Data asset value evaluation method and system
By generating secondary asset description information for data assets and identifying target data elements, combined with requester information, the lack of data asset valuation is resolved, and a comprehensive valuation of data assets is achieved.
Patent Information
- Application Number
- CN202411436448.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-15
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The lack of effective data asset valuation schemes in existing technologies makes it difficult to provide assistance in managing data assets.
By acquiring the data assets and their descriptions uploaded by the requester, a more objective second asset description is generated, multiple target data elements are identified, and asset values in different dimensions are determined based on these elements and the requester's information, ultimately determining the target asset value of the data assets.
It enables a comprehensive valuation of data assets, utilizing data assets, descriptive information, and requester information to provide the target asset value of the data assets.
Smart Images

Figure CN118941397A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a method and system for evaluating the value of data assets. Background Art
[0002] As a strategic and basic resource today, data is an important driving force for technological innovation, demand mining, and efficiency improvement in the digital economy. The value assessment of data assets is a key link in data asset management and the value baseline for data assetization.
[0003] However, related technologies lack solutions for evaluating the value of data assets, making it difficult to provide effective assistance for managing data assets. Summary of the invention
[0004] The present application embodiment provides a data asset value assessment method and system, which can assess the value of data assets. The technical solution is as follows: In one aspect, a method for evaluating the value of data assets is provided, the method comprising: Acquire the data assets uploaded by the evaluation requester and first asset description information describing the data assets by the evaluation requester, where the asset description information is used to reflect the asset status of the data assets; Based on the data asset and the first asset description information, generate second asset description information of the data asset; Identifying target data elements of the data asset to obtain multiple target data elements of the data asset, wherein the multiple target data elements are data elements in the data asset whose importance is higher than a preset importance; Determine a first asset value and a second asset value of the data asset based on the second asset description information of the data asset, the multiple target data elements, and the requester information of the evaluation requester, wherein the first asset value and the second asset value are used to represent asset values of different dimensions; Based on the first asset value of the data asset and the second asset value of the data asset, a target asset value of the data asset is determined.
[0005] In a possible implementation manner, generating second asset description information of the data asset based on the data asset and the first asset description information includes: Classifying the data assets to obtain the target data asset type to which the data assets belong; Based on the target data asset type, determining a target description information generation model corresponding to the target data asset type from a plurality of candidate description information generation models, the target description information generation model being used to generate second asset description information; The data asset and the first asset description information are input into the target description information generation model, and the data asset and the first asset description information are processed by the target description information generation model to obtain second asset description information of the data asset.
[0006] In a possible implementation manner, the processing the data asset and the first asset description information by using the target description information generation model to obtain the second asset description information of the data asset includes: Extracting key information of the data asset through the target description information generation model to obtain key asset information of the data asset; By using the target description information generation model, the first asset description information and the asset key information are integrated to obtain reference asset description information of the data asset; The reference asset description information is summarized and extracted through the target description information generation model to obtain the second asset description information of the data asset.
[0007] In a possible implementation, determining the first asset value and the second asset value of the data asset based on the second asset description information of the data asset, the multiple target data elements, and the requester information of the evaluation requester includes: Based on the multiple target data elements, determining sub-asset description information corresponding to each of the target data elements from the second asset description information; Determining a first asset value of the data asset based on the sub-asset description information corresponding to each of the target data elements; The second asset value is determined based on the second asset description information and the requester information.
[0008] In a possible implementation manner, determining, based on the multiple target data elements, from the second asset description information, sub-asset description information corresponding to each of the target data elements includes: Extracting features of each of the target data elements to obtain first data element features of each of the target data elements; Extracting features of the plurality of sub-asset description information in the second asset description information to obtain sub-asset description information features of each of the sub-asset description information; Based on the first data element characteristics of each of the target data elements and the sub-asset description information characteristics of each of the sub-asset description information, the sub-asset description information corresponding to each of the target data elements is determined from the second asset description information.
[0009] In a possible implementation manner, determining the first asset value of the data asset based on the sub-asset description information corresponding to each of the target data elements includes: Determine, based on the sub-asset description information corresponding to each of the target data elements, the element asset evaluation information of each of the target data elements, the element asset evaluation information being used to represent the asset evaluation information associated with the data element type corresponding to the target data element; Based on the element asset evaluation information of each of the target data elements, the first asset value of the data asset is determined.
[0010] In a possible implementation manner, determining the element asset evaluation information of each target data element based on the sub-asset description information corresponding to each target data element includes: Determining the data element type of each target data element based on the sub-asset description information corresponding to each target data element; Determining the element asset evaluation dimension of each of the target data elements based on the data element type of each of the target data elements; Each of the target data elements is evaluated based on the element asset evaluation dimension of each of the target data elements and the sub-asset description information corresponding to each of the target data elements to obtain element asset evaluation information of each of the target data elements.
[0011] In a possible implementation manner, determining the second asset value based on the second asset description information and the requesting party information includes: Determine, based on the requester information, a requester level of the evaluation requester, wherein the requester level is used to indicate the credibility of the evaluation requester in the asset dimension; Determining the initial asset value of the data asset based on the second asset description information; The initial asset value is adjusted based on the requester level to obtain the second asset value.
[0012] In a possible implementation manner, the adjusting the initial asset value based on the requester level to obtain the second asset value includes: Determine a level adjustment coefficient corresponding to the requester level; The initial asset value is multiplied by the level adjustment coefficient to obtain the second asset value.
