Digital asset monitoring method and system

Abstract

The invention relates to the field of data processing, in particular to a digital asset monitoring method and system. The method comprises the steps of obtaining a to-be-processed data asset object; the data asset object comes from a multi-source business system, and the multi-source business system at least comprises different business units of a target enterprise; mapping the data asset object to a target node corresponding to a graph isomorphic network according to an asset attribute and a business unit to which the data asset object belongs to obtain a target graph isomorphic network; the asset feature vector of each node in the target graph isomorphic network is updated through neighborhood aggregation processing; and monitoring the data asset object through the updated target graph isomorphic network, and outputting a real-time monitoring state of the data asset object. According to the method, the technical problem that data integration and sharing become extremely complex due to the fact that interfaces and protocols between systems are not unified in the related technology is effectively solved, and the decision-making efficiency and the response speed are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a digital asset monitoring method and system. Background Art

[0002] With the deepening of "Internet +" and digital transformation, enterprises are experiencing new changes in quality and efficiency in various fields. This change not only provides new impetus for economic transformation and growth, but also creates important opportunities for enterprises to open up blue oceans in the fiercely competitive market. However, the integration and transformation of traditional business and digital business inevitably brings technical challenges.

[0003] Enterprises must promote business innovation flexibly and efficiently on the basis of maintaining the steady development of traditional core businesses, and gradually achieve the re-upgrade of core businesses. This process requires enterprises to adopt a spiral iterative development model of "seeking innovation in stability" to promote the continuous evolution and optimization of businesses, so as to take the initiative in a market environment full of opportunities and uncertainties.

[0004] Taking airlines as an example, many airlines face the problem of lack of unified standards and specifications for internal systems during the digital transformation process. This makes it difficult to integrate and share data, thus forming "data islands". This situation is particularly evident in airlines that started informatization earlier and have more complete system construction. The interfaces and protocols between systems are not unified, making data integration and sharing extremely complicated, affecting decision-making efficiency and response speed. Summary of the invention

[0005] In view of the technical problems existing in the prior art, the present invention provides a digital asset monitoring method and system to solve the technical problems that the interfaces and protocols between various systems in the related technology are not unified, making data integration and sharing extremely complicated, and affecting the decision-making efficiency and response speed.

[0006] In a first aspect, an embodiment of the present application provides a digital asset monitoring method, the method comprising:

[0007] Acquire a data asset object to be processed; the data asset object comes from a multi-source business system, and the multi-source business system includes at least different business units of the target enterprise;

[0008] According to the asset attributes and the business units to which they belong, the data asset objects are mapped to the target nodes corresponding to the graph isomorphic network to obtain the target graph isomorphic network;

[0009] Updating the asset feature vector of each node in the target graph isomorphic network through neighborhood aggregation processing; wherein the neighborhood aggregation processing parameters are determined by the monitoring requirements of the data assets and the complexity between the multi-source business units;

[0010] The data asset object is monitored through the updated target graph isomorphic network, and the real-time monitoring status of the data asset object is output.

[0011] In a second aspect, an embodiment of the present application provides a digital asset monitoring system, the system comprising the following units, wherein:

[0012] A collection unit is configured to obtain a data asset object to be processed; the data asset object comes from a multi-source business system, and the multi-source business system includes at least different business units of the target enterprise;

[0013] A construction unit is configured to map the data asset object to a target node corresponding to the graph isomorphic network according to the asset attribute and the business unit to which it belongs, so as to obtain a target graph isomorphic network;

[0014] An aggregation unit is configured to update the asset feature vector of each node in the target graph isomorphic network through neighborhood aggregation processing; wherein the neighborhood aggregation processing parameters are determined by the monitoring requirements of the data assets and the complexity between the multi-source business units;

[0015] The optimization unit is configured to monitor the data asset object through the updated target graph isomorphic network and output the real-time monitoring status of the data asset object.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising:

[0017] at least one processor, memory, and input-output unit;

[0018] The memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the digital asset monitoring method of the first aspect.

[0019] In a fourth aspect, a computer-readable storage medium is provided, which includes instructions, and when the instructions are executed on a computer, the computer executes the digital asset monitoring method of the first aspect.

[0020] The beneficial effects of the present invention are: providing a digital asset monitoring method and system. In the technical scheme, a data asset object to be processed is obtained; the data asset object comes from a multi-source business system, and the multi-source business system includes at least different business units of the target enterprise; according to the asset attributes and the business units to which it belongs, the data asset object is mapped to the target node corresponding to the graph isomorphic network to obtain the target graph isomorphic network; the asset feature vector of each node in the target graph isomorphic network is updated through neighborhood aggregation processing; wherein the neighborhood aggregation processing parameters are determined by the monitoring requirements of the data assets and the complexity between the multi-source business units; the data asset object is monitored through the updated target graph isomorphic network, and the real-time monitoring status of the data asset object is output. In the technical scheme, through the structured representation of the graph isomorphic network and the neighborhood aggregation processing technology, the effective integration, dynamic update and real-time monitoring of multi-source data assets are realized, which has the technical advantages of high efficiency, adaptability and accuracy, and can provide strong data monitoring support in a complex business environment. The technical scheme effectively solves the technical problem that the interfaces and protocols between the systems in the related technology are not unified, making data integration and sharing extremely complicated, and improves the decision-making efficiency and response speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flowchart of a digital asset monitoring method according to an embodiment of the present application;

[0022] Figure 2 It is a structural diagram of a digital asset monitoring system according to an embodiment of the present application;

[0023] Figure 3 is a schematic diagram of the structure of an electronic device according to an embodiment of the present application;

[0024] Figure 4 It is a structural schematic diagram of a medium device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0026] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0027] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0028] The embodiment of the present application provides a digital asset monitoring method and system. In this technical solution, the data asset object to be processed is obtained; the data asset object comes from a multi-source business system, and the multi-source business system at least includes different business units of the target enterprise; according to the asset attributes and the business units to which it belongs, the data asset object is mapped to the target node corresponding to the graph isomorphic network to obtain the target graph isomorphic network; the asset feature vector of each node in the target graph isomorphic network is updated through neighborhood aggregation processing; wherein the neighborhood aggregation processing parameters are determined by the monitoring requirements of the data assets and the complexity between the multi-source business units; the data asset object is monitored through the updated target graph isomorphic network, and the real-time monitoring status of the data asset object is output.

