CN116595859A - Audit model construction method, device, equipment and medium based on machine learning - Google Patents
Audit model construction method, device, equipment and medium based on machine learning Download PDFInfo
- Publication number
- CN116595859A CN116595859A CN202310386928.7A CN202310386928A CN116595859A CN 116595859 A CN116595859 A CN 116595859A CN 202310386928 A CN202310386928 A CN 202310386928A CN 116595859 A CN116595859 A CN 116595859A
- Authority
- CN
- China
- Prior art keywords
- model
- data
- audit
- data analysis
- analysis application
- 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
- 238000012550 audit Methods 0.000 title claims abstract description 155
- 238000010276 construction Methods 0.000 title claims abstract description 40
- 238000010801 machine learning Methods 0.000 title claims abstract description 32
- 238000007405 data analysis Methods 0.000 claims abstract description 136
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000013500 data storage Methods 0.000 claims description 31
- 238000004458 analytical method Methods 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012163 sequencing technique Methods 0.000 claims description 11
- 238000013480 data collection Methods 0.000 claims description 10
- 238000000034 method Methods 0.000 abstract description 24
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000011157 data evaluation Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000008093 supporting effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/12—Accounting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Technology Law (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application belongs to the technical field of audit, and particularly relates to an audit model construction method, device, equipment and medium based on machine learning, wherein the method comprises the following steps: receiving a data analysis application, and judging whether source data exist in the data analysis application; if yes, obtaining model configuration according to the data analysis application, wherein the model configuration comprises a model catalog, model parameters and model attributes; and merging the model configuration into a model framework built in advance to obtain an audit model. According to the application, model construction is carried out according to the data analysis application so as to obtain an audit model which meets the data analysis requirement and has complete information, the audit model has the performance of analyzing and evaluating the data, and a user can use the audit model to audit the big data, so that the efficiency of data processing is improved.
Description
Technical Field
The application relates to the technical field of auditing, in particular to an auditing model construction method, device, equipment and medium based on machine learning.
Background
When huge power grid data is processed, an audit model is properly adopted to assist in processing, but the existing audit model is mainly in the form of document files (such as excel and word) and the like to record element information such as model ideas and rules, a model list is formed, and the model list is shared for other people to use.
Thus, how to construct an audit model that is complete in information and matches the needs of data analysis is a problem that needs to be addressed at present.
Disclosure of Invention
The application provides an audit model construction method, device, equipment and medium based on machine learning, and aims to construct an audit model with complete information and matching with data analysis requirements.
In order to achieve the above object, a first aspect of the present application provides an audit model construction method based on machine learning, the method comprising:
receiving a data analysis application, and judging whether source data exist in the data analysis application;
if yes, obtaining model configuration according to the data analysis application, wherein the model configuration comprises a model catalog, model parameters and model attributes;
and merging the model configuration into a model framework built in advance to obtain an audit model.
Further, after the receiving the data analysis application, the method further includes:
analyzing the data analysis application to obtain a data analysis demand list;
and sequencing the analysis applications in the data analysis demand list according to the emergency degree of the analysis demands to obtain a sequencing data analysis demand list.
Further, after determining whether the source data exists in the data analysis application, the method further includes:
and if the source data exists in the data analysis application, storing the source data into a preset data storage library according to a preset storage rule, and pushing the data storage library to a data processing center.
Further, after determining whether the source data exists in the data analysis application, the method further includes:
if the source data does not exist in the data analysis application, the source data is collected according to a preset data collection strategy, the source data is stored in a preset data storage library according to a preset storage rule, and the data storage library is pushed to a data processing center.
Further, after the audit model is obtained, the method further comprises:
checking the audit model, and judging whether the configuration information of the audit model is complete;
if the configuration information is complete, checking whether the audit model is correct;
and if the model is correct, confirming the audit model and terminating the model construction flow.
