CN116562785B - Auditing and welcome system - Google Patents
Auditing and welcome system Download PDFInfo
- Publication number
- CN116562785B CN116562785B CN202310267739.8A CN202310267739A CN116562785B CN 116562785 B CN116562785 B CN 116562785B CN 202310267739 A CN202310267739 A CN 202310267739A CN 116562785 B CN116562785 B CN 116562785B
- Authority
- CN
- China
- Prior art keywords
- audit
- data
- knowledge graph
- relation
- entity
- 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.)
- Active
Links
- 238000012550 audit Methods 0.000 claims abstract description 361
- 238000000034 method Methods 0.000 claims abstract description 73
- 230000008569 process Effects 0.000 claims abstract description 62
- 238000007726 management method Methods 0.000 claims abstract description 44
- 238000004458 analytical method Methods 0.000 claims abstract description 24
- 238000004140 cleaning Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000013480 data collection Methods 0.000 claims abstract description 6
- 238000013461 design Methods 0.000 claims abstract description 4
- 238000000605 extraction Methods 0.000 claims description 19
- 238000007619 statistical method Methods 0.000 claims description 15
- 238000005516 engineering process Methods 0.000 claims description 11
- 239000000463 material Substances 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 230000003068 static effect Effects 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 230000007246 mechanism Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 2
- 238000013474 audit trail Methods 0.000 claims 7
- 230000009286 beneficial effect Effects 0.000 description 12
- 238000012552 review Methods 0.000 description 7
- 238000002360 preparation method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an audit system, which is characterized by comprising a data collection module: collecting electronic data of an audit unit, and cleaning and preprocessing the collected data to obtain a first audit system; audit analysis module: acquiring data in the first audit system, performing overall analysis design, and constructing an audit data knowledge base; the welcome management module: constructing a knowledge graph of the audit management according to the entity content in the audit data knowledge base, and obtaining a second audit system after self-checking and management of the process of the audit work; and a template building module: and acquiring data in a second audit system, and automatically constructing an audit template according to the requirements of the user. The audit system meets the user requirements and improves the audit efficiency of staff.
Description
Technical Field
The invention relates to an audit supervision technology, in particular to an audit welcome system.
Background
Audit supervision is an important component of national administrative supervision. According to the auditing method and the regulations of the related policy documents, administrative institutions, national enterprises, schools, hospitals and other institutions need to receive the audit of the auditing institutions or the supervision and inspection of the administrative institutions at regular or irregular intervals.
Audit and supervision inspection of audit institutions, authorities and the like are frequently received each year by some units, the inspected projects are numerous, the related content is wide, different audit institutions have different requirements, and the units consume a large amount of personnel, time and energy of the audit institutions in order to cooperate with the audit work, so that the audit institutions are tired to deal with. In the trial-welcome work, the conditions of lack of unified collection management of data, information and data, repeated provision of related information, data, evidence-making materials and the like by multiple heads exist. And the existing audit management lacks of audit work and audit result statistical analysis, which is not beneficial to follow-up audit correction, review and other works. The follow-up tracking cannot be carried out along with the withdrawal of the main audit department in the current audit work, and the data of the field audit are incomplete, scattered and fragmented, so that the accumulation of experience results is not facilitated, and the information sharing and comprehensive utilization are difficult to realize.
Disclosure of Invention
The present invention provides audit catering to solve the above-mentioned problems in the prior art.
The audit system is characterized by comprising:
and a data collection module: collecting electronic data of an audit unit, and cleaning and preprocessing the collected data to obtain a first audit system;
audit analysis module: acquiring data in the first audit system, performing overall analysis design, and constructing an audit data knowledge base;
the welcome management module: constructing a knowledge graph of the audit management according to the entity content in the audit data knowledge base, and obtaining a second audit system after self-checking and management of the process of the audit work;
and a template building module: and acquiring data in a second audit system, and automatically constructing an audit template according to the requirements of the user.
Preferably, the cleaning and preprocessing of the collected data to obtain a first audit system is characterized by comprising:
the welcome management unit: after the audit system receives the audit notice, the system automatically creates an audit project team, and the audit data list and the working scheme are prepared as audit data by the audit project team; after the head-on data is obtained, a one-stop management workbench is established for head-on work and is used for tracking the whole course in the head-on work;
pretreatment unit: and according to the preset data cleaning standard in the audit system and different types in the audit data, classifying the audit data and performing standardized conversion to form unique standard conversion data, namely a first audit system.
Preferably, the constructing an audit data knowledge base is characterized by comprising:
the audit data in the first audit hierarchy is defined to include domain-related entities and attribute concepts and associations that exist between the entities,
preferably, the constructing an audit data knowledge base includes:
the audit data knowledge base uses a web crawler technology to crawl audit data, and the web crawler crawls the web page information in the network to a local warehouse of an audit system;
when a user sends an audit project request in an audit system, the web crawler extracts web page contents in a local warehouse;
the web crawler is divided into a grabbing submodule and a crawler submodule; the grabbing sub-module is used for grabbing content information related to audit data in a network through a search engine preset in an audit system, and the content information is grabbed to serve as wide area data; the crawler submodule is used for capturing content information defined as specific requirements in the wide area data by using a network as focusing data according to the requirements of users.