[0029] In the embodiment of the present application, by mapping the data asset objects of different business units to the target nodes in the graph isomorphic network, a unified view of multi-source data assets is achieved, and the efficiency of data integration and cross-system collaboration is improved. At the same time, the mapping of asset attributes and business units ensures the consistent representation of data assets, thereby forming a clear asset relationship map. Using neighborhood aggregation processing technology, the asset feature vector of the node is dynamically updated according to the data asset characteristics and neighborhood information, and the node characteristics are combined with the information of the node itself and other nodes in its neighborhood, so that the node characteristics more accurately reflect the actual state and business relationship. The method is highly adaptable and can adjust parameters according to monitoring requirements and business unit complexity, providing flexible and accurate feature updates. Through the updated graph isomorphic network, the state changes and potential risks of data asset objects can be monitored in real time, which improves the real-time and accuracy of monitoring. At the same time, the output of real-time monitoring status supports detailed monitoring reports and feedback, which helps to timely discover and handle abnormal situations and provide support for decision-making. Taking into account the complexity between multi-source business units, it can effectively handle complex relationships and dynamic changes in business systems, and enhance the stability and reliability of the system in complex business environments. In addition, by associating asset objects of different business units through graph isomorphic networks, cross-business unit asset relationship monitoring and analysis are realized, and data integration capabilities are improved. With the help of the structural characteristics of graph isomorphic networks and neighborhood aggregation technology, more accurate asset feature vectors and monitoring status are provided, and the accuracy of problem and risk identification is enhanced. At the same time, real-time updates and dynamic adjustment mechanisms improve the efficiency of the monitoring system and reduce manual intervention and maintenance costs.

[0030] In summary, this method achieves effective integration and real-time monitoring of multi-source data assets through structured representation and dynamic update. It is efficient, adaptable and accurate, and can provide strong data monitoring support in complex business environments. This technical solution effectively solves the technical problem that the interfaces and protocols between systems in related technologies are not unified, making data integration and sharing extremely complicated, and improves decision-making efficiency and response speed.

[0031] The digital asset monitoring solution provided in the embodiments of the present application may also be executed by an electronic device, which may be a server, a server cluster, or a cloud server. The electronic device may also be a terminal device such as a mobile phone, a computer, a tablet computer, a wearable device, or a dedicated device (such as a dedicated terminal device with a digital asset monitoring system). These electronic devices may also be equipped with the chips described in the above embodiments. Alternatively, these electronic devices may also be installed with a service program for executing the digital asset monitoring solution.

[0032] Figure 1 A flowchart of a digital asset monitoring method provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method comprises the following steps:

[0033] 101, obtaining the data asset object to be processed;

[0034] 102, mapping the data asset object to a target node corresponding to the graph isomorphic network according to the asset attribute and the business unit to which it belongs, to obtain a target graph isomorphic network;

[0035] 103, updating the asset feature vector of each node in the target graph isomorphic network through neighborhood aggregation processing;

[0036] 104. Monitor the data asset object through the updated target graph isomorphic network and output the real-time monitoring status of the data asset object.

[0037] In an embodiment of the present application, the data asset object comes from a multi-source business system, and the multi-source business system includes at least different business units of the target enterprise. The description that the data asset object comes from a multi-source business system means that the data asset does not come from a single business system, but from multiple different business systems, and there may be certain associations or complexities between these systems. These business systems include at least different business units of the target enterprise. Specifically, the source of the data asset object involves multiple business systems. These systems may be different systems within the target enterprise, or external systems related to the target enterprise. This collection of multi-source data may include sales systems, financial systems, customer relationship management systems, etc. These business systems may have different functions and data formats, but they jointly provide comprehensive data about the operation of the enterprise. For example, the business units of the target enterprise. The data asset objects in these business systems come from different business units within the target enterprise. These business units may refer to various departments, teams or branches in the enterprise, such as the marketing department, the research and development department, the production department, etc. For example, horizontal integration of data. Since these business units operate independently, the data may differ between the units. Therefore, it is necessary to integrate these data for unified management and analysis.

[0038] Data assets refer to the data generated, stored, and used in these business systems, such as sales records, financial statements, customer information, etc. Data asset objects refer to specific data entities that represent different business information or records.

[0039] In this way, since the data asset objects come from multiple business systems and business units, processing these data requires integrating data from different sources onto a unified platform for centralized management and analysis. Realizing the monitoring of these data assets can help enterprises fully understand the operating conditions of each business unit, identify potential problems and respond in a timely manner. In summary, the data asset objects in the embodiments of the present application come from multiple business systems, especially different business units within the target enterprise. This multi-source and multi-unit data structure requires the use of technical means that can handle diverse data sources and complex relationships in monitoring and management to achieve efficient data integration and real-time monitoring.

[0040] Further optionally, in 101, data assets in the multi-source business system are identified; and asset vectorization processing corresponding to the data assets is performed according to asset types to obtain data asset objects corresponding to the data assets. The asset types include at least one of financial assets, customer assets, inventory assets, route operation assets, equipment assets, operation assets, human resource scheduling assets, market dynamic monitoring assets, and compliance assets.

