Centralized multi-system linkage certificate review method, device and electronic equipment

Abstract

The present invention discloses a centralized multi-system linkage certificate review method, device and electronic equipment, belonging to the field of financial information technology. The method includes: using a unified interface to connect to the background database of each business system in a financial institution, and synchronously obtaining the customer certificate information of each business system in real time; identifying the text information of the certificate to be reviewed, setting a certificate consistency verification model, and combining the customer certificate information of each business system, calculating the certificate consistency verification score, and formulating a certificate review strategy based on the certificate consistency verification score; wherein, the certificate review strategy includes: when the certificate consistency verification score exceeds the set verification threshold, the certificate review is passed, otherwise, manual verification is performed. It effectively improves the accuracy and real-time performance of the certificate review work, and achieves the goals of simplifying the operating process, ensuring data consistency and strengthening risk control. It ensures business continuity and security, and solves the problem of information fragmentation between multiple business systems.

Description

Technical Field

[0001] The present invention relates to the field of financial information technology, and in particular to a centralized multi-system linked certificate review method, device and electronic equipment. Background Art

[0002] Currently, in financial institutions, when customers open accounts or update their documents through different channels such as counters, electronic banking, and mobile banking, operators are often required to log in to multiple back-end management systems separately to search and verify document information, resulting in cumbersome operations and low efficiency.

[0003] For example, Chinese patent application CN1728659A relates to a bank depositor identity document verification system and method, specifically disclosing the following technical solution: The bank depositor identity document verification system includes an intelligent terminal U1 located at each bank branch terminal counter, a branch server U2 located at each bank branch, and a central server U3 located in the bank's central computer room. Each bank branch's intelligent terminal U1 is connected to the branch server U2 of that bank branch via the bank's local area network (LAN), and the branch server U2 is connected to the bank's central server U3 via the bank's wide area network (WAN). The central server U3 is a computer installed with central server software and includes a central control module U31, a data management module U32, and a branch server communication module U33. The data management module U32 and branch server communication module U33 are respectively connected to the central control module U31, and the branch server communication module U33 is connected to the bank's local area network. The working process of the bank depositor identity document verification system is: 1. Place an intelligent terminal U1 on the counter of each branch, place a branch server U2 at the bank branch, and place a central server U3 in the bank's central computer room; 2. Each device is connected to the bank network, and the intelligent terminal U1 is connected to the bank counter terminal through its RS232 interface U15; 3. When a depositor opens an account, he / she hands the identity document to the front desk staff. When the front desk staff swipes the depositor's bank card, the card reader U12 sends the bank card number information to the bank savings system through the RS232 interface U15. At the same time, the card reader U12 sends the card number information to the branch server U2 through the central processing unit U16, the network module U14 and the bank's local area network; 4. The branch server U2 prompts the front desk staff to perform the operation through the LCD display on the intelligent terminal U1 5. The image collector U11 on the smart terminal U1 sends the ID information obtained by scanning or taking a photo to the central processing unit U16, which then sends it to the branch server U2 via the network module U14 and the bank's local area network for background processing. The relevant information sent by the branch server U2 will be displayed on the LCD screen. 6. When a depositor withdraws money, the front desk staff scans or takes a photo of the depositor's ID card. 7. The branch server U2 retrieves the ID card image information reserved when the depositor opened the account based on the card number information obtained by the card reader U12, compares it with the image information obtained by the smart terminal U1, and displays the comparison result on the LCD screen of the smart terminal U1. 8. The branch server U2 can obtain the depositor's account opening information reserved at other branches by exchanging the depositor's account opening information with the central server U3. This patent application discloses a system and method for verifying the ID card of a customer when opening an account at the bank counter. In addition to the bank counter, customers can also open accounts or update their ID cards through other channels such as e-banking and mobile banking. If you open an account through different channels, you need to develop corresponding document review systems and methods, which is not only cumbersome, but also inefficient and costly. Summary of the Invention

[0004] In order to solve the problems existing in the prior art, the present invention provides the following technical solutions.