Preferably, the web crawler crawls web page information in the network to a local warehouse of an audit system, and the method is characterized by comprising the following steps:
page judging unit: in the process of grabbing the webpage information, the web crawler judges the transmission mode of the current webpage data according to the webpage type, and sends the judging result to an audit system;
rule positioning unit: acquiring the judging result, if the current page belongs to the static page, firstly placing the grabbed data, and waiting for a uniform resource locator corresponding to the current data to request for downloading the data; formulating a classification rule by a user, screening the static page data, and finally obtaining required audit data;
automatic positioning unit: if the current page belongs to the dynamic page, the dynamic loading technology is used, the dynamic page is integrally operated by a simulator preset in the audit system, and the required audit data is obtained by judging the actual loading condition.
Preferably, the construction of the knowledge graph for trial-and-error management is characterized by comprising the following steps:
the welcome self-checking unit: acquiring the audit data knowledge base, providing an audit self-checking function by an audit system according to the requirements of audit types and contents in an audit notice, and carrying out self-checking on the current audit work to form a self-checking base for on-site audit call;
a process management unit: carrying out overall process management on the welcome-to-be-examined work, wherein the overall process management comprises audit environment and mechanism, carrying out overall record in the conference process, and archiving the final data to form an archiving library;
knowledge graph construction unit: acquiring the self-checking library and the filing library, and forming a knowledge graph by extracting internal data and analyzing the relation of entities among the data; and identifying the entity in the knowledge graph, and constructing a second audit system.
Preferably, the analyzing the relationship between the entities in the data forms a knowledge graph, including:
the second audit system comprises a mode layer, a data layer and an entity relation layer of the knowledge graph, and the entity relation layer is added and updated according to the structure of the mode layer;
identifying the current audit project through an audit system, obtaining audit structural features after identification, matching the audit structural features with corresponding structural features in a knowledge graph, and finally extracting entities with common features with audit data in the knowledge graph to obtain a relationship extraction model;
and carrying out regular description on structural features with similar information, and making audit rules on the described content according to industry rules and correlations.
Preferably, the identifying the current audit item includes:
feature extraction unit: the audit system acquires a current audit project, extracts common structural feature data similar to the data in the audit project and the knowledge graph, formulates set rules for the extracted data in a set mode, covers text information in the feature data with the formulated rules, and carries out deep analysis on the text information;
audit identification unit: and forming a service dictionary by the deep analysis result, identifying different types of audit projects, assisting a work flow by referring to the service dictionary in the audit process, classifying the service by using the service dictionary in the audit process, and formulating an identification strategy.
Preferably, the relation extraction model includes:
acquiring an identification result of an audit system on a current audit item, putting the identification result into a knowledge graph, and extracting entities of two similar texts corresponding to the audit item in the knowledge graph;
judging the relation between the entities, extracting the relation between the entities by using a deep learning mode, calculating the matching degree and the matching accuracy of the entity relation extracted by the relation and the audit item, and constructing a relation extraction model by calculating data;
and defining the contents of different audit item types in the relation extraction model, formulating type labels and relation labels, distinguishing different types of audit items by using different labels in the type labels, and searching data contents similar to the current audit items according to the relation labels.
Preferably, the automatic audit template construction method is characterized by comprising the following steps:
template configuration unit: configuring an audit facing template according to the audit notice, and configuring a corresponding preset template according to different services and audit; referencing the trial-welcome templates and the content in the preset templates to form a complete trial-welcome scheme, and allowing multiplexing from the historical trial-welcome projects in the template configuration process;
approval management unit: and configuring different audit flows and various examination and approval modes according to different audit services, implementing a dynamic assignment mode and a fixed assignment mode for the examination and approval flows, and setting approval and approval conditions for the examination and approval flows.
Preferably, the audit system further includes:
a trial-welcoming suspicion module: collecting the questions focused in the process of catering to the examination, forming a suspicious point list according to submitted evidence materials, performing the same type of reference on the examination questions, and assisting the corresponding units to perform self-checking in the working process;
and the trial-welcoming guide module: guiding document templates of various audit schemes provided by an audit system, forming a guiding list, and providing reference experience and a method for audit personnel;
and a statistical analysis module: and providing a statistical analysis interface of each performance index in the audit system, displaying the statistical analysis interface in a plurality of image forms, and carrying out visual analysis on the mode and the interrelation of the statistical analysis page.