[0041] In an embodiment of the present application, step 101 involves identifying data assets in a multi-source business system, performing vectorization processing according to different asset types, and finally generating data asset objects. Specifically, the enterprise first identifies valuable data assets, such as sales records, inventory levels, and customer information, from multiple sources such as financial systems, customer management systems, and inventory systems. Then, according to the asset type (such as financial assets, customer assets, inventory assets, etc.), these data assets are vectorized and the raw data is converted into computer-processable feature vectors. The processing method includes steps such as feature extraction, data encoding, and application of vectorization models. Ultimately, these vectorized data asset objects can be used for further analysis and real-time monitoring, thereby supporting the enterprise's decision-making and business management.

[0042] As an optional embodiment, in the implementation step of 101 above, performing asset vectorization processing corresponding to the data asset according to the asset type to obtain the data asset object corresponding to the data asset can be implemented as follows:

[0043] Identify the asset type corresponding to the data asset; determine at least one data-based indicator that matches the data asset based on the asset type; based on the at least one data-based indicator, use a corresponding preset feature extraction method to extract key feature information from the data asset to obtain an initial data asset object corresponding to the data asset; reconstruct the initial data asset object corresponding to the data asset to obtain a data asset object corresponding to the data asset.

[0044] Exemplarily, the asset quantization processing in step 101 can be implemented in the following manner: first, identify the type of data assets, such as financial assets or customer assets. Then, determine the matching data indicators based on these asset types, such as financial assets may involve indicators such as profit margins and cash flow, while customer assets may involve indicators such as purchase frequency and customer satisfaction. Next, based on these data indicators, a preset feature extraction method is used to extract key feature information from the data assets. For example, for customer assets, feature extraction may include analyzing the customer's purchasing behavior and interaction records to obtain an initial data asset object. Finally, the initial data asset object is reconstructed to convert it into a final data asset object that meets the analysis requirements. This processing process ensures that the data asset object can accurately reflect the key characteristics of the asset and provide support for further analysis and application.

[0045] As an optional embodiment, in 102, mapping the data asset object to the target node corresponding to the graph isomorphic network according to the asset attribute and the business unit to which it belongs can be implemented as follows:

[0046] Identify the asset attributes of the data asset object and the business unit to which it belongs; select a node prototype template corresponding to the data asset object according to the business unit to which it belongs;

[0047] According to the node prototype template, the asset attributes are constructed as asset attribute features in the node prototype to obtain the node prototype corresponding to the data asset object;

[0048] The node network development model is adopted to adaptively optimize the connection relationship between the node prototype and surrounding nodes, and the optimized node prototype is used as the target node.

[0049] The business unit is determined based on the business department to which the data asset object is collected, or the business unit is determined based on the business function to which the data asset object is collected.

[0050] The business department includes at least one of the business department, technical support department, post-sales department, logistics department, passenger department, finance department, sales department, and operation department; the business functions include at least one of technical services, decision-making and scheduling, passenger services, marketing, supply chain management, and logistics operations.

[0051] In the implementation step, the business unit can be determined based on the business department or business function to which the data asset object is collected. Assume that data assets are vectorized in a large airline and consider how the business unit of data assets is determined. If the data asset objects are collected from the sales department, such as sales order data or customer purchase records, these data asset objects will be assigned to the sales department business unit. If the data asset objects come from the technical support department, such as technical fault records or maintenance data, then these data asset objects will be classified into the technical support department business unit. For data asset objects related to passenger services, such as passenger satisfaction survey results or passenger complaint records, these data asset objects will be assigned to the passenger service business function unit. If the data asset objects involve supply chain management, such as supplier performance data or inventory flow, these objects will be assigned to the supply chain management business function unit.

[0052] The sales order data is as follows:

[0053] Business Department: Sales Department

[0054] Business function: Marketing

[0055] Sales order data can help the sales department analyze sales performance and be used to formulate marketing strategies. Therefore, the data asset object is classified into the sales department business unit and associated with the marketing function.

[0056] The inventory level data is as follows:

[0057] Business Department: Logistics Department

[0058] Business function: Supply chain management

[0059] Stock level data is crucial for the logistics department as it is used to manage inventory and logistics operations. Data asset objects are assigned to the logistics department and are closely related to the supply chain management function.

[0060] The technical failure record is as follows:

[0061] Business Department: Technical Support Department

[0062] Business function: Technical service

[0063] Technical trouble records reflect the service situation of the technical support department and are very important to the technical service function. Therefore, the data asset object is assigned to the technical support department and associated with the technical service function.

[0064] In this way, business unit identification of data asset objects can ensure that relevant departments and functions can make full use of data for effective analysis and decision support.

[0065] As an optional embodiment, in the implementation step 102 above, after selecting the node prototype template corresponding to the data asset object according to the business unit to which it belongs, it can also be implemented as follows:

[0066] Obtain the actual needs of the business unit to which the data asset object belongs; determine whether the selected node prototype template meets the asset attributes and the actual needs; if not, trigger the corresponding template optimization process to make the optimized node prototype template meet the asset attributes and the actual needs; or, if it meets, record the selected node prototype template as the judgment result.

