Data quality evaluation method and device, electronic equipment and storage medium

Abstract

The application provides a data quality evaluation method and device, electronic equipment and a storage medium, and belongs to the technical field of financial technology. If the target evaluation index is a first category evaluation index, a target root set is obtained by comparing the root with key data through a preset root knowledge base. The target root set is screened through a preset keyword knowledge base to obtain a target keyword. The reference value data of the target keyword is obtained, and the target value data is preliminarily scored according to the reference value data to obtain preliminary score data. First score data and second score data are obtained, and the first score data and the second score data are obtained by scoring insurance data according to the target evaluation index by the data production end and the data consumption end respectively. The target score data is obtained by weighting the preliminary score data, the first score data and the second score data. The target score data is sent to the data production end, and the insurance data can be accurately evaluated.

Description

Technical Field

[0001] This application relates to the field of financial technology, and in particular to a data quality assessment method and apparatus, electronic device and storage medium. Background Technology

[0002] In the insurance sector, insurance companies perform data processing tasks such as data analysis and risk assessment based on insurance data. By analyzing insurance data, insurance companies can understand customer needs and market conditions, thereby adjusting their insurance business strategies. High-quality insurance business data ensures the effectiveness and accuracy of data analysis, risk assessment, and other data processing tasks, serving as the foundation for data processing. Therefore, data quality assessment of insurance data is necessary to determine its quality. How to conduct data quality assessment has become a pressing issue. Summary of the Invention

[0003] The main objective of this application is to provide a data quality assessment method, apparatus, electronic device, and storage medium, which are designed to assess the data quality of insurance data.

[0004] To achieve the above objectives, a first aspect of this application proposes a data quality assessment method, which is applied to a data quality management system. The method includes:

[0005] Insurance data is obtained from the data production end; the insurance data includes key data and target value data of the key data; the key data is the insurance indicator item of the insurance data; the target value data is the indicator value of the insurance indicator item;

[0006] Obtain at least one of the preset evaluation indicators to obtain the target evaluation indicator; the preset evaluation indicators include the first category of evaluation indicators.

[0007] If the target evaluation indicator is the first category evaluation indicator, then the target word root set is obtained by comparing the word root with the key data through a preset word root knowledge base;

[0008] The target keywords are obtained by filtering the target word root set using a preset keyword knowledge base;

[0009] Obtain the baseline value data of the target keyword, and perform a preliminary score on the target value data based on the baseline value data to obtain preliminary score data;

[0010] Obtain first scoring data and second scoring data; wherein, the first scoring data is obtained by the data producer scoring the insurance data according to the target evaluation index, and the second scoring data is obtained by the data consumer scoring the insurance data according to the target evaluation index;

[0011] The target score data is obtained by weighting the preliminary score data, the first score data, and the second score data;

[0012] The target score data is sent to the data production terminal.

[0013] In some embodiments, obtaining the benchmark value data of the target keyword and performing a preliminary score on the target value data based on the benchmark value data to obtain preliminary score data includes:

[0014] The baseline value data is obtained by querying the preset value range knowledge base based on the target keywords.

[0015] Calculate the similarity data between the baseline data and the target data;

[0016] The target value data is initially scored based on the similarity data to obtain the initial score data.

[0017] In some embodiments, the benchmark data includes a data security level. The process of obtaining the benchmark data for the target keyword and performing a preliminary score on the target data based on the benchmark data to obtain preliminary score data includes:

[0018] Obtain the first security level of the target word root set and the second security level of the target keyword;

[0019] The data security level of the target keyword is obtained by selecting a security level based on the first security level and the second security level.

[0020] Based on the preset data lineage, the data flow direction of the target value data is analyzed to obtain the data flow direction of the target value data;

[0021] Determine the data security type of the target value data based on the data flow direction;

[0022] The target value data is initially scored based on the data security level and the data security type to obtain the initial score data.

[0023] In some embodiments, the benchmark data includes data definitions, data formats, and data mapping relationships. The process of obtaining the benchmark data for the target keyword and performing a preliminary score on the target value data based on the benchmark data to obtain preliminary score data includes:

[0024] Obtain the data definition, data format, and data mapping relationship of the target keywords;

[0025] Based on the data definition, a definition consistency score is obtained by performing a definition consistency score on the target value data.

[0026] The target value data is scored for format consistency according to the data format to obtain a format consistency score.

[0027] Based on the data mapping relationship, the target value data is scored for mapping consistency to obtain a mapping relationship consistency score.

[0028] The target value data is initially scored based on the defined consistency score, the format consistency score, and the mapping relationship consistency score to obtain the initial score data.

[0029] In some embodiments, the preset evaluation index further includes a second category of evaluation indexes. After obtaining at least one of the preset evaluation indexes to obtain the target evaluation index, the data quality assessment method further includes:

[0030] If the target evaluation indicator is the second category evaluation indicator, perform value field missing analysis on the target value data to obtain value field missing data; perform a preliminary accuracy score on the target value data based on the value field missing data to obtain the preliminary score data;

[0031] or,

[0032] If the target evaluation indicator is the second category evaluation indicator, perform annotation field missing analysis on the target value data to obtain annotation field missing data; perform a preliminary integrity score on the target value data based on the annotation field missing data to obtain the preliminary score data.

[0033] In some embodiments, the preset evaluation index further includes a second category of evaluation indexes. After obtaining at least one of the preset evaluation indexes to obtain the target evaluation index, the data quality assessment method further includes:

[0034] If the target evaluation indicator is the second category evaluation indicator, obtain the data update time of the target value data;

[0035] The timeliness of the target value data is initially scored based on the data update time and a preset time threshold to obtain the initial score data.