[0013] In one aspect, a data asset value assessment system is provided, the system comprising: An information acquisition module, used to acquire the data assets uploaded by the evaluation requester and first asset description information describing the data assets by the evaluation requester, where the asset description information is used to reflect the asset status of the data assets; An information generation module, configured to generate second asset description information of the data asset based on the data asset and the first asset description information; A data element identification module, used to identify target data elements of the data asset to obtain multiple target data elements of the data asset, wherein the multiple target data elements are data elements in the data asset whose importance is higher than a preset importance; an asset value determination module, configured to determine a first asset value and a second asset value of the data asset based on the second asset description information of the data asset, the multiple target data elements, and the requester information of the evaluation requester, wherein the first asset value and the second asset value are used to represent asset values of different dimensions; The asset value determination module is further used to determine the target asset value of the data asset based on the first asset value of the data asset and the second asset value of the data asset.
[0014] In one possible implementation, the information generation module is used to classify the data assets to obtain the target data asset type to which the data assets belong; based on the target data asset type, determine the target description information generation model corresponding to the target data asset type from multiple candidate description information generation models, and the target description information generation model is used to generate second asset description information; input the data assets and the first asset description information into the target description information generation model, and process the data assets and the first asset description information through the target description information generation model to obtain the second asset description information of the data assets.
[0015] In one possible implementation, the information generation module is used to extract key information of the data asset through the target description information generation model to obtain the asset key information of the data asset; to fuse the first asset description information and the asset key information through the target description information generation model to obtain the reference asset description information of the data asset; and to extract a summary of the reference asset description information through the target description information generation model to obtain the second asset description information of the data asset.
[0016] In one possible implementation, the asset value determination module is used to determine, based on the multiple target data elements, the sub-asset description information corresponding to each target data element from the second asset description information; determine the first asset value of the data asset based on the sub-asset description information corresponding to each target data element; and determine the second asset value based on the second asset description information and the requesting party information.
[0017] In one possible implementation, the asset value determination module is used to perform feature extraction on each of the target data elements to obtain a first data element feature of each of the target data elements; perform feature extraction on multiple sub-asset description information in the second asset description information to obtain a sub-asset description information feature of each of the sub-asset description information; and determine the sub-asset description information corresponding to each of the target data elements from the second asset description information based on the first data element feature of each of the target data elements and the sub-asset description information feature of each of the sub-asset description information.
[0018] In one possible implementation, the asset value determination module is used to determine element asset evaluation information of each of the target data elements based on the sub-asset description information corresponding to each of the target data elements, wherein the element asset evaluation information is used to represent the asset evaluation information associated with the data element type of the corresponding target data element; and determine the first asset value of the data asset based on the element asset evaluation information of each of the target data elements.
[0019] In a possible implementation, the asset value determination module is used to determine the data element type of each target data element based on the sub-asset description information corresponding to each target data element; determine the element asset evaluation dimension of each target data element based on the data element type of each target data element; and evaluate each target data element based on the element asset evaluation dimension of each target data element and the sub-asset description information corresponding to each target data element to obtain the element asset evaluation information of each target data element.
[0020] In one possible implementation, the asset value determination module is used to determine the requester level of the evaluation requester based on the requester information, and the requester level is used to indicate the credibility of the evaluation requester in the asset dimension; based on the second asset description information, determine the initial asset value of the data asset; and adjust the initial asset value based on the requester level to obtain the second asset value.
[0021] In a possible implementation manner, the asset value determination module is used to determine a level adjustment coefficient corresponding to the requester level; and multiply the initial asset value by the level adjustment coefficient to obtain the second asset value.
[0022] On the one hand, a computer device is provided, which includes one or more processors and one or more memories, wherein at least one computer program is stored in the one or more memories, and the computer program is loaded and executed by the one or more processors to implement the data asset value assessment method.
[0023] On the one hand, a computer-readable storage medium is provided, in which at least one computer program is stored, and the computer program is loaded and executed by a processor to implement the data asset value assessment method.
[0024] On the one hand, a computer program product or computer program is provided, which includes a program code, and the program code is stored in a computer-readable storage medium. A processor of a computer device reads the program code from the computer-readable storage medium, and the processor executes the program code, so that the computer device executes the above-mentioned data asset value assessment method.
[0025] Through the technical solution provided in the embodiment of the present application, the data assets uploaded by the evaluation requester and the first asset description information are obtained, and the asset description information is used to reflect the asset status of the data asset. Based on the data asset and the first asset description information, the second asset description information of the data asset is generated. The target data elements of the data asset are identified to obtain multiple target data elements of the data asset. Based on the second asset description information of the data asset, the multiple target data elements and the requester information of the evaluation requester, the first asset value and the second asset value of the data asset in different dimensions are determined. Based on the first asset value and the second asset value, the target asset value of the data asset is determined, thereby achieving full utilization of the data asset, the first asset description information and the requester information, obtaining the target asset value of the data asset, and completing the value evaluation of the data asset. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0027] Figure 1It is a schematic diagram of an implementation environment of a data asset value assessment method provided in an embodiment of the present application; Figure 2 This is a flow chart of a data asset value assessment method provided by an embodiment of the present application; Figure 3 This is a flow chart of another data asset value assessment method provided by an embodiment of the present application; Figure 4 It is a structural diagram of a data asset value assessment system provided in an embodiment of the present application; Figure 5 It is a structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0028] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.
[0029] In this application, the terms "first", "second", etc. are used to distinguish identical or similar items with basically the same effects and functions. It should be understood that there is no logical or temporal dependency between "first", "second", and "nth", nor is there any limitation on quantity and execution order.
[0030] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain better results.
[0031] Machine Learning (ML) is a multi-disciplinary subject involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, etc. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge sub-models to continuously improve their performance.
