CN110532301B - Audit method, system and readable storage medium - Google Patents
Audit method, system and readable storage medium Download PDFInfo
- Publication number
- CN110532301B CN110532301B CN201910815693.2A CN201910815693A CN110532301B CN 110532301 B CN110532301 B CN 110532301B CN 201910815693 A CN201910815693 A CN 201910815693A CN 110532301 B CN110532301 B CN 110532301B
- Authority
- CN
- China
- Prior art keywords
- audit
- data
- preset
- numerical value
- audit data
- 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
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
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured 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
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Fuzzy Systems (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides an auditing method, system and readable storage medium, wherein the method comprises the following steps: obtaining audit data; analyzing the audit data by using a preset audit model to determine an audit result; the audit result includes at least one of: an audit target point and an audit error point; the audit model is used for analyzing the audit data and determining an audit target point in the audit data; and performing error detection on the audit data to obtain an audit error point. Audit data is directly audited through an audit model constructed in advance, so that manual calculation is avoided, and the working efficiency and accuracy are improved.
Description
Technical Field
The present application relates to the field of data processing technology, and in particular, to an auditing method, system, and readable storage medium.
Background
In recent years, with the rapid development of computer technology and informatization construction, the informatization breadth and depth of economic management activities are also in progress, and as the audit of economic activity supervision, evaluation and identification, the traditional manual audit can not adapt to the audit requirement under informatization conditions, and the manual audit can possibly cause errors and has lower efficiency. The informatization of the audit objects and the development of the audit themselves all require that the audit operation mode must be advanced with time and corresponding adjustment is made.
Therefore, the method conforms to the development trend of informatization, updates the audit supervision concept, and creates a more efficient and accurate audit method, which is a new subject faced by the current informatization continuous online audit.
Disclosure of Invention
To solve at least one of the above technical problems, the present application proposes an auditing method, system and readable storage medium.
To achieve the above object, a first aspect of the present application proposes an auditing method, the method comprising: obtaining audit data;
analyzing the audit data by using a preset audit model to determine an audit result; the audit result includes at least one of: an audit target point and an audit error point;
the audit model is used for analyzing the audit data and determining an audit target point in the audit data; and performing error detection on the audit data to obtain an audit error point.
Specifically, the obtaining audit data includes at least one of:
transmitting a data acquisition instruction to at least one database, and receiving audit data transmitted by the at least one database;
sending an access instruction to at least one database, and after receiving an agreement message sent by the at least one database, accessing the at least one database by using a WebService, http service method to obtain the audit data;
sending a data acquisition instruction to a central database, and receiving audit data sent by the central database; the central database is used for periodically acquiring the audit data from the at least one database;
and sending an access instruction to the central database, and after receiving the approval message sent by the central database, accessing the central database by using a WebService, http service method to obtain the audit data.
Specifically, before the audit data is analyzed by using the preset audit model, the method further includes: preprocessing the audit data according to a preset rule;
the preprocessing of the audit data according to the preset rules comprises the following steps:
analyzing the audit data by using a semantic analysis method, and determining the data types included in the audit data and the numerical values corresponding to the data types;
judging whether the data type belongs to a preset required data type or not, and extracting the data type and the corresponding numerical value when the data type is determined to belong to the preset required data type;
judging whether the numerical value accords with a preset numerical value type or not, and if the numerical value accords with the preset numerical value type, reserving the numerical value; and if the numerical value does not accord with the preset numerical value type, performing type conversion on the numerical value so that the numerical value is correspondingly stored according to the preset numerical value type.
Specifically, the method further comprises: generating the audit model; the generating the audit model includes:
acquiring a preset neural network structure; the neural network structure comprises at least one input node and at least two output nodes;
acquiring sample audit data and a training label corresponding to the sample audit data; the training tag includes: sample audit target points and sample audit error points;
and training the neural network structure by using the sample audit data and the corresponding training label to obtain a trained neural network structure serving as the audit model.
