Verification method and device based on registration data, equipment, storage medium and product

Abstract

The invention relates to the technical field of data processing, and provides a verification method and device based on registration data, equipment, a storage medium and a product, and the method comprises the steps: obtaining registration file information from a registration platform according to a user query request; performing text extraction on the registration file information to obtain structured registration data; acquiring asset data associated with the registration data from an asset pool database; wherein the asset pool database is connected with a plurality of business systems, and asset data in the asset pool database is obtained by performing data processing on original data in each business system; and performing risk information verification processing according to the registration data and the associated asset data to obtain a verification result. According to the method, the registration file in the registration platform can be analyzed, the asset pool database can be created, the asset data in the asset pool database can be introduced for verification, the corresponding verification result can be automatically output, automatic verification of the registration data can be completed without manual participation, and the verification efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to verification methods, devices, equipment, storage media and products based on registration data. Background Art

[0002] The Movable Property Financing Unified Registration Platform (abbreviated as: Zhongdeng.com) is mainly used for the registration and publicity of movable property for the purpose of financing, and provides an important infrastructure for the development of supply chain finance business. By querying the registration platform, financial institutions can timely understand the collateral status of enterprises, which is helpful for risk prevention and control.

[0003] For example, when the authenticity of customer assets needs to be verified, the verification personnel need to manually check the corresponding customer's registration information on the China Securities Depository and Clearing Corporation Limited website to verify whether the information is consistent. However, this manual verification method requires a lot of manual review time. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the related art. To this end, the present application proposes a verification method based on registration data, which can automatically verify the registration data without manual participation, thereby improving the verification efficiency.

[0005] The present application also proposes a verification device, electronic device, storage medium and computer program product based on registration data.

[0006] According to the verification method based on registration data of the first aspect of the embodiment of the present application, the method includes: obtaining registration file information from a registration platform according to a user query request; performing text extraction on the registration file information to obtain structured registration data; obtaining asset data associated with the registration data from an asset pool database; wherein the asset pool database is connected to multiple business systems, and the asset data in the asset pool database is obtained by performing data processing on the original data in each business system; performing risk information verification processing based on the registration data and the associated asset data to obtain a verification result.

[0007] According to the verification method based on registration data in the embodiment of the present application, the registration files in the registration platform can be parsed, a new asset pool database can be created, and the asset data in the asset pool database can be introduced for verification and validation, and the corresponding verification results can be automatically output. Automatic verification of registration data can be completed without human intervention, thereby improving verification efficiency.

[0008] According to one embodiment of the present application, text extraction is performed on registration file information to obtain structured registration data, including: converting the content of the registration file information into a text layout, wherein the text layout includes a number of texts and coordinate information of each text on the layout; determining a target template based on the registration file information; segmenting the text layout based on the target template and the coordinate information to obtain a number of target position areas, each target position area including target information; and organizing the target information of the several target position areas to obtain structured registration data.

[0009] According to one embodiment of the present application, the text layout is segmented according to the target template and coordinate information to obtain a number of target position areas, each target position area includes target information, including: the text layout is segmented according to the target template and coordinate information to obtain the target position area; wherein the target position area includes at least one of a basic information area, a personnel information area and a property information area; the target information in the basic information area includes at least one of a registration number, a registration type and a registration time; the target information in the personnel information area includes at least one of a filler, a transferor and a transferee; the target information in the property information area includes a property description.

[0010] According to one embodiment of the present application, asset data associated with registration data is obtained from an asset pool database, including: obtaining associated words based on the registration data; wherein the associated words include at least one of the registration number, the person filling out the form, the transferor, the transferee and the property description; and determining matching asset data from the asset pool database as associated asset data based on the associated words.

[0011] According to one embodiment of the present application, risk information verification is performed based on registration data and associated asset data to obtain a verification result, including: verifying whether the contents of the registration data and the associated asset data are consistent, marking the consistent content, and obtaining a first marking result; verifying whether the description content in the registration data complies with preset rules, marking the description content that does not comply with the preset rules, and obtaining a second marking result; obtaining a verification result based on the first marking result and the second marking result.

[0012] According to one embodiment of the present application, before obtaining the asset data associated with the registration data from the asset pool database, it also includes: obtaining original data through multiple business systems; performing text extraction on non-text format data in the original data to obtain first intermediate data; performing data processing on the first intermediate data and the text format data in the original data to obtain asset data, and storing the asset data in the asset pool database.

[0013] According to one embodiment of the present application, determining a target template based on registration file information includes: obtaining at least one sample registration file information; classifying the sample registration file information and setting a sample template for each category of sample registration file information; and determining a sample template of the same category from the sample templates as a target template based on the category of the registration file information.