[0036] In some embodiments, the preset evaluation index further includes a second category of evaluation indexes. After obtaining at least one of the preset evaluation indexes to obtain the target evaluation index, the data quality assessment method further includes:

[0037] If the target evaluation index is the second category evaluation index, the target value data is divided to obtain the first target value data and the second target value data.

[0038] An interpretability score is obtained by performing an interpretability score on the first target value data;

[0039] The interpretability score of the second target value data is obtained by performing an interpretability score on the data.

[0040] The first explanatory score and the second explanatory score are weighted to obtain the preliminary score data.

[0041] To achieve the above objectives, a second aspect of this application provides a data quality assessment device, which is applied to a data quality management terminal, and the device includes:

[0042] An insurance data acquisition module is used to acquire insurance data from the data production end; the insurance data includes key data and target value data of the key data; the key data is the insurance indicator item of the insurance data; the target value data is the indicator value of the insurance indicator item;

[0043] The indicator acquisition module is used to acquire at least one of the preset evaluation indicators to obtain the target evaluation indicator; the preset evaluation indicators include a first category of evaluation indicators.

[0044] The word root comparison module is used to compare the word roots with the key data through a preset word root knowledge base to obtain a target word root set if the target evaluation index is the first category evaluation index.

[0045] The word root filtering module is used to filter the target word root set through a preset keyword knowledge base to obtain target keywords;

[0046] The preliminary scoring module is used to obtain the baseline value data of the target keyword, and to perform a preliminary scoring on the target value data based on the baseline value data to obtain preliminary scoring data;

[0047] The scoring data acquisition module is used to acquire first scoring data and second scoring data; wherein, the first scoring data is obtained by the data production end scoring the insurance data according to the target evaluation index, and the second scoring data is obtained by the data consumption end scoring the insurance data according to the target evaluation index;

[0048] The weighted scoring module is used to perform weighted scoring based on the preliminary scoring data, the first scoring data, and the second scoring data to obtain the target scoring data.

[0049] The scoring data sending module is used to send the target scoring data to the data production end.

[0050] To achieve the above objectives, a third aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the data quality assessment method described in the first aspect.

[0051] To achieve the above objectives, a fourth aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the data quality assessment method described in the first aspect.

[0052] The data quality assessment method, device, electronic equipment, and computer-readable storage medium proposed in this application acquire insurance data from the data production end, obtain at least one preset evaluation indicator, and obtain a target evaluation indicator. Data quality is then quantified based on the target evaluation indicator to assess the quality of the insurance data. If the target evaluation indicator is a first-category evaluation indicator, a target root word set is obtained by comparing the target root word set with key data using a preset root word knowledge base. Target keywords are then obtained by filtering the target root word set using a preset keyword knowledge base. Benchmark values ​​for the target keywords are acquired, and the target value data is initially scored based on these benchmark values ​​to obtain preliminary score data. The scoring results are made more objective by referencing root word and keyword knowledge bases. First and second score data are then acquired. The first score data is obtained by the data production end scoring the insurance data according to the target evaluation indicator, and the second score data is obtained by the data consumption end scoring the insurance data according to the target evaluation indicator. By introducing the first and second score data, the data quality assessment results can be integrated into the experience and intuitive perception of both the data production and consumption ends, thereby ensuring that the insurance data meets the expectations and needs of both ends. The target score is obtained by weighting the preliminary score data, the first score data, and the second score data. This target score includes both subjective and objective evaluations, increasing the authenticity and accuracy of the data quality score. The target score data is then sent to the data production team, allowing them to assess the quality of the insurance data and conduct data analysis based on high-quality insurance data. Attached Figure Description

[0053] Figure 1 This is a flowchart of the data quality assessment method provided in the embodiments of this application;

[0054] Figure 2 This is another flowchart of the data quality assessment method provided in the embodiments of this application;

[0055] Figure 3 This is another flowchart of the data quality assessment method provided in the embodiments of this application;

[0056] Figure 4 This is another flowchart of the data quality assessment method provided in the embodiments of this application;

[0057] Figure 5 yes Figure 1 The flowchart of step S150 in the middle;

[0058] Figure 6 yes Figure 1 Another flowchart of step S150 in the process;

[0059] Figure 7 yes Figure 1 Another flowchart of step S150 in the process;

[0060] Figure 8 This is a schematic diagram of the data quality assessment device provided in the embodiments of this application;

[0061] Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0063] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0065] First, let's analyze some of the terms used in this application:

[0066] Data quality dimensions refer to the different aspects or characteristics used to assess and measure data quality. Common data quality dimensions include accuracy, completeness, consistency, timeliness, and reliability.

[0067] In the insurance sector, insurance companies perform data processing tasks such as data analysis and risk assessment based on insurance data. By analyzing insurance data, insurance companies can understand customer needs and market conditions, thereby adjusting their insurance business strategies. High-quality insurance business data ensures the effectiveness and accuracy of data analysis, risk assessment, and other data processing tasks, serving as the foundation for data processing. Therefore, data quality assessment of insurance data is necessary to determine its quality. How to conduct data quality assessment has become a pressing issue.

[0068] Based on this, embodiments of this application provide a data quality assessment method, a data quality assessment device, an electronic device, and a computer-readable storage medium, which are intended to assess the data quality of insurance data.

[0069] The data quality assessment method, data quality assessment device, electronic device, and computer-readable storage medium provided in this application are specifically described through the following embodiments. First, the data quality assessment method in this application is described.

[0070] The data quality assessment method provided in this application relates to the field of financial technology. This data quality assessment method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the data quality assessment method, but is not limited to the above forms.

