Digital credit archive generation method and device, equipment and storage medium

Abstract

The invention discloses a digital credit archive generation method and device, equipment and a storage medium, and relates to the technical field of computers, and the method comprises the steps: carrying out the key information extraction of a loan data source in a current effective state based on a preset image data obtaining interface; matching with a pre-configured image directory tree rule management table based on the information extraction result, and determining a target business tree and a target file tree; the image directory tree rule management table is a rule table used for managing a directory tree structure established based on image data; mapping the tree nodes of the target business tree to the tree nodes of the target archive tree by using a target tree node mapping rule determined based on the information extraction result to obtain a first archive tree; and based on the information extraction result, the first archive tree, the associated loan service type information corresponding to the current loan data source and a preset sorting strategy, performing archive construction to obtain a target digital credit archive. According to the invention, the digital credit file catalogue generation efficiency of various loan products can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a digital credit file generation method, device, equipment and storage medium. BACKGROUND

[0002] In the process of commercial bank loan handling, the credit file directory structure of different loan products is different, such as the requirements of personal operating loan and personal consumption loan file directory are different, and the file directories formed in different business types of the same loan product in the handling stage are also different, such as the file directories required by loan contract signing and real estate mortgage registration are also different. With the change of national, industry and regulatory requirements, the credit file requirements of different loan products are also constantly updated. For traditional credit file collection and archiving, the addition, modification and deletion of file directories are easy to cause repeated development and resource waste. Therefore, when collecting paper archives manually, for the account manager, the archive collection task of multiple loan varieties of the same customer and the archive collection task of different business types of one loan variety are tedious and repetitive, resulting in low efficiency of forming credit file data. SUMMARY

[0003] Therefore, the purpose of the present application is to provide a digital credit file generation method, device, equipment and storage medium, which can effectively improve the generation efficiency of the digital credit file directory of various loan products, and effectively reduce the workload of the account manager in collecting and arranging various business materials of a loan product of a customer, thereby improving the work efficiency and the timeliness and effectiveness of credit file data storage and collection. The specific scheme is as follows:

[0004] In a first aspect, the present application provides a digital credit file generation method, comprising:

[0005] Based on a preset image data acquisition interface, key information of a current loan data source in an effective state is extracted to determine an information extraction result corresponding to the current loan data source;

[0006] Based on the information extraction result and a preconfigured image directory tree rule management table, a target business tree and a target file tree corresponding to the current loan data source are determined; the image directory tree rule management table is a rule table for managing the directory tree structure based on image data;

[0007] Based on the information extraction result, a target tree node mapping rule is determined, and the tree nodes of the target business tree are mapped to the tree nodes of the target file tree by using the target tree node mapping rule, to obtain a first file tree;

[0008] construct the digital credit file based on the information extraction result, the first archive tree, the associated loan business type information corresponding to the current loan data source, and a preset sorting strategy, to obtain a target digital credit file corresponding to the current loan data source.

[0009] Optionally, before the matching based on the information extraction result and the preconfigured image directory tree rule management table to determine the target business tree and the target archive tree corresponding to the current loan data source, the method further includes:

[0010] initializing the image directory tree, and performing numbering configuration and attribute configuration on the tree nodes in the obtained image directory tree structure, to obtain an initial image directory tree structure;

[0011] performing parameterized configuration on the initial image directory tree structure based on the loan business type and the data type, to obtain the preconfigured image directory tree rule management table.

[0012] Optionally, the key information extraction based on the preset image data acquisition interface from the loan data source currently in an effective state includes:

[0013] extracting, based on the preset image data acquisition interface, the corresponding loan business type, loan investigation report type, customer name, and loan product name from the loan data source currently in the effective state, to obtain an information extraction result.

[0014] Optionally, the matching based on the information extraction result and the preconfigured image directory tree rule management table to determine the target business tree and the target archive tree corresponding to the current loan data source includes:

[0015] performing directory tree matching on the preconfigured image directory tree rule management table based on the loan business type and the loan investigation report type, to determine the target business tree and the target archive tree corresponding to the current loan data source.

[0016] Optionally, the determining of the target tree node mapping rule based on the information extraction result, and the mapping of the tree nodes of the target business tree to the tree nodes of the target archive tree by using the target tree node mapping rule includes:

[0017] matching, based on the information extraction result, the tree numbers of the target business tree, and the tree numbers of the target archive tree, and a preconfigured tree node mapping rule, to determine a target tree node mapping rule;

[0018] finding, based on a first preset algorithm, the image data of the tree nodes at each level in the target business tree from the current loan data source, to obtain a finding result;

[0019] determine whether a preset data addition triggering condition is met based on the search result, to obtain a determination result;

[0020] generate target image data of tree nodes at each level in the target archive tree based on the search result, the determination result, and the target tree node mapping rule, to complete a corresponding tree node mapping operation, and determine a first archive tree and a first mapping completion time corresponding to the first archive tree;

[0021] perform file integrity verification, file format verification, digital signature verification, and content verification on the target image data corresponding to each tree node in the first archive tree based on a preset verification rule, to determine a corresponding data verification result.

[0022] Optionally, the digital credit archive construction based on the information extraction result, the first archive tree, associated loan business type information corresponding to the current loan data source, and a preset sorting strategy includes:

[0023] determine a plurality of associated loan business types corresponding to the current loan data source based on the information extraction result;

[0024] obtain a second archive tree corresponding to loan data sources of the plurality of associated loan business types and a second mapping completion time corresponding to the second archive tree;

[0025] perform archive tree arrangement based on the first archive tree corresponding to the current loan data source and the first mapping completion time, a preset sorting strategy, and the second archive tree corresponding to the plurality of associated loan business types and the second mapping completion time, to determine a target digital credit archive corresponding to the current loan data source.

[0026] Optionally, after the corresponding data verification result is determined, the method further includes:

[0027] if the data verification result indicates that the target image data of a tree node is incomplete, analyze the target image data based on a second preset algorithm, to determine a target missing item;

[0028] search for information corresponding to the target missing item from the current loan data source based on a first preset algorithm, to obtain to-be-completed information;

[0029] or feed back the target missing item to a client based on a preset interactive interface, to receive the to-be-completed information returned by the client;

[0030] supplement the target image data based on the to-be-completed information, to obtain the target image data after completion.

[0031] In a second aspect, the present application provides a digital credit file generation device, comprising:

[0032] An information extraction module is configured to extract key information from a current active loan data source based on a preset image data acquisition interface, to determine an information extraction result corresponding to the current loan data source;

[0033] A directory tree matching module is configured to match the information extraction result with a preconfigured image directory tree rule management table, to determine a target business tree and a target file tree corresponding to the current loan data source; the image directory tree rule management table is a rule table for managing a directory tree structure built based on image data;

[0034] A tree node mapping module is configured to determine a target tree node mapping rule based on the information extraction result, and map tree nodes of the target business tree to tree nodes of the target file tree using the target tree node mapping rule, to obtain a first file tree;

[0035] A digital credit file construction module is configured to construct a digital credit file based on the information extraction result, the first file tree, associated loan business type information corresponding to the current loan data source, and a preset sorting strategy, to obtain a target digital credit file corresponding to the current loan data source.

[0036] In a third aspect, the present application provides an electronic device, comprising:

[0037] A memory is configured to save a computer program;

[0038] A processor is configured to execute the computer program to implement the steps of the aforementioned digital credit file generation method.

[0039] In a fourth aspect, the present application provides a computer readable storage medium configured to save a computer program, which is executed by a processor to implement the steps of the aforementioned digital credit file generation method.

[0040] It can be seen that, in the present application, the key information of the current loan data source in the effective state is extracted based on the preset image data acquisition interface to determine the information extraction result corresponding to the current loan data source; the information extraction result is matched with the preconfigured image directory tree rule management table to determine the target business tree and the target archive tree corresponding to the current loan data source; the image directory tree rule management table is a rule table for managing the directory tree structure built based on image data; the target tree node mapping rule is determined based on the information extraction result, and the tree node of the target business tree is mapped to the tree node of the target archive tree using the target tree node mapping rule to obtain a first archive tree; and the digital credit archive is constructed based on the information extraction result, the first archive tree, the associated loan business type information corresponding to the current loan data source, and the preset sorting strategy to obtain the target digital credit archive corresponding to the current loan data source. That is, in the present application, the key information in the current loan data source in the effective state is first extracted in real time, and then the information extraction result is matched with the preconfigured image directory tree rule management table to determine the target business tree and the target archive tree. Then, the target tree node mapping rule is used to map the tree node of the target business tree to the tree node of the target archive tree to obtain a first archive tree. Finally, the information extraction result, the first archive tree, the associated loan business type information corresponding to the current loan data source, and the preset sorting strategy are used to construct the target digital credit archive corresponding to the current loan data source. In this way, the digital credit archive directory generation efficiency of various loan products can be effectively improved, and the workload of the client manager in collecting and sorting various business materials of a loan product of a customer can be effectively reduced, thereby improving the work efficiency and the timeliness and effectiveness of credit archive material storage and collection. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor based on the provided drawings.

[0042] Figure 1 A digital credit archive generation method flowchart is provided for the present application;

[0043] Figure 2 A specific digital credit archive generation method flowchart is provided for the present application;

[0044] Figure 3 An image directory tree structure schematic diagram is provided for the present application;

[0045] Figure 4 An archive tree structure schematic diagram provided for the present application;

[0046] Figure 5 A business tree structure schematic diagram provided for the present application;

[0047] Figure 6 A front page display schematic diagram of a digital credit archive provided for the present application;

[0048] Figure 7 A digital credit archive generation device structure schematic diagram provided for the present application;

[0049] Figure 8 An electronic device structure diagram provided for the present application. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts fall within the scope of the present application.

[0051] In the loan handling process of a commercial bank, the credit archive material directory structures of different loan products are different from each other, such as the archive material directory requirements of personal operating loans and personal consumption loans are different, and the archive directories formed in different business types of the same loan product in different handling stages are also different, such as the archive directories required by loan contract signing and real estate mortgage registration are also different. With the changes of national, industry and regulatory requirements, the credit archive material requirements of different loan products are also constantly updated. For the traditional collection and archiving of credit archive materials, the addition, modification and deletion of archive directories are easy to cause repeated development and resource waste. Therefore, when collecting paper archives manually, for a client manager, the archive material collection and collection tasks of multiple loan varieties of the same client and the archive collection tasks of different business types of one loan variety are tedious and repetitive, resulting in low efficiency of forming credit archive materials. Therefore, the present application provides a digital credit archive generation scheme, which can effectively improve the generation efficiency of the digital credit archive directories of various loan products and effectively reduce the workload of the client manager in collecting and arranging various business materials of one loan product of a client.

[0052] Referring to Figure 1 The embodiments of the present application disclose a digital credit archive generation method, which comprises:

[0053] Step S11, based on a preset image data acquisition interface, key information of a loan data source currently in an effective state is extracted to determine an information extraction result corresponding to the current loan data source.

[0054] Specifically, when it is needed to build a digital credit file for any loan of a customer in the embodiment, first, the information to be used is extracted, that is, the corresponding loan business type (also referred to as the business type to which the loan belongs), the loan investigation report type (also referred to as the investigation report type of the loan), the customer name, and the loan product name are extracted from the current loan data source in an effective state based on a preset image data acquisition interface to obtain an information extraction result. It can be understood that the loan data source not only needs to be in an effective state, but also needs to be the data source corresponding to the loan of the customer.

[0055] In step S12, the information extraction result is matched with a preconfigured image directory tree rule management table to determine a target business tree and a target file tree corresponding to the current loan data source; the image directory tree rule management table is a rule table used to manage the directory tree structure built based on image data.

[0056] In the embodiment, after the key information of the loan needed to be used is extracted, the information extraction result is matched with the preconfigured image directory tree rule management table to determine the target business tree and the target file tree corresponding to the current loan data source. That is, the preconfigured image directory tree rule management table is matched with the directory tree based on the loan business type and the loan investigation report type to determine the target business tree and the target file tree corresponding to the current loan data source. It can be understood that the target business tree and the target file tree are both image directory trees.

