CN110544035A - internal control detection method, system and computer readable storage medium - Google Patents
internal control detection method, system and computer readable storage medium Download PDFInfo
- Publication number
- CN110544035A CN110544035A CN201910815700.9A CN201910815700A CN110544035A CN 110544035 A CN110544035 A CN 110544035A CN 201910815700 A CN201910815700 A CN 201910815700A CN 110544035 A CN110544035 A CN 110544035A
- Authority
- CN
- China
- Prior art keywords
- data
- internal control
- sample data
- unstructured
- control detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Machine Translation (AREA)
Abstract
the invention provides an internal control detection method, a system and a computer readable storage medium, wherein the method comprises the following steps: collecting sample data related to internal control through a big data technology; preprocessing the sample data and acquiring effective data; establishing an internal control sample data warehouse according to the effective data; training and constructing an internal control detection model based on the sample data in the internal control sample data warehouse; and receiving data to be detected and business requirements, inputting the data to be detected and the business requirements into the internal control detection model, and automatically outputting and displaying detection result information. The invention breaks through the technical bottleneck, solves the service problem of internal control management, creates an internal control detection model based on the word segmentation technology and the unstructured data analysis technology, verifies the information correctness between service data and financial data, service and associated service and the like, gradually perfects an internal control system, improves the efficiency and effect of internal control evaluation, and promotes the improvement of enterprise operation.
Description
Technical Field
The invention relates to the technical field of big data, in particular to an internal control detection method, an internal control detection system and a computer readable storage medium.
Background
at present, internal control evaluation of some companies still takes offline management as a main part, online monitoring results are disconnected from defect rectification, and a real internal control closed-loop management effect cannot be realized, mainly because technical means are lacked, application research of new technologies is urgently needed to be developed, the problem of how to play a second line of defense of an internal control management functional department of business difficulty of internal control management is solved, it is ensured that enterprise risk management is put into effect, continuous monitoring is carried out on related work, and the method becomes a primary task to be solved in the process of developing internal control management of enterprises.
the continuous development of internet, internet of things and enterprise internal informatization technologies brings people to step into the era of big data, the big data technology can reduce the problem that non-compliance is actively avoided due to human factors, meanwhile, information data can be comprehensively and automatically judged, and the problem that non-compliance information omission is caused by random sampling is reduced. Therefore, the enterprise internal control which is an important guarantee for enterprise competitiveness should be changed and innovated fully by means of big data.
1. The big data provides powerful data support for comprehensive internal control management, and the internal control management department is used as a comprehensive economic supervision department and inherits the tradition of speaking by data. Neither comprehensive evaluation nor problem revealing in the internal control report is supported by numbers. The data objects of the full-coverage internal control management not only comprise basic data of a full service chain and structured data of transaction data, but also comprise text data of various reports, image data of original certificates and the like, monitoring screen data, Internet of things collected data and the like, and the data objects are large in scale and diverse in types and need powerful support of big data.
one of the remarkable characteristics of big data is the timeliness of structured data and unstructured data, under the big data technology, enterprises can timely collect a large amount of data information from channels such as an internal information platform, the Internet of things and the like, on the basis, timely evaluation of internal control effects becomes possible, and the aging defect of regular report type supervision can be remedied. Secondly, big data is helpful for comprehensive internal control supervision. Another significant feature of big data is the availability and analyzability of the overall data, and the defects of sampling evaluation in traditional auditing can be avoided under the big data. The internal control evaluation based on the technology is more objective and comprehensive.
2. the big data provides intelligent technical support for internal control data analysis, the internal control data analysis can dig out the characteristics and problem clues of certain group behaviors through analysis of data formed in related fields in the years, and the internal control data analysis is a necessary means for future internal control management. In the big data era, technologies such as data warehouse, online analysis, cloud computing, data mining and data visualization are fully utilized, massive data which are discretely stored in different systems are related to each other and are subjected to deep mining analysis, the enterprise management condition and the effect of related internal control measures can be evaluated, and objective internal control conclusions can be obtained, so that the intellectualization of internal control data analysis needs powerful support of the big data.
based on the above requirements, there is an urgent need to provide an internal control detection method based on big data technology.
Disclosure of Invention
In order to solve at least one technical problem, the invention provides an internal control detection method, which comprises the following steps:
Collecting sample data related to internal control through a big data technology;
preprocessing the sample data and acquiring effective data;
Establishing an internal control sample data warehouse according to the effective data;
Training and constructing an internal control detection model based on the sample data in the internal control sample data warehouse;
and receiving data to be detected and business requirements, inputting the data to be detected and the business requirements into the internal control detection model, and automatically outputting and displaying detection result information.
In this scheme, preprocessing the sample data and acquiring valid data specifically includes:
Pre-establishing a table about service types;
Classifying the structured sample data according to the service type;
and storing the structured sample data in a corresponding table according to the classification result.
in this scheme, the preprocessing the sample data and acquiring valid data specifically further include:
when the received sample data is unstructured data, defining a file format of an unstructured data carrier and generating a standard structure file;
extracting metadata of the standard structure file, establishing a corresponding file template and writing template information into a file template table of an Oracle database;
performing structure matching operation according to the generated file template, eliminating structure conflict, semantic conflict and contact conflict, extracting Data contents in each professional output file and writing the Data contents into corresponding Data XML documents;
And writing the obtained Data in the Data XML document into a result table of an Oracle database according to structure matching, semantic matching and related algorithms, wherein the Data in the result table is structured Data obtained after converting unstructured Data.