[0067] As an optional embodiment, when executing step 102, not only the corresponding node prototype template should be selected according to the business unit to which the data asset object belongs, but also the actual needs of the business unit should be considered, and the selected template should be ensured to be consistent with the asset attributes and these needs. First, it is necessary to have a deep understanding of the specific workflow and business needs of the business unit to which the data asset object belongs. For example, if the data asset object comes from the sales department, it may be necessary to understand how they track sales leads, manage customer relationships, and analyze sales data. After selecting the preliminary node prototype template, it is necessary to determine whether the template can fully reflect the attributes of the data asset object and meet the actual needs of the sales department. This may involve whether the fields, data display methods, interactive functions, etc. in the template are consistent with the working habits and analysis needs of the sales department. If it is found that the selected node prototype template does not meet the asset attributes or actual needs, it is necessary to trigger the template optimization process. For example, the sales department may need a template that can update sales data in real time, display sales trends, and provide early warning functions. In this case, the design of the template can be adjusted to add necessary data visualization components and interactive functions to meet these specific needs. If the selected node prototype template already meets the asset attributes and actual needs, it can be used as the final selected template and recorded as the judgment result. In this way, in future data analysis or visualization processes, this verified template can be used directly to improve work efficiency and accuracy.

[0068] For example, suppose there is a data asset object that is a data set about product sales volume, which belongs to the sales department. The sales department hopes to monitor the sales of each product in real time so as to adjust the sales strategy in time. They need an intuitive and real-time sales data display template. A node prototype template containing a bar chart and a line chart was initially selected to display the sales volume and sales trend of each product. After communicating with the sales department, it was found that they also needed a function to set a sales volume threshold and issue an early warning when the sales volume was lower than the threshold. The template initially selected did not include this function. According to the feedback from the sales department, the template was optimized, an early warning function component was added, and the frequency of data updates was adjusted to ensure real-time performance. The optimized template was recognized by the sales department and recorded as a standard template for future sales data analysis. Through this embodiment, it can be seen that when selecting a node prototype template, not only the attributes and business units of the data asset object should be considered, but also customization and optimization should be closely combined with actual business needs.

[0069] As an optional embodiment, it is assumed that the node network development model includes at least the following structures: an exploration layer, a scoring layer, and an optimization layer.

[0070] Based on the assumption, in the implementation step 102 above, the node network development model is adopted to adaptively optimize the connection relationship between the node prototype and the surrounding nodes, which can be implemented as follows:

[0071] Through the exploration layer, all surrounding nodes connected to the node prototype are traversed to obtain preliminary connection relationship features between the node prototype and each surrounding node, as well as corresponding potential connection patterns;

[0072] Through the scoring layer, based on the preliminary connection relationship characteristics and potential connection patterns with each surrounding node, the scoring performance value between each surrounding node is predicted; the scoring performance value is determined by at least one of the similarity between nodes, interaction frequency, business relevance, business interaction stability, and historical data support status;

[0073] Through the optimization layer, based on the score performance value, the connection relationship between the node prototype and at least part of the surrounding nodes in the graph isomorphic network is adjusted to complete the connection relationship between the node prototype and the surrounding nodes.

[0074] As an optional embodiment, assuming that the node network development model includes an exploration layer, a scoring layer and an optimization layer, the implementation step 102 can adaptively optimize the connection relationship between the node prototype and the surrounding nodes in the following manner. First, in the exploration layer, by traversing all the surrounding nodes connected to the node prototype, the preliminary connection relationship characteristics and potential connection patterns between these nodes can be obtained. For example, in a sales data analysis system, the node prototype represents a salesperson, and the surrounding nodes may include other salespeople, customers and product data. The exploration layer will analyze the interactive characteristics of these nodes, such as sales, customer feedback, etc., to identify potential association patterns. Next, the scoring layer uses these preliminary connection relationship characteristics and potential connection patterns to predict the scoring performance values ​​between the nodes. These scoring performance values ​​may be determined based on factors such as similarity, interaction frequency, business relevance, etc. between nodes, for example, the frequency of cooperation between salespeople and the interaction of common customers. Finally, in the optimization layer, according to the scoring performance value, the connection relationship between the node prototype and at least part of the surrounding nodes is adjusted to optimize the structure of the graph isomorphic network. Continuing with the above example, through the optimization layer, the system may readjust the data connection between salespeople and customers, so that salespeople with similar sales patterns can collaborate better and ultimately improve overall sales performance. This adaptive optimization process ensures that the network structure can effectively support business goals and actual needs.

[0075] Furthermore, in the above model, through the scoring layer, based on the preliminary connection relationship characteristics and potential connection patterns with each surrounding node, the score performance value between each surrounding node is predicted, which can be implemented as follows:

[0076] A business unit scoring function corresponding to the node prototype and an optimization target corresponding to the asset attribute are set; based on the business unit scoring function and the optimization target, the preliminary connection relationship characteristics and potential connection patterns between the node prototype and each surrounding node are adaptively evaluated to obtain a scoring performance value corresponding to each surrounding node.

[0077] In the above model, through the scoring layer, the scoring performance value of each surrounding node can be predicted based on the preliminary connection relationship characteristics and potential connection patterns between the node prototype and each surrounding node. This process first involves setting the business unit scoring function corresponding to the node prototype and the optimization objectives corresponding to the asset attributes. The optimization objectives can include interaction evaluation attributes, business evaluation attributes, and resource utilization. The business unit scoring function is designed to integrate these objectives in order to evaluate the connection quality between the node prototype and the surrounding nodes.

[0078] In an embodiment of the present application, the optimization objectives include at least: interaction evaluation attributes, business evaluation attributes, and resource utilization. For example, in an intelligent recommendation system, interaction evaluation attributes may be the click-through rate and interaction frequency between users and recommended content; business evaluation attributes may involve the conversion rate and user satisfaction of recommended content; and resource utilization focuses on the efficiency of computing resources and storage resources in the recommendation system. The optimization process adjusts the recommendation algorithm and resource allocation strategy according to these goals, thereby improving the overall performance and user experience of the system, ensuring that the recommendation results are more accurate and that system resources are effectively utilized.

[0079] In the embodiment of the present application, the business unit scoring function is expressed as:

[0080]

[0081] Among them, P(i) represents the score performance value corresponding to the i-th surrounding node, P i-1 Indicates the historical score performance value corresponding to the i-1th surrounding node, represents the influence weight of the i-1th surrounding node on the i-th surrounding node, the i-th surrounding node and the i-1th node are adjacent nodes, Si is the similarity coefficient between the i-th surrounding node and the prototype node, Ii is the historical data support state coefficient between the i-th surrounding node and the prototype node, Bi is the business correlation coefficient between the i-th surrounding node and the prototype node, w1, w2, w3, u, αi are the evaluation weight parameter values ​​corresponding to the i-th surrounding node.

[0082] This scoring function combines factors from multiple dimensions, such as historical performance, similarity, data support status, and business relevance, so that the scoring performance value can accurately reflect the quality of the connection between the node prototype and each surrounding node. In this way, the model can adaptively optimize the connection relationship between the node prototype and the surrounding nodes to achieve more efficient data asset management and business operations.

[0083] Furthermore, in the above model, by means of the optimization layer, based on the score performance value, adjusting the connection relationship between the node prototype and at least part of the surrounding nodes in the graph isomorphic network can be implemented as follows:

[0084] Determine the interval to which the size relationship between P(i) and the preset threshold belongs; if P(i) is not less than the first preset threshold, and P(i) is less than the second preset threshold, then keep the connection relationship between the node prototype and the i-th surrounding node in the current state; if P(i) is greater than the second preset threshold, then reduce the strength of the connection relationship between the node prototype and the i-th surrounding node; if P(i) is less than the first preset threshold, then increase the strength of the connection relationship between the node prototype and the i-th surrounding node.

[0085] In the above model, the connection relationship between the node prototype and the surrounding nodes can be adjusted based on the score performance value through the optimization layer. Specifically, a preset threshold interval can be set, and according to the relationship between the score performance value and the threshold interval, it is decided whether to maintain the current connection state, increase the connection strength, or weaken the connection strength.

[0086] For example, suppose there is a data asset of a trading platform, the node prototype represents the product, and the surrounding nodes represent consumers and similar products. The score performance value reflects the intensity of each consumer's interest in the product and the market competitiveness of similar products. Set the first preset threshold to 0.7 and the second preset threshold to 0.9. When the score performance value of a product is greater than or equal to 0.9, it means that it has strong competitiveness in the current market, has a strong connection with consumers, and will maintain this connection; when the score performance value is between 0.7 and 0.9, the competitiveness of the product is average, and the current connection relationship will remain unchanged; and when the score performance value is less than 0.7, the competitiveness of the product is weak and does not have a market advantage. The connection relationship between the product and other similar products will be increased to enhance its competitiveness, while reducing the connection strength with current consumers to promote the repositioning of the product and market redevelopment.

[0087] In short, through such an adjustment process, it can be ensured that the connection relationship between the node prototypes and the surrounding nodes in the graph isomorphic network always remains in an efficient state to meet the actual needs and optimization goals of the business unit.

[0088] As an optional embodiment, in 103, the asset feature vector of each node in the target graph isomorphic network is updated through neighborhood aggregation processing. The neighborhood aggregation processing parameters are determined by the monitoring requirements of the data assets and the complexity between the multi-source business units. In 104, the data asset object is monitored through the updated target graph isomorphic network, and the real-time monitoring status of the data asset object is output.

[0089] It is worth noting that in the embodiment of the present application, the neighborhood aggregation processing parameters are determined by the monitoring requirements of the data assets and the complexity between the multi-source business units.

[0090] In an embodiment of the present application, the setting of neighborhood aggregation processing parameters is determined by the monitoring requirements of data assets and the complexity between multi-source business units. First, the monitoring requirements of data assets. Different data asset monitoring requirements may include real-time performance monitoring, anomaly detection, trend analysis, etc. These requirements determine the focus of neighborhood aggregation processing, such as whether more detailed node information, more frequent updates, or more accurate feature vectors are required. The type and characteristics of data assets (such as the frequency, update speed, importance, etc. of data) affect the setting of neighborhood aggregation processing parameters. For example, high-frequency data may require higher aggregation accuracy and update frequency. Monitoring requirements also involve the granularity of monitoring, which may be a macroscopic system level or a microscopic node level. Different granularities require different parameter configurations to achieve the best monitoring effect. Second, the complexity between multi-source business units. There may be complex dependencies and data interactions between different business units. For example, the data relationship between the sales system and the inventory system is close, which affects the fluency and accuracy of the overall business. The complex data relationship between multi-source business units needs to be effectively integrated and updated through neighborhood aggregation processing. For example, a change in the status of one business unit may have a ripple effect on other units, so these complex interactions need to be considered when processing. The complexity of the system refers to the complexity of the relationships between business units, including the path of data flow, the complexity of data conversion, etc. Complex systems may require more aggregation processing parameter adjustments to ensure accurate integration and update of data.

[0091] Here, the setting of neighborhood aggregation processing parameters is not fixed, but dynamically adjusted according to monitoring requirements and business complexity. This ensures that the effect of aggregation processing can meet actual monitoring requirements. According to the characteristics of data assets and the complexity of business units, adjusting neighborhood aggregation processing parameters can optimize the aggregation effect of data and improve the accuracy and real-time performance of the monitoring system.

[0092] In the embodiment of the present application, the setting of the neighborhood aggregation processing parameters takes into account the monitoring requirements of data assets and the complexity between multi-source business units. This setting method ensures the effective monitoring and management of data assets, and can dynamically adapt to different monitoring requirements and business environments, thereby providing accurate and efficient data analysis and monitoring support.

[0093] For example, suppose there is a large enterprise whose business includes sales, inventory management, and customer service. There are multiple business units within the enterprise, and the data assets of each unit are stored in different business systems. These business systems are connected through a graph isomorphic network to form a graph containing multiple nodes, each of which represents a data asset object. In this business scenario, the enterprise uses a graph isomorphic network to manage and monitor data assets from sales, inventory, and customer service systems. First, the data asset objects in these systems are mapped to nodes in the graph isomorphic network, where each node represents a data asset object, and the edges between nodes represent the business relationship between them. For neighborhood aggregation processing, the enterprise determines the parameter settings based on monitoring requirements and data complexity. For example, in order to monitor inventory level changes in real time, the enterprise sets higher aggregation processing parameters to ensure that inventory data can be quickly and accurately reflected in the graph isomorphic network. At the same time, the node aggregation processing between the sales system and the inventory system is adjusted to strengthen the monitoring of the relationship between the two. Relatively speaking, since the data of the customer service system has a lower relationship with inventory, the aggregation processing parameters for its nodes are set lower. Through neighborhood aggregation processing, the system will dynamically update the asset feature vectors of relevant nodes in the inventory system according to changes in sales orders, thereby accurately reflecting the real-time status of the inventory. The updated graph isomorphic network can monitor inventory levels and sales data in real time. When the inventory level is lower than the preset warning line, the system will output an alarm and prompt the relevant departments to take replenishment actions. In addition, the monitoring status is displayed in the form of a dashboard or report, including inventory levels, sales trends, and early warning information, helping companies to respond quickly to business needs and potential problems. This approach ensures accurate reflection and timely feedback of the status of data assets, significantly improving the company's monitoring efficiency and responsiveness.

[0094] In the embodiments of the present application, the structured representation of graph isomorphic networks and neighborhood aggregation processing technology are used to achieve effective integration, dynamic update and real-time monitoring of multi-source data assets, with the technical advantages of high efficiency, adaptability and accuracy, and can provide strong data monitoring support in complex business environments. This technical solution effectively solves the technical problem that the interfaces and protocols between various systems in related technologies are not unified, making data integration and sharing extremely complicated, and improves decision-making efficiency and response speed.

[0095] In another embodiment of the present application, a digital asset monitoring system is also provided. Figure 2 The digital asset monitoring system comprises the following units:

[0096] A collection unit is configured to obtain a data asset object to be processed; the data asset object comes from a multi-source business system, and the multi-source business system includes at least different business units of the target enterprise;

[0097] A construction unit is configured to map the data asset object to a target node corresponding to the graph isomorphic network according to the asset attribute and the business unit to which it belongs, so as to obtain a target graph isomorphic network;

[0098] An aggregation unit is configured to update the asset feature vector of each node in the target graph isomorphic network through neighborhood aggregation processing; wherein the neighborhood aggregation processing parameters are determined by the monitoring requirements of the data assets and the complexity between the multi-source business units;

[0099] The optimization unit is configured to monitor the data asset object through the updated target graph isomorphic network and output the real-time monitoring status of the data asset object.

[0100] Further optionally, the acquisition unit obtains the data asset object to be processed and is configured to:

[0101] Identifying data assets in the multi-source business system;

[0102] According to the asset type, perform asset vectorization processing corresponding to the data asset to obtain a data asset object corresponding to the data asset;

[0103] Among them, the asset types include at least one of financial assets, customer assets, inventory assets, route operation assets, equipment assets, operation assets, human resource scheduling assets, market dynamics monitoring assets, and compliance assets.

[0104] Further optionally, the acquisition unit performs asset vectorization processing corresponding to the data asset according to the asset type to obtain a data asset object corresponding to the data asset, and is configured as follows:

[0105] Identify the asset type corresponding to the data asset;

[0106] Determining, based on the asset type, at least one data indicator matching the data asset;

[0107] Based on the at least one data indicator, using a corresponding preset feature extraction method, extracting key feature information from the data asset to obtain an initial data asset object corresponding to the data asset;

[0108] The initial data asset object corresponding to the data asset is reconstructed to obtain the data asset object corresponding to the data asset.

[0109] Further optionally, the construction unit maps the data asset object to a target node corresponding to the graph isomorphic network according to the asset attribute and the business unit to which it belongs, and is configured as follows:

[0110] Identify the asset attributes of the data asset object and the business unit to which it belongs; wherein the business unit is determined based on the business department to which the data asset object is collected, or the business unit is determined based on the business function to which the data asset object is collected; the business department includes at least one of the business department, technical support department, post-production department, logistics department, passenger department, finance department, sales department, and operation department; the business function includes at least one of technical service, decision-making and scheduling, passenger service, marketing, supply chain management, and logistics operation;

[0111] Select the node prototype template corresponding to the data asset object according to the business unit to which it belongs;

[0112] According to the node prototype template, the asset attributes are constructed as asset attribute features in the node prototype to obtain the node prototype corresponding to the data asset object;

[0113] The node network development model is adopted to adaptively optimize the connection relationship between the node prototype and surrounding nodes, and the optimized node prototype is used as the target node.

[0114] Further optionally, after the construction unit selects the node prototype template corresponding to the data asset object according to the business unit to which it belongs, it is further configured to:

[0115] Obtaining the actual needs of the business unit to which the data asset object belongs;

[0116] Determine whether the selected node prototype template meets the asset attributes and the actual needs;

[0117] If not, the corresponding template optimization process is triggered to make the optimized node prototype template conform to the asset attributes and the actual needs; or, if conforming, the selected node prototype template is recorded as the judgment result.