Compared with the prior art, the invention has the following advantages:
the invention provides an audit and welcome examination system, a set of scheme templates for welcome examination are provided, and the welcome examination scheme is automatically generated according to the content, the whole flow and the record of the examination and examination result corresponding to the history; custom setting of template elements is also supported. An automatic head-on examination mechanism is constructed, the on-line automatic operation of all business processes such as self-examination before examination, head-on examination preparation, head-on examination process and the like is realized, improving the working efficiency and quality of the welcome examination
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a module of an audit system in an embodiment of the invention;
FIG. 2 is a flow chart for constructing an audit system knowledge graph in an embodiment of the invention;
fig. 3 is a block diagram of an audit system for conducting a guide and statistical analysis of points of interest in an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The embodiment of the invention provides an audit system, which is characterized by comprising the following components:
and a data collection module: collecting electronic data of an audit unit, and cleaning and preprocessing the collected data to obtain a first audit system;
audit analysis module: acquiring data in the first audit system, performing overall analysis design, and constructing an audit data knowledge base;
the welcome management module: constructing a knowledge graph of the audit management according to the entity content in the audit data knowledge base, and obtaining a second audit system after self-checking and management of the process of the audit work;
and a template building module: and acquiring data in a second audit system, and automatically constructing an audit template according to the requirements of the user.
The working principle of the technical scheme is as follows: in the scheme adopted by the embodiment, in an audit system, data of audit units are collected, the collected data are cleaned and preprocessed to construct an audit model, the audit model is subjected to data audit analysis to obtain a first audit system, audit problems are found by searching clues in the first audit system, and an audit report is generated. Extracting useful audit information from the audit report, managing the audit information according to the useful audit information in the audit report, constructing an audit data knowledge base, reasoning audit contents in the audit data knowledge base, and mining implicit data through logic rules and an uncertainty reasoning algorithm. And constructing a knowledge graph of the processed audit data, completing the audit facing process through the knowledge graph, and obtaining a second audit system according to self-checking and management of the audit facing process. Extracting content in a second audit system, and automatically constructing an audit template for the user to use according to the requirement of the user
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the on-line automatic operation of full business processes such as self-checking before the trial, trial-and-error trial preparation, and the like is realized through an automatic trial-and-error mechanism, and the working efficiency and quality of the trial-and-error trial and error are improved.
In another embodiment, the cleaning and preprocessing the collected data to obtain a first audit system is characterized by comprising:
the welcome management unit: after the audit system receives the audit notice, the system automatically creates an audit project team, and the audit data list and the working scheme are prepared as audit data by the audit project team; after the head-on data is obtained, a one-stop management workbench is established for head-on work and is used for tracking the whole course in the head-on work;
pretreatment unit: and according to the preset data cleaning standard in the audit system and different types in the audit data, classifying the audit data and performing standardized conversion to form unique standard conversion data, namely a first audit system.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is that after the audit system receives the audit notice, the audit project needs to be established first, an audit work group is established, responsibility people are definitely provided for preparing the audit data list, the audit work and the development of self-checking work are carried out, an audit work table is established for the audit work, one-stop management of the audit work is realized, and the one-stop management of the audit work comprises audit notice, audit work scheme, work task allocation, evidence obtaining management, suspense point record, investigation opinion reply, whole process list of audit data, whole process record of audit report and the like, and the whole process trace of the audit work is ensured. Because the types of the censoring data are different, the censoring data are required to be classified and converted into standard data, and after the standard data are converted into the standard data, the unique standardized conversion data, namely the first censoring system, is obtained.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the real-time supervision of the trial-welcome data is completed through the management of the trial-welcome project and the management of the court trial workbench in the audit system, and the standardized conversion of the audit data is completed through the classification of the audit data so as to find out the problems in the audit and correct the problems in time.
In another embodiment, the building an audit data repository includes:
the audit data knowledge base uses a web crawler technology to crawl audit data, and the web crawler crawls the web page information in the network to a local warehouse of an audit system;
when a user sends an audit project request in an audit system, the web crawler extracts web page contents in a local warehouse;
the web crawler is divided into a grabbing submodule and a crawler submodule; the grabbing sub-module is used for grabbing content information related to audit data in a network through a search engine preset in an audit system, and the content information is grabbed to serve as wide area data; the crawler submodule is used for capturing content information defined as specific requirements in the wide area data by using a network as focusing data according to the requirements of users.
The working principle of the technical scheme is as follows: in the scheme adopted by the embodiment, a large amount of data is required to be prepared as preparation of an audit work in the audit process, a web crawler crawls related data information in a network to establish an audit data knowledge base, and when a user sends an audit request in an audit system, the web crawler analyzes data in a bank system in the network and completes examination and supervision of the data in the bank through extraction of a plurality of credit clients. Web crawlers are also divided into two major categories, crawling of audit data by using search engines, and crawler technology for specific department needs in banks.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the user can accurately position the data required in the auditing process and the auditing flow requirement through the web crawler technology, so that the integrity, timeliness and reliability of the auditing process are further ensured.