[0014] According to the second aspect of the embodiment of the present application, the verification device based on registration data includes: a first acquisition module, used to obtain registration file information from a registration platform according to a user query request; an extraction module, used to perform text extraction on the registration file information to obtain structured registration data; a second acquisition module, used to obtain asset data associated with the registration data from an asset pool database; wherein the asset pool database is connected to multiple business systems, and the asset data in the asset pool database is obtained by processing the original data in each business system; a verification module, used to perform risk information verification processing based on the registration data and the associated asset data to obtain a verification result.

[0015] According to an electronic device of an embodiment of the third aspect of the present application, the electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device implements any of the above-mentioned verification methods based on registration data.

[0016] According to the non-transitory computer-readable storage medium of the fourth aspect embodiment of the present application, a computer program is stored thereon, and when the computer program is executed by a processor, any of the above-mentioned verification methods based on registration data is implemented.

[0017] According to the computer program product of the fifth aspect of the present application, the computer program includes a computer program, which, when executed by a processor, implements any of the above-mentioned verification methods based on registration data.

[0018] The above one or more technical solutions in the embodiments of the present application have at least one of the following technical effects: Parse the registration documents in the registration platform, create a new asset pool database and introduce the asset data in the asset pool database for verification and validation, automatically output the corresponding verification results, and complete the automatic verification of registration data without manual participation, thereby improving the verification efficiency; Furthermore, the text layout can be segmented by coordinate information to extract target information, thereby completing the parsing of the registration document without the need for optical character recognition (OCR) related technology, thereby reducing deployment and maintenance costs; Furthermore, by applying big data platform technology, it is possible to collect raw data sets scattered across different business systems, process them to generate data required for the business, batch process and calculate customer asset-related indicator data, and establish a reliable and accurate asset pool database, thereby obtaining customer-related asset data conveniently and efficiently.

[0019] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 It is a flowchart of the verification method based on registration data provided in an embodiment of the present application.

[0022] Figure 2 It is a structural diagram of the asset pool database provided in an embodiment of the present application.

[0023] Figure 3 It is a working diagram of the risk control engine provided in an embodiment of the present application.

[0024] Figure 4 It is a structural diagram of a verification device based on registration data provided in an embodiment of the present application.

[0025] Figure 5 It is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The following is a further detailed description of the implementation of the present application in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but cannot be used to limit the scope of the present application.

[0027] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiments of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0028] It should be noted that all actions of acquiring signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located, and with the authorization given by the owner of the corresponding device.

[0029] This application embodiment provides a verification method based on registration data, please refer to Figure 1 , Figure 1 1 is a flow chart of a verification method based on registration data provided in an embodiment of the present application. In this embodiment, the verification method based on registration data may include steps 110 to 140, and each step is specifically as follows: Step 110: Obtain registration file information from the registration platform according to the user query request.

[0030] This embodiment is applied to data verification in the field of financial technology, for example, involving a credit duplication checking system based on big data processing and risk control engine; the credit duplication checking system is designed for credit pledge, factoring transfer and other business to improve the accuracy and efficiency of checking whether there is duplication in the registration.

[0031] The user can log in to the registration platform through the account information, and can send a query request to the registration platform through command operation. The registration platform can be China Securities Depository and Clearing Corporation Limited or other financial registration platforms.

[0032] Optionally, before sending the user query request, the user is required to register on the registration platform. After successful registration, the registration platform generates the user's account information.

[0033] After receiving the user's query request, the registration platform can retrieve the corresponding registration file information from its own database and send it to the user in response to the user's query request.

[0034] Step 120: Perform text extraction on the registration file information to obtain structured registration data.

[0035] In this embodiment, by reading the text information in the registration file information, structured registration data can be obtained through sorting. The structured registration data refers to data organized according to specific formats and rules to facilitate data analysis and verification in subsequent steps. For example, each data in the structured registration data has a clear field name and data type, and the relationship between the data can be clearly defined.

[0036] In this step, different text extraction methods can be adopted according to the type of registration file information. If the registration file information is in text format, text extraction can be directly performed on the registration file information in text format, and structured registration data can be obtained after sorting; if the registration file information is in image format, the registration file information in image format is converted into text format, and then subsequent processing is performed in the same manner as the registration file information in text format; if the registration file information is in formats other than image format and text format, the registration file information in other formats is converted into image format, and then subsequent processing is performed in the same manner as the registration file information in image format.

[0037] Optionally, the technologies used in the text extraction process include but are not limited to regular expressions, natural language processing, information extraction and optical character recognition.