[0118] Further optionally, the node network development model includes at least the following structures: an exploration layer, a scoring layer, and an optimization layer;

[0119] The construction unit adopts a node network development model to adaptively optimize the connection relationship between the node prototype and surrounding nodes, and is configured as follows:

[0120] Through the exploration layer, all surrounding nodes connected to the node prototype are traversed to obtain preliminary connection relationship features between the node prototype and each surrounding node, as well as corresponding potential connection patterns;

[0121] Through the scoring layer, based on the preliminary connection relationship characteristics and potential connection patterns with each surrounding node, the scoring performance value between each surrounding node is predicted; the scoring performance value is determined by at least one of the similarity between nodes, interaction frequency, business relevance, business interaction stability, and historical data support status;

[0122] Through the optimization layer, based on the score performance value, the connection relationship between the node prototype and at least part of the surrounding nodes in the graph isomorphic network is adjusted to complete the connection relationship between the node prototype and the surrounding nodes.

[0123] Further optionally, the construction unit predicts the score performance value between each surrounding node based on the preliminary connection relationship characteristics and potential connection mode with each surrounding node through the scoring layer, and is configured as follows:

[0124] Setting a business unit scoring function corresponding to the node prototype and an optimization target corresponding to the asset attribute; the optimization target at least includes: interaction evaluation attribute, business evaluation attribute, and resource utilization;

[0125] According to the business unit scoring function and the optimization goal, the preliminary connection relationship characteristics and potential connection patterns between the node prototype and each surrounding node are adaptively evaluated to obtain the scoring performance value corresponding to each surrounding node; wherein the business unit scoring function is expressed as: Among them, P(i) represents the score performance value corresponding to the i-th surrounding node, P i-1 Indicates the historical score performance value corresponding to the i-1th surrounding node, represents the influence weight of the i-1th surrounding node on the i-th surrounding node, the i-th surrounding node and the i-1th node are adjacent nodes, Si is the similarity coefficient between the i-th surrounding node and the prototype node, Ii is the historical data support state coefficient between the i-th surrounding node and the prototype node, Bi is the business correlation coefficient between the i-th surrounding node and the prototype node, w1, w2, w3, u, αi are the evaluation weight parameter values ​​corresponding to the i-th surrounding node.

[0126] The construction unit, through the optimization layer, adjusts the connection relationship between the node prototype and at least part of the surrounding nodes in the graph isomorphic network based on the score performance value, and is configured to:

[0127] Determine the interval to which the magnitude relationship between P(i) and a preset threshold belongs;

[0128] If P(i) is not less than a first preset threshold, and P(i) is less than a second preset threshold, then the connection relationship between the node prototype and the i-th surrounding node is maintained in the current state;

[0129] If P(i) is greater than a second preset threshold, reducing the strength of the connection relationship between the node prototype and the i-th surrounding node;

[0130] If P(i) is less than a first preset threshold, the connection strength between the node prototype and the i-th surrounding node is increased.

[0131] The system can implement various steps in the above method embodiment, which will not be expanded here.

[0132] In the embodiments of this application, the structured representation of graph isomorphic networks and neighborhood aggregation processing technology are used to achieve effective integration, dynamic update and real-time monitoring of multi-source data assets, with the technical advantages of high efficiency, adaptability and accuracy, and can provide strong data monitoring support in complex business environments. It effectively solves the technical problem that the interfaces and protocols between various systems in related technologies are not unified, making data integration and sharing extremely complicated, and improves decision-making efficiency and response speed.

[0133] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 5102 and a computer program 511 stored in the memory 510 and executable on the processor 5102. When the processor 5102 executes the computer program 511, the following steps are implemented: obtaining a data asset object to be processed; the data asset object comes from a multi-source business system, and the multi-source business system at least includes different business units of a target enterprise; according to asset attributes and business units, the data asset object is mapped to a target node corresponding to a graph isomorphic network to obtain a target graph isomorphic network; the asset feature vector of each node in the target graph isomorphic network is updated through neighborhood aggregation processing; wherein the neighborhood aggregation processing parameters are determined by the monitoring requirements of the data assets and the complexity between the multi-source business units; the data asset object is monitored through the updated target graph isomorphic network, and the real-time monitoring status of the data asset object is output.

[0134] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4As shown, this embodiment provides a computer-readable storage medium 600, on which a computer program 611 is stored, and when the computer program 611 is executed by a processor, the following steps are implemented: obtaining a data asset object to be processed; the data asset object comes from a multi-source business system, and the multi-source business system at least includes different business units of the target enterprise; according to the asset attributes and the business units to which it belongs, mapping the data asset object to the target node corresponding to the graph isomorphic network to obtain the target graph isomorphic network; updating the asset feature vector of each node in the target graph isomorphic network through neighborhood aggregation processing; wherein the neighborhood aggregation processing parameters are determined by the monitoring requirements of the data assets and the complexity between the multi-source business units; monitoring the data asset object through the updated target graph isomorphic network, and outputting the real-time monitoring status of the data asset object.

[0135] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0136] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented 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.

[0137] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0138] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0139] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0140] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0141] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A digital asset monitoring method, characterized in that: The method comprises: Acquire a data asset object to be processed; the data asset object comes from a multi-source business system, and the multi-source business system includes at least different business units of the target enterprise; According to the asset attributes and the business units to which they belong, the data asset objects are mapped to the target nodes corresponding to the graph isomorphic network to obtain the target graph isomorphic network; Updating the asset feature vector of each node in the target graph isomorphic network through neighborhood aggregation processing; wherein the neighborhood aggregation processing parameters are determined by the monitoring requirements of the data assets and the complexity between the multi-source business units; The data asset object is monitored through the updated target graph isomorphic network, and the real-time monitoring status of the data asset object is output.

2. The digital asset monitoring method according to claim 1, characterized in that: The step of obtaining the data asset object to be processed includes: Identifying data assets in the multi-source business system; According to the asset type, perform asset vectorization processing corresponding to the data asset to obtain a data asset object corresponding to the data asset; Among them, the asset types include at least one of financial assets, customer assets, inventory assets, route operation assets, equipment assets, operation assets, human resource scheduling assets, market dynamics monitoring assets, and compliance assets.