Further, after the audit model is obtained, the method further comprises:
selecting data of source data in the data storage library according to the data analysis application to obtain data to be analyzed;
and carrying out data processing on the data to be analyzed by using the audit model to obtain audit data.
The application also provides an audit model construction device based on machine learning, which comprises:
the receiving module is used for receiving a data analysis application and judging whether source data exist in the data analysis application;
the acquisition module is used for acquiring model configuration according to the data analysis application if source data exist, wherein the model configuration comprises a model catalog, model parameters and model attributes;
and the merging module is used for merging the model configuration into a model frame built in advance to obtain an audit model.
Further, the receiving module includes:
the analysis unit is used for analyzing the data analysis application and obtaining a data analysis demand list;
the sorting unit is used for sorting the analysis applications in the data analysis demand list according to the analysis demand emergency degree to obtain a sorted data analysis demand list
The application also provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of any one of the above machine learning based audit model construction methods when executing the computer program.
The application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the machine learning based audit model construction method described in any of the above.
The beneficial effects are that: in the application, a data analysis application submitted by a user is received, and whether source data exist in the data analysis application is judged; if the source data exists in the data analysis application, the data analysis application is indicated to meet the requirements, a model configuration is obtained according to the data analysis application, the model configuration comprises a model catalog, model parameters and model attributes, wherein the model catalog definitely defines the subject information of a model, the model parameters definitely define index variables of the model, and the model attributes definitely define the purposes of the model; and merging the model configuration into a model framework built in advance, so as to obtain an audit model which is complete in information and matched with the data analysis application, wherein the audit model has the performance of analyzing and evaluating the data, can provide technical support for the implementation of a digital audit project, and improves the data audit supervision efficiency.
Drawings
FIG. 1 is a flow chart of an embodiment of a machine learning based audit model construction method of the present application;
FIG. 2 is a flow chart of another embodiment of a machine learning based audit model construction method of the present application;
FIG. 3 is a flow chart of another embodiment of a machine learning based audit model construction method of the present application;
FIG. 4 is a flow chart of another embodiment of a machine learning based audit model construction method of the present application;
FIG. 5 is a schematic diagram of an embodiment of a machine learning based audit model construction apparatus according to the present application;
FIG. 6 is a schematic block diagram illustrating the construction of a computer device according to an embodiment of the present application.
The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, modules, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, modules, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any module and all combination of one or more of the associated listed items.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Referring to fig. 1, an embodiment of the present application provides an audit model construction method based on machine learning, including the following steps S1 to S3:
s1: and receiving a data analysis application, and judging whether source data exist in the data analysis application.
The data analysis application is triggered by a user according to the use requirement, specifically, the user fills specific requirement matters in a requirement analysis template according to the data analysis requirement, wherein the requirement matters can include, but are not limited to, analysis purposes, a used analysis method, expected analysis results and the like, after the requirement analysis template is filled, the filled requirement analysis template is submitted through a user side so as to start a data analysis application flow; the receiving end receives the data analysis application, analyzes the data analysis application and judges whether source data exists in the data analysis application, wherein the source data is power grid original data for data analysis; whether the data analysis application is complete is determined by judging whether source data exist in the data analysis application, if so, the source data are stored into a preset data storage library according to a preset storage rule, and the data storage library is pushed to a data processing center to provide a data basis for data analysis of a follow-up audit model.
S2: if yes, obtaining model configuration according to the data analysis application, wherein the model configuration comprises a model catalog, model parameters and model attributes.
After receiving a data analysis application and judging whether source data exist in the data analysis application, if the source data exist in the data analysis application, obtaining model configuration according to the data analysis application, wherein the model configuration comprises a model catalog, model parameters and model attributes, specifically, the model catalog is used for creating a corresponding audit topic according to an audit service supported by an audit model, and the audit topic can be used for creating catalogues such as financial topics, asset topics, marketing topics and the like as primary topics, secondary topics, tertiary topics and the like according to actual use conditions; the model parameters refer to model index variables designed by technicians according to actual conditions; the model attribute refers to the primary purpose of describing the model according to the business meaning of the model in combination with primary dimensions (such as: time, units), primary metrics (such as: amount, mileage). And obtaining the model configuration, and providing effective basis for the subsequent establishment of an audit model with complete information.
