Intelligent auditing system and method for coal inspection and detection items

Abstract

The invention discloses an intelligent auditing system and method for coal inspection and detection items, and the method comprises the steps: firstly obtaining a video picture of a detection sample before detection through detection equipment, recognizing the specification information of the detection sample, and checking whether the detection sample meets the requirements or not based on the recognized specification information; generating a corresponding detection report according to detection items and detection data recorded by detection personnel when the detection sample is detected based on the detection equipment according to the detection method; checking and verifying the content and format of a detection report formed by the detection sample; and auditing the accuracy of reference standards and the rationality of the detection method in the detection report through a big data model. According to the scheme provided by the invention, automatic auditing of the carbon inspection and detection items can be realized, the accuracy and efficiency of detection can be remarkably improved, and rapid development of inspection and detection tasks and high-quality completion of detection reports can be ensured.

Description

Technical Field

[0001] The present invention relates to coal inspection and testing technology, and in particular to coal inspection and testing project review technology. Background Art

[0002] At present, inspection and testing institutions in the coal field generally rely on offline manual methods to manage raw test data, test reports, inspector test data and other data. Therefore, they are unable to guarantee the accuracy of the data, ensure whether the testing is carried out in full compliance with standards and specifications, and determine the reasons why the testing is carried out in accordance with standards and specifications.

[0003] At the same time, offline manual data management leads to incomplete information in the original test records, such as test conditions, test process data, quality control measures, and equipment calibration. Offline inspection and testing data cannot achieve real-time cross-departmental data sharing and traceability, as well as rapid acquisition of key elements such as various data required by the laboratory.

[0004] Furthermore, the current inspection and testing institutions in the coal field conduct the review and management of corresponding testing projects manually, which still has many problems. For example, it affects the timely processing of the laboratory approval process, resulting in too long time to issue the test report. At the same time, the review and management of corresponding testing projects based on manual methods also leads to a lot of time spent on information statistics management, which is not only a huge workload and easy to go wrong, but also not conducive to the long-term preservation and traceability of information.

[0005] It can be seen that how to conduct efficient and intelligent review and management of coal inspection and testing items in coal field inspection and testing machines is an urgent problem that needs to be solved in this field. Summary of the invention

[0006] In view of the problem that existing coal inspection and testing institutions mainly conduct coal inspection and testing project audits based on offline manual methods, the purpose of the present invention is to provide an intelligent audit solution for coal inspection and testing projects, which can solve the problem of untimely approval by laboratory managers and avoid the problem of missing key information.

[0007] In order to achieve the above object, the present invention provides an intelligent review method for coal inspection and testing items, the review method comprising:

[0008] The test sample review step is to obtain the video image of the test sample before the test through the test equipment, and identify the specification information of the test sample, and check whether the test sample meets the requirements based on the identified specification information;

[0009] The test report generation step is to generate a corresponding test report based on the test items and test data recorded by the test personnel when the test equipment is used to test the test sample according to the test method;

[0010] The test report standardization review step is to review and verify the content and format of the test report generated by the test samples;

[0011] The scientific review step of the test report uses a big data model to review the accuracy of the referenced standards and the rationality of the test methods in the test report.

[0012] In some embodiments of the present invention, the specification information of the test sample identified in the test sample review step includes the test sample name, physical form, and weight.

[0013] In some embodiments of the present invention, the test sample review step introduces test standards related to the test sample to check whether the test sample meets the requirements.

[0014] In some embodiments of the present invention, the test report generated in the test report generating step includes at least one or more items of information including test equipment, inspection record data, and measurement units.

[0015] In some embodiments of the present invention, in the test report normative review step, an AI deep learning algorithm model is used to review and verify the content and format of the test report.

[0016] In order to achieve the above object, the present invention provides an intelligent review system for coal inspection and testing projects, the review system comprising:

[0017] A test sample review unit, wherein the test sample review unit is configured to obtain a video image of the test sample before the test through the test equipment, identify the specification information of the test sample, and check whether the test sample meets the requirements based on the identified specification information;

[0018] A test report generating unit, wherein the test report generating unit is configured to perform data interaction with the test sample review unit, and obtain test items and test data when the test device performs test on the test sample according to the test method through human-computer interaction, and thereby generate a corresponding test report;

[0019] A test report standardization review unit, which reviews and verifies the content and format of the test report generated by the test report generation unit;

[0020] The scientificity review unit of the test report reviews the accuracy of the referenced standards and the rationality of the test methods in the test report generated by the test report generation unit through a big data model.

