CN117436820B - Control method and system based on artificial intelligence - Google Patents

Control method and system based on artificial intelligence Download PDF

Info

Publication number
CN117436820B
CN117436820B CN202311726390.6A CN202311726390A CN117436820B CN 117436820 B CN117436820 B CN 117436820B CN 202311726390 A CN202311726390 A CN 202311726390A CN 117436820 B CN117436820 B CN 117436820B
Authority
CN
China
Prior art keywords
data
declaration
reporting
business
service
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
Application number
CN202311726390.6A
Other languages
Chinese (zh)
Other versions
CN117436820A (en
Inventor
阮江科
马遥
陈家意
黄乐轩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Minxing Digital Technology Co ltd
Original Assignee
Guangzhou Minxing Digital Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Minxing Digital Technology Co ltd filed Critical Guangzhou Minxing Digital Technology Co ltd
Priority to CN202311726390.6A priority Critical patent/CN117436820B/en
Publication of CN117436820A publication Critical patent/CN117436820A/en
Application granted granted Critical
Publication of CN117436820B publication Critical patent/CN117436820B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • 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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/10—Tax strategies

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Evolutionary Computation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Software Systems (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Technology Law (AREA)
  • Medical Informatics (AREA)
  • Educational Administration (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides a control method and a control system based on artificial intelligence, wherein the method comprises the following steps: analyzing the issued reporting business policy based on a semantic recognition method, and extracting reporting index requirement data; training and learning the extracted reporting index requirement data based on a machine learning model to obtain a data abnormality automatic identification model; based on the data abnormality automatic identification model, carrying out abnormality identification on the declaration service data sent by the enterprise to obtain an identification result, if the identification result is normal, executing security monitoring on the declaration service data and a service request end for sending the declaration service data, otherwise, storing the declaration service data with the abnormal identification result into a first-stage auditing abnormal storage area. The application improves the reporting data quality, the reporting efficiency and the accuracy and the reporting business security.