[0005] A first aspect of the present invention provides a centralized multi-system linkage certificate review method, comprising:

[0006] Use a unified interface to connect to the backend database of each business system within a financial institution, and obtain customer ID information from each business system in real time;

[0007] Identify the text information of the document to be reviewed, set up a document consistency verification model, and combine the customer document information of each business system to calculate the document consistency verification score. Formulate a document review strategy based on the document consistency verification score. The document review strategy includes: when the document consistency verification score exceeds the set verification threshold, the document review is passed; otherwise, manual verification is performed.

[0008] Preferably, the certificate review method also includes the steps of: creating a core database table structure and storing the data obtained from each business system in the table; wherein the core database table includes a customer information table, a certificate information table and a certificate change history table, the customer information table is used to record the customer's basic information; the certificate information table is used to record the customer's certificate information; the certificate change history table is used to record the customer's certificate change history.

[0009] Preferably, the customer information table includes fields: customer unique identification, name and certificate type; the certificate information table includes fields: certificate record unique identification, associated customer ID, certificate number, certificate issuance date, certificate expiration date, certificate issuing authority and certificate image file path; the certificate change history table includes fields: historical record unique identification, associated customer ID, associated certificate ID, certificate change type and change date.

[0010] Preferably, the document review method further comprises the steps of: creating a document recognition result table for storing text information recognized from the document to be reviewed; the document recognition result table comprises fields: unique identification of recognition result, associated document ID, recognized text content and recognition confidence score.

[0011] Preferably, the document review method further includes the steps of: creating a comparison result table for storing the comparison results of the document consistency verification score and the verification threshold; the comparison result table includes fields: comparison record unique identifier, associated document ID, source business system, comparison status and comparison details description.

[0012] Preferably, the document review method further comprises the steps of: creating an audit log table for recording each document review-related operation; the audit log table comprises fields: log record unique identifier, operator ID, operation time, associated customer ID, operation type and operation result.

[0013] Preferably, the document review method further comprises the steps of: constructing an integrated operation interface, which supports operators to conduct document review based on text information, data obtained from various business systems, and comparison results; the integrated operation interface also supports operators to search and query customer document information, initiate document update requests, and send the update requests to the corresponding business system through an internal interface for processing;

[0014] When the operator completes the certificate review and update operation, the newly submitted certificate information and comparison results will be updated; at the same time, the updated certificate information will be synchronized to the related business system through a unified interface.

[0015] Preferably, the certificate consistency verification model is specifically as follows:

[0016]

[0017] Among them, C text is the certificate consistency verification score, p is the number of fields in the text information of the certificate to be reviewed, and w k is the weight of the first field, H1(T k ) is the text information of the kth field in the text information of the document to be reviewed T k The first hash value, The text information of the kth field in the customer certificate information of each business system The first hash value, γ k is the first adjustment factor of the first hash value of the kth field, η k is the third adjustment factor of the first hash value of the kth field, δ k is the second adjustment factor of the first hash value of the kth field, H2(T k ) is the text information T of the kth field k The second hash value, The text information of the kth field in the customer certificate information of each business system The second hash value, γ′ k is the first adjustment factor of the second hash value of the kth field, η′ k is the third adjustment factor of the second hash value of the kth field, δ′ k is the second adjustment factor of the second hash value of the kth field, λ k is the adjustment factor for the edit distance of the kth field, Tk and The edit distance between .

[0018] A second aspect of the present invention provides a centralized multi-system linkage document verification device, comprising:

[0019] The data integration module is used to connect to the backend databases of various business systems within financial institutions using a unified interface, and obtain customer ID information from each business system in real time and synchronously;

[0020] The intelligent review module is used to identify the text information of the document to be reviewed, set up a document consistency verification model, and combine the customer document information of each business system to calculate the document consistency verification score. The document review strategy is formulated based on the document consistency verification score. Among them, the document review strategy includes: when the document consistency verification score exceeds the set verification threshold, the document review is passed; otherwise, manual verification is performed.