[0021] In some embodiments of the present invention, the test sample review unit identifies that the specification information of the test sample includes the name, physical form, and weight of the test sample.

[0022] In some embodiments of the present invention, the test sample review unit retrieves the test standard related to the test sample according to the identified specification information of the test sample to check whether the test sample meets the requirements.

[0023] In some embodiments of the present invention, the test report generated by the test report generating unit includes at least one or more items of information including test equipment, inspection record data, and measurement units.

[0024] In some embodiments of the present invention, the test report standardization review unit reviews and verifies the content and format of the test report by calling an AI deep learning algorithm model.

[0025] The intelligent audit scheme for coal inspection and testing projects provided by the present invention can realize automated audit of coal inspection and testing projects, can significantly improve the accuracy and efficiency of testing, ensure the rapid implementation of inspection and testing tasks, complete the test reports with high quality, and minimize the risk of accidents occurring during the testing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments.

[0027] Figure 1 This is a flow chart of the intelligent review of coal inspection and testing items in the present invention;

[0028] Figure 2 It is a system block diagram of the intelligent audit system for coal inspection and testing projects in the present invention;

[0029] Figure 3 This is the architecture diagram of the intelligent audit platform for coal inspection and testing projects in the example of the present invention. DETAILED DESCRIPTION

[0030] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below with reference to specific diagrams.

[0031] In view of the problem that the current coal inspection and testing institutions mainly rely on offline manual management to manage coal inspection and testing projects; the solution of the present invention constructs an intelligent audit solution for coal inspection and testing projects based on artificial intelligence to replace the manual audit management solution and realize the automated audit of coal inspection and testing projects.

[0032] See also Figure 1The intelligent audit scheme for coal inspection and testing projects provided by the present invention is specifically composed of the following stages:

[0033] First, the test sample review stage is carried out;

[0034] In this stage, the testing equipment obtains video images of the test sample before testing, identifies the specification information of the test sample, and verifies whether the test sample meets the requirements based on the identified specification information.

[0035] Next, the test report generation stage;

[0036] In this stage, the testing personnel will generate a corresponding test report based on the test items and test data recorded when the testing equipment tests the test samples according to the test methods.

[0037] Next, the test report normative review stage;

[0038] During this stage, the content and format of the test report generated by the test samples are reviewed and verified.

[0039] Finally, the scientific review stage of the test report;

[0040] At this stage, the big data model is used to review the accuracy of the referenced standards and the rationality of the testing methods in the test report.

[0041] With respect to the intelligent audit scheme for coal inspection and testing items provided by the present invention, its implementation process is described in detail below.

[0042] In some embodiments of the present invention, when performing the test sample review at the test sample review stage, it is first necessary to pre-register the object to be tested and the test project information in the intelligent review system or platform.

[0043] Next, based on the registered detection object information and detection item information, the relevant detection standards are extracted from the pre-built detection item database.

[0044] The testing project database here stores various information related to coal inspection and testing projects, such as testing standards, testing methods, testing equipment, etc.

[0045] Furthermore, the constructed testing project database can run on the cloud, which can not only ensure the security of the data but also facilitate retrieval and data updating.

[0046] Next, identify the basic information for the test project from the extracted relevant testing standards, such as the requirements for test samples, required testing equipment, corresponding testing matters, corresponding testing methods and processes, etc.

[0047] Next, based on the identified testing equipment information, the corresponding testing equipment is selected, and the test sample is placed on the testing equipment. The video image of the test sample before testing is obtained through the testing equipment, and then the specification information of the test sample is identified through the image video model based on the machine learning algorithm. The specification information of the test sample identified here includes the name, physical form, weight and other information of the test sample; the specific information can be determined according to actual needs and is not limited here.

[0048] Finally, the identified test sample specification information is compared with the test sample requirement information identified from the test standard to verify whether the test sample meets the requirements.

[0049] In this way, for the test samples that meet the requirements, they can enter the subsequent testing stage; for the test samples that do not meet the requirements, a conclusion that the samples do not meet the requirements will be given, and the current testing project will be ended.

[0050] In some embodiments of the present invention, when generating a test report in the test report generation stage, the test personnel are guided to select the corresponding test equipment based on identifying the required test equipment from the relevant test standards;

[0051] Next, the corresponding human-computer interaction process is further constructed based on the identification of corresponding inspection items, corresponding inspection methods and process information from relevant inspection standards. In this way, the inspection personnel can select the corresponding inspection equipment, complete the specified inspection items on the inspection samples according to the corresponding inspection processes and standards, and record the corresponding inspection data.

[0052] Finally, according to the basic requirements of the testing standards, a corresponding test report is generated by combining the test items and test data recorded by the test personnel when testing the test samples based on the testing equipment and the testing methods.

[0053] This enables a comprehensive test report to be generated with accurate data, reducing the chances of omissions or errors.

[0054] As a further explanation, the test report generated here includes at least one or more items of information including test equipment, test process, inspection record data, and measurement units.

[0055] In order to ensure a comprehensive and accurate review of the test report in the future, the scheme of the present invention abandons the electronic test report that generates a table format to facilitate the reading of various data. Instead, it innovatively forms a final graphic test report based on the final report specification requirements (i.e. the specifications of the final paper report, including content, format, layout, etc.), and the graphic test report cannot be modified in content and format, and the subsequent report review is carried out accordingly, avoiding the transmission of conventional electronic test reports, resulting in changes or errors in format and content, thereby affecting the quality of the final report.

[0056] In some embodiments of the present invention, during the normative review stage of the test report, the content and format of the test report formed in the test report generation stage are reviewed and verified through an AI deep learning algorithm model, thereby reviewing the accuracy and reliability of the test data in the test report.

[0057] Specifically, we first review the accuracy of the test data. First, we use the AI ​​deep learning algorithm model to identify the relevant content of the pictorial test report. Based on this, we conduct a comprehensive check on the content in the report to determine whether the test samples meet the requirements, the correctness of the test and judgment basis, the reasonable selection of test equipment, the originality, completeness and validity of the inspection records, the accuracy of the measurement units, and the format of the test report, such as punctuation, sentences and page numbers.

[0058] After completing the accuracy review of the test data in the report, the reliability of the test report is then reviewed. The reliability review here includes the completeness of the test report's basis materials, the review suggestions for unqualified items, the completeness and standardization of the test report content and format, and whether the cover, signature page, qualifications and attachments of the test report are complete and correct.

[0059] In some embodiments of the present invention, during the scientific review stage of the test report, the relevant content of the pictorial test report is first identified, and then the accuracy of the referenced standards and the rationality of the test methods in the test report are reviewed through a big data model.

[0060] On this basis, big data models are further used to mark and issue early warning reminders for key detection points that are prone to anchoring.

[0061] From the above, it can be seen that the present invention provides an intelligent audit solution for coal inspection and testing projects, which organically integrates artificial intelligence with information systems such as the coal inspection and testing project management system, and can realize intelligent testing and audit processes, thereby significantly improving the accuracy and efficiency of testing.

[0062] The intelligent audit scheme for coal inspection and testing projects given in this example can constitute a corresponding software program in specific application to form a corresponding intelligent audit system for coal inspection and testing projects. When the software program is running, it will execute the above-mentioned intelligent audit method for coal inspection and testing projects, and store it in the corresponding storage medium for the processor to call and execute.

[0063] See also Figure 2The intelligent audit system 100 for coal inspection and testing projects thus formed mainly includes functions such as: a test sample audit unit 110, a test report generation unit 120, a test report standardization audit unit 130, and a test report scientificity audit unit 140.

[0064] The test sample review unit 110 is configured to obtain video images of the test sample before testing through the testing equipment, identify the specification information of the test sample, and check whether the test sample meets the requirements based on the identified specification information.

[0065] The test report generation unit 120 is configured to exchange data with the test sample review unit 110, and obtain the test items and test data when the test equipment tests the test sample according to the test method through human-computer interaction, and thereby generate a corresponding test report.

[0066] The test report standardization review unit 130 is configured to perform data interaction with the test report generation unit 120 and can review and verify the content and format of the test report generated by the test report generation unit.

[0067] The test report scientificity review unit 140 is configured to interact with the test report generation unit 120 for data, and to review the accuracy of the referenced standards and the rationality of the test methods in the test report generated by the test report generation unit through a big data model.

[0068] The detection sample review unit 110 in the present system includes a registration information acquisition module, an extraction module, an identification module and a review module in specific implementation.

[0069] The registration information acquisition module here is configured to obtain information about objects to be tested and items to be tested that are pre-registered in the intelligent audit system or platform;

[0070] The extraction module is configured to extract relevant detection standards from a pre-built detection project database based on the registered detection object information and detection project information acquired by the registration information acquisition module.

[0071] The identification module is configured to be able to identify the basic information for conducting the test project from the relevant test standards extracted by the extraction module, such as the requirements for the test samples, the required test equipment, the corresponding test items, the corresponding test methods and processes, etc.; at the same time, it can also select the corresponding test equipment based on the identified test equipment information, and place the test sample on the test equipment, obtain the video image of the test sample before the test through the test equipment, and then identify the specification information of the test sample through the image video model based on the machine learning algorithm. The specification information of the test sample identified here includes the name, physical form, weight and other information of the test sample.

[0072] The audit module is configured to verify and compare the test sample specification information identified by the identification module with the test sample requirement information identified from the test standard, thereby verifying whether the test sample meets the requirements.

[0073] The test report generation unit 120 in the present system is specifically configured to guide the test personnel to select the corresponding test equipment based on identifying the required test equipment from the relevant test standards; then, the corresponding human-computer interaction process is further constructed based on identifying the corresponding test items, the corresponding test methods and process information from the relevant test standards, so that the test personnel can complete the specified test items on the test samples and record the corresponding test data in accordance with the corresponding test processes and standards when selecting the corresponding test equipment.

[0074] The test report generating unit 120 can also generate a corresponding test report according to the basic requirements of the test standard and in combination with the test items and test data recorded by the test personnel when the test equipment performs the test on the test sample according to the test method.

[0075] As a further explanation, the test report generated here includes at least one or more items of information including test equipment, test process, inspection record data, and measurement units.

[0076] To ensure a comprehensive and accurate review of the subsequent test report, the test report generation unit 120 generates a final pictorial test report based on the final report specification requirements (i.e., the specifications of the final paper report, including content, format, layout, etc.). The pictorial test report cannot be modified in terms of content and format, and subsequent report reviews are conducted based on this to avoid the transmission of conventional electronic test reports, which may cause changes or errors in format and content, thereby affecting the quality of the final report.

[0077] The test report standardization review unit 130 in this system obtains the pictorial test report generated by the test report generation unit 120, and reviews and verifies the content and format of the test report through an AI deep learning algorithm model, thereby reviewing the accuracy and reliability of the test data in the test report.

[0078] Specifically, the standardization review unit 130 of the test report first conducts an accuracy review of the test data. First, it uses the AI ​​deep learning algorithm model to identify the relevant content of the pictorial test report. On this basis, it conducts a comprehensive check on the content in the report to determine whether the test samples meet the requirements, the correctness of the test and judgment basis, the reasonable selection of test equipment, the originality, completeness and validity of the inspection records, the accuracy of the measurement units, and the format of the test report, such as punctuation, sentences and page numbers.

[0079] The test report scientificity review unit 140 in this system runs independently of the test report normative review unit 130, that is, the test report scientificity review unit 140 runs independently and in parallel with the test report normative review unit 130, and directly obtains the pictorial test report generated by the test report generation unit 120 to perform scientific test on the report, thereby avoiding the impact of the test data of the test report normative review unit 130 on the test results of the test report scientificity review unit 140.

[0080] Specifically, the scientific review unit 140 of the test report first identifies the relevant content of the pictorial test report, and then uses the big data model to review the accuracy of the referenced standards and the rationality of the test methods in the test report.

[0081] The reliability review here includes the completeness of the materials on which the test report is based, the review suggestions for unqualified items, the completeness and standardization of the content and format of the test report, and whether the cover, signature page, qualifications and attachments of the test report are complete and correct.

[0082] On this basis, big data models are further used to mark and issue early warning reminders for key detection points that are prone to anchoring.

[0083] The intelligent audit system for coal inspection and testing projects thus formed can solve various problems in the coal inspection process through automated audit algorithms and models, avoid omission of key information, and ensure the efficiency and accuracy of project audits; at the same time, it can also make logical judgments based on the reference range of the inspection items, use the database to support the comprehensive evaluation of inspection indicators, and add explanatory content to the inspection results, such as early warning prompts or suggestions.

[0084] In order to further illustrate this solution, a specific application example is given below.

[0085] See also Figure 3 , which shows an intelligent audit platform for coal inspection and testing projects based on the solution of the present invention. The intelligent audit platform mainly includes a basic layer, a technical layer, an application layer and a terminal layer in terms of architecture.

[0086] At the basic level, this platform builds the computing power required for artificial intelligence technology, data management, and builds artificial intelligence operating systems and virtualization technologies. In terms of computing power, it is first necessary to build an AI high-performance server to achieve high-speed data processing and stable operating performance to meet the detection industry's needs for high-precision and high-efficiency data processing.