S3: and merging the model configuration into a model framework built in advance to obtain an audit model.
After the model configuration is acquired according to the data analysis application, the model configuration based on the complete audit model comprises a model framework and model configuration, wherein the model framework is designed in advance for a technician, the model framework determines a structural system of the model, and designs configuration information and configuration positions which the model should be equipped with, so that the acquired model configuration can be integrated into the configuration positions which are designed in advance for the model framework, and the audit model is further obtained. In order to ensure the accuracy and the completeness of the constructed audit model, the constructed audit model is also checked, wherein the checking comprises checking whether the configuration information of the audit model is complete, whether the configuration position of the configuration information in the model is correct, and whether the configuration information is correct, if any item of the configuration information is not in accordance with the requirements, judging that the constructed audit model is not in accordance with the requirements, and reconstructing the audit model until a new audit model in accordance with the requirements is obtained; if the constructed audit model meets the requirements, confirming the audit model, terminating the model construction flow, and not constructing the model any more until a new data analysis application is received next time, and starting a new model construction flow.
The embodiment provides an audit model construction method based on machine learning, which is implemented by receiving a data analysis application submitted by a user and judging whether source data exist in the data analysis application; if the source data exists in the data analysis application, the data analysis application is indicated to meet the requirements, a model configuration is obtained according to the data analysis application, the model configuration comprises a model catalog, model parameters and model attributes, wherein the model catalog definitely defines the subject information of a model, the model parameters definitely define index variables of the model, and the model attributes definitely define the purposes of the model; and merging the model configuration into a model framework built in advance, so as to obtain an audit model which is complete in information and matched with the data analysis application, wherein the audit model has the performance of analyzing and evaluating the data, can provide technical support for the implementation of a digital audit project, and improves the data audit supervision efficiency.
Referring to fig. 2, in one embodiment, after the receiving the data analysis application, the method further includes:
s11, analyzing the data analysis application to obtain a data analysis demand list;
the data analysis application can be provided with a plurality of data analysis applications, and the data analysis application is analyzed to determine each application requirement contained in the data analysis application, and list each application requirement in a list form, so as to obtain a data analysis requirement list.
And S12, sorting the analysis applications in the data analysis demand list according to the emergency degree of the analysis demands to obtain a sorted data analysis demand list.
And sequencing the analysis applications in the data analysis demand list according to the emergency degree of the analysis demand so as to determine the processing level of each analysis application in the data analysis demand list and facilitate the subsequent priority processing of the emergency analysis application.
As described above, there may be a plurality of data analysis applications in the data analysis application, and by analyzing the data analysis application, each application requirement included in the data analysis application is clarified, and each application requirement is listed in a list form, so as to obtain a data analysis requirement list; and sorting the analysis applications in the data analysis demand list according to the emergency degree of the analysis demand, wherein the sorting can be descending sorting or ascending sorting, and the processing level of each analysis application in the data analysis demand list is determined through sorting to obtain the sorted data analysis demand list, and the acquisition of the sorted data analysis demand list is beneficial to the targeted priority processing of the emergency analysis applications of subsequent users.
In one embodiment, after determining whether the source data exists in the data analysis application, the method further includes:
and if the source data exists in the data analysis application, storing the source data into a preset data storage library according to a preset storage rule, and pushing the data storage library to a data processing center.
As described above, the preset storage rule refers to a data storage format preset by a user to provide the storage of the source data with regularity, wherein the storage rule includes a paste source layer storage, a detail layer storage, an application layer storage, and a temporary layer storage; the source layer storage refers to creating database mode classification storage according to data sources and service domains; the detail layer storage refers to the broad table for processing the data of the source layer according to the service use of the data, and then the broad table is classified and stored according to the use; the application layer storage refers to further processing of the source layer data and the detail layer data, focusing on a single audit problem point, and then using a database mode for storage; the temporary layer storage refers to a created data table or a temporarily created application table aiming at the audit project requirement, such as extracting data of an audit power grid from a source layer, temporarily storing data provided by an audit project group and the like; and storing the source data into a preset data storage library according to a preset storage rule, standardizing the storage format of the source data, further obtaining the data storage library with the storage rule, pushing the data storage library to a data processing center, and pushing the data storage library to the data processing center so as to be beneficial to providing a data analysis basis for an audit model when the audit model is used for data analysis.
In one embodiment, after determining whether the source data exists in the data analysis application, the method further includes:
if the source data does not exist in the data analysis application, the source data is collected according to a preset data collection strategy, the source data is stored in a preset data storage library according to a preset storage rule, and the data storage library is pushed to a data processing center.
As described above, if the source data does not exist in the data analysis application, the source data is collected according to a preset data collection policy, where the data collection policy refers to a data collection format and a data collection method preset by a user to obtain data meeting the data processing requirement, the data collection policy may include, but is not limited to, a direct push collection policy, a t+1 increment collection policy, a quarter increment collection policy, a manual full-quantity collection policy, and the like, where the data collection policy is preferably a direct push collection policy, that is, original data of a power grid is not classified into data types, but is directly captured, and the collected source data is stored in a preset data storage repository according to a preset storage rule, and the data storage repository is pushed to a data processing center, so that a data analysis basis exists when the data analysis is performed by using an audit model. Meanwhile, in order to ensure the integrity and consistency of the database, intermittent acquisition is carried out on the power grid source data through a T+1 increment acquisition strategy, a quarter increment acquisition strategy, a manual increment acquisition strategy and a manual total acquisition strategy so as to supplement the data of the database, specifically, each item of data is set according to an audit model and an audit application scene to set an acquisition strategy, and the strategy adopting T+1 increment acquisition is high in real-time requirement; the method is characterized in that the method adopts quarterly incremental acquisition once aiming at low real-time requirements, or the curing model involves manually executing incremental acquisition of data once before each batch of audit projects are developed, and whether the data volume of an audit data center and the data volume of the data center are consistent is checked.
Referring to fig. 3, in one embodiment, after obtaining the audit model, the method further includes:
s31: and checking the audit model, and judging whether the configuration information of the audit model is complete.
After the audit model is built, whether the audit model meets the requirements or not is checked, so that the subsequent use of the audit model which does not meet the requirements for data analysis is avoided; when the audit model is checked, whether the configuration information of the audit model is complete or not is firstly judged, specifically, whether the model catalogue, the model parameters and the model attributes of the audit model are complete or not is judged, if so, whether the configuration information of the audit model is complete or not is judged, and whether the audit model is correct or not can be further checked; however, if any item of the model catalog, the model parameters and the model attributes of the audit model is absent, the configuration information is incomplete and does not meet the model construction standard, and the audit model needs to be reconstructed until the configuration information of the new audit model is complete.
S32: and if the configuration information is complete, checking whether the audit model is correct.
Checking whether the audit model is accurate or not means checking whether the frame and configuration information of the audit model are consistent with the pre-designed frame and configuration information; if yes, judging that the audit model is correct, and can be normally used; if any item of the audit model is inconsistent with the preset design information, judging that the audit model is incorrect, and reconstructing the audit model until a new audit model meeting the requirements is obtained.
S33: and if the model is correct, confirming the audit model and terminating the model construction flow.
After the audit model is built, whether the audit model meets the requirements or not is checked, so that the follow-up data analysis by using the audit model which does not meet the requirements is avoided; when the audit model is checked, whether the configuration information of the audit model is complete and whether the audit model is correct is mainly checked, and specifically, whether a model catalog, model parameters and model attributes of the audit model are complete is firstly judged; if the audit model is complete, checking whether the audit model is correct, wherein checking whether the audit model is correct means checking whether the frame and configuration information of the audit model are consistent with the pre-designed frame and configuration information; if the model is consistent, judging that the audit model is correct, and can be used normally, confirming the audit model and terminating the model construction flow.
Referring to fig. 4, in one embodiment, after obtaining the audit model, the method further includes:
s34: and selecting the source data in the data storage library according to the data analysis application to obtain the data to be analyzed.
And based on the fact that a large amount of source data are stored in the data storage library, after an audit model is obtained, data selection is carried out on the source data in the data storage library according to the data analysis application, data meeting data analysis requirements or data needing to be subjected to data analysis are selected, and then data to be analyzed are obtained.
S35: and carrying out data processing on the data to be analyzed by using the audit model to obtain audit data.
As described above, based on the fact that a large amount of source data is stored in the data repository, after an audit model is obtained, data selection is performed on the source data in the data repository according to the data analysis application, so as to select data meeting data analysis requirements or data needing to be subjected to data analysis, and further data to be analyzed is obtained, the data to be analyzed is a plurality of data information, if the data to be analyzed is subjected to data analysis and evaluation manually, the workload is high, the efficiency is low, and therefore, the data to be analyzed can be subjected to data processing by using the audit model, wherein the audit model has the performance of analyzing and evaluating the data, and can provide supporting effect for digital audit project implementation and improve data audit supervision efficiency; and analyzing and evaluating the data to be analyzed through the audit model, so that the data analysis efficiency is greatly improved. Audit data obtained after data analysis is completed supports data editing, and the audit data can be edited, so that the audit data is converted into a visual graph, the visual graph is convenient for a user to understand, and the user is assisted in making decisions.
Referring to fig. 5, an audit model building device based on machine learning according to an embodiment of the present application further includes:
the receiving module 10 is used for receiving a data analysis application and judging whether source data exists in the data analysis application;
the obtaining module 20 is configured to obtain a model configuration according to the data analysis application if source data exists, where the model configuration includes a model directory, model parameters, and model attributes;
and the merging module 30 is used for merging the model configuration into a model framework built in advance to obtain an audit model.
As described above, the machine learning-based audit model construction apparatus can implement the machine learning-based audit model construction method.
In one embodiment, the receiving module 10 further includes:
the analysis unit is used for analyzing the data analysis application and obtaining a data analysis demand list;
and the sequencing unit is used for sequencing the analysis applications in the data analysis demand list according to the emergency degree of the analysis demands to obtain a sequencing data analysis demand list.
In one embodiment, the receiving module 10 further includes:
and the first pushing unit is used for storing the source data into a preset data storage library according to a preset storage rule and pushing the data storage library to a data processing center if the source data exist in the data analysis application.
In one embodiment, the receiving module 10 further includes:
and the second pushing unit is used for collecting the source data according to a preset data collection strategy if the source data does not exist in the data analysis application, storing the source data into a preset data storage library according to a preset storage rule, and pushing the data storage library to a data processing center.
In one embodiment, the merging module 30 further includes:
the first judging unit is used for checking the audit model and judging whether the configuration information of the audit model is complete or not;
the second judging unit is used for checking whether the audit model is correct or not if the configuration information is complete;
and the confirmation unit is used for confirming the audit model and terminating the model construction flow if the model is correct.
In one embodiment, the merging module 30 further includes;
the selection unit is used for carrying out data selection on the source data in the data storage library according to the data analysis application to obtain data to be analyzed;
and the processing unit is used for carrying out data processing on the data to be analyzed by using the audit model to obtain audit data.
Referring to fig. 6, an embodiment of the present application further provides a computer device, and an internal structure of the computer device may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The nonvolatile storage medium stores an operating device, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing relevant data of an audit model construction method based on machine learning and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. Further, the above-mentioned computer apparatus may be further provided with an input device, a display screen, and the like. The above computer program, when executed by a processor, implements a machine learning based audit model construction method, comprising the steps of: receiving a data analysis application, and judging whether source data exist in the data analysis application; if yes, obtaining model configuration according to the data analysis application, wherein the model configuration comprises a model catalog, model parameters and model attributes; and merging the model configuration into a model framework built in advance to obtain an audit model. It will be appreciated by those skilled in the art that the architecture shown in fig. 6 is merely a block diagram of a portion of the architecture in connection with the present inventive arrangements and is not intended to limit the computer devices to which the present inventive arrangements are applicable.
An embodiment of the present application further provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a machine learning-based audit model construction method, including the steps of: receiving a data analysis application, and judging whether source data exist in the data analysis application; if yes, obtaining model configuration according to the data analysis application, wherein the model configuration comprises a model catalog, model parameters and model attributes; and merging the model configuration into a model framework built in advance to obtain an audit model. It is understood that the computer readable storage medium in this embodiment may be a volatile readable storage medium or a nonvolatile readable storage medium.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided by the present application and used in embodiments may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the scope of the application, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application or directly or indirectly applied to other related technical fields are included in the scope of the application.
Claims (10)
1. An audit model construction method based on machine learning, which is characterized by comprising the following steps:
receiving a data analysis application, and judging whether source data exist in the data analysis application;
if yes, obtaining model configuration according to the data analysis application, wherein the model configuration comprises a model catalog, model parameters and model attributes;
and merging the model configuration into a model framework built in advance to obtain an audit model.
2. The machine learning based audit model construction method according to claim 1 further including, after receiving a data analysis application:
analyzing the data analysis application to obtain a data analysis demand list;
and sequencing the analysis applications in the data analysis demand list according to the emergency degree of the analysis demands to obtain a sequencing data analysis demand list.
3. The machine learning based audit model construction method according to claim 1 wherein after determining whether source data exists in the data analysis application, further comprising:
and if the source data exists in the data analysis application, storing the source data into a preset data storage library according to a preset storage rule, and pushing the data storage library to a data processing center.
4. The machine learning based audit model construction method according to claim 1 wherein after determining whether source data exists in the data analysis application, further comprising:
if the source data does not exist in the data analysis application, the source data is collected according to a preset data collection strategy, the source data is stored in a preset data storage library according to a preset storage rule, and the data storage library is pushed to a data processing center.
5. The machine learning based audit model construction method according to claim 1 further comprising, after obtaining an audit model:
checking the audit model, and judging whether the configuration information of the audit model is complete;
if the configuration information is complete, checking whether the audit model is correct;
and if the model is correct, confirming the audit model and terminating the model construction flow.
6. A machine learning based audit model construction method according to any of claims 3 or 4 and further comprising, after said obtaining an audit model:
selecting data of source data in the data storage library according to the data analysis application to obtain data to be analyzed;
and carrying out data processing on the data to be analyzed by using the audit model to obtain audit data.
7. An audit model building device based on machine learning, the device comprising:
the receiving module is used for receiving a data analysis application and judging whether source data exist in the data analysis application;
the acquisition module is used for acquiring model configuration according to the data analysis application if source data exist, wherein the model configuration comprises a model catalog, model parameters and model attributes;
and the merging module is used for merging the model configuration into a model frame built in advance to obtain an audit model.
8. The machine learning based audit model construction device according to claim 7 wherein the receiving module includes:
the analysis unit is used for analyzing the data analysis application and obtaining a data analysis demand list;
and the sequencing unit is used for sequencing the analysis applications in the data analysis demand list according to the emergency degree of the analysis demands to obtain a sequencing data analysis demand list.