In another embodiment, the web crawler crawls web page information in the network to a local warehouse of an audit system, and the method is characterized by comprising:
page judging unit: in the process of grabbing the webpage information, the web crawler judges the transmission mode of the current webpage data according to the webpage type, and sends the judging result to an audit system;
rule positioning unit: acquiring the judging result, if the current page belongs to the static page, firstly placing the grabbed data, and waiting for a uniform resource locator corresponding to the current data to request for downloading the data; formulating a classification rule by a user, screening the static page data, and finally obtaining required audit data;
automatic positioning unit: if the current page belongs to the dynamic page, the dynamic loading technology is used, the dynamic page is integrally operated by a simulator preset in the audit system, and the required audit data is obtained by judging the actual loading condition.
The working principle of the technical scheme is as follows: according to the scheme adopted by the embodiment, because development of various audit related data knowledge is different in the Internet, different website pages and data transmission modes are different, and therefore, according to different data expression modes, a web crawler needs to analyze different grabbing modes according to different pages in the process of acquiring data. For static pages, all data are stored in HTML, so that the whole HTML page needs to be downloaded by using URL, namely a uniform resource locator, and then classified according to the content in the page, and different data are captured by a web crawler according to the classification rules and the requirements of users by formulating the classification rules. For the dynamic page, a dynamic loading technology is mainly used, namely technologies such as Javascript page rendering or Ajax delay loading are used, the overall operation of the dynamic page is realized by establishing a simulator in an audit system, the loading condition of the page is judged, and finally required audit data is obtained.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, different judgments made by the audit system according to different conditions are reflected by the data acquisition modes based on the dynamic page and the static page, and the efficiency of the audit work process is improved.
In another embodiment, the building a knowledge graph for censoring management is characterized by comprising:
the welcome self-checking unit: acquiring the audit data knowledge base, providing an audit self-checking function by an audit system according to the requirements of audit types and contents in an audit notice, and carrying out self-checking on the current audit work to form a self-checking base for on-site audit call;
a process management unit: carrying out overall process management on the welcome-to-be-examined work, wherein the overall process management comprises audit environment and mechanism, carrying out overall record in the conference process, and archiving the final data to form an archiving library;
knowledge graph construction unit: acquiring the self-checking library and the filing library, and forming a knowledge graph by extracting internal data and analyzing the relation of entities among the data; and identifying the entity in the knowledge graph, and constructing a second audit system.
The working principle of the technical scheme is as follows: the proposal adopted by the embodiment is that in the process of conducting the audit by the unit, records such as audit institutions, types, contents, main auditors, audit personnel, working environments, mechanisms and the like are included, conference agenda data, audit problem talking objects and contents, solicitation comments, audit reports and problems focused in the audit process are realized, and all the processes from receiving the audit notice, working task allocation, proposal programming, internal self-checking, audit process recording to final data archiving are structured and standardized and are flowered. For each question, a list of potential points may be formed and archived by submitting evidence material, supplementing evidence material, soliciting comments to submit evidence material, etc. Because the auditing flow needs to relate to the relevant knowledge of the properties of the work units, a knowledge graph needs to be constructed, data in the relevant fields needed by the current auditing needs to be collected, after the data collection is completed, the relationship between the entities and the attributes in the data is analyzed, and an entity model is constructed according to the analysis content for a user to acquire a corresponding auditing scheme according to the auditing notification.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the head-on efficiency is improved by constructing the head-on self-checking unit and managing the head-on process; by constructing the knowledge graph, the arrangement of the audit data is clearer, the data collection is facilitated, and a corresponding audit scheme can be formed directly according to the audit notice.
In another embodiment, the analyzing the relationship of the entities between the data forms a knowledge graph, which is characterized by comprising:
the second audit system comprises a mode layer, a data layer and an entity relation layer of the knowledge graph, and the entity relation layer is added and updated according to the structure of the mode layer;
identifying the current audit project through an audit system, obtaining audit structural features after identification, matching the audit structural features with corresponding structural features in a knowledge graph, and finally extracting entities with common features with audit data in the knowledge graph to obtain a relationship extraction model;
and carrying out regular description on structural features with similar information, and making audit rules on the described content according to industry rules and correlations.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is that the knowledge graph semantically processes the structural network and is composed of nodes representing entities and connecting lines representing the relationship among the entities based on the structure of the directed graph. The knowledge graph is composed of a mode layer, a data layer and an entity relation layer, wherein the mode layer is used for constructing a conceptual layer of the knowledge graph, the data layer is used for storing text data required for constructing the knowledge graph, the entity relation layer is used for establishing the relation among various data in the knowledge graph, and the addition and integration of the data are finally realized by utilizing the content of each layer in the knowledge graph. After the knowledge graph is constructed, when an audit project is prepared, matching can be carried out in the knowledge graph according to requirements in the process of catering to the audit, working contents related to audit data are obtained according to the matched data, rules among the data in the knowledge graph are matched through multiple times of structural features, and audit rules are formulated through the rules.
