Index data management and control method and device, computer equipment and storage medium

Abstract

The invention belongs to the field of artificial intelligence information security, is applied to the field of intelligent government affairs, and relates to an index data management and control method, which comprises the steps of collecting management and control information for index data; performing feature extraction on the management and control information to obtain target features of multiple dimensions; generating a supervision rule model based on the target feature; and carrying out data identification control processing on to-be-controlled data by adopting the supervision rule model. The invention further provides an index data management and control device, computer equipment and a storage medium. In addition, the invention also relates to a block chain technology, and the quality inspection result can be stored in a block chain. The index data management and control quality is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, computer equipment and storage medium for controlling indicator data. Background Art

[0002] Enterprise management is inseparable from data management, and data management requires data warehouses, data middle platforms, etc. to carry it. In order to facilitate the definition, management, and use of indicators in the data middle platform, a special tool or platform is needed. From the birth of the data warehouse, to the dimensional modeling method proposed by Ralph Kimball, to the later indicator system, to the current indicator design platform, the entire tool has become increasingly mature. However, as the scale of the financial and insurance industries grows, the business methods become more and more complex, and the regulatory requirements are increasing, and the requirements for timeliness and data quality are also very strict.

[0003] The existing indicator design platform is designed based on historical experience and methodology. It cleans, converts, and verifies the original data in the source system to make it meet regulatory requirements, and then provides it to supervision. This obviously cannot respond to regulatory requirements quickly. The tables designed from the platform often fail to meet the regulatory verification rules, resulting in poor data management effects. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method, device, computer equipment and storage medium for controlling indicator data to improve the quality of indicator data control.

[0005] In order to solve the above technical problems, the present application embodiment provides a method for controlling indicator data, which adopts the following technical solution:

[0006] Collect control information for indicator data;

[0007] Extracting features from the control information to obtain target features of several dimensions;

[0008] Based on the target characteristics, a regulatory rule model is generated;

[0009] The regulatory rule model is used to perform data identification and control processing on the data to be controlled.

[0010] Furthermore, the step of collecting control information for indicator data specifically includes:

[0011] Obtaining at least one preset uniform resource locator;

[0012] By means of a web crawler, crawling and analyzing the page file corresponding to the preset uniform resource locator to obtain the content contained in the page file corresponding to the preset uniform resource locator;

[0013] By means of fuzzy matching, the regulatory rules related to the indicator data are extracted from the content contained in the page file corresponding to the preset uniform resource locator as the control information.

[0014] Furthermore, the step of extracting features from the control information to obtain target features of several dimensions specifically includes:

[0015] Using natural language semantic understanding to extract key information and word roots, the key information includes subject domains, metric words, keywords, modifiers, and dimension attributes;

[0016] The key information and the root word are fused to obtain the target feature.

[0017] Furthermore, the step of fusing the key information and the root word to obtain the target feature specifically includes:

[0018] Vectorizing the key information and the root word respectively to obtain a first vector and a second vector;

[0019] By using an attention mechanism, encoding and weighting the first vector and the second vector to obtain an enhanced vector;

[0020] A splicing method is adopted to mix, splice and fuse at least any two of the first vector, the second vector and the enhanced vector to obtain the target feature.

[0021] Furthermore, the step of generating a regulatory rule model based on the target characteristics specifically includes:

[0022] Based on the supervision rules of the indicator data and the target characteristics, a supervision table is designed, wherein the supervision table includes a dimension table, a detail-level fact table, and a summary-level fact table;

[0023] Trigger the supervision rules, verify the association between each supervision table, and obtain the verification results;

[0024] If the verification result is that the verification is passed, the supervision table and the target feature are associated and mapped to obtain the supervision rule model.

[0025] Furthermore, the step of using the regulatory rule model to perform data identification and control processing on the data to be controlled specifically includes:

[0026] When receiving a data supervision request, extracting the data to be controlled from the data supervision request;

[0027] Performing data cleaning and standardization on the data to be controlled to obtain standard data;

[0028] Perform type identification on the standard data to obtain a type identification result, determine a target supervision table based on a target feature corresponding to the type identification result, and use the target supervision table to verify and control the standard data.

[0029] Furthermore, after the step of using the regulatory rule model to perform data identification and control processing on the data to be controlled, the control method of indicator data specifically further includes the following steps:

[0030] Collect control information regularly as real-time control information;

[0031] If the real-time control information and the control information in the supervision rule model change, the supervision rule model is dynamically updated based on the real-time control information.

[0032] In order to solve the above technical problems, the embodiment of the present application also provides a control device for indicator data, which adopts the following technical solution:

[0033] The collection module is used to collect management and control information for indicator data;

[0034] An extraction module, used to extract features from the control information to obtain target features of several dimensions;

[0035] A generation module, used for generating a regulatory rule model based on the target characteristics;

[0036] The control module is used to adopt the regulatory rule model to perform data identification and control processing on the controlled data.

[0037] Furthermore, the acquisition module includes:

[0038] An acquisition unit, used to acquire at least one preset uniform resource locator;

[0039] A crawling unit, used to crawl and analyze the page file corresponding to the preset uniform resource locator by means of a network crawler, and obtain the content contained in the page file corresponding to the preset uniform resource locator;

[0040] The matching unit is used to extract the regulatory rules related to the indicator data from the content contained in the page file corresponding to the preset uniform resource locator through fuzzy matching as the management and control information.

[0041] Furthermore, the extraction module comprises:

[0042] An extraction unit, for extracting key information and word roots by natural language semantic understanding, wherein the key information includes subject domains, metric words, keywords, modifiers, and dimension attributes;

[0043] The fusion unit is used to fuse the key information and the root word to obtain the target feature.

[0044] Furthermore, the fusion unit comprises:

[0045] A vectorization subunit, used for vectorizing the key information and the root word respectively to obtain a first vector and a second vector;

[0046] An encoding subunit, configured to perform encoding weighting on the first vector and the second vector through an attention mechanism to obtain an enhanced vector;

[0047] The splicing subunit is used to adopt a splicing method to mix and splice at least any two of the first vector, the second vector and the enhanced vector to obtain the target feature.

[0048] Furthermore, the generating module comprises:

[0049] A design unit, configured to design a supervision table based on the supervision rules of the indicator data and the target characteristics, wherein the supervision table includes a dimension table, a detail-level fact table, and a summary-level fact table;

[0050] A trigger unit is used to trigger the supervision rules, verify the association between various supervision tables, and obtain the verification results;

[0051] The verification unit is used to, if the verification result is that the verification is passed, associate and map the supervision table with the target feature to obtain the supervision rule model.

[0052] Furthermore, the control module includes:

[0053] A data extraction unit, configured to extract the data to be managed from the data management request when receiving the data management request;

[0054] A data cleaning unit, used for cleaning and standardizing the data to be controlled to obtain standard data;

[0055] The type identification unit is used to perform type identification on the standard data to obtain a type identification result, determine a target supervision table according to a target feature corresponding to the type identification result, and use the supervision table to verify and control the standard data.

[0056] Furthermore, the control device for the indicator data further includes:

[0057] The regular collection module is used to regularly collect management and control information as real-time management and control information;

[0058] A dynamic update module is used to dynamically update the supervision rule model based on the real-time control information if the real-time control information and the control information in the supervision rule model change.

[0059] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0060] Collect control information for indicator data;

[0061] Extracting features from the control information to obtain target features of several dimensions;

[0062] Based on the target characteristics, a regulatory rule model is generated;

[0063] The regulatory rule model is used to perform data identification and control processing on the data to be controlled.

[0064] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0065] Collect control information for indicator data;

[0066] Extracting features from the control information to obtain target features of several dimensions;

[0067] Based on the target characteristics, a regulatory rule model is generated;

[0068] The regulatory rule model is used to perform data identification and control processing on the data to be controlled.

[0069] Compared with the prior art, the embodiments of the present application have the following beneficial effects: by extracting features from the control information, generating a regulatory rule model based on the extracted target features, and then using the regulatory rule model to identify and control the data, it is possible to integrate regulatory requirements from numerous sources into the regulatory rule model, thereby ensuring regulatory compliance and improving regulatory efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0071] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0072] Figure 2A flowchart of an embodiment of a method for controlling indicator data according to the present application;

[0073] Figure 3 is a structural schematic diagram of an embodiment of an indicator data control device according to the present application;

[0074] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0075] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0076] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0077] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0078] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0079] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0080] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0081] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0082] It should be noted that the indicator data control method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the indicator data control device is generally set in the server / terminal device.

[0083] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0084] Continue to refer Figure 2 , shows a flow chart of an embodiment of a real-time dual recording method according to the present application. The index data management and control method comprises the following steps:

[0085] Step S201, collecting management and control information for indicator data.

[0086] In this embodiment, the index data management and control method is executed on the electronic device (eg Figure 1 shown Serve Device / Terminal Equipment ) can receive indicator data (data to be controlled) through a wired connection or a wireless connection. It should be noted that the above wireless connection methods may include but are not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wi deband) connection, and other wireless connection methods currently known or to be developed in the future.

[0087] Specifically, to ensure that the regulatory rules are accurate and authoritative, this embodiment verifies and collects corresponding regulatory documents and regulatory specifications from multiple channels such as the websites and forums of various authoritative institutions. For example, it collects notices and documents issued by the State Financial Supervision and Administration Bureau and its subordinate branches to insurance companies; collects documents from the official website of the bureau; and collects existing regulatory specifications in combination with the current existing regulatory logic in the industry.

[0088] The specific method of collection may be through downloading, crawling, etc., which is not specifically limited here.

[0089] Step S202: extract features from the management and control information to obtain target features in several dimensions.

[0090] Specifically, after obtaining the control information, information recognition and extraction are performed on the control information according to the natural language semantic recognition method to obtain target features of multiple dimensions.

[0091] The target features specifically include but are not limited to key information, word roots, and a combination of key information and word roots. The key information includes but is not limited to subject domains, metric words, keywords, modifiers, and dimension attributes.

[0092] Step S203: Generate a supervision rule model based on the target characteristics.

[0093] Specifically, a regulatory rule model is generated based on the obtained target characteristics and regulatory requirements.

[0094] For example, in the financial field, the definitions of metrics and dimensional attributes refer to the corresponding definitions of the model, covering subject areas such as customers, products, sales force management, and support services, involving business processes such as new contract underwriting, insurance, preservation, and claims, and generating a regulatory rule model.

[0095] Step S204: adopt the supervision rule model to perform data identification and control processing on the data to be controlled.

[0096] In this embodiment, features are extracted from the control information, and a regulatory rule model is generated based on the extracted target features. The regulatory rule model is then used to identify and control the data, thereby integrating regulatory requirements from numerous sources into the regulatory rule model to ensure regulatory compliance while improving regulatory efficiency.

[0097] In some optional implementations, in step S201, the step of collecting management and control information for indicator data specifically includes:

[0098] Obtaining at least one preset uniform resource locator;

[0099] By means of a web crawler, crawl and analyze the page file corresponding to the preset uniform resource locator to obtain the content contained in the page file corresponding to the preset uniform resource locator;

[0100] By means of fuzzy matching, regulatory rules related to the indicator data are extracted from the content contained in the page file corresponding to the preset uniform resource locator as management and control information.

[0101] Specifically, before crawling the management and control information of the indicator data, it is necessary to obtain a preset uniform resource locator, each preset uniform resource locator corresponds to at least one page file, and the management and control information can be obtained through the page file corresponding to the uniform resource locator.

[0102] Among them, the Uniform Resource Locator (URL) is a concise representation of the location and access method of resources that can be obtained from the Internet. It is the address of standard resources on the Internet, such as the website of the State Administration of Financial Supervision and Administration, or the storage path of the financial management system within an enterprise.

[0103] Furthermore, due to the huge crawling range and number of web crawlers, the crawling speed and storage space requirements are relatively high, and the order requirements for crawling pages are relatively low. At the same time, due to the large number of pages to be refreshed, a parallel working mode is usually adopted. The structure of the web crawler can be roughly divided into a page crawling module, a page analysis module, a link filtering module, a page database, a URL queue, and an initial URL set. In order to improve work efficiency, general web crawlers will adopt certain crawling strategies. Common crawling strategies are: depth-first strategy and breadth-first strategy.

[0104] The basic method of the depth-first strategy is to visit the next level of web page links in order from low to high depth until it can no longer go deeper. After completing a crawl branch, the crawler returns to the previous link node to further search for other links. When all links are traversed, the crawling task ends.

[0105] Among them, the breadth-first strategy is to crawl pages according to the depth of the web page content directory hierarchy. Pages in the shallower directory hierarchy are crawled first. When the pages in the same hierarchy are crawled, the crawler will go deeper into the next level to continue crawling. This strategy can effectively control the crawling depth of the page and avoid the problem of being unable to end the crawling when encountering an infinitely deep branch. It is easy to implement and does not require the storage of a large number of intermediate nodes.

[0106] Preferably, the crawling strategy adopted in the embodiment of the present invention is a breadth-first strategy, which first crawls a preset uniform resource locator to obtain multiple page files corresponding to the preset uniform resource locator, and then subsequently crawls each page file to obtain the management and control information of the indicator data contained in each page file, thereby avoiding the extra time expenditure caused by crawling too much useless information and improving the crawling efficiency.

[0107] Furthermore, the management and control information of the indicator data is extracted from the content contained in the page file corresponding to the preset uniform resource locator by means of fuzzy matching.

[0108] Among them, the fuzzy matching methods include but are not limited to: fuzzy matching based on string pattern matching (Horspool) algorithm, fuzzy matching based on Trie tree to realize search terms, fuzzy matching based on jquery selector, etc.

[0109] In this embodiment, the management and control information of the indicator data is intelligently crawled through the uniform resource locator, which expands the source, and at the same time, saves the time of obtaining the management and control information of the indicator data, and improves the efficiency of obtaining the management and control information.

[0110] In some optional implementations, in step S202, the step of extracting features from the control information to obtain target features of several dimensions specifically includes:

[0111] Use natural language semantic understanding to extract key information and word roots. Key information includes subject domains, measurement words, keywords, modifiers, and dimension attributes.

[0112] The key information and word roots are fused to obtain the target features.

[0113] In a specific example, the natural language semantic understanding method was used to sort out the standard logic of the EAST life insurance company supervision standardization data submission standard No. 50, the anti-money laundering law enforcement inspection No. 63, the insurance statistical information system, the banking and insurance industry related transaction supervision system data filling specification (insurance institutions), and the China Insurance Registration System, and extracted the supervision model suitable for the indicator platform from each standard. The model includes the subject domain, modifiers, modification types, atomic indicators, measurements, dimension attributes and other elements, and the root word is mapped from the standard. Then, the root word and key information are combined to obtain the target feature.

[0114] In some optional implementations, the step of fusing the key information and the root word to obtain the target feature specifically includes:

[0115] Vectorize the key information and the root word respectively to obtain the first vector and the second vector;

[0116] Through the attention mechanism, the first vector and the second vector are encoded and weighted to obtain an enhanced vector;

[0117] A splicing method is adopted to mix and splice at least any two of the first vector, the second vector and the enhanced vector to obtain the target feature.

[0118] Specifically, the vectorization methods include but are not limited to: One-Hot encoding, Bag Of Words (BOW), TF-IDF, N-gram, Word Embeddings such as Word2Vec, GloVe, FastText, Doc2Vec, neural network-based Tokenizers such as BERT Tokenizer, and feature aggregation modules that consider contextual information such as SFAM (Scale Feature Aggregation Module) and CAM (Context Enhancement Module).

[0119] In this embodiment, the technical means of the attention mechanism include but are not limited to: soft attention (SoftAttention), hard attention (Hard Attention), self-attention (Self-Attention), multi-head attention (Multi-Head Attention), encoder-decoder attention (Encoder-Decoder Attention), attention gates (Attention Gates), graph attention networks (Graph Attention Networks, GATs), attention pooling (Attention Pooling), dynamic attention (Dynamic Attention), attention in reinforcement learning (Reinforcement Attention), etc.

