A method and device for evaluating audit data value

Abstract

The present invention relates to an audit data value evaluation method and device, the method comprising: constructing an audit data rule base; marking source attributes to which data type information belongs; constructing a data value to-be-evaluated set; based on an audit data value evaluation system, matching and comparing the data value to-be-evaluated set with rules of corresponding types in the audit data rule base, obtaining a score for each influencing factor, calculating the weight of each influencing factor, and calculating the audit data value evaluation result. When constructing the audit data rule base, the present invention comprehensively considers data dictionaries, national standards, local standards, industry standards, and expert knowledge bases, integrates subjective evaluation with objective evaluation, and evaluates the audit data value based on four influencing factors: data quality, data intrinsic value, data application value, and market value, thereby obtaining an evaluation result with high accuracy and comprehensiveness.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an audit data value evaluation method and device. Background Art

[0002] Audit data is data that is spontaneously generated, collected, maintained, managed, and owned during the long-term operation of the audit object. The data sources involved in the audit mainly include the internal management systems, financial systems, business systems of the audit objects such as enterprises, institutions, and individuals, as well as external data sources (such as public databases, third-party data providers, etc.). Audit data types include structured data (such as tables, databases) and unstructured data (such as text, pictures, audio, video, etc.). The content carried by audit data covers the financial records, transaction information, business activities, internal control and other related information of the audit object. As an important component of data resources, audit data plays an indispensable enabling role in improving government governance capabilities, improving and safeguarding people's livelihood services, and cultivating new momentum for economic development.

[0003] Currently, data value assessment generally adopts economic value method, decision value method, cost value method, strategic value method, expert evaluation method, etc. As for the value of audit data in the audit field, there is no mature audit data value evaluation method in the industry.

[0004] Therefore, how to improve the accurate and comprehensive evaluation of the value of audit data is a problem that technical personnel in this field need to solve. Summary of the Invention

[0005] Based on this, it is necessary to provide an audit data value evaluation method and equipment to address the above technical issues.

[0006] To achieve the above objectives, the present invention provides a method for evaluating the value of audit data, comprising:

[0007] Step 1: Obtain the data dictionary of the target database and build an audit data rule library based on the data dictionary of the target database and with reference to national standards, local standards, industry standards and expert knowledge base;

[0008] Step 2: Obtain the audit data to be evaluated from the target database, use a hash table to perform pre-check on the database table of the audit data to be evaluated, identify the data type information and file structure information contained in the audit data to be evaluated, and mark the source attribute to which the data type information belongs;

[0009] Step 3: Load the audit data to be evaluated based on the marked source attributes, use a bidirectional long short-term memory network to perform named entity recognition on the audit data to obtain the named entity information of the audit data to be evaluated, perform format screening, duplicate checking, and key information extraction on the audit data to obtain key quality characteristic information, and construct a data value evaluation set based on the source attributes, file structure information, named entity information, and key quality characteristic information;

[0010] Step 4: Based on the four influencing factors of data quality, data intrinsic value, data application value and market value, an audit data value evaluation system is constructed. Based on the audit data value evaluation system, the data value set to be evaluated is matched and compared with the corresponding types of rules in the audit data rule library to obtain the score of each influencing factor. The hierarchical analysis method is used to calculate the weight of each influencing factor. The score of each influencing factor and the weight of each influencing factor are input into the audit data value evaluation model to calculate the audit data value evaluation result.

[0011] Optionally, the data dictionary includes: definition and description information of target database objects, attribute information of target database objects, association relationships of target database objects, target database users and authority information, and parameters and configuration information of the target database.

[0012] Optionally, in step 2, a hash table is used to perform a pre-check of the library table on the audit data to be evaluated, to identify the data type information and file structure information contained in the audit data to be evaluated, and to mark the source attribute to which the data type information belongs, including:

[0013] NLP technology is used to identify the data type and length of the table header items and the first five non-blank rows of the audit data to be evaluated, and the data type information contained in the audit data to be evaluated is obtained. OCR technology is used to perform structured recognition on the audit data to be evaluated, and the file structure information contained in the audit data to be evaluated is obtained. The identified content is then spliced ​​with the file name of the audit data to be evaluated to obtain spliced ​​data. The spliced ​​data is then converted into character format and converted into a character vector or a string scalar. The MD5 algorithm is used to calculate the hash value, and the source attribute to which the data type information belongs is marked by matching and comparing with the hash value of the stored source attribute.

[0014] Optionally, in step 3, the audit data to be evaluated is loaded according to the marked source attributes, and a bidirectional long short-term memory network is used to perform named entity recognition on the audit data to be evaluated to obtain named entity information of the audit data to be evaluated, including:

[0015] The audit data to be evaluated is loaded according to the marked source attributes, and data cleaning is performed on the audit data to obtain the cleaned named data information. A bidirectional long short-term memory network is used to perform named entity recognition on the cleaned named data information to obtain the named entity information of the audit data to be evaluated.

