CN109446188B - Tracking and auditing method based on big data and deep learning and robot system - Google Patents

Abstract

A tracking and auditing method based on big data and deep learning and a robot system comprise the following steps: acquiring an audit standard of a preset category, acquiring data of an object to be audited, acquiring data corresponding to the audit standard from the data of the object, comparing the data corresponding to the audit standard of the object to be audited with the data corresponding to the audit standard of the object to be audited during the last audit, and judging whether a change occurs: if yes, the step of tracking audit judgment is carried out; otherwise, the step of copying the audit result is executed. The method and the system improve the timeliness, objectivity, reliability and efficiency of audit and reduce the audit cost through the audit tracking technology based on big data and deep learning.

Description

Tracking and auditing method based on big data and deep learning and robot system

Technical Field

The invention relates to the technical field of information, in particular to a big data and deep learning based tracking and auditing method and a robot system.

Background

In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art: in the prior art, auditing (such as financial auditing, benefit auditing and the like) is performed once, and is not tracked after the auditing is completed, some objects (including enterprises, individuals and the like) may pass through the auditing process, but once the objects pass through the auditing process, the objects do not have auditing pressure any more, and the requirements on the objects are relaxed, so that the auditing requirements may not be met any more within a period of time after the auditing is passed, but the result of the previous auditing is not influenced, and the auditing result does not have timeliness, namely, the result of the past auditing is not always met the actual condition of the objects, so that the auditing loses credibility and significance; some objects strive to obtain after the audit is not passed, and after a certain time of effort, although the objects reach the audit standard, the objects are dared not to apply for the audit again all the time because of the failure of the previous audit, even the objects lose confidence and do not apply for the audit all the time because of the failure of the previous audit, so that the objects which reach the audit standard are in an un-audited state all the time because of the failure of applying for the audit again, and the audit result is incomplete; in summary, existing auditing techniques result in objects that no longer meet the auditing criteria still maintaining an audited result; but the object which meets the auditing standard still keeps the result that the auditing is not passed, so that the auditing result can not be advanced all the time, and the timeliness, objectivity and credibility of the audited result are lost; in the prior art, most audit-passing results are permanently effective, so that the defects are very obvious as described above, and a few audit-passing results are effective within a certain period of time (for example, several years), and need to be audited again after expiration, which still cannot solve the above-described defects because the effective period of time is generally relatively long, and objects change greatly during that period of time, and are likely to change from meeting the audit standard to not meeting the audit standard, thereby still causing the audit results to lose timeliness, objectivity and credibility; meanwhile, on the other hand, the result of the audit is only valid within a certain period of time, and the audit needs to be reapplied after the result is expired, which wastes time, manpower and material resources of the audited object to reapply the audit and wastes time, manpower and material resources of an audit administration unit, because the audit does not need to be reapplied if the data change of the audited object does not affect the result of the audit, the cost and the efficiency of the existing audit technology are high; the third aspect is also the most important aspect, in the prior art, auditing is performed at the auditing time specified by the auditing administration, so that the audited objects are not stressed and do not make effort at ordinary times, and the temporary effort is useless even after the auditing time is too late, so that some audited objects go to risk in order to pass the auditing, and illegal behaviors such as finding relations, making mistakes and the like are made.

Accordingly, the prior art is yet to be improved and developed.

Disclosure of Invention

Based on this, it is necessary to provide a tracking and auditing method and a robot system based on big data and deep learning to solve the defects of timeliness, objectivity, reliability, accuracy, high cost and low efficiency of auditing in the prior art.

In a first aspect, an embodiment of the present invention provides an auditing method, where the method includes:

an audit standard obtaining step, which is used for obtaining the audit standard of the preset category;

an object data acquisition step, which is used for acquiring the data of an object to be audited; the acquired data comprises third-party data, and the data is more objective and feasible, so that the objectivity and the credibility of audit can be improved; if the data is not objective, the audit cannot be accurate, and the accuracy is improved because the data is more objective;

a data acquisition step corresponding to a standard, which is used for acquiring data corresponding to the audit standard from the data of the object to be audited;

a data change detection step, configured to compare data corresponding to the audit standard of the object to be audited with data corresponding to the audit standard of the object to be audited during the last audit, and determine whether a change has occurred: if yes, the step of tracking audit judgment is carried out; if not, the step of copying the audit result is executed;

a tracking audit judgment step for judging whether the data corresponding to the audit standard meets the audit standard;

an auditing result copying step, which is used for taking the last auditing result of the object to be audited as the auditing result of the object to be audited;

and a tracking control step, which is used for acquiring a preset time period or a preset time point, and re-executing all steps in the auditing method every other preset time period or when the preset time point is reached. Whether the object to be audited applies for auditing or not, the audit is regularly tracked, so that the timeliness of the audit can be improved, the audit can be more consistent with the real-time condition of the object, and the audit result is more credible and accurate. Meanwhile, after the audit is over, the object passing the audit trail does not need to be audited manually again, so that the cost is reduced.

Preferably, the method further comprises:

a result feedback step, which is used for judging the change of the auditing result and sending the change to the object to be audited;

and early warning step, which is used for judging whether the number of times that the object to be audited fails to pass the audit in the current continuous and multiple times of tracking audit reaches a threshold value: and if yes, early warning is carried out.

Preferably, the object data acquiring step includes:

a data source obtaining step for obtaining a data source;

an object data retrieval step, which is used for retrieving and acquiring the data of the object to be audited from the data source;

the data acquisition step corresponding to the standard comprises the following steps:

a data screening step, which is used for screening out data corresponding to the auditing standard from the data of the object to be audited as first data;

and a data cleaning step, which is used for extracting data corresponding to each standard from the first data as second data corresponding to each standard.

Preferably, the first and second electrodes are formed of a metal,

the result feedback step includes:

comparing and judging whether the result of the object to be audited in the current audit and the result of the object to be audited in the last audit are changed: if yes, informing the changed result to the object to be audited, and judging whether the result of the audit is that the audit is passed:

if so, informing the object to be audited that the object to be audited has passed the audit or informing the object to be audited to invite the object to be audited to go through the process of applying for audit. Because the automatic judgment is carried out by the system, and some administrative procedures are required in the actual auditing process, for example, some application materials for unit sealing of the object to be audited, some types of auditing need to inform the object to be audited to go through the process of applying for auditing;

if not, informing the object to be audited to carry out rectification and waiting for next tracking audit, feeding back a result of audit which does not pass through the preset type of audit to the object to be audited, obtaining each standard or overall standard which is not in conformity with the target to be audited, feeding back the standard or overall standard which is not in conformity with the target to be audited, and sending information to remind the object to be audited to carry out rectification aiming at each standard or overall standard which is not in conformity with the target to be audited;

the early warning step comprises the following steps: acquiring a preset first frequency, and judging whether the frequency of the object to be audited, which does not pass the audit in the current continuous multi-time tracking audit, reaches the preset first frequency:

if yes, sending information to inform the object to be audited of relevant investigation and punishment, and sending information to inform relevant departments of investigating and punishment on the object to be audited;

if not, judging whether the number of times that the audit of the object to be audited in the current continuous and multiple audit trails reaches a preset second number of times or not: if yes, sending information to inform the object to be audited of early warning, and sending information to inform the object to be audited of rectification or else, after reaching the first times, being subjected to relevant investigation and punishment.

Preferably, the first and second electrodes are formed of a metal,

the tracking audit judgment step comprises the following steps:

a sub-standard obtaining step, which is used for obtaining each standard and the overall standard in the auditing standard;

a corresponding data extracting step, configured to extract the second data corresponding to each criterion from the first data;

a corresponding data change detection step, configured to compare second data corresponding to each standard of the object to be audited with second data corresponding to each standard of the object to be audited during the last audit, and determine whether a change occurs: if yes, executing a preset model obtaining step or each standard judging step corresponding to each standard; if not, jumping to a corresponding data extraction step or a preset model acquisition step corresponding to the overall standard for execution;

a preset model obtaining step corresponding to each standard, which is used for obtaining a preset model corresponding to each standard;

a third data generation step corresponding to each standard, wherein the third data generation step is used for calculating to obtain third data corresponding to each standard according to the second data corresponding to each standard and the preset model corresponding to each standard;

each standard judging step is used for judging whether the object to be audited meets each standard or not according to the third data corresponding to each standard, a preset range and a preset range;

a preset model obtaining step corresponding to the overall standard, which is used for obtaining a preset model corresponding to the overall standard;

a total standard judging step, configured to judge whether the object to be audited meets the total standard according to the third data corresponding to each standard, the preset model corresponding to the total standard, and the preset range;

and a comprehensive judgment step for judging whether the object to be audited meets each standard and the overall standard in the auditing standard.

