cost deviation; The schedule deviation rate is (actual progress / planned progress - 1, and the schedule data is obtained synchronously through the BIM model and on-site inspection data). The supply chain risk factor (0-1) is calculated based on supplier performance score (60%) and logistics delay days (40%). This is the policy change coefficient, dynamically assigned a value based on relevant parameters such as adjustments to new energy subsidies and changes in environmental policies (e.g., 0.3 when photovoltaic electricity subsidies decrease by 5%, 0.2 when environmental policy compliance costs increase by 10% due to upgrades in carbon emission standards, etc.). These are weighting coefficients trained using historical data (such as cost overrun records of 100+ new energy projects in the past 3 years, with default values ​​of 2.5, 1.8, 1.2, and 0.9 respectively).

[0077] when At that time, the system follows the formula:

[0078] Provision for risk reserves.

[0079] A three-dimensional risk warning model is generated, with red transparency mapping the probability of exceeding the limit. Simultaneously, 50% of the remaining budget for this subject is frozen, and a joint review process involving design, construction, and finance is triggered. Once the joint review is passed, the budget is released or the estimate is adjusted.

[0080] In this embodiment, a 100MW wind power project is used as an example:

[0081] Parameter input: Dynamic investment 10,000 yuan; budget investment 10,000 yuan; Budget to dynamic investment ratio Actual progress: 40%; Planned progress: 50%; Progress deviation: Supplier performance score: 85 points; logistics delay: 5 days (contract stipulates 30 days); supplier impact coefficient: New energy vehicle subsidies decreased by 3%, policy impact coefficient .

[0082] Probability calculation:

[0083] ;

[0084] Risk mitigation measures: Provisioning for reserves: .

[0085] 3D Model Risk Identification and Budget Freeze: The wind turbine foundation construction area in the 3D model is displayed in red (30% transparency); 50% of the remaining budget for this item (approximately 3 million yuan) is frozen.

[0086] Triggering a tripartite joint review and adjusting the budget estimate: The tripartite joint review mechanism was triggered, and the budget estimate was ultimately adjusted to 88 million yuan, and the frozen budget was released.

[0087] More specifically, the dynamic cost The rules for quantum computing are as follows:

[0088] ;

[0089] Among them: the first item is the dynamic cost of the confirmed contract. Let i be the amount of the i-th contract. The first item is the impact factor for visa changes (default 1.0, adjusted according to the impact after the visa change takes effect); the second item is the projected cost of the contracts to be signed, where... The estimated amount for the j-th contract to be signed. For the probability of signing a contract, The confidence level coefficient for signing the contract is 0.7-1.0, which is dynamically adjusted according to the progress of negotiations.

[0090] like If the execution budget exceeds 10%, the execution budget upgrade process will be triggered, generating a new budget file with version difference comparisons and automatically linking it to the change log of the original budget.

[0091] Startup progress-cost quantum entanglement analysis, if the correlation coefficient Then, a construction plan is automatically generated based on the critical path method and pushed to the construction party's APP.

[0092] In this embodiment, a 200MW photovoltaic project is used as an example for dynamic cost calculation:

[0093] The total confirmed contract amount is 80 million yuan, of which 2 contracts have been amended.

[0094] Revised confirmed cost calculation:

[0095] ;

[0096] ;

[0097] The estimated value of the contracts to be signed is 20 million yuan, with an average probability of signing of 0.8 and a confidence coefficient of 0.85.

[0098] Cost calculation for pending signatures:

[0099] ;

[0100] ;

[0101] Dynamic Costs calculate:

[0102] ;

[0103] ;

[0104] Execution budget It amounted to 90 million yuan.

[0105] Over-probability calculation:

[0106] ;

[0107] ;

[0108] Because the over-budget ratio (11.2%) is greater than 10%, the budget upgrade is triggered;

[0109] Generate version V1.1 budget estimate, and mark the "Component Procurement" and "Bracket Installation" items as exceeding the budget estimate; link 3 change order records (numbered CV-001 to CV-003).

[0110] Schedule-cost analysis:

[0111] Calculated The critical path is "foundation construction → component installation";

[0112] Generate an expedited construction plan: dispatch 30 additional workers, shorten the component installation period by 5 days, and push the plan to the construction party's APP. The construction party must confirm receipt within 24 hours.

