CN115689721A - Credit system information processing method, device, equipment and medium - Google Patents
Credit system information processing method, device, equipment and medium Download PDFInfo
- Publication number
- CN115689721A CN115689721A CN202211314457.0A CN202211314457A CN115689721A CN 115689721 A CN115689721 A CN 115689721A CN 202211314457 A CN202211314457 A CN 202211314457A CN 115689721 A CN115689721 A CN 115689721A
- Authority
- CN
- China
- Prior art keywords
- credit
- rule
- keywords
- label
- matching
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure provides a credit system information processing method which can be applied to the technical field of artificial intelligence. The method comprises the following steps: acquiring business elements in a credit system information query application, wherein the business elements comprise customer information and business information of a credit application business; obtaining N first keywords according to the service elements; matching the N first keywords with at least one of credit category labels, credit rule labels and regulation contents of each credit system in M credit systems, wherein each credit system is preset with a corresponding credit category label and/or credit rule label; returning the matched at least one first credit system. The present disclosure also provides a credit system information processing apparatus, a device, a storage medium, and a program product.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence technologies, and in particular, to a credit system information processing method, apparatus, device, medium, and program product.
Background
The internal control compliance management is a basic management work of a commercial bank, the compliance risk is also the first combination of credit risk, market risk, operation risk and other risks, and the bank emphasizes on ensuring the consistency of various risk management policies and procedures.
As an important gripper for preventing and resolving major risks in banking industry, internal control compliance faces many problems in practice, particularly in the credit field, credit practitioners must execute according to policy system files, but at present, business personnel often encounter the problems of 'unavailable, incomplete and incomplete' and the like when searching system files manually or by using a general search engine, the number of the credit system files is large, the credit system files are frequently updated, cross-covered items often exist, manual searching and comparison are needed, and the business handling efficiency is reduced. If the found credit system content is incomplete, the business operation credit risk caused by not knowing the policy system still exists.
Disclosure of Invention
In view of the foregoing, the present disclosure provides a credit system information processing method, apparatus, device, medium, and program product that achieve accurate matching.
One aspect of the disclosed embodiments provides a credit system information processing method, including: acquiring business elements in a credit system information query application, wherein the business elements comprise customer information and business information of a credit application business; obtaining N first keywords according to the service elements, wherein N is greater than or equal to 1; matching the N first keywords with at least one of credit category labels, credit rule labels and regulation contents of each credit system in M credit systems, wherein each credit system is preset with a corresponding credit category label and/or credit rule label, and M is greater than or equal to 1; returning the matched at least one first credit system.
According to an embodiment of the disclosure, the matching the N first keywords with at least one of credit category labels, credit rule labels, and regulatory content of each credit institution in the M credit institutions comprises: matching the N first keywords with credit category labels of the M credit systems to obtain at least one second credit system matched with the credit category labels; matching the N first keywords with the credit rule tags of the at least one second credit system to obtain at least one third credit system matched with the credit rule tags; and matching the N first keywords with the content of the at least one third credit system to obtain the at least one first credit system.
According to an embodiment of the disclosure, said matching the N first keywords with the content of the at least one third credit regime comprises: obtaining a first feature vector according to the N first keywords; obtaining a corresponding second feature vector according to the content of each third credit system; and calculating the similarity between the first feature vector and a second feature vector corresponding to each third credit system.
According to an embodiment of the disclosure, the M credit regimes belong to S rules and regulations documents, the method further comprises, before matching the N first keywords to at least one of a credit category label, a credit rule label, and a regulatory content of each credit regime of the M credit regimes: classifying said S regulatory documents to obtain at least one credit category label for each regulatory document, said each regulatory document comprising at least one credit regime, S being greater than or equal to 1; and setting a corresponding credit category label for each credit system according to at least one credit category label of each regulatory document.
According to an embodiment of the disclosure, the classifying the S regulatory documents includes: performing word frequency calculation on part or all of the contents in each regulation document; matching the second keywords with the word frequency larger than or equal to a preset value with the dictionary value under each credit category label; determining at least one credit category label for each of the regulatory documents based on the matched dictionary values.
According to the embodiment of the disclosure, after setting the corresponding credit category label for each credit system, the method further comprises the following steps: according to the credit category label of each credit system, performing credit rule extraction on the credit system, wherein the credit rule extraction modes between different credit category labels are the same or different; and setting a corresponding credit rule label according to the credit rule extraction result of each credit system.
According to the embodiment of the disclosure, setting the corresponding credit rule tag according to the credit rule extraction result of each credit system comprises: standardizing the credit rule extraction result of each credit system; matching the credit rule extraction result after the standardization processing with at least one service element; and setting a corresponding credit rule label according to the matched business element.
