A data asset analysis method and system

Abstract

This application discloses a data asset analysis method and system. Based on this data asset analysis method, in response to user operations, target data is collected; the target data is preprocessed and packaged to obtain a data asset package; the data asset package is input into a pre-built data risk control model to obtain a risk control report corresponding to the data asset package; a risk reference price for the data asset package is obtained according to pre-stored risk pricing rules; and a target financial product is obtained based on the risk control report and risk reference price of the data asset package. By transforming data into data assets, classifying and tagging these assets, and digitizing user assets, and by using a data risk control model to differentiate the pricing of data assets based on risk identification, the utilization rate of data assets is improved, thereby providing users with more comprehensive and accurate risk information about their data assets.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and more specifically, to a data asset analysis method and system. Background Technology

[0002] Generally, the supply chain of a specific product, from raw material procurement to the production of intermediate and final products, and finally to the delivery of the product to consumers through a sales network, connects suppliers, manufacturers, distributors, retailers, and end users into a unified whole. Within this supply chain, the party with stronger competitiveness, larger scale, and greater bargaining power is referred to as the core enterprise. Currently, an increasing number of core enterprises, holding dominant positions in the industrial chain, are actively engaging in industrial chain finance. However, the following problems generally exist: failure to process enterprise data into data assets and implement hierarchical and categorized management; lack of risk control capabilities for data assets; inability to effectively identify the potential risk distribution of existing assets; and due to a lack of risk identification capabilities, often applying uniform pricing to various assets—that is, adopting a uniform pricing strategy for different customers, different asset targets, and different stages of financing needs. It is evident that existing technological solutions suffer from low data asset utilization rates and insufficient access to risk information for users, resulting in low risk control capabilities for users regarding data assets. Summary of the Invention

[0003] The purpose of this application is to provide a data asset analysis method and system. Based on the execution of this data asset analysis method, data assets are digitized, the utilization rate of data assets is improved, and users are provided with more comprehensive and accurate risk information of data assets.

[0004] To achieve the above objectives, in a first aspect, this application provides a data asset analysis method, the method comprising:

[0005] Responding to user actions, collect target data;

[0006] The target data is preprocessed to obtain preprocessed data;

[0007] The preprocessed data is then packaged to obtain a data asset package;

[0008] The data asset package is input into a pre-built data risk control model to obtain a risk control report corresponding to the data asset package;

[0009] Based on the pre-stored risk pricing rules, obtain the risk reference price of the data asset package;

[0010] Based on the risk control report of the data asset package and the risk reference pricing, a risk assessment report is generated and returned.

[0011] Optionally, the preprocessing of the target data to obtain preprocessed data includes:

[0012] The target data is extracted, cleaned, and transformed using a preset data processing tool to obtain the preprocessed data.

[0013] Optionally, after preprocessing the target data to obtain preprocessed data, the method further includes:

[0014] The preprocessed data is classified and labeled according to preset rules to obtain multiple preprocessed data with labels.

[0015] The process of encapsulating the preprocessed data to obtain a data asset package includes:

[0016] The preprocessed data carrying the tags are encapsulated to form data assets corresponding to the tags.

[0017] The data assets corresponding to the multiple tags are packaged together to obtain the data asset package.

[0018] Optionally, the risk pricing rules are generated and stored based on the financial institution's risk tolerance, its expected future returns, and its historical financial product pricing rules.

[0019] Optionally, the method further includes:

[0020] Publish the risk reference pricing of the data asset package, and use the price discovery mechanism to obtain the risk transaction pricing of the data asset package;

[0021] The risk pricing rule is adjusted based on the risk transaction pricing of the data asset package to obtain the adjusted risk pricing rule.

[0022] Optionally, after generating and returning a risk assessment report based on the risk control report of the data asset package and the risk reference pricing, the method further includes:

[0023] Based on the risk control report of the data asset package and the risk reference pricing, a set of financial products is obtained and returned;

[0024] In response to the selection operation of the target financial product, the financial institution corresponding to the target financial product is determined; wherein the target financial product is one of the multiple financial products included in the financial product set.