Specifically, the data type of the audit data includes: financial domain business data and cross-business domain data;
the financial domain business data comprises at least one of the following: business data such as daily charge reimbursement, travel charge reimbursement, engineering payment, electric charge payment, salary payment and the like;
the cross-service domain data comprises at least one of the following data: engineering project, engineering contract, material contract, engineering budget, material input and output bill, project settlement report, marketing financial account checking and electric charge collection;
the at least one input node comprises: a first input node, a second input node, and a third input node;
the training of the neural network structure by using the sample audit data and the corresponding training label thereof comprises the following steps:
inputting sample financial domain business data and sample cross-business domain data into a first input node;
inputting the sample financial domain business data into a second input node;
inputting the sample cross-service domain data into a third input node;
and training the neural network structure according to the data respectively received by the first input node, the second input node and the third input node and the corresponding training labels.
Specifically, after the audit data is preprocessed according to the preset rule, the method further includes:
determining a numerical value N of the target audit data according to the following formula;
wherein R represents the overall value, BV represents the risk coefficient, TM represents the tolerable error reporting, E represents the expected error reporting, R represents the expansion coefficient, and v represents the data importance;
selecting N target audit data from the preprocessed audit data;
correspondingly, the analyzing the audit data by using a preset audit model comprises the following steps:
and analyzing the N target audit data by using a preset audit model.
The second aspect of the present application also proposes an auditing system, the auditing system comprising: the system comprises a memory and a processor, wherein the memory comprises an auditing method program which is executed by the processor to realize the following steps:
obtaining audit data;
analyzing the audit data by using a preset audit model to determine an audit result; the audit result includes at least one of: an audit target point and an audit error point;
the audit model is used for analyzing the audit data and determining an audit target point in the audit data; and performing error detection on the audit data to obtain an audit error point.
Specifically, the obtaining audit data includes at least one of:
transmitting a data acquisition instruction to at least one database, and receiving audit data transmitted by the at least one database;
sending an access instruction to at least one database, and after receiving an agreement message sent by the at least one database, accessing the at least one database by using a WebService, http service method to obtain the audit data;
sending a data acquisition instruction to a central database, and receiving audit data sent by the central database; the central database is used for periodically acquiring the audit data from the at least one database;
and sending an access instruction to the central database, and after receiving the approval message sent by the central database, accessing the central database by using a WebService, http service method to obtain the audit data.
Specifically, before the audit data is analyzed by using the preset audit model, the method further includes: preprocessing the audit data according to a preset rule;
the preprocessing of the audit data according to the preset rules comprises the following steps:
analyzing the audit data by using a semantic analysis method, and determining the data types included in the audit data and the numerical values corresponding to the data types;
judging whether the data type belongs to a preset required data type or not, and extracting the data type and the corresponding numerical value when the data type is determined to belong to the preset required data type;
judging whether the numerical value accords with a preset numerical value type or not, and if the numerical value accords with the preset numerical value type, reserving the numerical value; and if the numerical value does not accord with the preset numerical value type, performing type conversion on the numerical value so that the numerical value is correspondingly stored according to the preset numerical value type.
The third aspect of the present application also proposes a computer-readable storage medium, in which an auditing method program is included, which, when executed by a processor, implements the steps of an auditing method as described above.
The embodiment of the application provides an auditing method, an auditing system and a storage medium, which are used for acquiring auditing data; analyzing the audit data by using a preset audit model to determine an audit result; the audit result includes at least one of: an audit target point and an audit error point; the audit model is used for analyzing the audit data and determining an audit target point in the audit data; and performing error detection on the audit data to obtain an audit error point. In the scheme, audit data is directly audited through the pre-constructed audit model, so that manual calculation is avoided, and the working efficiency and accuracy are improved.
Additional aspects and advantages of the application 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 application.
Drawings
FIG. 1 is a schematic flow chart of an auditing method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an auditing apparatus according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an audit system according to an embodiment of the present application.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited to the specific embodiments disclosed below.
FIG. 1 is a schematic flow chart of an auditing method according to an embodiment of the present application; as shown in fig. 1, the method can be applied to loading intelligent electronic devices such as servers, computers and the like of an auditing system; the method comprises the following steps:
and 101, obtaining audit data.
Here, the audit data includes: financial domain business data and cross-business domain data.
Wherein the financial domain business data comprises at least one of: business data such as daily charge reimbursement, travel charge reimbursement, engineering payment, electric charge payment, salary payment and the like;
the cross-service domain data comprises at least one of the following data: engineering project, engineering contract, material contract, engineering budget, material entry and exit list, project settlement report, marketing financial account checking and electric charge collection.