[0071] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0072] It should be noted that in various specific embodiments of this application, when processing data related to the identity or characteristics of an object, such as object information, object behavior data, object historical data, and object location information, the object's permission or consent will be obtained first. Furthermore, the collection, use, and processing of this data will comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require obtaining the object's personal information, separate permission or consent from the object will be obtained through pop-ups or redirection to a confirmation page. Only after obtaining the object's separate permission or consent will the necessary object-related data for the proper functioning of the embodiments of this application be obtained.

[0073] Figure 1 This is an optional flowchart of the data quality assessment method provided in the embodiments of this application. The data quality assessment method is applied to the data quality management end, which is connected to the data production end, and the data production end is connected to the data consumption end. Figure 1 The method may include, but is not limited to, steps S110 to S180.

[0074] Step S110: Obtain insurance data from the data production end; the insurance data includes key data and target value data of the key data; the key data is the insurance indicator item of the insurance data; the target value data is the indicator value of the insurance indicator item.

[0075] Step S120: Obtain at least one of the preset evaluation indicators to obtain the target evaluation indicator; the preset evaluation indicators include the first category of evaluation indicators.

[0076] Step S130: If the target evaluation indicator is the first category evaluation indicator, then the target word root set is obtained by comparing the word roots with the key data through the preset word root knowledge base;

[0077] Step S140: Filter the target word root set through a preset keyword knowledge base to obtain the target keywords;

[0078] Step S150: Obtain the baseline value data of the target keyword, and perform a preliminary score on the target value data based on the baseline value data to obtain preliminary score data;

[0079] Step S160: Obtain first scoring data and second scoring data; wherein, the first scoring data is obtained by the data producer scoring the insurance data according to the target evaluation indicators, and the second scoring data is obtained by the data consumer scoring the insurance data according to the target evaluation indicators;

[0080] Step S170: Perform a weighted score based on the preliminary score data, the first score data, and the second score data to obtain the target score data;

[0081] Step S180: Send the target score data to the data production end.

[0082] Steps S110 to S180, as illustrated in the embodiments of this application, quantify data quality through target evaluation indicators to assess the quality of insurance data. A weighted score is obtained based on preliminary scoring data, first scoring data, and second scoring data, resulting in target scoring data that includes both subjective and objective scores, thereby increasing the authenticity and accuracy of the data quality score.

[0083] In step S110 of some embodiments, insurance data is obtained from the data production end. The data production end utilizes a large amount of insurance data accumulated in the insurance industry for data development to mine the user risk characteristics and user behavior patterns implicit in the insurance data. Based on these user risk characteristics and behavior patterns, risk assessment and claims optimization are performed to provide users with better insurance services. The insurance data includes key data and target value data for the key data. The key data consists of insurance indicator items, which can be individual monthly average FYC, insurance type, insured amount, premium payment method, etc. The target value data is the indicator value of the insurance indicator item; for example, the indicator value for the insurance type is life insurance. The data consumption end consumes the data generated by the data production end.

[0084] In step S120 of some embodiments, the preset evaluation indicators refer to data quality dimensions, which include eight major categories: security, effectiveness, accuracy, completeness, usability, timeliness, interpretability, and consistency. Depending on the scoring object, these eight major categories are further divided into 28 subcategories. The scoring objects include target programs from the data production end, data consumption end, and data quality management end. The security data quality dimension subcategory includes data production end self-assessed security, data consumption end experiential security, and program capture security. The effectiveness data quality dimension subcategory includes data production end self-assessed effectiveness, data consumption end experiential effectiveness, and program capture effectiveness. The accuracy data quality dimension subcategory includes program capture order-of-magnitude accuracy, data production end self-assessed accuracy, and data consumption end experiential accuracy. The completeness data quality dimension subcategory includes data production end self-assessed completeness, data consumption end experiential completeness, dataset completeness, requirement document completeness, and indicator document completeness. The usability data quality dimension subcategory includes data production end self-assessed usability and data consumption end experiential usability. The timeliness data quality dimensions include timeliness of self-assessment by data producers, timeliness of experience by data consumers, and timeliness of program capture. The interpretability data quality dimensions include interpretability of self-assessment by data producers, interpretability of experience by data consumers, interpretability of indicator documents, and interpretability of requirement documents. The consistency data quality dimensions include consistency of self-assessment by data producers, consistency of experience by data consumers, definition consistency, format consistency, and mapping consistency.

[0085] It should be noted that, based on the characteristics of different data quality dimensions, real backend data is obtained and compared with predefined values ​​to obtain the scores for each data quality dimension, which are the data quality dimension scores captured by the program.

[0086] Based on whether a knowledge base is involved in the data quality assessment process, the pre-set evaluation indicators are divided into two categories: Category I indicators and Category II indicators. Category I indicators require knowledge base involvement and include validity, security, and consistency. Category II indicators do not require knowledge base involvement and include accuracy, completeness, usability, timeliness, and interpretability. At least one indicator is selected from these eight pre-set indicators to obtain the target evaluation indicator.

[0087] Please see Figure 2 In some embodiments, the preset evaluation index further includes a second category of evaluation index. After step S120, the data quality assessment method may include, but is not limited to, step S210 or step S220:

[0088] Step S210: If the target evaluation index is a second-category evaluation index, perform value field missing analysis on the target value data to obtain value field missing data; perform preliminary accuracy scoring on the target value data based on the value field missing data to obtain preliminary score data;

[0089] Step S220: If the target evaluation index is a second-category evaluation index, perform annotation field missing analysis on the target value data to obtain annotation field missing data; perform preliminary integrity scoring on the target value data based on the annotation field missing data to obtain preliminary score data.

