AI-based enterprise data asset value exploration and reconstruction service method and system

Abstract

The invention provides an enterprise data asset value exploration and reconstruction service method and system based on AI, and relates to the technical field of data asset management.The identification method comprises the specific steps that data assets are prepared and standardized, and the data assets are subjected to multi-source heterogeneous data collection, cleaning, structured conversion, intelligent classification and man-machine collaborative labeling; generating standardized metadata containing quality, service, safety and time-space dimension information; data asset value evaluation and analysis: constructing a multi-dimensional evaluation index system, quantitatively evaluating the data asset value through a machine learning algorithm and predicting an evolution trend, and constructing a value association network based on a knowledge graph to form a dynamic evaluation model; according to the method, a block chain-driven trusted data sharing mechanism is constructed through an AI technology, a data sharing protocol is automatically executed by using an intelligent contract, permission, responsibility and benefit distribution of all parties are defined, and the problems of imperfect data sharing mechanism and data islands among enterprises are effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of data asset management technology, and in particular to an AI-based enterprise data asset value exploration and reconstruction service method and system. Background Art

[0002] In today's digital age, data has become an important asset for enterprises. Its value mining and effective management are crucial to the innovative development of enterprises. With the rapid development of the Internet of Things, mobile devices and sensor technology, the amount of data generated by enterprises has exploded, and the data types are becoming more diverse, covering structured tables, unstructured text, and coordinate information with spatiotemporal characteristics. These data contain huge potential. If they can be used reasonably, they will bring significant competitive advantages to enterprises. However, how to efficiently manage and mine the value of massive and complex data has become a major challenge facing enterprises, and has also prompted continuous exploration and innovation in related technology fields.

[0003] Traditional data asset management models have many limitations. Their scope is limited to within the enterprise, and they rely on manual experience and simple statistics for value assessment. They lack systematic data asset reconstruction methods, making it difficult to accurately assess and fully unleash the potential value of data. Patent publication number CN116611438A discloses an intelligent information reconstruction method, system, and device for data asset management. This method solves the time-consuming and labor-intensive problem of manually defining event templates through a template-free supervision approach. During the event structuring process, it avoids the problem of event templates omitting important event information. However, it lacks a quantitative assessment system for value dimensions such as data quality, business impact, and market potential. Furthermore, it does not involve a cross-enterprise data sharing mechanism, which is imperfect and creates data silos. This makes it impossible to achieve collaborative innovation in upstream and downstream of the industrial chain and joint market expansion. Furthermore, existing technologies struggle to effectively handle the multidimensional characteristics and dynamic correlations of data with spatiotemporal characteristics, making it impossible to explore the potential correlation value of spatiotemporal data in different dimensions, hindering the innovative application of data assets in multiple fields. Summary of the Invention

[0004] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions:

[0005] In one aspect, a method for exploring and reconstructing the value of enterprise data assets based on AI is provided. The method is implemented by an electronic device and includes:

[0006] Data asset preparation and standardization: Generate standardized metadata containing quality, business, security, and temporal and spatial information through multi-source heterogeneous data collection, cleaning, structured conversion, intelligent classification, and human-machine collaborative labeling;

[0007] Data asset value assessment and analysis: Build a multi-dimensional assessment indicator system, quantitatively assess the value of data assets and predict evolution trends through machine learning algorithms, and construct a value association network based on the knowledge graph to form a dynamic assessment model;

[0008] Data asset reconstruction and optimization: Generate data asset reconstruction strategies based on corporate strategic goals, optimize data structures using federated learning and dynamic indexing technologies, and dynamically adjust optimization strategies through real-time monitoring and feedback mechanisms;

[0009] Cross-enterprise data asset collaboration and sharing: Build a blockchain-driven trusted data sharing platform and use secure computing technology to protect data privacy. At the same time, by addressing cross-enterprise data heterogeneity, a data asset pool under a unified spatiotemporal reference system will be built.

[0010] Collaborative value mining and implementation: Based on a cross-enterprise data asset pool, explore the collaborative value of the industrial chain, develop spatiotemporal association rules to identify data patterns in different dimensions, convert the mining results into executable strategies and simulate optimization through digital twin technology.

[0011] Furthermore, in the data asset value assessment and analysis step, a multi-dimensional assessment indicator system including data quality, business impact, market potential, risk factor and time-space characteristics is established, and the data asset value is quantitatively assessed through machine learning algorithms. Based on the assessment results, prediction technology is used to analyze the potential value and change trends of data assets in different business scenarios and time-space dimensions. At the same time, a data asset value association network is constructed based on the knowledge graph to reveal the implicit associations and transmission paths between data, forming a dynamic value assessment model.

[0012] Furthermore, in the data asset value assessment and analysis step, the data asset value is quantitatively assessed using a machine learning model, and the model formula is: ,in, is the comprehensive value score of data assets, Represents the value assessment dimension, Corresponding to the data quality dimension, Corresponding to the business impact dimension, Corresponding to the market potential dimension, Corresponding to the risk coefficient dimension, Corresponding to the spatial and temporal characteristic dimension, It is Dimensions at the moment The dynamic weight of It is Data assets in each dimension at the moment 's rating.

[0013] Furthermore, in the data asset value assessment and analysis step, prediction technology is used to analyze the potential value and change trend of data assets in different business scenarios and time and space dimensions. The prediction formula is: ,in, It is the current moment The spatiotemporal data value score, It's the future The predicted value of the spatiotemporal data value score at the moment, are time intervals of different time granularities, For daily intervals, Weekly intervals, For monthly intervals, It is the time value change coefficient corresponding to different time granularities, are parameters of different spatial dimensions, is the spatial coverage, is the regional economic weight, is the spatial value impact coefficient corresponding to different spatial dimension parameters, is the spatiotemporal interaction coefficient, is a spatiotemporal interaction indicator.

[0014] Furthermore, the is the spatiotemporal interaction index, and its calculation formula is: ,in, is the number of time partitions, is the number of spatial partitions, It is The feature vector of the time partition, It is The eigenvectors of the spatial partitions, is the spatiotemporal correlation function, which is calculated as follows: ,in, is the feature vector of the time partition and the eigenvectors of the spatial partitions The covariance of , are the standard deviations of the time partition eigenvector and the space partition eigenvector, is the space-time distance function, is the attenuation coefficient, which controls the range of influence of time and space distance, is the spatiotemporal partition weight.

[0015] Furthermore, in the data asset reconstruction and optimization step, based on the enterprise strategic goals and business needs, a data asset reconstruction strategy is generated through intelligent decision-making technology. The reconstruction strategy determination formula is: ,in, is the optimal data asset reconstruction strategy generated, The set of all possible reconstruction strategies, It is a reconstruction strategy evaluation function, which is used to evaluate the degree to which each strategy satisfies the enterprise's strategic goals. It is a set of enterprise strategic goal parameters. is a set of current data asset status parameters, It is a set of historical data asset reconstruction experience parameters. It is a function Strategy for achieving maximum value The reconstruction strategy includes data aggregation, splitting, derivation and spatiotemporal dimension reorganization operations, and adopts data federated learning technology to conduct cross-domain model training without leaking the original data. It also optimizes the storage structure and access efficiency of spatiotemporal data through dynamic indexing technology, establishes a real-time monitoring feedback mechanism, and dynamically adjusts the optimization strategy by comparing the data value indicators before and after reconstruction.

[0016] Furthermore, in the cross-enterprise data asset collaboration and sharing step, a blockchain-driven trusted data sharing platform is built, and data sharing agreements are automatically executed through smart contracts. The rights, responsibilities and benefit distribution mechanisms of the participants are clarified, and homomorphic encryption and differential privacy technologies are used to ensure the security of data during transmission and processing. At the same time, semantic mapping technology is used to solve the heterogeneity problem of cross-enterprise data. In view of the characteristics of spatiotemporal data, a cross-enterprise spatiotemporal data asset pool is built through coordinate system conversion and time precision unification technology.

[0017] Furthermore, in the cross-enterprise data asset collaboration and sharing step, semantic mapping technology is used to solve the heterogeneity problem of cross-enterprise data. The mapping formula is: ,in, It is a unified semantic mapping model across enterprises. is the number of enterprises, It is Semantic models of the original data of participating enterprises, is the weight coefficient of each enterprise semantic model, is the reference semantic model, i.e. the benchmark for semantic mapping, It is an adaptive semantic mapping function that dynamically adjusts the mapping rules based on the differences between each enterprise's semantic model and the reference semantic model.