Specifically, the obtaining audit data includes at least one of:
transmitting a data acquisition instruction to at least one database, and receiving audit data transmitted by the at least one database;
sending an access instruction to at least one database, and after receiving an agreement message sent by the at least one database, accessing the at least one database by using a WebService, http service method to obtain the audit data;
sending a data acquisition instruction to a central database, and receiving audit data sent by the central database; the central database is used for periodically acquiring the audit data from the at least one database;
and sending an access instruction to the central database, and after receiving the approval message sent by the central database, accessing the central database by using a WebService, http service method to obtain the audit data.
102, analyzing the audit data by using a preset audit model to determine an audit result; the audit result includes at least one of: an audit target point and an audit error point.
Here, the audit model is used for analyzing the audit data and determining an audit target point in the audit data; and performing error detection on the audit data to obtain an audit error point.
In order to ensure the integrity, consistency, normalization and other aspects of the audit data, the data needs to be unified before being processed.
Specifically, before the audit data is analyzed by using the preset audit model, the method further includes: preprocessing the audit data according to a preset rule;
the preprocessing of the audit data according to the preset rules comprises the following steps:
analyzing the audit data by using a semantic analysis method, and determining the data types included in the audit data and the numerical values corresponding to the data types;
judging whether the data type belongs to a preset required data type or not, and extracting the data type and the corresponding numerical value when the data type is determined to belong to the preset required data type;
judging whether the numerical value accords with a preset numerical value type or not, and if the numerical value accords with the preset numerical value type, reserving the numerical value; and if the numerical value does not accord with the preset numerical value type, performing type conversion on the numerical value so that the numerical value is correspondingly stored according to the preset numerical value type.
Here, the preset value type may be preset and stored by a developer.
The numerical types may include: intelger (Integer), long (Long Integer), single (Single precision floating point type), double (Double precision floating point type), and Currency (Currency type); in order to facilitate data processing, the numerical types of all data can be unified in advance through preprocessing, so that calculation is facilitated, and auditing efficiency is improved.
Specifically, the method further comprises: generating the audit model; the auditing model is established following the auditing business targets, and has the value of achieving the auditing work targets of identifying risks, revealing risks and preventing and controlling risks. And large data analysis is realized under model calculation, an audit group is helped to determine audit key points and doubtful points, and finally an audit target is realized. Specifically, the generating the audit model includes:
acquiring a preset neural network structure; the neural network structure comprises at least one input node and at least two output nodes;
acquiring sample audit data and a training label corresponding to the sample audit data; the training tag includes: sample audit target points and sample audit error points;
and training the neural network structure by using the sample audit data and the corresponding training label to obtain a trained neural network structure serving as the audit model.
And the sample audit data and the corresponding training label are obtained by a developer according to the historical audit data and the audit result. And considering the sample audit data and the corresponding training label as a group of sample audit data pairs.
The number of the sample audit data and the corresponding training labels is at least one, namely the number of the sample audit data pairs is at least one. Dividing at least one sample audit data pair into a training set and a detection set; training the neural network structure through the sample audit data pair in the training set, and obtaining the audit model through the detection set.
Before the audit model is generated, the audit service requirements are subjected to carding and analysis, and the contents of the audit supervision field, the monitored indexes, the management requirements and the like are definitely determined, so that basis is provided for model design, test and other works, and the required audit data and audit targets (the audit targets can be used as training labels) are specifically determined.
Specifically, the data types of the audit data include the following two main types: financial domain business data and cross-business domain data;
the at least one input node comprises: a first input node, a second input node, and a third input node;
the training of the neural network structure by using the sample audit data and the corresponding training label thereof comprises the following steps:
inputting sample financial domain business data and sample cross-business domain data into a first input node;
inputting the sample financial domain business data into a second input node;
inputting the sample cross-service domain data into a third input node;
and training the neural network structure according to the data respectively received by the first input node, the second input node and the third input node and the corresponding training labels.
Here, the above-mentioned high generalization, ambiguity, relevance of each item of audit data is considered, i.e. training from the respective point of view and from the point of view of mutual relevance. Therefore, the existing data change rule and data relation mode can be mined, so that an audit trail can be found, and verification is further carried out to obtain relevant audit evidences.
