Inspection and detection report quality examination method, system, device and equipment and storage medium

Abstract

The invention discloses an inspection and detection report quality examination method, system, device and equipment and a storage medium. The method comprises the following steps: acquiring a to-be-examined target inspection and detection report; the target inspection and detection report is input into a target artificial intelligence quality examination large model obtained through pre-training for quality examination of the inspection and detection report, and the quality examination at least comprises detection logic examination, technical examination and standard examination; on the basis of the output of the target artificial intelligence quality inspection large model, a report inspection text is obtained, the report inspection text comprises a report quality text and a revision suggestion text, and therefore logical, technical and normative errors of the inspection and detection report can be accurately and rapidly recognized, dependence on professionals is reduced, and the inspection and detection efficiency is improved. Therefore, the labor cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of report review, and in particular to a method, system, device, equipment and storage medium for quality review of inspection and testing reports. Background Art

[0002] In inspection and testing institutions, the quality of inspection and testing reports directly affects the credibility and scientificity of the results. The quality and compliance of inspection and testing reports are also the main supervision directions of regulatory authorities. At present, inspection and testing institutions mainly rely on internal auditors for self-inspection, and regulatory authorities implement supervision mainly by setting up expert groups for on-site inspections. Existing technologies have problems such as single application scenarios, reliance on preset rules, lack of real-time monitoring and early warning functions, insufficient multi-dimensional comprehensive evaluation capabilities, insufficient historical data analysis and pattern recognition capabilities, and high manual dependence in the quality review and supervision of inspection and testing reports. These shortcomings limit their effectiveness and efficiency in practical applications, and it is difficult to meet the needs of comprehensive and intelligent quality review. At the same time, the method of relying on internal auditors for random inspections has problems such as large workload, low efficiency, high cost, insufficient random inspection coverage, and inability to monitor and warn of potential problems in real time. Summary of the invention

[0003] The present invention provides a method, system, device, equipment and storage medium for quality review of inspection and testing reports, so as to accurately and quickly identify logical, technical and normative errors in inspection and testing reports, reduce dependence on professionals, and thus reduce labor costs.

[0004] According to one aspect of the present invention, a method for quality review of inspection and testing reports is provided. The method comprises:

[0005] Obtain the target inspection and testing reports to be reviewed;

[0006] Input the target inspection and testing report into the pre-trained target artificial intelligence quality review large model to conduct a quality review of the inspection and testing report, wherein the quality review at least includes a detection logic review, a technical review, and a specification review;

[0007] Based on the output of the target artificial intelligence quality review model, a report review text is obtained, wherein the report review text includes a report quality text and a revision suggestion text.

[0008] According to another aspect of the present invention, a system for reviewing the quality of inspection and testing reports is provided, the system comprising:

[0009] A task construction device is used to establish a report review task according to the report review plan, and send the target inspection and testing report corresponding to the report review task to the report review device;

[0010] A report review device, used to receive the target inspection and testing report sent by the task construction device, and perform a quality review on the target inspection and testing report based on the target artificial intelligence quality review big model to determine the report review text;

[0011] The quality management device is used to analyze and process the report review text, generate text revision suggestions corresponding to the report review text, and send the text revision suggestions to the task construction device so that the task construction device updates the report review text.

[0012] According to another aspect of the present invention, there is provided a device for reviewing the quality of an inspection and testing report, the device comprising:

[0013] Inspection and testing report acquisition module, used to obtain the target inspection and testing report to be reviewed;

[0014] A report quality review execution module, used for inputting the target inspection and testing report into the pre-trained target artificial intelligence quality review large model to perform a quality review of the inspection and testing report, wherein the quality review at least includes a detection logic review, a technical review, and a specification review;

[0015] A report review text determination module is used to obtain a report review text based on the output of the target artificial intelligence quality review model, wherein the report review text includes a report quality text and a revision suggestion text.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the inspection and testing report quality review method described in any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the inspection and testing report quality review method described in any embodiment of the present invention when executed.

[0021] The technical solution of the embodiment of the present invention obtains the target inspection and testing report to be reviewed. The target inspection and testing report is input into the pre-trained target artificial intelligence quality review large model to conduct a quality review of the inspection and testing report. Based on the output of the target artificial intelligence quality review large model, the report review text is obtained, so that the logical, technical and normative errors of the inspection and testing report can be accurately and quickly identified, reducing the dependence on professionals, thereby reducing labor costs.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 is a flow chart of a method for quality review of inspection and testing reports provided according to Embodiment 1 of the present invention;

[0025] Figure 2 is a schematic diagram of a system for quality review of inspection and testing reports provided according to Embodiment 2 of the present invention;

[0026] Figure 3 is a schematic diagram of the architecture of a report review device provided according to Embodiment 2 of the present invention;

[0027] Figure 4 is a structural diagram of an inspection and testing report quality review device provided according to Embodiment 3 of the present invention;

[0028] Figure 5 It is a structural diagram of an electronic device for implementing the inspection and testing report quality review method of an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Embodiment 1

[0032] Figure 1 A flowchart of a method for quality review of inspection and testing reports is provided for the first embodiment of the present invention. This embodiment is applicable to the case of quality review of the generated inspection and testing reports. The method can be executed by an inspection and testing report quality review device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0033] S101. Obtain the target inspection and testing report to be reviewed.

[0034] Among them, the target inspection and testing report may refer to the inspection and testing report to be subject to quality review. The target inspection and testing report may cover a wide range of technical fields, and the present disclosure is not limited to inspection and testing reports in specific technical fields. The target inspection and testing report may be a product or material inspection and testing report, a food inspection and testing report, a motor vehicle inspection and testing report, an environmental analysis test report, a medical inspection and testing report, a network security scan report, or a software and hardware failure inspection and testing report, etc.

[0035] Specifically, according to the review instructions of the inspection and testing report, the target inspection and testing report of the inspection is obtained.

[0036] S102. Input the target inspection and testing report into the pre-trained target artificial intelligence quality review model to conduct quality review of the inspection and testing report.

[0037] Among them, the quality review includes at least detection logic review, technical review and specification review. The target AI quality review model can be a neural network model pre-trained based on sample data. It is worth noting that the target AI quality review model supports technical and compliance reviews, which can quickly and effectively ensure the accuracy and compliance of each report.

[0038] It should be noted that the target inspection and testing report for each technical field has its specific report content and standard format. For different technical fields, the target artificial intelligence quality review big model is trained through the sample inspection and testing reports in the technical field, and the target artificial intelligence quality review big model can process the target inspection and testing reports in the technical field.

[0039] Specifically, the collected target inspection and testing reports can be input into the target artificial intelligence quality review big model, so that the target artificial intelligence quality review big model can determine the quality problems existing in the target inspection and testing reports in combination with the target inspection and testing reports, thereby improving the accuracy of the quality review.

[0040] Exemplarily, the training process of the target artificial intelligence quality review model includes:

[0041] Obtain a sample inspection and testing report and the theoretical review conclusion corresponding to the sample inspection and testing report; input the sample inspection and testing report into a preset artificial intelligence quality review big model to conduct a quality review of the inspection and testing report, and obtain an output review conclusion based on the output of the preset artificial intelligence quality review big model; determine the training error based on the output review conclusion and the theoretical review conclusion, and back-propagate the training error to the preset artificial intelligence quality review big model to adjust the network parameters in the preset artificial intelligence quality review big model; when the preset convergence conditions are met, determine that the training of the preset artificial intelligence quality review big model is completed, and obtain the target artificial intelligence quality review big model.

[0042] The sample inspection and testing report includes a positive sample report and a negative sample report. A negative sample report may refer to a sample report with quality problems. A positive sample report may refer to a sample report that meets quality standards. The sample inspection and testing report includes at least review rule information, testing standard information, inspection and testing report information, testing record information, equipment information, organization information, and process information.

[0043] Specifically, positive sample reports and negative sample reports are collected, and they are sorted and processed to provide relevant data materials such as review rules, testing standards, inspection and testing reports, testing records, personnel information, equipment information, institutional information, and program files. These data materials include not only structured information, such as tables, lists, and normative documents, but also unstructured information, such as text reports and handwritten records. The collected sample inspection and testing reports are cleaned and formatted to ensure data quality and consistency, and to provide accurate and clean input data for model training.

[0044] Based on the training function, the sample inspection and testing report can be input into the preset artificial intelligence quality review big model for quality review, and the training error can be determined based on the output review conclusion and theoretical review conclusion output by the preset artificial intelligence quality review big model, and the training error can be back-propagated to the preset artificial intelligence quality review big model to adjust the network parameters in the preset artificial intelligence quality review big model to optimize the detection accuracy, reduce errors, etc., so that the target artificial intelligence quality review big model can self-learn and adjust in the actual detection scenario. At the same time, during the model training process, real-time feedback is continuously provided to the model, including positive rewards and negative penalties, to guide the model to better understand and implement the detection standards and review rules until the preset convergence conditions are met, such as when the number of iterations reaches the preset number or the training error converges, it is determined that the training of the preset artificial intelligence quality review big model is completed, at which time the preset artificial intelligence quality review big model that has completed training can be used as the target artificial intelligence quality review big model.

[0045] In addition, the experience and knowledge of industry experts can be introduced at the key stage of the training of the target AI quality review model to evaluate and provide feedback on the learning outcomes of the target AI quality review model. Experts can review the output of the target AI quality review model and mark cases where the target AI quality review model has handled things improperly. Fine-tune the target AI quality review model based on the feedback from experts, adjust the learning algorithm or re-weight the importance of the input data to ensure that the model can accurately understand and implement industry specifications.

[0046] After the training of the target AI quality review model is completed, the performance of the model is verified through a series of preset test cases and historical data to ensure that it can maintain high accuracy and reliability in various situations. The model is iteratively optimized based on the test results to continuously improve the accuracy and adaptability of the target AI quality review model.

[0047] By using sample inspection and testing reports and the theoretical review conclusions corresponding to the sample inspection and testing reports for model training, the accuracy of the quality review of inspection and testing reports by the target artificial intelligence quality review model can be ensured.

[0048] S103. Based on the output of the target artificial intelligence quality review model, obtain a report review text.

[0049] Among them, the report review text may include report quality text and revision suggestion text, etc.

[0050] Specifically, the target AI quality review model can be used to conduct a detailed review of the technical parameter accuracy, data consistency, and all relevant compliance requirements of the target inspection and testing report, and a report quality text can be obtained. At the same time, a revision suggestion text can be provided based on the report quality text. Among them, the revision suggestion text at least includes how to correct errors and improve the report content, as well as ensuring that the target inspection and testing report meets the required standards.

[0051] The technical solution of the embodiment of the present invention obtains the target inspection and testing report to be reviewed. The target inspection and testing report is input into the pre-trained target artificial intelligence quality review large model to conduct a quality review of the inspection and testing report. Based on the output of the target artificial intelligence quality review large model, the report review text is obtained, so that the logical, technical and normative errors of the inspection and testing report can be accurately and quickly identified, reducing the dependence on professionals, thereby reducing labor costs.

[0052] Embodiment 2

[0053] Figure 2 This is a schematic diagram of a system for quality review of inspection and testing reports provided in Embodiment 2 of the present invention. Figure 2 As shown, the system includes: a task construction device 201, a report review device 202 and a quality management device 203. Among them,

[0054] The task construction device 201 is used to establish a report review task according to the report review plan, and send the target inspection and testing report corresponding to the report review task to the report review device.

[0055] The report review device 202 is used to receive the target inspection and testing report sent by the task construction device, and perform a quality review on the target inspection and testing report based on the target artificial intelligence quality review model to determine the report review text.

[0056] The quality management device 203 is used to analyze and process the report review text, generate text revision suggestions corresponding to the report review text, and send the text revision suggestions to the task construction device so that the task construction device updates the report review text.

[0057] It should be noted that the report review device 202 is composed of a gateway firewall, a target artificial intelligence quality review model and a database. The gateway firewall is used to receive the target inspection and detection report sent by the task construction device. The target artificial intelligence quality review model is used to perform a quality review on the target inspection and detection report and determine the report review text. The database is used to store the report review text corresponding to the target inspection and detection report.

[0058] The task construction device 201 can establish a report review task according to a pre-established report review plan. The task construction device 201 can access the database through the gateway firewall to upload the target inspection and testing report, and download the report review text, test data and other information, and can also perform quality review on the specified report by calling the target artificial intelligence quality review model.

[0059] The quality management device 203 can analyze and process the report review text to generate text revision suggestions corresponding to the report review text to achieve self-learning and self-updating. At the same time, the text revision suggestions can be sent to the task construction device so that the task construction device updates the report review device.

[0060] Exemplarily, the quality management device 203 is also used to: establish a batch review task, and send the batch inspection and testing report corresponding to the batch review task to the report review device, so that the report review device performs a quality review on each batch inspection and testing report and generates a report review text.

[0061] Among them, the task priority corresponding to the task construction device is higher than the task priority corresponding to the quality management device.

[0062] Specifically, the quality management device 203 can establish a batch review task and send the batch inspection and testing report corresponding to the batch review task to the report review device 202, so that the target artificial intelligence quality review large model in the report review device 202 can automatically analyze and identify various potential risks, logical errors, technical errors and normative errors, including but not limited to data inconsistencies, typos, equipment out of validity and standards expired. Based on the results of the target artificial intelligence quality review large model analysis, the system generates a detailed report review text to list the problems found and their severity levels. At the same time, based on the identified problems, the target artificial intelligence quality review large model can also propose specific processing suggestions and corrective measures to help the task construction device 201 formulate improvement plans or penalty suggestions.

[0063] In addition, the task priority corresponding to the task construction device 201 is higher than the task priority corresponding to the quality management device. The task construction device 201 usually involves an immediate quality review of a single target inspection and test report. This type of review is usually time-sensitive and requires rapid feedback to ensure the continuity and accuracy of the review work. The system sets a high priority for the task construction device 201 by default, ensuring that immediate quality review can be obtained during daily inspection and analysis, so as to promptly discover and correct errors or problems in the report.

[0064] The review of the call of the quality management device 203 usually involves the compliance review of batch reports. Although such review is important, it does not usually require immediate feedback. When there is no urgent task, the call of the quality management device 203 is prioritized after the task construction device 201. This call can be made when the system resources are relatively idle to optimize the overall operation efficiency of the system. In certain circumstances, the quality management device 203 may need to conduct an urgent review of certain reports, such as reports involving critical safety issues. In this case, the system should allow the adjustment of the priority of the task to process these urgent tasks in advance.

[0065] Figure 3 This is a schematic diagram of the report review device architecture provided by the present invention. Figure 3 As shown, the report review device architecture includes an application layer, a business layer, a big model layer, a data link layer and a database; wherein the application layer is used to interact with the task construction device and / or the quality management device; the business layer is used to organize and process the report data of the target inspection and testing report; the big model layer is used to provide a review platform for the target artificial intelligence quality review big model; the data link layer is used to support data storage process, database reading and writing, and data caching; the database is used to store the review text data corresponding to the report review text.

[0066] It should be noted that the application layer, business layer and data link layer belong to the server part of the report quality review and supervision system, serving the target artificial intelligence quality review model. The remote access interface in the application layer is responsible for interacting with the client to achieve remote access, the UI interface is responsible for local interaction, and the notification system is responsible for pushing the review report.

[0067] The permission management module in the business layer is used to manage account login permissions; the logging module is used to record system behavior; the decision-making module is used to support system automatic decision-making; the task scheduling module is used to prioritize the tasks of the task construction device and the quality management device, and to queue the report review tasks; the data acquisition module is used to receive and cache the data submitted by the client; the data preprocessing module is used to organize the submitted data and communicate with the target artificial intelligence quality review big model; the big model processing module is used to call the target artificial intelligence quality review big model so that the target artificial intelligence quality review big model can perform data analysis and review, and generate a report review text; the visualization and reporting module is used to view and print the report review text.

[0068] On the other hand, the inspection and testing report quality review system can maximize resource utilization by automatically performing quality reviews of unreviewed reports during off-peak hours (such as after work hours), ensuring that all inspection and testing reports are strictly reviewed and potential problems are discovered and handled in a timely manner.

[0069] The inspection and testing report quality review system is equipped with a timed task scheduler, which is responsible for automatically activating the review task during the set idle time period (usually at night after get off work). The scheduler monitors the queue of reports to be reviewed in the database to identify the inspection and testing reports that have not yet undergone quality review. The inspection and testing report quality review system automatically takes out the inspection and testing reports that have not undergone quality review from the queue to be reviewed and inputs them into the target artificial intelligence quality review big model for quality review. The target artificial intelligence quality review big model will evaluate the compliance, accuracy and completeness of the report and identify any logical, technical or normative errors.

[0070] After the quality review is completed, the inspection and testing report quality review system automatically generates a detailed report review text, including the review results, the problems found and their severity ratings. The inspection and testing report quality review system automatically pushes the report review text to the mailbox or system account of the relevant person in charge or team to ensure that the relevant personnel can obtain the report results as soon as possible.

[0071] In addition, if serious problems or violations are found during the automatic review process, the inspection and testing report quality review system will automatically trigger an early warning mechanism. The early warning information will be sent directly to the emergency contact to ensure that the problem can be noticed and measures can be taken in time.

[0072] Embodiment 3

[0073] Figure 4 This is a schematic diagram of the structure of a device for quality review of inspection and testing reports provided in Embodiment 3 of the present invention. Figure 4 As shown, the device comprises:

[0074] The inspection and testing report acquisition module 301 is used to obtain the target inspection and testing report to be reviewed;

[0075] A report quality review execution module 302 is used to input the target inspection and testing report into a pre-trained target artificial intelligence quality review large model to perform a quality review of the inspection and testing report, wherein the quality review at least includes a detection logic review, a technical review, and a specification review;

[0076] The report review text determination module 303 is used to obtain the report review text based on the output of the target artificial intelligence quality review model, wherein the report review text includes a report quality text and a revision suggestion text.

[0077] The technical solution of the embodiment of the present invention obtains the target inspection and testing report to be reviewed. The target inspection and testing report is input into the pre-trained target artificial intelligence quality review large model to conduct a quality review of the inspection and testing report. Based on the output of the target artificial intelligence quality review large model, the report review text is obtained, so that the logical, technical and normative errors of the inspection and testing report can be accurately and quickly identified, reducing the dependence on professionals, thereby reducing labor costs.

[0078] Optionally, the device further includes a model training module, which is used to:

[0079] Obtain a sample inspection and testing report and a theoretical review conclusion corresponding to the sample inspection and testing report, wherein the sample inspection and testing report includes a positive sample report and a negative sample report, and the sample inspection and testing report includes at least review rule information, testing standard information, inspection and testing report information, testing record information, equipment information, organization information, and process information;

[0080] Input the sample inspection and testing report into the preset artificial intelligence quality review model to conduct a quality review of the inspection and testing report, and obtain an output review conclusion based on the output of the preset artificial intelligence quality review model;

[0081] Determine the training error based on the output review conclusion and the theoretical review conclusion, and back-propagate the training error to the preset artificial intelligence quality review large model to adjust the network parameters in the preset artificial intelligence quality review large model;

[0082] When the preset convergence conditions are met, it is determined that the training of the preset quality review model is completed, and the target artificial intelligence quality review large model is obtained.

[0083] The inspection and testing report quality review device provided in the embodiment of the present invention can execute the inspection and testing report quality review method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0084] Embodiment 4

[0085] Figure 5A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0086] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0087] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0088] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 performs the various methods and processes described above, such as method inspection and test report quality review.

[0089] In some embodiments, the method inspection test report quality review can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method inspection test report quality review described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the method inspection test report quality review by any other suitable means (for example, by means of firmware).

[0090] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0091] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0092] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0093] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0094] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0095] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0096] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired text of the technical solution of the present invention can be achieved, and this document is not limited here.

[0097] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for quality review of inspection and testing reports, characterized in that: include: Obtain the target inspection and testing reports to be reviewed; Input the target inspection and testing report into the pre-trained target artificial intelligence quality review large model to conduct a quality review of the inspection and testing report, wherein the quality review at least includes a detection logic review, a specification review, and a technical review; Based on the output of the target artificial intelligence quality review model, a report review text is obtained, wherein the report review text includes a report quality text and a revision suggestion text.

2. The method according to claim 1, characterized in that Before obtaining the target inspection and testing report to be reviewed, it also includes: Obtain a sample inspection and testing report and a theoretical review conclusion corresponding to the sample inspection and testing report, wherein the sample inspection and testing report includes a positive sample report and a negative sample report, and the sample inspection and testing report includes at least review rule information, testing standard information, inspection and testing report information, testing record information, equipment information, organization information, and process information; Input the sample inspection and testing report into a preset artificial intelligence quality review model to conduct a quality review of the inspection and testing report, and obtain an output review conclusion based on the output of the preset artificial intelligence quality review model; Determine the training error based on the output review conclusion and the theoretical review conclusion, and back-propagate the training error to the preset artificial intelligence quality review large model to adjust the network parameters in the preset artificial intelligence quality review large model; When the preset convergence conditions are met, it is determined that the training of the preset artificial intelligence quality review large model is completed, and the target artificial intelligence quality review large model is obtained.

3. A quality review system for inspection and testing reports, characterized in that: include: A task construction device is used to establish a report review task according to the report review plan, and send the target inspection and testing report corresponding to the report review task to the report review device; A report review device, used to receive the target inspection and testing report sent by the task construction device, and perform a quality review on the target inspection and testing report based on the target artificial intelligence quality review big model to determine the report review text; The quality management device is used to analyze and process the report review text, generate text revision suggestions corresponding to the report review text, and send the text revision suggestions to the task construction device so that the task construction device updates the report review text.

4. The system according to claim 3, characterized in that The report reviews equipment including: A gateway firewall, used for receiving the target inspection and detection report sent by the task construction device; The target artificial intelligence quality review model is used to conduct a quality review of the target inspection and testing report and determine the report review text; A database is used to store the report review text corresponding to the target inspection and testing report.

5. The system according to claim 3, characterized in that The report review device architecture includes an application layer, a business layer, a large model layer, a data link layer and a database; wherein, The application layer is used to interact with the task construction device and / or the quality management device; The business layer is used to organize and process the data of the target inspection and testing report; The large model layer is used to provide a review platform for the target artificial intelligence quality review large model; The data link layer is used to support data storage process, database reading and writing, and data caching; The database is used to store the review text data corresponding to the report review text.

6. The system according to claim 5, characterized in that The business layer includes: The permission management module is used to manage account login permissions; The logging module is used to record system behavior; The decision module is used to support the system's automatic decision-making; The task scheduling module is used to prioritize the tasks of the task construction device and the quality management device, and to queue the report review tasks; The data collection module is used to receive and cache the data submitted by the client; The data preprocessing module is used to organize the submitted data and communicate with the target artificial intelligence quality review model; The large model processing module is used to call the target artificial intelligence quality review large model so that the target artificial intelligence quality review large model performs data analysis and review and generates a report review text; The visualization and reporting module is used to view and print the report review text.

7. The system according to claim 3, characterized in that The quality management equipment is also used for: Establishing a batch review task, and sending the batch inspection and testing reports corresponding to the batch review task to the report review device, so that the report review device performs a quality review on each batch inspection and testing report and generates a report review text; Among them, the task priority corresponding to the task construction device is higher than the task priority corresponding to the quality management device.

8. A device for reviewing the quality of inspection and testing reports, characterized in that: include: Inspection and testing report acquisition module, used to obtain the target inspection and testing report to be reviewed; A report quality review execution module, used for inputting the target inspection and testing report into the pre-trained target artificial intelligence quality review large model to perform a quality review of the inspection and testing report, wherein the quality review at least includes a detection logic review, a technical review, and a specification review; A report review text determination module is used to obtain a report review text based on the output of the target artificial intelligence quality review model, wherein the report review text includes a report quality text and a revision suggestion text.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the inspection and testing report quality review method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the inspection and testing report quality review method described in any one of claims 1-7 when executed.

Images