[0018] Furthermore, in the collaborative value mining and implementation step, based on the cross-enterprise data asset pool, the collaborative value between upstream and downstream data in the industrial chain is mined, and the calculation formula is: ,in, It is the collaborative value correlation between cross-enterprise spatiotemporal data. is the number of data samples, It is Enterprises in the sample The characteristic value of data assets, It is Enterprises in the sample The characteristic value of data assets, It is The time characteristic value of the sample, It is The spatial eigenvalues ​​of samples, It is an enterprise The average value of the data asset characteristic value, It is an enterprise The average value of the data asset characteristic value, is the average value of the time characteristic value, It is the average value of the spatial eigenvalues, and dynamically optimizes the resource allocation strategy through reinforcement learning. For spatiotemporal data, it identifies data patterns and anomalies in different time and space dimensions through spatiotemporal association rules, and converts the mining results into executable collaborative innovation strategies. It simulates the effect of strategy implementation through digital twin technology to form a closed-loop optimization mechanism.

[0019] On the other hand, an AI-based enterprise data asset value exploration and reconstruction service system is provided. The system is used for an AI-based enterprise data asset value exploration and reconstruction service method, and the system includes:

[0020] Data asset preparation and standardization module: Generates standardized metadata through the collection, cleaning, structured conversion, intelligent classification, and human-machine collaborative annotation of multi-source heterogeneous data;

[0021] Data asset value assessment and analysis module: Build a multi-dimensional assessment indicator system, use machine learning to quantitatively assess the value of data assets and predict their evolution trends, and construct a value association network based on the knowledge graph to form a dynamic assessment model;

[0022] Data asset reconstruction and optimization module: Generates data asset reconstruction strategies based on corporate strategic goals, optimizes data structures, and dynamically adjusts optimization strategies through real-time monitoring and feedback mechanisms;

[0023] Cross-enterprise data asset collaboration and sharing module: Build a blockchain-driven trusted data sharing platform, use secure computing technology to ensure data privacy, and solve the problem of cross-enterprise data heterogeneity to build a data asset pool under a unified spatiotemporal reference system;

[0024] Collaborative value mining and implementation module: Based on the cross-enterprise data asset pool, it mines the collaborative value of the industrial chain, converts the mining results into executable strategies, and simulates and optimizes them through digital twin technology.

[0025] The beneficial effects brought about by the technical solution provided by the present invention include at least:

[0026] 1. The present invention uses AI technology to build a blockchain-driven trusted data sharing mechanism, uses smart contracts to automatically execute data sharing agreements, clarifies the rights, responsibilities and benefit distribution of all parties, and effectively solves the problems of imperfect data sharing mechanisms and data silos among enterprises. At the same time, it uses semantic mapping technology to solve the heterogeneity of cross-enterprise data, develops coordinate system conversion and time precision unified algorithms based on the characteristics of spatiotemporal data, and builds a cross-enterprise spatiotemporal data asset pool, so that enterprises can share data assets safely and efficiently, promote collaborative innovation in upstream and downstream of the industrial chain and joint market expansion, achieve optimal resource allocation, and create more business opportunities and value for enterprises.

[0027] 2. Based on a cross-enterprise data asset pool, the present invention mines the collaborative value between upstream and downstream data in the industrial chain, dynamically optimizes resource allocation strategies through reinforcement learning, develops spatiotemporal association rule mining algorithms for spatiotemporal data, and identifies data patterns and anomalies in different time and space dimensions. At the same time, the mining results are converted into executable collaborative innovation strategies, and the implementation effects of strategies are simulated through digital twin technology to form a closed-loop optimization mechanism, thereby accurately mining the value of data, providing enterprises with data-driven intelligent decision-making support, helping enterprises optimize resource allocation, promote innovation and development, and enhance the competitiveness of enterprises in the market. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 It is a flowchart of an AI-based enterprise data asset value exploration and reconstruction service method;

[0030] Figure 2 It is a flowchart of data asset reconstruction and optimization in the AI-based enterprise data asset value exploration and reconstruction service method;

[0031] Figure 3 It is a flowchart of collaborative value mining and implementation in an AI-based enterprise data asset value exploration and reconstruction service method;

[0032] Figure 4 It is a structural diagram of an AI-based enterprise data asset value exploration and reconstruction service system. DETAILED DESCRIPTION

[0033] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0034] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0035] In the embodiments of the present invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same. The terms "of," "corresponding," and "corresponding" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same.

[0036] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript form such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0037] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0038] Example 1

[0039] A city’s transportation management department has teamed up with several logistics companies and bus operating companies to jointly explore and reconstruct the value of data assets.

[0040] like Figure 1 As shown in the figure, during the data asset preparation and standardization stage, data is collected from multiple sources such as traffic cameras, GPS positioning equipment, logistics enterprise transportation management systems, and bus operation and dispatching systems. These include structured and unstructured data such as real-time traffic flow data on different road sections, logistics vehicle driving trajectory data, and bus line operation data. Data cleaning technology is used to remove duplicate and erroneous data, and unstructured traffic condition description data is converted into structured data through semantic parsing. The data is classified according to data type, source, and spatiotemporal characteristics. Combined with manual annotation, the data is given quality grades, business value labels, security levels, and spatiotemporal dimension labels to form standardized metadata.

[0041] Next, in the data asset value assessment and analysis phase, we used the constructed multi-dimensional evaluation index system to quantitatively evaluate the collected data assets from the dimensions of data quality, business impact on traffic congestion management, potential in the intelligent transportation market, data security risks, and spatiotemporal characteristics. The formula is: ,in, is the comprehensive value score of data assets, Represents the value assessment dimension, Corresponding to the data quality dimension, Corresponding to the business impact dimension, Corresponding to the market potential dimension, Corresponding to the risk coefficient dimension, Corresponding to the spatial and temporal characteristic dimension, It is Dimensions at the moment The dynamic weight of It is Data assets in each dimension at the moment By analyzing the correlation between historical traffic flow data and congestion conditions and combining time series analysis, we can predict the trend of traffic flow value changes in different time periods and sections in the future. The prediction formula is: ,in, It is the current moment The spatiotemporal data value score, It's the future The predicted value of the spatiotemporal data value score at the moment, are time intervals of different time granularities, For daily intervals, Weekly intervals, For monthly intervals, It is the time value change coefficient corresponding to different time granularities, are parameters of different spatial dimensions, is the spatial coverage, is the regional economic weight, is the spatial value impact coefficient corresponding to different spatial dimension parameters, is the spatiotemporal interaction coefficient, It is a spatiotemporal interaction indicator that takes into account the impact of traffic congestion in different spatial regions on data value.

[0042] Then, based on the strategic goals of urban traffic congestion control and improving logistics distribution efficiency, the current data asset status is analyzed and the historical reconstruction experience database is called, such as Figure 2 As shown in the figure, in the data asset reconstruction and optimization stage, the data asset reconstruction strategy is generated through intelligent decision-making technology, and the reconstruction strategy determination formula is: ,in, is the optimal data asset reconstruction strategy generated, is the set of all possible reconstruction strategies, It is a reconstruction strategy evaluation function, which is used to evaluate the degree to which each strategy satisfies the enterprise's strategic goals. It is a set of enterprise strategic goal parameters. is a set of current data asset status parameters, It is a set of historical data asset reconstruction experience parameters. It is a function Strategy for achieving maximum value It aggregates scattered logistics vehicle trajectory data and bus route operation data, reorganizes the data in the time and space dimensions, optimizes the data storage structure to improve query efficiency, monitors the reconstruction effect in real time, and dynamically adjusts the strategy based on feedback.

[0043] In terms of cross-enterprise data asset collaboration and sharing, a blockchain-driven trusted data sharing platform is built, a data sharing agreement is formulated, the data sharing scope, authority, and responsibilities of all parties are clarified, encryption technology is used to ensure data security, and semantic mapping technology is used to solve the heterogeneous problem of data from different enterprises. A unified cross-city transportation spatiotemporal data asset pool is built. The mapping formula is: ,in, It is a unified semantic mapping model across enterprises. It is Semantic models of the original data of participating enterprises, is the weight coefficient of each enterprise semantic model, is the reference semantic model, i.e. the benchmark for semantic mapping, It is an adaptive semantic mapping function that dynamically adjusts the mapping rules based on the differences between each enterprise's semantic model and the reference semantic model.

[0044] Finally, in the collaborative value exploration and implementation stage, such as Figure 3 As shown in the figure, we access the cross-enterprise data asset pool, explore the collaborative value between logistics enterprise transportation routes and bus route planning, and identify the dynamic correlation between traffic peak hours, congested sections, logistics distribution efficiency, and bus route punctuality through spatiotemporal correlation analysis. The calculation formula is: ,in, It is the collaborative value correlation between cross-enterprise spatiotemporal data. is the number of data samples, It is Enterprises in the sample The characteristic value of data assets, It is Enterprises in the sample The characteristic value of data assets, It is The time characteristic value of the sample, It is The spatial eigenvalues ​​of samples, It is an enterprise The average value of the data asset characteristic value, It is an enterprise The average value of the data asset characteristic value, is the average value of the time characteristic value, It is the average value of the spatial eigenvalues. Collaborative innovation strategies are formulated based on the mining results, such as optimizing the coordinated planning of bus routes and logistics distribution routes. The digital twin technology is used to simulate the implementation effect of the strategy and continuously optimize it, so as to alleviate urban traffic congestion and improve logistics distribution efficiency.

[0045] Example 2

[0046] In order to enhance market competitiveness, a large retail enterprise group applies the service system of the present invention to manage and mine the value of enterprise data assets.

[0047] like Figure 4 As shown in the figure, the data asset preparation and standardization module collects data from multiple sources such as the enterprise's internal ERP system, CRM system, online and offline sales terminals, as well as external market research institutions, social media, etc., covering product sales data, customer purchase records, market trend data, etc., and cleans and structures the collected data. It pre-processes spatiotemporal data for sales data containing geographic location and time information. The data classification and labeling sub-module realizes automatic data classification based on the deep learning model, and combines manual labeling to assign spatiotemporal dimension labels and other information to complete the standardization preparation of data assets.

[0048] The data asset value assessment and analysis module uses the constructed multi-dimensional assessment system to evaluate the value of data assets from the perspectives of data quality, business impact on sales growth, market potential, risk factor, and spatiotemporal characteristics through formulas. Quantitatively evaluate enterprise data assets by analyzing the changing trends of commodity sales data in different regions and time periods, and using formulas Predict the value evolution of data assets in the future market environment and provide a basis for corporate decision-making.

[0049] The data asset reconstruction and optimization module uses intelligent decision-making technology to generate data asset reconstruction strategies based on the company's strategic goals of expanding into new markets and optimizing product inventory management. This includes aggregate analysis of product sales data, segmented processing of customer data, and data optimization in the time and space dimensions. It then executes reconstruction operations, monitors the reconstruction effects through a real-time monitoring system, and dynamically adjusts strategies based on feedback.

[0050] The cross-enterprise data asset collaboration and sharing module builds a blockchain-driven trusted data sharing platform, automatically executes data sharing agreements through smart contracts, clarifies the rights, responsibilities and benefit distribution mechanisms of participants, and uses homomorphic encryption and differential privacy technologies to ensure the security of data during transmission and processing. At the same time, it uses semantic mapping formulas to Solve the problem of heterogeneity of cross-enterprise data. For the spatiotemporal data in commodity logistics and distribution, use the spatiotemporal data fusion engine to handle the inconsistency of coordinate systems and time accuracy, and build a unified data asset pool.

[0051] The collaborative value mining and implementation module is based on a cross-enterprise data asset pool, mining the collaborative relationship between supplier inventory data and enterprise sales data. Through the spatiotemporal correlation analysis engine, it identifies the sales patterns and trends of goods in different regions and seasons. The decision optimization engine converts the mining results into executable business strategies, such as optimizing supply chain management and adjusting product promotion plans. It also continuously optimizes strategies through real-time monitoring and feedback mechanisms to maximize the value of enterprise data assets.

[0052] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are fully or partially performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0053] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0054] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0055] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0056] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0057] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0058] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of the device or unit, which can be electrical, mechanical or other forms.

[0059] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0060] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0061] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical disks.

[0062] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. An AI-based enterprise data asset value exploration and reconstruction service method, characterized by: The method comprises: Data asset preparation and standardization: Generate standardized metadata containing quality, business, security, and temporal and spatial information through multi-source heterogeneous data collection, cleaning, structured conversion, intelligent classification, and human-machine collaborative labeling; Data asset value assessment and analysis: Build a multi-dimensional assessment indicator system, quantitatively assess the value of data assets and predict evolution trends through machine learning algorithms, and construct a value association network based on the knowledge graph to form a dynamic assessment model; Data asset reconstruction and optimization: Generate data asset reconstruction strategies based on corporate strategic goals, optimize data structures using federated learning and dynamic indexing technologies, and dynamically adjust optimization strategies through real-time monitoring and feedback mechanisms; Cross-enterprise data asset collaboration and sharing: Build a blockchain-driven trusted data sharing platform and use secure computing technology to protect data privacy. At the same time, by addressing cross-enterprise data heterogeneity, a data asset pool under a unified spatiotemporal reference system will be built. Collaborative value mining and implementation: Based on a cross-enterprise data asset pool, explore the collaborative value of the industrial chain, develop spatiotemporal association rules to identify data patterns in different dimensions, convert the mining results into executable strategies and simulate optimization through digital twin technology.

2. The AI-based enterprise data asset value exploration and reconstruction service method according to claim 1 is characterized in that: In the data asset value assessment and analysis steps, a multi-dimensional assessment indicator system including data quality, business impact, market potential, risk factor and time-space characteristics is established, and the value of data assets is quantitatively assessed through machine learning algorithms. Based on the assessment results, predictive technology is used to analyze the potential value and change trends of data assets in different business scenarios and time-space dimensions. At the same time, a data asset value association network is constructed based on the knowledge graph to reveal the implicit associations and transmission paths between data, forming a dynamic value assessment model.

3. The AI-based enterprise data asset value exploration and reconstruction service method according to claim 2 is characterized in that: In the data asset value assessment and analysis step, the data asset value is quantitatively assessed using a machine learning model, and the model formula is: ， in, is the comprehensive value score of data assets, Represents the value assessment dimension, Corresponding to the data quality dimension, Corresponding to the business impact dimension, Corresponding to the market potential dimension, Corresponding to the risk coefficient dimension, Corresponding to the spatial and temporal characteristic dimension, It is Dimensions at the moment The dynamic weight of It is Data assets in each dimension at the moment 's rating.

4. The AI-based enterprise data asset value exploration and reconstruction service method according to claim 2 is characterized in that: In the data asset value assessment and analysis step, prediction technology is used to analyze the potential value and change trend of data assets in different business scenarios and time and space dimensions. The prediction formula is: ， in, It is the current moment The spatiotemporal data value score, It's the future The predicted value of the spatiotemporal data value score at the moment, are time intervals of different time granularities, For daily intervals, Weekly intervals, For monthly intervals, It is the time value change coefficient corresponding to different time granularities, are parameters of different spatial dimensions, is the spatial coverage, is the regional economic weight, is the spatial value impact coefficient corresponding to different spatial dimension parameters, is the spatiotemporal interaction coefficient, is a spatiotemporal interaction indicator.

5. The AI-based enterprise data asset value exploration and reconstruction service method according to claim 3 is characterized in that: described is the spatiotemporal interaction index, and its calculation formula is: ， in, is the number of time partitions, is the number of spatial partitions, It is The feature vector of the time partition, It is The eigenvectors of the spatial partitions, is the spatiotemporal correlation function, which is calculated as follows: ， in, is the feature vector of the time partition and the eigenvectors of the spatial partitions The covariance of , are the standard deviations of the time partition eigenvector and the space partition eigenvector, is the space-time distance function, is the attenuation coefficient, which controls the range of influence of time and space distance, is the spatiotemporal partition weight.