Specifically, after determining the audit result, the method further includes:
after the audit error point is determined, providing a corresponding error solution based on the audit error point; and sending the error solution to the user terminal.
Here, the developer can set and store various audit error points and corresponding solutions in the server in advance according to experience, and when the audit error points are determined, the corresponding error solutions are directly provided for the user, so that the user can quickly solve the problems, and the efficiency is improved.
In this embodiment, to improve processing efficiency, partial data processing is selected. Specifically, after preprocessing the audit data according to a preset rule, the method further includes:
determining a numerical value N of the target audit data according to the following formula;
wherein R represents the overall value, BV represents the risk coefficient, TM represents the tolerable error reporting, E represents the expected error reporting, R represents the expansion coefficient, and v represents the data importance;
selecting N target audit data from the preprocessed audit data;
correspondingly, the analyzing the audit data by using a preset audit model comprises the following steps:
and analyzing the N target audit data by using a preset audit model.
Wherein BV, TM, E, r is preset and stored; TM, E, and BV may be different for different types of audit data; and carrying out accumulated calculation and determination on the total value according to the audit data. The value of v can be any value between 0.5 and 1.5, and the specific value is determined according to the type of audit data, namely, different values can be taken for business data such as daily expense reimbursement, travel expense reimbursement, engineering payment, electric charge payment, salary payment, engineering project, engineering contract, material contract, engineering general budget, material input-output-input bill, project settlement report, marketing financial account, electric charge is required to be received. The more important the audit data, the higher the specific value of v, the more values of the required target audit data, and the higher the accuracy. v can be determined by the user specifically according to his own needs.
Fig. 2 is a schematic structural diagram of an auditing apparatus according to an embodiment of the present application; as shown in fig. 2, the auditing apparatus may include: a first processing module and a second processing module.
The first processing module is used for acquiring audit data;
the second processing module is used for analyzing the audit data by using a preset audit model to determine an audit result; the audit result includes at least one of: an audit target point and an audit error point; here, the audit model is used for analyzing the audit data and determining an audit target point in the audit data; and performing error detection on the audit data to obtain an audit error point.
It should be noted that, when the auditing device performs auditing, the auditing device and the auditing method shown in fig. 1 belong to a unified concept, so that no further description is given.
Fig. 3 is a schematic structural diagram of an audit system according to an embodiment of the present application. As shown in fig. 3, the second aspect of the present application further proposes an auditing system 3, the auditing system 3 comprising: the device comprises a memory 31 and a processor 32, wherein the memory 31 comprises an auditing method program which realizes the following steps when being executed by the processor 32:
obtaining audit data;
analyzing the audit data by using a preset audit model to determine an audit result; the audit result includes at least one of: an audit target point and an audit error point;
the audit model is used for analyzing the audit data and determining an audit target point in the audit data; and performing error detection on the audit data to obtain an audit error point.
It should be noted that the system of the present application may be operated in terminal devices such as PC, mobile phone, PAD, etc.
It should be noted that the processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processing (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Further, audit data is obtained, including at least one of:
transmitting a data acquisition instruction to at least one database, and receiving audit data transmitted by the at least one database;
sending an access instruction to at least one database, and after receiving an agreement message sent by the at least one database, accessing the at least one database by using a WebService, http service method to obtain the audit data;
sending a data acquisition instruction to a central database, and receiving audit data sent by the central database; the central database is used for periodically acquiring the audit data from the at least one database;
and sending an access instruction to the central database, and after receiving the approval message sent by the central database, accessing the central database by using a WebService, http service method to obtain the audit data.
Further, before analyzing the audit data by using a preset audit model, the method further includes: preprocessing the audit data according to a preset rule;
the preprocessing of the audit data according to the preset rules comprises the following steps:
analyzing the audit data by using a semantic analysis method, and determining the data types included in the audit data and the numerical values corresponding to the data types;
judging whether the data type belongs to a preset required data type or not, and extracting the data type and the corresponding numerical value when the data type is determined to belong to the preset required data type;
judging whether the numerical value accords with a preset numerical value type or not, and if the numerical value accords with the preset numerical value type, reserving the numerical value; and if the numerical value does not accord with the preset numerical value type, performing type conversion on the numerical value so that the numerical value is correspondingly stored according to the preset numerical value type.
Further, the method further comprises: generating the audit model; the generating the audit model includes:
acquiring a preset neural network structure; the neural network structure comprises at least one input node and at least two output nodes;
acquiring sample audit data and a training label corresponding to the sample audit data; the training tag includes: sample audit target points and sample audit error points;
and training the neural network structure by using the sample audit data and the corresponding training label to obtain a trained neural network structure serving as the audit model.
Further, the data type of the audit data includes: financial domain business data and cross-business domain data;
the financial domain business data comprises at least one of the following: business data such as daily charge reimbursement, travel charge reimbursement, engineering payment, electric charge payment, salary payment and the like;
the cross-service domain data comprises at least one of the following data: engineering project, engineering contract, material contract, engineering budget, material input and output bill, project settlement report, marketing financial account checking and electric charge collection;
the at least one input node comprises: a first input node, a second input node, and a third input node;
the training of the neural network structure by using the sample audit data and the corresponding training label thereof comprises the following steps:
inputting sample financial domain business data and sample cross-business domain data into a first input node;
inputting the sample financial domain business data into a second input node;
inputting the sample cross-service domain data into a third input node;
and training the neural network structure according to the data respectively received by the first input node, the second input node and the third input node and the corresponding training labels.
Further, after determining the audit result, the method further includes:
after the audit error point is determined, providing a corresponding error solution based on the audit error point; and sending the error solution to the user terminal.
Further, after the pre-processing the audit data according to the preset rule, the method further includes:
determining a numerical value N of the target audit data according to the following formula;
wherein R represents the overall value, BV represents the risk coefficient, TM represents the tolerable error reporting, E represents the expected error reporting, R represents the expansion coefficient, and v represents the data importance;
selecting N target audit data from the preprocessed audit data;
correspondingly, the analyzing the audit data by using a preset audit model comprises the following steps:
and analyzing the N target audit data by using a preset audit model.
The third aspect of the present application also proposes a computer-readable storage medium, in which an auditing method program is included, which, when executed by a processor, implements the steps of an auditing method as described above.
In the several embodiments provided by 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 only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present application may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present application may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (5)
1. An auditing method, the method comprising:
obtaining audit data;
analyzing the audit data by using a preset audit model to determine an audit result; the audit result includes at least one of: an audit target point and an audit error point; the audit model is used for analyzing the audit data and determining an audit target point in the audit data; performing error detection on the audit data to obtain an audit error point;
before the audit data is analyzed by using the preset audit model, the method further comprises the following steps: preprocessing the audit data according to a preset rule;
the preprocessing of the audit data according to the preset rules comprises the following steps:
analyzing the audit data by using a semantic analysis method, and determining the data types included in the audit data and the numerical values corresponding to the data types;
judging whether the data type belongs to a preset required data type or not, and extracting the data type and the corresponding numerical value when the data type is determined to belong to the preset required data type;
judging whether the numerical value accords with a preset numerical value type or not, and if the numerical value accords with the preset numerical value type, reserving the numerical value; if the numerical value is determined to be not in accordance with the preset numerical value type, performing type conversion on the numerical value so that the numerical value is correspondingly stored according to the preset numerical value type;
the method further comprises the steps of: generating the audit model; the generating the audit model includes:
acquiring a preset neural network structure; the neural network structure comprises at least one input node and at least two output nodes;
acquiring sample audit data and a training label corresponding to the sample audit data; the training tag includes: sample audit target points and sample audit error points;
training the neural network structure by using the sample audit data and the corresponding training label to obtain a trained neural network structure serving as the audit model;
after the audit data is preprocessed according to the preset rule, the method further comprises:
determining a numerical value N of the target audit data according to the following formula;
；
wherein R represents the overall value, BV represents the risk coefficient, TM represents the tolerable error reporting, E represents the expected error reporting, R represents the expansion coefficient, and v represents the data importance;
selecting N target audit data from the preprocessed audit data;
correspondingly, the analyzing the audit data by using a preset audit model comprises the following steps:
and analyzing the N target audit data by using a preset audit model.
2. An auditing method according to claim 1, in which the obtaining audit data includes at least one of:
transmitting a data acquisition instruction to at least one database, and receiving audit data transmitted by the at least one database;
sending an access instruction to at least one database, and after receiving an agreement message sent by the at least one database, accessing the at least one database by using a WebService, http service method to obtain the audit data;
sending a data acquisition instruction to a central database, and receiving audit data sent by the central database; the central database is used for periodically acquiring the audit data from the at least one database;
and sending an access instruction to the central database, and after receiving the approval message sent by the central database, accessing the central database by using a WebService, http service method to obtain the audit data.
3. An auditing method according to claim 1, characterised in that the data type of the audit data comprises: financial domain business data and cross-business domain data;
the financial domain business data comprises at least one of the following: business data such as daily charge reimbursement, travel charge reimbursement, engineering payment, electric charge payment, salary payment and the like;
the cross-service domain data comprises at least one of the following data: engineering project, engineering contract, material contract, engineering budget, material input and output bill, project settlement report, marketing financial account checking and electric charge collection;
the at least one input node comprises: a first input node, a second input node, and a third input node;
the training of the neural network structure by using the sample audit data and the corresponding training label thereof comprises the following steps:
inputting sample financial domain business data and sample cross-business domain data into a first input node;
inputting the sample financial domain business data into a second input node;
inputting the sample cross-service domain data into a third input node;
and training the neural network structure according to the data respectively received by the first input node, the second input node and the third input node and the corresponding training labels.
4. An auditing system, the auditing system comprising: the system comprises a memory and a processor, wherein the memory comprises an auditing method program which is executed by the processor to realize the following steps:
obtaining audit data;
analyzing the audit data by using a preset audit model to determine an audit result; the audit result includes at least one of: an audit target point and an audit error point; the audit model is used for analyzing the audit data and determining an audit target point in the audit data; performing error detection on the audit data to obtain an audit error point;
before the audit data is analyzed by using the preset audit model, the method further comprises the following steps: preprocessing the audit data according to a preset rule;
the preprocessing of the audit data according to the preset rules comprises the following steps:
analyzing the audit data by using a semantic analysis method, and determining the data types included in the audit data and the numerical values corresponding to the data types;
judging whether the data type belongs to a preset required data type or not, and extracting the data type and the corresponding numerical value when the data type is determined to belong to the preset required data type;
judging whether the numerical value accords with a preset numerical value type or not, and if the numerical value accords with the preset numerical value type, reserving the numerical value; if the numerical value is determined to be not in accordance with the preset numerical value type, performing type conversion on the numerical value so that the numerical value is correspondingly stored according to the preset numerical value type;
the method further comprises the steps of: generating the audit model; the generating the audit model includes:
acquiring a preset neural network structure; the neural network structure comprises at least one input node and at least two output nodes;
acquiring sample audit data and a training label corresponding to the sample audit data; the training tag includes: sample audit target points and sample audit error points;
training the neural network structure by using the sample audit data and the corresponding training label to obtain a trained neural network structure serving as the audit model;
after the audit data is preprocessed according to the preset rule, the method further comprises:
determining a numerical value N of the target audit data according to the following formula;
；
wherein R represents the overall value, BV represents the risk coefficient, TM represents the tolerable error reporting, E represents the expected error reporting, R represents the expansion coefficient, and v represents the data importance;
selecting N target audit data from the preprocessed audit data;
correspondingly, the analyzing the audit data by using a preset audit model comprises the following steps:
and analyzing the N target audit data by using a preset audit model.
5. A computer readable storage medium, comprising an auditing method program, which when executed by a processor, implements the steps of an auditing method according to any of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910815693.2A CN110532301B (en) | 2019-08-30 | 2019-08-30 | Audit method, system and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910815693.2A CN110532301B (en) | 2019-08-30 | 2019-08-30 | Audit method, system and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110532301A CN110532301A (en) | 2019-12-03 |
| CN110532301B true CN110532301B (en) | 2023-08-22 |
Family
ID=68665617
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910815693.2A Active CN110532301B (en) | 2019-08-30 | 2019-08-30 | Audit method, system and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110532301B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111177779B (en) * | 2019-12-24 | 2023-04-25 | 深圳昂楷科技有限公司 | Database auditing method, device, electronic equipment and computer storage medium |
| CN112465397A (en) * | 2020-12-15 | 2021-03-09 | 广东电网有限责任公司 | Audit data analysis method and device |
| CN112651618A (en) * | 2020-12-21 | 2021-04-13 | 国家电网有限公司大数据中心 | Construction method of audit dimension model for online audit of metering data |
| CN112711772A (en) * | 2020-12-30 | 2021-04-27 | 杭州未名信科科技有限公司 | Auditing system, method and storage medium for function execution in service |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5845285A (en) * | 1997-01-07 | 1998-12-01 | Klein; Laurence C. | Computer system and method of data analysis |
| CN106503102A (en) * | 2016-10-17 | 2017-03-15 | 汉蓝（北京）科技有限公司 | A kind of search engine formula audit analysis method |
| CN107832429A (en) * | 2017-11-14 | 2018-03-23 | 广州供电局有限公司 | audit data processing method and system |
| CN108268656A (en) * | 2018-01-31 | 2018-07-10 | 合肥和钧正策信息技术有限公司 | A kind of big data intelligent cloud auditing method and system |
| CN108460521A (en) * | 2018-02-02 | 2018-08-28 | 广州供电局有限公司 | The recommendation method and system of the audit target |
| CN108959349A (en) * | 2018-04-23 | 2018-12-07 | 厦门快商通信息技术有限公司 | A kind of financial audit circular for confirmation system |
-
2019
- 2019-08-30 CN CN201910815693.2A patent/CN110532301B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5845285A (en) * | 1997-01-07 | 1998-12-01 | Klein; Laurence C. | Computer system and method of data analysis |
| CN106503102A (en) * | 2016-10-17 | 2017-03-15 | 汉蓝（北京）科技有限公司 | A kind of search engine formula audit analysis method |
| CN107832429A (en) * | 2017-11-14 | 2018-03-23 | 广州供电局有限公司 | audit data processing method and system |
| CN108268656A (en) * | 2018-01-31 | 2018-07-10 | 合肥和钧正策信息技术有限公司 | A kind of big data intelligent cloud auditing method and system |
| CN108460521A (en) * | 2018-02-02 | 2018-08-28 | 广州供电局有限公司 | The recommendation method and system of the audit target |
| CN108959349A (en) * | 2018-04-23 | 2018-12-07 | 厦门快商通信息技术有限公司 | A kind of financial audit circular for confirmation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110532301A (en) | 2019-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110532301B (en) | Audit method, system and readable storage medium | |
| CN109993233B (en) | Method and system for predicting data auditing objective based on machine learning | |
| AU2022204197A1 (en) | Security weakness and infiltration detection and repair in obfuscated website content | |
| CN111881158B (en) | Processing method, device, computer system and readable storage medium for managing report data | |
| CN112330412A (en) | Product recommendation method and device, computer equipment and storage medium | |
| Castaño et al. | Exploring the Carbon Footprint of Hugging Face's ML Models: A Repository Mining Study | |
| CN110543565A (en) | Auditing method, system and readable storage medium based on convolutional neural network model | |
| CN113762973A (en) | Data processing method and device, computer readable medium and electronic equipment | |
| CN111582645B (en) | APP risk assessment method and device based on factoring machine and electronic equipment | |
| CN111178701B (en) | Risk control method and device based on feature derivation technology and electronic equipment | |
| CN113807469A (en) | Multi-energy user value prediction method, device, storage medium and equipment | |
| CN106022640B (en) | Electric quantity index checking system and method | |
| CN112990989B (en) | Value prediction model input data generation method, device, equipment and medium | |
| CN113450158A (en) | Bank activity information pushing method and device | |
| CN117743601A (en) | Natural resource knowledge graph completion method, device, equipment and medium | |
| CN111639916A (en) | Online auditing method, system and readable storage medium based on block chain technology and deep learning | |
| US11568308B2 (en) | Correcting bias in supervised machine learning data | |
| CN115358894A (en) | Intellectual property life cycle trusteeship management method, device, equipment and medium | |
| CN112712270B (en) | Information processing method, device, equipment and storage medium | |
| CN114912538A (en) | Information push model training method, information push method, device and equipment | |
| CN113052509A (en) | Model evaluation method, model evaluation apparatus, electronic device, and storage medium | |
| CN113849618A (en) | Strategy determination method and device based on knowledge graph, electronic equipment and medium | |
| CN113704407A (en) | Complaint amount analysis method, device, equipment and storage medium based on category analysis | |
| CN110532302B (en) | Audit method, system and readable storage medium | |
| CN111429257A (en) | Transaction monitoring method and device |
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 |