CN111966716B - Data processing method and device - Google Patents

Abstract

The embodiment of the specification provides a data processing method and a device, wherein the data processing method comprises the following steps: receiving service requirements submitted by users, determining a target service category according to the service requirements, extracting target entity attributes from service data to be audited of the target service category, determining audit reference information associated with the target service category, inquiring whether audit rules matched with the audit reference information exist in a pre-constructed knowledge base, if not, creating and storing target service audit rules associated with the target entity attributes based on the audit reference information and the target entity attributes; by the method, the compliance self-checking rule associated with the target entity attribute is created and stored, and in the process of carrying out compliance self-checking on the business data to be checked in the later period, the new self-checking rule is not needed, so that the compliance checking efficiency is improved.

Description

Data processing method and device

Technical Field

The embodiment of the specification relates to the field of compliance data management, in particular to a data processing method. One or more embodiments of the present specification also relate to a data processing apparatus, a computing device, and a computer-readable storage medium.

Background

With the development of internet technology, various services have been developed on-line, and although the on-line mode is more convenient for users, more merchants or stores can choose to develop on-line services alone, develop off-line services alone, or develop both on-line and off-line services simultaneously in order to obtain a large sales market, thereby attracting more users.

However, as this phenomenon increases, sales scenarios become more complicated, and when some merchants or shops provide services to users, compliance self-checking needs to be performed to determine whether the operation range or operation mode meets the specified compliance conditions, so that with the continuous occurrence of new technologies, the conventional regulatory compliance means is difficult to cope with the rapid development of various industries. At present, the compliance of the business is mainly analyzed and judged by means of experience of supervision compliance professional manpower, so that the efficiency is low, the requirement on the experience of personnel supervision compliance industry is high, the efficiency of information acquisition lag, information authenticity and the like is low, the timeliness and effectiveness of supervision are greatly impaired, and therefore, an effective method is needed to solve the problems.

Disclosure of Invention

In view of this, the present embodiments provide a data processing method. One or more embodiments of the present specification are also directed to a data processing apparatus, a computing device, and a computer-readable storage medium, which address the technical deficiencies of the prior art.

According to a first aspect of embodiments of the present specification, there is provided a data processing method, including:

receiving service demands submitted by users, and determining target service categories according to the service demands;

extracting target entity attributes from business data to be audited of the target business category;

determining audit reference information associated with the target business category, and inquiring whether audit rules matched with the audit reference information exist in a pre-constructed knowledge base; wherein the auditing rule corresponds to the target entity attribute;

If not, creating and storing a target business auditing rule associated with the target entity attribute based on the auditing reference information and the target entity attribute.

Optionally, after determining the target service category according to the service requirement, the method further includes:

Acquiring a service table corresponding to the target service category, wherein the service table contains the service data to be checked;

Judging whether each field of the target entity attribute contained in the service table is associated with an audit rule corresponding to the target entity attribute;

If not, executing the audit rule which is inquired whether to be matched with the audit reference information exists in the pre-constructed knowledge base.

Optionally, after determining the target service category according to the service requirement, the method further includes:

Acquiring at least one knowledge graph corresponding to the target business category;

Constructing at least one business table associated with the target business category based on the at least one knowledge graph, wherein a plurality of fields of the at least one business table are respectively used for storing target entity information and target entity attribute information associated with business data to be audited of the target business category;

Judging whether each field of the target entity attribute contained in the service table is associated with an audit rule corresponding to the target entity attribute;

If not, executing the audit rule which is inquired whether to be matched with the audit reference information exists in the pre-constructed knowledge base.

Optionally, if the auditing rule corresponding to the target entity attribute does not exist in the knowledge base, executing the following operations:

creating a target business audit rule corresponding to the target entity attribute based on the audit reference information and the target entity attribute;

and establishing and storing the association relation between the target business auditing rule and the field to which the target entity attribute belongs.

Optionally, the knowledge base is constructed by:

acquiring historical auditing reference information, historical auditing rules and historical auditing business data;

determining the association relation among the history auditing reference information, the history auditing rules and the history auditing business data;

And constructing the knowledge base according to the association relation.

Optionally, the extracting the target entity attribute from the business data to be audited of the target business category includes:

word segmentation processing is carried out on the business data to be checked to obtain the target entity attribute; or alternatively, the first and second heat exchangers may be,

And extracting and identifying the target entity attribute contained in the business data to be checked through a named entity identification model and/or a preset keyword extraction rule.

Optionally, the querying whether the audit rule matching with the audit reference information exists in the pre-constructed knowledge base includes:

Reading audit entries from the knowledge base; the audit entry comprises audit reference information and audit rules;

extracting keywords from the audit reference information and the audit rule respectively;

and determining whether keywords contained in the extraction result are associated with the target entity attribute.

Optionally, the querying whether the audit rule matching with the audit reference information exists in the pre-constructed knowledge base includes:

Calculating a first association degree between the target entity attribute and the auditing reference information, and calculating a second association degree between the target entity attribute and the auditing rule; the knowledge base comprises a plurality of auditing reference information and a plurality of auditing rules;

And determining the auditing rule corresponding to the target entity attribute in the knowledge base based on the first association degree between the target entity attribute and the auditing reference information and the second association degree between the auditing rules.

Optionally, the querying whether the audit rule matching with the audit reference information exists in the pre-constructed knowledge base includes:

Inquiring whether an auditing rule corresponding to the target entity attribute under each field in the service table exists in the knowledge base;

if yes, establishing the association relation between the field of each target entity attribute and the auditing rule.

Optionally, after querying whether the audit rule matching with the audit reference information exists in the pre-constructed knowledge base, the method further includes:

If yes, establishing and storing the association relation between each target entity attribute and the auditing rule.

Optionally, the data processing method further includes:

receiving an audit request, wherein the audit request carries identification information of a target business category;

extracting target entity attributes from business data to be audited of the target business category;

inquiring a target business auditing rule associated with the target entity attribute in a pre-constructed knowledge base according to the identification information;

And auditing the business data to be audited of the target business category based on the target business auditing rule, and outputting an auditing result to respond to the auditing request.

According to a second aspect of embodiments of the present specification, there is provided a data processing apparatus comprising:

the receiving module is configured to receive service demands submitted by users and determine target service categories according to the service demands;

The extraction module is configured to extract target entity attributes from business data to be audited of the target business category;

The query module is configured to determine audit reference information associated with the target business category and query whether audit rules matched with the audit reference information exist in a pre-constructed knowledge base; wherein the auditing rule corresponds to the target entity attribute;

if the operation result of the query module is no, the creation module is operated;

the creation module is configured to create and store a target business audit rule associated with the target entity attribute based on the audit reference information and the target entity attribute.

According to a third aspect of embodiments of the present specification, there is provided a computing device comprising:

A memory and a processor;

the memory is for storing computer-executable instructions, and the processor is for executing the computer-executable instructions:

receiving service demands submitted by users, and determining target service categories according to the service demands;

extracting target entity attributes from business data to be audited of the target business category;

determining audit reference information associated with the target business category, and inquiring whether audit rules matched with the audit reference information exist in a pre-constructed knowledge base; wherein the auditing rule corresponds to the target entity attribute;

If not, creating and storing a target business auditing rule associated with the target entity attribute based on the auditing reference information and the target entity attribute.

According to a fourth aspect of embodiments of the present description, there is provided a computer-readable storage medium storing computer-executable instructions which, when executed by a processor, implement the steps of the data processing method.

According to one embodiment of the specification, through receiving service requirements submitted by a user, determining a target service category according to the service requirements, extracting target entity attributes from service data to be audited of the target service category, determining audit reference information associated with the target service category, and inquiring whether audit rules matched with the audit reference information exist in a pre-constructed knowledge base, wherein the audit rules correspond to the target entity attributes, and if not, establishing and storing target service audit rules associated with the target entity attributes based on the audit reference information and the target entity attributes;

by the method, the target business auditing rule related to the target entity attribute is established for the target entity attribute, the target business auditing rule is stored in the knowledge base, and the target business auditing rule is used for compliance self-checking, so that the efficiency of compliance auditing is improved.

Drawings

FIG. 1 is a process flow diagram of a data processing method provided in one embodiment of the present disclosure;

FIG. 2 is a process flow diagram of a data processing method according to one embodiment of the present disclosure;

FIG. 3 is a schematic diagram of a data processing apparatus according to one embodiment of the present disclosure;

FIG. 4 is a block diagram of a computing device provided in one embodiment of the present description.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present description. This description may be embodied in many other forms than described herein and similarly generalized by those skilled in the art to whom this disclosure pertains without departing from the spirit of the disclosure and, therefore, this disclosure is not limited by the specific implementations disclosed below.

The terminology used in the one or more embodiments of the specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the specification. As used in this specification, one or more embodiments and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any or all possible combinations of one or more of the associated listed items.

It should be understood that, although the terms first, second, etc. may be used in one or more embodiments of this specification to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first may also be referred to as a second, and similarly, a second may also be referred to as a first, without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "in response to a determination" depending on the context.

In the present specification, a data processing method is provided, and the present specification relates to a data processing apparatus, a computing device, and a computer-readable storage medium, which are described in detail in the following embodiments one by one.

Fig. 1 shows a process flow diagram of a data processing method according to one embodiment of the present disclosure, including steps 102 to 108.

And 102, receiving service requirements submitted by a user, and determining target service categories according to the service requirements.

When an enterprise provides services for users, compliance self-check is mostly carried out to determine whether the operation range or the operation mode of the enterprise meets the specified compliance conditions, and along with the continuous appearance of new technologies, the conventional supervision compliance means is difficult to deal with the rapid development of various industries. At present, the compliance of the business is mainly analyzed and judged by means of experience of supervision compliance professional manpower, so that the efficiency is low, the requirement on the experience of personnel supervision compliance industry is high, the efficiency of information acquisition lag, information authenticity and the like is low, the timeliness and effectiveness of supervision are greatly impaired, and therefore, an effective method is needed to solve the problems.

Based on the above, in the embodiment of the present disclosure, by receiving a service requirement submitted by a user, determining a target service category according to the service requirement, extracting a target entity attribute from service data to be audited of the target service category, determining audit reference information associated with the target service category, and querying whether there is an audit rule matching with the audit reference information in a pre-constructed knowledge base, where the audit rule corresponds to the target entity attribute, and if not, creating and storing a target service audit rule associated with the target entity attribute based on the audit reference information and the target entity attribute;

by the method, the target business auditing rule related to the target entity attribute is established for the target entity attribute, the target business auditing rule is stored in the knowledge base, and the target business auditing rule is used for compliance self-checking, so that the efficiency of compliance auditing is improved.

Specifically, the user is a party to be audited, and the party to be audited specifically refers to an enterprise, a merchant or a shop that needs to audit service compliance with a target service, where the target service in the embodiment of the present disclosure is a target service of the party to be audited, and the target service includes, but is not limited to, a fund transaction service, a data resource transaction service, a computing resource transaction service, a virtual resource transaction service, and the like; compliance refers to the fact that business activities of an enterprise, merchant or store are consistent with laws, rules and guidelines; the service compliance auditing range specifically refers to-be-inspected service data corresponding to the target service of the to-be-inspected party; the business data to be checked comprises business data of transaction businesses such as fund transaction businesses, data resource transaction businesses, computing resource transaction businesses, virtual resource transaction businesses and the like, and business categories are business categories under the target business of a party to be checked, for example, business categories corresponding to the fund transaction businesses comprise but are not limited to fund transaction businesses, borrowing businesses and the like; the business categories corresponding to the virtual resource transaction business include, but are not limited to, purchase business of virtual currency, transfer business, and the like.

The service requirement is the requirement of compliance self-checking of the service data to be checked, and under the condition that a new service is developed by a to-be-checked party, the to-be-checked service data related to the new service can be subjected to compliance self-checking in a mode of submitting the service requirement.

Because the business services provided by the to-be-audited party comprise a plurality of types, and auditing rules corresponding to each business may have differences, after receiving business requirements, a target business category can be determined according to the business requirements so as to inquire the auditing rules according to the target business category.

And 104, extracting the target entity attribute from the business data to be audited of the target business category.

Specifically, after receiving the service requirement submitted by the user, the target entity attribute can be extracted from the service data to be audited of the target service category.

In practical application, the target entity attribute is an attribute corresponding to a target entity contained in the business data to be checked.

Taking the category of the target service as a lending service as an example, the target entity is a user of the lending service, and the attribute of the target entity includes, but is not limited to, the gender, age, occupation, and the like of the user.

In the implementation, the extracting the target entity attribute from the business data to be audited of the target business category may be implemented specifically by the following manner:

word segmentation processing is carried out on the business data to be checked to obtain the target entity attribute; or alternatively, the first and second heat exchangers may be,

And extracting and identifying the target entity attribute contained in the business data to be checked through a named entity identification model and/or a preset keyword extraction rule.

Specifically, word segmentation is carried out on business data to be audited by adopting a word segmentation technology so as to obtain target entity attributes; the target entity attributes include, but are not limited to, information for characterizing specific attributes, such as attribute information for characterizing a region, attribute information for characterizing an audience, attribute information for characterizing an applicable scene, and the like.

Performing word segmentation processing according to the to-be-checked business data to obtain one or more new words, for example, the to-be-checked business data is a limiting condition on the age of borrowers, the word segmentation processing is performed on the to-be-checked business data, and the obtained word segmentation result is that: the attribute of the target entity is 'age' obtained according to the word segmentation processing result.

In addition, named entity Recognition (NAMED ENTITY Recognition, abbreviated as NER), also called "special name Recognition", refers to an entity with specific meaning in a Recognition text, mainly including a person name, a place name, a mechanism name, a proper noun, etc., is a basic tool of application fields such as information extraction, question-answering system, syntax analysis, machine translation, etc., plays an important role in the process of the natural language processing technology going to practical use, and generally, named entity Recognition can recognize named entities of three major classes (entity class, time class and digital class) and seven minor classes (person name, mechanism name, place name, time, date, currency and percentage) in the text to be processed.

Extracting and identifying the target entity attribute contained in the business data to be checked through a named entity identification model, namely inputting the business data to be checked into the named entity identification model to identify the target entity attribute, and acquiring a target entity attribute identification result output by the model.

In practical application, the model corresponding to the NER can be trained in advance, and the entity attribute or concept and the like contained in the business data to be audited can be accurately acquired by the trained model, for example, based on the example, the model corresponding to the NER can identify named entities comprising three major classes and seven minor classes. And respectively inputting each piece of information in the business data to be checked into the corresponding model of the NER, and extracting and identifying entity attributes contained in the business data to be checked to obtain related information of entity attributes or concepts contained in each piece of information in the business data to be checked.

In addition, the keyword extraction rule may include various types, such as a natural language processing technique, a graph-based ranking algorithm for Text (Text Rank algorithm), TF-IDF (Term Frequency-inverse document Frequency), etc., and the keyword extraction rule may be one or a combination of a plurality of types thereof, and may be specifically set according to actual situations, which is not limited in the embodiment of the present specification.

After extracting and identifying the target entity attribute contained in the service data to be audited, the content, the context relation and the like of each piece of information in the service data to be audited can be analyzed, and the association relation information of the corresponding information is extracted from each piece of information in the service data to be audited.

The word segmentation processing is carried out on the business data to be checked, or the word segmentation processing is carried out on the business data to be checked contained in the business data to be checked through a named entity recognition model and/or a preset keyword extraction rule, so that the accuracy of the obtained extraction and recognition results is improved.

Step 106, determining audit reference information associated with the target business category, and inquiring whether audit rules matched with the audit reference information exist in a pre-constructed knowledge base; wherein the auditing rule corresponds to the target entity attribute.

Specifically, the audit reference information, that is, the external supervision information, includes preset business audit rules and/or business environment data, where the preset business audit rules, that is, the supervision rules, include, but are not limited to, supervision treaty, policy and regulation, and the like, and the business environment data includes, but is not limited to, external management environment data, external supervision environment data, external business feedback data, and the like.