6. The AI-based enterprise data asset value exploration and reconstruction service method according to claim 1 is characterized in that: In the data asset reconstruction and optimization step, based on the enterprise strategic goals and business needs, a data asset reconstruction strategy is generated through intelligent decision-making technology. The reconstruction strategy determination formula is: ， in, is the optimal data asset reconstruction strategy generated, The set of all possible reconstruction strategies, It is a reconstruction strategy evaluation function, which is used to evaluate the degree to which each strategy satisfies the enterprise's strategic goals. It is a set of enterprise strategic goal parameters. is a set of current data asset status parameters, It is a set of historical data asset reconstruction experience parameters. It is a function Strategy for achieving maximum value The reconstruction strategy includes data aggregation, splitting, derivation and spatiotemporal dimension reorganization operations, and adopts data federated learning technology to conduct cross-domain model training without leaking the original data. It also optimizes the storage structure and access efficiency of spatiotemporal data through dynamic indexing technology, establishes a real-time monitoring feedback mechanism, and dynamically adjusts the optimization strategy by comparing the data value indicators before and after reconstruction.

7. The AI-based enterprise data asset value exploration and reconstruction service method according to claim 1 is characterized in that: In the cross-enterprise data asset collaboration and sharing steps, a blockchain-driven trusted data sharing platform is built, and data sharing agreements are automatically executed through smart contracts. The rights, responsibilities and benefit distribution mechanisms of the participants are clarified, and homomorphic encryption and differential privacy technologies are used to ensure the security of data during transmission and processing. At the same time, semantic mapping technology is used to solve the heterogeneity problem of cross-enterprise data. In view of the characteristics of spatiotemporal data, a cross-enterprise spatiotemporal data asset pool is built through coordinate system conversion and time precision unification technology.

8. The AI-based enterprise data asset value exploration and reconstruction service method according to claim 7 is characterized in that: In the cross-enterprise data asset collaboration and sharing step, semantic mapping technology is used to solve the heterogeneity problem of cross-enterprise data. The mapping formula is: ， in, It is a unified semantic mapping model across enterprises. is the number of enterprises, It is Semantic models of the original data of participating enterprises, is the weight coefficient of each enterprise semantic model, is the reference semantic model, i.e. the benchmark for semantic mapping, It is an adaptive semantic mapping function that dynamically adjusts the mapping rules based on the differences between each enterprise's semantic model and the reference semantic model.

9. The AI-based enterprise data asset value exploration and reconstruction service method according to claim 1 is characterized in that: In the collaborative value mining and implementation steps, based on the cross-enterprise data asset pool, the collaborative value between upstream and downstream data in the industrial chain is mined, and the calculation formula is: ， in, It is the collaborative value correlation between cross-enterprise spatiotemporal data. is the number of data samples, It is Enterprises in the sample The characteristic value of data assets, It is Enterprises in the sample The characteristic value of data assets, It is The time characteristic value of the sample, It is The spatial eigenvalues ​​of samples, It is an enterprise The average value of the data asset characteristic value, It is an enterprise The average value of the data asset characteristic value, is the average value of the time characteristic value, It is the average value of the spatial eigenvalues, and dynamically optimizes the resource allocation strategy through reinforcement learning. For spatiotemporal data, it identifies data patterns and anomalies in different time and space dimensions through spatiotemporal association rules, and converts the mining results into executable collaborative innovation strategies. It simulates the effect of strategy implementation through digital twin technology to form a closed-loop optimization mechanism.

10. An AI-based enterprise data asset value exploration and reconstruction service system, which is applicable to the AI-based enterprise data asset value exploration and reconstruction service method according to any one of claims 1 to 9, characterized in that: The system comprises the following components: Data asset preparation and standardization module: Generates standardized metadata through the collection, cleaning, structured conversion, intelligent classification, and human-machine collaborative annotation of multi-source heterogeneous data; Data asset value assessment and analysis module: Build a multi-dimensional assessment indicator system, use machine learning to quantitatively assess the value of data assets and predict their evolution trends, and construct a value association network based on the knowledge graph to form a dynamic assessment model; Data asset reconstruction and optimization module: Generates data asset reconstruction strategies based on corporate strategic goals, optimizes data structures, and dynamically adjusts optimization strategies through real-time monitoring and feedback mechanisms; Cross-enterprise data asset collaboration and sharing module: Build a blockchain-driven trusted data sharing platform, use secure computing technology to ensure data privacy, and solve the problem of cross-enterprise data heterogeneity to build a data asset pool under a unified spatiotemporal reference system; Collaborative value mining and implementation module: Based on the cross-enterprise data asset pool, it mines the collaborative value of the industrial chain, converts the mining results into executable strategies, and simulates and optimizes them through digital twin technology.

Images