[0090] In step S210 of some embodiments, the target value data includes value fields and annotation fields for the value fields. Accuracy, or the precision of the data, is used to measure the deviation between the target value data and the actual data. If the target evaluation index is accuracy, a value field missing analysis is performed on the target value data to determine whether a value field is missing. If a value field is null, the missing value field is retrieved to obtain the missing value field data. The number of value fields in the missing value field data is obtained to obtain the first number of value fields. The total number of value fields in the target value data is obtained to obtain the second number of value fields. The ratio of the first number of value fields to the second number of value fields is calculated. The accuracy score corresponding to the ratio is determined according to a preset mapping relationship to obtain preliminary scoring data. The preset mapping relationship can be a scoring function, an interval relationship between the ratio and the scoring value, etc. If the preset mapping relationship is a scoring function, the ratio is used as the input parameter of the scoring function, and the output result of the scoring function is used as the preliminary scoring data. If the preset mapping relationship is an interval relationship, the target interval to which the ratio belongs is determined, and the scoring value corresponding to the target interval is determined, and the scoring value corresponding to the target interval is used as the preliminary scoring data.

[0091] In step S220 of some embodiments, completeness refers to the degree of data integrity, used to measure whether target value data is missing. If the target evaluation index is completeness, a missing annotation field analysis is performed on the target value data to determine whether the annotation fields are missing. If an annotation field is null, the annotation field is retrieved to obtain the missing annotation field data. The number of annotation fields in the missing annotation field data is obtained to obtain the first annotation field number. The total number of annotation fields in the target value data is obtained to obtain the second annotation field number. The ratio of the first annotation field number to the second annotation field number is calculated, and the completeness score is determined based on the ratio to obtain preliminary score data. The calculation method for the completeness score is the same as the calculation method for the accuracy score, and can be referred to step S210, which will not be repeated here.

[0092] In some embodiments, the target value data is partitioned into dataset data, requirement document data, and indicator document data to evaluate the completeness of each. The dataset is the collection of data used in data analysis; it can be a policy dataset, including information such as policy number, insurance product, premium, insurance liability, and policy status. The requirement document is a document generated during the product requirement and maintenance phases, recording information such as the content, background, value, and acceptance criteria of the product requirements. The indicator document is a document generated during the product development phase, recording metadata information such as table names, field names, definition criteria, and developers for the indicators developed based on the product requirements.

[0093] Perform missing annotation field analysis on the dataset to obtain the first set of missing annotation fields. Perform missing annotation field analysis on the requirement document data to obtain the second set of missing annotation fields. Perform missing annotation field analysis on the indicator document data to obtain the third set of missing annotation fields. Obtain the number of annotation fields in the first set of missing annotation fields to obtain the number of the third set of missing annotation fields. Obtain the total number of annotation fields in the dataset to obtain the fourth set of missing annotation fields. Calculate the ratio of the number of the third set of missing annotation fields to the number of the fourth set of missing annotation fields, and determine the first completeness score of the dataset based on this ratio. Determine the second completeness score of the requirement document data based on the second set of missing annotation fields. Determine the third completeness score of the indicator document data based on the third set of missing annotation fields. The calculation methods for the second and third completeness scores are the same as those for the first completeness score, and will not be repeated here. Perform a weighted scoring on the first, second, and third completeness scores to obtain preliminary scoring data. Specifically, determine the weight of the dataset data as w1, the weight of the requirement document data as w2, and the weight of the indicator document data as w3. Multiply w1 by the first integrity score, w2 by the second integrity score, and w3 by the third integrity score, then add the results of these three multiplications to obtain the preliminary score data.

[0094] Steps S210 to S220 above assess the accuracy and completeness of insurance data. Based on the accuracy score and completeness score, the accuracy and completeness of the insurance data can be determined, and missing value fields and annotation fields in the insurance data can be supplemented, thereby improving the data quality of the insurance data.

[0095] Please see Figure 3 In some embodiments, after step S120, the data quality assessment method may also include, but is not limited to, steps S310 to S320:

[0096] Step S310: If the target evaluation indicator is a second category evaluation indicator, obtain the data update time of the target value data;

[0097] Step S320: Based on the data update time and the preset time threshold, perform a preliminary timeliness score on the target value data to obtain preliminary score data.

[0098] In step S310 of some embodiments, timeliness is used to measure the update speed of target value data and can be used to determine whether the target value data is the latest version. If the target evaluation index is timeliness, a scheduling task for monitoring insurance data is set, and the completion time of the scheduling task and the update time of the target value data in the base table are obtained. The maximum value of the completion time and the update time is selected as the data update time of the target value data. It is understood that the completion time of the scheduling task and the update time of the base table are usually consistent, but they may differ when the network environment fluctuates. Therefore, it is necessary to select the maximum value as the data update time to confirm the accurate time of data update.

[0099] In step S320 of some embodiments, insurance data is targeted at business needs. At the beginning of each business request, the timeliness requirements of the insurance data need to be confirmed with the business party. The timeliness score of the insurance data is obtained by judging whether the data update time is within the time range required by the business. The preset time threshold is the data update time point of the business party for the timeliness requirement. If the data update time does not exceed the preset time threshold, it means that the data update time meets the timeliness requirement, and the preliminary score data is 100 points. The preset time threshold can be 8 o'clock every day, which means that the insurance data needs to be updated before 8 o'clock every day. If the data update time is before 8 o'clock, the insurance data is considered to meet the timeliness requirement. If the data update time exceeds the preset time threshold, the data update time is subtracted from the preset time threshold to obtain the overtime duration. The target value data is initially scored for timeliness based on the overtime duration and the overtime duration threshold to obtain the preliminary score data. The preliminary score data is greater than or equal to 0. Specifically, for each time the overtime duration exceeds the overtime duration threshold, the preset score is subtracted to obtain the preliminary score data. Calculate the ratio of the overtime duration to the overtime threshold, round the ratio up to obtain a preset number. Subtract this preset number of preset scores from 100 points to obtain the preliminary score data. For example, if the overtime duration is 35 minutes, the overtime threshold is 10 minutes, and the preset score is 10 points, then the preliminary score data is 100 - 10 × 4 = 60.