In this scheme, the preprocessing the sample data and acquiring valid data specifically further include:
dividing the sample data into shorter sentences or strings by using some symbols with a separation function;
Inputting a character string Yi, calling a self-adaptive hidden Markov model to perform word segmentation, and calculating the number of professional terms in a term set contained in a paragraph where the character string is located;
If the word sequence is larger than a certain threshold, calling a second-order hidden Markov model to perform word segmentation, dividing the word string Yi into word sequences Xi (Xi) 1, Xi (Xi) 2, … and xin, otherwise, calling a first-order hidden Markov model to perform word segmentation, and dividing the word string Yi into word sequences Xi (Xi) 1, Xi (Xi) 2, … and xin;
Traversing Xi, judging whether xij (j is 1, …, n) is in the domain dictionary, if so, searching adjacent upper and lower words of the word xij, and recording the word xij, Xi, j-1, Xi, j +1 and the string number i to an array S;
And judging whether the array S is completely traversed, if so, ending word segmentation and outputting a word segmentation result.
in this scheme, gather through big data technology and interior accuse relevant sample data, specifically include:
setting a specific interface in an enterprise information system for a conversion platform to connect and access, so as to realize automatic acquisition of unstructured sample data generated by the enterprise information system; and/or
The method comprises the steps of copying unstructured sample data into a mobile storage device in batches, copying the unstructured sample data into a conversion platform from the mobile storage device, and achieving automatic acquisition of the unstructured sample data; and/or
extracting unstructured sample data from a specified website through a web crawler, and storing the unstructured sample data into a conversion platform in a structured mode through corresponding conversion processing;
the conversion platform is used for converting unstructured sample data into structured sample data and storing the structured sample data.
In this scheme, after the big data technology is used to collect the sample data related to internal control, the method further includes:
Uniformly converting unstructured sample data resources into an XML document, and loading data in the XML document to a relational database through a mapping strategy; and/or
storing unstructured sample data with large occupied space and metadata information thereof into a non-relational database, copying and importing the metadata information with small occupied space into the relational database for management so as to maintain the relation between the sample data; and/or
And storing the unstructured sample data record as a key/value, wherein the key is used as a main key, the rest data is used as an integral value, each attribute of the key and the value forms a two-dimensional sub-table, the storage of the field value with the non-fixed length is converted into a sub-block with the fixed length for storage, and a fixed length space is allocated to each field value for storage.
in this scheme, training is built interior accuse detection model, specifically includes:
starting from the analysis of the internal control risk of the engineering money application payment service, training and constructing an engineering money application payment service evaluation model; and/or
starting from the analysis of the internal control risk of the cost expense reimbursement payment service, training and constructing a cost expense reimbursement payment service evaluation model; and/or
Starting from the analysis of marketing, external banking and internal control risks of financial data reconciliation business, training and constructing a banking and finance three-party reconciliation business internal control automatic evaluation model; and/or
Starting with the analysis of the internal control risk of the account card object consistency business, training and constructing an asset management field evaluation model.
in this scheme, the database that interior accuse detection model training used includes:
The model word segmentation library is used for storing internal control service professional words and synonyms which are combed out from the sample data description information so as to be used for word segmentation analysis;
the HBASE database is used for storing unstructured data and structured data which are depended by the internal control detection model and the data which are subjected to structured processing;
And the analysis result OLAP is used for storing the analysis result of the internal control detection model.
the second aspect of the present invention further provides an internal control detection system, which includes: the internal control detection method comprises a memory and a processor, wherein the memory comprises an internal control detection method program, and the internal control detection method program realizes the steps of the internal control detection method when being executed by the processor.
the third aspect of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a program of an internal control detection method, and when the program of the internal control detection method is executed by a processor, the steps of the internal control detection method are implemented.
the invention breaks through the technical bottleneck, solves the service problem of internal control management, and supports automatic analysis and evaluation of text data samples based on the word segmentation technology and the unstructured data analysis technology. By collecting, analyzing and preprocessing structured and unstructured business data and combining the inspection requirements and the control standards of the internal control business, an internal control detection model is created, the information correctness between the business data and financial data, the business and associated business and the like is verified, an internal control system is gradually perfected, the efficiency and the effect of internal control evaluation are improved, the improvement of enterprise operation is promoted, and the maximization of the enterprise operation target is realized.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is a flow chart illustrating an internal control detection method of the present invention;
FIG. 2 is an architecture diagram of the unstructured data to structured data conversion platform of the present invention;
FIG. 3 shows a flow chart of a segmentation algorithm of the present invention;
FIG. 4 shows the overall technical architecture diagram of big data processing of the present invention;
FIG. 5 is a flow chart of a model modeling method of the present invention;
FIG. 6 illustrates an architecture diagram of an internal control application deployment of the present invention;
FIG. 7 illustrates an architecture diagram of the model data warehouse of the present invention;
FIG. 8 shows a block diagram of an internal control detection system of the present invention.
Detailed Description
in order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
in the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
The key technology of big data comprises the following five parts: big data perception, distributed data storage, distributed data calculation, big data analysis and data visualization.
FIG. 1 shows a flow chart of an internal control detection method of the present invention.
as shown in fig. 1, a first aspect of the present invention provides an internal control detection method, including:
S102, collecting sample data related to internal control through a big data technology;
S104, preprocessing the sample data and acquiring effective data;
S106, creating an internal control sample data warehouse according to the effective data;
s108, training and constructing an internal control detection model based on sample data in the internal control sample data storage;
And S110, receiving the data to be detected and the service requirement, inputting the data to be detected and the service requirement into the internal control detection model, and automatically outputting and displaying the detection result information.
it can be understood that the data to be detected can be cost expense reimbursement payment information, engineering money application payment information, financial reconciliation information, marketing and finance reconciliation information and the like; the service requirements can be account checking service, payment applying service and the like; the detection result may be a judgment result made on the authenticity of the service, the integrity of the material, and the like.
according to the embodiment of the present invention, preprocessing the sample data and acquiring valid data specifically includes:
Pre-establishing a table about service types;
classifying the structured sample data according to the service type;
and storing the structured sample data in a corresponding table according to the classification result.
structured Data (Structured Data) is Data that has a certain structure, can be divided into fixed basic components, and can be represented by one or more two-dimensional tables. Structured data is typically stored in relational databases, with some logical structure, represented by tables or views of the relational database, and managing structured data using relational databases is currently the best approach.
Specifically, the structured data information is stored in a pre-established relational database, the data is classified according to the service, a corresponding table is designed, and then the corresponding information is stored in the corresponding table. In practical application, the tables are convenient for inquiring statistics, and are simple to operate and easy to maintain.
According to the embodiment of the present invention, preprocessing the sample data and acquiring valid data, specifically, the method further includes:
when the received sample data is unstructured data, defining a file format of an unstructured data carrier and generating a standard structure file;
extracting metadata of the standard structure file, establishing a corresponding file template and writing template information into a file template table of an Oracle database;
Performing structure matching operation according to the generated file template, eliminating structure conflict, semantic conflict and contact conflict, extracting Data contents in each professional output file and writing the Data contents into corresponding Data XML documents;
And writing the obtained Data in the Data XML document into a result table of an Oracle database according to structure matching, semantic matching and related algorithms, wherein the Data in the result table is structured Data obtained after converting unstructured Data.
it should be noted that Unstructured Data (Unstructured Data) refers to Data other than structured Data, and the Data structure is not fixed, and cannot be stored using a relational database, and can only be stored in various types of files, such as office documents, text files, office documents (including documents in formats of PDF, Rtf, caj, and the like), pictures, financial statements, images, audio, video, and the like.
Most of the unstructured data are documents, videos, pictures and the like. Such data capacity is huge and difficult to store by two-dimensional table decomposition logic. The invention selects an Oracle database management system or a cloud storage form to store unstructured data.
The Oracle data storage has the advantages of high speed, simple management and maintenance and the like for texts, documents and PDFs with relatively small storage volumes; cloud storage is the development and extension of numerous technologies such as grid, parallel and distributed computing, the full virtualization of storage is realized, and stronger storage and sharing functions are provided.
as shown in fig. 2, the platform for converting unstructured data into structured data is composed of a database, a file system, a template library, a file format definition module, a metadata extraction module, a template creation and management module, an intermediate data representation module, an XML data conversion module, and the like. The whole system is structurally divided into three levels: the system comprises an interface application layer, a program logic layer and a data storage layer.
The interface application layer provides a graphical data conversion interface for users to use, and through the application interface, the users can use the related operation of the unstructured-structured data conversion without concerning the specific implementation of the data conversion.
The program logic layer is composed of five functional modules of the system, and the work key is to realize the business logic of the unstructured-to-structured data conversion platform. The interface application layer client sends a data conversion request after acquiring an output file in the file system, and then an application program receives the request sent by the client and transmits the file to be converted to the data conversion module. After receiving the file, the module classifies the file according to the file type and determines which program is used for conversion. And then, the five functional modules start working, firstly defining a file format, finishing the generation of a standard structure file, extracting metadata of the file, establishing a corresponding file template, writing template information into a file template table of an Oracle database, creating a result table structure, then realizing the conversion from unstructured data to semi-structured data, finally finishing the conversion from semi-structured data to structured data, and writing the processed data into a result table of the Oracle database. The application program returns the conversion result to the user and prompts the user whether to perform the next data conversion, and finally the whole process of the data conversion is completed.
The data storage layer integrates Oracle database tables used in the system, such as a file template table, a file association table and a result table. The file template table and the file association table need to be created before the system runs. The data in the result table is the structured data obtained after the unstructured data is converted. After the data conversion is completed, the system writes the relevant information into the file association table.
the functions of the modules are as follows:
Oracle database: the system comprises a storage module, a conversion module and a display module, wherein the storage module is used for storing attribute information, template information and a result table generated after conversion of an unstructured output file;
a file system: for storing various unstructured output files;
template library: the file template is used for storing the file template generated in the system conversion process;
The file format definition module: the method comprises the following steps of uniformly converting unstructured files of various structure types encountered in practice into strict standard structure files, and converting the unstructured files into XML documents of uniform standard formats by utilizing the strict standard structure files;
a metadata extraction module: directly and effectively extracting metadata in an output file to establish the metadata and information such as a database field name, a field type, constraint conditions and the like corresponding to the metadata;
the template creating and managing module: constructing corresponding file templates according to metadata definitions of unstructured files, and then storing the template information into a template library and a file template table for management;
An intermediate data representation module: performing structure matching operation according to the generated file template, eliminating structure conflict, semantic conflict and contact conflict, extracting Data contents in each professional output file and writing the Data contents into corresponding Data XML documents;
XML data conversion module: and writing the obtained Data XML document into a result table of an Oracle database according to structure matching, semantic matching and related algorithms.
according to the embodiment of the present invention, preprocessing the sample data and acquiring valid data, specifically, the method further includes:
Dividing the sample data into shorter sentences or strings by using some symbols with a separation function;
Inputting a character string Yi, calling a self-adaptive hidden Markov model to perform word segmentation, and calculating the number of professional terms in a term set contained in a paragraph where the character string is located;
If the word sequence is larger than a certain threshold, calling a second-order hidden Markov model to perform word segmentation, dividing the word string Yi into word sequences Xi (Xi) 1, Xi (Xi) 2, … and xin, otherwise, calling a first-order hidden Markov model to perform word segmentation, and dividing the word string Yi into word sequences Xi (Xi) 1, Xi (Xi) 2, … and xin;
traversing Xi, judging whether xij (j is 1, …, n) is in the domain dictionary, if so, searching adjacent upper and lower words of the word xij, and recording the word xij, Xi, j-1, Xi, j +1 and the string number i to an array S;
and judging whether the array S is completely traversed, if so, ending word segmentation and outputting a word segmentation result.
First, a term set is defined, which is a representative set of terms in the art. The individual sub-disciplines in the field (e.g., power) are numbered from 1 to i, and the n most commonly used terms for each sub-discipline are counted. Then, the representative professional terms of each sub-discipline are formed into a set, the term set of the sub-discipline numbered i is Qi, and the total term set is Qi
the action principle of the self-adaptive hidden Markov model is as follows: firstly, judging the number of the professional terms contained in the document to be segmented in advance according to the term set, then comparing the number of the professional terms with a threshold value, if the number of the contained professional terms is larger than the threshold value, indicating that the paragraph contains more professional terms and should be accurately segmented, and then calling a second-order hidden Markov model to segment the word; otherwise, performing fast word segmentation, and calling a first-order hidden Markov model to perform word segmentation.
Firstly, judging which sub-subject field the document belongs to according to the input document, assuming that the input document is D, the number of the sub-subject to which the document belongs is m, and extracting a term set Q which is Qm. Assuming that the number of representative terms contained in Qm is n, traversing Qm searches for the number of representative terms contained in document D, X ═ X1, X2.., an, xn ], xi represents the number of representative terms with number i contained in document D, and then document D contains the number of representative terms: and determining a professional term number threshold value s which is num & alpha according to the document word number num and the proportionality coefficient alpha.
FIG. 3 shows a flow chart of a segmentation algorithm of the present invention.
as shown in fig. 3, the algorithm flow includes a data preprocessing stage and a word segmentation stage.
Before word segmentation calculation, the document to be segmented needs to be preprocessed, namely, the document is segmented into shorter sentences or character strings by using some symbols with separation function, so that the matching times are reduced, the word segmentation efficiency is improved, and the word segmentation difficulty is reduced. The method comprises the steps of firstly carrying out paragraph segmentation according to paragraph separators, dividing a document into a plurality of paragraphs, and then subdividing the paragraphs into shorter sentences or character strings by using separators such as punctuation marks, numbers, English and single words with poor word-building capability.
Assuming that the document to be divided is D, r paragraphs and s minimum character strings are obtained after preprocessing. The word Yi-Yi 1, Yi2, …, yin, yij indicates a single word. And calling a self-adaptive hidden Markov model to perform word segmentation, judging whether the segmented word is in a domain dictionary, if so, judging the closeness between upper and lower words adjacent to the word and whether the word needs to be re-segmented, otherwise, substituting the word into a constraint matrix to perform grammar and semantic constraint calibration, and finally outputting a word segmentation result. The specific word segmentation steps are as follows:
Step 1, inputting a character string Yi, calling a self-adaptive hidden Markov model to perform word segmentation, calculating the number of professional terms in a term set contained in a paragraph where the character string is located, if the number of the professional terms is greater than a certain threshold value, turning to step 2, and otherwise, turning to step 3;
step 2, calling a second-order hidden Markov model to perform word segmentation, segmenting the word string Yi into word sequences Xi ═ Xi1, Xi2, … and xin, and turning to step 4;
Step 3, calling a first-order hidden Markov model to perform word segmentation, segmenting the word string Yi into word sequences Xi ═ Xi1, Xi2, … and xin, and turning to step 4;
Step 4, traversing Xi, judging whether xij (j is 1, …, n) is in the domain dictionary, if so, turning to step 5, otherwise, turning to step 6;
step 5, searching adjacent upper and lower words of the word xij, recording the words xij, xi, j-1, xi, j +1 and the string number i to an array S, and turning to step 8;
step 6, substituting the words into the constraint matrix for verification, if the constraint matrix is met, switching to step 8, otherwise, recording and eliminating the word segmentation mode, and switching to step 1;
Step 7, judging whether the frequency of the combined words is greater than a threshold value, if so, inputting the sentence with the number i as a character string, and turning to the step 1, otherwise, turning to the step 6;
And 8, judging whether the array S is completely traversed, if so, ending word segmentation and outputting word segmentation results, otherwise, traversing the frequency of the whole document statistical combination words xi, j-1xij, xi, jxi, j +1 and turning to the step 7.
according to the embodiment of the invention, the acquisition of the sample data related to internal control by a big data technology specifically comprises the following steps:
setting a specific interface in an enterprise information system for a conversion platform to connect and access, so as to realize automatic acquisition of unstructured sample data generated by the enterprise information system; and/or
The method comprises the steps of copying unstructured sample data into a mobile storage device in batches, copying the unstructured sample data into a conversion platform from the mobile storage device, and achieving automatic acquisition of the unstructured sample data; and/or
extracting unstructured sample data from a specified website through a web crawler, and storing the unstructured sample data into a conversion platform in a structured mode through corresponding conversion processing;
The conversion platform is used for converting unstructured sample data into structured sample data and storing the structured sample data.
it should be noted that the unstructured data may be data generated, collected or purchased by subordinate units, and some necessary external data, such as related information from the internet. For the existing unstructured data, data acquisition can be carried out by using a system interface transmission or batch data copying mode, and for external data from the Internet, data acquisition can be carried out by using a network crawling mode.
(1) and establishing a specific system interface for transmitting data. For unstructured data generated by an enterprise information system, under the condition of low confidentiality requirement, specific interface conversion platform connection and access can be set in the information system, and automatic acquisition of the unstructured data can be conveniently realized according to requirements and according to certain limiting conditions such as frequency, content and range.
(2) and (4) batch replication. Under the condition of high requirement on confidentiality, for the consideration of data security, the data collection can be realized by copying the unstructured data into the mobile storage device in batch and then copying the unstructured data from the mobile storage device to the corresponding enterprise subsystem in the conversion platform.
(3) and (5) network crawling. For external network resource data, a web crawling technology can be adopted, unstructured data can be extracted from a specified website according to set web crawling operation in a mode of web crawlers or website open Application Programming Interfaces (APIs) and the like, and the unstructured data are stored in a conversion platform in a structured mode through corresponding conversion processing. The method can support the collection of files or attachments such as pictures, audio, video and the like, and automatically associate the attachments with the text.
According to an embodiment of the present invention, after collecting sample data related to internal control by big data technology, the method further comprises:
Uniformly converting unstructured sample data resources into an XML document, and loading data in the XML document to a relational database through a mapping strategy; and/or
Storing unstructured sample data with large occupied space and metadata information thereof into a non-relational database, copying and importing the metadata information with small occupied space into the relational database for management so as to maintain the relation between the sample data; and/or
and storing the unstructured sample data record as a key/value, wherein the key is used as a main key, the rest data is used as an integral value, each attribute of the key and the value forms a two-dimensional sub-table, the storage of the field value with the non-fixed length is converted into a sub-block with the fixed length for storage, and a fixed length space is allocated to each field value for storage.
The invention collects the determined service data (including structured and unstructured data) in the service system through the related big data technology, and performs preliminary analysis and pretreatment. For example, in fund management, data extraction includes bank statement extraction, reconciliation record extraction, balance adjustment table extraction, and the like.
FIG. 4 shows the overall technical architecture diagram of big data processing of the present invention;
As shown in fig. 4, the whole technology architecture of big data processing of the present invention is mainly divided into five layers, namely, data source, data integration, big data platform, result storage, and data application.
and the data source layer supports the integration of a plurality of data sources and the integration of structured data sources of business systems such as a financial management and control system. The method also supports the integration of semi-structured data such as logs, mails and the like, and also supports the integration of unstructured data such as office files, contracts, pictures, videos and the like. The main business data comprises an internal control system, accounting documents, engineering reimbursement payment accessories, document information and the like;
The data integration layer acquires structured data (relational database records), semi-structured data (logs, mails and the like), unstructured data (files, videos, audios, network data streams and the like) and real-time data with specific needs from an external data source through various technologies such as ETL extraction, file adapters, real-time data acquisition and the like.
and the large data platform layer is used for storing data and is responsible for storing large data, aiming at the requirements of all data types and various calculations, and is characterized by mass scale storage and quick query reading, storing various data from each service system and supporting the advanced application of the data calculation and analysis layer. And data calculation, namely reasonably distributing and optimizing application related calculation task workflow by utilizing a distributed calculation technology and combining technologies such as stream calculation, memory calculation and the like required by a specific scene, so as to realize timely and effective completion of a calculation task. And data analysis, namely providing analysis engines such as data analysis and data mining.
and storing the result, storing the analysis and mining result in a relational database and calling the application.
and the data application layer supports the front-end application functions of three models, namely fund payment, money and money checking and property card consistency.
According to the embodiment of the invention, training and constructing the internal control detection model specifically comprises the following steps:
Starting from the analysis of the internal control risk of the engineering money application payment service, training and constructing an engineering money application payment service evaluation model; and/or
starting from the analysis of the internal control risk of the cost expense reimbursement payment service, training and constructing a cost expense reimbursement payment service evaluation model; and/or
Starting from the analysis of marketing, external banking and internal control risks of financial data reconciliation business, training and constructing a banking and finance three-party reconciliation business internal control automatic evaluation model; and/or
Starting with the analysis of the internal control risk of the account card object consistency business, training and constructing an asset management field evaluation model.
Capturing cost expense reimbursement payment business activities, engineering money application payment business activities, financial and bank primary reconciliation, financial and bank secondary reconciliation and financial and bank monthly reconciliation in the aspects of fund payment and banking and financial three-party reconciliation in the field of fund management, and constructing a model; and capturing business activities of asset increase, production halt, combination, scrapping and inventory shortage in the aspect of account card object consistency in the field of asset management to construct a model.
the capital management plays an important role in the financial management, the capital safety risk is the important factor in the financial risk, and the capital safety control measures are required to ensure the capital safety without any loss. Therefore, the effective evaluation means is adopted to regularly evaluate the effectiveness of the capital safety control measures, comprehensively and objectively evaluate whether the capital safety internal control measures are implemented and whether the internal control system design is complete, and is vital to timely managing and improving and avoiding the capital safety risk.
And a fund payment service internal control automatic evaluation model and a bank and finance three-party account checking service internal control automatic evaluation model are established in the fund management internal control field, and a payment document data integrity and timeliness check model, a payment approval process compliance check model and the like are provided. The fund payment service internal control automatic evaluation model comprises an engineering money application payment service evaluation model and a cost expense reimbursement payment service evaluation model.
As shown in fig. 5, the modeling steps of the capital management payment service, the capital management business and banking and financial three-party reconciliation service and the asset management debit card object consistency based on big data are as follows:
Step 1, defining a data model: the data model definition describes how the system sets and configures the service model;
Step 2, data model storage: a physical data model of the data;
Step 3, establishing a data model: establishing a logic model of data;
Step 4, establishing an algorithm model: establishing three models by combining semantic analysis, data mining and the like;
And step 5, task execution: the method mainly comprises the following two steps: the system automatically generates tasks and manually executes the tasks;
And 6, visualization: and the fund management payment model, the fund management business and bank three-party account checking model and the asset management account card object consistency model are displayed on the foreground.
As shown in fig. 6, the business of model analysis is acquired from the internal control application service, stored in the big data platform, and input to the fund management payment model, the fund management business-banking-finance three-party account checking model and the asset management account card object consistency model through unstructured to structured processing, and the result data is stored in the model result OLAP through model data mining and analysis, and finally the foreground display is performed through the internal control business analysis model application service.
As shown in fig. 7, the database for training the internal control detection model includes:
The model word segmentation library is used for storing internal control service professional words and synonyms which are combed out from the sample data description information so as to be used for word segmentation analysis; specifically, professional words, synonyms and the like of the internal control business can be combed according to description information such as an internal control system, an accounting document and the like, and a model word segmentation library is established so as to be used for word segmentation analysis;
the HBASE database is used for storing unstructured data and structured data which are depended by the internal control detection model and the data which are subjected to structured processing;
and the analysis result OLAP is used for storing the analysis result of the internal control detection model.
FIG. 8 shows a block diagram of an internal control detection system of the present invention.
as shown in fig. 8, the second aspect of the present invention further provides an internal control detection system 8, where the internal control detection system 8 includes: a memory 81 and a processor 82, wherein the memory 81 includes an internal control detection method program, and when the internal control detection method program is executed by the processor, the following steps are implemented:
collecting sample data related to internal control through a big data technology;
preprocessing the sample data and acquiring effective data;
establishing an internal control sample data warehouse according to the effective data;
training and constructing an internal control detection model based on the sample data in the internal control sample data warehouse;
And receiving data to be detected and business requirements, inputting the data to be detected and the business requirements into the internal control detection model, and automatically outputting and displaying detection result information.
Further, preprocessing the sample data and acquiring valid data specifically includes:
Pre-establishing a table about service types;
classifying the structured sample data according to the service type;
and storing the structured sample data in a corresponding table according to the classification result.
further, preprocessing the sample data and acquiring valid data, and specifically includes:
When the received sample data is unstructured data, defining a file format of an unstructured data carrier and generating a standard structure file;
extracting metadata of the standard structure file, establishing a corresponding file template and writing template information into a file template table of an Oracle database;
Performing structure matching operation according to the generated file template, eliminating structure conflict, semantic conflict and contact conflict, extracting Data contents in each professional output file and writing the Data contents into corresponding Data XML documents;
and writing the obtained Data in the Data XML document into a result table of an Oracle database according to structure matching, semantic matching and related algorithms, wherein the Data in the result table is structured Data obtained after converting unstructured Data.
further, preprocessing the sample data and acquiring valid data, and specifically includes:
dividing the sample data into shorter sentences or strings by using some symbols with a separation function;
inputting a character string Yi, calling a self-adaptive hidden Markov model to perform word segmentation, and calculating the number of professional terms in a term set contained in a paragraph where the character string is located;
if the word sequence is larger than a certain threshold, calling a second-order hidden Markov model to perform word segmentation, dividing the word string Yi into word sequences Xi (Xi) 1, Xi (Xi) 2, … and xin, otherwise, calling a first-order hidden Markov model to perform word segmentation, and dividing the word string Yi into word sequences Xi (Xi) 1, Xi (Xi) 2, … and xin;
traversing Xi, judging whether xij (j is 1, …, n) is in the domain dictionary, if so, searching adjacent upper and lower words of the word xij, and recording the word xij, Xi, j-1, Xi, j +1 and the string number i to an array S;
and judging whether the array S is completely traversed, if so, ending word segmentation and outputting a word segmentation result.
further, the method for acquiring the sample data related to internal control by the big data technology specifically comprises the following steps:
Setting a specific interface in an enterprise information system for a conversion platform to connect and access, so as to realize automatic acquisition of unstructured sample data generated by the enterprise information system; and/or
the method comprises the steps of copying unstructured sample data into a mobile storage device in batches, copying the unstructured sample data into a conversion platform from the mobile storage device, and achieving automatic acquisition of the unstructured sample data; and/or
extracting unstructured sample data from a specified website through a web crawler, and storing the unstructured sample data into a conversion platform in a structured mode through corresponding conversion processing;
the conversion platform is used for converting unstructured sample data into structured sample data and storing the structured sample data.
further, after collecting sample data related to internal control by a big data technology, the method further comprises:
Uniformly converting unstructured sample data resources into an XML document, and loading data in the XML document to a relational database through a mapping strategy; and/or
Storing unstructured sample data with large occupied space and metadata information thereof into a non-relational database, copying and importing the metadata information with small occupied space into the relational database for management so as to maintain the relation between the sample data; and/or
And storing the unstructured sample data record as a key/value, wherein the key is used as a main key, the rest data is used as an integral value, each attribute of the key and the value forms a two-dimensional sub-table, the storage of the field value with the non-fixed length is converted into a sub-block with the fixed length for storage, and a fixed length space is allocated to each field value for storage.
Further, training and constructing an internal control detection model specifically comprises:
Starting from the analysis of the internal control risk of the engineering money application payment service, training and constructing an engineering money application payment service evaluation model; and/or
starting from the analysis of the internal control risk of the cost expense reimbursement payment service, training and constructing a cost expense reimbursement payment service evaluation model; and/or
Starting from the analysis of marketing, external banking and internal control risks of financial data reconciliation business, training and constructing a banking and finance three-party reconciliation business internal control automatic evaluation model; and/or
Starting with the analysis of the internal control risk of the account card object consistency business, training and constructing an asset management field evaluation model.
Further, the database for training the internal control detection model comprises:
The model word segmentation library is used for storing internal control service professional words and synonyms which are combed out from the sample data description information so as to be used for word segmentation analysis;
The HBASE database is used for storing unstructured data and structured data which are depended by the internal control detection model and the data which are subjected to structured processing;
and the analysis result OLAP is used for storing the analysis result of the internal control detection model.
The third aspect of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a program of an internal control detection method, and when the program of the internal control detection method is executed by a processor, the steps of the internal control detection method are implemented.
the invention breaks through the technical bottleneck, solves the service problem of internal control management, and supports automatic analysis and evaluation of text data samples based on the word segmentation technology and the unstructured data analysis technology. By collecting, analyzing and preprocessing structured and unstructured business data and combining the inspection requirements and the control standards of the internal control business, an internal control detection model is created, the information correctness between the business data and financial data, the business and associated business and the like is verified, an internal control system is gradually perfected, the efficiency and the effect of internal control evaluation are improved, the improvement of enterprise operation is promoted, and the maximization of the enterprise operation target is realized.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
in addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
the above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. an internal control detection method is characterized by comprising the following steps:
Collecting sample data related to internal control through a big data technology;
Preprocessing the sample data and acquiring effective data;
establishing an internal control sample data warehouse according to the effective data;
training and constructing an internal control detection model based on the sample data in the internal control sample data warehouse;
And receiving data to be detected and business requirements, inputting the data to be detected and the business requirements into the internal control detection model, and automatically outputting and displaying detection result information.
2. The internal control detection method according to claim 1, wherein the preprocessing is performed on the sample data, and effective data is obtained, specifically including:
Pre-establishing a table about service types;
Classifying the structured sample data according to the service type;
and storing the structured sample data in a corresponding table according to the classification result.
3. the internal control detection method according to claim 1, wherein the sample data is preprocessed to obtain valid data, and specifically the method further comprises:
when the received sample data is unstructured data, defining a file format of an unstructured data carrier and generating a standard structure file;
extracting metadata of the standard structure file, establishing a corresponding file template and writing template information into a file template table of an Oracle database;
Performing structure matching operation according to the generated file template, eliminating structure conflict, semantic conflict and contact conflict, extracting Data contents in each professional output file and writing the Data contents into corresponding Data XML documents;
and writing the obtained Data in the Data XML document into a result table of an Oracle database according to structure matching, semantic matching and related algorithms, wherein the Data in the result table is structured Data obtained after converting unstructured Data.
4. the internal control detection method according to claim 1, wherein the sample data is preprocessed to obtain valid data, and specifically the method further comprises:
Dividing the sample data into shorter sentences or strings by using some symbols with a separation function;
Inputting a character string Yi, calling a self-adaptive hidden Markov model to perform word segmentation, and calculating the number of professional terms in a term set contained in a paragraph where the character string is located;
if the word sequence is larger than a certain threshold, calling a second-order hidden Markov model to perform word segmentation, dividing the word string Yi into word sequences Xi (Xi) 1, Xi (Xi) 2, … and xin, otherwise, calling a first-order hidden Markov model to perform word segmentation, and dividing the word string Yi into word sequences Xi (Xi) 1, Xi (Xi) 2, … and xin;
traversing Xi, judging whether xij (j is 1, …, n) is in the domain dictionary, if so, searching adjacent upper and lower words of the word xij, and recording the word xij, Xi, j-1, Xi, j +1 and the string number i to an array S;
And judging whether the array S is completely traversed, if so, ending word segmentation and outputting a word segmentation result.
5. the internal control detection method according to claim 1, wherein the collecting of sample data related to internal control by a big data technology specifically comprises:
setting a specific interface in an enterprise information system for a conversion platform to connect and access, so as to realize automatic acquisition of unstructured sample data generated by the enterprise information system; and/or
the method comprises the steps of copying unstructured sample data into a mobile storage device in batches, copying the unstructured sample data into a conversion platform from the mobile storage device, and achieving automatic acquisition of the unstructured sample data; and/or
Extracting unstructured sample data from a specified website through a web crawler, and storing the unstructured sample data into a conversion platform in a structured mode through corresponding conversion processing;
The conversion platform is used for converting unstructured sample data into structured sample data and storing the structured sample data.
6. The internal control detection method according to claim 1, wherein after collecting sample data related to internal control by big data technology, the method further comprises:
Uniformly converting unstructured sample data resources into an XML document, and loading data in the XML document to a relational database through a mapping strategy; and/or
storing unstructured sample data with large occupied space and metadata information thereof into a non-relational database, copying and importing the metadata information with small occupied space into the relational database for management so as to maintain the relation between the sample data; and/or
and storing the unstructured sample data record as a key/value, wherein the key is used as a main key, the rest data is used as an integral value, each attribute of the key and the value forms a two-dimensional sub-table, the storage of the field value with the non-fixed length is converted into a sub-block with the fixed length for storage, and a fixed length space is allocated to each field value for storage.
7. the internal control detection method according to claim 1, wherein training and constructing the internal control detection model specifically comprises:
starting from the analysis of the internal control risk of the engineering money application payment service, training and constructing an engineering money application payment service evaluation model; and/or
starting from the analysis of the internal control risk of the cost expense reimbursement payment service, training and constructing a cost expense reimbursement payment service evaluation model; and/or
starting from the analysis of marketing, external banking and internal control risks of financial data reconciliation business, training and constructing a banking and finance three-party reconciliation business internal control automatic evaluation model; and/or
Starting with the analysis of the internal control risk of the account card object consistency business, training and constructing an asset management field evaluation model.
8. The internal control detection method according to claim 1, wherein the database for training the internal control detection model comprises:
The model word segmentation library is used for storing internal control service professional words and synonyms which are combed out from the sample data description information so as to be used for word segmentation analysis;
the HBASE database is used for storing unstructured data and structured data which are depended by the internal control detection model and the data which are subjected to structured processing;
and the analysis result OLAP is used for storing the analysis result of the internal control detection model.
9. an internal control detection system, comprising: a memory and a processor, the memory including an internal control detection method program, the internal control detection method program when executed by the processor implementing the steps of an internal control detection method according to any one of claims 1 to 8.
10. a computer-readable storage medium, characterized in that the computer-readable storage medium comprises a program of an internal control detection method, which when executed by a processor implements the steps of a method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910815700.9A CN110544035A (en) | 2019-08-30 | 2019-08-30 | internal control detection method, system and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910815700.9A CN110544035A (en) | 2019-08-30 | 2019-08-30 | internal control detection method, system and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110544035A true CN110544035A (en) | 2019-12-06 |
Family
ID=68711007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910815700.9A Pending CN110544035A (en) | 2019-08-30 | 2019-08-30 | internal control detection method, system and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110544035A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111126955A (en) * | 2019-12-17 | 2020-05-08 | 中国建设银行股份有限公司 | Business data analysis method, processing server and storage medium |
| CN113936183A (en) * | 2021-09-10 | 2022-01-14 | 南方电网深圳数字电网研究院有限公司 | Data prediction method and device based on model training |
| CN114238317A (en) * | 2021-12-03 | 2022-03-25 | 武汉联影医疗科技有限公司 | Data storage and synchronization method and device, computer equipment and storage medium |
| CN114612018A (en) * | 2022-05-11 | 2022-06-10 | 中国南方电网有限责任公司 | Internal control risk monitoring method and system and readable storage medium |
| CN117910884A (en) * | 2024-03-18 | 2024-04-19 | 深圳华锐分布式技术股份有限公司 | Method, device, equipment and medium for detecting quality of stock futures industry control |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537461A (en) * | 2014-12-09 | 2015-04-22 | 华迪计算机集团有限公司 | Method and device for carrying out compliance inspection on enterprise internal control systems |
| CN106157132A (en) * | 2016-06-20 | 2016-11-23 | 中国工商银行股份有限公司 | Credit risk monitoring system and method |
| CN106203944A (en) * | 2016-06-27 | 2016-12-07 | 远光软件股份有限公司 | The method and system of internal control test and appraisal defect processing whole-process management |
| CN107301048A (en) * | 2017-06-23 | 2017-10-27 | 北京中泰合信管理顾问有限公司 | Using the internal control and management system of response type sharing application framework |
| US20190171944A1 (en) * | 2017-12-06 | 2019-06-06 | Accenture Global Solutions Limited | Integrity evaluation of unstructured processes using artificial intelligence (ai) techniques |
| CN109872057A (en) * | 2019-01-31 | 2019-06-11 | 深圳顺禧管理咨询有限公司 | A kind of internal control system |
-
2019
- 2019-08-30 CN CN201910815700.9A patent/CN110544035A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537461A (en) * | 2014-12-09 | 2015-04-22 | 华迪计算机集团有限公司 | Method and device for carrying out compliance inspection on enterprise internal control systems |
| CN106157132A (en) * | 2016-06-20 | 2016-11-23 | 中国工商银行股份有限公司 | Credit risk monitoring system and method |
| CN106203944A (en) * | 2016-06-27 | 2016-12-07 | 远光软件股份有限公司 | The method and system of internal control test and appraisal defect processing whole-process management |
| CN107301048A (en) * | 2017-06-23 | 2017-10-27 | 北京中泰合信管理顾问有限公司 | Using the internal control and management system of response type sharing application framework |
| US20190171944A1 (en) * | 2017-12-06 | 2019-06-06 | Accenture Global Solutions Limited | Integrity evaluation of unstructured processes using artificial intelligence (ai) techniques |
| CN109872057A (en) * | 2019-01-31 | 2019-06-11 | 深圳顺禧管理咨询有限公司 | A kind of internal control system |
Non-Patent Citations (5)
| Title |
|---|
| 万里鹏: "非结构化到结构化数据转换的研究与实现", 《HTTPS:https://D.WANFANGDATA.COM.CN/THESIS/Y2335110》 * |
| 宫法明等: "基于自适应隐马尔可夫模型的石油领域文档分词", 《计算机科学》 * |
| 沈红雨: "高校非结构化档案数据的数据库管理技术应用与比较研究", 《浙江档案》 * |
| 王晶: "非结构化数据结构化存储中的查询语句重写技术研究", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑（月刊）》 * |
| 采招网: "基于大数据的内控业务分析模型的研究项目招标公告", 《HTTPS:https://WWW.BIDCENTER.COM.CN/NEWSCONTENT-57564977-1.HTML》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111126955A (en) * | 2019-12-17 | 2020-05-08 | 中国建设银行股份有限公司 | Business data analysis method, processing server and storage medium |
| CN113936183A (en) * | 2021-09-10 | 2022-01-14 | 南方电网深圳数字电网研究院有限公司 | Data prediction method and device based on model training |
| CN114238317A (en) * | 2021-12-03 | 2022-03-25 | 武汉联影医疗科技有限公司 | Data storage and synchronization method and device, computer equipment and storage medium |
| CN114612018A (en) * | 2022-05-11 | 2022-06-10 | 中国南方电网有限责任公司 | Internal control risk monitoring method and system and readable storage medium |
| CN117910884A (en) * | 2024-03-18 | 2024-04-19 | 深圳华锐分布式技术股份有限公司 | Method, device, equipment and medium for detecting quality of stock futures industry control |
| CN117910884B (en) * | 2024-03-18 | 2024-06-04 | 深圳华锐分布式技术股份有限公司 | Method, device, equipment and medium for detecting quality of stock futures industry control |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110544035A (en) | internal control detection method, system and computer readable storage medium | |
| CN112182246B (en) | Method, system, medium, and application for creating an enterprise representation through big data analysis | |
| US8533235B2 (en) | Infrastructure and architecture for development and execution of predictive models | |
| CN110851667B (en) | Integration analysis method and tool for large amount of data of multiple sources | |
| US10115058B2 (en) | Predictive modeling | |
| US20210366055A1 (en) | Systems and methods for generating accurate transaction data and manipulation | |
| CN111967761A (en) | Monitoring and early warning method and device based on knowledge graph and electronic equipment | |
| CN112131203A (en) | Method and system for building data warehouse | |
| CN107945092A (en) | Big data integrated management approach and system for audit field | |
| CN114880405A (en) | Data lake-based data processing method and system | |
| CN114238655A (en) | Enterprise association relation identification method, device, equipment and medium | |
| CN116244367A (en) | Visual big data analysis platform based on multi-model custom algorithm | |
| Wibowo | XBRL Open Information Model for Risk Based Tax Audit using Machine Learning | |
| CN117436768A (en) | Unified supervision index method based on data management | |
| CN117131106A (en) | Scientific and technological data mining and decision-making auxiliary system | |
| Minggao et al. | Research on the Application of LLM in Power Finance Middle Platform | |
| CN114626940A (en) | Data analysis method and device and electronic equipment | |
| Huang et al. | Digital Transformation Strategy for Financial Management of Entity Enterprises in the Information Age | |
| CN118377854B (en) | Innovative full-chain science and technology information service integration method and platform | |
| Ye et al. | Study on budget preparation and forecast model based on apriori rule algorithm | |
| CN113836313B (en) | Audit information identification method and system based on map | |
| Yanjun | Study on computer audit based on OLAP technology | |
| Yan | Construction of Smart Audit System Based on Big Data Analysis | |
| CN118864076A (en) | Closed-loop operation risk early warning data generation method, device, medium and equipment | |
| Xu | Construction of Doubt Prediction Model of Audit Big Data Based on Fuzzy Clustering Algorithm |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191206 |
|
| RJ01 | Rejection of invention patent application after publication |