Label verification method and device, electronic equipment and storage medium

Abstract

The embodiment of the application provides a label verification method and device, an electronic device and a storage medium, and belongs to the technical field of financial technology. The method comprises the following steps: obtaining a data label to be verified; classifying the data label, and screening out a target data label of a numerical type; inputting the target data label into a preset decile label model in batches to generate a verification result of the target data label; generating a data control chart based on the verification result; and performing rationality judgment on the data distribution of the target data label according to the data control chart and a preset threshold range to obtain a judgment result, wherein the judgment result comprises whether the target data label is an abnormal data label. Based on this, the embodiment of the application can quickly, efficiently and accurately verify customer labels, so that insurance business personnel can analyze the characteristics of customers from multiple angles, select customers according to the labels, and thus realize accurate customer touch and provide more refined operation targets for customers.

Description

Technical Field

[0001] This application relates to the field of financial technology (Fintech), and more particularly to a tag verification method and apparatus, electronic device and storage medium. Background Technology

[0002] Customer tags are symbolic representations of customer characteristics. Each data tag represents a perspective for understanding, observing, and describing a customer. To gain a comprehensive understanding of customers, a vast amount of rich and diverse tags from multiple perspectives and dimensions are needed. These include: raw customer data such as demographic attributes, location information, and account information; platform activity information such as news preferences and activity preferences; predictive customer tags such as churn probability and recent needs; and strategic customer tags such as potential retainers and potential customers. By leveraging this wealth of tags, a complete customer profile can be created.

[0003] In the insurance industry, to assist insurance agents in analyzing customer characteristics from multiple perspectives, selecting customers based on tags, and thus achieving precise customer outreach and providing customers with more refined operational goals, it is necessary to verify massive amounts of customer tags. However, current technology relies on manual testing to verify such a large number of tags, which presents significant challenges. Therefore, how to quickly, efficiently, and accurately verify customer tags has become an urgent technical problem to be solved. Summary of the Invention

[0004] The main objective of this application is to propose a tag verification method, device, electronic device, and storage medium that can quickly, efficiently, and accurately verify customer tags. This can assist insurance agents in analyzing customer characteristics from multiple perspectives, selecting customers based on tags, and thus achieving precise customer outreach. This allows for more refined operational goals for customers, thereby enhancing the competitiveness of insurance agents and their insurance companies.

[0005] To achieve the above objectives, a first aspect of this application proposes a label verification method, the method comprising:

[0006] Retrieve the data tags to be verified;

[0007] The data tags are classified, and target data tags of numerical type are selected;

[0008] The target data labels are input in batches into a preset tenths label model for tenths method verification processing to generate the verification results of the target data labels;

[0009] A data control chart is generated based on the verification results;

[0010] The reasonableness of the data distribution of the target data tag is judged based on the data control chart and the preset threshold range, and the judgment result is obtained. The judgment result includes judging whether the target data tag belongs to abnormal data tag.

[0011] In some embodiments, obtaining the data tag to be verified includes:

[0012] Connect to a pre-defined big data cluster;

[0013] Read the large wide table that needs to be verified from the big data cluster;

[0014] Find the table structure corresponding to the wide table;

[0015] Obtain the data label to be verified from the table structure.

[0016] In some embodiments, classifying the data tags and filtering out target data tags of numerical type includes:

[0017] Identify the name roots of the data tags;

[0018] The name root is compared with the preset keywords to obtain the comparison result;

[0019] The target data labels of numerical type are selected based on the verification results.

[0020] In some embodiments, the step of batch inputting the target data tags into a preset tenths tag model for tenths verification processing to generate verification results for the target data tags includes:

[0021] The target data labels are batch input into a preset tenths place label model for tenths method verification processing, wherein the tenths place label model defines a label processing function;

[0022] Determine the number of missing indicators, the percentage of missing indicators, the mean, the maximum, and the minimum values ​​in the target data labels;

[0023] Divide the numerical range between the maximum and the minimum values ​​into ten equal parts to obtain decimal places;

[0024] The target data tag is embedded into the tag processing function to generate the data volume of each of the tenth positions of the target data tag;

[0025] The verification result of the target data label is determined based on the number of missing indicators, the percentage of missing indicators, the mean, the maximum value, the minimum value, and the amount of data at each decimal point.

[0026] In some embodiments, embedding the target data tag into the tag processing function to generate the data volume of each of the tenths of the target data tag includes:

[0027] Import the target data tags into the YAML file;

[0028] By repeatedly reading the target data tags in the YAML file and inputting the target data tags into the tag processing function, the data volume of each tenth position of the target data tag is obtained.

[0029] In some embodiments, the reasonableness judgment of the data distribution of the target data tag based on the data control chart and a preset threshold range is obtained to obtain a judgment result. The judgment result includes determining whether the target data tag belongs to an abnormal data tag, including:

[0030] Convert the data control chart into a normal distribution chart;

[0031] Determine the location of the threshold range on the normal distribution graph;

[0032] If the target data label is determined to be outside the threshold range in the normal distribution plot, the target data label is determined to be an anomalous data label.

[0033] In some embodiments, after determining the reasonableness of the data distribution of the target data tag based on the data control chart and a preset threshold range, and obtaining a determination result, the determination result includes determining whether the target data tag belongs to an abnormal data tag, and further includes:

[0034] When the target data tag is determined to be an abnormal data tag, an error message is issued.

[0035] To achieve the above objectives, a second aspect of this application provides a label verification device, the device comprising:

[0036] The acquisition module is used to acquire the data tags to be verified.