[0038] Step 130: Obtain asset data associated with the registration data from the asset pool database.

[0039] Among them, the asset pool database is connected to multiple business systems, and the asset data in the asset pool database is obtained by processing the original data in each business system.

[0040] In this step, the registration data obtained through the above steps can be used to obtain associated asset data from the asset pool database, and the associated asset data is data obtained from other business systems.

[0041] See also Figure 2 , Figure 2 It is a structural diagram of the asset pool database provided in an embodiment of the present application.

[0042] Users' asset data is provided by multiple internal and external systems, as well as manually uploaded data. The data types are diverse, and big data technology is needed to process and clean data from different data sources, summarize indicator data according to customer dimensions, and output them uniformly through data interfaces.

[0043] In this embodiment, the asset pool database can be regarded as a big data platform 210, which connects multiple business systems as data sources 200 such as inventory, orders, finance, contracts, invoices, etc., and provides a data interface 220 for external inquiries, so as to obtain related asset information conveniently and efficiently. Furthermore, the big data platform 210 can have functions such as offline computing, real-time computing, and machine learning.

[0044] For example, the data source can be directly obtained from various modules of the Enterprise Resource Planning (ERP) system, or users can independently upload contract and invoice data to provide asset proof.

[0045] After the data source is determined, the big data platform-related technologies can be used to centrally collect and process data scattered in different places to generate data required for the business.

[0046] For example, for order, financial and other system data, by building a data warehouse, we extract original data from various business systems every day, and batch process and calculate customer asset-related indicator data; to ensure the accuracy and real-time nature of the data, the real-time calculation system synchronizes business system data at the time of query, and promptly processes and updates core data, providing a reliable data foundation for subsequent decision-making.

[0047] For example, for unstructured data such as invoice and contract images and documents, we introduce and deploy OCR (Optical Character Recognition) algorithms to perform image recognition, complete key information reading, and reduce manual data entry work.

[0048] The above big data calculation and processing can establish the latest asset pool database, and then provide call query through the data interface 220, so as to obtain asset information conveniently and efficiently.

[0049] Step 140: Perform risk information verification based on the registration data and associated asset data to obtain verification results.

[0050] In order to avoid the financial risk of users repeatedly pledging or transferring assets, a risk control engine is introduced in this embodiment, which is used to automatically check the registration data and the associated asset data. The risk control engine is deployed with preset verification rules, which can check the registration data and the associated asset data involved in this business.

[0051] See also Figure 3 , Figure 3 300 is a working diagram of the risk control engine provided in the embodiment of the present application. The content executed by the risk control engine 300 includes steps 301 to 303, and each step is specifically as follows: Step 301: Data acquisition.

[0052] The risk control engine 300 obtains the registration data organized by the registration platform and the associated asset data organized by the asset pool database through the data interface 310.

[0053] In some embodiments, data preprocessing may also be included to filter out other data that is not relevant to risk assessment in advance.

[0054] Step 301: Risk assessment.

[0055] Verification rules are pre-set in the risk control engine 300. According to the preset verification rules, the risk control engine can determine from multiple dimensions whether the registration data has financial risks of repeated pledge and transfer.

[0056] It should be noted that the verification rules can be set according to different scenarios, for example, they can include verifying the standardization and rationality of the registration data and the consistency of the registration data and the associated asset data.

[0057] Step 303: The result is returned.

[0058] After the risk control engine 300 executes all the rule judgments, it will generate the final verification result, which may include the current serial number, verification object, verification status (processing success or failure), etc.

[0059] In addition, the returned verification results can be saved and displayed in the duplicate checking record module 320.

[0060] Through the above method, the embodiment of the present application provides a verification method based on registration data, which can parse the registration files in the registration platform, create a new asset pool database and introduce the asset data in the asset pool database for verification and validation, and automatically output the corresponding verification results. The automatic verification of registration data can be completed without human participation, thereby improving the verification efficiency.

[0061] Based on any of the above embodiments, the step of extracting text from the registration file information to obtain structured registration data may specifically include: The content of the registration file information is converted into a text layout, wherein the text layout includes a number of texts and the coordinate information of each text on the layout; the target template is determined according to the registration file information; the text layout is segmented according to the target template and the coordinate information to obtain a number of target position areas, each target position area includes target information; the target information of the several target position areas is sorted to obtain structured registration data.

[0062] In this embodiment, the registration file information is in a non-text format, such as a picture format or a PDF format. Therefore, the content of the registration file information can be converted into a text layout in a text format. The text layout includes a plurality of texts, and each text carries coordinate information on the text layout.