Preferably, the first and second electrodes are formed of a metal,

the preset model acquisition step corresponding to each standard comprises the following steps:

a deep learning model initialization step corresponding to each standard, which is used for initializing the deep learning model corresponding to each standard as a first deep learning model;

a historical data acquisition step corresponding to each standard, which is used for acquiring the second data and the third data of each object which is subjected to auditing and corresponds to each standard from historical big data;

a second deep learning model generation step, configured to use the second data of each object, which is subjected to auditing and corresponds to each standard, as input data of the first deep learning model, perform unsupervised training on the first deep learning model, and use the obtained first deep learning model as a second deep learning model;

a third deep learning model generation step, configured to respectively use the second data and the third data of each object, which is subjected to auditing and corresponds to each standard, as input data and output data of the second deep learning model, perform supervised training on the second deep learning model, and use the obtained second deep learning model as a third deep learning model;

a preset model setting step corresponding to each standard, which is used for taking the third deep learning model as a preset model corresponding to each standard;

the step of obtaining the preset model corresponding to the overall standard comprises the following steps:

a deep learning model initialization step corresponding to an overall standard, which is used for initializing the deep learning model corresponding to the overall standard, and taking the obtained deep learning model as a fourth deep learning model;

a historical data acquisition step corresponding to an overall standard, which is used for acquiring a set of third data corresponding to each standard in the auditing standard of each object which is audited and third data corresponding to the overall standard from historical big data;

a fifth deep learning model generation step, configured to use the set of the third data of each object that has undergone audit and corresponds to each standard in the audit standards as input data of the deep learning model, perform unsupervised training on the fourth deep learning model, and use the obtained fourth deep learning model as a fifth deep learning model;

a sixth deep learning model generation step of taking the set of the third data corresponding to each standard in the audit standard of each object that has been audited and the third data corresponding to the overall standard as input data and output data of the fifth deep learning model, respectively, performing supervised training on the fifth deep learning model, and taking the obtained fifth deep learning model as a sixth deep learning model;

and a preset model setting step corresponding to the overall standard, wherein the preset model setting step is used for taking the sixth deep learning model as a preset model corresponding to the overall standard.

Preferably, the first and second electrodes are formed of a metal,

each standard judging step comprises the following steps:

a preset range acquisition step corresponding to each standard, which is used for acquiring the preset range corresponding to each standard;

a third data judgment step corresponding to each standard, which is used for judging whether the object to be audited meets each standard;

a change reminding step corresponding to each standard, which is used for judging whether the object to be audited is changed in the aspect of meeting each standard or not and sending change information to the object to be audited;

the overall standard judging step comprises the following steps:

a third data generation step corresponding to the overall standard, configured to calculate third data corresponding to the overall standard according to the third data corresponding to each standard and the preset model corresponding to the overall standard;

a preset range acquisition step corresponding to the overall standard, which is used for acquiring the preset range corresponding to the overall standard;

and a third data judgment step corresponding to the overall standard, which is used for judging whether the object to be audited meets the overall standard.

In a second aspect, an embodiment of the present invention provides an auditing system, where the system includes:

the audit standard acquisition module is used for acquiring the audit standard of a preset category;

the object data acquisition module is used for acquiring data of an object to be audited;

the data acquisition module corresponding to the standard is used for acquiring data corresponding to the audit standard from the data of the object to be audited;

a data change detection module, configured to compare data corresponding to the audit standard of the object to be audited with data corresponding to the audit standard of the object to be audited during the last audit, and determine whether a change occurs: if yes, the operation is carried out by a tracking audit judgment module; if not, the operation is transferred to a module for copying an audit result for execution;

the tracking and auditing judgment module is used for judging whether the data corresponding to the auditing standard meets the auditing standard or not;

the replication auditing result module is used for taking the last auditing result of the object to be audited as the auditing result of the object to be audited;

the result feedback module is used for judging the change of the auditing result and sending the change to the object to be audited;

the early warning module is used for judging whether the number of times that the audit of the object to be audited fails in the current continuous and multiple times of audit tracking reaches a threshold value: if yes, early warning is carried out;

and the tracking control module is used for acquiring a preset time period or a preset time point and re-executing all modules in the auditing system every other preset time period or when the preset time point is reached.

Preferably, the first and second electrodes are formed of a metal,

the object data acquisition module includes:

the data source acquisition module is used for acquiring a data source;

the object data retrieval module is used for retrieving and acquiring the data of the object to be audited from the data source;

the data acquisition module corresponding to the standard comprises:

the data screening module is used for screening out data corresponding to the auditing standard from the data of the object to be audited as first data;

the data cleaning module is used for extracting data corresponding to each standard from the first data to serve as second data corresponding to each standard;

the tracking audit judgment module comprises:

the sub-standard acquisition module is used for acquiring each standard and the overall standard in the audit standard;

a corresponding data extraction module, configured to extract the second data corresponding to each criterion from the first data;

a corresponding data change detection module, configured to compare second data corresponding to each standard of the object to be audited with second data corresponding to each standard of the object to be audited during the last audit, and determine whether a change occurs: if yes, jumping to a preset model acquisition module corresponding to each standard or executing by each standard judgment module; if not, jumping to a corresponding data extraction module or a preset model acquisition module corresponding to the overall standard for execution;

the preset model acquisition module corresponding to each standard is used for acquiring a preset model corresponding to each standard;

the third data generation module corresponding to each standard is used for calculating to obtain third data corresponding to each standard according to the second data corresponding to each standard and the preset model corresponding to each standard;

each standard judging module is used for judging whether the object to be audited meets each standard or not according to the third data corresponding to each standard, a preset range and a preset range;

the preset model acquisition module corresponding to the overall standard is used for acquiring a preset model corresponding to the overall standard;

the overall standard judging module is used for judging whether the object to be audited meets the overall standard or not according to the third data corresponding to each standard, the preset model corresponding to the overall standard and the preset range;

and the comprehensive judgment module is used for judging whether the object to be audited meets each standard and the overall standard in the auditing standard.

In a third aspect, an embodiment of the present invention provides a robot system, where the auditing systems of the second aspect are respectively configured in the robots.

The embodiment of the invention has the advantages and beneficial effects that:

1. the embodiment of the invention automatically tracks and audits the enterprise which has been audited regularly or irregularly or in real time, and can detect whether the object still meets the requirement of auditing in the time after auditing, thereby updating the auditing result, leading the auditing result to have timeliness, and updating the auditing result when the past auditing result does not meet the actual condition of the object. However, in the prior art, auditing (for example, high and new enterprise auditing, talent auditing, etc.) is performed once, and an object may no longer meet the auditing requirement within a period of time after the auditing is passed, but the result of the previous auditing is not affected, so that the auditing result does not have timeliness, that is, the result of the past auditing does not necessarily meet the actual condition of the object, so that the auditing loses credibility and significance.

2. The embodiment of the invention also carries out tracking and auditing on the object which does not pass the auditing, and actively invites the object to reapply the auditing or directly passes the object and already passes the auditing once the object is found to meet the auditing standard, thereby ensuring that the auditing result is more comprehensive. However, some objects in the prior art strive to obtain after the audit is not passed, and after a certain time of effort, although the object reaches the audit standard, because the previous audit fails, the object dares not to apply for the audit again all the time, and even possibly, because the previous audit fails, the object loses confidence and does not apply for the audit any more, so that the object reaching the audit standard is in an un-audited state all the time because the object does not apply for the audit again, and the audit result is incomplete.

3. The embodiment of the invention informs the object to modify only when the object which passes the audit does not accord with the standard of the audit any more in the development process, which can remind the enterprise to modify automatically on the one hand, and saves the time, manpower and material resources of the object on the other hand. In the prior art, the result of the audit is only effective within a certain time period, and the audit needs to be reapplied after expiration, so that the time and the manpower and the material resources of the audited object are wasted to reapply the audit, and the time and the manpower and the material resources of an audit administration unit are wasted.

4. The embodiment of the invention continuously performs the tracking audit at ordinary times to continuously remind the objects which have certain standards and do not pass the audit or do not pass the audit totally to perform rectification, thereby avoiding the tragedy situation that the objects can not pass the audit finally, so the tracking audit is helpful for the audited objects to pass the audit finally, the obtaining feeling and the safety feeling of the audited objects can be improved, and the possibility of illegal behaviors of finding relations, making mistakes and the like of the audited objects for passing the audit is reduced. However, in the prior art, auditing is carried out at the auditing time specified by the auditing administration, so that the audited objects are not stressed and do not make effort at ordinary times, and the temporary effort is useless even after the auditing time is too late, so that some audited objects are in danger for auditing and do illegal behaviors such as finding relations, making fake and the like.

5. The embodiment of the invention can assist the auditing of the auditing experts by tracking the auditing result:

(1) the embodiment of the invention judges whether the object can be audited to the preset category by intelligently analyzing based on the big data and the audit standard so as to assist the auditing of the expert, thereby reducing the workload of auditing by the auditing expert and improving the efficiency of auditing by the auditing expert.

(2) The embodiment of the invention adopts a deep learning technology to automatically generate the preset model for auditing based on historical big data, and can further improve the intelligence and accuracy of auditing.

(3) According to the embodiment of the invention, the data and the objects which meet the preset type audit standard can be screened out through the audit method and the audit system for reference of the audit expert, so that the audit speed of the audit expert can be improved, and the audit workload of the audit expert can be reduced.

(4) According to the embodiment of the invention, the data and the object which do not accord with the preset type audit standard can be screened out through the audit method and the audit system to be referred by the audit expert, so that the audit expert can carry out more strict audit on the data and the object which do not accord with the conditions, and the audit accuracy is improved.

The embodiment of the invention provides a big data and deep learning-based tracking and auditing method and a robot system, which comprise the following steps: acquiring an audit standard of a preset category, acquiring data of an object to be audited, acquiring data corresponding to the audit standard from the data of the object, comparing the data corresponding to the audit standard of the object to be audited with the data corresponding to the audit standard of the object to be audited during the last audit, and judging whether a change occurs: if yes, the step of tracking audit judgment is carried out; otherwise, the step of copying the audit result is executed. The embodiment of the invention can timely update the auditing result according to the actual data of the object in real time and remind the object to carry out rectification or invite the object to apply for auditing again. The method and the system improve the timeliness, objectivity, reliability and efficiency of audit and reduce the audit cost through the audit tracking technology based on big data and deep learning.

Drawings

FIG. 1 is a flow chart of an auditing method provided by embodiment 1 of the present invention;

FIG. 2 is a flowchart of the trace audit determination steps provided in embodiment 4 of the present invention;

fig. 3 is a flowchart of a preset model obtaining step corresponding to each criterion according to embodiment 5 of the present invention;

fig. 4 is a flowchart of a preset model obtaining step corresponding to the overall standard provided in embodiment 5 of the present invention;

FIG. 5 is a functional block diagram of an audit system provided by embodiment 7 of the present invention;

FIG. 6 is a block diagram of a trace audit determination module provided in embodiment 10 of the present invention;

fig. 7 is a schematic block diagram of a preset model obtaining module corresponding to each standard according to embodiment 11 of the present invention;

fig. 8 is a schematic block diagram of a preset model obtaining module corresponding to the overall standard according to embodiment 11 of the present invention.

Detailed Description

The technical solutions in the examples of the present invention are described in detail below with reference to the embodiments of the present invention.

The methods in various embodiments of the present invention include various combinations of the following steps:

an audit standard acquisition step S100: and acquiring the audit standard of a preset category.

The preset type audit standard is a standard used for carrying out preset type audit on an object, such as financial audit, project audit, benefit audit, innovation level audit, project audit, system audit and the like on an enterprise object. The preset categories are financial, benefit and the like, and the auditing of the preset categories is financial auditing, benefit auditing and the like.

Object data acquisition step S200: and acquiring data of the object to be audited. The object to be audited refers to the object to be tracked and audited. Such as a business, an individual, etc. For example, it is necessary to audit whether the financial use of an enterprise is in compliance, whether an individual financial use is in compliance, whether an enterprise innovation capability is in preparation for a new enterprise, and the like. The objects to be audited comprise objects which are audited and audited to pass, objects which are audited and audited to fail, and objects which are not audited to pass. The object to be audited can be the object applying for auditing or the object not applying for auditing. When the object to be audited is tracked and audited, the object to be audited does not need to apply for auditing; whether the object to be audited applies for auditing or not, the object to be audited is subjected to tracking auditing at intervals.

The object data acquisition step S200 includes a data source acquisition step S210 and an object data retrieval step S220.

Data source acquisition step S210: a data source is acquired. The data source comprises data provided by an object and data provided by a third party. Object provided data refers to data provided by the object. The data provided by the third party comprises object data stored by government departments, industry associations, intellectual property offices and the like. The data source is provided by a data retrieval and acquisition interface. The relevant data can be retrieved and acquired automatically by the computer program through the interface. The data source is generally an online data source, and data in the online data source can be remotely acquired through the internet. The data source may include a plurality of data sources distributed in different departments.

Object data retrieval step S220: data for the object is retrieved and acquired from a data source. Because the data source contains many object data and other data, if the data source is obtained as a whole and then retrieved, it will take too much network transmission time, so the object data needs to be retrieved first, and then the object data needs to be obtained locally. When there are multiple data sources, the data of the object is retrieved from the multiple data sources respectively and then downloaded to the local.

Data acquisition step S300 corresponding to the standard: and acquiring data corresponding to the audit standard from the data of the object to be audited.

The data acquiring step S300 corresponding to the standard includes a data filtering step S310 and a data cleaning step S320.

Data filtering step S310: and screening out first data corresponding to the object from the data of the object according to the auditing standard. The data of the object includes various data, wherein the data is not necessarily related to the preset category audit standard, so that the data related to the preset category audit standard needs to be retrieved from the data of the object as the first data corresponding to the object. The preset type audit standard has a plurality of items, data corresponding to each item of standard may be in different data sources, for example, financial data is in a data source provided by an industrial and commercial department, intellectual property data is in a data source provided by an intellectual property office, quality inspection data is in a data source provided by a quality inspection department, and safety data is in a data source provided by a public security department. For example, the data source provided by the intellectual property department corresponds to an intellectual property standard, the data source provided by the intellectual property department includes payment data, application data, acceptance data and authorization data of the intellectual property of the object, wherein the three categories of data of the application data, the acceptance data and the authorization data are related to the intellectual property standard audited in a preset category, and then the corresponding relationship is established between the three categories of data and the intellectual property standard audited in the preset category in the data source provided by the intellectual property department as the preset corresponding relationship.

Data cleaning step S320: and extracting second data corresponding to each standard from the first data. And taking the data corresponding to each standard in the first data as second data. Judging whether second data corresponding to each standard exists or not: if not, sending reminding information of the second data corresponding to each item of standard which is lacked to the user; if yes, judging whether the second data corresponding to each standard is unique: if not, judging whether the plurality of second data corresponding to each standard are consistent: and if not, retaining the second data with the highest credibility in the plurality of second data, and deleting other second data in the plurality of second data. The second data corresponding to the each criterion extracted from the first data is the data corresponding to the each criterion in the first data.

In the data cleaning step S320, the step of retaining the second data with the highest reliability in the plurality of second data, and the step of deleting other second data in the plurality of second data include a corresponding data source obtaining step S321, a reliability obtaining step S322, and a reliability selecting step S323.

Corresponding data source acquisition step S321: and acquiring a data source corresponding to each second data in the plurality of second data. Because the first data is obtained from the data source and the second data is extracted from the first data, the data source corresponding to each second data can be obtained.

Confidence level acquisition step S322: and acquiring the credibility of the data source corresponding to each second data. The confidence level may be preset. For example, the credibility of the data source of the police department is 100%, the credibility of the data source of the industrial and commercial department is 99%, the credibility of the data source of the intellectual property department is 98%, and the credibility of the data source provided by the object itself is 80%. The method for presetting the credibility comprises the steps of setting the credibility by an expert and automatically generating the credibility.

The step of automatically generating the reliability in the reliability obtaining step S322 includes: the trustworthiness of all data sources is initialized to an initial value, e.g. 50%. And acquiring the first data and the cleaned second data of each object from the historical big data. Increasing the credibility of the data source corresponding to the cleaned second data by a preset value, increasing the credibility of the data source corresponding to other second data in the first data, which is consistent with the cleaned second data, by a preset value, for example, 0.1%, and reducing the credibility of the data source corresponding to other second data in the first data, which is inconsistent with the cleaned second data, by a preset value, for example, 0.05%. When the credibility of the data source corresponding to the second data reaches 100%, no preset value is added; and when the credibility of the data source corresponding to the second data is reduced to 0%, no preset value is built. Therefore, the credibility of different data sources can be increased or decreased according to whether the historical second data is correct or not, and different credibility of different data sources is formed. The second data obtained by cleaning refers to correct second data confirmed by manual mode or other modes. Therefore, when the preset category is checked for many times before the credibility of each data source is not clear, the data needs to be cleaned manually, and then the credibility of each data source can be analyzed and obtained according to the historical data.

Reliability selecting step S323: and selecting the highest credibility from the credibility of the data source corresponding to each second data. And reserving second data corresponding to the highest reliability in the plurality of second data, and deleting other second data except the second data corresponding to the highest reliability in the plurality of second data. This makes it possible to retain the most reliable data and delete the other conflicting data when a plurality of second data conflicts with each other.

Data change detection step S400: judging whether the object to be audited is audited before the audit:

if yes, comparing the data corresponding to the audit standard of the object to be audited with the data corresponding to the audit standard of the object to be audited during the last audit and judging whether the data change occurs: if yes, the step S500 of tracking audit judgment is carried out; if not, the step S600 of copying the audit result is executed;

if not (under the condition of not being audited), the process goes to the tracking and auditing judgment step S500 to execute. If the object to be audited is not audited before the audit, the audit is the first audit, the last audit does not exist, and the audit cannot be compared with the last audit naturally, so that if the audit is the first audit of the object to be audited, the step is switched to the tracking audit judgment step S500 to be executed.

A tracking audit judgment step S500: judging whether the data corresponding to the audit standard meets the audit standard: if yes, judging that the object to be audited passes the audit of the preset category; and if not, judging that the object to be audited does not pass the audit of the preset category.

The audit judgment step S500 includes a sub-standard acquisition step S510, a corresponding data extraction step S520, a corresponding data change detection step S530, a preset model acquisition step S540 corresponding to each standard, a third data generation step S550 corresponding to each standard, a judgment step S560 for each standard, a preset model acquisition step S570 corresponding to an overall standard, an overall standard judgment step S580, and a comprehensive judgment step S590.

Sub-standard acquisition step S510: and acquiring each standard and the overall standard in the audit standard.

Corresponding data extraction step S520: and extracting second data corresponding to each standard from the first data.

Corresponding data change detection step S530: comparing the second data corresponding to each standard of the object to be audited with the second data corresponding to each standard of the object to be audited during the last audit, and judging whether the change occurs:

if yes, judging whether second data corresponding to each standard exists: if yes, jumping to S540 to continue execution; otherwise, setting the third data corresponding to each standard to be null, and then jumping to S560 to continue execution.

If not, obtaining the result whether the last time of the object to be audited meets each standard as the result whether the current time of the object to be audited meets each standard, and then not continuing to execute S540, S550 and S560. Whether the last time of the object to be audited meets the result of each standard or not comprises meeting and not meeting.

A preset model obtaining step S540 corresponding to each standard: and acquiring a preset model corresponding to each standard. The preset model comprises a formula or an algorithm or a deep learning model.

When the preset model is a deep learning model, the preset model obtaining step S540 corresponding to each standard includes a deep learning model initializing step S541 corresponding to each standard, a historical data obtaining step S542 corresponding to each standard, a second deep learning model generating step S543, a third deep learning model generating step S544, and a preset deep learning model setting step S545 corresponding to each standard.

Initializing a deep learning model corresponding to each standard, setting an input format of the deep learning model as a format of second data corresponding to each standard, setting an output format of the deep learning model as a format of third data corresponding to each standard, and taking the deep learning model obtained through initialization as a first deep learning model.

A history data acquiring step S542 corresponding to each criterion: and acquiring second data and third data of each object which is subjected to auditing and corresponds to each standard from historical big data. Historical big data refers to a large amount of historical data or data accumulated for a long time. The objects to be audited comprise objects which have been audited to pass and objects which have been audited but have not passed. The third data may be a score or an evaluation result corresponding to each criterion or other numerical values reflecting the degree of the second data meeting each criterion. The degree may be a percentage, e.g., 0% to 100%, 0% indicating complete non-compliance, and 100% indicating complete compliance.

And a second deep learning model generation step S543 of taking second data of each object which is subjected to auditing and corresponds to each standard as input data of the first deep learning model, carrying out unsupervised training on the first deep learning model, and taking the first deep learning model obtained through unsupervised learning as the second deep learning model.

And a third deep learning model generation step S544, wherein the second data and the third data of each object which is subjected to auditing and corresponds to each standard are respectively used as input data and output data of the second deep learning model, and the second deep learning model is subjected to supervised training. And respectively taking the second data and the third data of each object subjected to auditing and corresponding to each standard as input data and output data of the second deep learning model, namely taking the second data of each object subjected to auditing and corresponding to each standard as the input data of the second deep learning model, taking the third data of each object subjected to auditing and corresponding to each standard as the output data of the second deep learning model, and taking the second deep learning model obtained through supervised learning as the third deep learning model.

A step S545 of setting a preset model corresponding to each standard: and taking the third deep learning model as a preset model corresponding to each standard.

And a third data generation step S550 corresponding to each standard, wherein the third data corresponding to each standard is obtained through calculation according to the second data corresponding to each standard and the preset model corresponding to each standard. Executing the preset model corresponding to each standard on a computer, taking the second data corresponding to each standard as the input of the preset model corresponding to each standard, and taking the calculated output as the third data corresponding to each standard. Preferably, the second data corresponding to each criterion is used as the input of the third deep learning model corresponding to each criterion, and the calculated output of the third deep learning model is used as the third data corresponding to each criterion. The third data may be a score or an evaluation result corresponding to each criterion or other numerical values reflecting the degree of the second data meeting each criterion.

And step S560, judging whether the object to be audited meets each standard according to the third data and the preset range corresponding to each standard.

Each criterion determining step S560 includes a preset range acquiring step S561 corresponding to each criterion, a third data determining step S562 corresponding to each criterion, and a change reminding step S563 corresponding to each criterion.

A preset range obtaining step S561 corresponding to each standard, obtaining a preset range corresponding to each standard. The preset ranges corresponding to different standards are different, some standards are hard standards, and have fixed ranges, and some standards are not hard standards, and the ranges are set from negative infinity to positive infinity. If a criterion is not a hard criterion, the result corresponding to this criterion is within the preset range. However, whether a standard is hard or not will affect whether the object to be audited can be audited, because it will affect the final overall score, and the overall standard corresponding to the overall score will generally have a range, for example, greater than 80 points.

A third data judgment step S562 corresponding to each standard, which is to judge whether the third data corresponding to each standard is empty:

if yes, judging whether the preset range corresponding to each standard is from negative infinity to positive infinity: if yes, judging that the object to be audited meets each standard; if not, judging that the object to be audited does not accord with each standard;

otherwise: judging whether the third data corresponding to each standard is in a preset range corresponding to each standard: if yes, judging that the object to be audited meets each standard; and if not, judging that the object to be audited does not meet each standard.

And a change reminding step S563 for each standard, namely judging whether the object to be audited is audited before the audit: if so, judging whether the object to be audited meets the change of each standard, and sending the change information to the object to be audited.

If the object to be audited is not audited before the audit, the audit is the first audit, the last audit does not exist, and the audit cannot be compared with the last audit naturally, so that if the audit is the first audit of the object to be audited, the step does not need to be executed continuously.

If the object to be audited is audited before, comparing and judging whether the result of whether the object to be audited meets each standard during the audit and the result of whether the object to be audited meets each standard during the last audit are changed: if yes, informing the object to be audited of the change of the result meeting each standard, and judging whether the result meeting each standard in the current auditing is audit pass: and if not, informing the object to be audited to correct and modify according to each standard. Whether the result of each criterion is met or not includes the result of each criterion being met and the result of each criterion not being met. For example, whether the object to be audited meets each standard during the current audit results in that the object to be audited meets each standard, and whether the object to be audited meets each standard during the last audit results in that the object to be audited does not meet each standard indicates that a change has occurred; or whether the object to be audited meets each standard in the current audit results in that the object to be audited does not meet each standard, and whether the object to be audited meets each standard in the last audit results in that the object to be audited meets each standard indicates that the object to be audited meets each standard, and then the change occurs.

A step S570 of obtaining a preset model corresponding to the overall standard: and acquiring a preset model corresponding to the overall standard. The preset model comprises a formula or an algorithm or a deep learning model. S500 is executed only when the change is detected in the data change detecting step S400, so that S570 is executed, because the change of the data inevitably causes the change of the second data corresponding to one or more criteria, which inevitably causes the change of the third data, which consequently affects the result of the overall criteria determination, so that the determination result of whether the object to be audited meets the overall criteria may be changed regardless of whether the determination result of whether the object to be audited meets the each criteria changes, and therefore, once the change is detected in the data change detecting step S400, a step of determining whether the object to be audited meets the overall criteria is indispensable.

When the preset model is a deep learning model, the step S570 of obtaining the preset model corresponding to the overall standard includes a step S571 of initializing the deep learning model corresponding to the overall standard, a step S572 of obtaining historical data corresponding to the overall standard, a step S573 of generating a fifth deep learning model, a step S574 of generating a sixth deep learning model, and a step S575 of setting the preset model corresponding to the overall standard:

initializing a deep learning model corresponding to the overall standard, setting the input format of the deep learning model as the format of a set of third data corresponding to each standard in the audit standard, setting the output format of the deep learning model as the format of the third data corresponding to the overall standard, and taking the deep learning model obtained through initialization as a fourth deep learning model.

A history data acquisition step S572 corresponding to the overall standard: and acquiring a set of third data corresponding to each standard in the auditing standards of each object which is audited and third data corresponding to the overall standard from historical big data. The third data corresponding to each criterion may be a score or an evaluation result corresponding to each criterion or other numerical values reflecting the degree of the second data meeting each criterion. The third data corresponding to the overall standard may be a score or evaluation result corresponding to the overall standard or other numerical value reflecting the degree to which the third data corresponding to each standard meets the overall standard.

And a fifth deep learning model generation step S573, wherein a set of third data of each object which is subjected to auditing and corresponds to each standard in the auditing standards is used as input data of the deep learning model, the fourth deep learning model is subjected to unsupervised training, and the fourth deep learning model obtained through unsupervised learning is used as the fifth deep learning model.

And a sixth deep learning model generating step S574, wherein a set of third data corresponding to each standard in the auditing standard of each object which is audited and third data corresponding to the overall standard are respectively used as input data and output data of the fifth deep learning model, and supervised training is carried out on the fifth deep learning model. And respectively taking the set of third data of each object which is subjected to auditing and corresponds to each standard in the auditing standards and the third data corresponding to the overall standard as input data and output data of the fifth deep learning model, namely taking the third data of each object which is subjected to auditing and corresponds to each standard as the input data of the fifth deep learning model, taking the third data of each object which is subjected to auditing and corresponds to the overall standard as the output data of the fifth deep learning model, and taking the fifth deep learning model obtained through supervised learning as a sixth deep learning model.

A preset model setting step S575 corresponding to the overall standard: and taking the sixth deep learning model as a preset model corresponding to the overall standard.

And a step S580 of judging an overall standard, namely judging whether the object to be audited meets the overall standard or not according to the third data corresponding to each standard, the preset model corresponding to the overall standard and the preset range.

The overall standard determination step S580 includes a third data generation step S581 corresponding to the overall standard, a preset range acquisition step S582 corresponding to the overall standard, and a third data determination step S583 corresponding to the overall standard.

And a third data generation step S581, namely calculating to obtain third data corresponding to the overall standard according to the third data corresponding to each standard and the preset model corresponding to the overall standard. And executing the preset model corresponding to each standard on a computer, taking the third data corresponding to each standard as the input of the preset model corresponding to the overall standard, and taking the calculated output as the third data corresponding to the overall standard. Preferably, the third data corresponding to each criterion is used as the input of the sixth deep learning model corresponding to the overall criterion, and the calculated output of the sixth deep learning model is used as the third data corresponding to the overall criterion. The third data corresponding to each criterion may be a score or an evaluation result corresponding to each criterion or other numerical values reflecting the degree of the second data meeting each criterion. The third data corresponding to the overall standard may be a score or evaluation result corresponding to the overall standard or other numerical value reflecting the degree to which the third data corresponding to each standard meets the overall standard.

And a preset range acquiring step S582, namely acquiring a preset range corresponding to the overall standard. The overall score for the overall criteria will generally have a range, e.g., greater than 80 points.

A third data judgment step S583, which is to judge whether the third data corresponding to the overall standard is in a preset range corresponding to the overall standard: if yes, judging that the object to be audited meets the overall standard; and if not, judging that the object to be audited does not accord with the overall standard.

Comprehensive judgment step S590: judging whether the object to be audited meets each standard and the overall standard in the auditing standard: if so, judging that the object to be audited passes the audit of the preset category, namely judging that the result of the audit is that the result of the audit of the object to be audited is audit passing; and if not, judging that the object to be audited does not pass the audit of the preset category, namely, judging that the result of the audit is that the result of the audit of the object to be audited is that the audit does not pass. Compliance with each of the audit standards and the overall standard refers to compliance with both of the audit standards and the overall standard. And if a certain standard or the total standard is not met, judging that the object to be audited does not pass the audit of the preset category.

A step S600 of copying an audit result: and taking the last auditing result of the object to be audited as the auditing result of the object to be audited. The auditing result comprises that the auditing is passed and not passed. The last audit refers to the last audit before the current time, and the last audit may be the first audit, the traditional audit or the tracking audit.

Result feedback step S700: judging whether the object to be audited is audited before the audit: if yes, judging the change of the auditing result and sending the change to the object to be audited; and if not, sending the result of the audit to the object to be audited.

If the object to be audited is not audited before the audit, the audit is the first audit, the last audit does not exist, and the result cannot be compared with the last audit result naturally, so that if the audit is the first audit of the object to be audited, the step only needs to send the result of the audit to the object to be audited.

If the object to be audited is audited before, comparing and judging whether the result of the object to be audited in the current audit and the result of the object to be audited in the last audit are changed: if yes, informing the changed result to the object to be audited, and judging whether the result of the audit is that the audit is passed:

if yes (the last audit is not passed, and the current audit is passed), informing that the object to be audited has passed the audit or informing that the object to be audited is invited to go through the process of applying for the audit. Because the automatic judgment is carried out by the system, and some administrative procedures are required in the actual auditing process, for example, some application materials for unit sealing of the object to be audited, some types of auditing need to inform the object to be audited to go through the process of applying for auditing;

if not (the last audit is passed and the current audit is not passed), informing the object to be audited to carry out rectification and waiting for next tracking audit, feeding back the result of the audit which does not pass through the preset type to the object to be audited, obtaining each non-conforming standard or total standard and feeding back the result to the object to be audited, and sending information to remind the object to be audited to carry out rectification aiming at each non-conforming standard or total standard.

For example, if the result of the current audit is that the object to be audited passes the audit of the preset category, and the result of the previous audit is that the object to be audited does not pass the audit of the preset category, the change is indicated, and the last audit does not pass the audit and the current audit passes the audit; or the result of the audit is that the object to be audited does not pass the audit of the preset category, and the result of the audit of the last time is that the object to be audited passes the audit of the preset category, the change is indicated, and the change is changed from the pass of the audit of the last time to the fail of the audit of the current time. Whether the object to be audited meets each standard has been judged in each standard judgment step S560, so it can be obtained. For example, 6 criteria are provided, wherein, if the items 1 and 3 are not met, the items 1 and 3 are fed back to the object to be audited. Whether the object to be audited meets the overall standard is judged in the overall standard judging step S580, so that the object to be audited can be obtained.

An early warning step S800: judging whether the number of times that the object to be audited fails in the current continuous and multiple tracking audits reaches a threshold value: and if yes, early warning is carried out. Acquiring a preset first frequency, and judging whether the frequency of the object to be audited, which does not pass the audit in the current continuous multi-time tracking audit, reaches the preset first frequency: if yes, sending information to inform the object to be audited of relevant investigation and punishment, and sending information to inform relevant departments of investigating and punishment on the object to be audited; if not, judging whether the number of times that the audit of the object to be audited in the current continuous and multiple audit trails reaches a preset second number of times or not: if yes, sending information to inform the object to be audited of early warning, sending information to inform the object to be audited of rectification, and otherwise, after the first times, the object to be audited is subjected to related investigation and punishment. Wherein the first number is greater than the second number. The number of times that the object to be audited cannot pass the audit in the current continuous multiple trace audit refers to the number of times that the audit does not pass and the audit cannot pass in the continuous multiple trace audit before the current time, for example: the audit is not passed, the last audit is not passed, and the last audit is passed, so that the number of times of continuous audit non-passing is 3. Statistical non-passing passes must be continuous and non-spaced.

Tracking control step S900: and acquiring a preset time period or a preset time point, and re-executing all the steps in the auditing method every other preset time period or when the preset time point is reached.

The steps can be executed on a big data platform such as Spark and the like to accelerate the speed of big data processing.

(II) the system in various embodiments of the invention includes various combinations of the following modules:

the audit standard acquisition module 100 performs the audit standard acquisition step S100.

The execution object data acquisition module 200 executes the object data acquisition step S200.

The object data acquisition module 200 includes a data source acquisition module 210 and an object data retrieval module 220.

The data source acquisition module 210 performs a data source acquisition step S210.

The object data retrieving module 220 performs the object data retrieving step S220.

The data acquisition module 300 corresponding to the standard performs the data acquisition step S300 corresponding to the standard.

The standard corresponding data acquisition module 300 comprises a data screening module 310 and a data cleaning module 320.

The data filtering module 310 performs a data filtering step S310.

The data washing module 320 performs a data washing step S320.

The data cleaning module 320 includes a corresponding data source obtaining module 321, a reliability obtaining module 322, and a reliability selecting module 323.

The corresponding data source acquiring module 321 executes the corresponding data source acquiring step S321.

The reliability acquisition module 322 executes the reliability acquisition step S322.

The reliability selecting module 323 performs the reliability selecting step S323.

The data change detecting module 400 performs a data change detecting step S400.

The trace audit determination module 500 performs a trace audit determination step S500.

The tracking and auditing judgment module 500 includes a sub-standard acquisition module 510, a corresponding data extraction module 520, a corresponding data change detection module 530, a preset model acquisition module 540 corresponding to each standard, a third data generation module 550 corresponding to each standard, a standard judgment module 560, a preset model acquisition module 570 corresponding to the overall standard, an overall standard judgment module 580, and a comprehensive judgment module 590.

The sub-criterion acquisition module 510 performs a sub-criterion acquisition step S510.

The corresponding data extracting module 520 performs the corresponding data extracting step S520.

The corresponding data change detecting module 530 performs a corresponding data change detecting step S530.

The preset model obtaining module 540 corresponding to each standard executes the preset model obtaining step S540 corresponding to each standard.

The preset model obtaining module 540 corresponding to each standard includes a deep learning model initialization module 541 corresponding to each standard, a historical data obtaining module 542 corresponding to each standard, a second deep learning model generation module 543, a third deep learning model generation module 544, and a preset deep learning model setting module 545 corresponding to each standard.

The deep learning model initialization module 541 corresponding to each criterion performs the deep learning model initialization step S541 corresponding to each criterion.

The history data acquisition module 542 corresponding to each criterion performs the history data acquisition step S542 corresponding to each criterion.

The second deep learning model generation module 543 performs a second deep learning model generation step S543.

The third deep learning model generation module 544 executes a third deep learning model generation step S544.

The preset deep learning model setting module 545 corresponding to each criterion performs the preset model setting step S545 corresponding to each criterion.

The third data generating module 550 corresponding to each item of standard performs the third data generating step S550 corresponding to each item of standard.

Each criterion judging module 560 performs each criterion judging step S560.

Each criterion judging module 560 includes a preset range obtaining module 561 corresponding to each criterion, a third data judging module 562 corresponding to each criterion, and a change reminding module 563 corresponding to each criterion.

The preset range acquiring module 561 corresponding to each standard performs the preset range acquiring step S561 corresponding to each standard.

The third data determining module 562 corresponding to each criterion performs the third data determining step S562 corresponding to each criterion.

The change reminding module 563 corresponding to each criterion executes the change reminding step S563 corresponding to each criterion.

The preset model obtaining module 570 corresponding to the overall standard performs the preset model obtaining step S570 corresponding to the overall standard.

The preset model obtaining module 570 corresponding to the overall standard includes a deep learning model initializing module 571 corresponding to the overall standard, a historical data obtaining module 572 corresponding to the overall standard, a fifth deep learning model generating module 573, a sixth deep learning model generating module 574, and a preset model setting module 575 corresponding to the overall standard:

the deep learning model initialization module 571 corresponding to the overall standard performs the deep learning model initialization step S571 corresponding to the overall standard.

The history data acquiring module 572 corresponding to the overall standard executes the history data acquiring step S572 corresponding to the overall standard.

The fifth deep learning model generation module 573 executes the fifth deep learning model generation step S573.

The sixth deep learning model generation module 574 executes a sixth deep learning model generation step S574.

The preset model setting module 575 corresponding to the overall standard performs the preset model setting step S575 corresponding to the overall standard.

The overall criterion judging module 580 performs an overall criterion judging step S580.

The overall standard determining module 580 includes a third data generating module 581 corresponding to the overall standard, a preset range acquiring module 582 corresponding to the overall standard, and a third data determining module 583 corresponding to the overall standard.

The third data generation module 581 corresponding to the overall standard performs the third data generation step S581 corresponding to the overall standard.

The preset range acquiring module 582 corresponding to the overall standard performs the preset range acquiring step S582 corresponding to the overall standard.

The third data judgment module 583 corresponding to the overall criterion performs a third data judgment step S583 corresponding to the overall criterion.

The comprehensive judgment module 590 performs a comprehensive judgment step S590.

The duplicate audit result module 600 performs a duplicate audit result step S600.

The result feedback module 700 performs the result feedback step S700.

The warning module 800 performs the warning step S800.

The tracking control module 900 performs a tracking control step S900.

And acquiring a preset time period or a preset time point, and re-executing all modules in the auditing system every other preset time period or when the preset time point is reached.

The modules can be deployed on large data platforms such as Spark and the like to accelerate the speed of large data processing.

(III) several embodiments of the invention

Embodiment 1 provides an auditing method, which includes an auditing standard acquisition step S100, an object data acquisition step S200, a data acquisition step S300 corresponding to a standard, a data change detection step S400, a trace auditing determination step S500, an auditing result copying step S600, a result feedback step S700, an early warning step S800, and a trace control step S900, as shown in fig. 1.

Embodiment 2 provides an auditing method comprising the steps of the method described in embodiment 1; the object data acquiring step S200 includes a data source acquiring step S210 and an object data retrieving step S220, and the data acquiring step S300 corresponding to the standard includes a data screening step S310 and a data cleaning step S320.

Embodiment 3 provides an auditing method comprising the steps of the method described in embodiment 2; the data cleaning step S320 includes a corresponding data source obtaining step S321, a reliability obtaining step S322, and a reliability selecting step S323.

Embodiment 4 provides an auditing method comprising the steps of the method described in embodiment 2; the audit determination step S500 includes a sub-standard obtaining step S510, a corresponding data extracting step S520, a corresponding data change detecting step S530, a preset model obtaining step S540 corresponding to each standard, a third data generating step S550 corresponding to each standard, a judgment step S560 for each standard, a preset model obtaining step S570 corresponding to an overall standard, a judgment step S580 for the overall standard, and a comprehensive judgment step S590, as shown in fig. 2.

Embodiment 5 provides an auditing method comprising the steps of the method described in embodiment 4; the preset model obtaining step S540 corresponding to each standard includes a deep learning model initializing step S541 corresponding to each standard, a historical data obtaining step S542 corresponding to each standard, a second deep learning model generating step S543, a third deep learning model generating step S544, and a preset deep learning model setting step S545 corresponding to each standard, as shown in fig. 3; the preset model obtaining step S570 corresponding to the overall standard includes a deep learning model initializing step S571 corresponding to the overall standard, a historical data obtaining step S572 corresponding to the overall standard, a fifth deep learning model generating step S573, a sixth deep learning model generating step S574, and a preset model setting step S575 corresponding to the overall standard, as shown in fig. 4.

Embodiment 6 provides an auditing method comprising the steps of the method described in embodiment 4; each criterion judging step S560 includes a preset range obtaining step S561 corresponding to each criterion, and a third data judging step S562 corresponding to each criterion; the overall standard determination step S580 includes a third data generation step S581 corresponding to the overall standard, a preset range acquisition step S582 corresponding to the overall standard, and a third data determination step S583 corresponding to the overall standard.

Embodiment 7 provides an auditing system, which includes an auditing standard obtaining module 100, an object data obtaining module 200, a data obtaining module 300 corresponding to the standards, a data change detecting module 400, a trace auditing judging module 500, a duplicate auditing result module 600, a result feedback module 700, an early warning module 800, and a trace control module 900, as shown in fig. 5.

Embodiment 8 provides an auditing system comprising the steps of the system described in embodiment 7; the object data obtaining module 200 includes a data source obtaining module 210 and an object data retrieving S220, and the data obtaining module 300 corresponding to the standard includes a data screening module 310 and a data cleaning module 320.

Embodiment 9 provides an auditing system comprising the steps of the system described in embodiment 8; the data cleaning module 320 includes a corresponding data source obtaining module 321, a reliability obtaining module 322, and a reliability selecting module 323.

Embodiment 10 provides an auditing system comprising the steps of the system described in embodiment 8; the tracking and auditing determination module 500 includes a sub-standard obtaining module 510, a corresponding data extracting module 520, a corresponding data change detecting module 530, a preset model obtaining module 540 corresponding to each standard, a third data generating module 550 corresponding to each standard, each standard determining module 560, a preset model obtaining module 570 corresponding to the overall standard, an overall standard determining module 580, and a comprehensive determining module 590, as shown in fig. 6.

Embodiment 11 provides an auditing system comprising the steps of the system described in embodiment 10; the preset model obtaining module 540 corresponding to each standard includes a deep learning model initializing module 541 corresponding to each standard, a historical data obtaining module 542 corresponding to each standard, a second deep learning model generating module 543, a third deep learning model generating module 544, and a preset deep learning model setting module 545 corresponding to each standard, as shown in fig. 7; the preset model obtaining module 570 corresponding to the overall standard includes a deep learning model initializing module 571 corresponding to the overall standard, a historical data obtaining module 572 corresponding to the overall standard, a fifth deep learning model generating module 573, a sixth deep learning model generating module 574, and a preset model setting module 575 corresponding to the overall standard, as shown in fig. 8.

Embodiment 12 provides an auditing system comprising the steps of the system described in embodiment 10; each standard judging module 560 comprises a preset range obtaining module 561 corresponding to each standard and a third data judging module 562 corresponding to each standard; the overall standard determining module 580 includes a third data generating module 581 corresponding to the overall standard, a preset range acquiring module 582 corresponding to the overall standard, and a third data determining module 583 corresponding to the overall standard.

Embodiment 13 provides a robot system in which the auditing systems as described in embodiments 7 to 12 are respectively arranged.

The methods and systems of the various embodiments described above may be performed and deployed on computers, servers, cloud servers, supercomputers, robots, embedded devices, electronic devices, and the like.

The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (10)

1. A trace-auditing method for performing trace-auditing for a plurality of businesses or a plurality of individuals; when the object to be audited is tracked and audited, the object to be audited does not need to apply for auditing; the method comprises the following steps:

an audit standard obtaining step, which is used for obtaining the audit standard of the preset category;

an object data acquisition step, which is used for automatically retrieving and acquiring the data of the object to be audited from the data source provided by the object to be audited and the data source provided by the third party;

a data acquisition step corresponding to a standard, which is used for acquiring data corresponding to the auditing standard from the data of the object to be audited according to the reliability of a data source;

a data change detection step, configured to compare data corresponding to the audit standard of the object to be audited with data corresponding to the audit standard of the object to be audited during the last audit, and determine whether a change has occurred: if yes, the step of tracking audit judgment is carried out; if not, the step of copying the audit result is executed;

a tracking audit judgment step for judging whether the data corresponding to the audit standard meets the audit standard;

an auditing result copying step, which is used for taking the last auditing result of the object to be audited as the auditing result of the object to be audited;

a tracking control step, which is used for acquiring a preset time period or a preset time point and re-executing all steps in the tracking and auditing method every other preset time period or when the preset time point is reached;

the tracking audit judgment step comprises the generation of a preset model corresponding to each standard, and the generation step of the preset model corresponding to each standard comprises the following steps:

initializing a deep learning model corresponding to each standard, wherein the deep learning model is used for initializing the deep learning model corresponding to each standard as a first deep learning model;

a historical data acquisition step corresponding to each standard, which is used for acquiring second data and third data of each object which is subjected to auditing and corresponds to each standard from historical big data;

a second deep learning model generation step, which is used for taking the second data of each object which is subjected to auditing and corresponds to each standard as input data of the first deep learning model, carrying out unsupervised training on the first deep learning model, and taking the obtained first deep learning model as a second deep learning model;

a third deep learning model generation step, configured to respectively use the second data and the third data of each object, which is subjected to auditing and corresponds to each standard, as input data and output data of a second deep learning model, perform supervised training on the second deep learning model, and use the obtained second deep learning model as the third deep learning model;

and a preset model setting step corresponding to each standard, wherein the preset model setting step is used for taking the third deep learning model as a preset model corresponding to each standard.

2. The auditing method of claim 1, the method further comprising:

a result feedback step, which is used for judging the change of the auditing result and sending the change to the object to be audited;

and early warning step, which is used for judging whether the number of times that the object to be audited fails to pass the audit in the current continuous and multiple times of tracking audit reaches a threshold value: and if yes, early warning is carried out.

3. An auditing method according to claim 1,

the object data acquiring step includes:

a data source obtaining step for obtaining a data source;

an object data retrieval step, which is used for retrieving and acquiring the data of the object to be audited from the data source;

the data acquisition step corresponding to the standard comprises the following steps:

a data screening step, which is used for screening out data corresponding to the auditing standard from the data of the object to be audited as first data;

and a data cleaning step, which is used for extracting data corresponding to each standard from the first data as second data corresponding to each standard.

4. An auditing method according to claim 2,

the result feedback step includes:

comparing and judging whether the result of the object to be audited in the current audit and the result of the object to be audited in the last audit are changed: if yes, informing the changed result to the object to be audited, and judging whether the result of the audit is that the audit is passed:

if so, informing the object to be audited that the object to be audited has passed the audit or informing the object to be audited to invite the object to be audited to go through the process of applying for audit;

if not, informing the object to be audited to carry out rectification and waiting for next tracking audit, feeding back a result of audit which does not pass through the preset type of audit to the object to be audited, obtaining each standard or overall standard which is not in conformity with the target to be audited, feeding back the standard or overall standard which is not in conformity with the target to be audited, and sending information to remind the object to be audited to carry out rectification aiming at each standard or overall standard which is not in conformity with the target to be audited;

the early warning step comprises the following steps: acquiring a preset first frequency, and judging whether the frequency of the object to be audited, which does not pass the audit in the current continuous multi-time tracking audit, reaches the preset first frequency:

if yes, sending information to inform the object to be audited of relevant investigation and punishment, and sending information to inform relevant departments of investigating and punishment on the object to be audited;

if not, judging whether the number of times that the audit of the object to be audited in the current continuous and multiple audit trails reaches a preset second number of times or not: if yes, sending information to inform the object to be audited of early warning, and sending information to inform the object to be audited of rectification or else, after reaching the first times, being subjected to relevant investigation and punishment.

5. An auditing method according to claim 3,

the tracking audit judgment step comprises the following steps:

a sub-standard obtaining step, which is used for obtaining each standard and the overall standard in the auditing standard;

a corresponding data extracting step, configured to extract the second data corresponding to each criterion from the first data;

a corresponding data change detection step, configured to compare second data corresponding to each standard of the object to be audited with second data corresponding to each standard of the object to be audited during the last audit, and determine whether a change occurs: if yes, executing a preset model obtaining step or each standard judging step corresponding to each standard; if not, jumping to a corresponding data extraction step or a preset model acquisition step corresponding to the overall standard for execution;

a preset model obtaining step corresponding to each standard, which is used for obtaining a preset model corresponding to each standard;

a third data generation step corresponding to each standard, wherein the third data generation step is used for calculating to obtain third data corresponding to each standard according to the second data corresponding to each standard and the preset model corresponding to each standard;

each standard judging step is used for judging whether the object to be audited meets each standard or not according to the third data corresponding to each standard, a preset range and a preset range;

a preset model obtaining step corresponding to the overall standard, which is used for obtaining a preset model corresponding to the overall standard;

a total standard judging step, configured to judge whether the object to be audited meets the total standard according to the third data corresponding to each standard, the preset model corresponding to the total standard, and the preset range;

and a comprehensive judgment step for judging whether the object to be audited meets each standard and the overall standard in the auditing standard.

6. An auditing method according to claim 5,

the step of obtaining the preset model corresponding to the overall standard comprises the following steps:

a deep learning model initialization step corresponding to an overall standard, which is used for initializing the deep learning model corresponding to the overall standard, and taking the obtained deep learning model as a fourth deep learning model;

a historical data acquisition step corresponding to an overall standard, which is used for acquiring a set of third data corresponding to each standard in the auditing standard of each object which is audited and third data corresponding to the overall standard from historical big data;

a fifth deep learning model generation step, configured to use the set of the third data of each object that has undergone audit and corresponds to each standard in the audit standards as input data of the deep learning model, perform unsupervised training on the fourth deep learning model, and use the obtained fourth deep learning model as a fifth deep learning model;

a sixth deep learning model generation step of taking the set of the third data corresponding to each standard in the audit standard of each object that has been audited and the third data corresponding to the overall standard as input data and output data of the fifth deep learning model, respectively, performing supervised training on the fifth deep learning model, and taking the obtained fifth deep learning model as a sixth deep learning model;

and a preset model setting step corresponding to the overall standard, wherein the preset model setting step is used for taking the sixth deep learning model as a preset model corresponding to the overall standard.

7. An auditing method according to claim 5,

the overall standard judging step comprises the following steps:

a third data generation step corresponding to the overall standard, configured to calculate third data corresponding to the overall standard according to the third data corresponding to each standard and the preset model corresponding to the overall standard;

a preset range acquisition step corresponding to the overall standard, which is used for acquiring the preset range corresponding to the overall standard;

and a third data judgment step corresponding to the overall standard, which is used for judging whether the object to be audited meets the overall standard.

8. A trace-auditing system, the system being for performing trace-auditing for a plurality of businesses or a plurality of individuals; when the object to be audited is tracked and audited, the object to be audited does not need to apply for auditing; the system comprises:

the audit standard acquisition module is used for acquiring the audit standard of a preset category;

the object data acquisition module is used for automatically retrieving and acquiring the data of the object to be audited from the data source provided by the object to be audited and the data source provided by the third party;

the data acquisition module corresponding to the standard is used for acquiring data corresponding to the auditing standard from the data of the object to be audited according to the data source credibility;

a data change detection module, configured to compare data corresponding to the audit standard of the object to be audited with data corresponding to the audit standard of the object to be audited during the last audit, and determine whether a change occurs: if yes, the operation is carried out by a tracking audit judgment module; if not, the operation is transferred to a module for copying an audit result for execution;

the tracking and auditing judgment module is used for judging whether the data corresponding to the auditing standard meets the auditing standard or not;

the replication auditing result module is used for taking the last auditing result of the object to be audited as the auditing result of the object to be audited;

the result feedback module is used for judging the change of the auditing result and sending the change to the object to be audited;

the early warning module is used for judging whether the number of times that the audit of the object to be audited fails in the current continuous and multiple times of audit tracking reaches a threshold value: if yes, early warning is carried out;

the tracking control module is used for acquiring a preset time period or a preset time point and re-executing all modules in the tracking and auditing system every other preset time period or when the preset time point is reached;

the tracking audit judgment module comprises a module for generating a preset model corresponding to each standard, and the generation step of the preset model corresponding to each standard comprises the following steps:

initializing a deep learning model corresponding to each standard, wherein the deep learning model is used for initializing the deep learning model corresponding to each standard as a first deep learning model;

a historical data acquisition step corresponding to each standard, which is used for acquiring second data and third data of each object which is subjected to auditing and corresponds to each standard from historical big data;

a second deep learning model generation step, which is used for taking the second data of each object which is subjected to auditing and corresponds to each standard as input data of the first deep learning model, carrying out unsupervised training on the first deep learning model, and taking the obtained first deep learning model as a second deep learning model;

a third deep learning model generation step, configured to respectively use the second data and the third data of each object, which is subjected to auditing and corresponds to each standard, as input data and output data of a second deep learning model, perform supervised training on the second deep learning model, and use the obtained second deep learning model as the third deep learning model;

and a preset model setting step corresponding to each standard, wherein the preset model setting step is used for taking the third deep learning model as a preset model corresponding to each standard.

9. The audit system of claim 8,

the object data acquisition module includes:

the data source acquisition module is used for acquiring a data source;

the object data retrieval module is used for retrieving and acquiring the data of the object to be audited from the data source;

the data acquisition module corresponding to the standard comprises:

the data screening module is used for screening out data corresponding to the auditing standard from the data of the object to be audited as first data;

the data cleaning module is used for extracting data corresponding to each standard from the first data to serve as second data corresponding to each standard;

the tracking audit judgment module comprises:

the sub-standard acquisition module is used for acquiring each standard and the overall standard in the audit standard;

a corresponding data extraction module, configured to extract the second data corresponding to each criterion from the first data;

a corresponding data change detection module, configured to compare second data corresponding to each standard of the object to be audited with second data corresponding to each standard of the object to be audited during the last audit, and determine whether a change occurs: if yes, jumping to a preset model acquisition module corresponding to each standard or executing by each standard judgment module; if not, jumping to a corresponding data extraction module or a preset model acquisition module corresponding to the overall standard for execution;

the preset model acquisition module corresponding to each standard is used for acquiring a preset model corresponding to each standard;

the third data generation module corresponding to each standard is used for calculating to obtain third data corresponding to each standard according to the second data corresponding to each standard and the preset model corresponding to each standard;

each standard judging module is used for judging whether the object to be audited meets each standard or not according to the third data corresponding to each standard, a preset range and a preset range;

the preset model acquisition module corresponding to the overall standard is used for acquiring a preset model corresponding to the overall standard;

the overall standard judging module is used for judging whether the object to be audited meets the overall standard or not according to the third data corresponding to each standard, the preset model corresponding to the overall standard and the preset range;

and the comprehensive judgment module is used for judging whether the object to be audited meets each standard and the overall standard in the auditing standard.

10. A robot system, characterized in that the robot is provided with an auditing system according to any one of claims 8-9.

Images