9. A computer device comprising a memory and a processor, the memory having stored therein a computer program, wherein the processor when executing the computer program performs the steps of the machine learning based audit model construction method according to any of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the steps of the machine learning based audit model construction method according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310386928.7A CN116595859A (en) | 2023-04-11 | 2023-04-11 | Audit model construction method, device, equipment and medium based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310386928.7A CN116595859A (en) | 2023-04-11 | 2023-04-11 | Audit model construction method, device, equipment and medium based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116595859A true CN116595859A (en) | 2023-08-15 |
Family
ID=87594521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310386928.7A Pending CN116595859A (en) | 2023-04-11 | 2023-04-11 | Audit model construction method, device, equipment and medium based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116595859A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117234739A (en) * | 2023-11-10 | 2023-12-15 | 中国信息通信研究院 | Method, apparatus, system, and storage medium for industrial data analysis |
| CN117370809A (en) * | 2023-11-02 | 2024-01-09 | 快朵儿(广州)云科技有限公司 | Artificial intelligence model construction method, system and storage medium based on deep learning |
-
2023
- 2023-04-11 CN CN202310386928.7A patent/CN116595859A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117370809A (en) * | 2023-11-02 | 2024-01-09 | 快朵儿(广州)云科技有限公司 | Artificial intelligence model construction method, system and storage medium based on deep learning |
| CN117370809B (en) * | 2023-11-02 | 2024-04-12 | 快朵儿(广州)云科技有限公司 | Artificial intelligence model construction method, system and storage medium based on deep learning |
| CN117234739A (en) * | 2023-11-10 | 2023-12-15 | 中国信息通信研究院 | Method, apparatus, system, and storage medium for industrial data analysis |
| CN117234739B (en) * | 2023-11-10 | 2024-02-23 | 中国信息通信研究院 | Method, apparatus, system, and storage medium for industrial data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116595859A (en) | Audit model construction method, device, equipment and medium based on machine learning | |
| CN109254959B (en) | Data evaluation method and device, terminal equipment and readable storage medium | |
| CN112883692B (en) | Automatic generation method of PPT data report | |
| CN114511019A (en) | Sensitive data classification and grading identification method and system | |
| CN112286934A (en) | Database table importing method, device, equipment and medium | |
| CN112328499A (en) | Test data generation method, device, equipment and medium | |
| CN113220672A (en) | Military and civil fusion policy information database system | |
| CN116775879A (en) | Fine tuning training method of large language model, contract risk review method and system | |
| CN114819941A (en) | Method and device for generating study-leaving user payment life cycle model | |
| CN111708810B (en) | Model optimization recommendation method and device and computer storage medium | |
| CN111224859A (en) | Method for deleting chat records, computer equipment and storage medium | |
| CN111427544A (en) | Software requirement document generation method and device, storage medium and electronic equipment | |
| CN112507129B (en) | Content change processing method of power distribution network operation file and related equipment | |
| CN113434946B (en) | Building model checking system and method based on BIM | |
| CN112487022B (en) | Method, system, storage medium and electronic equipment for collecting associated data | |
| CN110727897B (en) | Geological survey information service rapid publishing method and system supporting multi-terminal operation | |
| CN111752984B (en) | Information processing method, device and storage medium | |
| Nor et al. | Automating Aspects of Forensic Case Management | |
| CN116596683A (en) | Audit data acquisition and fusion method, audit data acquisition and fusion device, audit data acquisition and fusion equipment and storage medium | |
| Rahayuda et al. | Web Harvesting for Data Retrieval on Scientific Journal Sites | |
| CN114862369A (en) | Distribution network automation manufacturer data sorting and analyzing method, device and storage medium | |
| CN117033447A (en) | Service function label catalog construction method, medium and system based on application catalog | |
| CN115994838A (en) | Patent information pushing method and device, computer equipment and storage medium | |
| CN114896301A (en) | Data analysis method and device, storage medium and electronic equipment | |
| CN114722215A (en) | Method and system for constructing knowledge graph model |
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 |