[0113] More specifically, the smart contract execution process of the blockchain collaboration bus module satisfies:

[0114] ;

[0115] in: The hash value of the purchase order is used to generate a 256-bit digest using the SHA-3 algorithm; This is a string of characters concatenated from the following: contract content (the complete text data of the procurement contract, including the subject matter, amount, performance terms, etc.), bidding results (bidding results file, including the name of the winning supplier, bid price, and summary of the bid evaluation report), and payment plan (payment plan information, including payment nodes, amount, conditions, etc.). For zero-knowledge proof parameters, used to verify the legality of data without revealing specific content, it is generated through the following steps: extract the hash values ​​of key contract elements (such as amount, supplier ID); use a zero-knowledge proof algorithm (such as Groth16) to generate a proof to verify the legality of the data without revealing specific content.

[0116] Calculate the impact index of tampering ,when When the impact index exceeds 3%, the payment process will be frozen;

[0117] The number of times data tampering was detected within a specified time window (e.g., 7 days); This represents the total number of transactions during the same period. Risk level (1-5, determined by factors such as purchase amount and supplier credit; for example, if the amount > 10 million yuan) =4).

[0118] The system automatically calls the timestamp service to generate audit reports, initiates the supplier blacklist review process through a multi-signature mechanism, and automatically synchronizes the blacklist to the supplier management system after the review is approved.

[0119] In this embodiment, a photovoltaic module purchase order is used as an example:

[0120] Data on the blockchain:

[0121] Component procurement contract (amount: RMB 10 million, supplier A);

[0122] Supplier A won the bid (quoted 9.8 million yuan, with a bid score of 92 points).

[0123] Payment will be made in three installments (30% prepayment, 50% upon delivery, and 20% upon acceptance).

[0124] Verify the legitimacy of supplier A's qualifications using zero-knowledge proofs without disclosing its financial data.

[0125] Tampering Detection and Response: The payment plan for this order was detected to have been tampered with twice within 3 days. =2), Total number of transactions in the same period =50, =3 (based on a risk assessment of RMB 10 million).

[0126] The impact of the alteration is calculated as follows:

[0127] ;

[0128] Since 12% > 3%, the following responses are triggered: the remaining 7 million yuan payment is frozen; an audit report is generated showing that the payment schedule has been altered (the original plan of 20% payment upon acceptance has been changed to 70% payment upon delivery); the project manager, financial director, and supervisor initiate a blacklist review through electronic signatures, and supplier A is added to the blacklist.

[0129] More specifically, the spatial coordinate hashing algorithm of the metaverse decision support module is as follows:

[0130] ;

[0131] in: The hash value of the three-dimensional coordinates and cost item; The three-dimensional coordinates of the BIM component (unit: meters, accurate to 3 decimal places (e.g., x=10.250, y=20.500, z=5.750)); For the related cost account code, a 6-digit fixed-length string is used (e.g., "030101" represents "photovoltaic module procurement"). For timestamps, the format is Unix timestamp (e.g., 1690000000). To perform a bitwise XOR operation, the coordinates, codes, and timestamps are converted to binary and then operated bit by bit to strengthen the binding relationship between the coordinates and codes;

[0132] Schedule Deviation Rate When the percentage exceeds 10%, the corresponding BIM component will be displayed in red and HoloLens vibration feedback will be triggered. At the same time, the three most recent related change orders will be highlighted.

[0133] When you click on a component, the system automatically retrieves the cost item details, supplier performance evaluation, and 3D construction log.

[0134] In this embodiment, we take the inverter installation components of a photovoltaic project as an example:

[0135] Hash value generation: Component coordinates: x=50.000, y=30.000, z=2.500;

[0136] Cost item code: "040201" (Inverter procurement);

[0137] Timestamp: 1690000000;

[0138] XOR operation: Convert the coordinates, code, and timestamp to binary and then XOR them to generate a Blake3 hash value.

[0139] Schedule deviation triggers warning:

[0140] Scheduled progress: Inverter installation 50% complete;

[0141] Actual progress: 35% complete;

[0142] (The negative sign indicates a lag), an absolute value of 30% > 10% triggers an alert;

[0143] In Hololens, the inverter component is displayed in red, with vibration feedback, and three related change orders are highlighted (such as CV-007: Inverter Model Change).

[0144] Click interaction response:

[0145] Retrieve cost item: Inverter purchases, total cost 8 million yuan;

[0146] Supplier evaluation: Sungrow Power Supply, rating 4.7, on-time delivery rate 92%;

[0147] Construction Log: 2025-05-15: Inverter arrives and is inspected; 2025-05-20: Wiring begins.