[0100] If the timeout duration is less than the timeout duration threshold, a first preset score is subtracted from 100 points to obtain the preliminary score. If the timeout duration is greater than or equal to the timeout duration threshold, a second preset score is subtracted from 100 points to obtain the preliminary score. The first preset score and the second preset score can be the same or different.

[0101] Steps S310 to S320 above assess the timeliness of insurance data to determine a timeliness score, thereby determining the data update speed. Furthermore, based on the timeliness score, insurance data can be updated promptly, improving its quality in terms of timeliness.

[0102] Please see Figure 4 In some embodiments, after step S120, the data quality assessment method may also include, but is not limited to, steps S410 to S440:

[0103] Step S410: If the target evaluation index is a second category evaluation index, the target value data is divided into first target value data and second target value data.

[0104] Step S420: Perform interpretability scoring on the first target value data to obtain the first interpretability score;

[0105] Step S430: Perform interpretability scoring on the second target value data to obtain the second interpretability score;

[0106] Step S440: Weight the first explanatory score and the second explanatory score to obtain preliminary score data.

[0107] In step S410 of some embodiments, interpretability refers to the ability of data to be interpreted and described. If the target evaluation index is interpretability, the target value data is divided into first target value data and second target value data. The first target value data is the requirement document data, and the second target value data is the index document data.

[0108] In step S420 of some embodiments, interpretability can indirectly reflect the data quality of insurance data. If all fields of a document are filled in and the content is understandable to others, the document is considered high-quality. Specifically, an integrity assessment is performed on the first target value data to obtain an integrity score. An interpretability assessment is then performed on the first target value data through multiple data groups to obtain multiple interpretability scores. These multiple interpretability scores are then averaged to obtain an average score. Finally, a weighted average of the integrity score and the average score is calculated to obtain a first interpretability score.

[0109] In step S430 of some embodiments, the second target value data is given an interpretability score to obtain a second interpretability score. The calculation method of the second interpretability score is the same as that of the first interpretability score, and can be referred to step S420, which will not be repeated here.

[0110] In step S440 of some embodiments, a weighted calculation is performed on the first interpretive score and the second interpretive score to obtain preliminary score data. The weight of the requirement document data is w2, and the weight of the indicator document data is w3. w2 is multiplied by the first interpretive score, and w3 is multiplied by the second interpretive score. The two multiplication results are then added together to obtain the preliminary score data.

[0111] Steps S410 to S440 above, by conducting an interpretability assessment of the insurance data, can determine the quality of the insurance data entry, and modify the insurance data based on the entry quality, thereby improving the data quality of the insurance data.

[0112] In step S130 of some embodiments, the preset root word knowledge base includes multiple root words. If the target evaluation metric is at least one of effectiveness, security, and consistency, then the preset root word knowledge base is used to compare the root words with the key data, dividing the key data into multiple root words to obtain the target root word set. For example, if the key data is an individual's average monthly FYC, the key data is matched with the root words in the root word knowledge base, dividing the key data into three root words: individual, average monthly, and FYC, thus obtaining the target root word set.

[0113] In step S140 of some embodiments, a preset keyword knowledge base includes multiple keywords. Multiple roots in a target root word set are matched against these keywords in the preset keyword knowledge base to filter the target root word set and obtain the target keyword. For example, the target root word set includes the roots "personal," "monthly average," and "FYC." Keywords are identified from the target root word set based on the keyword knowledge base, resulting in the target keyword "FYC."

[0114] Please see Figure 5 In some embodiments, step S150 may include, but is not limited to, steps S510 to S530:

[0115] Step S510: Query the preset value range knowledge base according to the target keywords to obtain the baseline value data;

[0116] Step S520: Calculate the similarity data between the baseline data and the target data;

[0117] Step S530: Perform a preliminary validity score on the target value data based on the similarity data to obtain preliminary score data.

[0118] In step S510 of some embodiments, validity is used to determine whether the data value is consistent with the defined value range. If the target evaluation index is validity, a value range knowledge query is performed on the preset value range knowledge base based on the target keywords to obtain the benchmark value data. The benchmark value data includes value range data, which includes data type, data precision, unit, etc.

[0119] The data type for length, width, and height fields is numeric, with floating-point precision, an expected value of 38 positive digits, and the unit is millimeters. The data type for amount fields is numeric, with floating-point precision, and an expected value of 38 positive digits. The data type for time and date fields is character, with an expected length of 10 digits. If the target keyword is FYC, searching the value range knowledge base will show that the value range of FYC is numbers greater than 0.

[0120] In step S520 of some embodiments, the target value data and the benchmark value data are compared to determine whether the field value of each field in the target value data is within the theoretical value range represented by the value range data. If the field value is within the theoretical value range, the field is considered similar to the benchmark value data, and the number of similar fields is used as the similarity data. If the field value of a certain field in the target value data is not within the theoretical value range, the field is considered dissimilar to the benchmark value data.

[0121] By comparing the field values ​​of FYC with the baseline data, if the field value is within the value range represented by the baseline data (i.e., the field value is greater than 0), then the FYC field and the baseline data are considered similar.

[0122] In step S530 of some embodiments, the number of field values ​​of the target value data is obtained, the ratio of similarity data to the number of field values ​​is calculated, and the validity score corresponding to the ratio is determined according to a preset mapping relationship to obtain preliminary score data.