[0032] Data Asset: refers to data resources owned or controlled by individuals or enterprises that can bring future economic benefits to enterprises. It covers various forms of data, including but not limited to text, images, audio, video, web pages, databases, sensor signals and other structured or unstructured data. The value of data assets lies in their ability to be measured and traded, and can influence the decision-making and economic activities of organizations to a certain extent.
[0033] Data elements: Data elements are the basic units that constitute data assets, including raw data, processed data, and analyzed data. Raw data is the initial data that has not been processed, processed data is the data that has been cleaned and sorted, and analyzed data is the result of further analysis based on this. Each data element carries specific information and value, and is the basis for enterprise data asset management.
[0034] Normalization: Mapping sequences with different value ranges to the interval (0, 1) makes data processing easier. In some cases, the normalized values can be directly implemented as probabilities.
[0035] Embedded Coding: Embedded coding mathematically represents a correspondence, that is, mapping data in X space to Y space through a function F, where the function F is an injective function, and the mapping result is structural preservation. The injective function indicates that the data after mapping is uniquely corresponding to the data before mapping, and structural preservation indicates that the size relationship of the data before mapping is the same as the size relationship of the data after mapping. For example, there are data X1 and X2 before mapping, and after mapping, Y1 corresponding to X1 and Y2 corresponding to X2 are obtained. If the data X1 before mapping is greater than X2, then correspondingly, the data Y1 after mapping is greater than Y2. For words, it means mapping the words to another space to facilitate subsequent machine learning and processing.
[0036] Figure 1 This is a schematic diagram of the implementation environment of a data asset value assessment method provided in an embodiment of the present application, see Figure 1 , the implementation environment may include a terminal 110 and a server 140.
[0037] The terminal 110 is connected to the server 140 via a wireless network or a wired network. Optionally, the terminal 110 is a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal 110 installs and runs an application that supports the value assessment of data assets. The terminal 110 is a terminal used by the assessment requester.
[0038] The server 140 is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, distribution networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms. The server 140 can provide background services for applications running on the terminal 110.
[0039] The following is an explanation of the data asset value assessment method provided in the embodiments of the present application. Figure 2 This is a flow chart of a data asset value assessment method provided in an embodiment of the present application, see Figure 2 Taking the execution subject as a server as an example, the method includes the following steps.
[0040] 201. The server obtains the data asset uploaded by the evaluation requester and the first asset description information describing the data asset by the evaluation requester, where the asset description information is used to reflect the asset status of the data asset.
[0041] The evaluation requester is a user who requests a value assessment of a data asset. A data asset refers to a data resource with economic value. The first asset description information is the asset description information provided by the evaluation requester, and is used to reflect the evaluation requester's understanding of the data asset.
[0042] 202. The server generates second asset description information of the data asset based on the data asset and the first asset description information.
[0043] Among them, the second asset description information is generated based on the data asset and the first asset description information, and can describe the asset situation of the data asset in combination with the first asset description information. Compared with the first asset description information, the second asset description information is more objective.
[0044] 203. The server identifies target data elements of the data asset and obtains multiple target data elements of the data asset. The multiple target data elements are data elements in the data asset whose importance is higher than a preset importance.
[0045] The purpose of identifying target data elements is to find target data elements in data assets, and then use multiple target data elements to evaluate the value of data assets. If the target data element is a data element in the data asset whose importance is higher than the preset importance, it means that the target data element is a data element with a higher importance.
[0046] 204. The server determines the first asset value and the second asset value of the data asset based on the second asset description information of the data asset, the multiple target data elements, and the requester information of the evaluation requester, where the first asset value and the second asset value are used to represent asset values in different dimensions.
[0047] Among them, the first asset value and the second asset value are used to represent asset values in different dimensions. Therefore, the first asset value and the second asset value can also reflect the asset value of the data asset from different dimensions, thereby determining the final recognized asset value of the data asset.
[0048] 205. The server determines a target asset value of the data asset based on the first asset value of the data asset and the second asset value of the data asset.
[0049] Among them, the target asset value is the asset value finally recognized by the data asset.
[0050] Through the technical solution provided in the embodiment of the present application, the data assets uploaded by the evaluation requester and the first asset description information are obtained, and the asset description information is used to reflect the asset status of the data asset. Based on the data asset and the first asset description information, the second asset description information of the data asset is generated. The target data elements of the data asset are identified to obtain multiple target data elements of the data asset. Based on the second asset description information of the data asset, the multiple target data elements and the requester information of the evaluation requester, the first asset value and the second asset value of the data asset in different dimensions are determined. Based on the first asset value and the second asset value, the target asset value of the data asset is determined, thereby achieving full utilization of the data asset, the first asset description information and the requester information, obtaining the target asset value of the data asset, and completing the value evaluation of the data asset.
[0051] The above steps 201-205 are a brief introduction to the value assessment method of data assets provided in the embodiment of the present application. The value assessment method of data assets provided in the embodiment of the present application will be more clearly explained below with reference to some examples. Figure 3 Taking the execution subject as a server as an example, the method includes the following steps.
[0052] 301. The server obtains the data asset uploaded by the evaluation requester and the first asset description information describing the data asset by the evaluation requester, where the asset description information is used to reflect the asset status of the data asset.
[0053] Among them, the evaluation requester is a user who requests a value assessment of a data asset. For example, the server uses a user account to identify the user. Data assets refer to data resources with economic value. The first asset description information is the asset description information provided by the evaluation requester, which is used to reflect the evaluation requester's understanding of the data asset.
[0054] In a possible implementation, the server obtains a data asset evaluation request uploaded by the evaluation requester, and parses the data asset evaluation request to obtain the data asset and the first asset description information.