Another aspect of the disclosed embodiments provides a credit system information processing apparatus including: the business element module is used for acquiring business elements in the credit system information inquiry application, wherein the business elements comprise customer information and business information of the credit application business; the keyword module is used for obtaining N first keywords according to the service elements, wherein N is greater than or equal to 1; the matching module is used for matching the N first keywords with at least one of credit category labels, credit rule labels and regulation contents of each credit system in M credit systems, wherein each credit system is preset with a corresponding credit category label and/or credit rule label, and M is greater than or equal to 1; and the target system returning module is used for returning the matched at least one first credit system.
The credit system information processing apparatus includes modules for performing the respective steps of the method as described in any one of the above.
Another aspect of the disclosed embodiments provides an electronic device, including: one or more processors; a storage device to store one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method as described above.
Yet another aspect of the embodiments of the present disclosure provides a computer-readable storage medium having stored thereon executable instructions, which when executed by a processor, cause the processor to perform the method as described above.
Another aspect of the embodiments of the present disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements the method as described above.
One or more of the above embodiments have the following advantageous effects: compared with the prior art that the information of the credit system is found manually or by using a general search engine, the method sets a corresponding credit category label and/or credit rule label for each credit system in advance, and matches N keywords during application inquiry according to the information of the credit system with at least one of the credit category label, the credit rule label and the content of the regulation and regulation of each credit system in M credit systems, so that a target system to be inquired can be returned from at least one dimension of the credit category label, the credit rule label and the content of the regulation and regulation, thereby effectively solving the problems of inaccuracy, time consumption and labor consumption during the existing search, screening, evaluation and matching of the information of the credit system and improving the handling efficiency.
Drawings
The foregoing and other objects, features and advantages of the disclosure will be apparent from the following description of embodiments of the disclosure, which proceeds with reference to the accompanying drawings, in which:
fig. 1 schematically shows an application scenario diagram of a credit system information processing method according to an embodiment of the present disclosure;
FIG. 2 schematically shows a flow diagram of a credit system information processing method according to an embodiment of the disclosure;
FIG. 3 schematically illustrates a flow chart for matching first keywords according to an embodiment of the disclosure;
FIG. 4 schematically illustrates a flow diagram for matching first keywords according to another embodiment of the disclosure;
FIG. 5 schematically illustrates a flow diagram for setting a credit category label according to an embodiment of the disclosure;
FIG. 6 schematically illustrates a flow chart for classifying regulatory documents according to an embodiment of the present disclosure;
FIG. 7 schematically illustrates a flow diagram for setting credit rule tags according to an embodiment of the disclosure;
FIG. 8 schematically shows a flow diagram for setting credit rule tags according to another embodiment of the present disclosure;
FIG. 9 schematically shows a flow diagram of a credit regime information processing method according to another embodiment of the disclosure;
fig. 10 schematically shows a block diagram of the structure of a credit system information processing apparatus according to an embodiment of the present disclosure; and
FIG. 11 schematically illustrates a block diagram of an electronic device adapted to implement a credit regime information processing method according to an embodiment of the disclosure.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that these descriptions are illustrative only and are not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
In those instances where a convention analogous to "at least one of A, B, and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B, and C" would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, and C together, etc.).
Fig. 1 schematically shows an application scenario diagram of a credit system information processing method according to an embodiment of the present disclosure.
As shown in fig. 1, an application scenario 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. Network 104 is the medium used to provide communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 105 may be a server providing various services, such as a background management server (for example only) providing support for websites browsed by users using the terminal devices 101, 102, 103. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to the user request) to the terminal device.
It should be noted that the credit system information processing method provided by the embodiment of the present disclosure may be generally executed by the server 105. Accordingly, the credit system information processing apparatus provided by the embodiment of the present disclosure may be generally provided in the server 105. The credit system information processing method provided by the embodiment of the present disclosure may also be executed by a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105. Accordingly, the credit system information processing apparatus provided in the embodiment of the present disclosure may also be provided in a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
The credit system information processing method of the embodiment of the present disclosure will be described in detail below with reference to fig. 2 to 9 based on the scenario described in fig. 1.
Fig. 2 schematically shows a flow chart of a credit system information processing method according to an embodiment of the present disclosure.
As shown in fig. 2, the credit system information processing method of this embodiment includes operations S210 to S240.
In operation S210, the credit system information is acquired to query the service elements in the application, and the service elements include customer information and service information of the credit application service.