[0148] More specifically, the multi-dimensional parameterized formula library includes a procurement price fluctuation prediction model, the calculation formula of which is:

[0149] ;

[0150] in: To predict the purchase price (in ten thousand yuan or yuan / unit); The historical rolling benchmark price (the moving average of the purchase prices of similar equipment over the past 6 months); The ratio of the current purchase quantity to the minimum economic purchase quantity ( This refers to the quantity to be purchased (e.g., 100 inverters). The minimum order quantity for suppliers (e.g., 50 units) reflects economies of scale. The price index for new energy equipment is synchronized with industry association data in real time. This is the carbon tariff impact coefficient (0-0.2), which is dynamically adjusted according to the carbon tariff policy of the target market. For example, when the EU carbon tariff is €20 / ton, : Fluctuation coefficient, obtained through training with historical procurement data, with default values ​​of 0.3, 0.5, and 0.2 respectively.

[0151] like If the predicted price fluctuates by more than 8% compared to the procurement budget, a re-review process will be triggered, and a list of 3 alternative suppliers will be automatically pushed based on the supplier database data.

[0152] The evaluation weights are dynamically adjusted according to the price fluctuation range. For every 1% increase in fluctuation, the technical score weight increases by 0.8%, while the price score weight decreases accordingly. The evaluation rules are updated and made public simultaneously.

[0153] In this embodiment, taking the purchase of 100 string inverters for a photovoltaic project as an example, the parameter input and predicted price calculation are as follows:

[0154] Parameter input: Price: 10,000 RMB / unit (average price over the past 6 months) tower, tower, ; (Industry index rose 8%) (Target market carbon tariff policy is moderate); Procurement budget = 1.2 million yuan ( Ten thousand yuan / unit 100 units).

[0155] Price prediction calculation:

[0156] ;

[0157] ;

[0158] ;

[0159] ;

[0160] Total price forecast: ;

[0161] Compared to budget fluctuations: ;

[0162] Triggering a re-evaluation: Three alternative suppliers are recommended, with prices of RMB 23,000 / unit, RMB 24,000 / unit, and RMB 24,500 / unit, respectively.

[0163] Adjustment of evaluation weights: The weight of technical scores has been increased from 40% to [missing information]. Price rating weight reduced to The new bidding rules were publicized, and the re-bidding process was initiated.

[0164] More specifically, the platform supports a multi-party collaborative quantum key distribution mechanism, and the formula for generating communication keys among the participants is as follows:

[0165] ;

[0166] in: It serves as a communication key for participating parties, used to encrypt the transmission of business data (such as contract texts and approval records). The Diffie-Hellman algorithm is used for elliptic curves. As an identifier for the participants; The hash value of the project is generated by using the SHA-256 algorithm to produce a 256-bit digest of the project's basic information (such as project name and number). The key is a quantum random number, generated by a quantum random number generator (QRNG), with a length of 256 bits. It is provided by the quantum random number generator to ensure that the key is unpredictable. To perform a bitwise XOR operation, each parameter is converted to binary and then the operation is performed bit by bit, thus increasing the key complexity.

[0167] The key is automatically updated every 10 minutes, and the key update log is broadcast through the blockchain. The log contains the key entropy value detection results.

[0168] When an abnormal cross-regional call is detected (such as a Beijing account logging in in Shenzhen), a second biometric authentication (fingerprint + face) is triggered, and the account's contract approval privileges are frozen until authentication is successful.

[0169] In this embodiment, we take the supplier access of a photovoltaic project as an example:

[0170] Key generation:

[0171] PID: "SUPPLIER-007";

[0172] The hash value generated by hashing "Photovoltaic Project A-2025" using the SHA-256 algorithm;

[0173] A 256-bit random sequence generated by a quantum random number generator;

[0174] Generate key This key is used for encrypting contractual communications between the supplier and the client;

[0175] Abnormal call scenario: A supplier account (registered in Beijing) attempts to log in from an IP address in Shenzhen; the system detects that this login is a cross-regional call and is abnormal; the system automatically freezes the account's contract approval permissions and pops up a biometric authentication interface; after the supplier's authorized person completes dual authentication via fingerprint and facial recognition, the account's contract approval permissions are restored; at the same time, this abnormal event is recorded on the blockchain for later review.

[0176] More specifically, the dynamic cost analysis incorporates quantum Monte Carlo simulation, and the formula for calculating the cost confidence interval is as follows:

[0177] ;

[0178] in: The cost fluctuation range is defined as having a 95% confidence level (meaning there is a 95% probability that the actual cost will fall within this range). These are the quantiles of the standard normal distribution; The standard deviation of historical cost fluctuations reflects the stability of the account's cost. The risk factor (0.1-0.5) is assigned a value based on parameters such as geological conditions and technical difficulty.