[0016] Optionally, in step 4, the factors affecting data quality include six secondary factors: accuracy, completeness, consistency, accessibility, standardization and timeliness; the factors affecting data intrinsic value include four secondary factors: data scale, data frequency, data structure and data granularity; the factors affecting data application value include five secondary factors: user visits, user browsing or downloading volume, proportion of business data, proportion of field or subject data and proportion of industry data; the factors affecting market value include five secondary factors: data scarcity, external data cooperation, proportion of data with high download rate, expected social value benefits and expected economic value benefits.

[0017] Optionally, in step 4, based on the audit data value evaluation system, the data value set to be evaluated is matched and compared with the rules under the corresponding attributes in the audit data rule library to obtain a score for each influencing factor, including:

[0018] According to the marked source attributes, the data value set to be evaluated is matched and compared with the corresponding types of rules in the audit data rule library. Based on the four influencing factors of data quality, data intrinsic value, data application value and market value, the error rate and score of the data information contained in the data value set to be evaluated under each influencing factor are calculated to obtain the score of each influencing factor.

[0019] Optionally, the calculation formula of the audit data value evaluation model is as follows:

[0020]

[0021] The constraints are: , V is the audit data value score, Q is the data quality score, N is the data intrinsic value score, A is the data application value score, and M is the market value score. is the weight of data quality, is the weight of the intrinsic value of data, is the weight of data application value, The weight of data application value.

[0022] The present invention also provides an audit data value evaluation device, comprising:

[0023] Data dictionary acquisition module, used to obtain the data dictionary of the target database;

[0024] The audit data rule base construction module is used to construct the audit data rule base based on the data dictionary of the target database and with reference to national standards, local standards, industry standards and expert knowledge base;

[0025] The audit data acquisition and pre-detection module is used to obtain the audit data to be evaluated from the target database, use a hash table to perform pre-detection of the database table on the audit data to be evaluated, identify the data type information and file structure information contained in the audit data to be evaluated, and mark the source attribute to which the data type information belongs;

[0026] The named entity recognition module is used to load the audit data to be evaluated according to the marked source attributes, and use a bidirectional long short-term memory network to perform named entity recognition on the audit data to be evaluated to obtain the named entity information of the audit data to be evaluated;

[0027] The data processing module is used to perform format screening, duplicate checking, and key information extraction on the audit data to be evaluated, and obtain key quality characteristic information;

[0028] The data set construction module is used to construct a data value evaluation set based on source attributes, file structure information, named entity information and key quality characteristics information;

[0029] Audit data value evaluation system construction module, which is used to build an audit data value evaluation system based on four influencing factors: data quality, data intrinsic value, data application value and market value;

[0030] The matching and comparison module is used to match and compare the data value set to be evaluated with the corresponding types of rules in the audit data rule library based on the audit data value evaluation system to obtain the score of each influencing factor;

[0031] The weight calculation module is used to calculate the weight of each influencing factor using the hierarchical analysis method;

[0032] The data value evaluation module is used to input the score of each influencing factor and the weight of each influencing factor into the audit data value evaluation model to calculate the audit data value evaluation results.

[0033] The present invention also provides a computer device, comprising: a processor, wherein the processor is configured to implement the steps of any of the above methods when executing a computer program stored in a memory.

[0034] The present invention also provides a computer-readable storage medium having computer instructions stored thereon, which implement the steps of any of the above methods when executed by a processor.

[0035] The advantages and beneficial effects of the present invention are as follows: the present invention provides an audit data value evaluation method and device, which is based on the audit data value evaluation model, combines NLP technology, OCR technology, MD5 algorithm and bidirectional long short-term memory network, and specifically constructs a data value to be evaluated set with source attributes. According to the source attributes of the audit data to be evaluated, the rules of corresponding types are matched and compared in the audit data rule library, and the four influencing factors of data quality, data intrinsic value, data application value and market value are comprehensively considered to obtain a score for each influencing factor, and the weight of each influencing factor is calculated by using the hierarchical analysis method to obtain the audit data value evaluation result. When constructing the audit data rule library, this method comprehensively considers the data dictionary, national standards, local standards, industry standards and expert knowledge base, integrates subjective evaluation with objective evaluation, and evaluates the audit data value based on the four influencing factors of data quality, data intrinsic value, data application value and market value, thereby obtaining an evaluation result with high accuracy and comprehensiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a flow chart of a method for evaluating the value of audit data according to an embodiment of the present invention;

[0037] Figure 2 Schematic diagram of the structure of an audit data value evaluation device in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below through specific embodiments in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0039] To facilitate understanding of this embodiment, the embodiment of the present invention is described in detail below.

[0040] Example 1

[0041] Figure 1 This is a flowchart of a method for evaluating the value of audit data provided in Example 1 of the present invention.