[0055] The data asset evaluation request is sent by the evaluation requester to the server using the terminal. The terminal displays a data asset evaluation page. The evaluation requester selects the data asset that needs to be evaluated on the data asset evaluation page and fills in the first asset description information. In response to the confirmation operation on the data asset evaluation page, the terminal generates a data asset evaluation request based on the selected data asset and the first asset description information, and sends the data asset evaluation request to the server, which obtains the data asset evaluation request.
[0056] 302. The server generates second asset description information of the data asset based on the data asset and the first asset description information.
[0057] Among them, the second asset description information is generated based on the data asset and the first asset description information, and can describe the asset situation of the data asset in combination with the first asset description information. Compared with the first asset description information, the second asset description information is more objective.
[0058] In a possible implementation, the server classifies the data asset to obtain the target data asset type to which the data asset belongs. Based on the target data asset type, the server determines a target description information generation model corresponding to the target data asset type from a plurality of candidate description information generation models, and the target description information generation model is used to generate the second asset description information. The server inputs the data asset and the first asset description information into the target description information generation model, processes the data asset and the first asset description information through the target description information generation model, and obtains the second asset description information of the data asset.
[0059] Among them, multiple candidate description information generation models are all models for generating second asset description information, and different candidate description information generation models correspond to different data asset types, that is, the candidate description information generation model corresponding to the data asset type can generate the second asset description information corresponding to the data asset type, thereby realizing the fine-grained generation of the second asset description information. In addition, the multiple candidate description information are all generative models, such as a large language model with data asset analysis and natural language processing capabilities.
[0060] In this implementation, based on the target data asset type to which the data asset belongs, the target description information generation model corresponding to the target data asset type is determined from multiple candidate description information generation models, thereby implementing the screening of candidate description information generation models. The screened target description information generation model is used to process the data asset and the first asset description information, so as to obtain the second asset description information of the data asset, which is highly efficient.
[0061] In order to explain the above implementation more clearly, the above implementation will be explained in several parts below.
[0062] In the first part, the server classifies the data asset to obtain the target data asset type to which the data asset belongs.
[0063] In a possible implementation, the server inputs the data asset into a data asset classification model, extracts features of the data asset through the data asset classification model, and obtains data asset features of the data asset. The server classifies the data asset based on the data asset features through the data asset classification model to obtain the target data asset type to which the data asset belongs.
[0064] In this implementation, the data asset classification model can be used to quickly classify the data asset.
[0065] For example, the server inputs the data asset into the data asset classification model, and performs multiple convolutions on the data asset through the data asset classification model to obtain the data asset features of the data asset. The server uses the data asset classification model to fully connect and normalize the data asset features to obtain a probability set corresponding to the data asset, which includes multiple probabilities, and one probability corresponds to one candidate data asset type. The server determines the candidate data asset type corresponding to the highest probability in the probability set as the target data asset type to which the data asset belongs.
[0066] Among them, the data asset classification model is a multi-classification model, which is obtained through supervised training based on multiple sample data assets and the labeled data asset types corresponding to each sample data asset, and has the ability to classify data assets.
[0067] In the second part, the server determines a target description information generation model corresponding to the target data asset type from a plurality of candidate description information generation models based on the target data asset type.
[0068] In a possible implementation, the server uses the target data asset type to match multiple candidate description information generation models, and determines the target description information generation model from the multiple candidate description information generation models, and the target description information generation model is the candidate description information generation model that successfully matches the target data asset type.
[0069] Among them, one candidate description information corresponds to at least one candidate data asset type, and successful matching with the target data asset type means that at least one candidate data asset type corresponding to the candidate description information generation model includes the target data asset type.
[0070] In the third part, the server inputs the data asset and the first asset description information into the target description information generation model, processes the data asset and the first asset description information through the target description information generation model, and obtains the second asset description information of the data asset.
[0071] In a possible implementation, the server inputs the data asset and the first asset description information into the target description information generation model, extracts key information of the data asset through the target description information generation model, and obtains the asset key information of the data asset. The server merges the first asset description information and the asset key information through the target description information generation model to obtain the reference asset description information of the data asset. The server extracts a summary of the reference asset description information through the target description information generation model to obtain the second asset description information of the data asset.
[0072] For example, the server inputs the data asset and the first asset description information into the target description information generation model, and performs data segmentation on the data asset through the target description information generation model to obtain multiple data contents of the data asset, the multiple data contents constitute the data asset, and one data content contains multiple interrelated data elements. The server extracts key information from each data content through the target description information generation model to obtain the content key information of each data content. The server splices the content key information of each data content to obtain the asset key information of the data asset. The server splices the first asset description information and the asset key information through the target description information generation model to obtain the reference asset description information of the data asset. The server generates a first prompt text based on the reference asset description information, and the first prompt text is used to indicate that a summary of the reference asset description information is extracted. The server extracts a summary of the reference asset description information based on the first prompt text through the target description information generation model to obtain the second asset description information of the data asset.
[0073] Among them, data elements are the smallest components of data assets.
[0074] For example, the server inputs the data asset and the first asset description information into the target description information generation model, clusters the data elements in the data asset through the target description information generation model, and obtains multiple data contents of the data asset. For any data content in the multiple data contents, the server extracts features of the multiple data elements and the data content in the data content through the target description information generation model, and obtains the second data element features of each data element in the data content and the data content features of the data content. The server determines the key score of each data element in the data content in the data content based on the second data element features of each data element in the data content and the data content features of the data content. The server determines the N data elements with the highest key scores among the data elements in the data content as the key data elements corresponding to the data content, where N is a positive integer. The server merges the N key data elements corresponding to the data content through the target description information generation model to obtain the content key information of the data content. The server splices the content key information of each data content to obtain the asset key information of the data asset. The server uses the target description information generation model to concatenate the first asset description information and the asset key information to obtain the reference asset description information of the data asset. The server fills the reference asset description information into the first prompt text template to obtain the first prompt text. The server uses the target description information generation model to encode the first prompt text based on the attention mechanism to obtain the first prompt text feature of the first prompt text. The server uses the target description information generation model to perform multiple rounds of iterative decoding on the first prompt text feature based on the attention mechanism to obtain the second asset description information of the data asset.
[0075] Among them, N is set by the technician according to the actual situation, and the embodiments of the present application do not limit this. The key score is determined based on the feature similarity between the second data element feature of the data element and the data content feature of the data content. For example, the feature similarity between the second data element feature of the data element and the data content feature of the data content is normalized to obtain the key score.
[0076] 303. The server identifies target data elements of the data asset and obtains multiple target data elements of the data asset. The multiple target data elements are data elements in the data asset whose importance is higher than a preset importance.
[0077] The purpose of identifying target data elements is to find target data elements in data assets, and then use multiple target data elements to evaluate the value of data assets. If the target data element is a data element in the data asset whose importance is higher than the preset importance, it means that the target data element is a data element with a higher importance.
[0078] In a possible implementation, the server performs paragraph segmentation on the data asset to obtain multiple data paragraphs of the data asset, the multiple data paragraphs constitute the data asset, and one data paragraph contains multiple adjacent data elements. The server performs feature extraction on the multiple data paragraphs and the multiple data elements in each data paragraph to obtain data paragraph features of each data paragraph and second data element features of each data element in each data paragraph. Based on the data paragraph features of each data paragraph and the second data element features of each data element in each data paragraph, the server determines multiple reference data elements from the multiple data elements in the multiple data paragraphs. Based on the data asset features of the data asset and the second data element features of each reference data element, the server determines multiple target data elements from the multiple reference data elements.
[0079] Among them, the division methods of data paragraphs and data content are different. Multiple data elements in a data paragraph are adjacent in the data asset, and multiple data elements in the data content are not necessarily adjacent, but are interrelated. The interrelationship here refers to the interrelationship in content.
[0080] For example, the server segments the data asset according to a preset paragraph interval to obtain multiple data paragraphs of the data asset. The server encodes the multiple data paragraphs and multiple data elements in each data paragraph based on the attention mechanism to obtain the data paragraph features of each data paragraph and the second data element features of each data element in each data paragraph. For any data paragraph in the multiple data paragraphs, the server determines the first importance of each data element in the data paragraph in the data paragraph based on the data paragraph features of the data paragraph and the second data element features of each data element in the data paragraph. The server determines the M data elements with the highest first importance among the data elements in the data paragraph as the reference data elements of the data paragraph, where M is a positive integer. The server determines the second importance of each reference data element in the data asset based on the data asset features of the data asset and the second data element features of each reference data element. The server determines the L reference data elements with the highest second importance among the multiple reference data elements as the multiple target data elements, where L is a positive integer.
[0081] The first importance is determined based on the feature similarity between the data paragraph feature and the second data element feature, for example, the first importance is obtained by normalizing the feature similarity between the data paragraph feature and the second data element feature; the second importance is determined based on the feature similarity between the data asset feature and the second data element feature, for example, the second importance is obtained by normalizing the feature similarity between the data asset feature and the second data element feature. The preset paragraph interval is set by the technician according to the actual situation, and the embodiment of the present application does not limit this.
[0082] 304. The server determines the first asset value of the data asset based on the second asset description information of the data asset and the multiple target data elements.
[0083] Among them, the first asset value is the asset value obtained by evaluating the value of the data asset from the dimension of the target data element.
[0084] In a possible implementation, the server determines sub-asset description information corresponding to each target data element from the second asset description information based on the multiple target data elements. The server determines the first asset value of the data asset based on the sub-asset description information corresponding to each target data element.
[0085] In order to explain the above implementation more clearly, the above implementation will be explained in several parts below.
[0086] In the first part, the server determines, based on the multiple target data elements, the sub-asset description information corresponding to each of the target data elements from the second asset description information.
[0087] In a possible implementation, the server extracts features from each of the target data elements to obtain first data element features of each of the target data elements. The server extracts features from multiple sub-asset description information in the second asset description information to obtain sub-asset description information features of each of the sub-asset description information. The server determines sub-asset description information corresponding to each of the target data elements from the second asset description information based on the first data element features of each of the target data elements and the sub-asset description information features of each of the sub-asset description information.
[0088] Among them, the first data element feature is different from the second data element feature, the dimension of the first data element feature is higher than the second data element feature, so the first data element feature has stronger expressive power than the second data element feature, and the feature extraction of the data element before step 304 to obtain the second data element feature instead of the first data element feature is to speed up the processing speed, and the first data element feature is used in step 304 to improve accuracy. Multiple sub-asset description information constitute the second asset description information.
[0089] For example, the server extracts features from each target data element to obtain the first data element features of each target data element. The server extracts features from multiple sub-asset description information in the second asset description information to obtain sub-asset description information features of each sub-asset description information. The server determines the degree of match between each target data element and each sub-asset description information based on the first data element features of each target data element and the sub-asset description information features of each sub-asset description information. The server determines the sub-asset description information corresponding to each target data element based on the degree of match between each target data element and each sub-asset description information.
[0090] The matching degree is the feature similarity between the first data element feature and the sub-asset description information feature. For any target data element among the multiple target data elements, the sub-asset description information corresponding to the target data element is the sub-asset description information with the highest matching degree with the target data element among the multiple sub-asset description information.
[0091] In the second part, the server determines the first asset value of the data asset based on the sub-asset description information corresponding to each target data element.