[0179] If the lower limit of the confidence interval is less than 15% of the execution estimate, then follow the formula:

[0180] Release reserves to over-quota accounts. This refers to the number of subjects exceeding the general estimate.

[0181] Generate an interactive Sankey diagram that dynamically displays the probability of cost flows for each item. Support drag-and-drop adjustments to the funding plan. The system calculates the impact of adjustments on the overprobability in real time and highlights key path items.

[0182] In this embodiment, taking a certain offshore wind power project as an example, the parameter input is as follows:

[0183] Dynamic Investment 100 million yuan; historical fluctuation standard deviation 100 million yuan; geological condition risk factors (Complex sea areas); Execution budget 100 million yuan; Number of items exceeding the budget ("Foundation construction", "Cable laying").

[0184] The confidence interval calculation process is as follows:

[0185] ;

[0186] Substitute the specific values ​​into the formula:

[0187]

[0188] ;

[0189] Due to the lower limit of the confidence interval Less than 100 million yuan The amount was 100 million yuan, thus triggering the release of reserves.

[0190] The allocation of reserve funds is calculated as follows:

[0191] ;

[0192] Specifically, RMB 35.58 million will be allocated to "basic construction" and "cable laying" as reserve funds.

[0193] Sankey diagram interaction process: The user increases the budget for "cable laying" from 0.8 billion yuan to 0.9 billion yuan. The system recalculates the result as follows:

[0194] The probability of exceeding the target decreased from 0.75 to 0.62; the lower limit of the confidence interval rose to 0.85 billion yuan, no longer lower than the execution budget. The number of critical path subjects has been reduced from two to one.

[0195] More specifically, the metaverse decision support module supports multi-project quantum entanglement analysis, calculating the risk correlation degree of project clusters using the following formula:

[0196] ;

[0197] in: The risk correlation of the project cluster (value range [-1,1], the larger the absolute value, the stronger the correlation) reflects the correlation of the excess probability between projects; Each project With the project The overprobability vector (containing the monthly overprobability sequence); The mean of the excess probability. Number of projects, when analyzing When a project is completed, This formula is based on the Pearson correlation coefficient.

[0198] when At that time, a cross-project resource allocation plan is generated according to the following formula:

[0199] ;

[0200] in, The amount of resources available for allocation in a single project; The total amount of cross-project risk reserves is managed centrally by the Group's finance department. For the project The level of urgency (1-5);

[0201] The system automatically performs the following steps: Prioritizes projects by urgency to determine resource allocation; calculates the available resources for each project, for example, project A's... If project B=3, then A will receive more resources; generate a resource allocation details table, including: projects to be transferred out (resource surplus projects) and projects to be transferred in (resource shortage projects); types and quantities of resources to be allocated (such as equipment, manpower, and funds); and allocation time nodes (such as completion within 3 working days).

[0202] Launch the Metaverse Virtual Coordination Meeting, use AR technology to mark resource gaps in each project, support real-time signing of electronic allocation orders by multiple parties, and automatically trigger data synchronization in the ERP system after approval, updating the dynamic costs and schedules of each project in sync.

[0203] In this embodiment, taking two wind power projects of an energy group as an example, the correlation calculation and resource allocation scheme are as follows:

[0204] Correlation calculation:

[0205] The excess probability vectors for Project A (100MW) and Project B (50MW) are as follows:

[0206] (Probability of exceeding the expected value in the past 3 months);

[0207] ;

[0208] The mean vector is:

[0209] ;

[0210] Calculate the correlation between project A and project B. (The results are given directly here using the Pearson correlation coefficient calculation method):

[0211] ;

[0212] Since the correlation is greater than 0.5, the resource allocation mechanism is triggered.

[0213] Resource allocation plan:

[0214] Risk Reserve: =10 million yuan;

[0215] The urgency level of Project A: =4;

[0216] Urgency level of Project B: =5;

[0217] Calculate the resource reallocation amounts for Project A and Project B based on their relevance and urgency:

[0218] Ten thousand yuan;

[0219] Ten thousand yuan;

[0220] Solution: Allocate 911,000 yuan from Project A to Project B, prioritizing the wind turbine installation progress of Project B.

