Data-driven county industrial collaborative investment management method and system

Abstract

The application discloses a county area industry collaborative investment management and governance method and system based on data driving, relates to the technical field of regional economic governance, obtains an investment management whole-process knowledge graph, obtains a cross-industry decision report through a cross-industry intelligent matching algorithm combined with a dynamic weight, establishes a meta-universe investigation space for remote interaction and service based on the object attributes of county area industries, generates supply and demand side interaction reservation information in response to the cross-industry decision report, remotely signs through the meta-universe investigation space, calls a corresponding industry blockchain smart contract template based on a signing agreement, triggers cross-industry collaborative action execution, evaluates project benefits in response to cross-industry collaborative whole-life cycle operation data, optimizes a cross-industry resource matching scheme and adjusts the investment management whole-process knowledge graph according to the evaluation result. The application improves investment management response efficiency, realizes dynamic supervision of landed projects, and improves industry collaborative operation efficiency.

Description

Technical Field

[0001] This application relates to the field of regional economic governance technology, specifically a data-driven county-level industrial collaborative investment promotion governance method and system. Background Technology

[0002] Against the backdrop of high-quality regional economic development, investment promotion, as a key driver of industrial upgrading and economic growth, has evolved significantly from "policy-driven" to "service-driven" and "digital-driven." However, current mainstream investment promotion management systems still have significant shortcomings in supporting efficient decision-making and agile governance, particularly in the lack of remote interaction capabilities and a reliable end-to-end tracking mechanism, which severely restricts the speed of investment promotion response and the effectiveness of regional governance. Existing investment promotion platforms mainly focus on static information dissemination, providing only basic content such as park introductions, policy compilations, or project lists, lacking real-time, two-way, and immersive interactive capabilities with investors. The patent, "A Smart Matching Investment Promotion Strategy System and Method Based on Enterprise Needs," publication number CN202111678574.0, uses an LM-BP neural network to perform deep learning on four types of features: industry, policy, location, and architecture. It then utilizes an improved random forest model to score and classify enterprise needs, achieving multi-source heterogeneous data fusion and intelligent matching. However, when potential investors are located in different areas, they cannot remotely experience the factory layout, infrastructure, or industrial ecosystem through the system, often forcing them to rely on multiple on-site inspections. This not only increases time and economic costs but also delays the investment decision-making cycle. Although virtual reality (VR) and 3D modeling technologies are widely used in cultural tourism and real estate, they have not been effectively integrated into investment promotion scenarios, resulting in a persistent problem of "seeing policies but not being able to touch the site." Furthermore, the investment promotion process itself heavily relies on offline coordination and manual follow-up. From initial contact, intention assessment, on-site inspection, business negotiations to final signing, information at each stage is scattered across emails, meeting minutes, paper documents, or different business systems, lacking a unified online process carrier. The lack of visibility into key milestones, the untraceability of operational records, and the unclear definition of responsible parties make it difficult for management to dynamically monitor project progress and to intervene in risks or allocate resources in a timely manner.

[0003] Furthermore, even when some systems attempt to introduce digital tools, they are often limited to single functional modules, failing to organically integrate capabilities such as remote interaction, process management, and data tracking. For example, some platforms support online appointment scheduling for site visits but cannot simultaneously generate site visit reports and link them to subsequent negotiation stages; some systems record signing information but are not integrated with subsequent services such as business establishment, land use approval, and financial access. This "point-based digitization" rather than "chain-based collaboration" keeps investment promotion work stuck in an inefficient "experience-driven, fragmented operation" model, making it difficult to achieve rapid response to investment leads, transparent control over project progress, and precise governance of the regional industrial ecosystem. Summary of the Invention

[0004] This application addresses the problems of delayed investment promotion decision-making and low regional economic governance efficiency caused by the inability of investment promotion management systems to conduct remote interactive inspections and reliable full-process tracking. It proposes a data-driven county-level industrial collaborative investment promotion governance method and system. By establishing a remote interactive channel, it enables remote interactive inspections and remote signing between supply and demand parties, and online cross-industry collaborative actions, thereby improving the efficiency of investment promotion response. Furthermore, it optimizes cross-industry collaborative solutions based on operational data, enabling a closed loop and traceability of the entire investment promotion lifecycle, achieving dynamic supervision of implemented projects, and improving the efficiency of industrial collaborative operations.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows: In a first aspect, embodiments of this application provide a data-driven method for county-level industrial collaborative investment promotion governance, the method comprising: Obtain a knowledge graph of the entire investment promotion process, and generate cross-industry decision-making reports through cross-industry intelligent matching algorithms combined with dynamic weights; Based on the attributes of county-level industries, a meta-universe exploration space is established for remote interaction and services. In response to cross-industry decision-making reports, supply and demand parties can generate interactive appointment information and sign contracts remotely through the meta-universe exploration space. Based on the signed agreement, the corresponding industry's blockchain smart contract template is retrieved to trigger cross-industry collaborative actions. In response to the cross-industry collaborative full lifecycle operation data assessment project benefits, optimize cross-industry resource matching schemes and adjust the knowledge graph of the entire investment promotion process based on the assessment results.

[0006] This solution utilizes a knowledge graph covering the entire investment promotion process to store core data from stages such as demand diagnosis and breakpoint identification on the blockchain, ensuring the diagnostic process is tamper-proof and verifiable. This provides a unified data source for credible tracking throughout the entire process and standardized spatial and industry parameters (such as building load and supply chain data) to support remote inspections. Furthermore, it leverages cross-industry intelligent matching algorithms combined with dynamic weights to generate cross-industry decision reports, avoiding invalid matching caused by unreliable demands. Continuous optimization of dynamic weights reduces subjective bias in human decision-making, balancing the matching efficiency and accuracy of cross-industry collaborative solutions and improving decision-making response speed. By establishing a metaverse inspection space, remote interaction and signing are achieved without dedicated equipment, reducing equipment and time costs for remote inspections and filling the gap in credible traceability in the investment promotion process. Through blockchain smart contract templates, cross-industry collaborative actions are triggered, transforming investment promotion results from signed data into operational data. This enables dynamic monitoring of implemented projects, improves industrial operational efficiency, and continuously optimizes investment promotion governance capabilities based on operational data. This enhances the accuracy and policy adaptability of the cross-industry intelligent matching algorithm, ensuring that cross-industry collaborative projects continuously adapt to the county's industrial development needs throughout the entire process.

[0007] Optionally, the acquisition of the entire investment promotion process knowledge graph, and the generation of cross-industry decision-making reports through cross-industry intelligent matching algorithms combined with dynamic weights, includes: Based on the type of industrial entity, multi-source heterogeneous data of county-level economic business is obtained through cross-departmental data exchange interfaces; A knowledge graph of the entire investment promotion process is constructed based on multi-source heterogeneous data, and a cross-industry investment promotion target graph and investment demand list are obtained through graph computing algorithms. Based on the node data of the investment target map and the list of investment needs, multi-dimensional characteristics of supply and demand sides are extracted to determine resource matching indicators. Based on the weight of dynamic resource matching indicators, a decision report containing cross-industry resource matching solutions and risk warnings is obtained.

[0008] Optionally, the step of constructing a knowledge graph of the entire investment promotion process based on multi-source heterogeneous data, and obtaining a cross-industry investment promotion target graph and a list of investment promotion needs through graph computing algorithms, includes: Entity association rules are determined based on industry entities and their attributes. Based on multi-source heterogeneous data and entity association rules, NLP technology is used to extract data from all nodes of the investment promotion process and construct a knowledge graph of the entire investment promotion process. After hashing the data at each node in the knowledge graph of the entire investment promotion process, the data is stored in the blockchain to generate a unique and verifiable credential. Based on graph computing algorithms, we analyze graph data to identify single-industry breakpoints and cross-industry collaboration gaps, and obtain a structured list of investment needs and a map of investment targets that include technology requirements, investment scale, and cross-industry supporting requirements.

[0009] Optionally, the step of extracting multi-dimensional features of supply and demand sides based on the node data of the investment target map and the investment demand list, determining resource matching indicators, and obtaining a decision report containing cross-industry resource matching solutions and risk warnings based on the dynamic resource matching indicator weights includes: Based on the node data of the investment target map and the list of investment needs, obtain demand characteristic data and supply characteristic data; Based on demand and supply characteristic data, resource matching indicators are determined to assess the matching degree between enterprise demand and county resources. These resource matching indicators include at least industrial relevance, technological matching, spatial resource suitability, policy fit, and cross-industry synergy. Based on the dynamic matching index weights of the county-level industrial demand database and the external factor supply database, the degree of industrial relevance, technology matching degree, spatial resource adaptability, policy fit, and cross-industry synergy are weighted and calculated to obtain the comprehensive matching degree. This results in a list of enterprises and county-level resources that meet the matching degree threshold, and cross-industry resource matching schemes are generated by integrating demand and supply characteristics.

[0010] Optionally, the step of extracting multi-dimensional features of supply and demand sides based on the node data of the investment target map and the list of investment needs, determining resource matching indicators, and obtaining a decision report containing cross-industry resource matching solutions and risk warnings based on the dynamic resource matching indicator weights, further includes: Based on the full-process data of cross-industry collaboration, an LSTM time series model is used to predict the development trend of cross-industry collaboration and obtain the industry development trend value. By integrating multi-source heterogeneous data on current county-level industries with cross-industry collaborative operation data, we can obtain the county's primary competitiveness indicators corresponding to agriculture, industry, service industry, and cross-industry collaboration. Based on publicly available industry data from benchmark counties, we obtained the second competitiveness indicators for the benchmark counties corresponding to agriculture, industry, service industry, and cross-industry collaboration. The primary competitiveness indicator is weighted based on the industrial development trend value. The weighted primary competitiveness indicator is compared with the secondary competitiveness indicator to obtain the industrial competitiveness assessment results of each county. Risk warnings are then issued based on the assessment results.

[0011] Optionally, the establishment of a metaverse exploration space for remote interaction and services based on the attributes of county-level industry objects includes: Establish digital twins of industrial parks, benchmark enterprises, and distinctive carriers within the county, and integrate structured data of spatial resources to obtain a county spatial resource model; A metaverse exploration space corresponding to the county-level spatial resource model is constructed based on 3D roaming and VR / AR rendering engines.

[0012] Optionally, the step of generating supply and demand interaction reservation information in response to cross-industry decision-making reports and conducting remote contract signing through the metaverse exploration space includes: In response to cross-industry decision-making reports, it generates supply and demand matching appointment information and grants access to the metaverse exploration space based on the appointment information. Based on the metaverse exploration space, remote interaction between supply and demand parties is carried out, and remote signing is achieved through the metaverse exploration space's electronic signing system.

[0013] Optionally, the step of retrieving the corresponding industry's blockchain smart contract template based on the signing agreement to trigger cross-industry collaborative actions includes: Establish blockchain smart contract templates corresponding to different industry types based on enterprise procurement needs; Based on the signed agreement, the corresponding industry's blockchain smart contract template is retrieved to generate industry-coordinated digital orders for the supplier. Real-time production data is obtained based on the execution status of digital orders in industry collaboration. When the production data meets the contract conditions, payment and reward / penalty actions are triggered.

[0014] Optionally, the method further includes: The hash value of the signed document is linked to the corresponding node in the knowledge graph of the entire investment promotion process through a unique and trusted credential, thereby realizing the signing and storage of evidence and obtaining the full life cycle operation data of cross-industry collaborative projects. Combined with the remote signing process data, a full-process trusted record of cross-industry collaboration is formed.

[0015] Secondly, embodiments of this application provide a data-driven county-level industrial collaborative investment promotion governance system, including: The data analysis engine module is used to obtain a knowledge graph of the entire investment promotion process and to generate cross-industry decision-making reports through cross-industry intelligent matching algorithms combined with dynamic weights. The remote interaction service module is used to establish a metaverse exploration space for remote interaction and services based on the attributes of county-level industry objects. It responds to cross-industry decision-making reports by generating supply and demand interaction appointment information and conducts remote contract signing through the metaverse exploration space. The industry collaboration execution module is used to retrieve the corresponding industry's blockchain smart contract template based on the signed agreement and trigger cross-industry collaborative actions. The Operations Feedback Optimization Module is used to respond to the evaluation of project benefits based on cross-industry collaborative full lifecycle operations data, optimize cross-industry resource matching schemes based on evaluation results, and adjust the knowledge graph of the entire investment promotion process.

[0016] The beneficial effects of this application are: 1. Through knowledge graphs and graph computing, dynamic diagnosis of complex industrial relationships is realized, transforming the unstructured investment promotion decision-making process into a data-based, visualized, and computable process, thereby improving the depth and efficiency of industrial data analysis. Furthermore, by combining cross-industry intelligent matching algorithms with dynamic weights, the limitations of simple keyword matching are overcome, enabling intelligent coupling of supply and demand at multiple levels and dimensions, reducing the workload of manual screening, and thus improving the accuracy and efficiency of resource matching. 2. By integrating VR / AR, 3D roaming, and blockchain signing, the constructed metaverse exploration space has an immersive, secure, and legally binding online connection channel, reducing investment attraction costs and improving response speed. 3. By applying blockchain smart contract templates, the projects and resources introduced through investment promotion are directly embedded into the digital production process of the real economy, ensuring the reliability, operability, and long-term optimization of investment promotion results. This forms a closed loop of county-level industrial collaborative investment promotion governance, which is driven by data and generates investment promotion feedback data. It avoids the problem of disconnect between investment promotion and operation, and provides a fully controllable framework for county-level industrial diagnosis, investment promotion services, and ecological operation, effectively improving the efficiency of regional economic governance. Attached Figure Description

[0017] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings. The drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings.

[0018] Figure 1 A flowchart of a data-driven county-level industrial collaborative investment promotion governance method is provided for embodiments of this application.

[0019] Figure 2 This is a schematic diagram illustrating a process for obtaining a cross-industry resource matching solution, provided as an embodiment of this application. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely one preferred embodiment of this application and are only used to explain this application. They do not limit the scope of protection of this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] Example 1: As Figure 1 As shown, a data-driven county-level industrial collaborative investment promotion governance method includes steps S1-S4, wherein: S1. Obtain the knowledge graph of the entire investment promotion process, and obtain cross-industry decision-making reports through cross-industry intelligent matching algorithms combined with dynamic weights.

[0022] In an optional embodiment, combined with Figure 2 As shown, step S1 includes: Based on the type of industrial entity, multi-source heterogeneous data of county-level economic business is obtained through cross-departmental data exchange interfaces; A knowledge graph of the entire investment promotion process is constructed based on multi-source heterogeneous data, and a cross-industry investment promotion target graph and investment demand list are obtained through graph computing algorithms. Based on the node data of the investment target map and the list of investment needs, multi-dimensional characteristics of supply and demand sides are extracted to determine resource matching indicators. Based on the weight of dynamic resource matching indicators, a decision report containing cross-industry resource matching solutions and risk warnings is obtained.

[0023] In some embodiments, the industry entity types include agriculture, industry, and service industries in a county. Industry entities correspond to data entities in agriculture, industry, and service industries in a county, such as "enterprise", "industry chain link", "policy", "spatial resources", and "technological achievements". Each entity has basic attributes and scalable attributes. For example, the basic attributes of the "spatial resources" entity include macro location, meso-level park facilities, and micro-level building parameters (load, energy conservation and environmental protection indicators). Scalable attributes can be added according to the industry type (such as the arable land grade for agriculture and the factory building height for industry).

[0024] In some embodiments, based on the RESTful API specification, the access and output formats of government data (such as business registration and taxation), enterprise data (such as output value and demand), and scientific research data (such as technology patents) are unified to achieve synchronous collection and updating of multi-source heterogeneous data.

[0025] In an optional embodiment, the step of constructing a knowledge graph of the entire investment promotion process based on multi-source heterogeneous data, and obtaining a cross-industry investment promotion target graph and a list of investment promotion needs through graph computing algorithms, includes: Entity association rules are determined based on industry entities and their attributes. Based on multi-source heterogeneous data and entity association rules, NLP technology is used to extract data from all nodes of the investment promotion process and construct a knowledge graph of the entire investment promotion process. After hashing the data at each node in the knowledge graph of the entire investment promotion process, the data is stored in the blockchain to generate a unique and verifiable credential. Based on graph computing algorithms, we analyze graph data to identify single-industry breakpoints and cross-industry collaboration gaps, and obtain a structured list of investment needs and a map of investment targets that include technology requirements, investment scale, and cross-industry supporting requirements.

[0026] In some examples, the entire investment promotion process includes at least the following nodes: demand diagnosis, intelligent matching, remote site visits, negotiation minutes, and contract signing and archiving. NLP technology is used to extract core information from each node entity. For example, the "intelligent matching" node includes the matching algorithm version, feature dimension weights, and matching result scores; the "remote site visits" node includes the visit time, participating parties, and feedback. The data from each node in the knowledge graph (including matching scoring criteria, site visit records, and negotiation minutes) is hashed and stored on the blockchain to generate unique and trustworthy credentials. Leveraging the immutability of the blockchain, the entire process from demand generation to decision implementation is ensured to be traceable and verifiable.

[0027] Furthermore, through graph computing algorithms (such as community discovery and centrality analysis), we can diagnose breakpoints in a single industry and identify cross-industry collaboration gaps. For example, breakpoints in agricultural deep processing can be linked with food processing technology resources in industry and brand marketing resources in service industry to generate cross-industry investment target maps and demand lists.

[0028] The investment target map visually marks the breakpoints in the county's industrial chain and the gaps in cross-industry collaboration, while the demand list transforms these gaps into structured and quantifiable investment needs. By highlighting the inter-industry linkage needs through the investment target map and demand list, precise target areas are defined for investment promotion, thereby improving matching accuracy and avoiding resource waste caused by mismatches between county-level industrial needs.

[0029] In an optional embodiment, the step of extracting multi-dimensional features of supply and demand sides based on the node data of the investment target map and the investment demand list, determining resource matching indicators, and obtaining a decision report containing cross-industry resource matching solutions and risk warnings based on the dynamic resource matching indicator weights includes: Based on the node data of the investment target map and the list of investment needs, obtain demand characteristic data and supply characteristic data; Based on demand and supply characteristic data, resource matching indicators are determined to assess the matching degree between enterprise demand and county resources. These resource matching indicators include at least industrial relevance, technological matching, spatial resource suitability, policy fit, and cross-industry synergy. Based on the dynamic matching index weights of the county-level industrial demand database and the external factor supply database, the degree of industrial relevance, technology matching degree, spatial resource adaptability, policy fit, and cross-industry synergy are weighted and calculated to obtain the comprehensive matching degree. This results in a list of enterprises and county-level resources that meet the matching degree threshold, and cross-industry resource matching schemes are generated by integrating demand and supply characteristics.

[0030] In this embodiment, cross-industry synergy and spatial resource adaptability are added to the existing industrial relevance and technology matching. Cross-industry synergy is used to assess the resource complementarity between different industries, while spatial resource adaptability is used to assess the resource allocation of building load, energy conservation and environmental protection, and transportation and logistics, so as to ensure the accurate matching of enterprise needs with county resources.

[0031] Specifically, a dynamic "county-level industry demand database" and "external factor supply database" (including enterprises, technology, talent, capital, etc.) are established and maintained. All entities in the database are tagged according to their industry type, and used to train a weighted allocation model based on an attention mechanism. The model obtains the weights for each dimension of the indicators based on the feature vectors of the industry relevance, technology matching, spatial resource suitability, policy alignment, and cross-industry synergy between the demand and supply entities. The feature vectors of each dimension are weighted and summed to output a comprehensive matching score, which is then sorted. A Top-N recommendation list (a list of matching enterprises and county-level resources) is obtained based on the ranking that meets the threshold.

[0032] In this embodiment, dynamic weighted matching of multi-dimensional indicators improves the comprehensiveness of the matching, avoids the limitations of single-industry investment promotion, and avoids the problems of low matching efficiency and poor accuracy caused by traditional keywords and manual screening. This shortens the decision-making cycle and improves the response speed of investment promotion decisions. The obtained Top-N recommendation list and cross-industry resource matching scheme clarify the priority targets and supporting strategies for remote docking, providing a basis for subsequent remote interaction, avoiding the blindness of remote inspections, and reducing the cost of cross-regional interaction.

[0033] In an optional embodiment, the step of extracting multi-dimensional features of supply and demand sides based on the node data of the investment target map and the investment demand list, determining resource matching indicators, and obtaining a decision report containing cross-industry resource matching solutions and risk warnings based on the dynamic resource matching indicator weights, further includes: Based on the full-process data of cross-industry collaboration, an LSTM time series model is used to predict the development trend of cross-industry collaboration and obtain the industry development trend value. By integrating multi-source heterogeneous data on current county-level industries with cross-industry collaborative operation data, we can obtain the county's primary competitiveness indicators corresponding to agriculture, industry, service industry, and cross-industry collaboration. Based on publicly available industry data from benchmark counties, we obtained the second competitiveness indicators for the benchmark counties corresponding to agriculture, industry, service industry, and cross-industry collaboration. The primary competitiveness indicator is weighted based on the industrial development trend value. The weighted primary competitiveness indicator is compared with the secondary competitiveness indicator to obtain the industrial competitiveness assessment results of each county. Risk warnings are then issued based on the assessment results.

[0034] In some embodiments, risks include industry-specific risks, cross-industry synergy risks, and competition risks. Industry-specific risks include agricultural risks, industrial risks, and service industry risks. Cross-industry synergy risks include resource misallocation risks and policy conflict risks. Competition risks include the risk that the competitiveness growth rate of a certain industry in a benchmark county will far exceed that of the industry itself.

[0035] The existence of individual risks and cross-industry collaborative risks is determined by comparing the values ​​of each individual competitiveness indicator with set thresholds. The existence of competitive risks in the county is determined by comparing the comprehensive indicator results (i.e., the comprehensive first competitiveness indicator and the comprehensive second competitiveness indicator). Risk warnings are triggered based on different risk types.

[0036] In this embodiment, traditional county-level industrial competitiveness assessment relies solely on static data such as current output value and enterprise metrics, which can easily lead to short-sighted decision-making. By acquiring static competitiveness indicators (the first competitiveness indicator) for agriculture, industry, services, and cross-industry collaboration, and simultaneously predicting cross-industry collaborative development trends, future potential is incorporated into the assessment system. This transforms a static snapshot into a dynamic, panoramic competitiveness assessment model, allowing the assessment results to simultaneously reflect future competitive risks. For example, if a county's current industrial competitiveness is weaker than that of a benchmark county, but its cross-industry collaboration trend value is high, its overall competitiveness may surpass that of a benchmark county after weighting. Based on this, industrial policies can be formulated to address weaknesses through collaboration, avoiding blindly imitating the single-industry investment attraction path of benchmark counties and improving the precision of regional economic governance.

[0037] Specifically, the trend value is used as a weight; the higher the trend value, the greater the future potential, and the higher the weight of the corresponding industry or collaborative link in the evaluation. This avoids overlooking the investment value of an industry due to poor static indicators. The trend value is updated in real time based on an LSTM model, and the corresponding weight is also dynamically adjusted with industry development, enhancing the dynamic adaptability of the evaluation results and ensuring that the evaluation results always align with the direction of industry development.

[0038] Furthermore, risk warnings are issued based on the assessment results. The aim is to adjust the weights of multi-dimensional indicators in reverse, making the matching algorithm more suitable for the regional industrial development needs, continuously improving the accuracy of investment promotion decisions, and thus continuously improving the efficiency of regional economic governance.

[0039] S2. Based on the attributes of county-level industry objects, establish a metaverse exploration space for remote interaction and services, respond to cross-industry decision-making reports to generate supply and demand interaction appointment information, and conduct remote contract signing through the metaverse exploration space.

[0040] In an optional embodiment, step S2, which involves establishing a metaverse exploration space for remote interaction and services based on the attributes of county-level industry objects, includes: Establish digital twins of industrial parks, benchmark enterprises, and distinctive carriers within the county, and integrate structured data of spatial resources to obtain a county spatial resource model; A metaverse exploration space corresponding to the county-level spatial resource model is constructed based on 3D roaming and VR / AR rendering engines.

[0041] In some embodiments, the Metaverse Exploration Space is a virtual remote interactive platform that combines lightweight 3D roaming functionality on a web page with the immersive VR / AR experience mode, used to replicate county-level spatial resources. The 3D roaming allows for online viewing and parameter querying of spatial resources without VR / AR devices, but retains the VR / AR mode to meet the needs of different users.

[0042] In this embodiment, a metaverse-based observation space is constructed to enable remote interaction between supply and demand parties. A digital twin is embedded with spatial resource data, precisely matching the enterprise's needs in a cross-industry resource matching scheme. This avoids information asymmetry during remote observations and provides reliable data support for subsequent remote contract signing. The combination of 3D roaming and a VR / AR rendering engine solves the problems of spatiotemporal barriers and the lack of virtual-real integration capabilities in remote observations, avoiding the absence of interactive remote observations, simplifying the investment promotion process, and improving the efficiency of investment promotion decisions.

[0043] In an optional embodiment, step S2, which involves generating supply and demand interaction reservation information in response to a cross-industry decision report and conducting remote contract signing via the metaverse exploration space, includes: In response to cross-industry decision-making reports, it generates supply and demand matching appointment information and grants access to the metaverse exploration space based on the appointment information. Based on the metaverse exploration space, remote interaction between supply and demand parties is carried out, and remote signing is achieved through the metaverse exploration space's electronic signing system.

[0044] Specifically, it connects to the electronic signing system and uses digital certificates and blockchain timestamp technology to sign investment agreements / cooperation contracts.

[0045] In this embodiment, the metaverse exploration space is connected to an electronic signing system that complies with the Electronic Signature Law. The signing process is recorded and the document hash is stored on the blockchain as evidence, ensuring that the signing has legal effect and the process is traceable. This realizes a fully online service for cloud exploration, interaction and signing, shortening the decision response time.

[0046] S3. Based on the signed agreement, retrieve the corresponding industry's blockchain smart contract template to trigger cross-industry collaborative actions.

[0047] In an optional embodiment, step S3 includes: Establish blockchain smart contract templates corresponding to different industry types based on enterprise procurement needs; Based on the signed agreement, the corresponding industry's blockchain smart contract template is retrieved to generate industry-coordinated digital orders for the supplier. Real-time production data is obtained based on the execution status of digital orders in industry collaboration. When the production data meets the contract conditions, payment and reward / penalty actions are triggered.

[0048] Specifically, blockchain smart contract templates include, but are not limited to, agricultural order contracts, industrial supply chain contracts, and service industry cooperation contracts. After a supplier accepts an order online, the contract is deployed to the blockchain network to monitor the contract execution process in real time and obtain production data. When the production data meets preset conditions (such as output reaching the target and energy consumption meeting the standard), payment, reward and punishment actions are automatically executed.

[0049] In this embodiment, cross-industry blockchain smart contracts are deployed by calling the signed and stored data to avoid the risk of human intervention in contract execution. The blockchain smart contract template automatically triggers payment and reward / punishment actions according to preset conditions, realizing real-time supervision of the implemented projects, ensuring that the investment promotion results are transformed into actual industrial benefits, and solving the problem of data gaps after implementation.

[0050] In an optional embodiment, the method further includes: The hash value of the signed document is linked to the corresponding node in the knowledge graph of the entire investment promotion process through a unique and trusted credential, thereby realizing the signing and storage of evidence and obtaining the full life cycle operation data of cross-industry collaborative projects. Combined with the remote signing process data, a full-process trusted record of cross-industry collaboration is formed.

[0051] In this embodiment, after the hash value of the signed document is uploaded to the blockchain, it is deeply associated with the signing node in the investment promotion full-process knowledge graph, forming a unique and trustworthy credential. This credential cannot be tampered with, and the entire chain of data, such as the matching basis before signing and remote inspection records, can be directly traced through the investment promotion full-process knowledge graph. This solves the problem of traditional contract evidence being isolated and difficult to verify. By uniformly associating remote signing process data with the full lifecycle operation data of cross-industry collaborative projects to the corresponding project nodes in the knowledge graph, a complete data chain of investment promotion projects is obtained, enabling transparent management of the entire investment promotion process and enhancing the traceability of the entire process data.

[0052] S4. Respond to the cross-industry collaborative full life cycle operation data assessment project benefits, optimize cross-industry resource matching schemes and adjust the knowledge graph of the entire investment promotion process based on the assessment results.

[0053] In an optional embodiment, step S4 includes: Based on cross-industry collaborative full life cycle operation data analysis, the correlation between county spatial resource data and production data is obtained to acquire resource matching error terms; Adjust cross-industry collaboration solutions based on resource matching error terms, and provide feedback to optimize the knowledge graph of the entire investment promotion process.

[0054] In this embodiment, the industrial breakpoint diagnosis is a static result. The repair effect can be verified based on production data, and the investment demand list can be dynamically updated to achieve a dynamic closed loop of breakpoint diagnosis, investment repair, and effect verification.

[0055] Based on the same inventive concept, this application also provides a data-driven county-level industrial collaborative investment promotion governance system corresponding to the data-driven county-level industrial collaborative investment promotion governance method. This system includes: The data analysis engine module is used to obtain a knowledge graph of the entire investment promotion process and to generate cross-industry decision-making reports through cross-industry intelligent matching algorithms combined with dynamic weights. The remote interaction service module is used to establish a metaverse exploration space for remote interaction and services based on the attributes of county-level industry objects. It responds to cross-industry decision-making reports by generating supply and demand interaction appointment information and conducts remote contract signing through the metaverse exploration space. The industry collaboration execution module is used to retrieve the corresponding industry's blockchain smart contract template based on the signed agreement and trigger cross-industry collaborative actions. The Operations Feedback Optimization Module is used to respond to the evaluation of project benefits based on cross-industry collaborative full lifecycle operations data, optimize cross-industry resource matching schemes based on evaluation results, and adjust the knowledge graph of the entire investment promotion process.

[0056] The beneficial effects of this embodiment are as follows: Through the collaboration of various modules, from generating investment targets through industry data analysis, to intelligent matching triggering remote connections, to online signing facilitating digital contracts, and finally implementing contract terms into physical operations through the Internet of Things and blockchain, and feeding back new data generated from operations to the analysis engine, a smart ecosystem is formed. This provides a digital twin closed-loop framework for county-level systematic industrial diagnosis, investment services, and ecosystem operation, thereby improving the digitalization level of regional economic governance.

[0057] The above-described embodiments are preferred embodiments of this application and are not intended to limit the specific scope of this application. The scope of this application includes but is not limited to the specific embodiments described above. All equivalent changes made in accordance with the shape, structure, and method of this application are within the protection scope of this application.

Claims

1. A data-driven approach to county-level industrial collaborative investment promotion governance, characterized by: Includes the following steps: Obtain a knowledge graph of the entire investment promotion process, and generate cross-industry decision-making reports through cross-industry intelligent matching algorithms combined with dynamic weights; Based on the attributes of county-level industries, a meta-universe exploration space is established for remote interaction and services. In response to cross-industry decision-making reports, supply and demand parties can generate interactive appointment information and sign contracts remotely through the meta-universe exploration space. Based on the signed agreement, the corresponding industry's blockchain smart contract template is retrieved to trigger cross-industry collaborative actions. In response to the cross-industry collaborative full lifecycle operation data assessment project benefits, optimize cross-industry resource matching schemes and adjust the knowledge graph of the entire investment promotion process based on the assessment results.

2. The data-driven county-level industrial collaborative investment promotion governance method according to claim 1, characterized in that: The process of acquiring a knowledge graph of the entire investment promotion process, and obtaining cross-industry decision-making reports through cross-industry intelligent matching algorithms combined with dynamic weights, includes: Based on the type of industrial entity, multi-source heterogeneous data of county-level economic business is obtained through cross-departmental data exchange interfaces; A knowledge graph of the entire investment promotion process is constructed based on multi-source heterogeneous data, and a cross-industry investment promotion target graph and investment demand list are obtained through graph computing algorithms. Based on the node data of the investment target map and the list of investment needs, multi-dimensional characteristics of supply and demand sides are extracted to determine resource matching indicators. Based on the weight of dynamic resource matching indicators, a decision report containing cross-industry resource matching solutions and risk warnings is obtained.

3. The data-driven county-level industrial collaborative investment promotion governance method according to claim 2, characterized in that: The process involves constructing a knowledge graph for the entire investment promotion process based on multi-source heterogeneous data, and using graph computing algorithms to obtain a cross-industry investment promotion target graph and a list of investment promotion needs, including: Entity association rules are determined based on industry entities and their attributes. Based on multi-source heterogeneous data and entity association rules, NLP technology is used to extract data from all nodes of the investment promotion process and construct a knowledge graph of the entire investment promotion process. After hashing the data at each node in the knowledge graph of the entire investment promotion process, the data is stored in the blockchain to generate a unique and verifiable credential. Based on graph computing algorithms, we analyze graph data to identify single-industry breakpoints and cross-industry collaboration gaps, and obtain a structured list of investment needs and a map of investment targets that include technology requirements, investment scale, and cross-industry supporting requirements.

4. The data-driven county-level industrial collaborative investment promotion governance method according to claim 2, characterized in that: The process involves extracting multi-dimensional features of supply and demand sides based on node data from the investment target map and the investment demand list, determining resource matching indicators, and generating a decision report containing cross-industry resource matching solutions and risk warnings based on the dynamic resource matching indicator weights. Based on the node data of the investment target map and the list of investment needs, obtain demand characteristic data and supply characteristic data; Based on demand and supply characteristic data, resource matching indicators are determined to assess the matching degree between enterprise demand and county resources. These resource matching indicators include at least industrial relevance, technological matching, spatial resource suitability, policy fit, and cross-industry synergy. Based on the dynamic matching index weights of the county-level industrial demand database and the external factor supply database, the degree of industrial relevance, technology matching degree, spatial resource adaptability, policy fit, and cross-industry synergy are weighted and calculated to obtain the comprehensive matching degree. This results in a list of enterprises and county-level resources that meet the matching degree threshold, and cross-industry resource matching schemes are generated by integrating demand and supply characteristics.

5. The data-driven county-level industrial collaborative investment promotion governance method according to claim 4, characterized in that: The process of extracting multi-dimensional features of supply and demand sides based on node data of the investment target map and the investment demand list, determining resource matching indicators, and obtaining a decision report containing cross-industry resource matching solutions and risk warnings based on dynamic resource matching indicator weights also includes: Based on the full-process data of cross-industry collaboration, an LSTM time series model is used to predict the development trend of cross-industry collaboration and obtain the industry development trend value. By integrating multi-source heterogeneous data on current county-level industries with cross-industry collaborative operation data, we can obtain the county's primary competitiveness indicators corresponding to agriculture, industry, service industry, and cross-industry collaboration. Based on publicly available industry data from benchmark counties, we obtained the second competitiveness indicators for the benchmark counties corresponding to agriculture, industry, service industry, and cross-industry collaboration. The primary competitiveness indicator is weighted based on the industrial development trend value. The weighted primary competitiveness indicator is compared with the secondary competitiveness indicator to obtain the industrial competitiveness assessment results of each county. Risk warnings are then issued based on the assessment results.

6. The data-driven county-level industrial collaborative investment promotion governance method according to claim 1, characterized in that: The metaverse exploration space established based on the attributes of county-level industry objects for remote interaction and services includes: Establish digital twins of industrial parks, benchmark enterprises, and distinctive carriers within the county, and integrate structured data of spatial resources to obtain a county spatial resource model; A metaverse exploration space corresponding to the county-level spatial resource model is constructed based on 3D roaming and VR / AR rendering engines.

7. The data-driven county-level industrial collaborative investment promotion governance method according to claim 6, characterized in that: The response to the cross-industry decision-making report generates supply and demand side interactive reservation information, and remote signing is conducted through the metaverse exploration space, including: In response to cross-industry decision-making reports, it generates supply and demand matching appointment information and grants access to the metaverse exploration space based on the appointment information. Based on the metaverse exploration space, remote interaction between supply and demand parties is carried out, and remote signing is achieved through the metaverse exploration space's electronic signing system.

8. The data-driven county-level industrial collaborative investment promotion governance method according to claim 1, characterized in that: The process of retrieving the corresponding industry's blockchain smart contract template based on the signed agreement to trigger cross-industry collaborative actions includes: Establish blockchain smart contract templates corresponding to different industry types based on enterprise procurement needs; Based on the signed agreement, the corresponding industry's blockchain smart contract template is retrieved to generate industry-coordinated digital orders for the supplier. Real-time production data is obtained based on the execution status of digital orders in industry collaboration. When the production data meets the contract conditions, payment and reward / penalty actions are triggered.

9. The data-driven county-level industrial collaborative investment promotion governance method according to claim 7 or 8, characterized in that: The method further includes: The hash value of the signed document is linked to the corresponding node in the knowledge graph of the entire investment promotion process through a unique and trusted credential, thereby realizing the signing and storage of evidence and obtaining the full life cycle operation data of cross-industry collaborative projects. Combined with the remote signing process data, a full-process trusted record of cross-industry collaboration is formed.

10. A data-driven county-level industrial collaborative investment promotion governance system, applicable to the data-driven county-level industrial collaborative investment promotion governance method as described in any one of claims 1-9, characterized in that: include: The data analysis engine module is used to obtain a knowledge graph of the entire investment promotion process and to generate cross-industry decision-making reports through cross-industry intelligent matching algorithms combined with dynamic weights. The remote interaction service module is used to establish a metaverse exploration space for remote interaction and services based on the attributes of county-level industry objects. It responds to cross-industry decision-making reports by generating supply and demand interaction appointment information and conducts remote contract signing through the metaverse exploration space. The industry collaboration execution module is used to retrieve the corresponding industry's blockchain smart contract template based on the signed agreement and trigger cross-industry collaborative actions. The Operations Feedback Optimization Module is used to respond to the evaluation of project benefits based on cross-industry collaborative full lifecycle operations data, optimize cross-industry resource matching schemes based on evaluation results, and adjust the knowledge graph of the entire investment promotion process.

Images