The credit system refers to a general term of various rules, criteria and the like related to credit and credit business, and may include organization of credit activities, establishment of credit laws and regulations, setting of credit institutions and the like. The credit system information includes the above credit institutions, organizations, credit laws and regulations, etc. A user (e.g., credit service personnel) may enter information to be queried through a terminal device browser and send a query application. The credit business comprises the business that the credit institution withdraws principal and interest through loan, and the client information comprises information such as the type, occupation, property condition and loan application of the loan client. The service information comprises information such as loan types, loan terms, loan range, loan links and the like.
In operation S220, N first keywords are obtained according to the service element, where N is greater than or equal to 1.
For example, according to business elements such as a customer code, a customer name or a loan type, which are input by a foreground customer manager, the customer code is utilized to inquire out that the type of the customer is 'personal customer' from a corresponding database, the type of the loan is input by the foreground as 'legal account overdraft business', the specific term of a page is input, and the like, the N first keywords are determined to comprise 'personal customer, legal account overdraft business, term'.
In operation S230, the N first keywords are matched with at least one of a credit category tag, a credit rule tag, and a regulatory content of each credit system of M credit systems, each credit system is preset with a corresponding credit category tag and/or credit rule tag, and M is greater than or equal to 1.
Illustratively, after the query application of the page is responded, the business elements input by the foreground system are obtained and the keywords are extracted, the extracted keywords are input into a pre-established regulation and regulation item library. The rules and regulations entry library comprises M credit systems, and each credit system is associated with one or more corresponding credit category labels and/or one or more credit rule labels.
The credit category labels are used for identifying content categories recorded by each credit system, for example, the content categories are classified according to three dimensions of products, customer types and business links, and corresponding category labels are allocated according to business information in each dimension. The credit rule tags are used to classify rules that exist in various credit regimes, such as deadline rules, interest rate rules, and customer credit rating rules.
In operation S240, the matched at least one first credit system is returned.
For example, "individual customer, legal account overdraft service, deadline" may be matched to one or more of a credit category label, a credit rule label, and regulatory content, and the matching results returned. The matching result may include a system with one of a hit credit category tag, a credit rule tag, and regulatory content or a hit of at least two.
According to the embodiment of the disclosure, for the mode of manually or using a general search engine to search the information of the credit system in the prior art, the corresponding credit category label and/or credit rule label is set for each credit system in advance, the N keywords during the inquiry application according to the information of the credit system are matched with at least one of the credit category label, the credit rule label and the content of the regulation of each credit system in the M credit systems, the target system to be inquired can be returned from at least one dimension of the credit category label, the credit rule label and the content of the regulation, the problems of inaccuracy, time consumption and labor consumption during the existing search, screening, evaluation and matching of the information of the credit system are effectively solved, and the processing efficiency is improved.
Fig. 3 schematically shows a flow chart of matching first keywords according to an embodiment of the present disclosure.
As shown in fig. 3, matching the N first keywords with at least one of the credit category label, the credit rule label, and the regulatory content of each credit system of the M credit systems in operation S230 includes operations S310 to S330.
In operation S310, the N first keywords are matched with the credit category tags of the M credit systems, and at least one second credit system having the matched credit category tags is obtained.
In some embodiments, each first keyword may be matched to a credit category label for each system. In other embodiments, the common types of tags in the M credit systems may be counted, and the N first keywords may be matched with the types of tags.
As described above, the labels with dimensions such as product, customer type, business link, and the like are present, and the label with the individual customer type can be obtained by matching the "overdraft business of individual customer, legal account, term" with the label with each dimension. The system in which the individual customer type tag is set is a second credit system.
In operation S320, the N first keywords are matched with the credit rule tags of the at least one second credit regime, obtaining at least one third credit regime having the matched credit rule tags.
For example, the 'personal customer, legal account overdraft service, deadline' is matched with the credit rule label of each second credit system, and the system provided with the deadline label is a third credit system.
In operation S330, the N first keywords are matched with the content of the at least one third credit system to obtain the at least one first credit system.
In some embodiments, the N first keywords may be searched in each third credit system, and whether the first credit system is determined based on the number of keywords (e.g., greater than some preset threshold) searched. In other embodiments, a similarity between the N first keywords and each piece of the third credit system content may be calculated.
According to the embodiment of the disclosure, by sequentially matching the credit category label, the credit rule label and the regulatory content, the target range can be gradually narrowed, and the accuracy of the returned system can be improved by combining factors of multiple aspects of the category, the rule and the content.
Fig. 4 schematically shows a flow chart of matching a first keyword according to another embodiment of the present disclosure.
As shown in fig. 4, matching the N first keywords with the content of the at least one third credit regime in operation S330 includes operations S410 to S430.
In operation S410, a first feature vector is obtained according to the N first keywords.
For example, a foreground-entered service factor is obtained, a corresponding keyword is generated, and a first feature vector a = { a } is formed 1 ，a 2 ，…，a n }。
In operation S420, a corresponding second feature vector is obtained according to the content of each third credit system.