[0042] refer to Figure 1 , the evaluation method comprises the following steps:

[0043] S1. Obtain the data dictionary of the target database, and build an audit data rule library based on the data dictionary of the target database and with reference to national standards, local standards, industry standards and expert knowledge base.

[0044] In this embodiment, in order to build an audit data rule base, it is first necessary to obtain the data dictionary of the target database, which mainly contains the following information: definition and description information of target database objects, attribute information of target database objects, association relationships of target database objects, target database users and permission information, parameters and configuration information of the target database, etc.

[0045] It should be understood that the data dictionary is an important component of the target database. It is mainly used to store a collection of various objects in the target database, including the definition and description information of all objects in the target database. The objects here are also audit data. The data dictionary can help users understand the various objects and data structures in the target database, as well as the relationships and associations between them.

[0046] Among them, the definition and description information of the target database objects include but are not limited to tables, views, indexes, stored procedures, etc.; the attribute information of the target database objects include but are not limited to the object name, type, size, creation time, modification time, etc.; the association relationships of the target database objects include but are not limited to the relationship between tables, the relationship between views and tables, the relationship between indexes and tables, etc.; the target database user and permission information includes but is not limited to the user name, role, permission, etc.; the target database parameter and configuration information includes but is not limited to the database name, character set, time zone, etc.

[0047] In this embodiment, an audit data rule base is constructed with reference to national standards, local standards, industry standards, and an expert knowledge base. Specifically, a data dictionary of audit data is obtained, and evaluation rules for audit data with different source attributes are determined with reference to national standards, industry standards, and the standards of the province to which the city belongs or the local standards of the city. Expert knowledge resources are then aggregated to form an expert knowledge base. The evaluation rules involved in the expert knowledge base are primarily formulated based on the various secondary influencing factors in the audit data value evaluation system. The audit data rule base is then constructed by comprehensively considering national standards, industry standards, the standards of the province to which the city belongs or the local standards of the city, and the expert knowledge base.

[0048] In this embodiment, the audit data rule base includes pre-rules, basic rules, business rules and intelligent rules; the pre-rules include database naming rules and database structure rules, which are used to detect whether the database naming and database structure comply with the pre-specifications of audit data quality evaluation; the basic rules include audit data format rules, which are used to detect format quality problems of audit data; the business rules include general rules and scope of use rules, which are used to detect whether the general identification data and scope of use data of audit data comply with the general rules and scope of use rules established by national standards, local standards and industry standards; the intelligent rules include data feature rules, usage scenario rules, business model rules, supply and demand relationship rules, application risk rules and association verification rules, which are used to detect the specific data feature information, application scenarios, business models, market supply and demand relationships, risk factors and the degree of logical association matching between audit data and users and / or other data and / or business applications.

[0049] Among them, the pre-rules involved in the present invention are mainly used to detect whether the naming and structure of the database meet the pre-specifications of the audit data quality evaluation; the basic rules are mainly used to detect the general format quality problems of the audit data (such as missing data and duplicate data, etc.) without the help of national standards, industry standards and local standards; business rules are mainly data quality rules established according to national, industry and local standards, and are composed of general rules (such as unified credit code, organization code, certificate number representing personal identity, mobile phone number and email address, etc., and general identification data validation rules) and usage scope rules, among which the usage scope represents the breadth of data application, including industries, fields and regions. Domain, industry refers to the industry to which data can be applied, field refers to the field and application scenario to which data can be applied, and region refers to the area to which data can be applied, such as administrative divisions. It should be understood that: if the scope of data use is larger, the data utilization rate will be higher, thereby creating more economic benefits and the value of data assets will be higher. However, there are exceptions. If the scope of data use is small but the degree of professionalism is high, the data will also have higher value. Therefore, the data use scope rules need to be combined with the data user to analyze the data asset value; intelligent rules mainly include: data feature rules, usage scenario rules, business model rules, supply and demand relationship rules, application risk rules and association verification rules, among which data features Rules refer to the objective description of data asset objects, including information such as data attributes and data scale. Data attribute information includes data source, data type and data activity, and data scale information includes data volume, growth rate and update rate. Usage scenarios refer to the usage described from multiple dimensions such as data usage, data openness and data usage frequency in specific audit application scenarios. Business models refer to the profit model of secondary development with audit data assets as the core, including data product and service models, empowerment models and financial models. It should be understood that the same data assets will have different values ​​due to their different usage scopes, usage scenarios and business models. The supply and demand relationship analyzes the asset value of data from the perspective of market supply and demand. Data scarcity is measured by the supply quantity of a certain type of data in the market and the number of suppliers. In the data source market, if the supply quantity or the number of suppliers of a certain type of data is scarce, then the value of its data asset will be higher. Value density further measures the effectiveness of data supply. Market size is measured by the amount of market demand. Data relevance includes the degree of logical association between data and users, such as the association between information retrieval results and the user's expected search topic, the association between data and data with logical relationships, and the association between data and business application implementation.It should be understood that in data applications, the higher the data's relevance, the greater the value it creates with other data assets. When data is used for decision support, it is often necessary to integrate data from different information systems. The higher the data's relevance, the more efficient its integration and utilization, and the higher the value of the data assets it embodies. Risk factors influence the risk-return ratio and discount rate, including management risk, circulation risk, data security risk, and supervisory risk. Specific factors can be determined by referring to the results of the data security risk assessment report.

