Data asset management method and device, computer equipment and readable storage medium

Abstract

The invention relates to a data asset management method and device, computer equipment, a computer readable storage medium and a computer program product, and the method comprises the steps: obtaining basic asset data and user behavior data of a target user on a data platform, the target user being a user having a metadata subscription behavior; performing process analysis on the metadata subscription behavior according to the user behavior data to obtain evaluation data related to the metadata; finally, value evaluation is conducted through the basic asset data and the evaluation data related to the metadata, value data of all the metadata are obtained, and the value data of all the metadata are used for recognizing and obtaining key data assets. According to the method, the key influence factor, namely the user behavior data, is combined to help an enterprise to identify key data assets, optimize a data use strategy and improve the overall value of the data assets.

Description

Technical Field

[0001] The present application relates to the technical field of data processing and analysis, and in particular to a data asset management method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the deepening of digital construction, more and more institutions and enterprises have accumulated a large amount of data resources. In order to use data resources more effectively, integrating them into data assets and managing them in a unified manner has become an important direction. More importantly, how to process and utilize data, release data value, and realize data asset evaluation is also an important issue facing enterprises.

[0003] Among traditional technologies, there are asset valuation methods such as cost method, income method and market method. These methods are applicable when applied to data asset valuation, but they also have certain limitations. Currently, there is no mature data asset valuation method. Gradually exploring and promoting the value analysis of data assets in specific fields or specific cases may be a feasible way to continue to deepen this research in the future. Summary of the invention

[0004] Based on this, it is necessary to provide a data asset management method, apparatus, computer equipment, computer-readable storage medium and computer program product to address the technical problem that a mature and reliable data asset valuation method has not yet been formed.

[0005] A data asset management method, the method comprising:

[0006] Obtaining basic asset data and user behavior data of target users on the data platform, where the target users are users who have metadata subscription behavior;

[0007] Performing a process analysis on the metadata subscription behavior according to the user behavior data to obtain evaluation data related to the metadata;

[0008] The value assessment is performed through the basic asset data and the assessment data related to the metadata to obtain the value data of each metadata, and the value data of each metadata is used to identify key data assets.

[0009] In one of the embodiments, the evaluation data related to the metadata includes a search add-to-cart hit rate;

[0010] Performing a process analysis on the metadata subscription behavior according to the user behavior data to obtain evaluation data related to the metadata, including:

[0011] Extracting operation path data of the metadata subscription behavior from the user behavior data;

[0012] The search and add-to-cart hit rate is calculated based on the operation path data.

[0013] In one of the embodiments, the evaluation data related to the metadata includes an add-to-cart conversion rate;

[0014] Performing a process analysis on the metadata subscription behavior according to the user behavior data to obtain evaluation data related to the metadata, including:

[0015] Filtering the user behavior data to obtain target user behavior data corresponding to metadata belonging to the same data set;

[0016] Funnel analysis is performed on the target user behavior data to obtain the add-to-cart conversion rate during the metadata subscription process.

[0017] In one embodiment, the performing funnel analysis on the target user behavior data to obtain the purchase conversion rate during the metadata subscription process includes:

[0018] Based on the basic path of the metadata subscription behavior, multiple basic stages are obtained, wherein the basic stage includes an add-to-purchase stage;

[0019] Extracting the metadata quantity corresponding to each of the basic stages from the target user behavior data;

[0020] A calculation is performed based on the quantity of metadata corresponding to each of the basic stages to obtain an add-to-cart conversion rate corresponding to the add-to-cart stage.

[0021] In one embodiment, the performing of value assessment on the basic asset data and the assessment data related to the metadata to obtain the value data of each metadata includes:

[0022] Performing correlation analysis based on the basic asset data and the evaluation data related to the metadata to obtain core feature data;

[0023] The value of each metadata is estimated based on the core feature data to obtain value data of each metadata.