Content keywords of each third credit system can be extracted to form a second feature vector b = { b = { (b) } 1 ，b 2 ，......，b n }。
In some embodiments, tf-idf keyword extraction may be performed on each regulatory document to which the third credit system belongs, and a second feature vector may be generated based on the keyword extraction result. The details are as follows.
E.g. calculated according to the tf-idf algorithmAnd forming feature vectors b = { b) by the key phrases obtained by sequencing 1 ，b 2 ，......，b n }. And (4) extracting the keyword features aiming at each third credit system, and solving the tf-idf value of each word in the published regulatory system items based on the tf-idf algorithm. The following equation 1):
tf-idf (t, d) = tf (t, d) × idf (t) formula 1)
Wherein t is a word, d is a regulatory document, tf (t, d) is the number of times a word appears in the corresponding document,
n is the total number of documents, idf (t) is the number of documents containing the word t.
Sorting the tf-idf values of a plurality of words in a regulation document according to the sequence from big to small, screening the first 5 words (only for example) as the keywords of the document according to the sorting result, identifying, and generating a second feature vector b according to the 5 words.
In operation S430, a similarity between the first feature vector and a second feature vector corresponding to each third credit regime is calculated.
Calculating the similarity between a and b, then using a i 、b i Respectively representing the word frequency of each keyword in a and b, and calculating the similarity by using a Vector Space Model (VSM), as shown in the following formula 2):
and by analogy, similarity calculation is carried out on the characteristic vector a which is recorded and inquired and each characteristic vector in the regulation library one by one, and therefore the policy system item ordering from high similarity to low similarity is obtained.
In some embodiments, keyword recognition may be performed according to the content of each rule and if a keyword that is the same as or similar to a credit category tag is recognized, the corresponding tag will be set. In other embodiments, the credit category label may be determined from a file in which each regulatory regime resides. This is further illustrated by fig. 5 and 6.
FIG. 5 schematically shows a flow diagram for setting a credit category label according to an embodiment of the disclosure.
Before the N first keywords are matched with at least one of the credit category label, the credit rule label, and the regulatory content of each credit system of the M credit systems in operation S230, as shown in fig. 5, setting the credit category label of this embodiment includes operations S510 to S520.
At operation S510, the S regulatory documents are categorized to obtain at least one credit category label for each regulatory document, each regulatory document including at least one credit regime, and S is greater than or equal to 1. The M credit systems belong to the S regulation documents.
The S regulatory documents include credit system entries from various related departments, each of which may be instituted from multiple dimensions, so that one or more credit category labels may be provided according to the credit system content in each document. Tags may be determined, for example, by document topic recognition using Natural Language Processing (NLP) techniques on entire documents. For another example, word frequency calculation may be performed on the entire document to determine the label based on the keyword.
FIG. 6 schematically illustrates a flow chart for classifying regulatory documents according to an embodiment of the present disclosure.
As shown in FIG. 6, classifying S regulatory documents in operation S510 includes operations S610 through S630.
In operation S610, a word frequency calculation is performed on part or all of the contents of each regulatory document.
When the word frequency calculation is performed on the part of the content, the word frequency calculation can be performed on the content of each chapter.
In operation S620, the second keyword having the word frequency greater than or equal to the preset value is matched with the dictionary value under each credit category tag.
At operation S630, at least one credit category label for each regulatory document is determined based on the matched dictionary values.
Illustratively, the classification is carried out according to three dimensions of products, client types and business links, each classification corresponds to a first-level label, corresponding dictionary values are collected from a database under each category (for example, dictionary values under the product category, including operating capital loan, project loan, general legal overdraft loan and the like, dictionary values under the client type, including legal clients, institution clients, small enterprise clients, personal clients and the like, and dictionary values under the business links, including rating, credit granting, business handling and the like). And performing word frequency calculation on a structured regulation system, extracting a second keyword with the most occurrence frequency or more than or equal to a preset value to perform large-class matching and classification, and performing data tagging by using a defined primary tag and a specific class, such as a product large class-project loan class tag, a client type large class-legal client class tag, a business link large class-credit category tag and the like.
At operation S520, a corresponding credit category label is set for each credit regime according to the at least one credit category label of each regulatory document.
For example, where a regulatory document has a credit category label, the label may be assigned to all entries in the document. Where a regulatory document has multiple credit category labels, items therein may be assigned corresponding labels based on the source content (e.g., each chapter) of each credit category label.
According to the embodiment of the disclosure, there may be a case where the contents of a credit system are few and sufficient information cannot be given for classification. Considering that the content of each regulatory document has sufficient information and can embody the subject of the article, the setting of the credit category label can be more accurate by starting from one regulatory document.
Fig. 7 schematically illustrates a flow diagram for setting a credit rule tag according to an embodiment of the disclosure.
After the corresponding credit category tag is set for each credit system in operation S520, as shown in fig. 7, setting the credit rule tag of this embodiment includes operations S710 to S720.
In operation S710, credit rule extraction is performed on each credit system according to the credit category label of the credit system, wherein the credit rule extraction manner between different credit category labels is the same or different.
For example, a project loan category label and a credit granting category label are used, the project loan category label and the credit granting category label belong to different categories of products and business links, the category difference is large, different credit rule requirements exist for loan clients, and the loan clients can pay only if the loan clients meet respective credit rules. For example, a project loan has credit rules of project types, research and development personnel backgrounds, project contents, years and the like, while a credit link has credit rules of overdue requirements, cash flow requirements, good operating conditions, good financial conditions and the like, and different analytic modes, namely credit rule extraction modes, are provided due to the different characteristics of the credit rules.
And different credit categories under the same category may have the same credit rule extraction mode, and can be selected according to actual conditions.
In operation S720, a corresponding credit rule tag is set according to the credit rule extraction result of each credit system. The credit rule extraction result comprises the content of the credit rule contained in each credit system.
According to the embodiment of the disclosure, the corresponding credit rule tag is set through the content of the credit rule, so that the matching of the credit rule can be realized to a certain extent during inquiry, and the credit system information which is known by a user can be returned more accurately.
Fig. 8 schematically shows a flow diagram for setting a credit rule tag according to another embodiment of the disclosure.
As shown in fig. 8, setting the corresponding credit rule tag according to the credit rule extraction result of each credit system in operation S720 includes operations S810 to S830.
In operation S810, a credit rule extraction result of each credit system is standardized.
For example, the validity period of the overdraft credit for legal account does not exceed 2 years at most. The overdraft limit can be recycled in the validity period, and new overdraft can not be generated after the overdraft limit expires. The corporate account overdraft period is a specific period of actual overdraft of a client, and the rule extraction is carried out on a system entry of which the maximum time is not more than 3 months.
The credit rule extraction result is that the valid period of the corporate account overdraft limit is not more than 2 years to the maximum extent, the corporate account overdraft limit is the specific limit of the actual overdraft of the client and is not more than 3 months to the maximum extent, and after the standardization processing, the rule is that the valid period of the corporate account overdraft limit is not more than 2 years and the corporate account overdraft limit is not more than 3 months.
In operation S820, the standardized credit rule extraction result is matched with at least one business element.
The tagged credit rules may be tagged with credit rule tags matching business elements as secondary tags, such as detailed business elements, e.g., financing terms, financing rates, customer credit ratings, etc.
In operation S830, a corresponding credit rule tag is set according to the matched business element.
In some embodiments, if the matching secondary label is "deadline", the detailed rule label is "validity period of the corporate account overdraft limit is less than or equal to 2 years, and the corporate account overdraft limit is less than or equal to 3 months". In other embodiments, only the secondary label "deadline" may be used as a credit rule label.
According to the embodiment of the disclosure, the credit rules described by words in the rules and regulations may not be accurately searched, so that the rule contents are standardized, and the corresponding tags are set, which is more favorable for accurate query of the credit system information.
Fig. 9 schematically shows a flowchart of a credit system information processing method according to another embodiment of the present disclosure.
As shown in fig. 9, the credit system information processing method of this embodiment includes operations S910 to S960.
In operation S910, data is collected.
Illustratively, the policy and regulatory information, such as regulatory documents, issued by regulatory agencies and units are accessed, processed, and stored. The method comprises the steps of performing text preprocessing (cleaning dirty data) on published regulatory documents, performing structuring processing, extracting the same information in the regulatory documents with different formats, and filling the same information in a fixed template, so that subsequent identification is facilitated.
Because the formats and the institutional contents of the regulatory documents issued by different organizations, units or departments are different, the regulatory documents from different sources are processed in a structuralized way, and the efficiency of forming the regulatory entry library can be improved.
In operation S920, the storage is classified.
The preprocessed S rules and regulations documents may be classified and corresponding credit category labels may be set for each credit system, with reference to corresponding embodiments of fig. 5 and 6. And finally, storing the system credits and the corresponding primary labels (credit category labels).
Illustratively, a bank system file 'company client legal account overdraft business management method' is obtained, text preprocessing, cutting and structuring are carried out on the bank system file according to chapters and paragraphs to form a system text with a fixed format, word frequency calculation is carried out on the whole text to obtain a keyword with the highest word frequency of the file as 'legal account overdraft business', the keyword is successfully matched with dictionary value 'legal account overdraft business' under a primary label 'product', and the text is stored under a product large-class module.