Description

Control method and system based on artificial intelligence
Technical Field
The application relates to the technical field of data processing, in particular to a control method and system based on artificial intelligence.
Background
At present, the declaration business is a tax-related matter such as business, unit declaration and tax handling tax registration, change registration, deregistration and tax declaration to tax department. And the tax payer reports various tax calculation and service activities of paying related data and information to the tax authority according to legal program within a specified period. The reporting business comprises: value-added tax declaration, enterprise income tax declaration, personal income tax declaration, city maintenance construction tax declaration, education fee additional declaration, local education additional declaration, resource tax declaration, import tariff declaration, export tax refund declaration and the like.
Although the declaration service provides convenience for tax administration, there are some drawbacks in actual operation, and the main drawbacks are as follows:
Firstly, the declared data quality is not high: some tax payers may have problems such as missing report, misreport, false report, etc. in the reporting process, so that accuracy and integrity of reporting data are affected. In the process of reporting various projects, the enterprises need to actively pay attention to the dynamic and qualification confirmation of the related projects, the efficiency is low, important information is easy to miss, indiscriminate information push is often ignored by the enterprises due to lack of pertinence.
Second, reporting efficiency is low. The current reporting business relates to reporting of a plurality of tax types, and the reporting flow and the filling requirements of each tax type are different, so that the reporting burden of a tax payer is increased. Moreover, the reporting business is usually concentrated in a specific time period of each year, such as annual reporting of income tax of enterprises, quaternary reporting of income tax of individuals, and the like, and brings great time pressure to tax payers.
Third, the risk of declaration is higher.
Artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the discipline of studying certain mental processes and intelligent behaviors (e.g., learning, reasoning, thinking, planning, etc.) that make computers simulate humans, both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, machine learning, deep learning, a big data processing technology, a knowledge graph technology and the like.
Therefore, the technical problems to be solved are: how to provide a control method and a control system based on artificial intelligence, which can improve the reporting data quality, the reporting efficiency and accuracy and the reporting business security.
Disclosure of Invention
The application aims to provide a control method and a control system based on artificial intelligence, which can improve the quality of declaration data, the declaration efficiency and accuracy and the security of declaration business.
In order to achieve the above object, the present application provides an artificial intelligence based control method, which comprises the following steps:
analyzing the issued reporting business policy based on a semantic recognition method, and extracting reporting index requirement data;
training and learning the extracted reporting index requirement data based on a machine learning model to obtain a data abnormality automatic identification model;
Based on the data abnormality automatic identification model, carrying out abnormality identification on the declaration service data sent by an enterprise to obtain an identification result, if the identification result is normal, executing security monitoring on the declaration service data and a service request end for sending the declaration service data, otherwise, storing the declaration service data with abnormal identification result into a first-stage auditing abnormal storage area;
If the security monitoring is passed, executing the calculation of the matching degree value of the reporting service data and the reporting service policy of the service request terminal according to the reporting service data and the reporting index requirement data sent by the service request terminal;
storing the declaration business data to a first-level auditing passing storage area according to the sequence of the matching degree value from big to small;
And checking and comparing the reporting business data in the first-stage checking passing storage area with the enterprise business record information, performing second-stage checking operation, if the second-stage checking operation passes, storing the passing reporting business data into a second-stage checking passing storage area, and otherwise, storing the reporting business data into a second-stage checking abnormal storage area.
The control method based on artificial intelligence, wherein, the method for carrying out safety monitoring on the declaration service data and the service request end for sending the declaration service data comprises the following steps:
performing risk identification on the declaration service data based on a pre-constructed data risk identification model, extracting risk characteristic data of the declaration service data, and acquiring risk situation characteristic data of a service request end for transmitting the declaration service data;
Calculating a declaration risk prediction value of declaration service data of the service request end according to the risk characteristic data of the declaration service data and the risk situation characteristic data of the service request end;
Comparing the declaration risk predicted value of the declaration business data of the current business request end with a preset threshold value, if the declaration risk predicted value is smaller than the preset threshold value, allowing the current business request end to send the declaration business data to the receiver, otherwise, preventing the security monitoring from being passed, and prohibiting the current business request end from sending the declaration business data to the receiver.
The control method based on artificial intelligence as described above, wherein the reporting index requirement data includes: the type of business, the area to which the business belongs, the number of people in the business, the business turnover of the business, the duration of the establishment of the business and the credit rating of the business.