[0021] The present invention also provides an electronic device, comprising a processor and a memory connected to the processor, wherein the memory stores multiple instructions, which can be loaded and executed by the processor so that the processor can execute the centralized multi-system linkage document review method as described in the first aspect.

[0022] The beneficial effects of the present invention are as follows: the present invention provides a centralized multi-system linked certificate review method, device and electronic equipment, which obtains the background data of multiple business systems of financial institutions in real time and synchronously, integrates the customer certificate information of each business system into a centralized platform, and uses these data to compare and review the uploaded certificates to be reviewed on the centralized platform, effectively improving the accuracy and real-time performance of the certificate review work, achieving the goals of simplifying the operating process, ensuring data consistency and strengthening risk control. While avoiding the cumbersome operations caused by the fragmentation of multiple systems, it ensures the business continuity and security of financial institutions in the certificate review process. At the same time, it solves the problem of information fragmentation between multiple business systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of the centralized multi-system linkage certificate review method of the present invention;

[0024] Figure 2 This is a functional structure diagram of the centralized multi-system linkage certificate verification device of the present invention. DETAILED DESCRIPTION

[0025] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0026] The method provided by the present invention can be implemented in the following terminal environment, which may include one or more of the following components: a processor, a memory, and a display screen. The memory stores at least one instruction, which is loaded and executed by the processor to implement the method described in the following embodiments.

[0027] A processor can include one or more processing cores. It connects various components within the terminal using various interfaces and circuits. It executes instructions, programs, code sets, or instruction sets stored in memory, and accesses data stored in memory to perform various terminal functions and process data.

[0028] The memory may include random access memory (RAM) or read-only memory (ROM). The memory may be used to store instructions, programs, codes, code sets, or instructions.

[0029] The display is used to show the user interface of each application.

[0030] In addition, those skilled in the art will appreciate that the structure of the terminal described above does not limit the terminal. The terminal may include more or fewer components, or a combination of certain components, or a different arrangement of components. For example, the terminal may also include a radio frequency circuit, an input unit, a sensor, an audio circuit, a power supply, and other components, which will not be described in detail here.

[0031] Example 1

[0032] like Figure 1 As shown, an embodiment of the present invention provides a centralized multi-system linkage document review method, including: S101, using a unified interface to connect to the backend database of each business system in a financial institution, and synchronously obtaining customer document information of each business system in real time; S102, identifying the text information of the document to be reviewed, setting a document consistency verification model, and combining the customer document information of each business system to calculate the document consistency verification score, and formulating a document review strategy based on the document consistency verification score, wherein the document review strategy includes: when the document consistency verification score exceeds the set verification threshold, the document review is passed, otherwise, manual verification is performed.

[0033] In step S101, a unified data integration interface layer can be created, which connects to the backend databases of various business systems via predefined APIs or ETL tools. A core database table structure can also be created to store data obtained from various business systems. The core database tables include a customer information table, a document information table, and a document change history table. The customer information table records basic customer information; the document information table records customer document information; and the document change history table records a customer's document change history.

[0034] Furthermore, the customer information table may include fields: customer unique identification, name and certificate type; the certificate information table may include fields: certificate record unique identification, associated customer ID, certificate number, certificate issuance date, certificate expiration date, certificate issuing authority and certificate image file path; the certificate change history table may include fields: historical record unique identification, associated customer ID, associated certificate ID, certificate change type and change date.

[0035] In step S102, optical character recognition (OCR) technology can be used to identify the textual information of the document to be reviewed. During implementation, a document recognition results table can be created to store the textual information identified from the document to be reviewed. The document recognition results table can include fields such as a unique identifier for the recognition result, an associated document ID, the recognized textual content, and a recognition confidence score.

[0036] Furthermore, the document consistency verification model is as follows:

[0037]

[0038] Among them, C text is the certificate consistency verification score, p is the number of fields in the text information of the certificate to be reviewed, and w k is the weight of the first field, H1(T k ) is the text information of the kth field in the text information of the document to be reviewed T k The first hash value, The text information of the kth field in the customer certificate information of each business system The first hash value, γ k is the first adjustment factor of the first hash value of the kth field, η k is the third adjustment factor of the first hash value of the kth field, δ k is the second adjustment factor of the first hash value of the th field, H2(T k ) is the text information T of the kth field k The second hash value, The text information of the kth field in the customer certificate information of each business system The second hash value, γ′ k is the first adjustment factor of the second hash value of the kth field, η′ k is the third adjustment factor of the second hash value of the th field, δ′ k is the second adjustment factor of the second hash value of the kth field, λ k is the adjustment factor for the edit distance of the kth field, T k and The edit distance between .

[0039] In order to enhance the robustness of the document consistency verification model, this embodiment uses different hash algorithms to calculate the first hash value and the second hash value, that is, to calculate H1(T k )and For a hash algorithm, such as Perceptual Hash, calculate H2(T k )and is another hash algorithm, for example, SHA-256 hash. The example of hash algorithm in this embodiment does not mean that only the example hash algorithm can be used. Other hash algorithms can also be used as long as the calculation of H1(T k )and and calculate H2(T k )and The hash algorithm used is different.

[0040] The weights and adjustment factors in the document consistency verification model are fitted by the least squares method or ant colony algorithm, thereby improving the accuracy of the document consistency verification model.

[0041] In order to make the document review more accurate, this embodiment extracts the user photo on the document to be reviewed when the document consistency verification score exceeds the set verification threshold, compares the user photo with the user photos on other user documents in each business system, calculates the similarity, and uses the other user documents corresponding to the highest similarity among all similarities as the most similar other documents. If the highest similarity exceeds the preset similarity threshold, the document to be reviewed is manually verified, and the other most similar documents are simultaneously sent for manual verification. The purpose of this is to prevent users from forging documents, thereby completing the document review through forged documents.

[0042] In one embodiment of the present invention, a comparison result table can also be created to store the comparison results of the certificate consistency verification score and the verification threshold; the comparison result table can include fields: comparison record unique identifier, associated certificate ID, source business system, comparison status and comparison details.

[0043] In one embodiment of the present invention, business personnel can quickly perform one-stop document review operations based on the data in the customer information table, document information table, and the associated document change history table, document identification result table, and comparison result table. During the specific implementation process, an audit log table can be created to record each document review-related operation; the audit log table may include fields such as the log record unique identifier, operator ID, operation time, associated customer ID, operation type (such as query, review, modification, etc.), and operation results. All operation records of the review process can be automatically saved to the audit log table to facilitate subsequent auditing and tracking.

[0044] In one embodiment of the present invention, an integrated operation interface is constructed, which supports operators to perform document review based on text information, data obtained from various business systems, and comparison results; the integrated operation interface also supports operators to retrieve and query customer document information, and initiate document update requests, and send the update requests to the corresponding business system through an internal interface for processing; when the operator completes the document review and update operations, the newly submitted document information and comparison results are updated; at the same time, the updated document information is synchronized to the related business system through a unified interface to ensure consistency across all channels.

[0045] In a preferred embodiment of the present invention, the data obtained from various business systems can be associated and integrated according to the customer ID to build a complete customer certificate life cycle file.

[0046] In addition, during the document review process, if any information anomalies are discovered, an early warning signal will be immediately triggered and pushed to relevant personnel. Specifically, when document anomalies or information discrepancies are discovered, an early warning signal will be immediately triggered, and the risk event will be pushed to relevant personnel so that timely action can be taken to ensure the safe operation of the business. A risk event table can be established. When document anomalies are discovered, the risk event will be recorded in this table. The risk event table may include the following fields: event unique identifier, associated customer ID, risk level, risk description, and discovery time. Document changes in the document change history table are monitored regularly or in real time. When frequent or abnormal changes are discovered within a short period of time, the internal risk control process is triggered. When there is an inconsistency in the document consistency verification score or the risk level is high, the event will be recorded in the risk event table and an early warning notification will be sent to the relevant operations personnel.

[0047] This invention not only effectively solves the problem of document review in a multi-system environment, but also optimizes business processes and improves risk control capabilities through technical means, providing financial institutions with a more secure, convenient, and efficient document review solution. This is specifically reflected in the following points:

[0048] 1. Improved work efficiency: By integrating certificate information from multiple business systems into a centralized review platform, the workflow of operators is greatly simplified, the time cost of cross-system operations is reduced, and the overall efficiency of certificate review is significantly improved.

[0049] 2. Enhanced data consistency: By managing the customer's entire life cycle document files on a single platform, the consistency and accuracy of customer document information across different business channels is ensured, reducing the risks and errors caused by inconsistent information.

[0050] 3. Improved accuracy of intelligent recognition and verification: The use of advanced OCR technology and big data analysis algorithms effectively improves the automatic recognition and comparison verification capabilities of document images or text information in electronic information, greatly improving the accuracy of audits.

[0051] 4. Accelerated risk control response speed: When the system detects an abnormal situation, the early warning and risk control mechanism can be triggered quickly, and the risk event can be pushed to relevant personnel in a timely manner, which greatly shortens the time period for financial institutions to discover and respond to potential risks and enhances risk prevention capabilities.

[0052] 5. Optimized service experience: The integrated operation interface facilitates business personnel to efficiently query and handle certificate matters. It also supports customers' certificate update needs when switching seamlessly between channels, improving customer experience and service satisfaction.

[0053] 6. Meeting compliance and regulatory requirements: The centralized document review platform enables financial institutions to more effectively comply with relevant laws and regulatory requirements, provides complete and standardized audit tracking records, and helps maintain a good industry compliance image.

[0054] Example 2

[0055] like Figure 2 As shown, another aspect of the present invention also includes a functional module architecture that is completely consistent with the aforementioned method process, that is, an embodiment of the present invention also provides a centralized multi-system linkage document review device, including: a data integration module 201, which is used to use a unified interface to connect to the back-end database of each business system in a financial institution, and synchronously obtain customer document information of each business system in real time; an intelligent review module 202, which is used for the intelligent review module to identify the text information of the document to be reviewed, set a document consistency verification model, and calculate the document consistency verification score in combination with the customer document information of each business system, and formulate a document review strategy based on the document consistency verification score, wherein the document review strategy includes: when the document consistency verification score exceeds the set verification threshold, the document review is passed, otherwise, manual verification is performed.

[0056] The device can be implemented through the centralized multi-system linkage certificate review method provided in the above-mentioned embodiment 1. The specific implementation method can be found in the description of embodiment 1 and will not be repeated here.

[0057] The present invention also provides a memory storing a plurality of instructions, wherein the instructions are used to implement the centralized multi-system linkage certificate review method as described in the first embodiment.

[0058] The present invention also provides an electronic device, comprising a processor and a memory connected to the processor, wherein the memory stores a plurality of instructions, which can be loaded and executed by the processor so that the processor can execute the centralized multi-system linkage certificate review method as described in Example 1.

[0059] Although preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they are aware of the basic inventive concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the invention. Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the invention. Thus, the present invention is intended to include such changes and modifications as fall within the scope of the claims and their equivalents.

Claims

1. A centralized multi-system linkage certificate review method, characterized in that: include: Use a unified interface to connect to the backend database of each business system within a financial institution, and obtain customer ID information from each business system in real time; Identify the text information of the document to be reviewed, set up a document consistency verification model, and calculate the document consistency verification score based on the customer document information of each business system. The document review strategy is formulated based on the document consistency verification score. The document review strategy includes: when the document consistency verification score exceeds the set verification threshold, the document review is passed; otherwise, manual verification is performed; The document consistency verification model is as follows: ； in, The certificate consistency verification score is The number of fields of the text information of the document to be reviewed. For the The weight of the fields, The text information of the document to be reviewed is Text information of each field The first hash value, The first Text information of each field The first hash value, For the The first adjustment factor for the first hash value of the field, For the The third adjustment factor for the first hash value of the field, For the The second adjustment factor for the first hash value of the field, The text information of the document to be reviewed is Text information of each field The second hash value, The first Text information of each field The second hash value, For the The first adjustment factor for the second hash value of the field, For the The third adjustment factor for the second hash value of the field, For the The second adjustment factor for the second hash value of the field, For the The adjustment factor for the edit distance of each field, for and The edit distance between .

2. The centralized multi-system linkage certificate review method according to claim 1, characterized in that: The certificate review method also includes the steps of: creating a core database table structure and storing data obtained from various business systems in the table; wherein the core database table includes a customer information table, a certificate information table and a certificate change history table, the customer information table is used to record the customer's basic information; the certificate information table is used to record the customer's certificate information; and the certificate change history table is used to record the customer's certificate change history.

3. The centralized multi-system linkage certificate verification method according to claim 2, characterized in that: The customer information table includes fields: customer unique identification, name and certificate type; the certificate information table includes fields: certificate record unique identification, associated customer ID, certificate number, certificate issuance date, certificate expiration date, certificate issuing authority and certificate image file path; the certificate change history table includes fields: historical record unique identification, associated customer ID, associated currently valid certificate ID, certificate change type and change date.

4. The centralized multi-system linkage certificate verification method according to claim 1, characterized in that: The document review method further includes the steps of: creating a document recognition result table for storing text information recognized from the document to be reviewed; the document recognition result table includes fields: a unique identification of the recognition result, an associated document ID, recognized text content, and a recognition confidence score.

5. The centralized multi-system linkage certificate verification method according to claim 4, characterized in that: The document review method also includes the steps of: creating a comparison result table for storing the comparison results of the document consistency verification score and the verification threshold; the comparison result table includes fields: comparison record unique identifier, associated document ID, source business system, comparison status and comparison details description.

6. The centralized multi-system linkage certificate verification method according to claim 1, characterized in that: The document review method further includes the steps of: creating an audit log table for recording each document review-related operation; the audit log table includes fields: log record unique identifier, operator ID, operation time, associated customer ID, operation type and operation result.

7. The centralized multi-system linkage certificate verification method according to claim 1, characterized in that: The document review method further includes the steps of: constructing an integrated operation interface that supports operators in reviewing documents based on text information, data obtained from various business systems, and comparison results; the integrated operation interface also supports operators in retrieving and querying customer document information, initiating document update requests, and sending the update requests to the corresponding business system through an internal interface for processing; When the operator completes the certificate review and update operation, the newly submitted certificate information and comparison results will be updated; at the same time, the updated certificate information will be synchronized to the related business system through a unified interface.

8. A centralized multi-system linkage certificate verification device, used to implement the centralized multi-system linkage certificate verification method according to any one of claims 1 to 7, characterized in that: include: The data integration module is used to connect to the backend databases of various business systems within financial institutions using a unified interface, and obtain customer ID information from each business system in real time and synchronously; The intelligent review module is used to identify the text information of the document to be reviewed, set up a document consistency verification model, and combine the customer document information of each business system to calculate the document consistency verification score. The document review strategy is formulated based on the document consistency verification score. Among them, the document review strategy includes: when the document consistency verification score exceeds the set verification threshold, the document review is passed; otherwise, manual verification is performed.

9. An electronic device, characterized in that: It includes a processor and a memory connected to the processor, the memory stores multiple instructions, and the instructions can be loaded and executed by the processor to enable the processor to execute the centralized multi-system linkage document review method as described in any one of claims 1-7.

Images