[0024] In one embodiment, performing correlation analysis based on the basic asset data and the evaluation data related to the metadata to obtain core feature data includes:

[0025] Integrate the basic asset data and the evaluation data related to the metadata to form a comprehensive evaluation data set;

[0026] Extracting and deriving features from the basic asset data and the evaluation data related to the metadata to obtain a plurality of basic features;

[0027] The basic data corresponding to each of the basic features is extracted from the comprehensive evaluation data set, and prediction and identification are performed according to a preset analysis model to obtain core feature data.

[0028] In one embodiment, a data asset management device is also provided, the device comprising:

[0029] An acquisition module is used to acquire basic asset data and user behavior data of target users on the data platform, where the target users are users who have metadata subscription behavior;

[0030] An analysis module, used to perform a process analysis on the metadata subscription behavior according to the user behavior data to obtain evaluation data related to the metadata;

[0031] The evaluation module is used to perform value evaluation based on the basic asset data and the evaluation data related to the metadata to obtain the value data of each metadata, and the value data of each metadata is used to identify key data assets.

[0032] In one of the embodiments, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0033] In one of the embodiments, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0034] In one of the embodiments, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0035] The above-mentioned data asset management method, device, computer equipment, computer-readable storage medium and computer program product obtain the basic asset data and the user behavior data of the target user on the data platform, where the target user is a user with metadata subscription behavior; then perform process analysis on the metadata subscription behavior based on the user behavior data to obtain evaluation data related to the metadata; finally, perform value evaluation through the basic asset data and the evaluation data related to the metadata to obtain the value data of each metadata, and the value data of each metadata is used to identify key data assets. This application helps enterprises identify key data assets, optimize data usage strategies, and enhance the overall value of data assets by combining user behavior data as a key influencing factor. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 An application environment diagram of a data asset management method in an embodiment;

[0038] Figure 2 A flowchart of a data asset management method in one embodiment;

[0039] Figure 3 A schematic diagram of a flow chart of a step of calculating a search and purchase hit rate in one embodiment;

[0040] Figure 4 A schematic diagram of a flow chart of a step of calculating an add-to-cart conversion rate in one embodiment;

[0041] Figure 5 A schematic diagram of a flow chart of a step of calculating an add-to-cart conversion rate in another embodiment;

[0042] Figure 6 A schematic diagram of a flow chart of a step of calculating the value data of metadata in one embodiment;

[0043] Figure 7 A schematic flow chart of a step of calculating the value data of metadata in another embodiment;

[0044] Figure 8 A schematic diagram of a system block diagram of an asset value collection and analysis system in one embodiment;

[0045] Fig. 9 is a structural block diagram of a data asset management device in one embodiment;

[0046] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] The data asset management method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Specifically, the server 104 obtains the basic asset data and the user behavior data output by the target user on the data platform through the terminal 102, and the target user is a user with metadata subscription behavior; the metadata subscription behavior is analyzed according to the user behavior data to obtain the evaluation data related to the metadata; the value evaluation is performed through the basic asset data and the evaluation data related to the metadata to obtain the value data of each metadata, and the value data of each metadata is used to identify the key data assets. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0049] In an exemplary embodiment, Figure 2 As shown, a data asset management method is provided, which is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps 202 to 206. Among them:

[0050] Step 202, obtaining basic asset data and user behavior data of target users on the data platform, where the target users are users who have metadata subscription behavior.

[0051] Specifically, basic asset data refers to the core entity data of the data platform, or master data, such as population, legal person, geographic information, credit, electronic certificates and other data in smart cities. Basic asset data can be obtained by combing business and data resources to obtain a data resource list, and designing the database table structure based on business understanding, and then designing the data collection and cleaning process according to the data resource list, storing neat and clean data in the database or data warehouse, and finally obtaining basic asset data. In addition, basic asset data can also include metadata that associates the business meaning of data items with data items, so that business personnel can also understand the meaning of data fields in the database. It can be understood that metadata management is generally the management of data item attributes in the basic library and the subject library (i.e., core data assets), while the data resource list is the management of data items from various data sources.