The auditing rule is a rule which is pre-established and used for carrying out compliance self-checking on the business data to be audited, and because the compliance self-checking rules corresponding to the business data to be audited of different business categories have differences, after receiving the business requirements and determining the target business category and auditing reference information related to the target business category, whether the auditing rule matched with the auditing reference information exists or not can be inquired in a pre-established knowledge base.

If the pre-constructed knowledge base does not have the auditing rules matched with the auditing reference information, creating and storing the target business auditing rules associated with the target entity attribute based on the auditing reference information and the target entity attribute.

If the pre-constructed knowledge base has the auditing rule matched with the auditing reference information, establishing and storing the association relation between the target entity attribute and the auditing rule.

In specific implementation, the historical auditing reference information, the historical auditing rules and the historical auditing service data can be obtained, the association relationship among the historical auditing reference information, the historical auditing rules and the historical auditing service data is determined, and the knowledge base is constructed according to the association relationship.

The knowledge base is built based on the historical auditing reference information and the association relation between the historical auditing rules and the historical auditing business data, the whole knowledge base can be built automatically without consuming a great deal of labor cost, the built knowledge base can cover various auditing reference information and auditing rules, and in the application stage, the high coverage rate of the auditing reference information and auditing rules is beneficial to ensuring the accuracy of auditing results.

In the implementation, the query of whether the auditing rule matched with the auditing reference information exists in the pre-constructed knowledge base can be realized by the following steps:

Reading audit entries from the knowledge base; the audit entry comprises audit reference information and audit rules;

extracting keywords from the audit reference information and the audit rule respectively;

and determining whether keywords contained in the extraction result are associated with the target entity attribute.

Specifically, the knowledge base includes audit reference information and audit rules, after receiving a service requirement and determining a target service category, audit entries can be read from the knowledge base, keywords are extracted from the audit entries, and whether the extracted keywords are associated with the target entity attribute or not is determined by comparing the extracted keywords with the target entity attribute.

If the knowledge base is associated, it can be determined that the auditing rule matched with the auditing reference information exists in the pre-built knowledge base, and if the knowledge base is not associated, it can be determined that the auditing rule matched with the auditing reference information does not exist in the pre-built knowledge base.

By the method, whether the auditing rules matched with the auditing reference information exist in the knowledge base is determined, so that the inquiring efficiency of inquiring the auditing rules matched with the auditing reference information in the knowledge base is improved.

In addition, the query of whether the audit rule matched with the audit reference information exists in the pre-constructed knowledge base can be realized by the following ways:

Calculating a first association degree between the target entity attribute and the auditing reference information, and calculating a second association degree between the target entity attribute and the auditing rule; the knowledge base comprises a plurality of auditing reference information and a plurality of auditing rules;

And determining the auditing rule corresponding to the target entity attribute in the knowledge base based on the first association degree between the target entity attribute and the auditing reference information and the second association degree between the auditing rules.

Specifically, calculating a first association degree between a target entity attribute and audit reference information and calculating a second association degree between the target entity attribute and audit rules can be implemented by using a Word vector-based document similarity algorithm (Word river' S DISTANCE, WMD), before similarity calculation, word segmentation processing can be performed on the audit reference information and the audit rules to obtain a first Word set corresponding to the audit reference information and a second Word set corresponding to the audit rules, and the first association degree and the second association degree of Word segmentation results in the first Word set and the second Word set are calculated respectively, so that the audit rules corresponding to the target entity attribute are determined in the knowledge base based on the first association degree and the second association degree.

And determining the auditing rule corresponding to the target entity attribute in the knowledge base by combining the first association degree between the target entity attribute and the auditing reference information and the second association degree between the target entity attribute and the auditing rule, so that the accuracy of the determined auditing rule corresponding to the target entity attribute is guaranteed.

And step 108, creating and storing a target business auditing rule associated with the target entity attribute based on the auditing reference information and the target entity attribute.

Specifically, if there is no audit rule matching with audit reference information of a target business category in a pre-created knowledge base, a target business audit rule associated with the target entity attribute is created and stored based on the audit reference information and the target entity attribute.

For example, the target business category is a lending business, the business data to be checked is a limiting condition for the age of the borrower, and the target business category is subjected to word segmentation processing, so that the obtained word segmentation result is as follows: the attribute of the target entity is 'age' obtained according to the word segmentation processing result; one of the audit reference information associated with the borrowing service is "the borrower's age should be greater than or equal to 18 years old", and in the case that the audit rule matching with the audit reference information is queried in the pre-constructed knowledge base, a target service audit rule needs to be created based on the audit reference information and the target entity attribute of "age", where the created target service audit rule may be "whether the borrower's age is greater than or equal to 18 years old? ".

In a specific implementation, after determining the target service category according to the service requirement, the method further includes:

Acquiring a service table corresponding to the target service category, wherein the service table contains the service data to be checked;

Judging whether each field of the target entity attribute contained in the service table is associated with an audit rule corresponding to the target entity attribute;

if not, inquiring whether an audit rule corresponding to the target entity attribute under each field in the service table exists in the knowledge base;

If the target entity attribute exists, establishing the association relation between the field to which the target entity attribute belongs and the auditing rule.

Specifically, since the service data to be audited is generally stored in the form of a service table, after receiving a service requirement and determining a target service category, the service table corresponding to the target service category can be obtained, after obtaining the service table, whether the auditing rule corresponding to each attribute information is associated with each field of each attribute information in the service table is determined, if not, whether the auditing rule matched with each attribute information and the auditing reference information exists is queried in a pre-built knowledge base.

In addition, after the target business category is determined according to the business requirement, the method further comprises the following steps:

Acquiring at least one knowledge graph corresponding to the target business category;

Constructing at least one business table associated with the target business category based on the at least one knowledge graph, wherein a plurality of fields of the at least one business table are respectively used for storing target entity information and target entity attribute information associated with business data to be audited of the target business category;

Judging whether each field of the target entity attribute contained in the service table is associated with an audit rule corresponding to the target entity attribute;

If not, executing the audit rule which is inquired whether to be matched with the audit reference information exists in the pre-constructed knowledge base.

Specifically, a Knowledge Graph (knowledgegraph) is a Knowledge base called a semantic network (semantic network), i.e., a Knowledge base with a directed Graph structure, where nodes of the Graph represent entities (entities) or concepts (concepts), and edges of the Graph represent various semantic relationships between entities/concepts. An entity may have corresponding attribute information that may be used to characterize certain attributes of the entity (e.g., attributes such as categories, storage addresses, etc. of information that the entity characterizes). The knowledge graph can be applied to various fields, such as information searching, information recommending and the like.

After receiving a service demand and determining a target service category according to the service demand, at least one knowledge graph corresponding to the target service category can be obtained, a service table is constructed based on an entity and attribute information corresponding to the entity contained in the at least one knowledge graph, and the entity and the attribute information corresponding to the entity are used as fields to construct the service table.

After the business table is constructed, determining whether the fields of each attribute information in the business table are associated with auditing rules corresponding to each attribute information, and if not, inquiring whether auditing rules matched with each attribute information and the auditing reference information exist in a pre-constructed knowledge base.

Further, if the auditing rule corresponding to the target entity attribute does not exist in the knowledge base, a target business auditing rule corresponding to the target entity attribute is created based on the auditing reference information and the target entity attribute, and an association relation between the target business auditing rule and a field to which the target entity attribute belongs is established and stored.

For example, the target business category is a lending business, the business data to be checked is a limiting condition for the age of the borrower, and the target business category is subjected to word segmentation processing, so that the obtained word segmentation result is as follows: the attribute of the target entity is 'age' obtained according to the word segmentation processing result; one of the audit reference information associated with the borrowing service is "the borrower's age should be greater than or equal to 18 years old", and in the case that the audit rule matching with the audit reference information is queried in the pre-constructed knowledge base, a target service audit rule needs to be created based on the audit reference information and the target entity attribute of "age", where the created target service audit rule may be "whether the borrower's age is greater than or equal to 18 years old? And after the establishment is completed, establishing the association relation between the target business auditing rule and the field to which the age belongs and storing the association relation.

At least one business table associated with the target business category is constructed based on at least one knowledge graph corresponding to the target business category, so that comprehensiveness and diversity of target entity attributes contained in the constructed business table are guaranteed, target business auditing rules associated with the target entity attributes are created for the target entity attributes, the target business auditing rules are stored in a knowledge base, and the target business auditing rules are used for compliance self-checking, so that compliance auditing efficiency is improved.

In addition, after the target business auditing rule associated with the target entity attribute is created based on the auditing reference information and the target entity attribute, compliance self-checking can be performed on the business data to be audited of the target business category based on the target business auditing rule associated with the target entity attribute, specifically, the compliance self-checking can be realized by the following modes:

receiving an audit request, wherein the audit request carries identification information of a target business category;

extracting target entity attributes from business data to be audited of the target business category;

inquiring a target business auditing rule associated with the target entity attribute in a pre-constructed knowledge base according to the identification information;

And auditing the business data to be audited of the target business category based on the target business auditing rule, and outputting an auditing result to respond to the auditing request.

Specifically, the auditing request can be submitted by the to-be-audited party to carry out compliance self-checking on the to-be-audited business data, and under the condition that the to-be-audited party develops a new business, the to-be-audited business data related to the new business can be subjected to compliance self-checking in a mode of submitting auditing requirements.

After receiving an auditing request submitted by an auditing party, acquiring to-be-audited business data of a target business category according to identification information of the target business category carried in the auditing request, and extracting a target entity attribute from the to-be-audited business data. In practical application, the target entity attribute is an attribute corresponding to a target entity contained in the business data to be checked.

After extracting the target entity attribute, inquiring a target business auditing rule related to the target entity attribute in a pre-constructed knowledge base according to the identification information, auditing the business data to be audited of the target business category based on the target business auditing rule, and outputting an auditing result to respond to the auditing request.

As described above, the target business category is a lending business, the business data to be checked is a "limit condition for the age of the borrower", the borrower is subjected to word segmentation, and the attribute of the target entity is "age" according to the word segmentation result; the target business audit rule related to the age, which is inquired in the knowledge base according to the identification information of the borrowing business, is that "whether the age of the borrower is greater than or equal to 18 years? And checking the age information in the business data to be checked of the lending business based on the target business checking rule, and outputting a checking result.

By the method, the compliance self-checking rule associated with the target entity attribute is created and stored, and in the process of carrying out compliance self-checking on the business data to be checked in the later period, the new self-checking rule is not needed, so that the compliance checking efficiency is improved.

According to the embodiment of the specification, through receiving service requirements submitted by a user, determining a target service category according to the service requirements, extracting target entity attributes from service data to be audited of the target service category, determining audit reference information associated with the target service category, inquiring whether audit rules matched with the audit reference information exist in a pre-constructed knowledge base, wherein the audit rules correspond to the target entity attributes, and if not, establishing and storing target service audit rules associated with the target entity attributes based on the audit reference information and the target entity attributes;

by the method, the target business auditing rule related to the target entity attribute is established for the target entity attribute, the target business auditing rule is stored in the knowledge base, and the target business auditing rule is used for compliance self-checking, so that the efficiency of compliance auditing is improved.