[0050] S2. Obtain the audit data to be evaluated from the target database, use a hash table to perform a pre-check on the database table of the audit data to be evaluated, identify the data type information and file structure information contained in the audit data to be evaluated, and mark the source attribute to which the data type information belongs.

[0051] In this embodiment, the source attribute of the present invention is to classify audit data according to the line classification method specified in Section 6.2 of "Basic Principles and Methods of Information Classification and Coding" (GB / T 7027-2002). That is, the audit data is divided into several levels based on its information source characteristics, and each level is further divided into several categories. Categories at the same level in the same branch form a parallel relationship, and categories at different levels form a subordinate relationship.

[0052] It should be understood that there are a large amount of audit data in the target database involved in the present invention, and the audit data to be evaluated only belongs to one type.

[0053] In this embodiment, a hash table is used to perform pre-check on the audit data to be evaluated, identify the data type information and file structure information contained in the audit data to be evaluated, and mark the source attribute of the data type information accordingly, including:

[0054] NLP technology is used to identify the data type and length of the table header items and the first five non-blank rows of the audit data to be evaluated, and the data type information contained in the audit data to be evaluated is obtained. OCR technology is used to perform structured recognition on the audit data to be evaluated, and the file structure information contained in the audit data to be evaluated is obtained. The identified content is then spliced ​​with the file name of the audit data to be evaluated to obtain spliced ​​data. The spliced ​​data is then converted into character format and converted into a character vector or a string scalar. The MD5 algorithm is used to calculate the hash value, and the source attribute to which the data type information belongs is marked by matching and comparing with the hash value of the stored source attribute.

[0055] In this embodiment, NLP technology is used to process table header data to identify data type information of different types of audit data, and then OCR technology is used to perform structured recognition to obtain file structure information of different types of audit data. The data type information, file structure information and file name are then spliced ​​to obtain spliced ​​data, and the spliced ​​data is then converted into a character format that is convenient for MD5 algorithm operations, and then a hash value is calculated. By matching and comparing the calculated hash value with the hash value of the stored source attribute, the source attribute to which the data type information belongs is determined and marked.

[0056] S3. Load the audit data to be evaluated according to the marked source attributes, use a bidirectional long short-term memory network to perform named entity recognition on the audit data to be evaluated, obtain the named entity information of the audit data to be evaluated, perform format screening, duplicate checking and key information extraction on the audit data to be evaluated in turn, obtain key quality characteristic information, and construct a data value to be evaluated set based on source attributes, file structure information, named entity information and key quality characteristic information.

[0057] In this embodiment, the audit data to be evaluated is loaded according to the marked source attributes, and a bidirectional long short-term memory network is used to perform named entity recognition on the audit data to be evaluated, thereby obtaining named entity information of the audit data to be evaluated, including:

[0058] The audit data to be evaluated is loaded according to the marked source attributes, and data cleaning is performed on the audit data to obtain the cleaned named data information. A bidirectional long short-term memory network is used to perform named entity recognition on the cleaned named data information to obtain the named entity information of the audit data to be evaluated.

[0059] In this embodiment, the present invention adopts a bidirectional long short-term memory network (BiLSTM) to perform named entity recognition on the named data information of the audit data, so as to obtain the named entity information of the audit data to be evaluated, which is used for subsequent matching and comparison with the pre-rules in the audit data rule base.

[0060] In this embodiment, the audit data to be evaluated is subjected to format screening, duplication checking, and key information extraction to obtain key quality characteristic information, wherein format screening can adopt Excel format screening technology, the purpose of which is to detect incomplete data, erroneous data, and duplicate data, duplicate checking can adopt hash table duplication checking method, the purpose of which is to detect duplicate data, and key information extraction can adopt NLP technology to extract relevant key information, and the results obtained by the three processing methods are summarized to form key quality characteristic information (key quality characteristic information includes but is not limited to unified credit code, organization code, ID number representing personal identity, mobile phone number, email address, scope of use information, related information, feature information, application scenario, business model, market supply and demand relationship, risk factors, etc.).

[0061] In this embodiment, source attributes, file structure information, named entity information and key quality characteristic information are integrated, and a set of data values ​​to be evaluated with source attributes is specifically constructed.

[0062] S4. Based on the four influencing factors of data quality, data intrinsic value, data application value and market value, an audit data value evaluation system is constructed. Based on the audit data value evaluation system, the data value set to be evaluated is matched and compared with the corresponding types of rules in the audit data rule library to obtain the score of each influencing factor. The hierarchical analysis method is used to calculate the weight of each influencing factor. The score of each influencing factor and the weight of each influencing factor are input into the audit data value evaluation model to calculate the audit data value evaluation result.

[0063] In this embodiment, an audit data value evaluation system is constructed based on the four influencing factors of data quality, data intrinsic value, data application value and market value (as shown in Table 1 below). Among them, the data quality influencing factors include six secondary influencing factors of accuracy, completeness, consistency, accessibility, standardization and timeliness; the data intrinsic value influencing factors include four secondary influencing factors of data scale, data frequency, data structure and data granularity; the data application value influencing factors include five secondary influencing factors of user visits, user browsing or downloading volume, business data proportion, field or subject data proportion and industry data proportion; the market value influencing factors include five secondary influencing factors of data scarcity, external data cooperation, high download rate data proportion, expected social value benefits and expected economic value benefits.

[0064] Table 1 Audit data value evaluation system

[0065]

[0066] Among them, refer to Table 1 for the description of the secondary influencing factors in data quality (Q):

[0067] Normativity: The degree to which data conforms to data standards, data models, business rules, metadata, or authoritative reference data.

[0068] Completeness: The degree to which data elements are assigned values ​​as required by data rules.

[0069] Accuracy: The degree to which data accurately represents the true value of the real entity (actual object) it describes.

[0070] Consistency: The degree to which data does not contradict other data used in a specific context.

[0071] Timeliness: How accurate the data is over time.

[0072] Accessibility: The degree to which data can be accessed.

[0073] Description of each secondary influencing factor in the intrinsic value of data (N):

[0074] Data size: the number of data items stored in the database.

[0075] Data frequency: Monthly update rate of fields and / or daily update rate of fields.

[0076] Data structure: the proportion of structured data.

[0077] Data granularity: the proportion of district and county data.

[0078] Description of each secondary influencing factor in data application value (A):

[0079] User visits: Number of website visits and / or monthly visits.

[0080] Business data ratio: the ratio of data with business significance.

[0081] Proportion of domain or subject data: The proportion of data with clear domain or subject attributes.

[0082] Industry data proportion: the proportion of data with clear industry attributes.

[0083] Explanation of the secondary influencing factors in market value (M):

[0084] Data scarcity: scarcity of data fields and content.

[0085] External data cooperation: external data cooperation unit or amount of cooperation data.

[0086] High download rate data ratio: The proportion of data sets whose total download rate and download times exceed the preset threshold.

[0087] Expected social value benefits: the degree of improvement in convenience and / or satisfaction.

[0088] Expected economic value benefits: diversity of application scenarios and / or economic benefits achieved.

[0089] In this embodiment, based on the audit data value evaluation system, the data value set to be evaluated is matched and compared with the rules under the corresponding attributes in the audit data rule library to obtain a score for each influencing factor, including:

[0090] According to the marked source attributes, the data value set to be evaluated is matched and compared with the corresponding types of rules in the audit data rule library. Based on the four influencing factors of data quality, data intrinsic value, data application value and market value, the error rate and score of the data information contained in the data value set to be evaluated under each influencing factor are calculated to obtain the score of each influencing factor.

[0091] In this embodiment, according to the source attributes of the audit data to be evaluated, the corresponding types of rules are matched and compared in the audit data rule library to obtain the data detection results, and based on the four influencing factors of data quality, data intrinsic value, data application value and market value, the number of qualified data, number of abnormal data, error rate and score of the data information contained in the data value to be evaluated set under the four influencing factors are calculated to form a score for each influencing factor.

[0092] In this embodiment, the present invention adopts the hierarchical analysis method to determine the weight of each influencing factor. The basic idea of ​​the hierarchical analysis method is to transform the overall judgment of the weights of multiple dimensions that constitute a complex problem into a "two-by-two comparison" of these dimensions, and then transform it into a ranking judgment of the overall weights of these dimensions, and finally establish the weight of each dimension.

[0093] In this embodiment, the specific steps of using the hierarchical analysis method to calculate the weight of each dimension indicator are as follows:

[0094] (1) Based on the influencing factors at each level in the data value evaluation system, a hierarchical structure of influencing factors is constructed.

[0095] (2) Based on the hierarchical structure of influencing factors, the relative importance of each level of influencing factors in the data value evaluation system is assigned, a judgment matrix is ​​constructed, and the judgment matrix is ​​calculated. The maximum eigenvalue and eigenvector of are normalized to obtain the ranking weights of the relative importance of the influencing factors at the same level to the influencing factors at the previous level.

[0096] (3) Hierarchical single sorting and its consistency test,

[0097] Due to the influence of various subjective and objective factors, it is difficult for the judgment matrix to be strictly consistent. Therefore, after obtaining the characteristic roots, the consistency of the judgment matrix needs to be tested.

[0098] In order to test the consistency of the judgment matrix, it is necessary to calculate its consistency index CI, which is defined as: , when CI=0, the judgment matrix has complete consistency. The larger the CI, the worse the consistency of the judgment matrix. In order to test whether the judgment matrix has satisfactory consistency, it is also necessary to compare the CI with the average random consistency index RI. The value of the average random consistency index RI is shown in Table 2 below.

[0099] Table 2 The value of average random consistency index RI

[0100]

[0101] Considering that the deviation from consistency may be caused by random reasons, when checking whether the judgment matrix has satisfactory consistency, it is also necessary to compare CI and random consistency index RI to obtain the test coefficient CR, which is: ; Generally, if , then the judgment matrix is ​​considered to have passed the consistency test, otherwise it does not have satisfactory consistency. In addition, the pairwise comparisons between specific influencing factors are generally obtained by survey interviews and expert consultation methods, and then the judgment matrix is ​​constructed according to the importance of each influencing factor for calculation.

[0102] In this embodiment, the calculation formula of the audit data value evaluation model is as follows:

[0103]

[0104] The constraints are: , V is the audit data value score, Q is the data quality score, N is the data intrinsic value score, A is the data application value score, and M is the market value score. is the weight of data quality, is the weight of the intrinsic value of data, is the weight of data application value, The weight of data application value.

[0105] The present embodiment provides an audit data value evaluation method, comprising: obtaining a data dictionary of a target database, and constructing an audit data rule library based on the data dictionary of the target database with reference to national standards, local standards, industry standards and expert knowledge base; obtaining audit data to be evaluated in the target database, using a hash table to perform a pre-detection of the database table on the audit data to be evaluated, identifying the data type information and file structure information contained in the audit data to be evaluated, and correspondingly marking the source attributes to which the data type information belongs; loading the audit data to be evaluated according to the marked source attributes, using a bidirectional long short-term memory network to perform named entity recognition on the audit data to be evaluated, obtaining named entity information of the audit data to be evaluated, performing format screening, duplicate checking and key information extraction on the audit data to be evaluated in turn, obtaining key quality characteristic information, and constructing a data value to be evaluated set based on the source attributes, file structure information, named entity information and key quality characteristic information; and based on the four aspects of data quality, data intrinsic value, data application value and market value. Influencing factors are used to construct an audit data value evaluation system. Based on the audit data value evaluation system, the data value set to be evaluated is matched and compared with the corresponding types of rules in the audit data rule library to obtain the score of each influencing factor. The hierarchical analysis method is used to calculate the weight of each influencing factor. The score of each influencing factor and the weight of each influencing factor are input into the audit data value evaluation model to calculate the audit data value evaluation result. This implementation method is based on the audit data value evaluation model, combines NLP technology, OCR technology, MD5 algorithm and bidirectional long short-term memory network, and specifically constructs a data value set to be evaluated with source attributes. According to the source attributes of the audit data to be evaluated, the corresponding types of rules are matched and compared in the audit data rule library. The four influencing factors of data quality, data intrinsic value, data application value and market value are comprehensively considered to obtain the score of each influencing factor, and the hierarchical analysis method is used to calculate the weight of each influencing factor to obtain the audit data value evaluation result. When constructing the audit data rule base, this method comprehensively considers the data dictionary, national standards, local standards, industry standards and expert knowledge base, integrates subjective evaluation with objective evaluation, and evaluates the value of audit data based on four influencing factors: data quality, data intrinsic value, data application value and market value, thereby obtaining evaluation results with high accuracy and comprehensiveness.

[0106] Example 2

[0107] This embodiment provides an audit data value evaluation device 200 based on the above embodiment 1. Figure 2, used to implement the steps of an audit data value evaluation method described in the above embodiment 1, the device 200 mainly includes: a data dictionary acquisition module 201, an audit data rule base construction module 202, an audit data acquisition and pre-detection module 203, a named entity recognition module 204, a data processing module 205, a data set construction module 206, an audit data value evaluation system construction module 207, a matching comparison module 208, a weight calculation module 209 and a data value evaluation module 210, wherein,

[0108] A data dictionary acquisition module 201 is used to acquire a data dictionary of a target database;

[0109] The audit data rule base construction module 202 is used to construct an audit data rule base based on the data dictionary of the target database and with reference to national standards, local standards, industry standards and expert knowledge base;

[0110] The audit data acquisition and pre-check module 203 is used to obtain the audit data to be evaluated from the target database, perform pre-check on the database table of the audit data to be evaluated using a hash table, identify the data type information and file structure information contained in the audit data to be evaluated, and mark the source attribute to which the data type information belongs;

[0111] The named entity recognition module 204 is used to load the audit data to be evaluated according to the marked source attributes, and use a bidirectional long short-term memory network to perform named entity recognition on the audit data to be evaluated to obtain the named entity information of the audit data to be evaluated;

[0112] The data processing module 205 is used to sequentially perform format screening, duplicate checking, and key information extraction on the audit data to be evaluated to obtain key quality characteristic information;

[0113] The data set construction module 206 is used to construct a data value to be evaluated set based on source attributes, file structure information, named entity information and key quality characteristic information;

[0114] Audit data value evaluation system construction module 207 is used to construct an audit data value evaluation system based on four influencing factors: data quality, data intrinsic value, data application value and market value;

[0115] The matching and comparison module 208 is used to match and compare the data value to be evaluated set with the corresponding types of rules in the audit data rule library based on the audit data value evaluation system to obtain the score of each influencing factor;

[0116] The weight calculation module 209 is used to calculate the weight of each influencing factor using the hierarchical analysis method;

[0117] The data value evaluation module 210 is used to input the score of each influencing factor and the weight of each influencing factor into the audit data value evaluation model to calculate the audit data value evaluation result.

[0118] Example 3

[0119] Based on the above embodiment 1, this embodiment further provides a computer device, which includes: a processor, and the processor is used to implement the steps of any of the above methods when executing a computer program stored in a memory.

[0120] Example 4

[0121] The present invention also provides a computer-readable storage medium having computer instructions stored thereon. When the computer instructions are executed by a processor, the steps of any of the above methods are implemented. For example, the computer program can be divided into one or more modules / units, which are stored in a memory and executed by a processor to implement the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in a computer device.

[0122] A computer device may be a desktop computer, laptop, PDA, cloud server, or other computer device. A computer device may include, but is not limited to, a processor and memory. Those skilled in the art will appreciate that a computer device may include more or fewer components, or a combination of certain components, or different components. For example, a computer device may also include input / output devices, network access devices, buses, and the like.

[0123] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0124] Memory can be an internal storage unit of a computer device, such as a computer device's hard drive or memory. It can also be an external storage device, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, or a flash memory card. Furthermore, memory can include both internal storage units and external storage devices. Memory is used to store computer programs and other programs and data required by the computer device. Memory can also be used to temporarily store data that has been output or is about to be output.

[0125] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0126] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0127] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0128] In the embodiments provided by the present invention, it should be understood that the disclosed devices / computer equipment and methods can be implemented in other ways. For example, the device / computer equipment embodiments described above are merely illustrative. For example, the division of modules or units is merely a logical function division. In actual implementation, there may be other division methods. Multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection of devices or units, and may be electrical, mechanical or other forms.

[0129] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0130] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0131] If the integrated module / unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program can include computer program code, which can be in source code form, object code form, executable file, or some intermediate form. Computer-readable media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, removable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunications signals, and software distribution media. It should be noted that the content included in computer-readable media can be appropriately increased or decreased based on the requirements of legislation and patent practice within a jurisdiction. For example, in some jurisdictions, based on legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunications signals.

[0132] The above are only preferred embodiments of the present invention. It should be pointed out that various modifications and improvements made by those skilled in the art without departing from the present technical solution should also be deemed to fall within the scope of protection required by the present claims.

Claims

1. A method for evaluating the value of audit data, characterized in that: include: Step 1: Obtain the data dictionary of the target database, and build an audit data rule base based on the data dictionary of the target database, with reference to national standards, local standards, industry standards and expert knowledge base; Step 2: Obtain the audit data to be evaluated in the target database, use a hash table to perform a pre-check on the database table of the audit data to be evaluated, identify the data type information and file structure information contained in the audit data to be evaluated, and mark the source attribute to which the data type information belongs; Step 3: Load the audit data to be evaluated according to the marked source attributes, use the bidirectional long short-term memory network to perform named entity recognition on the audit data to be evaluated, obtain the named entity information of the audit data to be evaluated, perform format screening, duplicate checking and key information extraction on the audit data to be evaluated in turn, obtain key quality characteristic information, and construct the data value to be evaluated set based on the source attributes, file structure information, named entity information and key quality characteristic information; Step 4: Based on the four influencing factors of data quality, data intrinsic value, data application value and market value, an audit data value evaluation system is constructed. Based on the audit data value evaluation system, the data value set to be evaluated is matched and compared with the corresponding types of rules in the audit data rule library to obtain the score of each influencing factor. The hierarchical analysis method is used to calculate the weight of each influencing factor. The score of each influencing factor and the weight of each influencing factor are input into the audit data value evaluation model to calculate the audit data value evaluation result.

2. According to claim 1, a method for evaluating the value of audit data is characterized in that: The data dictionary includes: definition and description information of target database objects, attribute information of target database objects, association relationships of target database objects, target database users and authority information, and parameters and configuration information of the target database.

3. According to claim 1, a method for evaluating the value of audit data is characterized in that: In step 2, a hash table is used to perform a pre-check of the library table on the audit data to be evaluated, and the data type information and file structure information contained in the audit data to be evaluated are identified, and the source attribute to which the data type information belongs is marked accordingly, including: NLP technology is used to identify the data type and length of the table header items and the first five non-blank rows of the audit data to be evaluated, and the data type information contained in the audit data to be evaluated is obtained. OCR technology is used to perform structured recognition on the audit data to be evaluated, and the file structure information contained in the audit data to be evaluated is obtained. The identified content is then concatenated with the file name of the audit data to be evaluated to obtain concatenated data. The concatenated data is then converted into a character format and converted into a character vector or a string scalar. The MD5 algorithm is used to calculate the hash value, which is matched and compared with the hash value of the stored source attribute to mark the source attribute to which the data type information belongs.

4. The audit data value evaluation method according to claim 1 is characterized in that: In step 3, the audit data to be evaluated is loaded according to the marked source attributes, and a bidirectional long short-term memory network is used to perform named entity recognition on the audit data to be evaluated to obtain named entity information of the audit data to be evaluated, including: The audit data to be evaluated is loaded according to the marked source attributes, and data cleaning is performed on the audit data to obtain the cleaned named data information. A bidirectional long short-term memory network is used to perform named entity recognition on the cleaned named data information to obtain the named entity information of the audit data to be evaluated.

5. The audit data value evaluation method according to claim 1 is characterized in that: In step 4, the factors affecting data quality include six secondary factors, namely, accuracy, completeness, consistency, accessibility, standardization and timeliness; the factors affecting data intrinsic value include four secondary factors, namely, data scale, data frequency, data structure and data granularity; the factors affecting data application value include five secondary factors, namely, user visits, user browsing or downloading, proportion of business data, proportion of field or subject data and proportion of industry data; the factors affecting market value include five secondary factors, namely, data scarcity, external data cooperation, proportion of data with high download rate, expected social value benefits and expected economic value benefits.

6. The audit data value evaluation method according to claim 1 is characterized in that: In step 4, based on the audit data value evaluation system, the data value set to be evaluated is matched and compared with the rules under the corresponding attributes in the audit data rule library to obtain the score of each influencing factor, including: According to the marked source attributes, the data value set to be evaluated is matched and compared with the corresponding types of rules in the audit data rule library. Based on the four influencing factors of data quality, data intrinsic value, data application value and market value, the error rate and score of the data information contained in the data value set to be evaluated under each influencing factor are calculated to obtain the score of each influencing factor.

7. The audit data value evaluation method according to claim 1 is characterized in that: The calculation formula of the audit data value evaluation model is as follows: The constraints are: , V is the audit data value score, Q is the data quality score, N is the data intrinsic value score, A is the data application value score, and M is the market value score. is the weight of data quality, is the weight of the intrinsic value of data, is the weight of data application value, The weight of market value.

8. An audit data value evaluation device, characterized in that: include: A data dictionary acquisition module is used to acquire the data dictionary of the target database; Audit data rule base construction module, used to construct the audit data rule base according to the data dictionary of the target database, with reference to national standards, local standards, industry standards and expert knowledge base; The audit data acquisition and pre-detection module is used to obtain the audit data to be evaluated from the target database, use a hash table to perform pre-detection on the database table of the audit data to be evaluated, identify the data type information and file structure information contained in the audit data to be evaluated, and mark the source attribute to which the data type information belongs accordingly; A named entity recognition module is used to load the audit data to be evaluated according to the marked source attributes, and use a bidirectional long short-term memory network to perform named entity recognition on the audit data to be evaluated to obtain the named entity information of the audit data to be evaluated; The data processing module is used to perform format screening, duplicate checking and key information extraction on the audit data to be evaluated, and obtain key quality characteristic information; The data set construction module is used to construct a data value evaluation set based on source attributes, file structure information, named entity information and key quality characteristic information; Audit data value evaluation system construction module, which is used to build an audit data value evaluation system based on four influencing factors: data quality, data intrinsic value, data application value and market value; The matching and comparison module is used to match and compare the data value set to be evaluated with the corresponding types of rules in the audit data rule library based on the audit data value evaluation system to obtain the score of each influencing factor; The weight calculation module is used to calculate the weight of each influencing factor using the hierarchical analysis method; The data value evaluation module is used to input the score of each influencing factor and the weight of each influencing factor into the audit data value evaluation model to calculate the audit data value evaluation result.

9. A computer device, characterized in that: The computer device comprises: a processor, and the processor is used to implement the steps of any method according to claim 1-7 when executing a computer program stored in a memory.

10. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed by a processor, the steps of any method as claimed in claim 1-7 are implemented.

Images