[0052] Furthermore, enterprise users can perform various user behaviors on the data platform, and record their user behaviors to store and obtain user behavior data. For example, enterprise users can view different application modules, metadata management, data asset display, and data lineage on the data governance platform based on their roles. In the process of viewing the above modules, the user's clicks, searches, browsing and other behaviors and operation paths can be recorded to obtain user behavior data.

[0053] Among them, enterprise users can be divided into groups according to their roles. For example, users who can formulate data standards, policies and processes can be classified as data governance personnel; users who can manage data assets and maintain metadata information can be classified as data stewards to ensure the integrity and correctness of metadata information; users who can operate and maintain data in various systems at the headquarters can be classified as source system business personnel; users who can handle data business at the branch level can be classified as branch business personnel; users who can subscribe to metadata can be classified as asset subscription users.

[0054] Furthermore, traditional data asset management methods often ignore the key factor of user behavior, which makes it impossible to accurately evaluate the value of data assets. Therefore, in addition to obtaining basic asset data, this application will also target users with metadata subscription behavior, that is, asset subscription users, and simultaneously obtain their user behavior data to comprehensively consider user behavior and other asset factors to achieve more scientific management of enterprise data assets.

[0055] Exemplarily, user behavior data can be collected through point-of-sale design. For example, in order to collect user behavior in an all-round way, the point-of-sale collection design diagram shown in Table 1 below can be used to record user clicks, searches, and browsing behaviors in modules oriented to general users such as metadata management, data asset display, and data lineage of the data governance platform.

[0056] Table 1

[0057]

[0058] Step 204: Perform a process analysis on the metadata subscription behavior based on the user behavior data to obtain evaluation data related to the metadata.

[0059] Specifically, the user behavior data obtained in the previous step is the user behavior data of the target user on the data platform, that is, the user behavior data obtained by recording the operation of users who have metadata subscription behavior. Then, the metadata subscription behavior in the above user behavior data can be analyzed to obtain evaluation data related to metadata, so as to predict which metadata the target user is more interested in, or identify the important features that affect the user's metadata subscription behavior, which can be further used as the basis for identifying key data assets in the enterprise.

[0060] Exemplarily, the evaluation data related to metadata include the search add-to-cart hit rate, which can be used to characterize the proportion of users who add to cart after searching for metadata, that is, the ratio of the number of times users actually perform add-to-cart operations after searching to the total number of searches, which can be used to evaluate whether the search function for metadata on the data platform is effective, and the strength of the user's subscription intention after searching. Correspondingly, the way to perform process analysis on metadata subscription behavior can be to perform path analysis on the user behavior data of asset subscription users, and calculate it according to their operation sequence on the data platform.

[0061] Exemplarily, the evaluation data related to metadata include the purchase conversion rate, which can be used to characterize the ratio between the number of metadata that are purchased and subscribed to in the same data set and the number of metadata that are operated in other steps in the same data set during the statistical period, and can be used to reflect the attractiveness of the metadata in the data set to users and the conversion efficiency of potential subscription behavior. Correspondingly, the process analysis of metadata subscription behavior can be performed by performing a funnel analysis on the user behavior data of asset subscription users, and calculating the conversion rate based on the number of metadata in the basic stage before the metadata is subscribed.

[0062] Step 206, perform value assessment using the basic asset data and the assessment data related to the metadata to obtain value data of each metadata. The value data of each metadata is used to identify key data assets.

[0063] Specifically, the basic asset data and user behavior data obtained above, as well as the evaluation data related to metadata obtained from the previous step, can be integrated to form a comprehensive data set containing user behavior and asset information, and then the comprehensive data set can be mined through machine learning methods, and prediction and identification can be performed based on the preset analysis model to obtain the important features that affect the user's additional purchase behavior, namely the core feature data. Then, the asset value evaluation formula is set based on the core feature data, and the value of each metadata is estimated to obtain the value data of each metadata.