In operation S930, a rule is extracted.
Text cutting may be performed on each regulatory document to form regulatory entries, credit rule extraction may be performed entry by entry, and secondary tags (credit rule tags) may be matched and tagged, with reference to the embodiments of fig. 7 and 8. And finally, storing the secondary label and the corresponding regulation item.
In operation S940, a keyword is extracted.
The word frequency calculation extraction is performed on the regulation text generated in operation S920, for example, a certain system in the general rule in the "method for managing overdraft business of corporate client legal account" document:
corporate client corporate account overdraft (hereinafter "corporate account overdraft") is a short term financing method for approving the overdraft limit of a corporate client account and allowing the corporate client to overdraft directly within the approved overdraft limit to obtain credit funds when the account is not settled for payment.
And (3) obtaining the tf-idf (t, d) value of each word based on the tf-idf algorithm and sequencing, thus obtaining the keywords of overdraft, corporate account overdraft, company client, account and overdraft limit.
Particularly, the corresponding word frequency calculation rule may be set according to the first-level tag, and the keywords matched with the first-level tag are considered preferentially.
Through operations 910 to S940, a rule and regulation entry base storing each credit system, credit category label, credit rule label, and keyword extraction result may be obtained.
In operation S950, a match is queried.
Responding to the inquiry application of the page, acquiring the service elements input by the foreground system, extracting key words (such as the key word of 'company client and corporate account overdraft service, term'), inputting the extracted key words into a pre-established regulation and regulation item library, and firstly performing matching calculation with a first-level label to find a corresponding large class. And then, similarity calculation based on word vectors is respectively carried out on the secondary label and the key word of the issued regulation, and the regulation item related to the business to be managed is inquired.
For example, extracting keywords according to the service elements to obtain a feature vector a. And for each credit system, obtaining a characteristic vector b according to the primary label and/or the label under the primary label, and the secondary label and/or the specific label under the secondary label. A feature vector c is obtained according to the keyword extraction result of operation S940. Similarity is calculated between the feature vector a and the feature vectors b and c in turn, referring to the embodiment of fig. 3 and 4.
In operation S960, the result is pushed.
And acquiring matched system and regulation items, sorting according to the similarity and pushing to a reference policy interface of the foreground, displaying the system items and system files corresponding to the result with high similarity in the front, and supporting the viewing of the original text corresponding to the policy items in a hyperlink mode.
According to the embodiment of the disclosure, the system and the rules can be processed into the system clause cases with service dimensionality, client as a center, unified logic and rich content, the system clause cases matched with the query application operation can be obtained from the system and the rule clause entry library according to the key element keywords displayed by the system, the user can be quickly and accurately matched with the corresponding policy and system policies, the problems that the conventional searching, screening, evaluating and matching wastes time and labor are effectively solved, the user is better served, the user is ensured to clearly know the service specification main points and the handling requirements, and the handling efficiency is improved.
Based on the credit system information processing method, the disclosure also provides a credit system information processing device. The apparatus will be described in detail below with reference to fig. 10.
Fig. 10 schematically shows a block diagram of the structure of a credit system information processing apparatus according to an embodiment of the present disclosure.
As shown in fig. 10, the credit system information processing apparatus 1000 of this embodiment includes a business element module 1010, a keyword module 1020, a matching module 1030, and a target system return module 1040.
The service element module 1010 may perform operation S210 for obtaining the credit system information to query the service elements in the application, where the service elements include customer information and service information of the credit application service.
The keyword module 1020 may perform operation S220 for obtaining N first keywords from the service element, where N is greater than or equal to 1.
The keyword module 1020 is also used for keyword extraction of regulatory documents according to embodiments of the present disclosure.
The matching module 1030 may perform operation S230 for matching the N first keywords with at least one of a credit category tag, a credit rule tag, and a content of a regulation of each credit regime of M credit regimes, each credit regime being preset with a corresponding credit category tag and/or credit rule tag, M being greater than or equal to 1.
According to the embodiment of the present disclosure, the matching module 1030 may further perform operations S310 to S330, and operations S410 to S430, which are not described herein again.
The target system returning module 1040 may perform operation S240 for returning the matched at least one first credit system.
According to an embodiment of the present disclosure, the information processing apparatus 1000 may further include a data acquisition module for performing text preprocessing and structuring on the published regulatory document.
According to an embodiment of the present disclosure, the information processing apparatus 1000 may further include a classification storage module, and the module may perform operations S510 to S520, and operations S610 to S630, which are not described herein again.
According to an embodiment of the present disclosure, the information processing apparatus 1000 may further include a rule extraction module, and the rule extraction module may perform operations S710 to S720, and operations S810 to S830, which are not described herein again.
It should be noted that the information processing apparatus 1000 includes modules respectively configured to execute the steps of any one of the embodiments described in fig. 2 to 9. The implementation, solved technical problems, implemented functions, and achieved technical effects of each module/unit/subunit and the like in the apparatus part embodiment are respectively the same as or similar to the implementation, solved technical problems, implemented functions, and achieved technical effects of each corresponding step in the method part embodiment, and are not described herein again.
According to an embodiment of the present disclosure, any plurality of the business element module 1010, the keyword module 1020, the matching module 1030, and the target system returning module 1040 may be combined into one module to be implemented, or any one of the modules may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in one module.
According to an embodiment of the present disclosure, at least one of the business element module 1010, the keyword module 1020, the matching module 1030, and the target regime return module 1040 may be implemented at least partially as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or may be implemented in any one of three implementations of software, hardware, and firmware, or in a suitable combination of any of them. Alternatively, at least one of the business element module 1010, the keyword module 1020, the matching module 1030, and the target system return module 1040 may be at least partially implemented as a computer program module that, when executed, may perform a corresponding function.
Fig. 11 schematically shows a block diagram of an electronic device adapted to implement a credit system information processing method according to an embodiment of the disclosure.
As shown in fig. 11, an electronic device 1100 according to an embodiment of the present disclosure includes a processor 1101, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 1102 or a program loaded from a storage section 1108 into a Random Access Memory (RAM) 1103. The processor 1101 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or related chip sets and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 1101 may also include on-board memory for caching purposes. The processor 1101 may comprise a single processing unit or a plurality of processing units for performing the different actions of the method flows according to the embodiments of the present disclosure.
In the RAM 1103, various programs and data necessary for the operation of the electronic device 1100 are stored. The processor 1101, the ROM 1102, and the RAM 1103 are connected to each other by a bus 1104. The processor 1101 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 1102 and/or the RAM 1103. It is to be noted that the programs may also be stored in one or more memories other than the ROM 1102 and the RAM 1103. The processor 1101 may also perform various operations of the method flows according to the embodiments of the present disclosure by executing programs stored in the one or more memories.
The present disclosure also provides a computer-readable storage medium, which may be embodied in the devices/apparatuses/systems described in the above embodiments. Or may exist alone without being assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.
According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include the ROM 1102 and/or the RAM 1103 and/or one or more memories other than the ROM 1102 and the RAM 1103 described above.
Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the method illustrated in the flow chart. When the computer program product runs in a computer system, the program code is used for causing the computer system to realize the method provided by the embodiment of the disclosure.
The computer program performs the above-described functions defined in the system/apparatus of the embodiments of the present disclosure when executed by the processor 1101. The systems, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.
In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, and the like. In another embodiment, the computer program may also be transmitted in the form of a signal on a network medium, distributed, downloaded and installed via the communication part 1109, and/or installed from the removable medium 1111. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 1109 and/or installed from the removable medium 1111. The computer program, when executed by the processor 1101, performs the above-described functions defined in the system of the embodiment of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.
In accordance with embodiments of the present disclosure, program code for executing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, these computer programs may be implemented using high level procedural and/or object oriented programming languages, and/or assembly/machine languages. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, the "C" language, or the like. The program code may execute entirely on the user computing device, partly on the user device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It will be appreciated by a person skilled in the art that various combinations or/and combinations of features recited in the various embodiments of the disclosure and/or in the claims may be made, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.
The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the disclosure, and these alternatives and modifications are intended to fall within the scope of the disclosure.
Claims (11)
1. A credit system information processing method, comprising:
acquiring business elements in a credit system information query application, wherein the business elements comprise customer information and business information of a credit application business;
obtaining N first keywords according to the service elements, wherein N is greater than or equal to 1;
matching the N first keywords with at least one of credit category labels, credit rule labels and regulation contents of each credit system in M credit systems, wherein each credit system is preset with a corresponding credit category label and/or credit rule label, and M is greater than or equal to 1;
returning the matched at least one first credit system.
2. The method of claim 1, wherein the matching the N first keywords to at least one of credit category tags, credit rule tags, and regulatory content for each credit regime of M credit regimes comprises:
matching the N first keywords with credit category labels of the M credit systems to obtain at least one second credit system matched with the credit category labels;
matching the N first keywords with credit rule labels of the at least one second credit regime to obtain at least one third credit regime having matched credit rule labels;
and matching the N first keywords with the content of the at least one third credit system to obtain the at least one first credit system.
3. The method of claim 2, wherein the matching the N first keywords to the content of the at least one third credit regime comprises:
obtaining a first feature vector according to the N first keywords;
obtaining a corresponding second feature vector according to the content of each third credit system;
and calculating the similarity between the first feature vector and a second feature vector corresponding to each third credit system.
4. The method according to claim 1 or 2, wherein the M credit regimes belong to S part of the rules and regulations document, the method further comprising, prior to matching the N first keywords to at least one of credit category tags, credit rule tags, and regulatory content of each credit regime in the M credit regimes:
classifying said S regulatory documents to obtain at least one credit category label for each regulatory document, said each regulatory document comprising at least one credit regime, S being greater than or equal to 1;
and setting a corresponding credit category label for each credit system according to at least one credit category label of each regulatory document.
5. The method of claim 4, wherein said classifying said S regulatory documents comprises:
performing word frequency calculation on part or all of the contents in each regulation document;
matching the second keywords with the word frequency larger than or equal to a preset value with the dictionary value under each credit category label;
determining at least one credit category label for each of the regulatory documents based on the matched dictionary values.
6. The method of claim 4, wherein after setting a corresponding credit category label for each credit regime, further comprising:
according to the credit category label of each credit system, performing credit rule extraction on the credit system, wherein the credit rule extraction modes between different credit category labels are the same or different;
and setting a corresponding credit rule label according to the credit rule extraction result of each credit system.
7. The method of claim 6, wherein setting the corresponding credit rule tag according to the credit rule extraction result of each credit regime comprises:
standardizing the credit rule extraction result of each credit system;
matching the credit rule extraction result after the standardization processing with at least one service element;
and setting a corresponding credit rule label according to the matched business element.
8. A credit system information processing apparatus comprising:
the business element module is used for acquiring business elements in the credit system information inquiry application, wherein the business elements comprise customer information and business information of the credit application business;
the keyword module is used for obtaining N first keywords according to the service elements, wherein N is greater than or equal to 1;
the matching module is used for matching the N first keywords with at least one of credit category labels, credit rule labels and regulation contents of each credit system in M credit systems, wherein each credit system is preset with a corresponding credit category label and/or credit rule label, and M is greater than or equal to 1;
and the target system returning module is used for returning the matched at least one first credit system.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method recited in any of claims 1-7.
10. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 7.
11. A computer program product comprising a computer program which, when executed by a processor, carries out the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211314457.0A CN115689721A (en) | 2022-10-25 | 2022-10-25 | Credit system information processing method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211314457.0A CN115689721A (en) | 2022-10-25 | 2022-10-25 | Credit system information processing method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115689721A true CN115689721A (en) | 2023-02-03 |
Family
ID=85098719
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211314457.0A Pending CN115689721A (en) | 2022-10-25 | 2022-10-25 | Credit system information processing method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115689721A (en) |
-
2022
- 2022-10-25 CN CN202211314457.0A patent/CN115689721A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11238058B2 (en) | Search and retrieval of structured information cards | |
| AU2022201654A1 (en) | System and engine for seeded clustering of news events | |
| US10262283B2 (en) | Methods and systems for generating supply chain representations | |
| US9384278B2 (en) | Methods and systems for assessing excessive accessory listings in search results | |
| US20220164397A1 (en) | Systems and methods for analyzing media feeds | |
| CN113393306A (en) | Product recommendation method and device, electronic equipment and computer readable medium | |
| CN111582314A (en) | Target user determination method and device and electronic equipment | |
| CN111651552A (en) | Structured information determination method and device and electronic equipment | |
| CN112100216A (en) | Creative keyword processing method and device | |
| CN116048463A (en) | Intelligent recommendation method and device for content of demand item based on label management | |
| CN113095078A (en) | Associated asset determination method and device and electronic equipment | |
| CN115689721A (en) | Credit system information processing method, device, equipment and medium | |
| CN113785321A (en) | Company scale estimation system | |
| CN113177116B (en) | Information display method and device, electronic equipment, storage medium and program product | |
| US11900289B1 (en) | Structuring unstructured data via optical character recognition and analysis | |
| CN116361361A (en) | Data processing method, device, equipment and storage medium | |
| CN115689301A (en) | Method, device, equipment and medium for determining business target implementation degree | |
| CN115062110A (en) | Text processing method and device, electronic equipment and medium | |
| CN117435616A (en) | Recommendation method and device for production problem records, electronic equipment and medium | |
| CN117132343A (en) | Product recommendation method, device, electronic equipment, medium and computer program product | |
| CN115034476A (en) | Project risk prediction method, device, equipment, medium and program product | |
| CN114897567A (en) | Bill information processing method, device, medium and equipment | |
| CN115438151A (en) | Method, device, equipment and medium for determining standard clauses | |
| CN116797024A (en) | Service processing method, device, electronic equipment and storage medium | |
| CN115392933A (en) | Information sharing method and device and related products |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |