Digital work permission management system using artificial intelligence and robotic process automation, and method thereof

Abstract

A digital work permission management system according to an embodiment of the present invention comprises: a work permission approval request reception unit for receiving data requesting approval of work permission to perform work; a work permission determination unit for determining approval or rejection of the work permission for the work permission approval request data by using a first robotic process automation (RPA) and an automation recommendation model; an access permission token issuance unit for issuing an access permission token when the work permission approval is determined; an access permission approval request reception unit for receiving data requesting approval of permission for work zone access for the work zone access; a safety measure verification unit for photographing a worker existing in an access zone and verifying a safety measure by using a second robotic process automation (RPA) and a safety measure verification model; and an access permission determination unit for receiving data from the access permission approval request reception unit or the safety measure verification unit and determining worker access permission through the second robotic process automation (RPA).

Description

Digital work permit management system and method using artificial intelligence and robotic process automation

[0001] The present invention relates to a digital work permit management system and method using artificial intelligence and robotic process automation, and more particularly, to a digital work permit management system and method using artificial intelligence and robotic process automation that can automate digital work permit and work execution tasks using robotic process automation (RPA) and artificial intelligence technology to minimize work errors and automatically process repetitive tasks.

[0002] The modern business environment is becoming increasingly complex due to rapid change and rapid technological innovation. Companies are actively adopting automation technologies to achieve goals such as cost reduction, increased productivity, and improved customer service.

[0003] Robotic Process Automation (RPA) is a technology that automates repetitive and routine tasks using robotic software. This frees up human labor, allowing them to focus on more valuable tasks and improves work accuracy and efficiency.

[0004] In the past, automation was attempted using programming or scripting techniques, but these methods were expensive and difficult to implement. Furthermore, they were difficult to adapt to changes in the process and lacked flexibility.

[0005] Recent advances in machine learning and artificial intelligence have led to a dramatic shift in automation technology. These technologies recognize and learn processes through data-driven learning, providing the flexibility to adapt to change.

[0006] All work performed on-site must follow risk management procedures to prevent potential accidents. However, because workers must process numerous work permits in a short period of time, numerous errors can occur. Furthermore, manually managing work permits and monitoring the status of work execution can be difficult, making accident prevention difficult.

[0007] To address these issues, work permit and work execution management procedures must be digitized. Registering all information into the system allows for real-time status updates. The system's safety measures and processes can prevent accidents. In the event of an accident, any missed steps can be immediately identified, reducing the time it takes to assess the situation. However, digitization also requires a large number of tasks to be processed through the system, which can lead to information omissions due to human error in inputting or registering information. This can hinder proper monitoring of work permits and work execution, necessitating a reduction in the workload handled by the system.

[0008] Therefore, there is a need to establish a safe and efficient digital work permit management system by digitalizing the process of managing work permits and work execution directly through documents at the work site to minimize manual work and repetitive tasks.

[0009] The technical problem to be achieved by the present invention is to provide a digital work permit management system and method using artificial intelligence and robotic process automation, which can automate digital work permit and work execution tasks by using robotic process automation (RPA) and artificial intelligence technology to minimize work errors and automatically process repetitive tasks.

[0010] The technical task of the present invention is to provide a safe and efficient automated digital work permit management system by digitalizing the process of directly managing work permits and work performance through documents at a work site.

[0011] In addition, the technical task to be achieved by the present invention is to provide a digital work permit management system and method using artificial intelligence and robotic process automation, which can minimize work by automating tasks that can be automated among repetitive tasks that people had to process with a system in the past when digitalized, thereby allowing people to focus on tasks that require decision-making.

[0012] In addition, the technical task to be achieved by the present invention is to provide a digital work permit management system and method using artificial intelligence and robotic process automation, which can prevent and reduce the occurrence of accidents by restricting entry into the workplace depending on whether the worker is wearing safety equipment by automating the work execution task using CCTV footage and robotic process automation (RPA) and artificial intelligence technology in the work execution stage.

[0013] The technical problems to be solved by the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned can be clearly understood by a person having ordinary skill in the technical field to which the present invention belongs from the description below.

[0014] In order to achieve the above technical task, a digital work permit management system according to an embodiment of the present invention includes: a work permit approval request receiving unit that receives data requesting work permit approval for performing work; a work permit decision unit that determines whether to approve or reject the work permit using a first robotic process automation (RPA) and an automated recommendation model for the work permit approval request data; an access permit token issuing unit that issues an access permit token when the work permit approval is determined; an access permit approval request receiving unit that receives data requesting work area access permit approval for entering a work area; a safety measure verification unit that photographs a worker present in an access area and verifies safety measures using a second robotic process automation (RPA) and a safety measure verification model; and an access permit decision unit that receives data from the access permit approval request receiving unit and the safety measure verification unit and determines worker access permission using the second robotic process automation.

[0015] The above automated recommendation model can automate the classification of approval or rejection of the work permit through artificial intelligence learning on the work permit request data.

[0016] The above automated recommendation model may include a work permit record data collection unit that collects the work permit record data; a work permit classification unit that classifies the work permits from the work permit record data using the artificial intelligence; an automation target candidate work permit selection unit that selects candidate work permits that can be automated from among the classified ones; and a work permit decision automation unit that determines a group for which the work permit approval or rejection is automated.

[0017] The above work permit classification unit can classify work permits into an always approved group, a conditionally approved group, and an always rejected group, and the automation target candidate work permit selection unit can select the always approved group and the always rejected group that can be automated.

[0018] The above safety measure verification model can automate the approval or rejection classification of the entry permit through artificial intelligence learning on the video captured by the safety measure verification unit.

[0019] The above safety measure verification model may include a worker image collection unit that collects images taken by the safety measure verification unit; a safety attribute classification unit that classifies safety attributes of the images using the artificial intelligence; and an access permission decision automation unit that determines a group for which access permission approval or rejection is automated based on the attribute classification.

[0020] The above safety attribute classification section can be classified into a safety helmet wearing group, a work clothing wearing group, and a safety shoe wearing group.

[0021] The above digital work permit management system may further include a work permit review unit that receives data from the work permit approval request receiving unit and performs a review of the work permit; a work information collection unit that collects work information including work permit information; and a work information analysis and storage unit that analyzes and stores the work information including the work information, the work permit approval information, and the access permit approval information.

[0022] The above work permit approval request receiving unit, the work permit review unit, and the work permit decision unit may be implemented as a first robotic process automation (RPA), and the safety measure verification unit and the access permission decision unit may be implemented as a second robotic process automation (RPA).

[0023] The above digital work permit management system can automatically generate safety measure information based on a pre-work safety review meeting (TBM) form after the work permit approval is completed.

[0024] In addition, a digital work permit management method according to an embodiment of the present invention for achieving the above-described technical task includes the steps of: receiving data requesting approval of a work permit to perform a task; determining approval or rejection of the work permit using a first robotic process automation (RPA) and an automated recommendation model for the received work permit approval request data; issuing an access permit token when approval of the work permit is determined; requesting approval of an access permit to a work area for entry into the work area; photographing a worker present in the entry area and verifying safety measures using a second robotic process automation (RPA) and a safety measure verification model; and receiving data from the access permit approval request step and the safety measure verification step to determine whether to permit the worker to enter the work area using the second robotic process automation (RPA).

[0025] The step of determining whether to approve or reject the work permit may include: a step of analyzing work permit record data of the subject of the work permit approval request; a step of identifying an automation target using the automated recommendation model for the analyzed data; a step of identifying the automation target and determining whether to automatically execute the work permit decision; and a step of determining whether to approve or reject the work permit based on the result of whether to automatically execute the work permit decision.

[0026] The step of determining whether to approve or reject the above work permit may include a step of automatically determining approval or rejection if the work permit automation is possible; and a step of recognizing the work permit as requiring a decision on review and approval if the work permit automation is not possible, and sending a review and approval request message to the approval manager.

[0027] The step of verifying safety measures using the second robotic process automation (RPA) and safety measure verification model may include: scanning the access permission token; confirming whether the worker is permitted to enter the work area based on work permission information and worker information for each area; determining whether the worker is permitted to enter based on the confirmed information; confirming whether the worker present in the access area has performed safety measures using the safety measure verification model; determining whether the safety measure has been completed after confirming the safety measure performance; and determining whether to approve or reject the access permit based on the result of whether the safety measure has been completed.

[0028] According to an embodiment of the present invention, by automating digital work authorization and work execution tasks using robotic process automation (RPA) and artificial intelligence technologies, work errors can be minimized and repetitive tasks can be automatically processed.

[0029] According to an embodiment of the present invention, the process of directly managing work permits and work performance through documents at a work site can be digitized to ensure safe and efficient processing.

[0030] In addition, according to an embodiment of the present invention, when digitalized, tasks that can be automated among the repetitive tasks that a person had to process with a system in the past can be automated, thereby minimizing work by allowing a person to focus on tasks that require decision-making.

[0031] In addition, according to an embodiment of the present invention, by automating the work execution task using CCTV footage and robotic process automation (RPA) and artificial intelligence technology in the work execution stage, entry into the work site can be restricted depending on whether the worker is wearing safety equipment, and the occurrence of accidents can be prevented and reduced.

[0032] The effects of the present invention are not limited to the above-described effects, and should be understood to include all effects that can be inferred from the composition of the invention described in the description or claims of the present invention.

[0033] FIG. 1 is a diagram illustrating an overview of a digital work permit management system using artificial intelligence and robotic process automation according to an embodiment of the present invention.

[0034] FIG. 2 is a block diagram illustrating the configuration of a digital work permit management system using artificial intelligence and robotic process automation according to an embodiment of the present invention.

[0035] FIG. 3 is a block diagram illustrating the configuration of an automated recommendation model according to an embodiment of the present invention.

[0036] FIG. 4 is a block diagram illustrating the configuration of a safety measure verification model according to an embodiment of the present invention.

[0037] FIG. 5 is a flowchart illustrating a digital work permit management method using artificial intelligence and robotic process automation according to an embodiment of the present invention.

[0038] FIG. 6 is a flowchart illustrating a detailed method for determining work permit according to an embodiment of the present invention.

[0039] FIG. 7 is a flowchart illustrating a detailed method for determining entry permission according to an embodiment of the present invention.

[0040] Hereinafter, the present invention will be described with reference to the attached drawings. However, the present invention can be implemented in various different forms and is therefore not limited to the embodiments described herein. In the drawings, irrelevant parts have been omitted for clarity of description, and similar parts have been designated with similar reference numerals throughout the specification.

[0041] Throughout the specification, when a part is said to be "connected (connected, contacted, or coupled)" to another part, this includes not only cases where it is "directly connected," but also cases where it is "indirectly connected" with another part in between. Furthermore, when a part is said to "include" a component, this does not exclude other components, but rather implies that it may include other components, unless otherwise specifically stated.

[0042] The terminology used herein is merely used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this specification, it should be understood that the terms "comprises" or "has" indicate the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but do not exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0043] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

[0044] FIG. 1 is a diagram illustrating an overview of a digital work permit management system using artificial intelligence and robotic process automation according to an embodiment of the present invention.

[0045] As illustrated in FIG. 1, the digital work permit management system (100) can digitize document work managed at a work site and, in particular, automate repetitive and automatable tasks among repetitive tasks that a person must process with a system.

[0046] The digital work permit management system (100) can digitalize and automate work permit work and work execution work that were previously managed manually using robotic process automation (RPA) and artificial intelligence technology.

[0047] The work permit approval request unit (10) is a device that allows a worker or work person to request approval of a work permit in order to perform work, and can perform the following operations: a work permit writing step, a work permit approval request step, a work permit review step, and a work permit decision (approval or rejection) step.

[0048] The work permit approval request unit (10) can create a work permit document in the form of a standard permit registered in the digital work permit management system (100) to simplify the work of the work supervisor when work occurs and request the digital work permit management system (100) to review and approve the work permit.

[0049] The digital work permit management system (100) can issue an access permit token when it decides to approve a work permit.

[0050] Here, the digital work permit management system (100) can safely and efficiently process the process of managing work permits directly through documents at the work site by digitalizing it.

[0051] In addition, the digital work permit management system (100) can minimize work by automating tasks that can be automated among the repetitive tasks that people had to process with the system in the past when digitalized, thereby allowing people to focus on tasks that require decision-making.

[0052] The work execution approval request unit (20) requests work area entry approval for a worker to enter the work area and perform work after work permit approval is completed, and can perform the actions of an entry permit token scan step, a work area entry request step, a safety measure verification step, and an entry permit decision step.

[0053] After a work permit is approved, the digital work permit management system (100) can automatically generate safety measure information based on the pre-work safety inspection meeting (TBM Tool Box Meeting) form. The digital work permit management system (100) can transmit the generated safety measure information to the terminals of workers and work supervisors to notify them of the safety measures.

[0054] Here, the digital work permit management system (100) can automate work execution tasks using CCTV footage, robotic process automation (RPA), and artificial intelligence technology, thereby restricting entry into the workplace and preventing and reducing the occurrence of accidents depending on whether the worker is wearing safety equipment.

[0055] FIG. 2 is a block diagram illustrating the configuration of a digital work permit management system using artificial intelligence and robotic process automation according to an embodiment of the present invention.

[0056] As illustrated in FIG. 2, the digital work permit management system (100) may include a work permit approval request receiving unit (110), a work permit review unit (120), a work permit decision unit (130), an automated recommendation model (140), an access permit token generating unit (150), an access permit approval request receiving unit (160), a safety measure verification unit (170), a safety measure verification model (180), an access permit decision unit (190), a work information collection unit (200), and a work information analysis and storage unit (210).

[0057] The work permit approval request receiving unit (110) can receive data requesting work permit approval from a worker or work person to perform work through the work permit approval request unit.

[0058] Here, the work permit approval request data may include various information regarding work permit approval, such as work name, location, date, time, worker, equipment, work step, and cost.

[0059] The work permit review unit (120) can review work permits based on data received by the work permit approval request receiving unit (110). For example, the work permit review unit (120) can review whether the required format for the work permit request is followed and all required data has been entered. Additionally, the work permits can be classified into similar categories or categorized as suitable for automated work permit approval.

[0060] The work permit decision unit (130) can decide to approve or reject a work permit based on the results performed by the work permit review unit (120).

[0061] Here, the work permit approval request receiving unit (110), work permit review unit (120), and work permit decision unit (130) are implemented with robotic process automation (RPA), which prevents information omission and non-entry of the above components and enables quick and accurate processing when approving multiple work permits.

[0062] The automated recommendation model (140) can automate the classification of approval or rejection of work permits through artificial intelligence learning on work permit request data.

[0063] The specific configuration and steps of the automated recommendation model will be described later with reference to Fig. 3.

[0064] When the work permit decision unit (130) decides to approve a work permit, the entry permit token issuing unit (150) can issue an entry permit token that allows the worker to enter and exit the work area.

[0065] Here, the access authorization token is an authentication program used to verify the user's ID, and various security authentication programs such as QR code, one-time password (OTP), and mobile terminal authentication number can be used.

[0066] The access permission approval request receiving unit (160) can receive data requesting access permission approval for entering the work area.

[0067] For example, when a worker enters an access permission token into a terminal installed in an access area to enter a work area, data requesting approval for access to the work area is generated, and the generated data can be received by an access permission approval request receiving unit (160).

[0068] Here, the entry permit approval request data may include various data related to worker information, such as worker name, affiliation, and photo.

[0069] The safety measure verification unit (170) can use a camera terminal to capture whether workers in the entry area are wearing work clothes or safety equipment.

[0070] Here, the shooting terminal includes a closed circuit television (CCTV), etc., and can shoot a preset shooting range.

[0071] For example, the shooting terminal can preset shooting ranges A, B, and C, and shoot the worker's head area in shooting range A, the face to leg area in shooting range B, and the foot area in shooting range C. The shooting range settings can be categorized into multiple shooting ranges to accurately check whether the worker is wearing a safety helmet, work clothes (including safety equipment), safety shoes, etc.

[0072] The safety measure verification model (180) can use artificial intelligence to recognize objects in images taken by the safety measure verification unit (170) to check whether safety measures are in place and automate the approval or rejection classification of entry permits.

[0073] The specific configuration and steps of the safety measure verification model will be described later with reference to Fig. 4.

[0074] The entry permission decision unit (190) can decide whether to approve or reject the worker's entry permission based on data received from the entry permission approval request receiving unit (160) or the safety measure verification unit (170).

[0075] Here, the safety measure verification unit (170) and the access permission decision unit (190) are implemented using robotic process automation (RPA) to reduce and prevent safety accidents at work sites.

[0076] For example, the access permission decision unit (190) analyzes the access permission approval request data received from the access permission approval request receiving unit (160). Thereafter, the analyzed access permission approval request data is matched / analyzed with the work permission information and the area-specific worker information stored in the work information collection unit (200) or the work information analysis and storage unit (210) described below to determine whether the person is permitted to enter the work area and to decide whether to grant or reject the access permission.

[0077] For example, the entry permission decision unit (190) can decide to approve or reject an entry permission based on information determined in the safety measure verification model (180).

[0078] In addition, the access permission decision unit (190) is linked to the access door control unit (not shown), and the access door control unit can control the opening and closing of the access door and display an open / close status or warning notification with sound / color according to the determined access permission approval or access permission rejection, and can display a warning notification with sound / color if all work clothes or safety equipment are not worn during safety measure verification.

[0079] The work information collection unit (200) can collect work information.

[0080] Here, the task information may include various task information such as task name, location, date, time, worker, equipment, task step, cost, etc.

[0081] The work information analysis and storage unit (210) can analyze and store various work information such as work information, work permit approval information, and entry permit approval information.

[0082] In this way, the work permit approval request receiving unit (110), work permit review unit (120), work permit decision unit (130), safety measure verification unit (170), and access permit decision unit (190) of the digital work permit management system (100) are implemented with robotic process automation (RPA), so that multiple work permits can be approved quickly and accurately and safety accidents can be prevented.

[0083] In addition, the automated recommendation model (140) and safety measure inspection model (170) of the digital work permit management system (100) can quickly and accurately automate the classification of work permit approval decisions and entry permit decisions using artificial intelligence learning.

[0084] FIG. 3 is a block diagram illustrating the configuration of an automated recommendation model according to an embodiment of the present invention.

[0085] As illustrated in FIG. 3, the automated recommendation model (140) is one of the artificial intelligence models that can assign attributes to input data related to work permits and output a classification of whether work permits can be automated or not.

[0086] The automated recommendation model (140) may include a work permit record data collection unit (141), a work permit classification unit (142), an automation target candidate work permit selection unit (143), and a work permit decision automation unit (144).

[0087] The work permit record data collection unit (141) can collect work permit record data.

[0088] Here, the work permit record data relates to previous work permit information, including accumulated results data on work permit approval requests and approval / rejection results. The collected data can be used to classify work permits and train an artificial intelligence system to determine whether work permits can be automated using approval result data for each work permit category.

[0089] The work permit classification unit (142) can classify work permits for input data. Here, the work permit classification unit (142) can classify them into a always approved group, a conditional approved group, and a always rejected group.

[0090] For example, if the approval status of previous work permits A, B, and C is checked, and work permit A is always approved, work permit B is conditionally approved (approved in condition 1, rejected in condition 2), and work permit C is always rejected, then work permits A, B, and C can be classified into the always approved group, the conditionally approved group, and the always rejected group, respectively.

[0091] That is, using artificial intelligence learned from collected data, the work permit classification unit (142) can classify work permit A into the always approved group, work permit B into the conditionally approved group, and work permit C into the always rejected group for the input data.

[0092] The automation target candidate work permit selection unit (143) can select a candidate work permit that can be automated from among those classified in the work permit classification unit (142).

[0093] For example, the automation target candidate work permit selection unit (143) selects work permits A (always approved group) and work permit C (always rejected group) that are considered to be capable of automation.

[0094] Here, it is desirable to exclude the automation target candidate work permit selection unit (143) because work permit B is approved according to conditions and therefore cannot always be approved or always rejected.

[0095] The work permit approval / rejection automation unit (144) can determine the group for which work permit approval / rejection is automated.

[0096] For example, the work permit approval / rejection automation unit (144) determines that work permits that are always approved and work permits that are always rejected can be automated and thus determines them as a group to be automated.

[0097] Accordingly, the automated recommendation model (140) has the advantage of being able to quickly and accurately automate classification of work permit approval decisions using artificial intelligence learning.

[0098] In addition, the automated recommendation model (140) can model automated recommendations including a work permit record data collection step, a work permit classification step, a work permit selection step for automation candidates, and a work permit decision automation step.

[0099] Therefore, for work permits that have already been approved or rejected, as well as work permits that have some different attributes, the automated recommendation model (140) can classify whether the work permits are capable of automation and perform automatic approval or rejection.

[0100] FIG. 4 is a block diagram illustrating the configuration of a safety measure verification model according to an embodiment of the present invention.

[0101] As illustrated in Fig. 4, the safety measure verification model (180) is also an artificial intelligence model, which can assign safety attributes to input data related to safety measures of work and determine and output a classification of whether safety measure verification can be automated or not.

[0102] The safety measure verification model (180) may include a worker image collection unit (181), a safety attribute classification unit (182), and an access permission decision automation unit (183).

[0103] The worker video collection unit (181) can collect videos of workers wearing their clothing or safety equipment taken by the safety measure verification unit (170).

[0104] Here, the above image may include an image captured from a preset range (e.g., head (A), body (B), foot area (C), etc.) in the safety early verification unit (170).

[0105] The safety attribute classification unit (182) can classify the images collected from the worker image collection unit (181) by safety attribute using artificial intelligence.

[0106] Here, the classification by safety attribute can be categorized into a group wearing a hard hat, a group wearing work clothes, and a group wearing safety shoes.

[0107] For example, AI can recognize objects and classify them based on preset criteria, verifying whether workers are wearing all their work clothes and safety equipment as posted in the safety measures information on the TBM form generated by the digital work permit management system, and classifying them by safety attributes.

[0108] If the worker wears a safety helmet, work clothes, and safety shoes as posted in the safety action information, the safety attribute classification unit (182) creates data in the safety shoe wearing group, work clothes wearing group, and safety shoe wearing group. On the other hand, if the worker wears only a safety helmet and work clothes but not safety shoes as posted in the safety action information, the safety attribute classification unit (182) creates data only in the safety shoe wearing group and work clothes wearing group.

[0109] The entry permission decision automation unit (183) can automate the entry permission approval / rejection decision based on the group-specific data generation results of the safety attribute classification unit (182).

[0110] For example, the access permission decision automation unit (183) can compare the safety measure information with the generated data of the safety attribute classification unit (182), and if the generated data are identical, the access permission approval decision can be automated. However, the access permission decision automation unit (183) can compare the safety measure information with the generated data of the safety attribute classification unit (182), and if the generated data are different, the access permission rejection decision can be automated.

[0111] Accordingly, the safety measure verification model (180) has the advantage of being able to quickly and accurately automate the classification of entry permission decisions using artificial intelligence learning.

[0112] Additionally, the safety measure verification model (180) can model safety measure verification, including the worker image collection step, the safety attribute classification step, and the access permission decision automation step.

[0113] FIG. 5 is a flowchart illustrating a digital work permit management method using artificial intelligence and robotic process automation according to an embodiment of the present invention.

[0114] In step (S110), the digital work permit management system (100) receives data requesting work permit approval from a worker or work associate to enter a work area.

[0115] Here, the work permit approval request data may include various information regarding work permit approval, such as work name, location, date, time, worker, equipment, work step, and cost.

[0116] In step (S120), the digital work permit management system (100) can automatically classify and determine approval or rejection of a work permit using an automated recommendation model, which is an artificial intelligence model.

[0117] At this time, steps (S110-S120), i.e., the work permit approval request reception step and the work permit decision step, are implemented using robotic process automation (RPA). This prevents information omissions and omissions in these steps and enables fast and accurate processing of multiple work permit approvals.

[0118] Here, the detailed method for determining work permission in step (S120) will be described later with reference to FIG. 6.

[0119] In step (S130), when work permit approval is determined, the digital work permit management system (100) issues an access permit token that allows the worker to enter and exit the work area.

[0120] Here, the access authorization token is an authentication program used to verify the user's ID, and various security authentication programs such as QR code, one-time password (OTP), and mobile terminal authentication number can be used.

[0121] In step (S140), the digital work permit management system (100) can receive data requesting approval for work area entry permit to enter the work area.

[0122] In step (S150), the digital work permit management system (100) can automatically classify and determine approval or rejection of an entry permit using a safety measure verification model, which is an artificial intelligence model.

[0123] At this time, step (S150) can be implemented as a robotic process (RPA), including the safety measure verification step and the entry permission decision step, to reduce and prevent safety accidents at the work site.

[0124] Here, the detailed method for determining entry permission in step (S150) will be described later with reference to FIG. 7.

[0125] FIG. 6 is a flowchart illustrating a detailed method for determining work permit according to an embodiment of the present invention.

[0126] In step (S121), the digital work permit management system collects work permit record data of the subject of the work permit approval request and analyzes it.

[0127] Here, the digital work permit management system can perform a review of the work permit based on the data received in the work permit approval request receiving unit.

[0128] Work permit review can be performed based on data received from the work permit approval request receiving unit. For example, work permit review can verify that the required format is followed and all required data has been entered. Work permits can also be categorized into similar categories or categorized as suitable for automated work permit approval.

[0129] In step (S122), the digital work permit management system identifies the automation target using an automated recommendation model (140), which is an artificial intelligence model.

[0130] Here, the automated recommendation model (140) can automate the classification of approval or rejection of work permits through artificial intelligence learning on work permit request data.

[0131] The automated recommendation model (140) can model automated recommendations including a work permit record data collection step, a work permit classification step, a work permit selection step for automation candidates, and a work permit decision automation step.

[0132] For example, when checking the approval status of work permits A, B, and C, work permit A was always approved, work permit B was conditionally approved (approved under the first condition, rejected under the second condition), and work permit C was always rejected. The results of this AI training are as follows.

[0133] The work permit classification step can be used to classify work permit A into the always approved group, work permit B into the conditionally approved group, and work permit C into the always rejected group.

[0134] Afterwards, in the stage of selecting work permits for automation, work permits A (always approved group) and work permit C (always rejected group) that are considered to be amenable to automation can be selected from among the classified work permits.

[0135] Here, in the automation target candidate work permit selection step, work permit B is approved conditionally, so it is desirable to exclude it as it is impossible to always approve or always reject.

[0136] Afterwards, in the Work Permit Approval / Rejection Automation step, you can decide to automate which work permits are always approved and which work permits are always rejected.

[0137] Therefore, for work permits that have already been approved or rejected, as well as work permits that have some different attributes, the automated recommendation model (140) can classify whether the work permits are capable of automation and perform automatic approval or rejection.

[0138] In step (S123), the digital work permit management system determines whether automation is to be executed.

[0139] If work permit automation is executed, in step (S124), the digital work permit management system can automatically approve or reject the work permit.

[0140] On the other hand, if work permit automation is not executed, at step (S125), the digital work permit management system recognizes the work permit as requiring a decision on review and approval, and sends a review and approval request message to the approval manager.

[0141] Here, the approval officer can review and decide on a work permit (approval / rejection) for work permits that require human decision-making.

[0142] Thus, the digital work permit management system effectively digitizes the process of manually managing work permits on the job site, enabling safe and efficient processing. Furthermore, the digital work permit management system automates repetitive tasks previously handled by humans, allowing people to focus on tasks requiring decision-making, thereby minimizing workload.

[0143] FIG. 7 is a flowchart illustrating a detailed method for determining entry permission according to an embodiment of the present invention.

[0144] In step (S151), the digital work permit management system scans the access permit token.

[0145] An access authorization token is a security card that allows workers to enter and exit the work area, and is an authentication program used to verify the user's identity.

[0146] For example, access authorization tokens can use various security authentication programs such as QR codes, one-time passwords (OTPs), and mobile device authentication numbers.

[0147] In step (S152), the digital work permit management system verifies whether the worker is permitted to enter the work area.

[0148] For example, when a worker enters an access permission token into a terminal installed in an access area to enter a work area, data requesting approval for access to the work area is generated, and the generated data can be received by an access permission approval request receiving unit.

[0149] Here, the entry permit approval request data may include various data related to worker information, such as worker name, affiliation, and photo.

[0150] Additionally, the digital work permit management system can determine whether to grant or deny a worker's entry permission based on data received from the entry permit approval request receiving unit.

[0151] For example, a digital work permit management system analyzes access permit approval request data received from the access permit approval request receiving unit. The analyzed access permit approval request data is then matched / analyzed with the work permit information (D1) from the work information collection unit and the zone-specific worker information (D2) stored in the work information analysis and storage unit to determine whether the individual is authorized to enter the work area.