[0064] Furthermore, after obtaining the value data of each metadata, the identification rules of high-value assets can be defined according to the fields and data asset types that users are most interested in, and used to output the coordinates of high-value key data assets. The key data assets can be output by finding their specific locations in the database based on the blood relationship of the data assets. The blood relationship of the data assets is used to characterize which core library the metadata comes from and which data source the data of the core library comes from, that is, to establish the association relationship between the metadata and the data resource list.

[0065] Among them, the coordinates of the high-value key data assets outputted above can provide other data asset optimization suggestions, such as data integration and quality improvement measures. Data integration can be, for example, there are highly overlapping metadata fields between data sets A and B, but based on the above analysis, it is identified that data set A belongs to key data assets, and then data set B can be integrated into data set A to make the database clearer and easier to store and manage. Quality improvement can be, for example, after identifying that data set A belongs to key data assets, data set A can be analyzed for quality from multiple dimensions to ensure the accuracy, completeness and consistency of data set A, so that data sets are more valuable. Quality analysis methods can be, for example: offset, non-empty check, value range check, standardization check, repeatability check, association check, outlier check, fluctuation check, etc. Further, big data related technologies can be combined to ensure detection performance and reduce the performance impact on business systems, such as Hadoop, MapReduce, HBase, etc.

[0066] The above data asset management method obtains the basic asset data and the user behavior data of the target user on the data platform, where the target user is a user with metadata subscription behavior; then the metadata subscription behavior is analyzed according to the user behavior data to obtain the evaluation data related to the metadata; finally, the value evaluation is performed through the basic asset data and the evaluation data related to the metadata to obtain the value data of each metadata, and the value data of each metadata is used to identify key data assets. This application helps enterprises identify key data assets, optimize data usage strategies, and enhance the overall value of data assets by combining user behavior data as a key influencing factor.

[0067] In an exemplary embodiment, Figure 3 As shown, step 204 includes the following steps 302 to 304. Among them:

[0068] Step 302: extracting operation path data of metadata subscription behavior from user behavior data.

[0069] Specifically, the user behavior data records the operation sequence of the user in the data platform during the metadata subscription process, and the operation path data from finding assets to subscribing can be viewed. For example, the operation path data corresponding to a metadata subscription behavior is: search keyword "cntr" -> click table "k_cntr" -> click table "d_cntr" -> click table "f_cntr" -> order table "f_cntr".

[0070] It can be understood that when there are multiple metadata subscription behaviors in the user behavior data, there are also multiple corresponding operation path data, and each operation path data corresponds to the operation sequence in the process of a certain metadata being subscribed.

[0071] Step 304: Calculate the search add-to-cart hit rate based on the operation path data.

[0072] Specifically, after obtaining the operation path data, the search and add-to-cart hit rate of the metadata corresponding to the operation path data can be calculated based on the total number of metadata clicked by the user in the operation path data. Then, the search and add-to-cart hit rates of the same metadata are averaged to obtain the search and add-to-cart hit rate corresponding to the metadata.

[0073] For example, the operation path data corresponding to the above metadata subscription behavior is: search keyword "cntr" -> click table "k_cntr" -> click table "d_cntr" -> click table "f_cntr" -> order table "f_cntr". The total number of tables clicked by the user (the number of metadata) is 3, and the search and purchase hit rate of the order table "f_cntr" in this path is: 1 / total number of tables = 1 / 3*100%=33%. Furthermore, the final search and purchase hit rate of the order table "f_cntr" is the average of the search and purchase hit rates of the order table "f_cntr" in all operation path data.

[0074] In this embodiment, search generally refers to the behavior of users searching for metadata of interest through keywords or phrases, and add-to-cart refers to the behavior of users adding the selected metadata to their subscription list, which is generally regarded as a manifestation of purchase intention. By calculating the search and add-to-cart hit rate, the strength of the user's subscription intention for metadata after the search can be understood, which can not only optimize the search algorithm, but also provide suggestions for improving the quality of metadata, and effectively optimize the use strategy of data assets.

[0075] In an exemplary embodiment, Figure 4 As shown, step 204 includes the following steps 402 to 404. Among them:

[0076] Step 402: Filter the user behavior data to obtain target user behavior data corresponding to metadata belonging to the same data set.

[0077] Specifically, user behavior data records the process of executing metadata subscription behavior, so that each piece of user behavior data can be known, corresponding to which metadata subscription behavior is generated. Then, the metadata can be filtered according to the data set to which it belongs, and the target user behavior data corresponding to the metadata belonging to the same data set can be obtained.

[0078] It can be understood that the target user behavior data includes user behavior data corresponding to at least one data set.

[0079] Step 404: Perform funnel analysis on the target user behavior data to obtain the purchase conversion rate during the metadata subscription process.

[0080] Specifically, the process of a user subscribing to metadata may include multiple basic stages, for example, based on the order of operations, it may include: browsing stage, adding to cart stage, ordering stage, completion stage, and sharing stage, etc. It is understandable that there may be user loss from each stage to the next stage. For example, after a user has browsed 800 metadata, he may only purchase 500 of them, further share 300 of them, and finally place an order for 250 of them. The number of metadata that may be paid for may be reduced to 200.

[0081] Furthermore, funnel analysis can be performed on the target user behavior data. By tracking user behavior data, the user's subscription path can be broken down into a series of basic stages, and the conversion rate of each stage in the metadata subscription process can be obtained to discover problems in the conversion process and provide analytical suggestions for optimizing the conversion rate.

[0082] In an exemplary embodiment, Figure 5 As shown, step 404 includes the following steps 502 to 506. Among them:

[0083] Step 502 , based on the basic path of the metadata subscription behavior, multiple basic stages are obtained, wherein the basic stage includes an add-to-purchase stage.

[0084] Specifically, the path of the metadata subscription behavior performed by the user is tracked, from the user accessing the data platform to adding metadata to the final successful payment. The entire process can be broken down into multiple key steps, such as: browsing stage, adding to purchase stage, ordering stage and completion stage, which may also include branch stages. For example, after the browsing stage, it may also include a sharing stage and an information filling stage.

[0085] Furthermore, based on the different contents of each metadata, there may be different basic paths for its subscription behavior, which can also be divided into multiple basic stages. However, among the multiple basic stages, all metadata subscription behaviors should include the add-to-purchase stage, which is usually regarded as a manifestation of subscription intention.

[0086] Step 504: extract the metadata quantity corresponding to each basic stage from the target user behavior data.

[0087] Specifically, after multiple basic stages are obtained, the number of metadata corresponding to each basic stage can be counted in combination with the obtained target user behavior data. The following Table 2 shows the number of metadata corresponding to each basic stage obtained in an example.

[0088] Table 2

[0089]

[0090] Step 506, calculating based on the metadata quantity corresponding to each basic stage, to obtain the add-to-cart conversion rate corresponding to the add-to-cart stage.

[0091] Specifically, the conversion rate corresponding to each basic stage can be calculated based on the following conversion rate formula, which is: conversion rate = current layer event conversion data volume / upper layer event conversion data volume.

[0092] The add-to-cart conversion rate corresponding to the add-to-cart stage may refer to the conversion rate of the add-to-cart stage as a current-level event, or may refer to the conversion rate of the add-to-cart stage as a higher-level event.

[0093] For the data example shown in Table 2 above, the conversion rate can be calculated as follows: browse metadata → add to shopping cart: 500 / 800×100%=62.5%; add data to cart → start checkout: 300 / 500×100%=60%; share data → fill in information: 250 / 300×100%=83.3%; place an order for data → complete payment: 200 / 250×100%=80%.

[0094] In this embodiment, by using funnel analysis, a very effective data analysis method, on user behavior data, the entire metadata subscription behavior conversion process can be visualized, thereby helping to better understand user behavior and needs, improve metadata quality, provide suggestions, and effectively optimize the use strategy of data assets.

[0095] In an exemplary embodiment, Figure 6 As shown, step 206 includes the following steps 602 to 604. Among them:

[0096] Step 602, performing correlation analysis based on the basic asset data and the evaluation data related to the metadata to obtain core feature data.

[0097] Specifically, correlation analysis refers to integrating the basic asset data with the user behavior data as a whole data set, and then performing data mining on this whole data set through a machine learning algorithm to predict which metadata in the basic asset data the target users are more interested in, or to identify which features in the basic asset data affect the user's metadata subscription behavior, which can be further used as a basis for identifying key data assets in the enterprise.

[0098] It can be understood that the core feature data can be used to characterize which important features will affect users when they subscribe to metadata, and in which areas of basic asset data users are interested.

[0099] In an exemplary embodiment, Figure 7As shown, step 602 includes the following steps 702 to 706. Among them:

[0100] Step 702, integrating the basic asset data and the evaluation data related to the metadata to form a comprehensive evaluation data set.

[0101] Specifically, the process of integrating the two can be to first create a new data set in the database and name it the comprehensive evaluation data set. Then extract the basic asset data from the database and store it in the comprehensive evaluation data set. At the same time, the user behavior data obtained and the evaluation data related to the metadata obtained by the above steps are also stored in the comprehensive evaluation data set.

[0102] Step 704, extract and derive features from the basic asset data and the evaluation data related to the metadata to obtain a plurality of basic features.

[0103] Specifically, the comprehensive evaluation data set can be first subjected to feature extraction, that is, the features that can be used to evaluate the value of metadata can be preliminarily screened. For example, for user-related features, the features that can be extracted include: user ID, department, position, and group. For asset-related features, the features that can be extracted include: metadata ID, data type, click volume, field, purchase conversion rate, field note coverage, and data standard coverage. Among them, the field note coverage represents the ratio of the number of data in the data table that annotates the field to the number of data in the entire table; the data standard coverage represents the ratio of the number of data in the data table that has data standards to the number of data in the entire table. For features related to user subscription behavior, the features that can be extracted include: the number of purchases, the date of the most recent purchase, and the frequency of purchases.

[0104] Furthermore, after the features that can be used to evaluate the value of metadata are initially screened, other features that can be used to evaluate the value of metadata can be further derived based on the above features. For example, the usage frequency feature can be derived by calculating the number of times the user uses each data set. The activity feature can also be derived by calculating the user's activity score based on the time series data of the purchase behavior. The field preference feature can also be derived by counting the number of times the user purchases data sets in different fields to form a preference matrix.

[0105] The basic features may include the features that are initially screened and used to evaluate the value of metadata in the above process, as well as other features that are further derived and used to evaluate the value of metadata.

[0106] Step 706, extracting basic data corresponding to each basic feature from the comprehensive evaluation data set, and performing prediction and identification according to a preset analysis model to obtain core feature data.

[0107] Specifically, after obtaining multiple basic features, it is necessary to extract the basic data corresponding to each basic feature from the comprehensive evaluation data set as the training set for the preset analysis model.

[0108] In order to obtain different core feature data, multiple preset analysis models can be designed. For example, in order to predict the user's interest in a specific data set, a first preset analysis model can be designed based on a logistic regression algorithm. In order to identify important features that affect user subscription behavior, a second preset analysis model can be designed based on a random forest algorithm.

[0109] Furthermore, after the first preset analysis model and the second preset analysis model are trained by the training set, prediction and identification can be performed based on the trained models to obtain core feature data. For example, based on the first preset analysis model, the interest level of all current users of the platform in a data set containing a certain metadata can be predicted. Based on the second preset analysis model, the important features that affect the user's subscription behavior for a certain metadata can also be identified.

[0110] Step 604: estimate the value of each metadata based on the core feature data to obtain value data of each metadata.

[0111] Specifically, after obtaining the core feature data, a weight value can be set for the core feature data, and the core feature data and its weight value can be combined to form a preset asset value assessment formula for estimating the value of the metadata, so as to calculate the value data of each metadata.