[0123] Through the above steps S510 to S530, the insurance data can be evaluated for validity, and the insurance data can be modified using the preliminary scoring data to improve the quality of the insurance data in the validity quality dimension.

[0124] Please see Figure 6 In some embodiments, the benchmark data includes a data security level, and step S150 may include, but is not limited to, steps S610 to S650:

[0125] Step S610: Obtain the first security level of the target root word set and the second security level of the target keyword;

[0126] Step S620: Select a security level based on the first security level and the second security level to obtain the data security level of the target keyword;

[0127] Step S630: Analyze the data flow of the target value data according to the preset data lineage to obtain the data flow of the target value data;

[0128] Step S640: Determine the data security type of the target value data based on the data flow direction;

[0129] Step S650: Perform a preliminary security score on the target value data based on the data security level and data security type to obtain preliminary score data.

[0130] In step S610 of some embodiments, security is used to measure the security level of insurance data. If the target evaluation index is security, the first security level of each root word in the target root word set is queried through a preset root word knowledge base, and the second security level of the target keyword is queried through a preset keyword knowledge base.

[0131] In step S620 of some embodiments, the target keyword can be a combination of multiple word roots. When determining the security level of the indicator, the highest security level among the first security level and the second security level needs to be selected as the data security level of the target keyword.

[0132] In step S630 of some embodiments, a preset data lineage relationship records the upstream and downstream relationships of the target value data. Based on the preset data lineage relationship, an upstream and downstream relationship query is performed on the target value data to trace the data flow of the target value data. It is understood that big data task scheduling configures dependencies. Based on these dependencies, the specific upstream and downstream table tasks that the execution of a table task depends on can be determined. Through these dependencies, the association between a table and its dependent upstream and downstream tables can be found, thereby locating the data flow.

[0133] In step S640 of some embodiments, the purpose and destination of data can be identified by the data flow to obtain the data security type of the target keyword. Data security types include international-related types and non-international-related types. International-related data has a higher security level than non-international-related data. Data security type is used to confirm the correct security permission level for data use; for example, data with the highest security level cannot be exported internationally. Only when the data security level and data security type match is the insurance data considered to meet security requirements.

[0134] In step S650 of some embodiments, the matching degree data between data security level and data security type in insurance data is calculated. Based on a preset mapping relationship, the security score corresponding to the matching degree data is found to perform a preliminary security score on the target value data, resulting in preliminary score data. The matching degree data is used to measure the proportion of matching between data security level and data security type. For example, if insurance data includes three indicators and their corresponding indicator values, and the data security level and data security type corresponding to one indicator match, while the other two pairs of indicator-indicator value pairs do not match, then the matching degree data is 1 / 3.

[0135] Through the above steps S610 to S650, the security of insurance data can be assessed, thus ensuring the data security of insurance data.

[0136] Please see Figure 7 In some embodiments, the reference value data includes data definition, data format, and data mapping relationship, and step S150 may include, but is not limited to, steps S710 to S750:

[0137] Step S710: Obtain the data definition, data format, and data mapping relationship of the target keywords;

[0138] Step S720: Based on the data definition, perform definition consistency scoring on the target value data to obtain the definition consistency score;

[0139] Step S730: Calculate the format consistency score of the target value data according to the data format to obtain the format consistency score;

[0140] Step S740: Perform a mapping consistency score on the target value data based on the data mapping relationship to obtain the mapping relationship consistency score;

[0141] Step S750: Perform a preliminary consistency score on the target value data based on the definition consistency score, format consistency score, and mapping relationship consistency score to obtain preliminary score data.

[0142] In step S710 of some embodiments, consistency is used to determine whether data contradicts or conflicts with each other. The data definition, data format, and data mapping relationship of the target keywords are obtained through a preset keyword knowledge base. The data definition refers to the meaning represented by the data; different indicators should have different data definitions, while the same indicators should have the same data definition. For example, in a policy table, the insurance product name code is represented as ProductName, and in a claims table, it is represented as PN. Both ProductName and PN represent insurance product name codes, and their data definitions should be the same. The data format refers to the format in which the data is represented. For example, a mobile phone number must be 11 digits, and an IP address must be a string consisting of four digits from 0 to 255 and the character ".". The data mapping relationship refers to the logical relationship between the data. For example, derived indicators must be processed from atomic indicators, page views (PV) must be greater than the number of unique visitors (UV), the probability value must be between 0 and 1, the insurance start time must be less than or equal to the insurance end time, the insurance status must be "insured," and the insurance date should not be empty, etc.

[0143] In step S720 of some embodiments, if the data definition of the target value data is the same as the data definition of the target keyword, then the target value data and the target keyword definition are considered to be consistent. The proportion of consistent definitions in the insurance data is calculated, and the definition consistency score corresponding to the proportion is determined according to a preset mapping relationship to obtain the definition consistency score.

[0144] In step S730 of some embodiments, if the data format of the target value data is the same as the data format of the target keyword, then the target value data and the target keyword are considered to have consistent formats. The proportion of insurance data with consistent formats is calculated, and the format consistency score corresponding to the proportion is determined according to a preset mapping relationship to obtain a format consistency score.

[0145] In step S740 of some embodiments, it is determined whether the target value data conforms to the logical relationship based on the data mapping relationship. If the target value data conforms to the logical relationship, it is considered that the target value data meets the mapping relationship consistency requirement. The proportion of target value data in the insurance data that conforms to the logical relationship is calculated, and the mapping relationship consistency score corresponding to the proportion is determined according to the preset mapping relationship to obtain the mapping relationship consistency score.