[0063] The target template is determined according to the registration file information, wherein the target template is used to provide information support for the text layout, so as to segment the text layout according to the coordinate information to obtain a number of target position areas.

[0064] Each target location area includes target information, so structured registration data can be obtained by sorting the target information of the target location area.

[0065] In some embodiments, text extraction of registration file information to obtain structured registration data may also be performed by a pre-trained registration data extraction model, and the structured registration data may be structured JSON format data.

[0066] This embodiment further introduces a method for obtaining structured registration data, which can segment the text layout through coordinate information to extract target information, thereby completing the parsing of the registration file without the need for optical character recognition related technology, thereby reducing deployment and maintenance costs.

[0067] Based on any of the above embodiments, the step of segmenting the text layout according to the target template and the coordinate information to obtain a plurality of target position areas, each of which includes target information, may specifically include: The text layout is segmented according to the target template and coordinate information to obtain the target location area; wherein the target location area includes at least one of the basic information area, the personnel information area and the property information area; the target information in the basic information area includes at least one of the registration number, the registration type and the registration time; the target information in the personnel information area includes at least one of the person filling out the form, the transferor and the transferee; the target information in the property information area includes the property description.

[0068] In this embodiment, the type of the target location area and the content of the target information are further defined. The type of the target location area and the content of the target information are one-to-one corresponding, and the target location area may include a basic information area, a personnel information area, and a property information area, wherein the basic information includes information such as registration number, registration type, and registration time; the personnel information includes information such as the filler, transferor, and transferee; and the property information includes information such as property description.

[0069] The following is an example of the registration document downloaded from the China Login website: Directly connect to Zhongdeng.com to query and download the documents currently registered by the customer. After obtaining the Zhongdeng PDF document, input the document data into the Zhongdeng data extraction model. When the model is executed, the following steps are implemented: parse the information on the PDF file into text and the layout coordinates corresponding to the text; divide the text content into four parts according to the structure of the document template: filler, transferor, transferee, and property information; use regular expressions to extract text from the above four parts respectively, and convert the key information of Zhongdeng, including registration number, registration type, registration time, transferor name, transferee name, property description, etc., into structured JSON format data.

[0070] In addition, after the China Registration and Extraction Model is parsed, information such as the registration query serial number, query status, query registration record, and whether the parsing is successful can be saved and displayed on the display page to quickly locate the required information for calling and checking.

[0071] Based on any of the above embodiments, the step of determining the target template according to the registration file information may specifically include: At least one sample registration file information is obtained; the sample registration file information is classified and a sample template is set for each category of the sample registration file information; and a sample template of the same category is determined from the sample templates as a target template according to the category of the registration file information.

[0072] In this embodiment, a specific method for obtaining a target template is defined. In this embodiment, some sample registration file information can be collected in advance, and then the sample registration file information can be classified before designing a corresponding sample template, wherein the sample template can be stored in a template database. When it is necessary to determine a target template based on the registration file information, a sample template with the same category can be selected from the sample templates in the template database according to the category of the registration file information as the target template.

[0073] For example, the layout design of registration documents of the same registration platform in different years is different; for example, in the registration documents of the old years, the basic information is filled in the top, the personnel information is filled in the middle, and the property description is filled in the bottom; while in the registration documents of the new years, the basic information is filled in the upper left, the personnel information is filled in the lower left, and the property description is filled in the entire right. Therefore, the category of the template is year, and when obtaining the target template, it is necessary to select the appropriate target template according to the year of the registration file information.

[0074] For example, the registration documents of different registration platforms have different layout designs. Therefore, the category of the template is the type of the registration platform, and different sample templates can be configured for different registration platforms.

[0075] Based on any of the above embodiments, the step of obtaining the asset data associated with the registration data from the asset pool database may specifically include: Acquire associated words according to the registration data; wherein the associated words include at least one of the registration number, the person filling out the form, the transferor, the transferee and the property description; determine the matching asset data from the asset pool database as the associated asset data according to the associated words.

[0076] In this embodiment, a specific method of obtaining associated asset data from the asset pool database is defined. Specifically, the registration data may involve associated words, and then the associated asset data may be obtained by matching the associated words. The associated words include information such as registration number, form filler, transferor, transferee, and property description.

[0077] Based on any of the above embodiments, the step of performing risk information verification processing according to the registration data and the associated asset data to obtain the verification result may specifically include: Verify whether the contents of the registration data and the associated asset data are consistent, mark the consistent contents, and obtain a first marking result; verify whether the description content in the registration data complies with the preset rules, mark the description content that does not comply with the preset rules, and obtain a second marking result; obtain a verification result based on the first marking result and the second marking result.

[0078] In this embodiment, the specific method of risk information verification processing is defined, which includes two aspects. The first aspect is to verify the consistency of the content, and the second aspect is to verify the standardization of the description. The unqualified content is then marked, so that the verification result is obtained based on the marking results of the two aspects.

[0079] Content consistency verification is equivalent to a form of duplicate checking, which can determine whether the property description has been registered. The purpose is to focus on the registered asset data that is the same as that in the asset pool.

[0080] For example, use the risk control engine rule module to configure the duplicate checking rules of the China Securities Regulatory Commission; obtain data related to customer accounts receivable, invoices, contracts and assets (i.e. the above-mentioned asset data), as well as the parsed China Securities Regulatory Commission data (i.e. the above-mentioned registration data); use the configured duplicate checking rules to determine from multiple dimensions whether the asset data has been registered; if the judgment result is that it has been registered, initiate manual transfer or risk control rejection based on the level of the matched rules; save and display the duplicate checking serial number, duplicate checking customer, duplicate checking status, and duplicate checking results returned by the risk control.

[0081] Description compliance is a form of formal verification that determines whether the property description is recorded correctly.

[0082] For example, the duplicate checking rules of China Securities Depository and Clearing Corporation are configured according to the specific business duplicate checking requirements, such as whether the target company, contract number, invoice number, etc. are included, and whether "all", "all", "everything", etc. appear in the description of the transferred assets.

[0083] Based on any of the above embodiments, the steps before acquiring the asset data associated with the registration data from the asset pool database may further include: The original data is obtained through multiple business systems; non-text format data in the original data is extracted to obtain first intermediate data; the first intermediate data and text format data in the original data are processed to obtain asset data, and the asset data is stored in the asset pool database.

[0084] In this embodiment, the construction method of the asset pool database is limited. In order to facilitate the subsequent risk information verification and processing, the asset information stored in the asset pool database is all information in text format. Therefore, after obtaining the original data of multiple business systems, it is also necessary to extract the non-text format data in the original data to obtain the first intermediate data in text format, and then process the first intermediate data and the text format data in the original data to obtain a data structure that meets the risk control engine.

[0085] For example, data related to customer accounts receivable, invoices, contracts and assets, part of which comes from data stored in internal and external systems, and the other part comes from images uploaded by customers. Therefore, these data need to be processed through big data and OCR technology respectively to obtain structured asset data.

[0086] Through the above method, this embodiment applies big data platform technology processing, which can collect the original data sets scattered in different business systems, and process them to generate data required by the business, batch process and calculate customer asset-related indicator data, and establish a reliable and accurate asset pool database, so as to conveniently and efficiently obtain customer-related asset data.

[0087] In order to make the objectives, technical solutions and advantages of the present application more clear, the technical solutions in the embodiments of the present application are clearly and completely described below.

[0088] The embodiment of the present application can automatically check the solution for duplicate registration in the China Securities Depository and Clearing Corporation, and at the same time improve the identification and extraction method of the China Securities Depository and Clearing Corporation file data, flexibly configure the duplicate checking rules based on the risk control engine, obtain and process the information of the China Securities Depository and Clearing Corporation and the customer asset information from big data for risk judgment, and judge whether the customer's collateral has been registered based on the output duplicate checking results. The China Securities Depository and Clearing Corporation registration information is parsed through PDF text, divided into several fixed parts according to the structure of the document template, and the information is extracted and converted into structured data, thereby improving the overall audit efficiency.

[0089] First, according to the customer's principal name, obtain the customer's valid registration information on the Zhongdeng website. When the system receives a request for Zhongdeng query from the customer, the system automatically uses the specified account to log in to the Zhongdeng website, and then queries the customer's registration certificate based on the customer's identity information. If the customer has a Zhongdeng registration record, download the Zhongdeng registration PDF document; after downloading the Zhongdeng PDF document, input the document data into the Zhongdeng data extraction model. When the model is executed, it will first extract text from the PDF file, which can be achieved by using a PDF parsing library, such as Python's pymupdf library. The pymupdf library can convert the content of a PDF file into text while retaining the coordinate information of each text block on the layout.

[0090] After that, the extracted text needs to be processed. Specifically, since the layout format and field information of the Zhongdeng registration documents are similar, they can be segmented according to the content of the document template. For example, it can be assumed that the registration number, registration type, and registration time are located at the top of the document, the transferor and transferee information are located in the middle of the document, and the property description is located at the bottom of the document. Then, based on these assumptions, write a text processing script that can divide the text content into four different parts: the filler, the transferor, the transferee, and the property information according to the layout coordinates of the text block. Then, use regular expressions to extract text from the above four parts respectively. This step can be achieved by using Python's re library. For example, you can write a regular expression to match the registration number, registration type, and registration time to extract this information. Similarly, other regular expressions can also be written to extract information such as the transferor name, transferee name, and property description.

[0091] Next, the extracted information needs to be converted into structured JSON format data. This can be achieved by using Python's json library. For example, the extracted information can be used as the attribute of a JSON object, and then the json library can be used to convert the object into a JSON format string. In this way, the registration file can be easily parsed without the need for OCR related technology, thereby reducing deployment and maintenance costs.

[0092] After the China Registration and Depository and Clearing Corporation data model is parsed, information such as the registration query serial number, query status, query registration record, and whether the record is successfully parsed can be saved and displayed on the system page to facilitate quick location of the required information for call and verification.

[0093] In the asset pool database, customers' asset data is provided by multiple internal and external systems, as well as manually uploaded data. The data types are diverse, and big data technology is needed to process and clean data from different data sources, summarize indicator data according to customer dimensions, and output them uniformly through the data interface.

[0094] In order to avoid the financial risks of customers repeatedly pledging or transferring assets, the risk control engine of the China Securities Depository and Clearing Corporation Limited (CSDC) duplication checking rules is deployed to automatically check whether the property involved in this business has been registered on the CSDC website. The specific process is as follows: The risk control engine obtains the customer's registration and property data through the data interface. According to the type of business that the customer is currently applying for loans, the type of registration is filtered, and only the registration information that is currently valid and not from the company is obtained; if the customer applies for accounts receivable pledge or factoring, the customer's accounts receivable property data is summarized; if the customer applies for inventory pledge, the collateral property data is summarized. In short, the data acquisition module will configure different data filtering and processing logic according to the product information provided by the business system.

[0095] The registered asset transfer information is in the property transfer description column of the China Securities Depository and Clearing Corporation. Since there is no official standard specification for property transfer descriptions, registrants describe them differently based on their own contexts and fill in the invoice number, transaction contract name, asset corresponding project company name, etc. in a irregular manner.

[0096] Through the pre-set risk control rules of the Zhongdeng duplicate check, it is determined from multiple dimensions whether the customer's data is a hit. Specifically, multiple risk control rules are created and configured. These rules can be based on the specific needs of duplicate checking. For example, if the transferred assets contain the target company, or contain relevant asset information (including contract number, invoice number), they will be intercepted and notified; if the transferred assets contain adjectives such as "all", "all", and "everything", manual processing is required. Then, the customer's Zhongdeng registration and property data obtained are input into the risk control engine.

[0097] The risk control engine will perform duplicate checks based on the configured risk control rules. This process includes some logical judgments: 1. If the customer's target assets do not match any rules, the risk control engine will automatically pass without manual re-verification.

[0098] 2. If one or more of the rules are matched, the risk control engine will mark it as "duplicate" and transfer it to manual or intercept it.

[0099] 3. If the rules require manual judgment, the review will not be interrupted, and the risk control engine will generate a task to notify the risk personnel to make a manual judgment. The risk personnel can decide whether to confirm the data as "duplicate" based on the actual situation.

[0100] After the risk control engine has executed all the rule judgments, it will generate the final duplicate check result. This result includes the hit registration information and detailed information of the asset data marked as "duplicate". The duplicate check result returned by the risk control is saved and displayed in the duplicate check record module together with the serial number, duplicate check customer, and duplicate check status (processing success or failure). In this way, the risk control engine can be used to perform duplicate checks in the middle of the registration, effectively preventing the omission of registration information, while also trying to avoid false hits, and improving the efficiency and accuracy of duplicate checks.

[0101] As mentioned above, the embodiment of the present application provides a verification method based on registration data. When initiating a query on the customer's Zhongdeng registration, the algorithm is called to parse the registration file into structured data within seconds, and the registration information can be directly stored for display query; the processed accounts receivable information is obtained from the business system based on the invoices, contracts and big data uploaded by the customer, and the customer's asset data is obtained; through the risk control engine's duplicate checking rules, it is determined whether the customer's assets are already included in the Zhongdeng registration records, and the corresponding conclusions are automatically output to help auditors make risk decisions. The entire duplicate checking process is automatically completed by the system, and each process is visualized, without the need to manually check each customer's registration information, which improves the audit efficiency.

[0102] An embodiment of the present application provides a verification device based on registration data. The verification device based on registration data provided by the present application is described below. The verification device based on registration data described below and the verification method based on registration data described above can be referenced to each other.

[0103] See also Figure 4 , Figure 4 4 is a schematic diagram of the structure of the verification device based on registration data provided in the embodiment of the present application. In this embodiment, the verification device based on registration data may include a first acquisition module 410, an extraction module 420, a second acquisition module 430 and a verification module 440.

[0104] The first acquisition module 410 is used to acquire registration file information from the registration platform according to a user query request.

[0105] The extraction module 420 is used to extract text from the registration file information to obtain structured registration data.

[0106] The second acquisition module 430 is used to acquire the asset data associated with the registration data from the asset pool database, wherein the asset pool database is connected to multiple business systems, and the asset data in the asset pool database is obtained by processing the original data in each business system.

[0107] The verification module 440 is used to perform risk information verification processing based on the registration data and the associated asset data to obtain a verification result.

[0108] Based on any of the above embodiments, the extraction module 420 can be specifically used to: convert the content of the registration file information into a text layout, wherein the text layout includes a number of texts and the coordinate information of each text on the layout; determine the target template based on the registration file information; segment the text layout according to the target template and the coordinate information to obtain a number of target position areas, each target position area including target information; organize the target information of the several target position areas to obtain structured registration data.

[0109] Based on any of the above embodiments, the extraction module 420 can also be specifically used to: segment the text layout according to the target template and coordinate information to obtain the target position area; wherein the target position area includes at least one of the basic information area, the personnel information area and the property information area; the target information in the basic information area includes at least one of the registration number, the registration type and the registration time; the target information in the personnel information area includes at least one of the person filling out the form, the transferor and the transferee; the target information in the property information area includes the property description.

[0110] Based on any of the above embodiments, the second acquisition module 430 can be specifically used to: obtain associated words based on registration data; wherein the associated words include at least one of the registration number, the person filling out the form, the transferor, the transferee and the property description; and determine matching asset data from the asset pool database as associated asset data based on the associated words.

[0111] Based on any of the above embodiments, the root verification module 440 can be specifically used to: verify whether the contents of the registration data and the associated asset data are consistent, mark the consistent contents, and obtain a first marking result; verify whether the description content in the registration data complies with preset rules, mark the description content that does not comply with the preset rules, and obtain a second marking result; obtain a verification result based on the first marking result and the second marking result.

[0112] Based on any of the above embodiments, the verification device based on registration data may also include a database construction module, which can be specifically used to: obtain original data through multiple business systems; extract text from non-text format data in the original data to obtain first intermediate data; process the first intermediate data and text format data in the original data to obtain asset data, and store the asset data in the asset pool database.

[0113] Based on any of the above embodiments, the extraction module 420 can also be specifically used to: obtain at least one sample registration file information; classify the sample registration file information and set a sample template for each category of sample registration file information; determine a sample template of the same category from the sample templates as a target template according to the category of the registration file information.

[0114] In summary, the embodiment of the present application provides a verification device based on registration data, including: a first acquisition module, used to obtain registration file information from the registration platform according to a user query request; an extraction module, used to perform text extraction on the registration file information to obtain structured registration data; a second acquisition module, used to obtain asset data associated with the registration data from the asset pool database; wherein the asset pool database is connected to multiple business systems, and the asset data in the asset pool database is obtained by processing the original data in each business system; a verification module, used to perform risk information verification processing based on the registration data and the associated asset data to obtain a verification result. Through the above method, the present application can parse the registration file in the registration platform, create a new asset pool database and introduce the asset data in the asset pool database for verification and validation, automatically output the corresponding verification results, and complete the automatic verification of the registration data without human intervention, thereby improving the verification efficiency.

[0115] In another aspect, the present application also provides an electronic device. Figure 5 , Figure 5 : is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present application, and the electronic device may include: a processor (processor) 510, a communication interface (Communications Interface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call the logic instructions in the memory 530 to execute the following method: Acquire registration file information from the registration platform according to user query requests; perform text extraction on the registration file information to obtain structured registration data; acquire asset data associated with the registration data from the asset pool database; wherein the asset pool database is connected to multiple business systems, and the asset data in the asset pool database is obtained by processing the original data in each business system; perform risk information verification processing based on the registration data and the associated asset data to obtain verification results.

[0116] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the relevant technology. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0117] In another aspect, an embodiment of the present application discloses a computer program product, wherein the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program includes program instructions. When the computer program instructions are executed by a computer, the computer can perform the methods provided by the above-mentioned method embodiments, for example, including: Acquire registration file information from the registration platform according to user query requests; perform text extraction on the registration file information to obtain structured registration data; acquire asset data associated with the registration data from the asset pool database; wherein the asset pool database is connected to multiple business systems, and the asset data in the asset pool database is obtained by processing the original data in each business system; perform risk information verification processing based on the registration data and the associated asset data to obtain verification results.

[0118] In another aspect, an embodiment of the present application further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method provided in each of the above embodiments is implemented, for example, including: Acquire registration file information from the registration platform according to user query requests; perform text extraction on the registration file information to obtain structured registration data; acquire asset data associated with the registration data from the asset pool database; wherein the asset pool database is connected to multiple business systems, and the asset data in the asset pool database is obtained by processing the original data in each business system; perform risk information verification processing based on the registration data and the associated asset data to obtain verification results.

[0119] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0120] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0121] Finally, it should be noted that the above implementation modes are only used to illustrate the present application, rather than to limit the present application. Although the present application is described in detail with reference to the embodiments, a person skilled in the art should understand that various combinations, modifications or equivalent substitutions of the technical solutions of the present application do not depart from the spirit and scope of the technical solutions of the present application, and should be included in the scope of the claims of the present application.

Claims

1. A verification method based on registration data, characterized in that: include: Obtaining registration document information from the registration platform according to user query requests; Performing text extraction on the registration file information to obtain structured registration data; Acquire asset data associated with the registration data from an asset pool database; The asset pool database is connected to multiple business systems, and the asset data in the asset pool database is obtained by processing the original data in each business system; The risk information is verified based on the registration data and the associated asset data to obtain a verification result.

2. The verification method based on registration data according to claim 1, characterized in that: The text extraction of the registration file information to obtain structured registration data includes: Converting the content of the registration file information into a text layout, wherein the text layout includes a plurality of texts and coordinate information of each text on the layout; Determine a target template according to the registration file information; Segmenting the text layout according to the target template and the coordinate information to obtain a plurality of target position areas, each of which includes target information; The target information of the plurality of target location areas is sorted to obtain the structured registration data.

3. The verification method based on registration data according to claim 2, characterized in that: The text layout is segmented according to the target template and the coordinate information to obtain a plurality of target position areas, each of which includes target information, including: Segment the text layout according to the target template and the coordinate information to obtain the target location area; wherein the target location area includes at least one of a basic information area, a personnel information area, and a property information area; The target information in the basic information area includes at least one of the registration number, registration type and registration time; the target information in the personnel information area includes at least one of the person filling out the form, the transferor and the transferee; the target information in the property information area includes the property description.

4. The verification method based on registration data according to claim 1, characterized in that: The acquiring the asset data associated with the registration data from the asset pool database includes: Acquire associated words according to the registration data; wherein the associated words include at least one of the registration number, the person filling out the form, the transferor, the transferee and the property description; According to the associated words, matching asset data is determined from the asset pool database as associated asset data.

5. The verification method based on registration data according to claim 1, characterized in that: The risk information verification process is performed according to the registration data and the associated asset data to obtain a verification result, including: Verifying whether the contents of the registration data and the associated asset data are consistent, marking the consistent contents, and obtaining a first marking result; Verifying whether the description content in the registration data complies with a preset rule, marking the description content that does not comply with the preset rule, and obtaining a second marking result; A verification result is obtained according to the first marking result and the second marking result.

6. The verification method based on registration data according to claim 1, characterized in that: Before acquiring the asset data associated with the registration data from the asset pool database, the method further includes: Obtain raw data through multiple business systems; Extracting text from the non-text format data in the original data to obtain first intermediate data; The text format data in the first intermediate data and the original data are processed to obtain asset data, and the asset data is stored in the asset pool database.

7. The verification method based on registration data according to claim 2, characterized in that: The step of determining a target template according to the registration file information includes: obtaining at least one sample registration file information; Classifying the sample registration file information, and setting a sample template for each category of sample registration file information; According to the category of the registration document information, a sample template with the same category is determined from the sample templates as a target template.

8. A verification device based on registration data, characterized in that: include: A first acquisition module, used to acquire registration file information from the registration platform according to a user query request; An extraction module, used for performing text extraction on the registration file information to obtain structured registration data; A second acquisition module, used for acquiring asset data associated with the registration data from an asset pool database; The asset pool database is connected to multiple business systems, and the asset data in the asset pool database is obtained by processing the original data in each business system; The verification module is used to perform risk information verification processing based on the registration data and the associated asset data to obtain a verification result.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the verification method based on registration data as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the verification method based on registration data as described in any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the verification method based on registration data as described in any one of claims 1 to 7 is implemented.

Images