[0221] Metaverse Coordination Meeting: In the AR interface, the wind turbine foundation construction area for Project B is displayed in red (funding gap of 2 million yuan), while Project A's cable procurement item has a redundancy of 1.5 million yuan. The responsible persons of both parties confirm the allocation plan through gestures, and after electronic signing, the ERP system automatically deducts the budget of Project A, increases the budget of Project B, and updates the progress plan simultaneously.

[0222] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A multi-party collaborative digital management platform system for new energy projects, characterized in that, include: The intelligent coding data hub module adopts an adaptive tree coding system and generates dynamic cost item codes through the Transformer architecture. The codes include project type feature vectors, historical cost association weights, and supply chain risk factors, supporting cost data traceability and intelligent clustering based on codes. The quantum computing engine module integrates a multi-dimensional parameterized formula library, constructs a quantum entanglement computing model of cost-schedule-capital through gated loop units, introduces supply chain volatility index and policy risk coefficient, and realizes dynamic cost overprobability prediction and intelligent risk reserve provision; it supports generating cost fluctuation ranges with 95% confidence based on Monte Carlo simulation. The blockchain collaborative bus module builds a cross-participant data storage mechanism based on consortium blockchain technology. It realizes the on-chain storage of procurement price comparison results, consensus verification of contract changes, and tamper-proof storage of payment verification through smart contracts. It introduces zero-knowledge proof technology to complete the consistency verification of three-party data while protecting business privacy. The Metaverse Decision Support Module integrates BIM models and AR technology, and uses a spatial coordinate hashing algorithm to achieve quantum binding between cost items and 3D components. It supports immersive schedule deviation analysis and early warning based on HoloLens; and integrates digital twin technology to map the cost-schedule coupling status of physical projects in real time. The Transformer encoding generation algorithm of the intelligent encoding data hub module satisfies: ； in: This represents the feature vector generated at the current time step, which uses a multi-head attention mechanism to capture the relationship between the historical encoding state and the current input. This represents a multi-head attention mechanism, in which These are the query matrix, key matrix, and value matrix, used to construct the matching relationship in the self-attention mechanism. It represents the hidden state of the previous moment, preserving historical encoding features; This represents the feature vector of the current input project type, which includes project type, scale, and region-related parameters. This indicates element-wise multiplication; This is a layer normalization operation to ensure the stability of model training; When the coding level depth exceeds 5 levels, the system calculates the semantic distance of the subjects based on cosine similarity and automatically merges the last-level subjects with similarity ≥ 0.85; if the cost fluctuation coefficient of a certain category in the clustering results exceeds 15%, an early warning report with a heat map is generated, the spatial distribution of the fluctuating subjects in the BIM model is marked, and it is pushed to the finance department. The dynamic cost over-probability prediction model of the quantum computing engine module is as follows: ； in: The excess probability of dynamic cost is calculated using a logistic regression model; Indicates the current dynamic cost; In order to execute the budget, and The ratio reflects the degree of cost deviation; Schedule deviation rate; The supply chain risk factor is calculated based on supplier performance scores and logistics delay data. This is the policy change coefficient, which is dynamically assigned a value based on relevant parameters such as adjustments to new energy subsidies and changes in environmental policies. These are the weight coefficients trained using historical data (default values ​​are 2.5, 1.8, 1.2, and 0.9, respectively). when At that time, according to the formula: Provision for risk reserves; A three-dimensional risk warning model is generated, with red transparency mapping the probability of exceeding the limit. Simultaneously, 50% of the remaining budget for this subject is frozen, and a joint review process involving design, construction, and finance is triggered. Once the joint review is passed, the budget is released or the estimate is adjusted.

2. The new energy project multi-party collaborative digital management platform system according to claim 1, characterized in that, The dynamic cost The rules for quantum computing are as follows: ； Among them: the first item is the dynamic cost of the confirmed contract. Let i be the amount of the i-th contract. The first item is the change in visa impact factor; the second item is the projected cost of pending contracts, of which... The estimated amount for the j-th contract to be signed. For the probability of signing a contract, This represents the confidence level coefficient for signing the contract. like If the execution budget exceeds 10%, the execution budget upgrade process will be triggered, generating a new budget file with version difference comparisons and automatically linking it to the change log of the original budget. Startup progress-cost quantum entanglement analysis, if the correlation coefficient Then, a construction plan is automatically generated based on the critical path method and pushed to the construction party's APP.

3. The new energy project multi-party collaborative digital management platform system according to claim 2, characterized in that, The smart contract execution process of the blockchain collaboration bus module satisfies: ； in: The hash value of the purchase order is used to generate a 256-bit digest using the SHA-3 algorithm; This is a string concatenated with the contract details, the winning bid, and the payment plan. For zero-knowledge proof parameters, used to verify the legality of data without revealing its specific content; Calculate the impact index of tampering ,when When the impact index exceeds 3%, the payment process will be frozen. The number of data tampering detected within a specified time window; This represents the total number of transactions during the same period. Risk level; The system automatically calls the timestamp service to generate audit reports, initiates the supplier blacklist review process through a multi-signature mechanism, and automatically synchronizes the blacklist to the supplier management system after the review is approved.

4. The new energy project multi-party collaborative digital management platform system according to claim 3, characterized in that, The spatial coordinate hashing algorithm of the metaverse decision support module is as follows: ； in: The hash value of the three-dimensional coordinates and cost item; For BIM component 3D coordinates; Code related cost accounts; For timestamps; To enhance the binding relationship between coordinates and encoding for bitwise XOR operation; Schedule Deviation Rate When the percentage exceeds 10%, the corresponding BIM component will be displayed in red and HoloLens vibration feedback will be triggered. At the same time, the three most recent related change orders will be highlighted. When you click on a component, the system automatically retrieves the cost item details, supplier performance evaluation, and 3D construction log.

5. The new energy project multi-party collaborative digital management platform system according to claim 4, characterized in that, The multi-dimensional parameterized formula library includes a procurement price fluctuation prediction model, whose calculation formula is as follows: ； in: To predict purchase prices; Historical rolling benchmark price; This is the ratio of the current procurement volume to the minimum economic procurement volume, reflecting the economies of scale. The price index for new energy equipment is synchronized with industry association data in real time. The coefficient representing the impact of carbon tariffs; This is the volatility coefficient; like If the predicted price fluctuates by more than 8% compared to the procurement budget, a re-review process will be triggered, and a list of 3 alternative suppliers will be automatically pushed based on the supplier database. The evaluation weights are dynamically adjusted according to the price fluctuation range. For every 1% increase in fluctuation, the weight of the technical score increases by 0.8%, while the weight of the price score decreases accordingly. The evaluation rules are updated and publicized simultaneously.

6. The new energy project multi-party collaborative digital management platform system according to claim 5, characterized in that, The platform supports a multi-party collaborative quantum key distribution mechanism, and the formula for generating communication keys among the participants is as follows: ； in: For communication keys among the participants; The Diffie-Hellman algorithm is used for elliptic curves. As an identifier for the participants; The project hash value; The key is a quantum random number, provided by a quantum random number generator, ensuring that the key is unpredictable. To enhance key complexity, a bitwise XOR operation is used. The key is automatically updated every 10 minutes, and the key update log is broadcast through the blockchain. The log contains the key entropy value detection results. When an abnormal cross-regional call is detected, a second biometric authentication is triggered, and the account's contract approval privileges are frozen until authentication is successful.

7. The new energy project multi-party collaborative digital management platform system according to claim 6, characterized in that, The dynamic cost analysis incorporates quantum Monte Carlo simulation, and the formula for calculating the cost confidence interval is as follows: ； in: The cost fluctuation range represents a 95% confidence level. These are the quantiles of the standard normal distribution; The standard deviation of historical cost fluctuations reflects the stability of the account's cost. As a risk factor; If the lower limit of the confidence interval is less than 15% of the execution estimate, then follow the formula: Release reserves to over-quota accounts. For the number of subjects exceeding the estimate, This represents the lower limit of the confidence interval; Generate an interactive Sankey diagram that dynamically displays the probability of cost flows for each item. Support drag-and-drop adjustments to the funding plan. The system calculates the impact of adjustments on the overprobability in real time and highlights key path items.

8. The new energy project multi-party collaborative digital management platform system according to claim 7, characterized in that, The metaverse decision support module supports multi-project quantum entanglement analysis and calculates the risk correlation of project clusters using the following formula: ； in: The risk correlation of the project cluster reflects the correlation of the probability of exceeding the limit among projects; Each project With the project The overprobability vector; The formula is based on the Pearson correlation coefficient and represents the overprobability mean. when At that time, a cross-project resource allocation plan is generated according to the following formula: ； in, For the project The degree of urgency, The total amount of cross-project risk reserves; Launch the Metaverse Virtual Coordination Meeting, use AR technology to mark resource gaps in each project, support real-time signing of electronic allocation orders by multiple parties, and automatically trigger data synchronization in the ERP system after approval, updating the dynamic costs and schedules of each project in sync.

Images