The application of the data processing method provided in the present specification in the lending business scenario is taken as an example, and the data processing method is further described below with reference to fig. 2. Fig. 2 is a flowchart of a processing procedure of a data processing method according to an embodiment of the present disclosure, and specific steps include steps 202 to 218.

And 202, receiving service requirements submitted by a user, and determining target service categories according to the service requirements.

Specifically, the target service category is a lending service.

And 204, extracting and identifying the target entity attribute contained in the to-be-checked lending service data through a named entity identification model and/or a preset keyword extraction rule.

And 206, determining audit reference information associated with the lending service.

And step 208, acquiring a service table corresponding to the lending service.

Specifically, the service table includes the to-be-checked lending service data.

Step 210, determining whether each field of the target entity attribute included in the service table is associated with an audit rule corresponding to the target entity attribute.

If not, go to step 212; if yes, the processing is not performed.

Step 212, calculating a first association degree between the target entity attribute and the audit reference information, and calculating a second association degree between the target entity attribute and the audit rule.

Specifically, the knowledge base comprises a plurality of auditing reference information and a plurality of auditing rules.

And step 214, inquiring whether an auditing rule corresponding to the target entity attribute under each field in the service table exists in the knowledge base based on the first association degree between the target entity attribute and the auditing reference information and the second association degree between the auditing rules.

If the knowledge base has auditing rules corresponding to the target entity attributes under each field in the business table, establishing and storing the association relation between the target business auditing rules and the field to which the target entity attributes belong;

if the knowledge base does not have the auditing rule corresponding to the target entity attribute under each field in the business table, step 216 is executed.

And step 216, creating a target business auditing rule corresponding to the target entity attribute based on the auditing reference information and the target entity attribute.

And step 218, establishing and storing the association relation between the target business auditing rule and the field to which the target entity attribute belongs.

According to the embodiment of the specification, the target business auditing rule related to the target entity attribute is created and stored in the knowledge base, and the target business auditing rule is used for compliance self-checking, so that a new self-checking rule is not needed in the process of compliance self-checking of business data to be audited in the later period, and the compliance auditing efficiency is improved.

Corresponding to the above method embodiments, the present disclosure further provides an embodiment of a data processing apparatus, and fig. 3 shows a schematic diagram of a data processing apparatus provided in one embodiment of the present disclosure. As shown in fig. 3, the apparatus includes:

A receiving module 302, configured to receive a service requirement submitted by a user, and determine a target service category according to the service requirement;

An extraction module 304 configured to extract a target entity attribute from the business data to be audited for the target business category;

A query module 306 configured to determine audit reference information associated with the target business category and query a pre-built knowledge base for the existence of audit rules matching the audit reference information; wherein the auditing rule corresponds to the target entity attribute;

if the operation result of the query module is no, the operation creation module 308 is operated;

The creation module 308 is configured to create and store a target business audit rule associated with the target entity attribute based on the audit reference information and the target entity attribute.

Optionally, the data processing apparatus further includes:

The service table acquisition module is configured to acquire a service table corresponding to the target service category, wherein the service table contains the service data to be checked;

The first judging module is configured to judge whether each field of the target entity attribute contained in the service table is associated with an auditing rule corresponding to the target entity attribute;

and if the operation result of the first judging module is negative, operating the query module.

Optionally, the data processing apparatus further includes:

A knowledge graph acquisition module configured to acquire at least one knowledge graph corresponding to the target business category;

A construction module configured to construct at least one service table associated with the target service category based on the at least one knowledge graph, wherein a plurality of fields of the at least one service table are respectively used for storing target entity information and target entity attribute information associated with service data to be audited of the target service category;

the second judging module is configured to judge whether each field of the target entity attribute contained in the service table is associated with an auditing rule corresponding to the target entity attribute;

And if the operation result of the second judging module is negative, operating the query module.

Optionally, if the operation result of the first judging module is yes, the following operations are executed:

creating a target business audit rule corresponding to the target entity attribute based on the audit reference information and the target entity attribute;

and establishing and storing the association relation between the target business auditing rule and the field to which the target entity attribute belongs.

Optionally, if the operation result of the second judging module is yes, the following operations are executed:

creating a target business audit rule corresponding to the target entity attribute based on the audit reference information and the target entity attribute;

and establishing and storing the association relation between the target business auditing rule and the field to which the target entity attribute belongs.

Optionally, the knowledge base is constructed by:

acquiring historical auditing reference information, historical auditing rules and historical auditing business data;

determining the association relation among the history auditing reference information, the history auditing rules and the history auditing business data;

And constructing the knowledge base according to the association relation.

Optionally, the extracting module 304 includes:

The word segmentation processing sub-module is configured to perform word segmentation processing on the business data to be checked to obtain the target entity attribute; or alternatively, the first and second heat exchangers may be,

And the extraction sub-module is configured to extract and identify the target entity attribute contained in the business data to be checked through a named entity identification model and/or a preset keyword extraction rule.

Optionally, the query module 306 includes:

A reading sub-module configured to read audit entries from the knowledge base; the audit entry comprises audit reference information and audit rules;

The keyword extraction sub-module is configured to extract keywords from the auditing reference information and the auditing rules respectively;

a determination submodule configured to determine whether keywords included in the extraction result are associated with the target entity attribute.