[0112] Taking the important features that affect the user's subscription behavior for a certain metadata identified by the second preset analysis model as follows: search add-to-cart hit rate, add-to-cart conversion rate, field note coverage rate and data standard coverage rate as an example, the value data of the metadata can be calculated according to the following formula:

[0113] R(k)=(Aa+Dd)e+Bb+Cc

[0114] Among them, R(k) is the value data of metadata k, the add-to-cart conversion rate of metadata k is a, the corresponding weight of the add-to-cart conversion rate is A (0-100), the field note coverage rate is b, the weight of the field note coverage rate is B (0-100), the data standard coverage rate is c, the weight of the data standard coverage rate is C (0-100), the search add-to-cart hit rate of metadata k is d, the weight of the search add-to-cart hit rate is D (0-100), and the average interest level of all current users on the platform in the data set where metadata k is located is e (0-1).

[0115] In a specific embodiment, Figure 8As shown, an asset value collection and analysis system is provided. Specifically, the asset value collection and analysis system can be used to analyze and process various data information in the data platform to output the coordinates of high-value assets in the platform. Among them, the data acquisition module comprehensively collects various behavioral information of users in data interaction, such as visit frequency, residence time, number of orders, operation paths, etc. through point-of-sale technology. The data analysis engine module is used to group enterprise users, perform path analysis on the behavioral data of business personnel and data developers, perform funnel analysis on their data purchase behavior, and perform correlation analysis in combination with asset data to find their areas of concern and data assets. Define high-value asset identification rules, and automatically output high-value asset coordinates in combination with data analysis results. Finally, based on the analysis results, data asset optimization suggestions can be provided to enterprises, such as data integration, quality improvement and other measures.

[0116] In this embodiment, through in-depth mining of user behavior data, enterprises are helped to identify key data assets, optimize data usage strategies, and enhance the overall value of data assets.

[0117] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0118] Based on the same inventive concept, the embodiment of the present application also provides a data asset management device for implementing the data asset management method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more data asset management device embodiments provided below can refer to the limitations on the data asset management method above, and will not be repeated here.

[0119] In an exemplary embodiment, Fig. 9 As shown, a data asset management device is provided, including: an acquisition module 101, an analysis module 102 and an evaluation module 103, wherein:

[0120] An acquisition module 101 is used to acquire basic asset data and user behavior data of a target user on a data platform, where the target user is a user who has metadata subscription behavior;

[0121] An analysis module 102, configured to perform a process analysis on the metadata subscription behavior according to the user behavior data to obtain evaluation data related to the metadata;

[0122] The evaluation module 103 is used to perform value evaluation based on the basic asset data and the evaluation data related to the metadata to obtain value data of each metadata. The value data of each metadata is used to identify key data assets.

[0123] In an exemplary embodiment, the evaluation data associated with the metadata includes a search add-to-cart hit rate;

[0124] The analysis module 102 is further used to extract the operation path data of the metadata subscription behavior from the user behavior data; and calculate the search and add-to-cart hit rate based on the operation path data.

[0125] In an exemplary embodiment, the evaluation data associated with the metadata includes an add-to-cart conversion rate;

[0126] The analysis module 102 is further used to filter out target user behavior data corresponding to metadata belonging to the same data set from the user behavior data; perform funnel analysis on the target user behavior data to obtain the purchase conversion rate during the metadata subscription process.

[0127] In an exemplary embodiment, the analysis module 102 is further used to divide the basic path of the metadata subscription behavior into multiple basic stages, wherein the basic stage includes the add-to-cart stage; extract the number of metadata corresponding to each basic stage from the target user behavior data; and calculate based on the number of metadata corresponding to each basic stage to obtain the add-to-cart conversion rate corresponding to the add-to-cart stage.

[0128] In an exemplary embodiment, the evaluation module 103 is further used to perform correlation analysis based on the basic asset data and the evaluation data related to the metadata to obtain core feature data; and to estimate the value of each metadata based on the core feature data to obtain value data of each metadata.