[0120] In this embodiment, by extracting features from the management and control information, target features of several dimensions are obtained, so that the diversified management and control information can be quantified, which is beneficial to the subsequent construction and generation of the supervision model.

[0121] In some optional implementations, in step S203, the step of generating a regulatory rule model based on the target features specifically includes:

[0122] Based on the supervision rules and target characteristics of the indicator data, design the supervision table, which includes the dimension table, detail-level fact table and summary-level fact table;

[0123] Trigger the supervision rules, verify the association between each supervision table, and obtain the verification results;

[0124] If the verification result is passed, the supervision table and the target features are associated and mapped to obtain the supervision rule model.

[0125] Specifically, the target feature is used as one of the data sources of the supervision table, including internal databases, external data providers or real-time data streams. The supervision rules of indicator data are derived from actual needs and goals.

[0126] In this embodiment, regulatory rules are defined based on business logic and regulatory requirements. These rules will be used to automatically monitor data compliance and trigger alarms when anomalies are detected. Regulatory tables are used to store descriptive, non-quantitative data that are used to classify and describe factual data. For example, time dimension, geographic dimension, product dimension, etc.

[0127] The detail-level fact table stores the most detailed data records, each of which contains a measure value and a foreign key associated with the dimension table. These tables usually contain atomic-level data, such as detailed information on each transaction or event.

[0128] Summary-level fact tables store aggregated data, which is obtained by summarizing data from detail-level fact tables. These tables are used for fast query and reporting, reducing the computational burden when querying detail data.

[0129] Define primary keys and foreign keys for regulatory tables to ensure data integrity and accuracy. Primary keys uniquely identify each record in a table, while foreign keys are used to establish and maintain relationships between tables.

[0130] Furthermore, ensure that the data model complies with normalization principles to reduce data redundancy and improve data integrity. This may involve breaking down tables into smaller, more specific tables and ensuring consistency in data types and formats.

[0131] Furthermore, when designing the regulatory table, you need to ensure that the relationships between tables are correct. This includes checking foreign key constraints, data consistency, and data integrity.

[0132] In this embodiment, subsequent data quality inspection is performed by generating a regulatory rule model that meets the requirements, thereby improving the efficiency and quality of the quality inspection.

[0133] In some optional implementations, in step S204, the step of using the regulatory rule model to perform data identification and control processing on the data to be controlled specifically includes:

[0134] When receiving a data supervision request, extract the data to be controlled from the data supervision request;

[0135] Clean and standardize the data to be controlled to obtain standard data;

[0136] Perform type identification on the standard data to obtain a type identification result, determine a target supervision table based on the target feature corresponding to the type identification result, and use the target supervision table to verify and control the standard data.

[0137] In this embodiment, after the data to be controlled is standardized, the supervision table in the supervision rule model is used to perform rapid verification and control, thereby improving the efficiency of verification and control.

[0138] In some optional implementations, after adopting the regulatory rule model to perform data identification and control processing on the data to be controlled, the control method of indicator data specifically further includes the following steps:

[0139] Collect control information regularly as real-time control information;

[0140] If the real-time control information and the control information in the regulatory rule model change, the regulatory rule model is dynamically updated based on the real-time control information.

[0141] In this embodiment, the supervision rule model is dynamically updated by regularly collecting control information to ensure that the supervision rule model meets the requirements and is accurate.

[0142] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0143] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0144] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0145] This application can be applied in the field of smart real-time dual recording, thereby promoting the construction of smart cities.

[0146] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0147] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0148] Further references Figure 3 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of an indicator data control device, and the device embodiment is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0149] like Figure 3 As shown, the indicator data control device 300 described in this embodiment includes: a collection module 301, an extraction module 302, a generation module 303 and a control module 304. Among them:

[0150] A collection module 301 is used to collect management and control information for indicator data;

[0151] An extraction module 302 is used to extract features from the control information to obtain target features of several dimensions;

[0152] A generation module 303, used to generate a supervision rule model based on target features;

[0153] The control module 304 is used to adopt a regulatory rule model to perform data identification and control processing on the data to be controlled.

[0154] In this embodiment, features are extracted from the control information, and a regulatory rule model is generated based on the extracted target features. The regulatory rule model is then used to identify and control the data, thereby integrating regulatory requirements from numerous sources into the regulatory rule model to ensure regulatory compliance while improving regulatory efficiency.

[0155] In some optional implementations of this embodiment, the acquisition module 301 includes:

[0156] An acquisition unit, used to acquire at least one preset uniform resource locator;

[0157] A crawling unit, used to crawl and analyze the page file corresponding to the preset uniform resource locator by means of a network crawler, and obtain the content contained in the page file corresponding to the preset uniform resource locator;

[0158] The matching unit is used to extract regulatory rules related to the indicator data as management and control information from the content contained in the page file corresponding to the preset uniform resource locator through fuzzy matching.

[0159] In this embodiment, the management and control information of the indicator data is intelligently crawled through the uniform resource locator, which expands the source, and at the same time, saves the time of obtaining the management and control information of the indicator data, and improves the efficiency of obtaining the management and control information.

[0160] In some optional implementations of this embodiment, the extraction module 302 includes:

[0161] An extraction unit is used to extract key information and word roots by natural language semantic understanding. The key information includes subject domains, metric words, keywords, modifiers, and dimension attributes.

[0162] The fusion unit is used to fuse key information and word roots to obtain target features.

[0163] In some optional implementations of this embodiment, the fusion unit includes:

[0164] A vectorization subunit, used for vectorizing the key information and the root word respectively to obtain a first vector and a second vector;

[0165] An encoding subunit, configured to perform encoding weighting on the first vector and the second vector through an attention mechanism to obtain an enhanced vector;

[0166] The splicing subunit is used to adopt a splicing method to mix and splice at least any two of the first vector, the second vector and the enhanced vector to obtain the target feature.

[0167] In this embodiment, by extracting features from the management and control information, target features of several dimensions are obtained, so that the diversified management and control information can be quantified, which is beneficial to the subsequent construction and generation of the supervision model.

[0168] In some optional implementations of this embodiment, the generating module 303 includes:

[0169] Design unit, which is used to design supervision tables based on supervision rules and target characteristics of indicator data. Supervision tables include dimension tables, detail-level fact tables, and summary-level fact tables.

[0170] A trigger unit is used to trigger the supervision rules, verify the association between various supervision tables, and obtain the verification results;

[0171] The verification unit is used to associate and map the supervision table and the target feature to obtain a supervision rule model if the verification result is that the verification is passed.

[0172] In this embodiment, subsequent data quality inspection is performed by generating a regulatory rule model that meets the requirements, thereby improving the efficiency and quality of the quality inspection.

[0173] In some optional implementations of this embodiment, the management and control module 304 includes:

[0174] A data extraction unit, configured to extract the data to be managed from the data management request when receiving the data management request;

[0175] The data cleaning unit is used to clean and standardize the data to be controlled to obtain standard data;

[0176] The type identification unit is used to perform type identification on the standard data to obtain a type identification result, determine a target supervision table according to a target feature corresponding to the type identification result, and use the target supervision table to verify and control the standard data.

[0177] In this embodiment, after the data to be controlled is standardized, the supervision table in the supervision rule model is used to perform rapid verification and control, thereby improving the efficiency of verification and control.

[0178] In some optional implementations of this embodiment, the indicator data management and control device further includes:

[0179] The regular collection module is used to regularly collect management and control information as real-time management and control information;

[0180] The dynamic update module is used to dynamically update the supervision rule model based on the real-time control information if the real-time control information and the control information in the supervision rule model change.

[0181] In this embodiment, the supervision rule model is dynamically updated by regularly collecting control information to ensure that the supervision rule model meets the requirements and is accurate.

[0182] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0183] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 4 with a memory 41, a processor 42, and a network interface 43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0184] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0185] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or D real-time dual recording memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the control method of indicator data, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0186] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions or process data stored in the memory 41, such as computer-readable instructions for running the control method of the indicator data.

[0187] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0188] By extracting features from control information, generating a regulatory rule model based on the extracted target features, and then using the regulatory rule model to identify and control data, it is possible to integrate regulatory requirements from numerous sources into the regulatory rule model to ensure regulatory compliance while improving regulatory efficiency.

[0189] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the indicator data management and control method as described above.

[0190] By extracting features from control information, generating a regulatory rule model based on the extracted target features, and then using the regulatory rule model to identify and control data, it is possible to integrate regulatory requirements from numerous sources into the regulatory rule model to ensure regulatory compliance while improving regulatory efficiency.

[0191] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0192] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to replace some of the technical features therein with equivalents. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is also within the scope of patent protection of this application.

Claims

1. A method for controlling indicator data, characterized in that: The steps include: Collect control information for indicator data; Extracting features from the control information to obtain target features of several dimensions; Based on the target characteristics, a regulatory rule model is generated; The regulatory rule model is used to perform data identification and control processing on the data to be controlled.

2. The method for controlling indicator data according to claim 1, characterized in that: The step of collecting control information for indicator data specifically includes: Obtaining at least one preset uniform resource locator; By means of a web crawler, crawling and analyzing the page file corresponding to the preset uniform resource locator to obtain the content contained in the page file corresponding to the preset uniform resource locator; By means of fuzzy matching, the regulatory rules related to the indicator data are extracted from the content contained in the page file corresponding to the preset uniform resource locator as the control information.

3. The method for controlling indicator data according to claim 1, characterized in that: The step of extracting features from the control information to obtain target features of several dimensions specifically includes: Using natural language semantic understanding to extract key information and word roots, the key information includes subject domains, metric words, keywords, modifiers, and dimension attributes; The key information and the root word are fused to obtain the target feature.

4. The method for controlling indicator data according to claim 3, characterized in that: The step of fusing the key information and the root word to obtain the target feature specifically includes: Vectorizing the key information and the root word respectively to obtain a first vector and a second vector; By using an attention mechanism, encoding and weighting the first vector and the second vector to obtain an enhanced vector; A splicing method is adopted to mix and splice at least any two of the first vector, the second vector and the enhanced vector to obtain the target feature.

5. The method for controlling indicator data according to claim 1, characterized in that: The step of generating a regulatory rule model based on the target characteristics specifically includes: Based on the supervision rules of the indicator data and the target characteristics, a supervision table is designed, wherein the supervision table includes a dimension table, a detail-level fact table, and a summary-level fact table; Triggering the supervision rules, verifying the associations between the supervision tables, and obtaining the verification results; If the verification result is that the verification is passed, the supervision table and the target feature are associated and mapped to obtain the supervision rule model.

6. The method for controlling indicator data according to claim 5, characterized in that: The step of using the regulatory rule model to perform data identification and control processing on the data to be controlled specifically includes: When receiving a data supervision request, extracting the data to be controlled from the data supervision request; Performing data cleaning and standardization on the data to be controlled to obtain standard data; Perform type identification on the standard data to obtain a type identification result, determine a target supervision table based on a target feature corresponding to the type identification result, and use the target supervision table to verify and control the standard data.

7. The method for controlling indicator data according to claim 1, characterized in that: After the step of using the regulatory rule model to perform data identification and control processing on the data to be controlled, the control method of indicator data specifically further includes the following steps: Collect control information regularly as real-time control information; If the real-time control information and the control information in the supervision rule model change, the supervision rule model is dynamically updated based on the real-time control information.

8. A control device for indicator data, characterized in that: include: The collection module is used to collect management and control information for indicator data; An extraction module, used to extract features from the control information to obtain target features of several dimensions; A generation module, used for generating a regulatory rule model based on the target characteristics; The control module is used to adopt the regulatory rule model to perform data identification and control processing on the controlled data.

9. A computer device, characterized in that: It includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the indicator data management and control method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the indicator data management and control method according to any one of claims 1 to 7 are implemented.

Images