Optionally, the query module 306 includes:

The computing sub-module is configured to compute a first association degree between the target entity attribute and the auditing reference information and compute a second association degree between the target entity attribute and the auditing rule; the knowledge base comprises a plurality of auditing reference information and a plurality of auditing rules;

And the rule determining submodule is configured to determine the auditing rule corresponding to the target entity attribute in the knowledge base based on the first association degree between the target entity attribute and the auditing reference information and the second association degree between the auditing rules.

Optionally, the query module 306 includes:

the rule query sub-module is configured to query whether an audit rule corresponding to the target entity attribute under each field in the service table exists in the knowledge base;

if the operation result of the rule query sub-module is yes, operating the establishment sub-module;

The establishing submodule is configured to establish the association relation between the field of each target entity attribute and the auditing rule.

Optionally, the data processing apparatus further includes:

if the operation result of the query module 306 is yes, operating the establishment module;

The establishing module is configured to establish and store the association relation between each target entity attribute and the auditing rule.

Optionally, the data processing apparatus further includes:

The request receiving module is configured to receive an audit request, wherein the audit request carries identification information of a target business category;

The target entity attribute extraction module is configured to extract target entity attributes from business data to be audited of the target business category;

the auditing rule inquiring module is configured to inquire a target business auditing rule associated with the target entity attribute in a pre-constructed knowledge base according to the identification information;

and the auditing module is configured to audit the business data to be audited of the target business category based on the target business auditing rule and output an auditing result to respond to the auditing request.

The above is a schematic solution of a data processing apparatus of the present embodiment. It should be noted that, the technical solution of the data processing apparatus and the technical solution of the data processing method belong to the same conception, and details of the technical solution of the data processing apparatus, which are not described in detail, can be referred to the description of the technical solution of the data processing method.

Fig. 4 illustrates a block diagram of a computing device 400 provided in accordance with one embodiment of the present description. The components of the computing device 400 include, but are not limited to, a memory 410 and a processor 420. Processor 420 is coupled to memory 410 via bus 430 and database 450 is used to hold data.

Computing device 400 also includes access device 440, access device 440 enabling computing device 400 to communicate via one or more networks 460. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. The access device 440 may include one or more of any type of network interface, wired or wireless (e.g., a Network Interface Card (NIC)), such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.

In one embodiment of the present description, the above-described components of computing device 400, as well as other components not shown in FIG. 4, may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device shown in FIG. 4 is for exemplary purposes only and is not intended to limit the scope of the present description. Those skilled in the art may add or replace other components as desired.

Computing device 400 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), mobile phone (e.g., smart phone), wearable computing device (e.g., smart watch, smart glasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 400 may also be a mobile or stationary server.

Wherein the memory 410 is configured to store computer-executable instructions and the processor 420 is configured to execute the following computer-executable instructions:

receiving service demands submitted by users, and determining target service categories according to the service demands;

extracting target entity attributes from business data to be audited of the target business category;

determining audit reference information associated with the target business category, and inquiring whether audit rules matched with the audit reference information exist in a pre-constructed knowledge base; wherein the auditing rule corresponds to the target entity attribute;

If not, creating and storing a target business auditing rule associated with the target entity attribute based on the auditing reference information and the target entity attribute.

The foregoing is a schematic illustration of a computing device of this embodiment. It should be noted that, the technical solution of the computing device and the technical solution of the data processing method belong to the same concept, and details of the technical solution of the computing device, which are not described in detail, can be referred to the description of the technical solution of the data processing method.

An embodiment of the present specification also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, perform the steps of the data processing method.

The above is an exemplary version of a computer-readable storage medium of the present embodiment. It should be noted that, the technical solution of the storage medium and the technical solution of the data processing method belong to the same concept, and details of the technical solution of the storage medium which are not described in detail can be referred to the description of the technical solution of the data processing method.

The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

The computer instructions include computer program code that may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of combinations of actions, but it should be understood by those skilled in the art that the embodiments are not limited by the order of actions described, as some steps may be performed in other order or simultaneously according to the embodiments of the present disclosure. Further, those skilled in the art will appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily all required for the embodiments described in the specification.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.

The preferred embodiments of the present specification disclosed above are merely used to help clarify the present specification. Alternative embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the teaching of the embodiments. The embodiments were chosen and described in order to best explain the principles of the embodiments and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. This specification is to be limited only by the claims and the full scope and equivalents thereof.

Claims (13)

1. A data processing method, comprising:

Receiving service demands submitted by users, determining target service categories according to the service demands,

After the target business category is determined according to the business requirement, the method further comprises the following steps:

Acquiring at least one knowledge graph corresponding to the target business category;

Constructing at least one business table associated with the target business category based on the at least one knowledge graph, wherein a plurality of fields of the at least one business table are respectively used for storing target entity information and target entity attribute information associated with business data to be audited of the target business category;

Judging whether each field of the target entity attribute contained in the service table is associated with an audit rule corresponding to the target entity attribute;

If not, executing an audit rule which is matched with audit reference information in a pre-constructed knowledge base;

extracting target entity attributes from business data to be audited of the target business category;

determining audit reference information associated with the target business category, and inquiring whether audit rules matched with the audit reference information exist in a pre-constructed knowledge base, wherein the audit reference information comprises supervision rules and/or business environment data, and the audit rules correspond to the target entity attributes;

If not, creating and storing a target business auditing rule associated with the target entity attribute based on the auditing reference information and the target entity attribute.