[0129] In an exemplary embodiment, the evaluation module 103 is also used to integrate the basic asset data and the evaluation data related to the metadata to form a comprehensive evaluation data set; perform feature extraction and derivation on the basic asset data and the evaluation data related to the metadata to obtain multiple basic features; extract the basic data corresponding to each basic feature from the comprehensive evaluation data set, and perform prediction and identification according to a preset analysis model to obtain core feature data.

[0130] Each module in the above data asset management device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0131] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.10 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store basic asset data and user behavior data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a data asset management method is implemented.

[0132] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0133] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0134] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0135] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0136] It should be noted that the basic asset data and user behavior data and other information involved in this application (including but not limited to user device information, user personal information, etc.), as well as various data obtained by data processing based on the above information (including but not limited to data used for analysis, stored data, displayed data, etc.), are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0137] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0138] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0139] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A data asset management method, characterized in that: The method comprises: Obtaining basic asset data and user behavior data of target users on the data platform, where the target users are users who have metadata subscription behavior; Performing a process analysis on the metadata subscription behavior according to the user behavior data to obtain evaluation data related to the metadata; The value assessment is performed through the basic asset data and the assessment data related to the metadata to obtain the value data of each metadata, and the value data of each metadata is used to identify key data assets.

2. The method according to claim 1, characterized in that The evaluation data related to the metadata includes the search add-to-cart hit rate; Performing a process analysis on the metadata subscription behavior according to the user behavior data to obtain evaluation data related to the metadata, including: Extracting operation path data of the metadata subscription behavior from the user behavior data; The search and add-to-cart hit rate is calculated based on the operation path data.

3. The method according to claim 2, characterized in that The evaluation data related to the metadata includes the add-to-cart conversion rate; Performing a process analysis on the metadata subscription behavior according to the user behavior data to obtain evaluation data related to the metadata, including: Filtering the user behavior data to obtain target user behavior data corresponding to metadata belonging to the same data set; Funnel analysis is performed on the target user behavior data to obtain the add-to-cart conversion rate during the metadata subscription process.

4. The method according to claim 3, characterized in that The funnel analysis of the target user behavior data to obtain the purchase conversion rate during the metadata subscription process includes: Based on the basic path of the metadata subscription behavior, multiple basic stages are obtained, wherein the basic stage includes an add-to-purchase stage; Extracting the metadata quantity corresponding to each of the basic stages from the target user behavior data; A calculation is performed based on the quantity of metadata corresponding to each of the basic stages to obtain an add-to-cart conversion rate corresponding to the add-to-cart stage.

5. The method according to any one of claims 1 to 4, characterized in that: The step of performing value assessment on the basic asset data and the assessment data related to the metadata to obtain value data of each metadata includes: Performing correlation analysis based on the basic asset data and the evaluation data related to the metadata to obtain core feature data; The value of each metadata is estimated based on the core feature data to obtain value data of each metadata.

6. The method according to claim 5, characterized in that The performing of correlation analysis based on the basic asset data and the evaluation data related to the metadata to obtain core feature data includes: Integrate the basic asset data and the evaluation data related to the metadata to form a comprehensive evaluation data set; Extracting and deriving features from the basic asset data and the evaluation data related to the metadata to obtain a plurality of basic features; The basic data corresponding to each of the basic features is extracted from the comprehensive evaluation data set, and prediction and identification are performed according to a preset analysis model to obtain core feature data.

7. A data asset management device, characterized in that: The device comprises: An acquisition module is used to acquire basic asset data and user behavior data of target users on the data platform, where the target users are users who have metadata subscription behavior; An analysis module, used to perform a process analysis on the metadata subscription behavior according to the user behavior data to obtain evaluation data related to the metadata; The evaluation module is used to perform value evaluation based on the basic asset data and the evaluation data related to the metadata to obtain the value data of each metadata, and the value data of each metadata is used to identify key data assets.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images