[0092] In a possible implementation, the server determines the element asset evaluation information of each target data element based on the sub-asset description information corresponding to each target data element, and the element asset evaluation information is used to represent the asset evaluation information associated with the data element type corresponding to the target data element. The server determines the first asset value of the data asset based on the element asset evaluation information of each target data element.
[0093] In order to explain the above implementation more clearly, the above implementation will be further described in several parts below.
[0094] A. The server determines the element asset evaluation information of each target data element based on the sub-asset description information corresponding to each target data element.
[0095] In a possible implementation, the server determines the data element type of each target data element based on the sub-asset description information corresponding to each target data element. The server determines the element asset evaluation dimension of each target data element based on the data element type of each target data element. The server evaluates each target data element based on the element asset evaluation dimension of each target data element and the sub-asset description information corresponding to each target data element, and obtains the element asset evaluation information of each target data element.
[0096] Among them, the factor asset evaluation dimension refers to the dimension used to evaluate the target data element. For example, the factor asset evaluation dimension includes the time value dimension, the application value dimension, the risk dimension, etc. The time value dimension is used to indicate the change in the value of the target data element over time, the application value dimension is used to indicate the difficulty of applying the target data element to a specific business, and the risk dimension is used to indicate the impact of the risk of the target data element on the value. There is a corresponding relationship between the factor asset evaluation dimension and the data element type. One data element type corresponds to at least one factor asset evaluation dimension.
[0097] For example, the server determines the data element type of each target data element based on the sub-asset description information corresponding to each target data element. The server uses the data element type of each target data element to query the element asset evaluation dimension of each target data element. For any target data element among the multiple target data elements, the first data element feature of the target data element is input into at least one evaluation model corresponding to the element asset evaluation dimension of the target data element, and the first data element feature is processed by at least one evaluation model to obtain the element asset evaluation information of the target data element. One evaluation model corresponds to one element asset evaluation dimension, and the element asset evaluation information includes the result output by the at least one evaluation model.
[0098] B. The server determines the first asset value of the data asset based on the element asset evaluation information of each target data element.
[0099] In a possible implementation, the server concatenates the element asset evaluation information of each target data element to obtain the first asset evaluation information of the data asset. The server extracts features of the first asset evaluation information to obtain the first asset evaluation information features of the first asset evaluation information. The server fully connects and normalizes the first asset evaluation information features to obtain the first asset value of the data asset.
[0100] 305. The server determines the second asset value of the data asset based on the second asset description information of the data asset and the requester information of the evaluation requester. The first asset value and the second asset value are used to represent asset values in different dimensions.
[0101] The second asset value is the asset value obtained by evaluating the value of the data asset from the perspective of the requesting party.
[0102] In a possible implementation, the server determines the requester level of the evaluation requester based on the requester information, and the requester level is used to indicate the credibility of the evaluation requester in the asset dimension. The server determines the initial asset value of the data asset based on the second asset description information. The server adjusts the initial asset value based on the requester level to obtain the second asset value.
[0103] For example, the server sends the requester information to multiple credibility assessment nodes, and the multiple credibility assessment nodes determine the reference requester level of the assessment requester based on the requester information. The server obtains the reference requester levels returned by multiple credibility assessment nodes, and weightedly fuses the reference requester levels returned by multiple credibility assessment nodes to obtain the requester level of the assessment requester. The server performs feature extraction on the second asset description information to obtain the second asset description information feature of the second asset description information. The server performs full connection and normalization on the second asset description information feature to obtain the initial asset value of the data asset. The server determines the level adjustment coefficient corresponding to the requester level. The server multiplies the initial asset value by the level adjustment coefficient to obtain the second asset value.
[0104] Among them, the corresponding relationship between the requester level and the level adjustment coefficient is set by the technical personnel according to the actual situation, and the embodiment of the present application does not limit this.
[0105] The following describes the manner in which the credibility evaluation node determines the reference requester level of the evaluation requester based on the requester information in the above example.
[0106] In a possible implementation, for any credibility evaluation node among the multiple credibility evaluation nodes, the credibility evaluation node extracts features of the requester information to obtain the requester information features of the requester information. The credibility evaluation node determines a reference requester level of the evaluated requester from the multiple candidate requester levels based on the feature similarity between the requester information features of the requester information and the requester information features corresponding to the multiple candidate requester levels, and the reference requester level corresponds to the credibility evaluation node.
[0107] Among them, different multiple credibility evaluation nodes correspond to the same multiple candidate requester levels, but the requester information characteristics corresponding to the candidate requester levels are independently determined by the credibility evaluation nodes, and different credibility evaluation nodes do not affect each other to ensure independent evaluation of the evaluation requester.
[0108] 306. The server determines a target asset value of the data asset based on the first asset value of the data asset and the second asset value of the data asset.
[0109] Among them, the target asset value is the asset value finally recognized by the data asset.
[0110] In a possible implementation, the server performs weighted fusion on the first asset value of the data asset and the second asset value of the data asset to obtain the target asset value of the data asset.
[0111] Among them, the weights of weighted fusion are set by technical personnel according to actual conditions, and the embodiments of the present application do not limit this.
[0112] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.
[0113] Through the technical solution provided in the embodiment of the present application, the data assets uploaded by the evaluation requester and the first asset description information are obtained, and the asset description information is used to reflect the asset status of the data asset. Based on the data asset and the first asset description information, the second asset description information of the data asset is generated. The target data elements of the data asset are identified to obtain multiple target data elements of the data asset. Based on the second asset description information of the data asset, the multiple target data elements and the requester information of the evaluation requester, the first asset value and the second asset value of the data asset in different dimensions are determined. Based on the first asset value and the second asset value, the target asset value of the data asset is determined, thereby achieving full utilization of the data asset, the first asset description information and the requester information, obtaining the target asset value of the data asset, and completing the value evaluation of the data asset.
[0114] Figure 4 This is a schematic diagram of the structure of a data asset value assessment system provided in an embodiment of the present application, see Figure 4 , the system includes: The information acquisition module 401 is used to acquire the data assets uploaded by the evaluation requester and the first asset description information describing the data assets by the evaluation requester, where the asset description information is used to reflect the asset status of the data assets.
[0115] The information generation module 402 is used to generate second asset description information of the data asset based on the data asset and the first asset description information.
[0116] The data element identification module 403 is used to identify target data elements of the data asset to obtain multiple target data elements of the data asset, where the multiple target data elements are data elements in the data asset whose importance is higher than a preset importance.
[0117] The asset value determination module 404 is used to determine the first asset value and the second asset value of the data asset based on the second asset description information of the data asset, the multiple target data elements and the requester information of the evaluation requester, and the first asset value and the second asset value are used to represent asset values of different dimensions.
[0118] The asset value determination module 404 is further configured to determine a target asset value of the data asset based on the first asset value of the data asset and the second asset value of the data asset.
[0119] In a possible implementation, the information generation module 402 is used to classify the data asset to obtain the target data asset type to which the data asset belongs. Based on the target data asset type, a target description information generation model corresponding to the target data asset type is determined from multiple candidate description information generation models, and the target description information generation model is used to generate the second asset description information. The data asset and the first asset description information are input into the target description information generation model, and the data asset and the first asset description information are processed by the target description information generation model to obtain the second asset description information of the data asset.
[0120] In a possible implementation, the information generation module 402 is used to extract key information of the data asset through the target description information generation model to obtain the asset key information of the data asset. Through the target description information generation model, the first asset description information and the asset key information are merged to obtain the reference asset description information of the data asset. Through the target description information generation model, the reference asset description information is abstracted and extracted to obtain the second asset description information of the data asset.
[0121] In a possible implementation, the asset value determination module 404 is configured to determine, based on the multiple target data elements, sub-asset description information corresponding to each target data element from the second asset description information, determine the first asset value of the data asset based on the sub-asset description information corresponding to each target data element, and determine the second asset value based on the second asset description information and the requesting party information.
[0122] In a possible implementation, the asset value determination module 404 is used to extract features from each of the target data elements to obtain first data element features of each of the target data elements. Feature extraction is performed on multiple sub-asset description information in the second asset description information to obtain sub-asset description information features of each of the sub-asset description information. Based on the first data element features of each of the target data elements and the sub-asset description information features of each of the sub-asset description information, the sub-asset description information corresponding to each of the target data elements is determined from the second asset description information.
[0123] In a possible implementation, the asset value determination module 404 is used to determine the element asset evaluation information of each target data element based on the sub-asset description information corresponding to each target data element, where the element asset evaluation information is used to represent the asset evaluation information associated with the data element type corresponding to the target data element. Based on the element asset evaluation information of each target data element, the first asset value of the data asset is determined.
[0124] In a possible implementation, the asset value determination module 404 is used to determine the data element type of each target data element based on the sub-asset description information corresponding to each target data element. Based on the data element type of each target data element, determine the element asset evaluation dimension of each target data element. Evaluate each target data element based on the element asset evaluation dimension of each target data element and the sub-asset description information corresponding to each target data element to obtain the element asset evaluation information of each target data element.
[0125] In a possible implementation, the asset value determination module 404 is used to determine the requester level of the evaluation requester based on the requester information, and the requester level is used to indicate the credibility of the evaluation requester in the asset dimension. Based on the second asset description information, the initial asset value of the data asset is determined. The initial asset value is adjusted based on the requester level to obtain the second asset value.
[0126] In a possible implementation, the asset value determination module 404 is configured to determine a level adjustment coefficient corresponding to the requester level and to multiply the initial asset value by the level adjustment coefficient to obtain the second asset value.
[0127] It should be noted that: the data asset value assessment system provided in the above embodiment only uses the division of the above functional modules as an example when assessing the value of data assets. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the system can be divided into different functional modules to complete all or part of the functions described above. In addition, the data asset value assessment system provided in the above embodiment and the data asset value assessment method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.
[0128] Through the technical solution provided in the embodiment of the present application, the data assets uploaded by the evaluation requester and the first asset description information are obtained, and the asset description information is used to reflect the asset status of the data asset. Based on the data asset and the first asset description information, the second asset description information of the data asset is generated. The target data elements of the data asset are identified to obtain multiple target data elements of the data asset. Based on the second asset description information of the data asset, the multiple target data elements and the requester information of the evaluation requester, the first asset value and the second asset value of the data asset in different dimensions are determined. Based on the first asset value and the second asset value, the target asset value of the data asset is determined, thereby achieving full utilization of the data asset, the first asset description information and the requester information, obtaining the target asset value of the data asset, and completing the value evaluation of the data asset.
[0129] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. The computer device 500 may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 501 and one or more memories 502, wherein the one or more memories 502 store at least one computer program, and the at least one computer program is loaded and executed by the one or more processors 501 to implement the methods provided in the above-mentioned various method embodiments. Of course, the computer device 500 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output. The computer device 500 may also include other components for implementing device functions, which will not be described in detail here.
[0130] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including a computer program, and the computer program can be executed by a processor to complete the value assessment method of data assets in the above embodiment. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.
[0131] In an exemplary embodiment, a computer program product or a computer program is also provided, which includes a program code, and the program code is stored in a computer-readable storage medium. A processor of a computer device reads the program code from the computer-readable storage medium, and the processor executes the program code, so that the computer device executes the above-mentioned data asset value assessment method.
[0132] In some embodiments, the computer program involved in the embodiments of the present application may be deployed and executed on a computer device, or on multiple computer devices located at one location, or on multiple computer devices distributed at multiple locations and interconnected by a communication network. Multiple computer devices distributed at multiple locations and interconnected by a communication network may constitute a blockchain system.
[0133] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.
[0134] The above are only optional embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
Claims
1. A method for evaluating the value of data assets, characterized in that: The method comprises: Acquire the data assets uploaded by the evaluation requester and first asset description information describing the data assets by the evaluation requester, where the asset description information is used to reflect the asset status of the data assets; Based on the data asset and the first asset description information, generate second asset description information of the data asset; Identifying target data elements of the data asset to obtain multiple target data elements of the data asset, wherein the multiple target data elements are data elements in the data asset whose importance is higher than a preset importance; Determine a first asset value and a second asset value of the data asset based on the second asset description information of the data asset, the multiple target data elements, and the requester information of the evaluation requester, wherein the first asset value and the second asset value are used to represent asset values of different dimensions; Based on the first asset value of the data asset and the second asset value of the data asset, a target asset value of the data asset is determined.
2. The method according to claim 1, characterized in that: The generating second asset description information of the data asset based on the data asset and the first asset description information includes: Classifying the data assets to obtain the target data asset type to which the data assets belong; Based on the target data asset type, determining a target description information generation model corresponding to the target data asset type from a plurality of candidate description information generation models, the target description information generation model being used to generate second asset description information; The data asset and the first asset description information are input into the target description information generation model, and the data asset and the first asset description information are processed by the target description information generation model to obtain second asset description information of the data asset.
3. The method according to claim 2, characterized in that The step of processing the data asset and the first asset description information by using the target description information generation model to obtain the second asset description information of the data asset includes: Extracting key information of the data asset through the target description information generation model to obtain key asset information of the data asset; By using the target description information generation model, the first asset description information and the asset key information are integrated to obtain reference asset description information of the data asset; The reference asset description information is summarized and extracted through the target description information generation model to obtain the second asset description information of the data asset.
4. The method according to claim 1, characterized in that: The determining the first asset value and the second asset value of the data asset based on the second asset description information of the data asset, the multiple target data elements, and the requester information of the evaluation requester includes: Based on the multiple target data elements, determining sub-asset description information corresponding to each of the target data elements from the second asset description information; Determining a first asset value of the data asset based on the sub-asset description information corresponding to each of the target data elements; The second asset value is determined based on the second asset description information and the requester information.
5. The method according to claim 4, characterized in that The determining, based on the plurality of target data elements, from the second asset description information, sub-asset description information corresponding to each of the target data elements includes: Extracting features of each of the target data elements to obtain first data element features of each of the target data elements; Extracting features of the plurality of sub-asset description information in the second asset description information to obtain sub-asset description information features of each of the sub-asset description information; Based on the first data element characteristics of each of the target data elements and the sub-asset description information characteristics of each of the sub-asset description information, the sub-asset description information corresponding to each of the target data elements is determined from the second asset description information.
6. The method according to claim 4, characterized in that The determining the first asset value of the data asset based on the sub-asset description information corresponding to each of the target data elements includes: Determine, based on the sub-asset description information corresponding to each of the target data elements, the element asset evaluation information of each of the target data elements, the element asset evaluation information being used to represent the asset evaluation information associated with the data element type corresponding to the target data element; Based on the element asset evaluation information of each of the target data elements, the first asset value of the data asset is determined.
7. The method according to claim 6, characterized in that The determining of the element asset evaluation information of each target data element based on the sub-asset description information corresponding to each target data element includes: Determining the data element type of each target data element based on the sub-asset description information corresponding to each target data element; Determining the element asset evaluation dimension of each of the target data elements based on the data element type of each of the target data elements; Each of the target data elements is evaluated based on the element asset evaluation dimension of each of the target data elements and the sub-asset description information corresponding to each of the target data elements to obtain element asset evaluation information of each of the target data elements.
8. The method according to claim 4, characterized in that The determining the second asset value based on the second asset description information and the requester information includes: Determine, based on the requester information, a requester level of the evaluation requester, wherein the requester level is used to indicate the credibility of the evaluation requester in the asset dimension; Determining the initial asset value of the data asset based on the second asset description information; The initial asset value is adjusted based on the requester level to obtain the second asset value.
9. The method according to claim 8, characterized in that The adjusting the initial asset value based on the requester level to obtain the second asset value includes: Determine a level adjustment coefficient corresponding to the requester level; The initial asset value is multiplied by the level adjustment coefficient to obtain the second asset value.
10. A data asset value assessment system, characterized in that: The system comprises: An information acquisition module, used to acquire the data assets uploaded by the evaluation requester and first asset description information describing the data assets by the evaluation requester, where the asset description information is used to reflect the asset status of the data assets; An information generation module, configured to generate second asset description information of the data asset based on the data asset and the first asset description information; A data element identification module, used to identify target data elements of the data asset to obtain multiple target data elements of the data asset, wherein the multiple target data elements are data elements in the data asset whose importance is higher than a preset importance; an asset value determination module, configured to determine a first asset value and a second asset value of the data asset based on the second asset description information of the data asset, the multiple target data elements, and the requester information of the evaluation requester, wherein the first asset value and the second asset value are used to represent asset values of different dimensions; The asset value determination module is further used to determine the target asset value of the data asset based on the first asset value of the data asset and the second asset value of the data asset.
Citation Information
Patent Citations
Data asset value evaluation method
CN116797097A
Data asset value evaluation method and device
CN118278962A
KR20230146786A