[0025] The data asset package and the risk assessment report are sent to the financial institution corresponding to the target financial product.

[0026] Optionally, the method further includes:

[0027] Establish blockchain consensus with multiple nodes included in the blockchain through a consensus algorithm;

[0028] After collecting the target data, the method further includes:

[0029] The target data is verified using the blockchain to obtain a verification result. If the verification result of the target data meets the preset requirements, the target data is preprocessed to obtain preprocessed data.

[0030] Secondly, this application also provides a data asset analysis system, the system comprising:

[0031] The data acquisition unit is used to collect target data in response to user operations;

[0032] A data preprocessing unit is used to preprocess the target data to obtain preprocessed data;

[0033] The encapsulation unit is used to encapsulate the preprocessed data to obtain a data asset package;

[0034] The data asset analysis unit is used to input the data asset package into a pre-built data risk control model to obtain a risk control report corresponding to the data asset package; and to obtain a risk reference price for the data asset package based on pre-stored risk pricing rules.

[0035] The integration unit is used to generate and return a risk assessment report based on the risk control report of the data asset package and the risk reference pricing.

[0036] Optionally, the system further includes:

[0037] A consensus unit is used to establish blockchain consensus with multiple nodes included in the blockchain through a consensus algorithm; and to verify the target data using the blockchain to obtain the verification result of the target data.

[0038] The data preprocessing unit is used to perform preprocessing on the target data when the verification result of the target data obtained by the consensus unit meets the preset requirements, so as to obtain preprocessed data.

[0039] The purpose of this application is to provide a data asset analysis method and system. Based on this data asset analysis method, in response to user operations, target data is collected; the target data is preprocessed to obtain preprocessed data; the preprocessed data is packaged to obtain a data asset package; the data asset package is input into a pre-built data risk control model to obtain a risk control report corresponding to the data asset package; a risk reference price for the data asset package is obtained according to pre-stored risk pricing rules; and the target financial product is obtained based on the risk control report and risk reference price of the data asset package. This application transforms data into data assets, classifies and labels these data assets, digitizes user assets, and uses a data risk control model to set risk pricing rules for differentiated pricing of these data assets based on risk identification, thereby improving the utilization rate of data assets and providing users with more comprehensive and accurate risk information about their data assets. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0041] Figure 1 A flowchart illustrating a data asset analysis method provided in this application embodiment;

[0042] Figure 2 This is a schematic diagram of a data asset analysis system provided in an embodiment of this application. Detailed Implementation

[0043] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0044] This invention provides a data asset analysis method and system that transforms data into data assets, classifies and tags these assets for management, digitizes user assets, and uses a data risk control model to differentiate the pricing of these data assets based on risk identification and risk pricing rules. This improves the utilization rate of data assets and provides users with more comprehensive and accurate risk information about their data assets. This addresses the problems of low data asset utilization and insufficient access to risk information for users in existing technologies, which leads to low risk control capabilities for users of data assets.

[0045] First, a detailed introduction to some of the technical terms mentioned in this application will be provided:

[0046] Core Enterprise: Generally speaking, the supply chain of a specific product connects suppliers, manufacturers, distributors, retailers, and end users into a whole, from raw material procurement to the production of intermediate and final products, and finally to the delivery of the product to consumers through a sales network. In this supply chain, the party with stronger competitiveness, larger scale, and certain bargaining power is the core enterprise.

[0047] Blockchain: A term in the field of information technology. Essentially, it is a shared database where data or information is stored, possessing characteristics such as "unforgeable," "fully traceable," "transparent," and "collectively maintained." Based on these characteristics, blockchain technology lays a solid foundation of "trust," creates a reliable "cooperation" mechanism, and has broad application prospects.

[0048] Big Data: also known as massive data, refers to data of such a large scale that it is impossible to capture, manage, process, and organize it into information that helps businesses make decisions within a reasonable timeframe using mainstream software tools.

[0049] Price discovery mechanism: Two-way selection, centralized bidding principle. Suppliers can choose different financial institutions and products. Financial institutions, within their risk tolerance range, compete to acquire the asset, ultimately reaching a mutually satisfactory price result.

[0050] Risk pricing: Risk pricing refers to the determination of the price of risky assets, which reflects a functional relationship between the future returns and risks of capital assets.

[0051] The following is a detailed description of a data asset analysis method in this application:

[0052] Figure 1 A flowchart illustrating a data asset analysis method provided in an embodiment of this application. Figure 1 As shown, an embodiment of this application includes a data asset analysis method comprising:

[0053] S101: In response to user operation, collect target data.

[0054] Specifically, in this embodiment of the application, in response to the asset information selected by the user for financial transactions (such as financing), the system connects with data from the core enterprise's internal ERP system, materials system, and financial control system to obtain supply chain data between the core enterprise and its upstream and downstream customers. Furthermore, it connects with third-party institutions to obtain relevant judicial, tax, and credit data, such as judicial institutions, tax authorities, and credit reporting agencies.

[0055] It should be noted that the user can be a core enterprise, and the target data selected by the user can be one or more of the following: order type data, virtual type data (such as stocks, funds, bonds), equipment, buildings, etc. This application does not limit the asset information selected by the user as target data, and all of them are within the protection scope of this application.

[0056] Before collecting target data, this application embodiment can establish a group consensus through blockchain. Based on blockchain technology, a mutually recognized, trustworthy, tamper-proof, and traceable data consensus can be established among multiple parties. Moreover, blockchain technology can be used to reach a consensus with data requesters in various application scenarios in advance, confirming data security, data ownership, and data format, building a mutually trustworthy and secure environment, and improving the credibility of the data by combining the application of blockchain technology.

[0057] Specifically, consensus is established with multiple nodes in the blockchain through a consensus algorithm;

[0058] After collecting the target data, the method further includes: verifying the target data using the blockchain to obtain a verification result of the target data; if the verification result of the target data meets preset requirements, then performing preprocessing on the target data to obtain preprocessed data.

[0059] S102: Preprocess the target data to obtain preprocessed data.

[0060] Specifically, the preprocessing of the target data to obtain preprocessed data includes: using a preset data processing tool to extract data from the target data, clean and transform the data to obtain the preprocessed data.

[0061] It should be noted that the aforementioned preset data processing tool can be data warehouse technology (Extract-Transform-Load, ETL). ETL technology is a process of extracting, cleaning, and transforming data from business systems and then loading it into a data warehouse. The purpose is to integrate scattered, disorganized, and inconsistent data within an enterprise, providing analytical support for enterprise decision-making. ETL design consists of three parts: data extraction, data cleaning and transformation, and data loading.

[0062] Specifically, the aforementioned cleaning and transformation of target data includes handling missing values, handling deviations, data normalization, and data transformation. When the target data is unstructured, such as contract text information, it needs to be identified using text recognition technology within ETL technology to complete the data transformation and store it as structured data.

[0063] S103: Encapsulate the preprocessed data to obtain a data asset package.

[0064] It should be noted that this data asset package includes data assets of various asset types. These can include virtual assets such as funds, stocks, and bonds, as well as physical assets such as houses, buildings, and machinery. A user can generate multiple data asset packages for different financial transactions.

[0065] It should be noted that in this embodiment of the application, the preprocessed data can also be tagged and classified.

[0066] Specifically, after preprocessing the target data to obtain preprocessed data, the method may further include: classifying the preprocessed data according to preset rules and adding tags to obtain multiple preprocessed data carrying tags; then, encapsulating the preprocessed data to obtain a data asset package includes: encapsulating the multiple preprocessed data carrying tags respectively to form multiple data assets corresponding to the tags; and packaging the multiple data assets corresponding to the tags to obtain the data asset package.

[0067] It should be noted that encapsulating the multiple preprocessed data carrying tags to form multiple data assets corresponding to the tags can be achieved by arranging and combining the preprocessed data according to certain dimensions and then encapsulating them to form data assets.

[0068] Taking order assets as an example, after obtaining preprocessed data, the preprocessed data is filtered and tagged based on order transactions. Then, during encapsulation, the data is encapsulated according to the tags, packaging the master data of both parties to the order, the order header data, and the order line data. The encapsulated data assets are then tagged with order tags to form order assets.

[0069] S104: Input the data asset package into the pre-built data risk control model to obtain the risk control report corresponding to the data asset package.

[0070] It should be noted that the data asset package also includes basic user information, which may include business registration data, judicial registration data, company age, and other basic information. There are no restrictions on the user's basic information here.

[0071] Specifically, the data risk control model in this embodiment of the application is built based on machine learning technology: it is trained based on the user's multi-dimensional feature data and multi-level indicator evaluation data to obtain the data risk control model. Moreover, as the amount of data increases, the model is continuously optimized and adjusted to update the data risk control model. This data risk control model is used to control the risk of loan default.

[0072] The user's multi-dimensional characteristic data includes basic user data, which may include judicial registration information, business registration information, company age, transaction cooperation time, and default information. There are no restrictions on the user's basic information here. The multi-level indicator evaluation data for users consists of evaluation scores. Specifically, this may include the company's operating years (e.g., 0 points for new companies, 3 points for less than 2 years, 5 points for 2-5 years, 7 points for 5-7 years, and 10 points for more than 10 years), the company's annual order amount (e.g., 3 points for annual order amounts of 1 million-1.5 million, 4 points for 1.5 million-2 million), and the company's default information score, which may include business litigation, judicial penalties, and tax information. When a company defaults, points are deducted according to specified deduction rules. These scoring and deduction rules are pre-defined and generated in the system.

[0073] S105: Obtain the risk reference price of the data asset package according to the pre-stored risk pricing rules.

[0074] Specifically, risk pricing rules are generated and stored based on the financial institution's risk tolerance, its expected future returns, and its historical financial product pricing rules.

[0075] It should be noted that risk pricing rules can be stored in the system's local storage or on a server.

[0076] Specifically, the method further includes: publishing the risk reference pricing of the data asset package; using a price discovery mechanism to obtain the risk transaction pricing of the data asset package; and adjusting the risk pricing rules according to the risk transaction pricing of the data asset package to obtain the adjusted risk pricing rules.

[0077] To improve the accuracy of risk pricing in this embodiment, a price discovery mechanism can be utilized to obtain a more suitable and accurate risk price for the data asset package. By innovating a public bidding model, both funding demanders and providers are included in the bidding system. Through multiple rounds of bidding, a risk-return equilibrium price is ultimately obtained. Furthermore, the risk pricing rules can be continuously revised in real time, improving the accuracy of the risk reference pricing for the data asset package.

[0078] S106: Generate and return a risk assessment report based on the risk control report of the data asset package and the risk reference pricing.

[0079] In this embodiment, industry data is precisely matched with financial products, and financial needs are precisely matched with financial institutions, thus realizing the assetization of industry chain data. Specifically, based on the generated risk assessment report, matching financial products can be recommended to users, and the system can also connect with financial institutions to provide them with risk indicator information, thereby improving the efficiency and quality of transaction completion.

[0080] Specifically, after generating and returning a risk assessment report based on the risk control report of the data asset package and the risk reference pricing, the method further includes: obtaining and returning a set of financial products based on the risk control report of the data asset package and the risk reference pricing; determining the financial institution corresponding to the target financial product in response to a selection operation of the target financial product; wherein the target financial product is one of the multiple financial products included in the set of financial products; and sending the data asset package and the risk assessment report to the financial institution corresponding to the target financial product.

[0081] It should be noted that this application can also extract data such as users' historical operations, behavioral preferences, risk tolerance, and price tolerance to build an AI-based automatic supply and demand precision matching model based on big data analysis. The risk control report of the data asset package and the aforementioned risk reference pricing are input into the AI-based automatic supply and demand precision matching model to accurately recommend matching financial products to users.

[0082] It should be noted that this risk assessment report integrates the risk control report and risk reference pricing of the data asset package, and the risk assessment report is sent to financial institutions in the form of a document along with the data asset package.

[0083] This application embodiment can also realize status control during the financing process. When users conduct financial business operations at financial institutions, they will send back the business status to update the asset status, such as "financed, not financed, financing in progress".

[0084] The data asset analysis method in this embodiment of the application, in response to user operations, collects target data; preprocesses the target data to obtain preprocessed data; encapsulates the preprocessed data to obtain a data asset package; inputs the data asset package into a pre-built data risk control model to obtain a risk control report corresponding to the data asset package; obtains a risk reference price for the data asset package based on pre-stored risk pricing rules; and obtains the target financial product based on the risk control report and risk reference price of the data asset package. This application transforms data into data assets, classifies and tags these data assets, digitizes user assets, and uses a data risk control model to set risk pricing rules for differentiated pricing of these data assets based on risk identification, thereby improving the utilization rate of data assets and providing users with more comprehensive and accurate risk information about their data assets.

[0085] The following describes a data asset analysis system according to an embodiment of this application. Please refer to [link / reference]. Figure 2 Based on the data asset analysis method in the above embodiments, this application implements the data asset analysis method through a data asset analysis system. The data asset analysis system in this application includes:

[0086] The acquisition unit 10 is used to acquire target data in response to user operations;

[0087] Data preprocessing unit 20 is used to preprocess the target data to obtain preprocessed data;

[0088] Encapsulation unit 30 is used to encapsulate the preprocessed data to obtain a data asset package;

[0089] The data asset analysis unit 40 is used to input the data asset package into a pre-built data risk control model to obtain a risk control report corresponding to the data asset package; and to obtain a risk reference price for the data asset package according to a pre-stored risk pricing rule.

[0090] Integration unit 50 is used to generate and return a risk assessment report based on the risk control report of the data asset package and the risk reference pricing.

[0091] The data preprocessing unit 20 in the data asset analysis system is specifically used to: extract data from the target data and clean and transform the data using a preset data processing tool to obtain the preprocessed data.

[0092] The data asset analysis system also includes:

[0093] A classification unit is used to classify the preprocessed data according to preset rules and add labels to obtain multiple preprocessed data with labels.

[0094] The encapsulation unit 30 is used to: encapsulate the multiple preprocessed data carrying tags respectively to form multiple data assets corresponding to the tags; and package the multiple data assets corresponding to the tags to obtain the data asset package.

[0095] In the data asset analysis system, risk pricing rules are generated and stored based on the financial institution's risk tolerance, its expected future returns, and its historical financial product pricing rules.

[0096] In the data asset analysis system:

[0097] The data asset analysis unit 40 is also used to publish the risk reference pricing of the data asset package and to obtain the risk transaction pricing of the data asset package using a price discovery mechanism;

[0098] The update unit is used to adjust the risk pricing rule according to the risk transaction pricing of the data asset package to obtain the adjusted risk pricing rule.

[0099] The data asset analysis system also includes:

[0100] The matching unit is used to obtain and return a set of financial products based on the risk control report of the data asset package and the risk reference pricing.

[0101] A determining unit is configured to determine the financial institution corresponding to the target financial product in response to a selection operation of the target financial product; wherein the target financial product is one of the multiple financial products included in the financial product set.

[0102] The sending unit is used to send the data asset package and the risk assessment report to the financial institution corresponding to the target financial product.

[0103] The data asset analysis system also includes:

[0104] A consensus unit is used to establish blockchain consensus with multiple nodes included in the blockchain through a consensus algorithm; and to verify the target data using the blockchain to obtain the verification result of the target data.

[0105] The data preprocessing unit 20 is used to perform preprocessing on the target data when the verification result of the target data obtained by the consensus unit meets the preset requirements, so as to obtain preprocessed data.

[0106] The data asset analysis system in this embodiment of the application transforms data into data assets, classifies and labels these data assets for management, digitizes user assets, and uses a data risk control model to set risk pricing rules for the data assets based on risk identification, thereby improving the utilization rate of data assets and providing users with more comprehensive and accurate risk information about their data assets.

[0107] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data asset analysis method, characterized in that, The method includes: Responding to user actions, collect target data; The target data is preprocessed to obtain preprocessed data; wherein, the preprocessing of the target data to obtain preprocessed data includes: using a preset data processing tool to extract data, clean and transform data from the target data to obtain the preprocessed data; The preprocessed data is then packaged to obtain a data asset package; The data asset package is input into a pre-built data risk control model to obtain a risk control report corresponding to the data asset package. Based on the pre-stored risk pricing rules, obtain the risk reference price of the data asset package; Based on the risk control report of the data asset package and the risk reference pricing, a risk assessment report is generated and returned.

2. The method according to claim 1, characterized in that, After preprocessing the target data to obtain preprocessed data, the method further includes: The preprocessed data is classified and labeled according to preset rules to obtain multiple preprocessed data with labels. The process of encapsulating the preprocessed data to obtain a data asset package includes: The preprocessed data carrying the tags are encapsulated to form data assets corresponding to the tags. The data assets corresponding to the multiple tags are packaged together to obtain the data asset package.

3. The method according to claim 1, characterized in that, The risk pricing rules are generated and stored based on the financial institution's risk tolerance, its expected future returns, and its historical financial product pricing rules.

4. The method according to claim 3, characterized in that, The method further includes: Publish the risk reference pricing of the data asset package, and use the price discovery mechanism to obtain the risk transaction pricing of the data asset package; The risk pricing rule is adjusted based on the risk transaction pricing of the data asset package to obtain the adjusted risk pricing rule.

5. The method according to claim 1, characterized in that, After generating and returning a risk assessment report based on the risk control report of the data asset package and the risk reference pricing, the method further includes: Based on the risk control report of the data asset package and the risk reference pricing, a set of financial products is obtained and returned; In response to the selection operation of the target financial product, the financial institution corresponding to the target financial product is determined; wherein the target financial product is one of the multiple financial products included in the financial product set; The data asset package and the risk assessment report are sent to the financial institution corresponding to the target financial product.

6. The method according to claim 1, characterized in that, The method further includes: Establish blockchain consensus with multiple nodes included in the blockchain through a consensus algorithm; After collecting the target data, the method further includes: The target data is verified using the blockchain to obtain a verification result. If the verification result of the target data meets the preset requirements, the target data is preprocessed to obtain preprocessed data.

7. A data asset analysis system, characterized in that, The system includes: The data acquisition unit is used to collect target data in response to user operations; A data preprocessing unit is used to preprocess the target data to obtain preprocessed data; wherein, the preprocessing of the target data to obtain preprocessed data includes: using a preset data processing tool to extract data from the target data, clean and transform the data to obtain the preprocessed data; The encapsulation unit is used to encapsulate the preprocessed data to obtain a data asset package; The data asset analysis unit is used to input the data asset package into a pre-built data risk control model to obtain a risk control report corresponding to the data asset package; and to obtain a risk reference price for the data asset package based on pre-stored risk pricing rules. The integration unit is used to generate and return a risk assessment report based on the risk control report of the data asset package and the risk reference pricing.

8. The system according to claim 7, characterized in that, The system also includes: A consensus unit is used to establish blockchain consensus with multiple nodes included in the blockchain through a consensus algorithm; and to verify the target data using the blockchain to obtain the verification result of the target data. The data preprocessing unit is used to perform preprocessing on the target data to obtain preprocessed data when the verification result of the target data obtained by the consensus unit meets the preset requirements.

Images