Calculating the matching degree of the audit structural features and the knowledge graph by using a collaborative filtering method, and predicting the entity according to the commonality structural features, wherein the formula is as follows:
wherein i and i ' respectively represent a target entity and an entity with a common characteristic, sim (i, i ') represents the similarity between the two entities, i ' users with the highest similarity between the entity selected by the current user and the other entity can obtain a user set s at the moment i ,r′ ui And finally, calculating a weighted average value by using the scores of the user set on the target entity as similarity scores of the two entities, and finally obtaining a score predicted value, namely the matching degree is r.
The beneficial effects of the technical scheme are as follows: the scheme provided by the embodiment is beneficial to clearer integration and use of data, and accelerates audit and audit personnel to formulate more detailed schemes and strategies.
In another embodiment, the identifying the current audit item includes:
feature extraction unit: the audit system acquires a current audit project, extracts common structural feature data similar to the data in the audit project and the knowledge graph, formulates set rules for the extracted data in a set mode, covers text information in the feature data with the formulated rules, and carries out deep analysis on the text information;
audit identification unit: and forming a service dictionary by the deep analysis result, identifying different types of audit projects, assisting a work flow by referring to the service dictionary in the audit process, classifying the service by using the service dictionary in the audit process, and formulating an identification strategy.
The working principle of the technical scheme is as follows: in the scheme adopted by the embodiment, in an audit project, most data have specific structural features, all rule entities with common features and corresponding to the common features in the data are analyzed and extracted for identification and extraction, relevant information of the structural features in the data is analyzed, corresponding rule information is found, a certain element in a knowledge graph is described in a collection mode, a collection rule of the data is obtained, the obtained data text is covered according to the collection rule, and deep analysis is carried out on the data text, for example, in banking business, a user needs to transact various different businesses, and finally a business dictionary is formed according to the extraction of the different businesses, and in the audit process, the application of the audit project flow is completed by referring to the business dictionary. In the process of formulating the aggregation rule, different nouns appear, and auxiliary discrimination is needed by means of a service dictionary, so that similar services can be classified, an identification strategy is set, and a final entity name list is arranged.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the audit items are identified, so that audit strategies which need to be provided in the audit process can be better known, and the audit flow is completed.
In another embodiment, the relationship extraction model is characterized by comprising:
acquiring an identification result of an audit system on a current audit item, putting the identification result into a knowledge graph, and extracting entities of two similar texts corresponding to the audit item in the knowledge graph;
judging the relation between the entities, extracting the relation between the entities by using a deep learning mode, calculating the matching degree and the matching accuracy of the entity relation extracted by the relation and the audit item, and constructing a relation extraction model by calculating data;
and defining the contents of different audit item types in the relation extraction model, formulating type labels and relation labels, distinguishing different types of audit items by using different labels in the type labels, and searching data contents similar to the current audit items according to the relation labels.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is that, aiming at the recognition result of the audit and windward system on the audit item, the relationship between the entities is judged by extracting two entities with similar texts in the current audit item. And extracting the relation among the entities by using a deep learning mode. Calculating the matching degree of the entity relation extracted by the relation and the audit item, respectively selecting a plurality of training data and a plurality of verification data, calculating the accuracy rate, and constructing a relation extraction model to extract the audit item when the accuracy rate reaches a set threshold value.
Calculating the weight value of each feature in the recognition result of the audit system, and then carrying out weighted summation, wherein the larger the weight value is, the more accurate the recognition result is, and the formula is as follows:
wherein w is n tan(Q n K n +M n ) Representing the matching degree of entity relation and audit item, when the matching degree is larger, representing the importance is larger, Q n K is a weight parameter in an entity n Extracting model state for current relation, M n E, for auditing the business quantity of the project i And n is the number of entities, and a represents the weight value finally calculated.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the weight value is calculated, so that the auditing process can be more accurately carried out.
In another embodiment, the automatically constructing an audit template includes:
template configuration unit: configuring an audit facing template according to the audit notice, and configuring a corresponding preset template according to different services and audit; referencing the trial-welcome templates and the content in the preset templates to form a complete trial-welcome scheme, and allowing multiplexing from the historical trial-welcome projects in the template configuration process;
approval management unit: and configuring different audit flows and various examination and approval modes according to different audit services, implementing a dynamic assignment mode and a fixed assignment mode for the examination and approval flows, and setting approval and approval conditions for the examination and approval flows.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is that a template configuration unit and an approval management unit are respectively used for configuration of templates, template content reference and management of approval process configuration, the template configuration unit is used for providing form contents of different services in audit and approval work and templates preset by the scheme, presetting different template contents for projects according to different examination classifications, providing different template elements, realizing display of various different component contents, finally referring to the template contents in the audit projects and multiplexing the template contents from history projects; in the approval management unit, different approval processes are configured for approval nodes of different services, multiple approval modes such as one-time approval, a meeting, or an approval are configured, and approval conditions are set by dynamically assigning approval persons or assigning fixed approval persons, wherein the modes comprise a leading of each department, a specific post or a specific employee, and only the process meeting the conditions is required to be allowed to enter the approval processes.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the scheme template of the head-on review is configured, the head-on review scheme is automatically generated according to the content, the whole flow and the record of the review result of the review corresponding to the history, and the head-on review efficiency is improved.
In another embodiment, the method further comprises:
a trial-welcoming suspicion module: collecting the questions focused on in the process of catering to the examination, forming a suspicious point list according to submitted evidence materials, performing the same type of reference on the examination questions, and assisting the corresponding units to perform self-checking in the working process;
and the trial-welcoming guide module: guiding document templates of various audit schemes provided by an audit system, forming a guiding list, and providing experience and a method for reference for audit personnel;
and a statistical analysis module: and providing a statistical analysis interface of each performance index in the audit system, displaying the statistical analysis interface in a plurality of image forms, and carrying out visual analysis on the mode and the interrelation of the statistical analysis page.
The working principle of the technical scheme is as follows: the proposal adopted by the embodiment is that for each question, a list of suspicious points can be formed by submitting evidence materials, supplementing evidence materials, soliciting opinion to submit evidence materials and the like. The system provides various document templates and guidelines for various types of review work schemes, self-checking reports, solicited opinion reply manuscripts, guidelines for similar problem evidence materials and the like, and forms a guideline list. The audit system provides a statistical analysis interface of each performance index, including a plurality of analysis models such as a histogram, a line graph, a pie chart and the like, and can carry out visual analysis on the modes and interrelationships of the analysis models.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the method can be used as a reference for the similar problems of the audit response in the future, and can assist a unit to develop self-checking and self-checking so as to prevent the problems in the future. By providing borrowable experience, scheme and method for the reviewer, the resource reuse rate is improved, the time for preparing similar problem data is reduced, and the working efficiency of the staff is improved.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (8)
1. The audit system is characterized by comprising:
and a data collection module: collecting electronic data of an audit unit, and cleaning and preprocessing the collected data to obtain a first audit system;
audit analysis module: acquiring data in the first audit system, performing overall analysis design, and constructing an audit data knowledge base;
the welcome management module: constructing a knowledge graph of the audit management according to the entity content in the audit data knowledge base, and obtaining a second audit system after self-checking and management of the process of the audit work;
and a template building module: acquiring data in a second audit system, and automatically constructing an audit template according to the requirements of a user;
the construction of the knowledge graph for trial-oriented management comprises the following steps:
the welcome self-checking unit: acquiring the audit data knowledge base, providing an audit self-checking function by an audit system according to the requirements of audit types and contents in an audit notice, and carrying out self-checking on the current audit work to form a self-checking base for on-site audit call;
a process management unit: carrying out overall process management on the welcome-to-be-examined work, wherein the overall process management comprises audit environment and mechanism, carrying out overall record in the conference process, and archiving the final data to form an archiving library;
knowledge graph construction unit: acquiring the self-checking library and the filing library, and forming a knowledge graph by extracting internal data and analyzing the relation of entities among the data; identifying the entity in the knowledge graph, and constructing a second audit system;
the relationship of the entities between the analysis data forms a knowledge graph, which comprises the following steps:
the second audit system comprises a mode layer, a data layer and an entity relation layer of the knowledge graph, and the entity relation layer is added and updated according to the structure of the mode layer;
identifying the current audit project through an audit system, obtaining audit structural features after identification, matching the audit structural features with corresponding structural features in a knowledge graph, and finally extracting entities with common features with audit data in the knowledge graph to obtain a relationship extraction model;
regular description is carried out on structural features with similar information, and audit rules are formulated on the described content according to industry rules and correlations;
calculating the matching degree of the audit structural features and the knowledge graph by using a collaborative filtering method, and predicting the entity according to the commonality structural features, wherein the formula is as follows:
wherein i, i ′ Representing the target entity and the entity having a common characteristic therewith, respectively, sim (i, i ′ ) Representing the similarity between two entities, i with the highest similarity between the entity selected by the current user and the other entity ‘ Individual users, at which time a set s of users is available i ,r u ′ i And finally, calculating a weighted average value by using the scores of the user set on the target entity as similarity scores of the two entities, and finally obtaining a score predicted value, namely the matching degree is r.
2. The audit system according to claim 1 wherein the cleaning and preprocessing of the collected data results in a first audit system comprising:
the welcome management unit: after the audit system receives the audit notice, the system automatically creates an audit project team, and the audit data list and the working scheme are prepared as audit data by the audit project team; after the head-on data is obtained, a one-stop management workbench is established for head-on work and is used for tracking the whole course in the head-on work;
pretreatment unit: and according to the preset data cleaning standard in the audit system and different types in the audit data, classifying the audit data and performing standardized conversion to form unique standard conversion data, namely a first audit system.
3. The audit trail system according to claim 1, wherein the constructing an audit data knowledge base comprises:
the audit data knowledge base uses a web crawler technology to crawl audit data, and the web crawler crawls the web page information in the network to a local warehouse of an audit system;
when a user sends an audit project request in an audit system, the web crawler extracts web page contents in a local warehouse;
the web crawler is divided into a grabbing submodule and a crawler submodule; the grabbing sub-module is used for grabbing content information related to audit data in a network through a search engine preset in an audit system, and the content information is grabbed to serve as wide area data; the crawler submodule is used for capturing content information defined as specific requirements in the wide area data by using a network as focusing data according to the requirements of users.
4. An audit trail system according to claim 3 wherein the web crawlers crawl web page information from the network into a local repository of the audit trail system, comprising:
page judging unit: in the process of grabbing the webpage information, the web crawler judges the transmission mode of the current webpage data according to the webpage type, and sends the judging result to an audit system;
rule positioning unit: acquiring the judging result, if the current page belongs to the static page, firstly placing the grabbed data, and waiting for a uniform resource locator corresponding to the current data to request for downloading the data; formulating a classification rule by a user, screening the static page data, and finally obtaining required audit data;
automatic positioning unit: if the current page belongs to the dynamic page, the dynamic loading technology is used, the dynamic page is integrally operated by a simulator preset in the audit system, and the required audit data is obtained by judging the actual loading condition.
5. The audit trail system according to claim 1, wherein the identifying the current audit item includes:
feature extraction unit: the audit system acquires a current audit project, extracts common structural feature data similar to the data in the audit project and the knowledge graph, formulates set rules for the extracted data in a set mode, covers text information in the feature data with the formulated rules, and carries out deep analysis on the text information;
audit identification unit: and forming a service dictionary by the deep analysis result, identifying different types of audit projects, assisting a work flow by referring to the service dictionary in the audit process, classifying the service by using the service dictionary in the audit process, and formulating an identification strategy.
6. The audit trail system according to claim 1 wherein the relationship extraction model comprises:
acquiring an identification result of an audit system on a current audit item, putting the identification result into a knowledge graph, and extracting entities of two similar texts corresponding to the audit item in the knowledge graph;
judging the relation between the entities, extracting the relation between the entities by using a deep learning mode, calculating the matching degree and the matching accuracy of the entity relation extracted by the relation and the audit item, and constructing a relation extraction model by calculating data;
and defining the contents of different audit item types in the relation extraction model, formulating type labels and relation labels, distinguishing different types of audit items by using different labels in the type labels, and searching data contents similar to the current audit items according to the relation labels.
7. The audit trail system according to claim 1, wherein the automatically constructing an audit template includes:
template configuration unit: configuring an audit facing template according to the audit notice, and configuring a corresponding preset template according to different services and audit; referencing the trial-welcome templates and the content in the preset templates to form a complete trial-welcome scheme, and allowing multiplexing from the historical trial-welcome projects in the template configuration process;
approval management unit: and configuring different audit flows and various examination and approval modes according to different audit services, implementing a dynamic assignment mode and a fixed assignment mode for the examination and approval flows, and setting approval and approval conditions for the examination and approval flows.
8. The audit trail system according to claim 1 further comprising:
a trial-welcoming suspicion module: collecting the questions focused in the process of catering to the examination, forming a suspicious point list according to submitted evidence materials, performing the same type of reference on the examination questions, and assisting the corresponding units to perform self-checking in the working process;
and the trial-welcoming guide module: guiding document templates of various audit schemes provided by an audit system, forming a guiding list, and providing experience and a method for reference for audit personnel;
and a statistical analysis module: and providing a statistical analysis interface of each performance index in the audit system, displaying the statistical analysis interface in a plurality of image forms, and carrying out visual analysis on the mode and the interrelation of the statistical analysis interface.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310267739.8A CN116562785B (en) | 2023-03-17 | 2023-03-17 | Auditing and welcome system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310267739.8A CN116562785B (en) | 2023-03-17 | 2023-03-17 | Auditing and welcome system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116562785A CN116562785A (en) | 2023-08-08 |
CN116562785B true CN116562785B (en) | 2023-12-15 |
Family
ID=87495438
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310267739.8A Active CN116562785B (en) | 2023-03-17 | 2023-03-17 | Auditing and welcome system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116562785B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110334212A (en) * | 2019-07-01 | 2019-10-15 | 南京审计大学 | A kind of territoriality audit knowledge mapping construction method based on machine learning |
CN111813960A (en) * | 2020-07-29 | 2020-10-23 | 深圳供电局有限公司 | Data security audit model device and method based on knowledge graph and terminal equipment |
CN113535818A (en) * | 2021-07-15 | 2021-10-22 | 福建亿榕信息技术有限公司 | Method and equipment for constructing audit comprehensive knowledge base |
CN113657854A (en) * | 2021-08-04 | 2021-11-16 | 之江实验室 | Man-machine cooperation intelligent audit analysis method for incomplete data |
CN114117066A (en) * | 2021-11-12 | 2022-03-01 | 中国银行股份有限公司 | Recommendation method and device for audit retrieval data folder |
CN114372118A (en) * | 2021-12-29 | 2022-04-19 | 国网天津市电力公司 | Audit knowledge recommendation system and method based on recursive algorithm |
CN114385820A (en) * | 2020-10-19 | 2022-04-22 | 国网冀北电力有限公司 | Enterprise-level audit knowledge map construction method |
CN115203429A (en) * | 2022-06-27 | 2022-10-18 | 南京审计大学 | Automatic knowledge graph expansion method for constructing audit field ontology framework |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7953688B2 (en) * | 2007-05-08 | 2011-05-31 | Sharon Sadeh | Method and system for facilitating a compliance audit using a rule set |
US11574123B2 (en) * | 2020-03-25 | 2023-02-07 | Adobe Inc. | Content analysis utilizing general knowledge base |
EP4364031A1 (en) * | 2021-06-30 | 2024-05-08 | PWC Product Sales LLC | Ai-augmented auditing platform including techniques for automated assessment of vouching evidence |
-
2023
- 2023-03-17 CN CN202310267739.8A patent/CN116562785B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110334212A (en) * | 2019-07-01 | 2019-10-15 | 南京审计大学 | A kind of territoriality audit knowledge mapping construction method based on machine learning |
CN111813960A (en) * | 2020-07-29 | 2020-10-23 | 深圳供电局有限公司 | Data security audit model device and method based on knowledge graph and terminal equipment |
CN114385820A (en) * | 2020-10-19 | 2022-04-22 | 国网冀北电力有限公司 | Enterprise-level audit knowledge map construction method |
CN113535818A (en) * | 2021-07-15 | 2021-10-22 | 福建亿榕信息技术有限公司 | Method and equipment for constructing audit comprehensive knowledge base |
CN113657854A (en) * | 2021-08-04 | 2021-11-16 | 之江实验室 | Man-machine cooperation intelligent audit analysis method for incomplete data |
CN114117066A (en) * | 2021-11-12 | 2022-03-01 | 中国银行股份有限公司 | Recommendation method and device for audit retrieval data folder |
CN114372118A (en) * | 2021-12-29 | 2022-04-19 | 国网天津市电力公司 | Audit knowledge recommendation system and method based on recursive algorithm |
CN115203429A (en) * | 2022-06-27 | 2022-10-18 | 南京审计大学 | Automatic knowledge graph expansion method for constructing audit field ontology framework |
Non-Patent Citations (2)
Title |
---|
基于知识图谱的医保审计方法分析;崔婧;李真;;财会通讯(01);全文 * |
审计知识图谱的构建与研究――基于Neo4j的图谱技术;王瑞萍;刘峰;杨媛琦;邢春玉;;中国注册会计师(09);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN116562785A (en) | 2023-08-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sun et al. | Deep Learning and the Future of Auditing: How an Evolving Technology Could Transform Analysis and Improve Judgment. | |
US20090089126A1 (en) | Method and system for an automated corporate governance rating system | |
US20020107712A1 (en) | Methodology for creating and maintaining a scheme for categorizing electronic communications | |
CN115293131B (en) | Data matching method, device, equipment and storage medium | |
CN112632405B (en) | Recommendation method, recommendation device, recommendation equipment and storage medium | |
CN110580291B (en) | Intelligent searching method based on ERP customer service knowledge graph and computer equipment | |
Kewsuwun et al. | A sentiment analysis model of agritech startup on Facebook comments using naive Bayes classifier. | |
CN111680073A (en) | Financial service platform policy information recommendation method based on user data | |
CN116384889A (en) | Intelligent analysis method for information big data based on natural language processing technology | |
CN113901308A (en) | Knowledge graph-based enterprise recommendation method and recommendation device and electronic equipment | |
Zhang | Application of data mining technology in digital library. | |
CN115907568A (en) | Illegal financial activity monitoring method and system based on smoking index | |
CN114462556A (en) | Enterprise association industry chain classification method, training method, device, equipment and medium | |
Chen et al. | The best answers? think twice: online detection of commercial campaigns in the CQA forums | |
US9165053B2 (en) | Multi-source contextual information item grouping for document analysis | |
CN117520522B (en) | Intelligent dialogue method and device based on combination of RPA and AI and electronic equipment | |
CN114119322A (en) | Method, device, server and computer storage medium for policy full-flow service | |
Zhang et al. | Usage frequency and application variety of research methods in library and information science: Continuous investigation from 1991 to 2021 | |
CN116452212B (en) | Intelligent customer service commodity knowledge base information management method and system | |
Dai et al. | MinEDec: A decision support model that combines text mining with competitive intelligence | |
CN116562785B (en) | Auditing and welcome system | |
Gajanayake et al. | Candidate selection for the interview using github profile and user analysis for the position of software engineer | |
Sangeetha et al. | Modelling of E-governance framework for mining knowledge from massive grievance redressal data | |
Grimes | The Word on Text Mining | |
CN110674269A (en) | Cable information management and control method and system |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |