An artificial intelligence-based data asset operation decision method and system

Abstract

The application belongs to the technical field of data asset management, and particularly relates to a data asset operation decision method and system based on artificial intelligence. Firstly, multi-dimensional characteristic data of target data assets is collected, and the collected multi-dimensional characteristic data is vectorized and fused to form a feature representation F. Then, the feature representation F is quality evaluated. Next, the feature representation F, a comprehensive quality score Q and historical data are used to predict and evaluate a future expected value Vp, a predicted risk value Ri and a predicted cost value Zm of the target data assets. Secondly, a multi-objective decision function is constructed with the future expected value Vp maximization, the predicted risk value Ri minimization and the predicted cost value Zm optimization as targets. Strategy optimization is performed through an optimization algorithm, and a recommended operation action Aopt is generated. The prediction result can be automatically converted into an executable operation decision, and the dependence of the decision on artificial experience can be greatly reduced.

Description

Technical Field

[0001] This invention belongs to the field of data asset management technology, specifically relating to a data asset operation decision-making method and system based on artificial intelligence. Background Technology

[0002] With the deepening of digital transformation, data has become a core strategic asset for enterprises. Currently, enterprises face many challenges in the operation of data assets. First, the valuation of data assets often relies on static and single financial or technical indicators, lacking a comprehensive quantification of their dynamic value in multiple dimensions such as business influence, potential risks, and market scarcity. Second, operational decisions often rely on human experience, making it difficult to adapt to the rapidly changing internal and external environment. Moreover, the full lifecycle management of data assets is fragmented, lacking a value-oriented intelligent decision-making closed loop.

[0003] In the existing technology, there are some data asset assessment models and decision support systems, but the assessment dimensions are single and they fail to integrate the internal attributes of the data with the external business environment, thus failing to achieve a comprehensive, dynamic, and quantifiable assessment and prediction of the value of data assets.

[0004] To address the aforementioned issues, this application presents a data asset operation decision-making method and system based on artificial intelligence. Summary of the Invention

[0005] To address the shortcomings of existing technologies mentioned in the background section, this application proposes an artificial intelligence-based data asset operation decision-making method and system. First, multi-dimensional feature data of the target data asset is collected, and the collected multi-dimensional feature data is vectorized and fused to form a feature representation F. Then, the feature representation F is quality-assessed. Next, based on the feature representation F, the comprehensive quality score Q, and historical data, the future expected value Vp, predicted risk value Ri, and predicted cost value Zm of the target data asset are predicted and assessed. Then, a multi-objective decision function is constructed with the objectives of maximizing the future expected value Vp, minimizing the predicted risk value Ri, and optimizing the predicted cost value Zm. An optimization algorithm is used to find the optimal strategy, generating a recommended operational action Aopt. Finally, the actual effect after executing the recommended operational action Aopt is monitored, and a completion coefficient E is calculated. An alarm is issued when the evaluation value of the completion coefficient E is lower than a preset threshold, thereby solving the problems in the background section.

[0006] Firstly, to achieve the above objectives, this application provides a data asset operation decision-making method based on artificial intelligence, which includes the following specific steps: S1. Collect multi-dimensional feature data of the target data asset, and vectorize and fuse the collected multi-dimensional feature data to form feature representation F. The multi-dimensional feature data includes internal quality dimension features, business relationship dimension features, and market environment dimension features. S2. Perform a quality assessment on the feature representation F; The quality evaluation of the feature representation F includes the following steps: S21. Based on the preset quality rule engine, perform rule compliance checks on the internal quality dimension features in the feature representation F, and output the rule compliance score Sr; S22. Based on the dynamic anomaly detection machine, perform anomaly pattern recognition on the business-related dimension features and market environment dimension features in the feature representation F, and output the anomaly degree score Sa; S23. Obtain the recent historical quality score sequence of the target data asset, analyze its changing trend, and output the trend score St. S24. Calculate the overall quality score Q based on the results of the rule compliance score Sr, the anomaly score Sa, and the trend score St. S3. Based on the feature representation F, the comprehensive quality score Q, and historical data, predict and evaluate the future expected value Vp, the predicted risk value Ri, and the predicted cost value Zm of the target data asset. S4. Construct a multi-objective decision function with the objectives of maximizing the expected future value Vp, minimizing the predicted risk value Ri, and optimizing the predicted cost value Zm. Take the comprehensive quality score Q, real-time business demand Rb, and operational constraints C as inputs, and use the optimization algorithm to optimize the strategy to generate recommended operational actions Aopt. S5. Monitor the actual effect of the recommended operational action Aopt, calculate the completion coefficient E, and issue an alarm when the evaluation value of the completion coefficient E is lower than the preset threshold. The formula for calculating the completion coefficient E is: ; in, , , These are the weighting coefficients. The actual value of data assets This represents the actual risk value. This represents the actual cost value.