2. The data processing method according to claim 1, further comprising, after the determining the target business category according to the business requirement:

Acquiring a service table corresponding to the target service category, wherein the service table contains the service data to be checked;

Judging whether each field of the target entity attribute contained in the service table is associated with an audit rule corresponding to the target entity attribute;

If not, executing the audit rule which is inquired whether to be matched with the audit reference information exists in the pre-constructed knowledge base.

3. The data processing method according to claim 1 or 2, wherein if no auditing rule corresponding to the target entity attribute exists in the knowledge base, the following operations are performed:

creating a target business audit rule corresponding to the target entity attribute based on the audit reference information and the target entity attribute;

and establishing and storing the association relation between the target business auditing rule and the field to which the target entity attribute belongs.

4. The data processing method of claim 1, the knowledge base being constructed by:

acquiring historical auditing reference information, historical auditing rules and historical auditing business data;

determining the association relation among the history auditing reference information, the history auditing rules and the history auditing business data;

And constructing the knowledge base according to the association relation.

5. The data processing method according to claim 1, wherein the extracting the target entity attribute from the business data to be audited of the target business category includes:

word segmentation processing is carried out on the business data to be checked to obtain the target entity attribute; or alternatively, the first and second heat exchangers may be,

And extracting and identifying the target entity attribute contained in the business data to be checked through a named entity identification model and/or a preset keyword extraction rule.

6. The data processing method according to claim 1, wherein the querying, in the pre-constructed knowledge base, whether there is an audit rule matching the audit reference information includes:

Reading audit entries from the knowledge base; the audit entry comprises audit reference information and audit rules;

extracting keywords from the audit reference information and the audit rule respectively;

and determining whether keywords contained in the extraction result are associated with the target entity attribute.

7. The data processing method according to claim 1, wherein the querying, in the pre-constructed knowledge base, whether there is an audit rule matching the audit reference information includes:

Calculating a first association degree between the target entity attribute and the auditing reference information, and calculating a second association degree between the target entity attribute and the auditing rule; the knowledge base comprises a plurality of auditing reference information and a plurality of auditing rules;

And determining the auditing rule corresponding to the target entity attribute in the knowledge base based on the first association degree between the target entity attribute and the auditing reference information and the second association degree between the auditing rules.

8. The data processing method according to claim 2, wherein the querying, in the pre-constructed knowledge base, whether there is an audit rule matching the audit reference information includes:

Inquiring whether an auditing rule corresponding to the target entity attribute under each field in the service table exists in the knowledge base;

if yes, establishing the association relation between the field of each target entity attribute and the auditing rule.

9. The data processing method according to claim 1, further comprising, after querying a pre-built knowledge base for whether there is an audit rule matching the audit reference information:

if yes, establishing the association relation between each target entity attribute and the auditing rule and storing the association relation.

10. The data processing method of claim 1, further comprising:

receiving an audit request, wherein the audit request carries identification information of a target business category;

extracting target entity attributes from business data to be audited of the target business category;

inquiring a target business auditing rule associated with the target entity attribute in a pre-constructed knowledge base according to the identification information;

And auditing the business data to be audited of the target business category based on the target business auditing rule, and outputting an auditing result to respond to the auditing request.

11. A data processing apparatus comprising:

a receiving module configured to receive a service requirement submitted by a user and determine a target service category according to the service requirement,

After the target business category is determined according to the business requirement, the method further comprises the following steps:

Acquiring at least one knowledge graph corresponding to the target business category;

Constructing at least one business table associated with the target business category based on the at least one knowledge graph, wherein a plurality of fields of the at least one business table are respectively used for storing target entity information and target entity attribute information associated with business data to be audited of the target business category;

Judging whether each field of the target entity attribute contained in the service table is associated with an audit rule corresponding to the target entity attribute;

If not, executing an audit rule which is matched with audit reference information in a pre-constructed knowledge base;

The extraction module is configured to extract target entity attributes from business data to be audited of the target business category;

The query module is configured to determine audit reference information associated with the target business category, and query whether audit rules matched with the audit reference information exist in a pre-constructed knowledge base, wherein the audit reference information comprises supervision rules and/or business environment data, and the audit rules correspond to the target entity attributes;

if the operation result of the query module is no, the creation module is operated;

the creation module is configured to create and store a target business audit rule associated with the target entity attribute based on the audit reference information and the target entity attribute.

12. A computing device, comprising:

A memory and a processor;

the memory is for storing computer-executable instructions, and the processor is for executing the computer-executable instructions:

Receiving service demands submitted by users, determining target service categories according to the service demands,

After the target business category is determined according to the business requirement, the method further comprises the following steps:

Acquiring at least one knowledge graph corresponding to the target business category;

Constructing at least one business table associated with the target business category based on the at least one knowledge graph, wherein a plurality of fields of the at least one business table are respectively used for storing target entity information and target entity attribute information associated with business data to be audited of the target business category;

Judging whether each field of the target entity attribute contained in the service table is associated with an audit rule corresponding to the target entity attribute;

If not, executing an audit rule which is matched with audit reference information in a pre-constructed knowledge base;

extracting target entity attributes from business data to be audited of the target business category;

determining audit reference information associated with the target business category, and inquiring whether audit rules matched with the audit reference information exist in a pre-constructed knowledge base, wherein the audit reference information comprises supervision rules and/or business environment data, and the audit rules correspond to the target entity attributes;

If not, creating and storing a target business auditing rule associated with the target entity attribute based on the auditing reference information and the target entity attribute.

13. A computer readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the data processing method of any one of claims 1 to 10.