[0146] In step S750 of some embodiments, the definition consistency score, format consistency score and mapping relationship consistency score are weighted and scored to obtain preliminary score data.

[0147] Through the above steps S710 to S750, the insurance data can be evaluated for data consistency, and a consistency score of the insurance data can be obtained. The consistency score is used to determine the quality of the insurance data in the consistency quality dimension.

[0148] In step S160 of some embodiments, different enterprises have different data environments, including data backgrounds, data cultures, data requirements, data consumers, and data developers. To accurately and appropriately assess data quality in a practical way, a first score data is added, obtained by the data producer scoring the insurance data according to the target evaluation indicators, and a second score data is added, obtained by the data consumer scoring the insurance data according to the target evaluation indicators. This makes the data quality assessment more focused on the intuitive feelings of the data producer and data consumer, more closely aligned with business objectives, and closer to real-world application scenarios, increasing the authenticity and accuracy of the data quality score, thereby ensuring that the data quality meets the expectations and needs of the data producer and data consumer. The target evaluation indicators include at least one of security, effectiveness, accuracy, completeness, usability, timeliness, interpretability, and consistency. Among them, usability refers to the ease of use and accessibility of the data.

[0149] In step S170 of some embodiments, the preliminary scoring data, the first scoring data, and the second scoring data are weighted and calculated to obtain the target scoring data.

[0150] In step S180 of some embodiments, the target score data is sent to the data production end, enabling the data production end to perform data development on the insurance data based on the target score data, generate data development results, and send the data development results to the data consumption end for data consumption. It is understood that if the target score data is less than a preset score threshold, the insurance data is modified, and then the modified insurance data is evaluated for data quality according to steps S120 to S170. It should be noted that the data quality evaluation is not a one-time event, but rather aims to establish a long-term mechanism for evaluating and improving data quality. If the target score data is greater than or equal to the preset score threshold, it indicates that the insurance data is high-quality data, and the data production end can directly perform data development on the insurance data.

[0151] Please see Figure 8 This application also provides a data quality assessment device, which is applied to a data quality management terminal and can implement the above-mentioned data quality assessment method. The data quality assessment device includes:

[0152] The insurance data acquisition module 810 is used to acquire insurance data from the data production end; the insurance data includes key data and target value data of the key data; the key data is the insurance indicator item of the insurance data; the target value data is the indicator value of the insurance indicator item.

[0153] The indicator acquisition module 820 is used to acquire at least one of the preset evaluation indicators to obtain the target evaluation indicator; the preset evaluation indicators include the first category of evaluation indicators.

[0154] The word root comparison module 830 is used to compare word roots with key data through a preset word root knowledge base if the target evaluation index is the first category evaluation index, and obtain the target word root set.

[0155] The root word filtering module 840 is used to filter the target root word set through a preset keyword knowledge base to obtain the target keywords;

[0156] The preliminary scoring module 850 is used to obtain the baseline value data of the target keywords and to perform a preliminary scoring on the target value data based on the baseline value data to obtain the preliminary scoring data.

[0157] The scoring data acquisition module 860 is used to acquire first scoring data and second scoring data; wherein, the first scoring data is obtained by the data producer scoring the insurance data according to the target evaluation indicators, and the second scoring data is obtained by the data consumer scoring the insurance data according to the target evaluation indicators;

[0158] The weighted scoring module 870 is used to perform weighted scoring based on the preliminary scoring data, the first scoring data, and the second scoring data to obtain the target scoring data.

[0159] The scoring data sending module 880 is used to send the target scoring data to the data production end.

[0160] The specific implementation of this data quality assessment device is basically the same as the specific implementation of the data quality assessment method described above, and will not be repeated here.

[0161] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned data quality assessment method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0162] Please see Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0163] The processor 910 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0164] The memory 920 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 920 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 920 and is called and executed by the processor 910 using the data quality assessment method of the embodiments of this application.

[0165] The input / output interface 930 is used to implement information input and output;

[0166] The communication interface 940 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0167] Bus 950 transmits information between various components of the device (e.g., processor 910, memory 920, input / output interface 930, and communication interface 940);

[0168] The processor 910, memory 920, input / output interface 930 and communication interface 940 are connected to each other within the device via bus 950.

[0169] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described data quality assessment method.

[0170] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0171] The data quality assessment method, data quality assessment device, electronic device, and computer-readable storage medium provided in this application quantify data quality through target evaluation indicators to assess the quality of insurance data. A weighted score is obtained by weighting preliminary score data, first score data, and second score data, resulting in target score data that includes both subjective and objective scores, thus increasing the authenticity and accuracy of the data quality assessment.

[0172] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0173] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0174] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0175] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0176] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0177] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0178] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0179] The units described above as separate components may or may not be physically separate. The 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 the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0180] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0181] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0182] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A data quality assessment method, characterized in that, The method is applied to a data quality management system, and the method includes: Insurance data is obtained from the data production end; the insurance data includes key data and target value data of the key data; the key data is the insurance indicator item of the insurance data; the target value data is the indicator value of the insurance indicator item; Obtain at least one of the preset evaluation indicators to obtain the target evaluation indicator; the preset evaluation indicators include the first category of evaluation indicators; If the target evaluation indicator is the first category evaluation indicator, then the target word root set is obtained by comparing the word root with the key data through a preset word root knowledge base; The target keywords are obtained by filtering the target word root set using a preset keyword knowledge base; Obtain the baseline value data of the target keyword, and perform a preliminary score on the target value data based on the baseline value data to obtain preliminary score data; Obtain first scoring data and second scoring data; wherein, the first scoring data is obtained by the data producer scoring the insurance data according to the target evaluation index, and the second scoring data is obtained by the data consumer scoring the insurance data according to the target evaluation index; The target score data is obtained by weighting the preliminary score data, the first score data, and the second score data; The target score data is sent to the data production terminal; The benchmark data includes data security level. The process of obtaining the benchmark data for the target keyword, and performing a preliminary score on the target data based on the benchmark data to obtain preliminary score data, includes: Obtain the first security level of the target word root set and the second security level of the target keyword; select a security level based on the first and second security levels to obtain the data security level of the target keyword; perform data flow analysis on the target value data according to a preset data lineage relationship to obtain the data flow direction of the target value data; determine the data security type of the target value data based on the data flow direction; and perform a preliminary security score on the target value data based on the data security level and the data security type to obtain the preliminary score data.

2. A data quality assessment method, characterized in that, The method is applied to a data quality management system, and the method includes: Insurance data is obtained from the data production end; the insurance data includes key data and target value data of the key data; the key data is the insurance indicator item of the insurance data; the target value data is the indicator value of the insurance indicator item; Obtain at least one of the preset evaluation indicators to obtain the target evaluation indicator; the preset evaluation indicators include the first category of evaluation indicators; If the target evaluation indicator is the first category evaluation indicator, then the target word root set is obtained by comparing the word root with the key data through a preset word root knowledge base; The target keywords are obtained by filtering the target word root set using a preset keyword knowledge base; Obtain the baseline value data of the target keyword, and perform a preliminary score on the target value data based on the baseline value data to obtain preliminary score data; Obtain first scoring data and second scoring data; wherein, the first scoring data is obtained by the data producer scoring the insurance data according to the target evaluation index, and the second scoring data is obtained by the data consumer scoring the insurance data according to the target evaluation index; The target score data is obtained by weighting the preliminary score data, the first score data, and the second score data; The target score data is sent to the data production terminal; The benchmark data includes data definition, data format, and data mapping relationship. The process of obtaining the benchmark data for the target keyword, and performing a preliminary score on the target data based on the benchmark data to obtain preliminary score data, includes: Obtain the data definition, data format, and data mapping relationship of the target keyword; perform a definition consistency score on the target value data based on the data definition to obtain a definition consistency score; perform a format consistency score on the target value data based on the data format to obtain a format consistency score; perform a mapping consistency score on the target value data based on the data mapping relationship to obtain a mapping relationship consistency score; perform a preliminary consistency score on the target value data based on the definition consistency score, the format consistency score, and the mapping relationship consistency score to obtain the preliminary score data.

3. A data quality assessment method, characterized in that, The method is applied to a data quality management system, and the method includes: Insurance data is obtained from the data production end; the insurance data includes key data and target value data of the key data; the key data is the insurance indicator item of the insurance data; the target value data is the indicator value of the insurance indicator item; Obtain at least one of the preset evaluation indicators to obtain the target evaluation indicator; the preset evaluation indicators include the first category of evaluation indicators; If the target evaluation indicator is the first category evaluation indicator, then the target word root set is obtained by comparing the word root with the key data through a preset word root knowledge base; The target keywords are obtained by filtering the target word root set using a preset keyword knowledge base; Obtain the baseline value data of the target keyword, and perform a preliminary score on the target value data based on the baseline value data to obtain preliminary score data; Obtain first scoring data and second scoring data; wherein, the first scoring data is obtained by the data producer scoring the insurance data according to the target evaluation index, and the second scoring data is obtained by the data consumer scoring the insurance data according to the target evaluation index; The target score data is obtained by weighting the preliminary score data, the first score data, and the second score data; The target score data is sent to the data production terminal; The process of obtaining baseline data for the target keywords and performing preliminary scoring on the target data based on the baseline data to obtain preliminary scoring data includes: The baseline value data is obtained by querying the preset value range knowledge base according to the target keywords; the similarity data between the baseline value data and the target value data is calculated; and the target value data is preliminarily evaluated for validity based on the similarity data.

4. The data quality assessment method according to any one of claims 1 to 3, characterized in that, The preset evaluation indicators also include a second category of evaluation indicators. After obtaining at least one of the preset evaluation indicators to obtain the target evaluation indicator, the data quality assessment method further includes: If the target evaluation indicator is the second category evaluation indicator, perform value field missing analysis on the target value data to obtain value field missing data; perform a preliminary accuracy score on the target value data based on the value field missing data to obtain the preliminary score data; or, If the target evaluation indicator is the second category evaluation indicator, perform annotation field missing analysis on the target value data to obtain annotation field missing data; perform a preliminary integrity score on the target value data based on the annotation field missing data to obtain the preliminary score data.

5. The data quality assessment method according to any one of claims 1 to 3, characterized in that, The preset evaluation indicators also include a second category of evaluation indicators. After obtaining at least one of the preset evaluation indicators to obtain the target evaluation indicator, the data quality assessment method further includes: If the target evaluation indicator is the second category evaluation indicator, obtain the data update time of the target value data; The timeliness of the target value data is initially scored based on the data update time and a preset time threshold to obtain the initial score data.

6. The data quality assessment method according to any one of claims 1 to 3, characterized in that, The preset evaluation indicators also include a second category of evaluation indicators. After obtaining at least one of the preset evaluation indicators to obtain the target evaluation indicator, the data quality assessment method further includes: If the target evaluation index is the second category evaluation index, the target value data is divided to obtain the first target value data and the second target value data. An interpretability score is obtained by performing an interpretability score on the first target value data; The interpretability score of the second target value data is obtained by performing an interpretability score on the data. The first explanatory score and the second explanatory score are weighted to obtain the preliminary score data.

7. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the data quality assessment method according to any one of claims 1 to 6.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the data quality assessment method according to any one of claims 1 to 6.

Images