The control method based on artificial intelligence, wherein, the calculation formula of the matching degree value of the declaration service data and the declaration service policy of the service request end is as follows:
；
Wherein, A matching degree value of the declaration service data and the declaration service policy of the service request terminal is represented; /(I)Representing the historical reporting success times of the service request end on the current reporting service policy; /(I)Representing the total reporting times of the service request end on the current reporting service policy; /(I)Representing the average reporting times of the service request end under the history reporting of the current reporting service policy; /(I)Representing natural constants; /(I)Representing the total category number of the declaration service data; /(I)Represents the/>Whether the reporting business data accords with the parameter factors of reporting index requirement data or not; if/>The species declaration business data accords with the declaration index requirement data, and/>; Otherwise,/>；/>The number of the declaration business data which accords with the numerical property in the declaration index requirement data in the declaration business data is represented; /(I)Represents the/>The weight of the business data influence is declared; /(I)Represents the/>Actual values of the individual declaration business data; /(I)Represents the/>The lowest limit value of the business data is declared.
According to the control method based on the artificial intelligence, the declared business data in the first-level audit passing storage area is checked and compared with the enterprise business record information, if the declared business data is consistent with the enterprise business record information, the second-level audit operation is passed, and otherwise, the second-level audit operation is not passed.
The control method based on artificial intelligence, wherein, the matching degree value of the declaration business data and the declaration business policy is marked for each declaration business data through a storage area in the first level.
An artificial intelligence based control method as described above wherein the method further comprises: and carrying out classified recognition training on the declaration service data of the machine learning model, and recognizing classified information in the declaration service data.
The control method based on artificial intelligence, wherein the risk characteristic data of the declaration service data comprises the following steps: illegal statements, malicious instructions, and malicious links.
The control method based on artificial intelligence, wherein the dangerous situation characteristic data of the service request end comprises the following steps: the method comprises the steps of service request end malicious instruction data and service request end malicious keyword data.
As a second aspect of the present application, the present application provides an artificial intelligence based control system comprising:
The semantic extraction module is used for analyzing the issued declaration business policy based on a semantic recognition method and extracting declaration index requirement data;
The model acquisition module is used for training and learning the extracted declaration index requirement data based on a machine learning model to obtain a data abnormality automatic identification model;
The abnormality identification module is used for carrying out abnormality identification on the declaration service data sent by the enterprise based on the data abnormality automatic identification model, obtaining an identification result, if the identification result is normal, executing safety monitoring on the declaration service data and a service request end for sending the declaration service data, otherwise, storing the declaration service data with the abnormal identification result into the first-stage auditing abnormal storage area;
The data processor is used for executing the reporting service data and reporting index requirement data sent by the service request terminal and calculating the matching degree value of the reporting service data and the reporting service policy of the service request terminal if the safety monitoring is passed;
the storage module is used for storing the declaration business data to a first-level auditing passing storage area according to the sequence of the matching degree values from high to low;
And the checking and comparing module is used for checking and comparing the declaration service data in the first-stage checking and passing storage area with the enterprise business record information, performing second-stage checking operation, and if the second-stage checking operation passes, storing the passing declaration service data into the second-stage checking and passing storage area, otherwise, storing the declaration service data into the second-stage checking and abnormal storage area.
The beneficial effects achieved by the application are as follows:
(1) The artificial intelligence control method of the reporting business primarily identifies abnormal conditions of the reporting business data, for example, certain data are found to be out of specification in the reporting process, and automatically gives out warnings or prompts, so that the reporting efficiency is improved, the labor cost is reduced, and the reporting accuracy and reliability can be improved.
(2) The application carries out risk identification on the reporting service data and the service request terminal, monitors and early warns in real time, calculates the reporting risk prediction value of the reporting service data of the service request terminal according to the risk characteristic data of the reporting service data and the risk situation characteristic data of the service request terminal, and allows the current service request terminal to send the reporting service data to the receiver if the reporting risk prediction value is smaller than the preset threshold value, otherwise, prohibits the current service request terminal from sending the reporting service data to the receiver, thereby improving the safety of the whole reporting service.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings to those skilled in the art.
FIG. 1 is a flow chart of an artificial intelligence based control method according to an embodiment of the application.
Fig. 2 is a schematic structural diagram of an artificial intelligence-based control system according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Example 1
As shown in fig. 1, the present application provides an artificial intelligence based control method, which includes the steps of:
Step S1, analyzing the issued declaration business policy based on a semantic recognition method, and extracting declaration index requirement data.
Wherein the index requirement data includes: the type of business, the area to which the business belongs, the number of people in the business, the business turnover of the business, the duration of the establishment of the business, the credit level of the business, and the like.
Preferably, the declaration index requirement data is marked in a key way and then sent to the enterprise. Emphasis marks are for example: thickening, highlighting, underlining, or background color reminders, and the like.
And step S2, training and learning the extracted declaration index requirement data based on the machine learning model to obtain a data abnormality automatic identification model.
The data anomaly automatic identification model is used for carrying out anomaly identification on the reporting service data sent by the enterprise so as to obtain the abnormal reporting service data which does not meet the requirements (for example, a certain index requirement data is lacked, the content of the reporting service data is different from the type of the corresponding reporting index requirement data), and an early warning means is provided for early discovery of the reporting service data.
Wherein the machine learning model is a model in the prior art.
As a specific embodiment of the invention, the machine learning model is also subjected to classified recognition training of the declaration service data, so that the trained machine learning model can extract classified information in the declaration service data to perform classified storage management on the declaration service data. For example, the declaration type, tax declaration type and the like of the declaration business data are identified, and the declaration business data of the same type is subjected to classification management and classification processing, so that the processing efficiency of the declaration business is improved. The classification recognition training adopts the existing method, and is not described herein.
And step S3, based on the data abnormality automatic identification model, carrying out abnormality identification on the declaration service data sent by the enterprise to obtain an identification result, if the identification result is normal, carrying out safety monitoring on the declaration service data and the service request end, otherwise, storing the declaration service data with the abnormal identification result into a first-stage audit abnormal storage area.
Specifically, the enterprise sends a declaration service request to the host, the declaration service request carries declaration service data, the enterprise sends the declaration service data to the host through the declaration service request, the host stores a data abnormality automatic identification model in advance, the host identifies the declaration service data sent by the enterprise through the data abnormality automatic identification model to obtain an identification result, if the identification result is normal, the next step is executed to carry out security monitoring on the declaration service data and the service request end, and otherwise, the declaration service data with the identification result of abnormality is stored in a first-stage audit abnormal storage area.
In the process that the host receives the declaration service request, the number of the declaration service requests received in the sampling time is also recorded. The host sends the obtained identification result to the enterprise as a response to the enterprise's declaration service request.
The enterprise records the number of declared business requests it sends to the host, and the number of declared business requests the host has not received a response.
As a preferred embodiment of the invention, the host receives the declared business data and judges the level of the declared business data. And carrying out priority processing on the reporting service data with high priority. And data pressure brought to the host server in a short time is avoided.
And S4, carrying out safety monitoring on the declared business data and a business request end for sending the declared business data, if the safety monitoring is passed, executing the step S5, otherwise, prohibiting executing the step S5.
Step S4 includes the steps of:
Step S410, carrying out risk identification on the declared business data based on a pre-constructed data risk identification model, extracting risk characteristic data of the declared business data, and acquiring the risk situation characteristic data of a business request end for sending the declared business data.
The risk characteristic data of the declaration service data comprises: illegal statements, malicious instructions, malicious links, etc.
The dangerous situation characteristic data of the service request end comprises the following steps: malicious instruction data of a service request end, malicious keyword data of the service request end and the like.
Step S420, calculating the reporting risk prediction value of the reporting business data of the business request terminal according to the risk characteristic data of the reporting business data and the risk situation characteristic data of the business request terminal.
Specifically, the calculation formula of the declaration risk prediction value of the declaration service data of the service request end is as follows:
；
Wherein, A declaration risk prediction value for declaring business data of the business request terminal; /(I)Impact weight of risk characteristic data representing declaration service data; /(I)Representing the total category number of the risk characteristic data of the declaration service data; /(I)Presentation of declaration service dataThe number of seed risk profile data; /(I)Presentation of declaration service dataA weight factor of the seed risk feature data; /(I)Presentation of declaration service dataSeed/>Malicious values of the individual risk feature data; /(I)The influence weight of the dangerous situation characteristic data of the service request end is represented; /(I)The total number of dangerous situation characteristic data of the service request end is represented; /(I)Represents the business request end's/>A weight factor of the individual hazard situation feature data; /(I)Represents the business request end's/>Dangerous values of the individual dangerous situation feature data; /(I)An IP address abnormality factor representing a service request end; /(I)A communication protocol abnormality factor representing a service request end; if the IP address of the service request end is in the IP address range where the service is allowed to access,/>; Otherwise,/>. If the communication protocol of the service request end is in the range of the communication protocol type which declares that the service is allowed to be accessed,/>; Otherwise,/>。
Step S430, comparing the declaration risk predicted value of the declaration business data of the current business request end with a preset threshold value, if the declaration risk predicted value is smaller than the preset threshold value, allowing the current business request end to send the declaration business data to the receiver, otherwise, preventing the current business request end from sending the declaration business data to the receiver.
Specifically, the receiver is a party for issuing the reporting business policy, compares the reporting risk prediction value of the reporting business data of the current business request end with the preset threshold value, and allows the current business request end to send the reporting business data to the receiver if the reporting risk prediction value is smaller than the preset threshold value, otherwise, prohibits the current business request end from sending the reporting business data to the receiver, thereby improving the security of the reporting business data sent to the receiver, ensuring the security of the whole reporting business, and preventing the system from hidden troubles such as malicious invasion, data theft or data tampering.
And S5, calculating the matching degree value of the declaration service data and the declaration service policy of the service request terminal according to the declaration service data and the declaration index requirement data sent by the service request terminal.
As a specific embodiment of the invention, the method comprises the steps of receiving the declaration service data sent by a service request terminal, extracting declaration index requirement data from the issued declaration service policy based on a semantic identification method, and calculating the matching degree value of the declaration service data and the declaration service policy of an enterprise.
Wherein the reporting index requirement data includes: the type of business, the area to which the business belongs, the number of people in the business, the business turnover of the business, the duration of the establishment of the business, the credit level of the business, and the like.
The declaration service data sent by the service request terminal is actual data which is declared by the service request terminal and corresponds to the declaration index request data. For example: the declaration service data includes: the enterprise types are: a high-new enterprise; the area to which the enterprise belongs is: beijing city; the number of enterprises is: 100 persons; the business turnover of the enterprise is 1000 ten thousand; the establishment duration of the enterprise is 10 years; the credit rating of the enterprise is first class, etc.
Specifically, the calculation formula of the matching degree value of the declared business data and the declared business policy of the business request end is as follows:
；
Wherein, A matching degree value of the declaration service data and the declaration service policy of the service request terminal is represented; /(I)Representing the historical reporting success times of the service request end on the current reporting service policy; /(I)Representing the total reporting times of the service request end on the current reporting service policy; /(I)Representing the average reporting times of the service request end under the history reporting of the current reporting service policy; /(I)Representing natural constants; /(I)Representing the total category number of the declaration service data; /(I)Represents the/>Whether the reporting business data accords with the parameter factors of reporting index requirement data or not; if/>The species declaration business data accords with the declaration index requirement data, and/>; Otherwise,/>；/>The number of the declaration business data which accords with the numerical property in the declaration index requirement data in the declaration business data is represented; /(I)Represents the/>The weight of the business data influence is declared; /(I)Represents the/>Actual values of the individual declaration business data; /(I)Representing the corresponding/>, in the declaration index requirement dataThe lowest limit value of the business data is declared.
It should be explained that the declaration business data with numerical properties includes the following numbers of enterprises: 100 persons; the business turnover of the enterprise is 1000 ten thousand; the establishment time of the enterprise is 10 years.
And S6, storing the declaration service data to a first-stage audit passing storage area according to the sequence of the matching degree value from high to low.
The problem of low efficiency of reporting policies is solved; the efficiency and convenience of enterprise reporting policies can be improved.
As a specific embodiment of the invention, the matching degree value of the declaration business data and the declaration business policy is marked for each declaration business data through a storage area in the first level of examination.
And S7, checking and comparing the declaration service data in the first-stage audit passing storage area with enterprise business record information, performing second-stage audit operation, if the second-stage audit operation passes, storing the passing declaration service data in the second-stage audit passing storage area, and if not, storing the declaration service data in the second-stage audit exception storage area.
The enterprise business record information records the real enterprise data of the enterprise, and the method comprises the following steps: the number of enterprises, the type of the enterprises, the area to which the enterprises belong, the records of the enterprise violations, etc.
Specifically, the first-level audit passing storage area is checked and compared with the business record information of the enterprise, if the business data of the declaration is consistent with the business record information of the enterprise, the second-level audit passes, otherwise, the second-level audit does not pass.
Example two
As shown in FIG. 2, the present application provides an artificial intelligence based control system 100 comprising:
The semantic extraction module 10 is used for analyzing the issued declaration business policy based on a semantic recognition method and extracting declaration index requirement data;
The model acquisition module 20 is configured to perform training learning on the extracted declaration index requirement data based on a machine learning model, so as to obtain a data anomaly automatic recognition model;
The abnormality recognition module 30 is configured to perform abnormality recognition on the declared business data sent by the enterprise based on the data abnormality automatic recognition model, obtain a recognition result, perform security monitoring on the declared business data and a business request end that sends the declared business data if the recognition result is normal, and otherwise store the declared business data whose recognition result is abnormal into the first-stage audit abnormal storage area;
a data processor 40, configured to execute calculating a matching degree value of the declared business data and the declared business policy of the business request terminal according to the declared business data and the declared index requirement data sent by the business request terminal if the security monitoring passes;
The storage module 50 is used for storing the declaration service data to a first-level audit passing storage area according to the sequence of the matching degree values from high to low;
And the checking and comparing module 60 is used for checking and comparing the reporting business data in the first-stage checking and passing storage area with the enterprise business record information, performing second-stage checking operation, and if the second-stage checking operation is passed, storing the passing reporting business data in the second-stage checking and passing storage area, otherwise, storing the reporting business data in the second-stage checking and passing storage area.
Specifically, the calculation formula of the matching degree value of the declared business data and the declared business policy of the business request end is as follows:
；
Wherein, A matching degree value of the declaration service data and the declaration service policy of the service request terminal is represented; /(I)Representing the historical reporting success times of the service request end on the current reporting service policy; /(I)Representing the total reporting times of the service request end on the current reporting service policy; /(I)Representing the average reporting times of the service request end under the history reporting of the current reporting service policy; /(I)Representing natural constants; /(I)Representing the total category number of the declaration service data; /(I)Represents the/>Whether the reporting business data accords with the parameter factors of reporting index requirement data or not; if/>The species declaration business data accords with the declaration index requirement data, and/>; Otherwise,/>；/>The number of the declaration business data which accords with the numerical property in the declaration index requirement data in the declaration business data is represented; /(I)Represents the/>The weight of the business data influence is declared; /(I)Represents the/>Actual values of the individual declaration business data; /(I)Representing the corresponding/>, in the declaration index requirement dataThe lowest limit value of the business data is declared.
The embodiment of the invention provides a processor for processing the control method based on artificial intelligence.
In the embodiment of the invention, the processor may be an integrated circuit chip with signal processing capability. The Processor may be a general purpose Processor, a digital signal Processor (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field programmable gate array (Field Programmable GATE ARRAY, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The processor reads the information in the storage medium and, in combination with its hardware, performs the steps of the above method.
The storage medium may be memory, for example, may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory.
The nonvolatile Memory may be Read-Only Memory (ROM), programmable ROM (PROM), erasable Programmable ROM (z230078 f8xm2016. Eprom), electrically Erasable Programmable ROM (ELECTRICALLY EPROM EEPROM), or flash Memory. The volatile memory may be a random access memory (Random Access Memory, RAM for short) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as static random access memory (STATIC RAM, SRAM), dynamic random access memory (DYNAMIC RAM, DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate Synchronous dynamic random access memory (Double DATA RATE SDRAM, ddr SDRAM), enhanced Synchronous dynamic random access memory (ENHANCED SDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCHLINK DRAM, SLDRAM), and direct memory bus random access memory (Direct Rambus RAM, DRRAM).
The beneficial effects achieved by the application are as follows:
(1) The artificial intelligence control method of the reporting business primarily identifies abnormal conditions of the reporting business data, for example, certain data are found to be out of specification in the reporting process, and automatically gives out warnings or prompts, so that the reporting efficiency is improved, the labor cost is reduced, and the reporting accuracy and reliability can be improved.
(2) The application carries out risk identification on the reporting service data and the service request terminal, monitors and early warns in real time, calculates the reporting risk prediction value of the reporting service data of the service request terminal according to the risk characteristic data of the reporting service data and the risk situation characteristic data of the service request terminal, and allows the current service request terminal to send the reporting service data to the receiver if the reporting risk prediction value is smaller than the preset threshold value, otherwise, prohibits the current service request terminal from sending the reporting service data to the receiver, thereby improving the safety of the whole reporting service.
In the description of the present application, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the description of the present application, the word "for example" is used to mean "serving as an example, instance, or illustration. Any embodiment described as "for example" in this disclosure is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the application. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known structures and processes have not been described in detail so as not to obscure the description of the application with unnecessary detail. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
The foregoing description is only illustrative of the invention and is not to be construed as limiting the invention. Various modifications and variations of the present invention will be apparent to those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims (8)

1. An artificial intelligence-based control method is characterized by comprising the following steps:
analyzing the issued reporting business policy based on a semantic recognition method, and extracting reporting index requirement data;
training and learning the extracted reporting index requirement data based on a machine learning model to obtain a data abnormality automatic identification model;
Based on the data abnormality automatic identification model, carrying out abnormality identification on the declaration service data sent by an enterprise to obtain an identification result, if the identification result is normal, executing security monitoring on the declaration service data and a service request end for sending the declaration service data, otherwise, storing the declaration service data with abnormal identification result into a first-stage auditing abnormal storage area;
If the security monitoring is passed, executing the calculation of the matching degree value of the reporting service data and the reporting service policy of the service request terminal according to the reporting service data and the reporting index requirement data sent by the service request terminal;
Storing the declaration business data to a first-level auditing passing storage area according to the sequence of the matching degree value from big to small; marking the matching degree value of the reporting business data and the reporting business policy for each reporting business data in a first-level auditing through storage area;
Checking and comparing the reporting business data in the first-stage checking passing storage area with enterprise business record information, performing second-stage checking operation, if the second-stage checking operation passes, storing the passing reporting business data into a second-stage checking passing storage area, otherwise, storing the reporting business data into a second-stage checking abnormal storage area;
The calculation formula of the matching degree value of the declaration service data and the declaration service policy of the service request end is as follows:
；
Wherein, A matching degree value of the declaration service data and the declaration service policy of the service request terminal is represented; /(I)Representing the historical reporting success times of the service request end on the current reporting service policy; /(I)Representing the total reporting times of the service request end on the current reporting service policy; /(I)Representing the average reporting times of the service request end under the history reporting of the current reporting service policy; /(I)Representing natural constants; /(I)Representing the total category number of the declaration service data; /(I)Represents the/>Whether the reporting business data accords with the parameter factors of reporting index requirement data or not; if/>The species declaration service data accords with the declaration index requirement data, then; Otherwise,/>；/>The number of the declaration business data which accords with the numerical property in the declaration index requirement data in the declaration business data is represented; /(I)Represents the/>The weight of the business data influence is declared; /(I)Represents the/>Actual values of the individual declaration business data; /(I)Represents the/>The lowest limit value of the business data is declared.
2. The artificial intelligence based control method according to claim 1, wherein the method for security monitoring of the declared business data and the business request terminal transmitting the declared business data comprises the steps of:
performing risk identification on the declaration service data based on a pre-constructed data risk identification model, extracting risk characteristic data of the declaration service data, and acquiring risk situation characteristic data of a service request end for transmitting the declaration service data;
Calculating a declaration risk prediction value of declaration service data of the service request end according to the risk characteristic data of the declaration service data and the risk situation characteristic data of the service request end;
Comparing the declaration risk predicted value of the declaration business data of the current business request end with a preset threshold value, if the declaration risk predicted value is smaller than the preset threshold value, allowing the current business request end to send the declaration business data to the receiver, otherwise, preventing the security monitoring from being passed, and prohibiting the current business request end from sending the declaration business data to the receiver.
3. The artificial intelligence based control method of claim 1, wherein reporting the index requirement data comprises: the type of business, the area to which the business belongs, the number of people in the business, the business turnover of the business, the duration of the establishment of the business and the credit rating of the business.
4. The artificial intelligence based control method according to claim 1, wherein the first level audit passing storage area is checked and compared with the business record information of the enterprise, and if the business data of the declaration is consistent with the business record information of the enterprise, the second level audit passes, otherwise, the second level audit does not pass.
5. The artificial intelligence based control method of claim 1, further comprising: and carrying out classified recognition training on the declaration service data of the machine learning model, and recognizing classified information in the declaration service data.
6. The artificial intelligence based control method of claim 2, wherein reporting risk profile data of the business data comprises: illegal statements, malicious instructions, and malicious links.
7. The artificial intelligence based control method of claim 1, wherein the dangerous situation feature data of the service request terminal comprises: the method comprises the steps of service request end malicious instruction data and service request end malicious keyword data.
8. An artificial intelligence based control system, the system comprising:
The semantic extraction module is used for analyzing the issued declaration business policy based on a semantic recognition method and extracting declaration index requirement data;
The model acquisition module is used for training and learning the extracted declaration index requirement data based on a machine learning model to obtain a data abnormality automatic identification model;
The abnormality identification module is used for carrying out abnormality identification on the declaration service data sent by the enterprise based on the data abnormality automatic identification model, obtaining an identification result, if the identification result is normal, executing safety monitoring on the declaration service data and a service request end for sending the declaration service data, otherwise, storing the declaration service data with the abnormal identification result into the first-stage auditing abnormal storage area;
The data processor is used for executing the reporting service data and reporting index requirement data sent by the service request terminal and calculating the matching degree value of the reporting service data and the reporting service policy of the service request terminal if the safety monitoring is passed;
The storage module is used for storing the declaration business data to a first-level auditing passing storage area according to the sequence of the matching degree values from high to low; marking the matching degree value of the reporting business data and the reporting business policy for each reporting business data in a first-level auditing through storage area;
The verification comparison module is used for verifying and comparing the declaration service data in the first-stage verification passing storage area with the enterprise business record information, performing second-stage verification operation, and storing the passing declaration service data into the second-stage verification passing storage area if the second-stage verification operation passes, or storing the declaration service data into the second-stage verification abnormal storage area if the second-stage verification operation passes;
The calculation formula of the matching degree value of the declaration service data and the declaration service policy of the service request end is as follows:
；
Wherein, A matching degree value of the declaration service data and the declaration service policy of the service request terminal is represented; /(I)Representing the historical reporting success times of the service request end on the current reporting service policy; /(I)Representing the total reporting times of the service request end on the current reporting service policy; /(I)Representing the average reporting times of the service request end under the history reporting of the current reporting service policy; /(I)Representing natural constants; /(I)Representing the total category number of the declaration service data; /(I)Represents the/>Whether the reporting business data accords with the parameter factors of reporting index requirement data or not; if/>The species declaration service data accords with the declaration index requirement data, then; Otherwise,/>；/>The number of the declaration business data which accords with the numerical property in the declaration index requirement data in the declaration business data is represented; /(I)Represents the/>The weight of the business data influence is declared; /(I)Represents the/>Actual values of the individual declaration business data; /(I)Represents the/>The lowest limit value of the business data is declared.
CN202311726390.6A 2023-12-15 2023-12-15 Control method and system based on artificial intelligence Active CN117436820B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311726390.6A CN117436820B (en) 2023-12-15 2023-12-15 Control method and system based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311726390.6A CN117436820B (en) 2023-12-15 2023-12-15 Control method and system based on artificial intelligence

Publications (2)

Publication Number Publication Date
CN117436820A CN117436820A (en) 2024-01-23
CN117436820B true CN117436820B (en) 2024-04-30

Family

ID=89548325

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311726390.6A Active CN117436820B (en) 2023-12-15 2023-12-15 Control method and system based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN117436820B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109242326A (en) * 2018-09-19 2019-01-18 江苏风云科技服务有限公司 A kind of policy shared system based on big data and artificial intelligence
CN110619574A (en) * 2019-09-23 2019-12-27 中国工商银行股份有限公司 Remittance data processing method, remittance data processing apparatus, electronic device, and storage medium
CN113706056A (en) * 2021-09-23 2021-11-26 常州市公共资源交易中心 Bidding unit performance identification early warning method, device, equipment and storage medium
CN115456438A (en) * 2022-09-22 2022-12-09 城云科技（中国）有限公司 Enterprise operation behavior abnormity early warning method and application thereof
CN115936438A (en) * 2022-12-24 2023-04-07 航天信息股份有限公司 Early warning method and system for enterprise tax wind control
CN116385193A (en) * 2023-04-03 2023-07-04 山东省计量科学研究院 Automatic account setting processing method and system based on artificial intelligence

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109242326A (en) * 2018-09-19 2019-01-18 江苏风云科技服务有限公司 A kind of policy shared system based on big data and artificial intelligence
CN110619574A (en) * 2019-09-23 2019-12-27 中国工商银行股份有限公司 Remittance data processing method, remittance data processing apparatus, electronic device, and storage medium
CN113706056A (en) * 2021-09-23 2021-11-26 常州市公共资源交易中心 Bidding unit performance identification early warning method, device, equipment and storage medium
CN115456438A (en) * 2022-09-22 2022-12-09 城云科技（中国）有限公司 Enterprise operation behavior abnormity early warning method and application thereof
CN115936438A (en) * 2022-12-24 2023-04-07 航天信息股份有限公司 Early warning method and system for enterprise tax wind control
CN116385193A (en) * 2023-04-03 2023-07-04 山东省计量科学研究院 Automatic account setting processing method and system based on artificial intelligence

Also Published As

Publication number Publication date
CN117436820A (en) 2024-01-23

Similar Documents

Publication Publication Date Title
CN109829776B (en) Merchant risk assessment method, device, computer equipment and storage medium
CN110489415B (en) Data updating method and related equipment
CN101902366A (en) Method and system for detecting abnormal service behaviors
CN110493181B (en) User behavior detection method and device, computer equipment and storage medium
CN109145030B (en) Abnormal data access detection method and device
CN109242658B (en) Suspicious transaction report generation method, suspicious transaction report generation system, suspicious transaction report generation computer device and suspicious transaction report storage medium
CN112712429A (en) Remittance service auditing method, remittance service auditing device, computer equipment and storage medium
CN113067820A (en) Method, device and equipment for early warning abnormal webpage and/or APP
CN111222784A (en) Security monitoring method and system based on population big data
CN110009224A (en) Suspect's violation probability prediction technique, device, computer equipment and storage medium
US20130325731A1 (en) Systems and methods for providing organizational compliance monitoring
CN112308638A (en) False invoice behavior detection method and device, electronic equipment and storage medium
CN115564449A (en) Risk control method and device for transaction account and electronic equipment
CN117216801A (en) Enterprise financial data safety management system and method based on artificial intelligence
CN117436820B (en) Control method and system based on artificial intelligence
CN114978474A (en) Method and system for automatically handling user chat risk level
CN114626863A (en) Detection method, device, equipment and storage medium for export tax cheating enterprise
CN114429283A (en) Risk label processing method and device, wind control method and device and storage medium
CN113449059A (en) Event processing method, device, equipment and storage medium
CN110738570A (en) Information type manipulation automatic identification method based on multi-channel heterogeneous data
CN112256988A (en) Method and device for monitoring cross-border house-buying website, electronic equipment and storage medium
CN111914542A (en) Suspected illegal investment market subject identification method, device, terminal and storage medium
CN116862669B (en) Vehicle loan data analysis method, system and medium
CN115908026A (en) Tax information analysis method and device, electronic equipment and storage medium
CN114758457B (en) Intelligent monitoring method and device for illegal operation among banknote adding

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