[0087] At the technical level, this platform builds AI frameworks, AI algorithms, and application algorithms based on the basic layer to process and analyze data and provide technical support for the application of artificial intelligence. TensorFlow, PyTorch, MindSpore, etc. can be used for AI frameworks; and on the basis of the AI ​​framework, AI algorithms are used to complete the framework construction of inspection and testing audit projects.

[0088] At the application layer, this platform builds intelligent products, including intelligent testing equipment and intelligent robots. Intelligent testing equipment can be used in laboratory testing processes to improve the accuracy and efficiency of testing. The test robot runs the intelligent audit system for coal inspection and testing projects constructed by the solution of the present invention, thereby achieving efficient inspection project audits. In addition, intelligent robots can also be used for customer service, quickly and accurately responding to customers' common testing questions, and assigning complex problems to relevant personnel for professional processing.

[0089] At the terminal level, this platform is used to build products and services for end users, including testing customers, testing personnel, and testing managers. It provides real-time testing task completion data information to testing customers, important data information during the testing process to testing personnel, and finally provides operational management information to testing managers, such as testing completion rate and testing personnel performance.

[0090] Based on the above example scheme, it can be seen that the scheme of the present invention organically combines artificial intelligence machine learning with coal inspection and testing project review, which can realize data analysis and prediction in the inspection and testing process, discover potential laws and patterns in the data, and thus realize the prediction of inspection results and business trends.

[0091] Furthermore, the solution of the present invention can effectively solve the problem of low current data management level through the organic combination of artificial intelligence machine learning and coal inspection and testing project review, effectively mine and analyze data, evaluate and simulate experimental results, analyze business trends and rules, shorten detection time, provide macro-situation forecasts to support management decision-making, discover hidden information correlation relationships in data, and help inspection and testing institutions predict test results more accurately.

[0092] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0093] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An intelligent audit method for coal inspection and testing projects, characterized in that: The review methods include: The test sample review step is to obtain the video image of the test sample before the test through the test equipment, and identify the specification information of the test sample, and check whether the test sample meets the requirements based on the identified specification information; The test report generation step is to generate a corresponding test report based on the test items and test data recorded by the test personnel when the test equipment is used to test the test sample according to the test method; The test report standardization review step is to review and verify the content and format of the test report generated by the test samples; The scientific review step of the test report uses a big data model to review the accuracy of the referenced standards and the rationality of the test methods in the test report.

2. The intelligent audit method for coal inspection and testing items according to claim 1 is characterized in that: The specification information of the test sample identified in the test sample review step includes the test sample name, physical form, and weight.

3. The intelligent audit method for coal inspection and testing items according to claim 1 or 2 is characterized in that: In the test sample review step, the test standards related to the test samples are introduced to check whether the test samples meet the requirements.

4. The intelligent audit method for coal inspection and testing items according to claim 1 is characterized in that: The test report generated in the test report generation step includes at least one or more items of information including test equipment, inspection record data, and measurement units.

5. The intelligent audit method for coal inspection and testing items according to claim 1 is characterized in that: In the test report normative review step, an AI deep learning algorithm model is used to review and verify the content and format of the test report.

6. An intelligent audit system for coal inspection and testing projects, characterized in that: The review system includes: A test sample review unit, wherein the test sample review unit is configured to obtain a video image of the test sample before the test through the test equipment, identify the specification information of the test sample, and check whether the test sample meets the requirements based on the identified specification information; A test report generating unit, wherein the test report generating unit is configured to perform data interaction with the test sample review unit, and obtain test items and test data when the test device performs test on the test sample according to the test method through human-computer interaction, and thereby generate a corresponding test report; A test report standardization review unit, which reviews and verifies the content and format of the test report generated by the test report generation unit; The scientificity review unit of the test report reviews the accuracy of the referenced standards and the rationality of the test methods in the test report generated by the test report generation unit through a big data model.

7. The intelligent audit system for coal inspection and testing items according to claim 6 is characterized in that: The test sample review unit identifies that the specification information of the test sample includes the name, physical form and weight of the test sample.

8. The intelligent audit system for coal inspection and testing items according to claim 6 is characterized in that: The test sample review unit retrieves the test standards related to the test samples according to the identified specification information of the test samples to check whether the test samples meet the requirements.

9. The intelligent audit system for coal inspection and testing items according to claim 6 is characterized in that: The test report generated by the test report generating unit includes at least one or more items of information including test equipment, inspection record data, and measurement units.

10. The intelligent audit system for coal inspection and testing items according to claim 6 is characterized in that: The test report standardization review unit reviews and verifies the content and format of the test report by calling the AI ​​deep learning algorithm model.

Images