[0057] Further, regarding the image directory tree rule management table, it needs to be understood that, in combination with Figure 2 As shown in FIG. 8, before building the digital credit file, the image directory tree needs to be initialized, and the tree nodes in the obtained image directory tree structure need to be numbered and configured with attributes to obtain an initial image directory tree structure; the initial image directory tree structure is parameterized configured based on the loan business type and the data type to obtain the preconfigured image directory tree rule management table. For the created image directory tree structure, the image directory tree is composed of various tree nodes, the tree node is an independent unit, and has the following main attributes: tree node number, directory node name, parent node number, and child node number. The tree node number is unique and cannot be repeated, and can uniquely identify each tree node. The image directory tree structure can have multiple levels, the number of layers can be infinitely extended, the n-th layer is the parent layer of the n+1-th layer, the n+1-th layer is the child layer of the n-th layer, each layer can be configured with multiple tree nodes, and the number of tree nodes is not limited. The parent node of the tree node of the n+1-th layer is located in the n-th layer, and the child node of the tree node of the n+1-th layer is located in the n+2-th layer. In addition, the image directory tree has a unique image directory tree number, which cannot be repeated.

[0058] It can be understood that different levels and nodes in the image directory tree can refer to different kinds of loan key information, including but not limited to loan varieties, business scenarios (new loans, loan renewals, loan extensions, etc.), business types (credit, contracts, disbursement, etc.), image data nature, and specific data files.

[0059] In step S13, a target tree node mapping rule is determined based on the information extraction result, and the tree nodes of the target business tree are mapped to the tree nodes of the target archive tree using the target tree node mapping rule to obtain a first archive tree.

[0060] In this embodiment, in combination with Figure 2 As shown in the figure, after the target business tree and the target archive tree are determined, image data of the directory tree nodes need to be obtained and mapped. That is, first, the target tree node mapping rule is determined by matching the information extraction result, the tree numbers of the target business tree, and the tree numbers of the target archive tree with a pre-configured tree node mapping rule; then, the image data of the tree nodes at each level in the target business tree is searched from the current loan data source based on a first preset algorithm (which can be a computer vision algorithm or other algorithm selected based on actual needs) to obtain a search result; then, it is judged whether the preset data addition trigger condition is met based on the search result to obtain a judgment result; then, the target image data of the tree nodes at each level in the target archive tree is generated based on the search result, the judgment result, and the target tree node mapping rule to complete the corresponding tree node mapping operation, and the first archive tree and the first mapping completion time corresponding to the first archive tree are determined; then, the target image data corresponding to each tree node in the first archive tree is subjected to file integrity verification, file format verification, digital signature verification, and content verification based on a preset verification rule to determine the corresponding data verification result. That is, in this embodiment, the extracted loan key information is matched with the tree node mapping rule, and when the matching is successful, the image data of all levels of the business tree containing child nodes is found through the rule to generate the image data of all levels of the image directory tree (archive tree) containing child nodes. The mapping completion time of the corresponding archive tree is recorded.

[0061] It should be understood that the preset data addition trigger condition can be configured based on actual needs, for example, "automatically add board resolution when the loan amount is greater than 5 million". In addition, a cross-product inheritance mechanism can also be configured, through which different customer groups can inherit general data requirements. In this way, the data can be further improved, and the reliability of subsequent digital credit archive generation can be improved.

[0062] Further, after determining the corresponding material verification result, if the material verification result indicates that the target image material of the tree node is incomplete, the target missing item is determined based on a second preset algorithm (a natural language processing algorithm or other algorithm can be selected as the first preset algorithm based on actual needs); information corresponding to the target missing item is searched from the current loan data source based on the first preset algorithm to obtain to-be-completed information; or the target missing item is fed back to the client based on a preset interactive interface to receive the to-be-completed information returned by the client; and the target image material is supplemented based on the to-be-completed information to obtain the target image material after completion. That is, when the integrity of the image material is verified (which can be configured as 'optional' or'mandatory', and the same applies to the subsequent verification operations), the file format is verified, the digital signature is verified, and the content is verified (including verification of the completeness of the key terms of the contract), if it is found that the material is incomplete, the missing item needs to be detected and completed.

[0063] In addition, the embodiment can also provide a visual navigation experience related to the directory tree, including but not limited to multi-dimensional visual navigation, which is specifically used to provide different dimensions of the directory tree visual navigation experience, such as product dimension, customer dimension, business scenario (add, continue, extend, etc.) dimension, etc. In this way, the client manager, the file management personnel, the internal and external inspection personnel and other related personnel can conveniently view the target business tree and the target file tree, as well as the information covered by each node in the target business tree and the target file tree through the front-end page in real time, comprehensively and conveniently, thereby improving the user experience.

[0064] Step S14: Based on the information extraction result, the first file tree, the associated loan business type information corresponding to the current loan data source, and a preset sorting strategy, a digital credit file is constructed to obtain a target digital credit file corresponding to the current loan data source.

[0065] In the embodiment, the information extraction result is obtained based on the first file tree and the current loan data source. Figure 2As shown, after completing the tree node mapping, it is necessary to construct a digital credit file by using the loan key information and the mapped target file tree, i.e., the first file tree. Specifically, first, a plurality of associated loan business types corresponding to the current loan data source are determined based on the information extraction result; then, a second file tree corresponding to the plurality of associated loan business types and a second mapping completion time corresponding to the second file tree are obtained; and then, based on the first file tree corresponding to the current loan data source, the first mapping completion time, a preset sorting strategy, and the second file tree corresponding to the plurality of associated loan business types and the second mapping completion time, the file trees are arranged to determine the target digital credit file corresponding to the current loan data source. That is, in this embodiment, the key information of the loan is first obtained according to the key information of the loan, and then the target digital credit file of the loan of the customer is formed according to the image directory tree (file tree) generation time corresponding to each associated business type and the preset sorting rule.

[0066] As can be seen, in this application, first, the key information in the loan data source currently in the effective state is extracted in real time, and then the image directory tree rule management table is matched based on the information extraction result to determine the target business tree and the target file tree. Then, the target tree node mapping rule is used to map the tree nodes of the target business tree to the tree nodes of the target file tree to obtain the first file tree. Finally, the information extraction result, the first file tree, the associated loan business type information corresponding to the current loan data source, and the preset sorting strategy are used to construct the target digital credit file corresponding to the current loan data source. In this way, the generation efficiency of the digital credit file directory of various loan products can be effectively improved, and the workload of the customer manager in collecting and sorting various business materials of a loan product of a customer can be effectively reduced, thereby improving the work efficiency and the timeliness and effectiveness of the credit file management and collection.

[0067] The technical solutions of the embodiments of the application will be described in detail below with reference to the schematic diagrams disclosed in the specification. Figures 3-6

[0068] In a specific embodiment, in the image directory tree rule management table creation stage, each tree node is configured with a hierarchical attribute, a parent node number, and a child node number by numbering the tree nodes, such as tree node 0001, tree node 0002, tree node 0003, etc. The tree nodes can be flexibly configured into an image directory tree structure to form different image directory trees, and the image directory tree numbers can be image directory tree 001, image directory tree 002, etc. The structure of image directory tree 001 can be as follows: Figure 3 ​As shown, including tree node 0001, tree node 0002, tree node 0003, tree node 1200, tree node 2300, tree node 0004.

[0069] In the image directory tree matching stage, the pre-configured image directory tree rule management table includes the business tree rule management table and the archive tree rule management table corresponding to the business tree and the archive tree respectively, as shown in Table 1 and Table 2.

[0070] Table 1

[0071]

[0072] Table 2

[0073]

[0074] In the matching based on the tables shown in Table 1 and Table 2, Y-A1 is matched as the target business tree, and D-A1 is matched as the target archive tree. The structure of D-A1 is as shown in Figure 4 The structure of Y-A1 is as shown in Figure 5 After that, when mapping the tree nodes using Y-A1 and D-A1, a number of rules are matched from the pre-configured tree node mapping rules as target tree node mapping rules, and then mapping is performed. The pre-configured tree node mapping rules can be as shown in Table 3.

[0075] Table 3

[0076]

[0077] In Table 3, DXXXX is the tree node number of the image directory tree (archive tree), and YXXXX is the tree node number of the image directory tree (business tree). As can be seen from Table 3, in the tree node mapping from Y-A1 to D-A1, taking the tree node D2301 of D-A1 as an example, the image data of tree node D2301 needs to be generated based on the image data of tree nodes Y1301, Y1302, Y1303 and Y2001 in Y-A1 to complete the mapping, that is, if the image data under tree nodes Y1301, Y1302, Y1303 and Y2001 are customer rating declaration data, rating table, rating review and approval data, and customer operation flow analysis report, respectively, then the image data under D2301 are customer rating declaration data, rating table, rating review and approval data, and customer operation flow analysis report. Further, all nodes of the image directory tree (archive tree) D-A1 are traversed, and the image data of these nodes are found according to the mapping rules. The traversal completion time is recorded as the generation time of D-A1, that is, the mapping completion time.

[0078] Afterwards, the loan data source in the effective state is acquired in real time, and the image data of all nodes of the next image directory tree (file tree) D-XX is generated according to the loan key information, and the generation time T of D-XX is recorded.

[0079] Then, since the digital credit file construction needs to find the file tree of the associated business, the product of the customer is also needed to be obtained from the extracted loan key information as a personal business loan, and all associated business types of the loan of the customer are obtained, then all associated image directory trees (file trees) D-A1, D-A2, D-A3 and D-A4 are found, and the file trees are arranged in order according to the generation time and the preset sorting rule, then the digital credit file of the personal consumption loan of the customer is as follows:

[0080] 1. Specific business credit: D-A1, T1, M1;

[0081] 2. Loan contract: D-A2, T2, M2;

[0082] 3. Disbursement account: D-A3, T3, M3;

[0083] 4. Real estate mortgage registration: D-A4, T4, M4;

[0084] Wherein, T1, T2, T3 and T4 are the generation times of the corresponding image directory trees (file trees). M1, M2, M3 and M4 are the image data sets of the corresponding nodes. For example, M1 is the image data set of D2301, D2302 and D2303, which is composed of all tree nodes of the image directory tree (file tree) D-A1. Through the above information, the corresponding image data can be found, for example, the related image data of the specific business credit can be found through D-A1, T1, M1. The front page display example of the digital credit file is shown in Figure 6 .

[0085] Referring to Figure 7 , the embodiment of the application also discloses a digital credit file generation device, which comprises:

[0086] An information extraction module 11 is configured to extract key information from a loan data source in an effective state based on a preset image data acquisition interface, so as to determine an information extraction result corresponding to the current loan data source;

[0087] A directory tree matching module 12 is configured to match the information extraction result with a preconfigured image directory tree rule management table, so as to determine a target business tree and a target file tree corresponding to the current loan data source; the image directory tree rule management table is a rule table for managing the directory tree structure based on image data;

[0088] The tree node mapping module 13 is configured to determine a target tree node mapping rule based on the information extraction result, and map tree nodes of the target business tree to tree nodes of the target archive tree by using the target tree node mapping rule, to obtain a first archive tree.

[0089] The digital credit archive construction module 14 is configured to construct a target digital credit archive corresponding to the current loan data source based on the information extraction result, the first archive tree, associated loan business type information corresponding to the current loan data source, and a preset sorting strategy.

[0090] As can be seen, in the present application, first, key information in a loan data source currently in an effective state is extracted in real time, and then a pre-configured image directory tree rule management table is matched based on the information extraction result, to determine a target business tree and a target archive tree. Then, the tree nodes of the target business tree are mapped to the tree nodes of the target archive tree by using the determined target tree node mapping rule, to obtain a first archive tree. Finally, a target digital credit archive corresponding to the current loan data source is constructed by using the information extraction result, the first archive tree, associated loan business type information corresponding to the current loan data source, and a preset sorting strategy. In this way, the generation efficiency of the digital credit archive directory of various loan products can be effectively improved, and the workload of the client manager in collecting and sorting various business materials of a loan product of a client can be effectively reduced, thereby improving the work efficiency and the timeliness and effectiveness of the credit archive material storage and collection.

[0091] In some specific embodiments, the digital credit archive generation device can further include:

[0092] The directory tree initialization unit is configured to initialize an image directory tree, and perform number configuration and attribute configuration on the tree nodes in the obtained image directory tree structure, to obtain an initial image directory tree structure.

[0093] The management table determination unit is configured to perform parameterized configuration on the initial image directory tree structure based on a loan business type and a data type, to obtain the pre-configured image directory tree rule management table.

[0094] In some specific embodiments, the information extraction module 11 can include:

[0095] The information extraction unit is configured to extract corresponding loan business types, loan investigation report types, client names, and loan product names from a loan data source currently in an effective state based on a preset image data acquisition interface, to obtain an information extraction result.

[0096] In some specific embodiments, the directory tree matching module 12 can include:

[0097] a directory tree matching unit, configured to perform directory tree matching on a preconfigured image directory tree rule management table based on the loan business type and the loan investigation report type, to determine a target business tree and a target file tree corresponding to the current loan data source.

[0098] In some specific embodiments, the tree node mapping module 13 can specifically include:

[0099] a mapping rule matching unit, configured to perform matching on a preconfigured tree node mapping rule based on the information extraction result, the tree number of the target business tree, and the tree number of the target file tree, to determine a target tree node mapping rule;

[0100] an image data searching unit, configured to search for image data of tree nodes at each level in the target business tree from the current loan data source based on a first preset algorithm, to obtain a searching result;

[0101] a condition judging unit, configured to judge whether a preset data addition triggering condition is met based on the searching result, to obtain a judging result;

[0102] a tree node mapping unit, configured to generate target image data of tree nodes at each level in the target file tree based on the searching result, the judging result, and the target tree node mapping rule, to complete a corresponding tree node mapping operation, and determine a first file tree and a first mapping completion time corresponding to the first file tree;

[0103] a data verification unit, configured to perform file integrity verification, file format verification, digital signature verification, and content verification on the target image data corresponding to each tree node in the first file tree based on a preset verification rule, to determine a corresponding data verification result.

[0104] In some specific embodiments, the digital credit file construction module 14 can specifically include:

[0105] an associated business type determining unit, configured to determine a plurality of associated loan business types corresponding to the current loan data source based on the information extraction result;

[0106] a file tree obtaining unit, configured to obtain a second file tree corresponding to loan data sources of the plurality of associated loan business types and a second mapping completion time corresponding to the second file tree;

[0107] The digital credit profile construction unit is used to arrange the profile tree based on the first profile tree corresponding to the current loan data source and the first mapping completion time, the preset sorting strategy, and the second profile tree corresponding to the several associated loan business types and the second mapping completion time, so as to determine the target digital credit profile corresponding to the current loan data source.

[0108] In some specific embodiments, the digital credit profile generation device may further include:

[0109] The missing item determination unit is used to analyze the target image data based on a second preset algorithm to determine the target missing item if the data verification result shows that the target image data with tree nodes is incomplete.

[0110] The first information to be completed determination unit is used to search for information corresponding to the target missing item from the current loan data source based on a first preset algorithm, so as to obtain the information to be completed;

[0111] The second missing information determination unit is used to provide feedback on the target missing item to the client or based on a preset interactive interface, and to receive the missing information returned by the client.

[0112] The data completion unit is used to supplement the target image data based on the information to be completed, so as to obtain the completed target image data.

[0113] Furthermore, embodiments of this application also disclose an electronic device, Figure 8 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.

[0114] Figure 8 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the digital credit file generation method disclosed in any of the foregoing embodiments. Alternatively, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0115] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0116] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0117] The operating system 221 is used to manage and control the various hardware devices on the electronic device 20 and the computer program 222, which may be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program capable of performing the digital credit file generation method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs capable of performing other specific tasks.

[0118] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned disclosed digital credit profile generation method. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0119] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0120] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0121] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0122] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0123] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for generating digital credit profiles, characterized in that, include: Based on the preset image data acquisition interface, key information is extracted from the loan data source that is currently in effect, so as to determine the information extraction results corresponding to the current loan data source; Based on the information extraction results, the target business tree and target file tree corresponding to the current loan data source are determined by matching them with the pre-configured image catalog tree rule management table. The image directory tree rule management table is a rule table used to manage the directory tree structure built based on image data; Based on the information extraction results, the target tree node mapping rules are determined, and the target tree node mapping rules are used to map the tree nodes of the target business tree to the tree nodes of the target archive tree to obtain the first archive tree; Based on the information extraction results, the first file tree, the associated loan business type information corresponding to the current loan data source, and the preset sorting strategy, a digital credit file is constructed to obtain the target digital credit file corresponding to the current loan data source.

2. The method for generating digital credit files according to claim 1, characterized in that, Before matching the information extraction results with a pre-configured image catalog tree rule management table to determine the target business tree and target file tree corresponding to the current loan data source, the process also includes: Initialize the image catalog tree, and configure the numbering and attributes of the tree nodes in the obtained image catalog tree structure to obtain the initial image catalog tree structure; The initial image catalog tree structure is parameterized based on the loan business type and data type to obtain the configured image catalog tree rule management table.

3. The method for generating digital credit files according to claim 1, characterized in that, The extraction of key information from currently active loan data sources based on a preset image data acquisition interface includes: Based on the preset image data acquisition interface, the corresponding loan business type, loan investigation report type, customer name, and loan product name are extracted from the currently active loan data source to obtain the information extraction results.

4. The method for generating digital credit files according to claim 3, characterized in that, The process of matching the extracted information with a pre-configured image catalog tree rule management table to determine the target business tree and target file tree corresponding to the current loan data source includes: Based on the loan business type and the loan investigation report type, the pre-configured image directory tree rule management table is matched to determine the target business tree and target file tree corresponding to the current loan data source.

5. The method for generating digital credit files according to any one of claims 1 to 4, characterized in that, The step of determining the target tree node mapping rule based on the information extraction result, and using the target tree node mapping rule to map the tree nodes of the target business tree to the tree nodes of the target archive tree, includes: The target tree node mapping rule is determined by matching the information extraction results, the tree number of the target business tree, and the tree number of the target archive tree with the pre-configured tree node mapping rules. Based on the first preset algorithm, image data of tree nodes at each level in the target business tree are searched from the current loan data source to obtain search results; Based on the search results, determine whether the preset data appending trigger condition is met, and obtain the determination result; Based on the search results, the judgment results, and the target tree node mapping rules, target image data of tree nodes at each level in the target file tree are generated to complete the corresponding tree node mapping operation, and the first file tree and the first mapping completion time corresponding to the first file tree are determined. Based on preset verification rules, the target image data corresponding to each tree node in the first archive tree are subjected to file integrity verification, file format verification, digital signature verification, and content verification to determine the corresponding data verification results.

6. The method for generating digital credit profiles according to claim 5, characterized in that, The construction of digital credit files based on the information extraction results, the first file tree, the associated loan business type information corresponding to the current loan data source, and a preset sorting strategy includes: Based on the information extraction results, several associated loan business types corresponding to the current loan data source are determined; Obtain the second file tree corresponding to the loan data source of the plurality of associated loan business types and the second mapping completion time corresponding to the second file tree; The file tree is arranged based on the first file tree corresponding to the current loan data source, the first mapping completion time, the preset sorting strategy, and the second file tree and the second mapping completion time corresponding to the several associated loan business types, so as to determine the target digital credit file corresponding to the current loan data source.

7. The method for generating digital credit files according to claim 5, characterized in that, After determining the corresponding data verification result, the process also includes: If the data verification results indicate that the target image data containing tree nodes is incomplete, then the target image data is analyzed based on the second preset algorithm to determine the missing target items; Based on the first preset algorithm, information corresponding to the target missing item is searched from the current loan data source to obtain the information to be completed; Alternatively, the system may provide feedback on the target missing item to the client based on a preset interactive interface, and receive the information to be completed returned by the client. The target image data is supplemented based on the information to be supplemented to obtain the supplemented target image data.

8. A digital credit profile generation device, characterized in that, include: The information extraction module is used to extract key information from the currently active loan data source based on the preset image data acquisition interface, so as to determine the information extraction result corresponding to the current loan data source. The directory tree matching module is used to match the information extraction results with a pre-configured image directory tree rule management table to determine the target business tree and target file tree corresponding to the current loan data source. The image directory tree rule management table is a rule table used to manage the directory tree structure built based on image data; The tree node mapping module is used to determine the target tree node mapping rule based on the information extraction result, and to use the target tree node mapping rule to map the tree nodes of the target business tree to the tree nodes of the target archive tree to obtain the first archive tree; The digital credit profile construction module is used to construct a digital credit profile based on the information extraction results, the first profile tree, the associated loan business type information corresponding to the current loan data source, and a preset sorting strategy, so as to obtain a target digital credit profile corresponding to the current loan data source.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the digital credit file generation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store a computer program, which, when executed by a processor, implements the digital credit file generation method as described in any one of claims 1 to 7.

Images