[0037] The classification module is used to classify the data tags and filter out target data tags of numerical type;

[0038] The verification module is used to input the target data tags in batches into a preset tenths tag model for tenths method verification processing, and generate the verification results of the target data tags;

[0039] The generation module is used to generate a data control chart based on the verification results;

[0040] The judgment module is used to make a reasonable judgment on the data distribution of the target data tag based on the data control chart and a preset threshold range, and to obtain a judgment result, the judgment result including whether the target data tag belongs to an abnormal data tag.

[0041] 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 method described in the first aspect.

[0042] 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 method described in the first aspect.

[0043] The tag verification method, apparatus, electronic device, and storage medium proposed in this application acquire data tags to be verified; classify the data tags and filter out target data tags of numerical type; input the target data tags in batches into a preset decimal tag model to generate verification results for the target data tags; generate a data control chart based on the verification results; and make a reasonableness judgment on the data distribution of the target data tags according to the data control chart and a preset threshold range to obtain a judgment result, including whether the target data tags belong to abnormal data tags. Based on this, by filtering out target data tags of numerical type from the verified data tags, processing the target data tags using the decimal method, feeding the target data tags into the decimal intelligent customer tag model to generate the data volume of each target data tag in each decimal place, and then making a reasonableness judgment on the data distribution of each target data tag according to the data control chart and a preset threshold range, abnormal data tags in a large number of tags can be quickly identified. Compared with manual testing, this tag verification method is faster, more accurate, and more comprehensive, and can avoid missed detections. For abnormal data tags, it is convenient to backtrack and trace. Based on this, the embodiments of this application can quickly, efficiently, and accurately verify customer tags, thereby assisting insurance agents in analyzing customer characteristics from multiple perspectives, selecting customers based on tags, and achieving precise customer outreach to provide customers with more refined operational goals. By improving the efficiency of tag verification and reducing the investment of human resources, cost reduction and efficiency improvement are achieved, thereby enhancing the competitiveness of insurance agents and their insurance companies. Attached Figure Description

[0044] Figure 1 This is a flowchart of the label verification method provided in the embodiments of this application;

[0045] Figure 2 yes Figure 1 The flowchart of step S101 in the text;

[0046] Figure 3 yes Figure 1 The flowchart of step S102 in the document;

[0047] Figure 4 yes Figure 1 The flowchart of step S103 in the process;

[0048] Figure 5 yes Figure 4 The flowchart of step S404 in the document;

[0049] Figure 6 yes Figure 1 The flowchart of step S105 in the process;

[0050] Figure 7 This is a schematic diagram of the label verification device provided in the embodiments of this application;

[0051] Figure 8 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0052] 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.

[0053] 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.

[0054] 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.

[0055] First, let's analyze some of the terms used in this application:

[0056] Artificial intelligence (AI) is a new branch of computer science that studies, develops, and applies theories, methods, technologies, and systems to simulate, extend, and expand human intelligence. It aims to understand the essence of intelligence and produce intelligent machines that can react in a way similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. AI can simulate the information processes of human consciousness and thought. Furthermore, AI utilizes digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceiving the environment, acquiring knowledge, and using that knowledge to achieve optimal results.

[0057] Insurance refers to a commercial insurance activity in which the policyholder pays premiums to the insurer according to the contract, and the insurer assumes the responsibility of compensating for property losses caused by accidents stipulated in the contract, or paying insurance benefits when the insured dies, becomes disabled, falls ill, or reaches the age or term stipulated in the contract. From an economic perspective, insurance is a financial arrangement for sharing the losses of unexpected accidents; from a legal perspective, insurance is a contractual act, an arrangement in which one party agrees to compensate the other party for losses; from a social perspective, insurance is an important component of the social and economic security system, a "delicate stabilizer" of social production and social life; from a risk management perspective, insurance is a method of risk management.

[0058] An insurance agent is an individual who, authorized by an insurer, acts on behalf of the insurer to conduct insurance business and receives agency fees. Within the scope of the insurer's authorization, an insurance agent conducts business activities on behalf of the insurer, including soliciting business through promotional activities, accepting applications, issuing provisional policies or insurance policies, collecting premiums, and handling claims investigations. Agency fees are typically paid as a percentage of the business volume. Depending on the scope of business, insurance agents can be categorized as general agents, local agents, and part-time agents. Agency methods include dedicated agents who represent only one insurance company, and independent agents who operate independently and can represent multiple insurance companies simultaneously.

[0059] Business development, or business operations, refers to the activities undertaken by agents in lending, insurance, and wealth management to find clients. Insurance business development channels mainly include direct sales, agent sales, and broker sales. Direct sales refer to insurers relying on their own sales personnel to secure business; agent sales refer to agents promoting policies within the scope of the insurer's authorization, which can be further divided into professional agents and part-time agents. In property insurance, direct and part-time sales are primarily relied upon, while in life insurance, in addition to using direct sales, business is generally solicited by professional agents.

[0060] The Internet Control Message Protocol (ICMP) is a sub-protocol of the TCP / IP protocol suite used to transmit control messages between IP hosts and routers. Control messages are network-related messages indicating network connectivity, host reachability, and route availability. While these control messages do not transmit user data, they play a crucial role in the delivery of user data. ICMP utilizes basic IP support, acting as if it were a higher-level protocol; however, ICMP is actually an integral part of IP and must be implemented by every IP module.

[0061] Hive is a data warehouse tool based on Hadoop, used for data extraction, transformation, and loading. It's a mechanism for storing, querying, and analyzing large-scale data stored in Hadoop. Hive data warehouse tools can map structured data files to database tables and provide SQL query functionality, transforming SQL statements into MapReduce tasks for execution. Hive's advantages include a low learning curve; it allows for fast MapReduce statistics through SQL-like statements, simplifying MapReduce without requiring the development of dedicated MapReduce applications. Hive is well-suited for statistical analysis of data warehouses.

[0062] Macro: A term for batch processing. In computer science, a macro is an abstraction that replaces certain text patterns according to a set of predefined rules. The interpreter or compiler automatically performs this pattern replacement when it encounters a macro. For compiled languages, macro expansion occurs at compile time, and the tool that performs macro expansion is often called a macro expander. The term macro is also frequently used in many similar contexts derived from the concept of macro expansion, including keyboard macros and macro languages. In most cases, the use of the word "macro" implies the transformation of small commands or actions into a series of instructions. A macro is a group of commands organized together to complete a specific task as a single command.

[0063] The normal distribution, also known as the Gaussian distribution, was first derived by Abraham de Moivre in finding the asymptotic formula for the binomial distribution. CF Gauss derived it from another perspective when studying measurement errors. PS Laplace and Gauss studied its properties. It is a very important probability distribution in mathematics, physics, and engineering, and has a significant influence on many aspects of statistics. The normal curve is bell-shaped, low at both ends and high in the middle, and symmetrical. Because of its bell-shaped curve, it is often called the bell curve.

[0064] In the insurance industry, to assist insurance agents in analyzing customer characteristics from multiple perspectives, selecting customers based on tags, and thus achieving precise customer outreach and providing customers with more refined operational goals, it is necessary to verify massive amounts of customer tags. However, current technology relies on manual testing to verify such a large number of tags, which presents significant challenges. Therefore, how to quickly, efficiently, and accurately verify customer tags has become an urgent technical problem to be solved.

[0065] Based on this, embodiments of this application provide a tag verification method, apparatus, electronic device, and storage medium. The method involves acquiring data tags to be verified; classifying the data tags and filtering out target data tags of numerical type; batch inputting the target data tags into a preset decimal tag model to generate verification results for the target data tags; generating a data control chart based on the verification results; and making a reasonableness judgment on the data distribution of the target data tags according to the data control chart and a preset threshold range to obtain a judgment result, including whether the target data tags belong to abnormal data tags. Based on this, by filtering out target data tags of numerical type from the verified data tags, processing the target data tags using the decimal method, feeding the target data tags into the decimal intelligent customer tag model to generate the data volume of each target data tag in each decimal place, and then making a reasonableness judgment on the data distribution of each target data tag using the data control chart and a preset threshold range, abnormal data tags in a massive number of tags can be quickly identified. Compared to manual testing, this tag verification method is faster, more accurate, and more comprehensive, and can avoid missed detections. For abnormal data tags, it facilitates backtracking. Based on this, the embodiments of this application can quickly, efficiently, and accurately verify customer tags, thereby assisting insurance agents in analyzing customer characteristics from multiple perspectives, selecting customers based on tags, and achieving precise customer outreach to provide customers with more refined operational goals. By improving the efficiency of tag verification and reducing the investment of human resources, cost reduction and efficiency improvement are achieved, thereby enhancing the competitiveness of insurance agents and their insurance companies.

[0066] The label verification method, apparatus, electronic device, and storage medium provided in this application are specifically described through the following embodiments. First, the label verification method in this application is described.

[0067] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0068] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0069] The tag verification method provided in this application relates to the field of artificial intelligence technology. The tag verification method provided in this application 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 tag verification method, but is not limited to the above forms.

[0070] 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.

[0071] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0072] Figure 1 This is an optional flowchart of the label verification method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S105.

[0073] Step S101: Obtain the data label to be verified;

[0074] Step S102: Classify the data labels and filter out the target data labels of numerical type;

[0075] Step S103: Input the target data labels in batches into the preset tenths label model for tenths method verification processing, and generate the verification results of the target data labels;

[0076] Step S104: Generate a data control chart based on the verification results;

[0077] Step S105: Based on the data control chart and the preset threshold range, make a reasonable judgment on the data distribution of the target data label to obtain the judgment result, which includes whether the target data label belongs to the abnormal data label.

[0078] In step S101 of some embodiments, data tags to be verified are obtained. These data tags can be customer tags, which are symbolic representations of customer characteristics. Each data tag represents a perspective for understanding, observing, and describing a customer. To gain a comprehensive understanding of customers, a vast amount of rich and diverse tags from multiple perspectives and dimensions are needed. For example, in the insurance field, customer tags include: raw customer data (demographic attributes, location information, account information, etc.); customer platform activity information (information preferences, activity preferences, etc.); predictive customer tags (churn probability, recent needs, etc.); and strategic customer tags (potential customers to be retained, potential customers to be developed, etc.). By acquiring a large number of data tags, a comprehensive customer profile is created, facilitating insurance professionals to analyze customer characteristics from multiple angles, select customers based on tags, and achieve precise customer outreach, providing customers with more refined operational goals.

[0079] In step S102 of some embodiments, data tags are classified, and target data tags of numerical type are filtered out. In big data models, two commonly used data types are decimal and string. Decimal is used to store numerical data, and string is used to store data other than numerical data. Based on this, data tags are classified into decimal tags and string tags, and decimal tags that need to be verified, i.e., target data tags of numerical type, are filtered out. For example, in the insurance field, customer tags are classified into decimal tags and string tags, and decimal tags that need to be verified, i.e., customer tags of numerical type, are filtered out.

[0080] In step S103 of some embodiments, target data tags are batch-inputted into a preset decimal tag model for decimal validation, generating validation results for the target data tags. For example, in the insurance field, numerical customer tags are input into a decimal tag model for decimal validation. The preset decimal tag model is used to perform decimal processing on the customer tags. Decimal processing involves taking the maximum and minimum values ​​of the customer tags, dividing the numerical range of the data tags into 10 equal parts according to the set decimal points, and returning the values ​​of the data tags at each decimal point, thereby clarifying the data distribution of the customer tags and generating validation results for numerical customer tags. The validation results may also include the number of missing indicators for the customer tags (e.g., the amount of data where the customer tag is NULL in the entire population wide table), the percentage of missing indicators (e.g., the percentage of data where the customer tag is NULL in the entire population wide table), the mean, maximum, minimum values, and a statistical analysis of the data volume at each decimal point.

[0081] In step S104 of some embodiments, a data control chart is generated based on the verification results. For example, in the insurance field, a data control chart is generated based on the verification results output by the decimal tag model. The data control chart can visually display the data distribution of customer tags, facilitating the rapid identification of customer tags with anomalies.

[0082] In step S105 of some embodiments, the reasonableness of the data distribution of the target data tag is judged based on the data control chart and a preset threshold range to obtain a judgment result. The judgment result includes determining whether the target data tag belongs to abnormal data tags. For example, in the insurance field, for instance, by setting a threshold range on the position of the normal distribution chart, if it is determined that the customer tag is outside the threshold range in the data control chart, the customer tag is judged to be an abnormal data tag. This allows for the rapid identification of abnormal data tags among a large number of customer tags, thereby assisting insurance business personnel in analyzing customer characteristics from multiple perspectives, selecting customers based on tags, and achieving precise customer outreach to provide customers with more refined operational goals. By improving the efficiency of tag verification and reducing the investment of human resources, insurance companies can achieve cost reduction and efficiency improvement.

[0083] Steps S101 to S105 of this embodiment involve obtaining data tags to be verified; classifying the data tags and filtering out target data tags of numerical type; batch inputting the target data tags into a preset decimal tag model to generate verification results for the target data tags; generating a data control chart based on the verification results; and making a reasonable judgment on the data distribution of the target data tags according to the data control chart and a preset threshold range to obtain a judgment result, which includes determining whether the target data tags belong to abnormal data tags. Based on this, by filtering out target data tags of numerical type from the verified data tags, processing the target data tags using the decimal method, feeding the target data tags into the decimal intelligent customer tag model to generate the data volume of each target data tag in each decimal place, and then making a reasonable judgment on the data distribution of each target data tag using the data control chart and a preset threshold range, abnormal data tags in a massive number of tags can be quickly identified. Compared with manual testing, this tag verification method is faster, more accurate, and more comprehensive, and can avoid missed detections. For abnormal data tags, it facilitates backtracking. Based on this, the embodiments of this application can quickly, efficiently, and accurately verify customer tags, thereby assisting insurance agents in analyzing customer characteristics from multiple perspectives, selecting customers based on tags, and achieving precise customer outreach to provide customers with more refined operational goals. By improving the efficiency of tag verification and reducing the investment of human resources, cost reduction and efficiency improvement are achieved, thereby enhancing the competitiveness of insurance agents and their insurance companies.

[0084] Please see Figure 2 In some embodiments, step S101 may include, but is not limited to, steps S201 to S204:

[0085] Step S201: Connect to the preset big data cluster;

[0086] Step S202: Read the wide table that needs to be verified from the big data cluster;

[0087] Step S203: Locate the table structure corresponding to the wide table;

[0088] Step S204: Obtain the data tags to be verified from the table structure.

[0089] In some embodiments, a pre-defined big data cluster is connected. This big data cluster stores a massive amount of data tags. For example, it can connect to a Hive data cluster. Hive is an open-source data warehouse tool based on Hadoop, developed by Facebook. It can map structured data files to a table and provide SQL-like query functionality. A wide table to be verified is read from the big data cluster. This wide table is a database table with many fields. The corresponding table structure is found, and the data tags to be verified are obtained from the table structure. These data tags can then be appended to the table. Especially in the insurance industry, insurance agents can quickly obtain massive amounts of customer tags from the data cluster, thereby improving their work efficiency.

[0090] Please see Figure 3 In some embodiments, step S102 may include, but is not limited to, steps S301 to S303:

[0091] Step S301: Identify the name root of the data label;

[0092] Step S302: Check the name root with the preset keywords to obtain the check results;

[0093] Step S303: Filter out the target data labels of numerical type based on the verification results.

[0094] In some embodiments, the name root of a data tag is identified, and the root determines the meaning of the data tag's name. The name root is then compared with preset keywords. Keywords may include, but are not limited to, words that implicitly contain numerical values, such as frequency, number of people, and amount. For example, if the comparison shows that the frequency of the data tag's name root matches the preset keywords, then the data tag is selected as a numerical target data tag. Conversely, if there is no matching result between the data tag's name root and the preset keywords, then the data tag will not be selected as a numerical target data tag. In the insurance field, insurance agents can quickly identify numerical customer tags from a massive amount of customer tags, thereby improving their work efficiency.

[0095] Please see Figure 4 In some embodiments, step S103 may include, but is not limited to, steps S401 to S405:

[0096] Step S401: Input the target data labels in batches into the preset tenths place label model for tenths method verification processing, wherein the tenths place label model defines a label processing function;

[0097] Step S402: Determine the number of missing indicators, the percentage of missing indicators, the mean, the maximum value, and the minimum value in the target data labels;

[0098] Step S403: Divide the numerical range between the maximum and minimum values ​​into ten equal parts to obtain ten decimal places;

[0099] Step S404: Embed the target data tag into the tag processing function to generate the data volume of each tenth position of the target data tag;

[0100] Step S405: Determine the verification result of the target data label based on the number of missing indicators, the percentage of missing indicators, the mean, the maximum, the minimum, and the amount of data at the decimal point.

[0101] In some embodiments, target data labels are batch-input into a preset decimal labeling model for decimal validation. The decimal labeling model defines a label processing function to process the target data labels, yielding the number of missing indicators (the number of data points with the label NULL in the entire population wide table), the percentage of missing indicators (the ratio of data points with the label NULL in the entire population wide table to the total data volume), the mean, maximum, minimum, and a statistical analysis of the data volume at each decimal point. The decimal method involves taking the maximum and minimum values ​​of an indicator and dividing them equally into ten parts, for example, 0.01, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.99. Note that the starting and ending points are taken from the nearest 0.01, and the method returns the number of decimal points, thus clarifying the data distribution. In the insurance field, by filtering out numerical target data tags from verified data tags, processing the target data tags using the ten-digit method, and feeding the target data tags into the ten-digit intelligent customer tag model, the data volume of each target data tag in each tenth digit is generated. Compared with manual testing, this tag verification method is faster, more accurate, and more comprehensive, and can avoid missed tests. For abnormal data tags, it is convenient to backtrack and improve the work efficiency of insurance business personnel.

[0102] Please see Figure 5 In some embodiments, steps S404 may include, but are not limited to, steps S501 to S502:

[0103] Step S501: Import the target data tags into the YAML file;

[0104] Step S502: By reading the target data tags in the YAML file in a loop, the target data tags are input into the tag processing function to obtain the data volume of each tenth position of the target data tag.

[0105] In some embodiments, batch tag processing can be achieved using file-driven data technology, such as using YAML files for data-driven processing and parameterization. Specifically, YAML files are used to store parameters (mainly table names and fields). By iteratively reading the parameters from the YAML files and feeding them into the tag processing method macro, the data volume of each tenth position of the target data tag is obtained, thereby improving the speed of batch processing of target data tags and increasing the work efficiency of insurance business personnel.

[0106] Please see Figure 6 In some embodiments, step S105 may include, but is not limited to, steps S601 to S603:

[0107] Step S601: Convert the data control chart into a normal distribution chart;

[0108] Step S602: Determine the position of the threshold range on the normal distribution graph;

[0109] Step S603: If the target data label is determined to be outside the threshold range in the normal distribution map, the target data label is determined to be an abnormal data label.

[0110] In some embodiments, the data control chart generated based on the verification results is converted into a normal distribution chart. The position of the threshold range within the normal distribution chart is determined. If the target data label is found to be outside the threshold range in the normal distribution chart, the target data label is determined to be an anomalous data label. In the insurance field, taking customer age labels as an example, a threshold range of 0 to 150 years is pre-set. If a customer's age label is outside the threshold range in the normal distribution chart, for example, a customer label below 0 years old or above 150 years old, the value of that customer's age label is an outlier, and therefore, that customer's age label is determined to be an anomalous data label. Based on this, customer labels can be verified quickly, efficiently, and accurately, thereby assisting insurance agents in analyzing customer characteristics from multiple perspectives, selecting customers based on labels, and achieving precise customer outreach. This allows for more refined operational goals for customers. By improving the efficiency of label verification and reducing the investment of human resources, cost reduction and efficiency improvement are achieved, thereby enhancing the competitiveness of insurance agents and their insurance companies.

[0111] In some embodiments, step S105 may be followed by, but is not limited to, step S106:

[0112] Step S106: When it is determined that the target data label belongs to an abnormal data label, an abnormal prompt is issued.

[0113] In some embodiments, within the insurance field, when a target data tag is determined to be an abnormal data tag, an anomaly alert is issued promptly to remind insurance agents to handle the abnormal data tag appropriately, such as excluding it. This allows for the analysis of normal data tags, assisting insurance agents in analyzing customer characteristics from multiple perspectives, selecting customers based on tags, and achieving precise customer outreach. This enables more refined operational goals for customers. By improving the efficiency of tag verification and reducing the investment of human resources, cost reduction and efficiency improvement are achieved, thereby enhancing the competitiveness of insurance agents and their insurance companies.

[0114] The label verification method of this application is further illustrated below with reference to specific embodiments.

[0115] In the insurance field, data tags to be verified are acquired. These tags can be customer tags, which are symbolic representations of customer characteristics. Each tag represents a perspective for understanding, observing, and describing a customer. To gain a comprehensive understanding of customers, a vast amount of rich and diverse tags from multiple perspectives and dimensions are needed. Customer tags can include: raw customer data (demographic attributes, location information, account information, etc.); customer platform activity information (information preferences, activity preferences, etc.); predictive customer tags (churn probability, recent needs, etc.); and strategic customer tags (potential retainers, potential customers, etc.). In big data models, two common data types are decimal and string. Decimal is used to store numeric data, while string is used to store data other than numeric data. Data tags are categorized into decimal tags and string tags, and the decimal tags that need verification—that is, the target numeric data tags—are selected. Therefore, customer tags are categorized into decimal tags and string tags, and the decimal tags that need verification—that is, the numeric customer tags—are selected. Numerical customer tags are input into a decimal tagging model for decimal validation. The pre-defined decimal tagging model performs decimal processing on the customer tags, taking the maximum and minimum values ​​of each tag and dividing the data tag's numerical range into 10 equal parts based on predetermined decimal points. It then returns the data tag's value at each decimal point, thus clarifying the data distribution of customer tags and generating validation results for numerical customer tags. The validation results may also include the number of missing metrics for each customer tag (e.g., the number of data points where this customer tag is NULL in the entire population table), the percentage of missing metrics (e.g., the percentage of data points where this customer tag is NULL in the entire population table), the mean, maximum, minimum values, and a statistical breakdown of the data volume at each decimal point. A data control chart is generated based on the validation results output by the decimal tagging model. This data control chart visually displays the data distribution of customer tags, facilitating the rapid identification of abnormal customer tags. By setting a threshold range within the normal distribution chart, and determining that a customer tag falls outside the threshold range in the data control chart, the customer tag is identified as an abnormal data tag. This allows for the rapid identification of abnormal data tags from a massive number of customer tags, assisting insurance agents in analyzing customer characteristics from multiple perspectives. Customers can then be selected based on these tags, enabling precise customer outreach and more refined operational goals. By improving tag verification efficiency and reducing human resource investment, insurance companies can achieve cost reduction and efficiency improvement.

[0116] Based on this, the embodiments of this application obtain data tags to be verified; classify the data tags and filter out target data tags of numerical type; input the target data tags in batches into a preset decimal tag model to generate verification results of the target data tags; generate a data control chart based on the verification results; and make a reasonable judgment on the data distribution of the target data tags according to the data control chart and a preset threshold range to obtain a judgment result, including whether the target data tags belong to abnormal data tags. Based on this, by filtering out target data tags of numerical type from the verified data tags, processing the target data tags using the decimal method, feeding the target data tags into the decimal intelligent customer tag model to generate the data volume of each target data tag in each decimal place, and then making a reasonable judgment on the data distribution of each target data tag according to the data control chart and a preset threshold range, abnormal data tags in a large number of tags can be quickly identified. Compared with manual testing, this tag verification method is faster, more accurate, and more comprehensive, and can avoid missed detections. For abnormal data tags, it is convenient to backtrack and trace. Based on this, the embodiments of this application can quickly, efficiently, and accurately verify customer tags, thereby assisting insurance agents in analyzing customer characteristics from multiple perspectives, selecting customers based on tags, and achieving precise customer outreach to provide customers with more refined operational goals. By improving the efficiency of tag verification and reducing the investment of human resources, cost reduction and efficiency improvement are achieved, thereby enhancing the competitiveness of insurance agents and their insurance companies.

[0117] Please see Figure 7 This application also provides a label verification device that can implement the above-described label verification method. The device includes:

[0118] Module 710 is used to acquire the data tags to be verified.

[0119] The classification module 720 is used to classify data labels and filter out target data labels of numerical type;

[0120] The verification module 730 is used to input the target data labels in batches into the preset tenths label model for tenths method verification processing and generate the verification results of the target data labels.

[0121] Generation module 740 is used to generate data control charts based on verification results;

[0122] The judgment module 750 is used to make a reasonable judgment on the data distribution of the target data label based on the data control chart and the preset threshold range, and obtain the judgment result, including whether the target data label belongs to the abnormal data label.

[0123] In some embodiments of this application, the acquisition module 710 acquires the data tags to be verified; the classification module 720 classifies the data tags and filters out the target data tags of numerical type; the verification module 730 inputs the target data tags in batches into a preset tenths label model for tenths method verification processing and generates the verification results of the target data tags; the generation module 740 generates a data control chart based on the verification results; and the judgment module 750 makes a reasonable judgment on the data distribution of the target data tags according to the data control chart and a preset threshold range, and obtains a judgment result, which includes a judgment on whether the target data tags belong to abnormal data tags.

[0124] In some embodiments of this application, the acquisition module 710 acquires data tags to be verified. These data tags can be customer tags, which are symbolic representations of customer characteristics. Each data tag represents a perspective for understanding, observing, and describing a customer. To gain a comprehensive understanding of customers, a vast amount of rich and diverse tags from multiple perspectives and dimensions are needed. For example, in the insurance field, customer tags include: raw customer data (demographic attributes, location information, account information, etc.); customer platform activity information (information preferences, activity preferences, etc.); predictive customer tags (churn probability, recent needs, etc.); and strategic customer tags (potential customers to be retained, potential customers to be developed, etc.). By acquiring a large number of data tags, a comprehensive customer profile is created, facilitating insurance professionals to analyze customer characteristics from multiple angles, select customers based on tags, and achieve precise customer outreach, providing customers with more refined operational goals.

[0125] In some embodiments of this application, the classification module 720 classifies data tags and filters out target data tags of numerical type. In big data models, two commonly used data types are decimal and string. Decimal is used to store numerical data, while string is used to store data other than numerical data. Based on this, data tags are classified into decimal tags and string tags, and decimal tags that need to be verified, i.e., target data tags of numerical type, are filtered out. For example, in the insurance field, customer tags are classified into decimal tags and string tags, and decimal tags that need to be verified, i.e., customer tags of numerical type, are filtered out.

[0126] In some embodiments of this application, the verification module 730 inputs target data tags in batches into a preset decimal tag model for decimal method verification processing, generating verification results for the target data tags. For example, in the insurance field, numerical customer tags are input into the decimal tag model for decimal method verification processing. The preset decimal tag model is used to process customer tags using the decimal method, which involves taking the maximum and minimum values ​​of the customer tags, dividing the numerical range of the data tags into 10 equal parts according to the set decimal points, and returning the values ​​of the data tags at each decimal point, thereby clarifying the data distribution of the customer tags and generating verification results for numerical customer tags. The verification results may also include the number of missing indicators for the customer tags (e.g., the amount of data where the customer tag is NULL in the entire population wide table), the percentage of missing indicators (e.g., the percentage of data where the customer tag is NULL in the entire population wide table), the mean, maximum, minimum values, and a statistical analysis of the amount of data at each decimal point.

[0127] In some embodiments of this application, the generation module 740 generates a data control chart based on the verification results. For example, in the insurance field, a data control chart is generated based on the verification results output by the decimal tag model. The data control chart can visually display the data distribution of customer tags, facilitating the rapid identification of customer tags with anomalies.

[0128] In some embodiments of this application, the judgment module 750 performs a reasonableness judgment on the data distribution of the target data tag based on the data control chart and a preset threshold range, and obtains a judgment result, including whether the target data tag belongs to an abnormal data tag. For example, in the insurance field, for instance, by setting a threshold range on the position of the normal distribution chart, if a customer tag is determined to be outside the threshold range in the data control chart, the customer tag is judged to be an abnormal data tag. This allows for the rapid identification of abnormal data tags from a large number of customer tags, thereby assisting insurance business personnel in analyzing customer characteristics from multiple perspectives, selecting customers based on tags, and achieving precise customer outreach, providing customers with more refined operational goals. Because it improves the efficiency of tag verification and reduces the investment of human resources, it can achieve cost reduction and efficiency improvement for insurance companies.

[0129] Based on this, the label verification device of this application embodiment includes an acquisition module 710 acquiring data labels to be verified; a classification module 720 classifying the data labels and filtering out target data labels of numerical type; a verification module 730 batch inputting the target data labels into a preset tenths place label model for tenths method verification processing to generate verification results for the target data labels; a generation module 740 generating a data control chart based on the verification results; and a judgment module 750 performing a reasonableness judgment on the data distribution of the target data labels according to the data control chart and a preset threshold range to obtain a judgment result, which includes determining whether the target data labels belong to abnormal data labels. This application acquires data labels to be verified; classifies the data labels and filters out target data labels of numerical type; batch inputs the target data labels into a preset tenths place label model to generate verification results for the target data labels; generates a data control chart based on the verification results; and performs a reasonableness judgment on the data distribution of the target data labels according to the data control chart and a preset threshold range to obtain a judgment result, which includes determining whether the target data labels belong to abnormal data labels. Based on this, by filtering numerical target data tags from verified data tags, processing these target data tags using the ten-digit method, and feeding them into the ten-digit intelligent customer tag model, the data volume of each target data tag in each tenth digit is generated. Then, a data control chart and preset threshold ranges are used to judge the rationality of the data distribution of each target data tag, thereby quickly identifying abnormal data tags from a massive number of tags. Compared to manual testing, this tag verification method is faster, more accurate, and more comprehensive, and can avoid missed detections. For abnormal data tags, it facilitates backtracking. Based on this, the embodiments of this application can quickly, efficiently, and accurately verify customer tags, thereby assisting insurance agents in analyzing customer characteristics from multiple perspectives, selecting customers based on tags, and achieving precise customer outreach, providing customers with more refined operational goals. By improving the efficiency of tag verification and reducing the investment of human resources, cost reduction and efficiency improvement are achieved, thereby enhancing the competitiveness of insurance agents and their insurance companies.

[0130] The specific implementation of this label verification device is basically the same as the specific embodiment of the label verification method described above, and will not be repeated here.

[0131] 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 above-described tag verification method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0132] Please see Figure 8 , Figure 8 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0133] The processor 801 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.

[0134] The memory 802 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 802 can store the operating system and other applications. 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 802 and called and executed by the processor 801. Specifically, the method involves: acquiring the data tags to be verified; classifying the data tags and filtering out target data tags of numerical type; batch inputting the target data tags into a preset tenths digit tag model to generate verification results for the target data tags; generating a data control chart based on the verification results; and making a reasonableness judgment on the data distribution of the target data tags according to the data control chart and a preset threshold range to obtain a judgment result, which includes determining whether the target data tags belong to abnormal data tags. Based on this, by filtering numerical target data tags from verified data tags, processing these target data tags using the ten-digit method, and feeding them into the ten-digit intelligent customer tag model, the data volume of each target data tag in each tenth digit is generated. Then, a data control chart and preset threshold ranges are used to judge the rationality of the data distribution of each target data tag, thereby quickly identifying abnormal data tags from a massive number of tags. Compared to manual testing, this tag verification method is faster, more accurate, and more comprehensive, and can avoid missed detections. For abnormal data tags, it facilitates backtracking. Based on this, the embodiments of this application can quickly, efficiently, and accurately verify customer tags, thereby assisting insurance agents in analyzing customer characteristics from multiple perspectives, selecting customers based on tags, and achieving precise customer outreach, providing customers with more refined operational goals. By improving the efficiency of tag verification and reducing the investment of human resources, cost reduction and efficiency improvement are achieved, thereby enhancing the competitiveness of insurance agents and their insurance companies.

[0135] The input / output interface 803 is used to implement information input and output.

[0136] The communication interface 804 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.).

[0137] A bus transmits information between various components of a device (e.g., processor 801, memory 802, input / output interface 803, and communication interface 804).

[0138] The processor 801, memory 802, input / output interface 803, and communication interface 804 communicate with each other within the device via a bus.

[0139] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described label verification method.

[0140] 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.

[0141] The tag verification method, tag verification device, electronic device, and storage medium provided in this application embodiment acquire data tags to be verified; classify the data tags and filter out target data tags of numerical type; input the target data tags in batches into a preset decimal tag model to generate verification results for the target data tags; generate a data control chart based on the verification results; and make a reasonableness judgment on the data distribution of the target data tags according to the data control chart and a preset threshold range to obtain a judgment result, including whether the target data tags belong to abnormal data tags. Based on this, by filtering out target data tags of numerical type from the verified data tags, processing the target data tags using the decimal method, feeding the target data tags into the decimal intelligent customer tag model to generate the data volume of each target data tag in each decimal place, and then making a reasonableness judgment on the data distribution of each target data tag according to the data control chart and a preset threshold range, abnormal data tags in a large number of tags can be quickly identified. Compared with manual testing, this tag verification method is faster, more accurate, and more comprehensive, and can avoid missed detections. For abnormal data tags, it is convenient to backtrack and trace. Based on this, the embodiments of this application can quickly, efficiently, and accurately verify customer tags, thereby assisting insurance agents in analyzing customer characteristics from multiple perspectives, selecting customers based on tags, and achieving precise customer outreach to provide customers with more refined operational goals. By improving the efficiency of tag verification and reducing the investment of human resources, cost reduction and efficiency improvement are achieved, thereby enhancing the competitiveness of insurance agents and their insurance companies.

[0142] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable programs, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable programs, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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 label verification method, characterized in that, The method includes: Retrieve the data tags to be verified; The data tags are classified, and target data tags of numerical type are selected; The target data labels are input in batches into a preset tenths label model for tenths method verification processing to generate the verification results of the target data labels; A data control chart is generated based on the verification results; The data distribution of the target data label is judged for reasonableness based on the data control chart and the preset threshold range, and the judgment result is obtained. The judgment result includes judging whether the target data label belongs to abnormal data label. The step of batch inputting the target data labels into a preset tenths label model for tenths method verification processing to generate verification results for the target data labels includes: The target data labels are batch input into a preset tenths place label model for tenths method verification processing, wherein the tenths place label model defines a label processing function; Determine the number of missing indicators, the percentage of missing indicators, the mean, the maximum, and the minimum values ​​in the target data labels; Divide the numerical range between the maximum and the minimum values ​​into ten equal parts to obtain decimal places; The target data tag is embedded into the tag processing function to generate the data volume of each of the tenth positions of the target data tag; The verification result of the target data label is determined based on the number of missing indicators, the percentage of missing indicators, the mean, the maximum value, the minimum value, and the amount of data at each decimal point. The step of embedding the target data tag into the tag processing function to generate the data volume of each of the tenth positions of the target data tag includes: Import the target data tags into the YAML file; By repeatedly reading the target data tags in the YAML file and inputting the target data tags into the tag processing function, the data volume of each tenth position of the target data tag is obtained.

2. The method according to claim 1, characterized in that, The process of obtaining the data tag to be verified includes: Connect to a pre-defined big data cluster; Read the large wide table that needs to be verified from the big data cluster; Find the table structure corresponding to the wide table; Obtain the data label to be verified from the table structure.

3. The method according to claim 1, characterized in that, The process of classifying the data tags and filtering out target data tags of numerical type includes: Identify the name roots of the data tags; The name root is compared with the preset keywords to obtain the comparison result; The target data labels of numerical type are selected based on the verification results.

4. The method according to claim 1, characterized in that, The step of making a reasonable judgment on the data distribution of the target data tag based on the data control chart and a preset threshold range, and obtaining a judgment result, includes determining whether the target data tag belongs to an abnormal data tag, including: Convert the data control chart into a normal distribution chart; Determine the location of the threshold range on the normal distribution graph; If the target data label is determined to be outside the threshold range in the normal distribution plot, the target data label is determined to be an anomalous data label.

5. The method according to any one of claims 1 to 4, characterized in that, After determining the reasonableness of the data distribution of the target data tag based on the data control chart and a preset threshold range, and obtaining a determination result, the determination result includes determining whether the target data tag belongs to an abnormal data tag, and further includes: When the target data tag is determined to be an abnormal data tag, an error message is issued.

6. A label verification device, characterized in that, The device includes: The acquisition module is used to acquire the data tags to be verified. The classification module is used to classify the data tags and filter out target data tags of numerical type; The verification module is used to input the target data tags in batches into a preset tenths tag model for tenths method verification processing, and generate the verification results of the target data tags; The generation module is used to generate a data control chart based on the verification results; The judgment module is used to make a reasonable judgment on the data distribution of the target data label based on the data control chart and a preset threshold range, and to obtain a judgment result, the judgment result including whether the target data label belongs to an abnormal data label; The step of batch inputting the target data labels into a preset tenths label model for tenths method verification processing to generate verification results for the target data labels includes: The target data labels are batch input into a preset tenths place label model for tenths method verification processing, wherein the tenths place label model defines a label processing function; Determine the number of missing indicators, the percentage of missing indicators, the mean, the maximum, and the minimum values ​​in the target data labels; Divide the numerical range between the maximum and the minimum values ​​into ten equal parts to obtain decimal places; The target data tag is embedded into the tag processing function to generate the data volume of each of the tenth positions of the target data tag; The verification result of the target data label is determined based on the number of missing indicators, the percentage of missing indicators, the mean, the maximum value, the minimum value, and the amount of data at each decimal point. The step of embedding the target data tag into the tag processing function to generate the data volume of each of the tenth positions of the target data tag includes: Import the target data tags into the YAML file; By repeatedly reading the target data tags in the YAML file and inputting the target data tags into the tag processing function, the data volume of each tenth position of the target data tag is obtained.

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 label verification method according to any one of claims 1 to 5.

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 label verification method according to any one of claims 1 to 5.

Images