3. The digital asset monitoring method according to claim 2, characterized in that: The performing of asset vectorization processing corresponding to the data asset according to the asset type to obtain a data asset object corresponding to the data asset includes: Identify the asset type corresponding to the data asset; Determining, based on the asset type, at least one data indicator matching the data asset; Based on the at least one data indicator, using a corresponding preset feature extraction method, extracting key feature information from the data asset to obtain an initial data asset object corresponding to the data asset; The initial data asset object corresponding to the data asset is reconstructed to obtain the data asset object corresponding to the data asset.

4. The digital asset monitoring method according to claim 1, characterized in that: Mapping the data asset object to a target node corresponding to the graph isomorphic network according to the asset attribute and the business unit to which it belongs includes: Identify the asset attributes of the data asset object and the business unit to which it belongs; wherein the business unit is determined based on the business department to which the data asset object is collected, or the business unit is determined based on the business function to which the data asset object is collected; the business department includes at least one of the business department, technical support department, post-production department, logistics department, passenger department, finance department, sales department, and operation department; the business function includes at least one of technical service, decision-making and scheduling, passenger service, marketing, supply chain management, and logistics operation; Select the node prototype template corresponding to the data asset object according to the business unit to which it belongs; According to the node prototype template, the asset attributes are constructed as asset attribute features in the node prototype to obtain the node prototype corresponding to the data asset object; The node network development model is adopted to adaptively optimize the connection relationship between the node prototype and surrounding nodes, and the optimized node prototype is used as the target node.

5. The digital asset monitoring method according to claim 4, characterized in that: After selecting the node prototype template corresponding to the data asset object according to the business unit to which it belongs, the method further includes: Obtaining the actual needs of the business unit to which the data asset object belongs; Determine whether the selected node prototype template meets the asset attributes and the actual needs; If not, the corresponding template optimization process is triggered to make the optimized node prototype template conform to the asset attributes and the actual needs; or, if conforming, the selected node prototype template is recorded as the judgment result.

6. The digital asset monitoring method according to claim 4, characterized in that: The node network development model at least includes the following structures: exploration layer, scoring layer, and optimization layer; The node network development model is adopted to adaptively optimize the connection relationship between the node prototype and surrounding nodes, including: Through the exploration layer, all surrounding nodes connected to the node prototype are traversed to obtain preliminary connection relationship features between the node prototype and each surrounding node, as well as corresponding potential connection patterns; Through the scoring layer, based on the preliminary connection relationship characteristics and potential connection patterns with each surrounding node, the scoring performance value between each surrounding node is predicted; the scoring performance value is determined by at least one of the similarity between nodes, interaction frequency, business relevance, business interaction stability, and historical data support status; Through the optimization layer, based on the score performance value, the connection relationship between the node prototype and at least part of the surrounding nodes in the graph isomorphic network is adjusted to complete the connection relationship between the node prototype and the surrounding nodes.

7. The digital asset monitoring method according to claim 6, characterized in that: The scoring layer predicts the scoring performance value between each surrounding node based on the preliminary connection relationship characteristics and potential connection patterns with each surrounding node, including: Setting a business unit scoring function corresponding to the node prototype and an optimization target corresponding to the asset attribute; the optimization target at least includes: interaction evaluation attribute, business evaluation attribute, and resource utilization; According to the business unit scoring function and the optimization goal, the preliminary connection relationship characteristics and potential connection patterns between the node prototype and each surrounding node are adaptively evaluated to obtain the scoring performance value corresponding to each surrounding node; wherein the business unit scoring function is expressed as: Among them, P(i) represents the score performance value corresponding to the i-th surrounding node, P i-1 Indicates the historical score performance value corresponding to the i-1th surrounding node, represents the influence weight of the i-1th surrounding node on the i-th surrounding node, the i-th surrounding node and the i-1th node are adjacent nodes, Si is the similarity coefficient between the i-th surrounding node and the prototype node, Ii is the historical data support state coefficient between the i-th surrounding node and the prototype node, Bi is the business correlation coefficient between the i-th surrounding node and the prototype node, w1, w2, w3, u, αi are the evaluation weight parameter values ​​corresponding to the i-th surrounding node; The step of adjusting the connection relationship between the node prototype and at least part of the surrounding nodes in the graph isomorphic network based on the score performance value through the optimization layer includes: Determine the interval to which the magnitude relationship between P(i) and a preset threshold belongs; If P(i) is not less than a first preset threshold, and P(i) is less than a second preset threshold, then the connection relationship between the node prototype and the i-th surrounding node is maintained in the current state; If P(i) is greater than a second preset threshold, reducing the strength of the connection relationship between the node prototype and the i-th surrounding node; If P(i) is less than a first preset threshold, the connection strength between the node prototype and the i-th surrounding node is increased.

8. A digital asset monitoring system, characterized in that: The system comprises the following units, wherein: A collection unit is configured to obtain a data asset object to be processed; the data asset object comes from a multi-source business system, and the multi-source business system includes at least different business units of the target enterprise; A construction unit is configured to map the data asset object to a target node corresponding to the graph isomorphic network according to the asset attribute and the business unit to which it belongs, so as to obtain a target graph isomorphic network; An aggregation unit is configured to update the asset feature vector of each node in the target graph isomorphic network through neighborhood aggregation processing; wherein the neighborhood aggregation processing parameters are determined by the monitoring requirements of the data assets and the complexity between the multi-source business units; The optimization unit is configured to monitor the data asset object through the updated target graph isomorphic network and output the real-time monitoring status of the data asset object.

9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the digital asset monitoring method described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the digital asset monitoring method according to any one of claims 1 to 7 is implemented.

Images