[0007] Based on the above scheme, the preferred formula for calculating the rule compliance score Sr is: ; Where N is the total number of preset quality rules. Let K be the weight of the rule. This is an indicator function. It takes a value of 1 when feature F fully conforms to the k-th rule, a value of 0 when it does not conform at all, and a value within the range [0, 0] when it partially conforms, depending on the degree of conformity. The value is retrieved from within.

[0008] Based on the above scheme, the preferred formula for calculating the anomaly score Sa is: ; Where T is the number of detection time windows. The score for the business-related anomalies detected in the t-th detection time window is... Let be the score of the market environment anomalies detected in the t-th detection time window, and and All within the range The value is retrieved from within. These are the weighting coefficients.

[0009] Based on the above scheme, the preferred formula for calculating the trend score St is: ; Here, 50 points represents a neutral benchmark, with upward movement indicating an improving trend and downward movement indicating a deteriorating trend. 'b' represents the trend slope, 'P' is the autocorrelation coefficient of the historical quality score series, reflecting the persistence of the trend (closer to 1 indicates a more consistent trend, closer to 0 indicates a less persistent trend), and 'G' is the trend strength benchmark, a constant used to normalize the trend slope 'b'. The relative standard deviation is used to reflect the volatility of a series. The smaller the value, the more stable the trend; the larger the value, the greater the volatility and the less clear the trend.

[0010] Based on the above scheme, the preferred formula for calculating the comprehensive quality score Q is: ; in, , , All are weighting coefficients, and When the calculated comprehensive quality score Q is less than the set minimum value, it is marked as a low-quality data asset and a governance task is triggered.

[0011] In a preferred embodiment of the above scheme, the dynamic anomaly detection machine employs an unsupervised machine learning algorithm to identify latent anomalies in data relationships and distribution patterns.

[0012] Secondly, this application provides a data asset operation decision-making system based on artificial intelligence, which specifically includes: a data acquisition and feature fusion module, a comprehensive quality assessment module, a value dynamic prediction module, an intelligent decision generation module, and an execution effect evaluation and alarm module; The data acquisition and feature fusion module is used to collect multi-dimensional feature data of the target data asset and to perform vectorized fusion of the collected multi-dimensional feature data to form a feature representation F; The comprehensive quality assessment module includes three sub-modules: a preset rule engine, a dynamic anomaly detection machine, and a historical trend analysis, which are used to perform quality assessment and value classification on the feature representation F. The value dynamic prediction module is used to predict and evaluate the future expected value Vp, predicted risk value Ri, and predicted cost value Zm of the target data asset based on the feature representation F, the comprehensive quality score Q, and historical data. The intelligent decision generation module is used to execute step S4, constructing a multi-objective decision function with the objectives of maximizing the expected future value Vp, minimizing the predicted risk value Ri, and optimizing the predicted cost value Zm. It takes the comprehensive quality score Q, real-time business demand Rb, and operational constraints C as inputs, and performs strategy optimization through optimization algorithms to generate recommended operational actions Aopt. The execution effect evaluation and alarm module is used to monitor the actual effect after executing the recommended operation action Aopt, calculate the completion coefficient E, and issue an alarm when the evaluation value of the completion coefficient E is lower than a preset threshold.

[0013] Thirdly, this application provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the aforementioned data asset operation decision-making method based on artificial intelligence by calling the computer program stored in the memory.

[0014] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the aforementioned data asset operation decision-making method based on artificial intelligence.

[0015] Compared with the prior art, the beneficial effects of the present invention are: This invention first collects multi-dimensional feature data of the target data asset, and then vectorizes and fuses the collected multi-dimensional feature data to form a feature representation F. Next, the feature representation F is quality-assessed. Then, based on the feature representation F, the comprehensive quality score Q, and historical data, the future expected value Vp, predicted risk value Ri, and predicted cost value Zm of the target data asset are predicted and assessed. Next, a multi-objective decision function is constructed with the objectives of maximizing the future expected value Vp, minimizing the predicted risk value Ri, and optimizing the predicted cost value Zm. An optimization algorithm is used to find the best strategy and generate a recommended operational action Aopt. This automatically transforms the prediction results into executable operational decisions, significantly reducing the reliance on human experience. Finally, the actual effect of executing the recommended operational action Aopt is monitored, and a completion coefficient E is calculated. An alarm is issued when the evaluation value of the completion coefficient E is lower than a preset threshold. By integrating internal and external multi-modal features, a panoramic and real-time quantification of the data asset value is achieved, making value judgments more aligned with business realities and breaking through the limitations of static assessment. Combined with time series analysis, it not only predicts the value trend of the data asset itself but also captures its related impacts in the business ecosystem, improving the accuracy and foresight of the prediction. Attached Figure Description

[0016] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a schematic diagram of the overall process of a data asset operation decision-making method based on artificial intelligence according to the present invention; Figure 2 This is a flowchart illustrating step S2 in an artificial intelligence-based data asset operation decision-making method of the present invention. Figure 3 This is a schematic diagram of the framework of an artificial intelligence-based data asset operation decision-making system according to the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0018] Example 1 To address the technical problems raised in the background art, this application provides a preferred embodiment: such as Figures 1-3 As shown, an artificial intelligence-based data asset operation decision-making method includes the following specific steps: S1. Collect multi-dimensional feature data of the target data asset, and vectorize and fuse the collected multi-dimensional feature data to form feature representation F. The multi-dimensional feature data includes internal quality dimension features, business relationship dimension features, and market environment dimension features. S2. Perform a quality assessment on the feature representation F; The quality evaluation of the feature representation F includes the following steps: S21. Based on the preset quality rule engine, perform rule compliance checks on the internal quality dimension features in the feature representation F, and output the rule compliance score Sr; S22. Based on the dynamic anomaly detection machine, perform anomaly pattern recognition on the business-related dimension features and market environment dimension features in the feature representation F, and output the anomaly degree score Sa; S23. Obtain the recent historical quality score sequence of the target data asset, analyze its changing trend, and output the trend score St. S24. Calculate the overall quality score Q based on the results of the rule compliance score Sr, the anomaly score Sa, and the trend score St. S3. Based on the feature representation F, the comprehensive quality score Q, and historical data, predict and evaluate the future expected value Vp, the predicted risk value Ri, and the predicted cost value Zm of the target data asset. S4. Construct a multi-objective decision function with the objectives of maximizing the expected future value Vp, minimizing the predicted risk value Ri, and optimizing the predicted cost value Zm. Take the comprehensive quality score Q, real-time business demand Rb, and operational constraints C as inputs, and use the optimization algorithm to optimize the strategy to generate recommended operational actions Aopt. S5. Monitor the actual effect of the recommended operational action Aopt, calculate the completion coefficient E, and issue an alarm when the evaluation value of the completion coefficient E is lower than the preset threshold. The formula for calculating the completion coefficient E is: ; in, , , These are the weighting coefficients. The actual value of data assets This represents the actual risk value. This represents the actual cost value.

[0019] It should be noted that the calculation formula for the completion coefficient E in step S5 can be used to calculate the completion coefficient E from multiple aspects such as the actual value of data assets, actual risk value, and actual cost value. Finally, the calculation result of the completion coefficient E can be used to issue early warnings and monitor subsequent operations.

[0020] The advantages of this embodiment compared to the prior art are: it can automatically transform the prediction results into actionable operational decisions, significantly reduce the reliance on human experience in decision-making, and achieve a panoramic and real-time quantification of the value of data assets by integrating internal and external multimodal features, making value judgments more in line with actual business, breaking through the limitations of static evaluation, and combining time series analysis to not only predict the value trend of data assets themselves, but also capture their related impact in the business ecosystem, thereby improving the accuracy and foresight of predictions.

[0021] Furthermore: In an optional embodiment, the rule compliance score Sr is calculated using the following formula: ; Where N is the total number of preset quality rules. Let K be the weight of the rule. This is an indicator function. It takes a value of 1 when feature F fully conforms to the k-th rule, a value of 0 when it does not conform at all, and a value within the range [0, 0] when it partially conforms, depending on the degree of conformity. The value is retrieved from within.

[0022] It should be noted that: through indicator functions Map the ratings to intervals Within this range, the scoring can smoothly reflect subtle changes in quality indicators, ensuring that the calculated rule compliance score Sr ultimately remains within the range. This information is stored within the data to facilitate the subsequent calculation of the overall quality score Q.

[0023] In an optional embodiment, the abnormality score Sa is calculated using the following formula: ; Where T is the number of detection time windows. The score for the business-related anomalies detected in the t-th detection time window is... Let be the score of the market environment anomalies detected in the t-th detection time window, and and All within the range The value is retrieved from within. These are the weighting coefficients.

[0024] It should be noted that the calculation formula for the anomaly score Sa combines the business-related anomaly score and the market environment anomaly score, and ultimately ensures that the calculated anomaly score Sa remains within the specified range. This facilitates the subsequent calculation of the overall quality score Q and provides stable and reliable anomaly detection capabilities in complex and ever-changing business environments.

[0025] Furthermore: In an optional embodiment, the trend score St is calculated using the following formula: ; Here, 50 points represents a neutral benchmark, with upward movement indicating an improving trend and downward movement indicating a deteriorating trend. 'b' represents the trend slope, 'P' is the autocorrelation coefficient of the historical quality score series, reflecting the persistence of the trend (closer to 1 indicates a more consistent trend, closer to 0 indicates a less persistent trend), and 'G' is the trend strength benchmark, a constant used to normalize the trend slope 'b'. The relative standard deviation is used to reflect the volatility of a series. The smaller the value, the more stable the trend; the larger the value, the greater the volatility and the less clear the trend.

[0026] It should be noted that the formula for calculating the trend score St ensures that the result of the trend score St remains within the specified range. This allows for the subsequent calculation of the overall quality score Q, and the value is stable, avoiding score overflow due to extreme values.

[0027] In an optional embodiment, the formula for calculating the overall quality score Q is: ; in, , , All are weighting coefficients, and When the calculated comprehensive quality score Q is less than the set minimum value, it is marked as a low-quality data asset and a governance task is triggered.

[0028] It should be noted that the formula for calculating the comprehensive quality score Q integrates the rule compliance score Sr, the anomaly score Sa, and the trend score St. It can calculate the comprehensive quality score Q from multiple dimensions, enabling a panoramic and real-time quantification of the value of data assets. This makes the value judgment more aligned with actual business needs and breaks through the limitations of static evaluation.

[0029] In an optional embodiment, the dynamic anomaly detection machine employs an unsupervised machine learning algorithm to identify latent anomalies in data relationships and distribution patterns.

[0030] Example 2 Based on the same inventive concept as in Embodiment 1, such as Figure 1 As shown, this embodiment provides a data asset operation decision-making system based on artificial intelligence, which specifically includes: a data acquisition and feature fusion module, a comprehensive quality assessment module, a value dynamic prediction module, an intelligent decision generation module, and an execution effect evaluation and alarm module; The data acquisition and feature fusion module is used to collect multi-dimensional feature data of the target data asset and to perform vectorized fusion of the collected multi-dimensional feature data to form a feature representation F; The comprehensive quality assessment module includes three sub-modules: a preset rule engine, a dynamic anomaly detection machine, and a historical trend analysis, which are used to assess the quality and classify the value of the feature representation F. The value dynamic prediction module is used to predict and evaluate the future expected value Vp, predicted risk value Ri, and predicted cost value Zm of the target data asset based on the feature representation F, comprehensive quality score Q, and historical data. The intelligent decision generation module is used to execute step S4, which constructs a multi-objective decision function with the objectives of maximizing the future expected value Vp, minimizing the predicted risk value Ri, and optimizing the predicted cost value Zm. It takes the comprehensive quality score Q, real-time business demand Rb, and operational constraints C as inputs, and optimizes the strategy through the optimization algorithm to generate the recommended operational action Aopt. The performance evaluation and alert module is used to monitor the actual effect of the recommended operational action Aopt, calculate the completion coefficient E, and issue an alert when the evaluation value of the completion coefficient E is lower than a preset threshold.

[0031] The steps for implementing the corresponding functions of each parameter and each unit module in the data asset operation decision system based on artificial intelligence of the present invention described above can be referred to the parameters and steps in the embodiments of the data asset operation decision method based on artificial intelligence described above, and will not be repeated here.

[0032] Example 3 Based on the same inventive concept as Embodiment 1, this embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the aforementioned data asset operation decision-making method based on artificial intelligence by calling the computer program stored in the memory.

[0033] It should be noted that all computer programs for an AI-based data asset operation decision-making method are implemented using the C programming language.

[0034] Example 4 Based on the same inventive concept as in Embodiment 1, this embodiment proposes a computer-readable storage medium having an erasable and rewritable computer program stored thereon. When a computer program runs on a computer device, it enables the computer device to execute the aforementioned data asset operation decision-making method based on artificial intelligence.

[0035] For example, computer-readable storage media can be read-only memory, random access memory, read-only optical disc, magnetic tape, floppy disk, and optical data storage devices.

[0036] The various embodiments in this invention are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, the embodiments for IoT devices and media are relatively simple in description because they are fundamentally similar to the method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0037] The systems, media, and methods provided in the embodiments of the present invention are in one-to-one correspondence. Therefore, the systems and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be repeated here.

[0038] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0039] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0040] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0041] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0042] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0043] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0044] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0045] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. The above are merely embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A data asset operation decision-making method based on artificial intelligence, characterized in that, Includes the following steps: S1. Collect multi-dimensional feature data of the target data asset, and vectorize and fuse the collected multi-dimensional feature data to form feature representation F. The multi-dimensional feature data includes internal quality dimension features, business relationship dimension features, and market environment dimension features. S2. Perform a quality assessment on the feature representation F; The quality evaluation of the feature representation F includes the following steps: S21. Based on the preset quality rule engine, perform rule compliance checks on the internal quality dimension features in the feature representation F, and output the rule compliance score Sr; S22. Based on the dynamic anomaly detection machine, perform anomaly pattern recognition on the business-related dimension features and market environment dimension features in the feature representation F, and output the anomaly degree score Sa; S23. Obtain the recent historical quality score sequence of the target data asset, analyze its changing trend, and output the trend score St. S24. Calculate the overall quality score Q based on the results of the rule compliance score Sr, the anomaly score Sa, and the trend score St. S3. Based on the feature representation F, the comprehensive quality score Q, and historical data, predict and evaluate the future expected value Vp, the predicted risk value Ri, and the predicted cost value Zm of the target data asset. S4. Construct a multi-objective decision function with the objectives of maximizing the expected future value Vp, minimizing the predicted risk value Ri, and optimizing the predicted cost value Zm. Take the comprehensive quality score Q, real-time business demand Rb, and operational constraints C as inputs, and use the optimization algorithm to optimize the strategy to generate recommended operational actions Aopt. S5. Monitor the actual effect of the recommended operational action Aopt, calculate the completion coefficient E, and issue an alarm when the evaluation value of the completion coefficient E is lower than the preset threshold. The formula for calculating the completion coefficient E is: ； in, , , These are the weighting coefficients. The actual value of data assets This represents the actual risk value. This represents the actual cost value.

2. The data asset operation decision-making method based on artificial intelligence according to claim 1, characterized in that: The formula for calculating the rule compliance score Sr is as follows: ； Where N is the total number of preset quality rules. Let K be the weight of the rule. This is an indicator function. It takes a value of 1 when feature F fully conforms to the k-th rule, a value of 0 when it does not conform at all, and a value within the range [0, 0] when it partially conforms, depending on the degree of conformity. The value is retrieved from within.

3. The data asset operation decision-making method based on artificial intelligence according to claim 1, characterized in that: The formula for calculating the anomaly score Sa is as follows: ； Where T is the number of detection time windows. The score for the business-related anomalies detected in the t-th detection time window is... Let be the score of the market environment anomalies detected in the t-th detection time window, and and All within the range The value is retrieved from within. These are the weighting coefficients.

4. The data asset operation decision-making method based on artificial intelligence according to claim 1, characterized in that: The formula for calculating the trend score St is: ； Here, 50 points represents a neutral benchmark, with upward movement indicating an improving trend and downward movement indicating a deteriorating trend. 'b' represents the trend slope, 'P' is the autocorrelation coefficient of the historical quality score series, reflecting the persistence of the trend (closer to 1 indicates a more consistent trend, closer to 0 indicates a less persistent trend), and 'G' is the trend strength benchmark, a constant used to normalize the trend slope 'b'. The relative standard deviation is used to reflect the volatility of a series. The smaller the value, the more stable the trend; the larger the value, the greater the volatility and the less clear the trend.

5. The data asset operation decision-making method based on artificial intelligence according to claim 1, characterized in that: The formula for calculating the overall quality score Q is: ； in, , , All are weighting coefficients, and When the calculated comprehensive quality score Q is less than the set minimum value, it is marked as a low-quality data asset and a governance task is triggered.

6. The data asset operation decision-making method based on artificial intelligence according to claim 1, characterized in that: The dynamic anomaly detection machine employs an unsupervised machine learning algorithm to identify latent anomalies in data relationships and distribution patterns.

7. A data asset operation decision-making system based on artificial intelligence, implemented based on the data asset operation decision-making method based on artificial intelligence as described in any one of claims 1-6, characterized in that, Specifically, it includes: a data acquisition and feature fusion module, a comprehensive quality assessment module, a value dynamic prediction module, an intelligent decision generation module, and an execution effect evaluation and alert module; The data acquisition and feature fusion module is used to collect multi-dimensional feature data of the target data asset and to perform vectorized fusion of the collected multi-dimensional feature data to form a feature representation F; The comprehensive quality assessment module includes three sub-modules: a preset rule engine, a dynamic anomaly detection machine, and a historical trend analysis, which are used to perform quality assessment and value classification on the feature representation F. The value dynamic prediction module is used to predict and evaluate the future expected value Vp, predicted risk value Ri, and predicted cost value Zm of the target data asset based on the feature representation F, the comprehensive quality score Q, and historical data. The intelligent decision generation module is used to execute step S4, constructing a multi-objective decision function with the objectives of maximizing the expected future value Vp, minimizing the predicted risk value Ri, and optimizing the predicted cost value Zm. It takes the comprehensive quality score Q, real-time business demand Rb, and operational constraints C as inputs, and performs strategy optimization through optimization algorithms to generate recommended operational actions Aopt. The execution effect evaluation and alarm module is used to monitor the actual effect after executing the recommended operation action Aopt, calculate the completion coefficient E, and issue an alarm when the evaluation value of the completion coefficient E is lower than a preset threshold.

8. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor, characterized in that: the processor executes a data asset operation decision-making method based on artificial intelligence as described in any one of claims 1-6 by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that: The system stores instructions that, when executed on a computer, cause the computer to perform an artificial intelligence-based data asset operation decision-making method as described in any one of claims 1-6.

Images