[0152] In step (S153), the digital work permit management system determines whether the worker is permitted to enter based on the information confirmed in step (S152).

[0153] If the worker is not permitted to enter, in step (S154), the digital work permit management system rejects the worker's entry permit and displays a warning notification with sound / color.

[0154] On the other hand, if the worker is allowed to enter, in step (S155), the digital work permit management system verifies the implementation of safety measures, i.e., whether the worker present in the entry area is wearing work clothes or safety equipment.

[0155] First, the digital work permit management system can use a camera terminal to capture whether workers in the entry area are wearing work clothes or safety equipment.

[0156] The shooting terminal includes a closed circuit television (CCTV), etc., and can shoot a preset shooting range.

[0157] For example, the shooting terminal can preset shooting ranges A, B, and C, and shoot the worker's head area in shooting range A, the face to leg area in shooting range B, and the foot area in shooting range C. The shooting range settings can be categorized into multiple shooting ranges to accurately check whether the worker is wearing a safety helmet, work clothes (including safety equipment), safety shoes, etc.

[0158] Afterwards, the digital work permit management system verifies safety measures using an artificial intelligence model, the safety measure verification model (180).

[0159] The safety measure verification model (180) can use artificial intelligence to recognize objects in images taken by the safety measure verification unit to check whether safety measures are in place and automate the approval or rejection classification of entry permits.

[0160] The safety measure verification model (180) can model safety measure verification, including the worker image collection step, safety attribute classification step, and access permission decision automation step.

[0161] For example, in the worker video collection stage, videos of workers wearing their clothing or safety equipment, taken by the safety measure verification unit, can be collected. These videos can include videos taken from multiple preset areas (e.g., head (A), body (B), and foot area (C)) by the early safety verification unit.

[0162] In the safety attribute classification stage, images collected during the worker image collection stage can be classified by safety attribute using AI. These safety attribute classifications can be categorized into groups wearing hard hats, working clothes, and safety shoes. For example, AI can recognize objects and classify them based on preset criteria. It can verify whether workers are wearing all work clothes and safety equipment as listed in the safety measures information on the TBM form generated by the digital work permit management system, and then classify these by safety attribute.

[0163] If the worker wore a hard hat, work clothing, and safety shoes as listed in the safety precautions information, the safety attribute classification step generates data for the safety shoes wearing group, work clothing wearing group, and safety shoes wearing group. Conversely, if the worker wore only a hard hat and work clothing, but not safety shoes, as listed in the safety precautions information, the safety attribute classification step generates data only for the safety shoes wearing group and work clothing wearing group.

[0164] The automated access permit decision stage can automate access permit approval / rejection decisions based on the group-specific data generation results from the safety attribute classification section. For example, the automated access permit decision stage can compare safety measure information with the generated data from the safety attribute classification section. If the generated data are identical, the access permit approval decision can be automated. However, the automated access permit decision stage can also compare safety measure information with the generated data from the safety attribute classification section. If the generated data are different, the access permit rejection decision can be automated.

[0165] In step (S156), the digital work permit management system determines whether safety measures have been completed based on the information verified in step (S155).

[0166] If safety measures have been completed by correctly wearing the worker's work clothes or safety equipment, in step (S157), the digital work permit management system approves the worker's entry permit.

[0167] If the safety measures are not completed because the worker is not wearing the work clothes or safety equipment correctly, in step (S154), the digital work permit management system rejects the worker's entry permit and displays a warning notification with sound / color.

[0168] Here, the digital work permit management system can be linked to the access control unit (not shown) of the access area to control the opening and closing of the access door and indicate the opening and closing status with sound / color according to the determined approval or rejection of the access permit.

[0169] In this way, the digital work permit management system can automate work execution tasks by utilizing CCTV footage, robotic process automation (RPA), and artificial intelligence technologies during the work execution stage, thereby restricting entry into the workplace based on whether workers are wearing safety equipment and preventing and reducing the occurrence of accidents.

[0170] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will readily appreciate that the present invention can be readily modified into other specific forms without altering the technical spirit or essential characteristics of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single entity may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined manner.

[0171] The scope of the present invention is indicated by the claims set forth below, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention.

[0172] The mode for carrying out the invention is described together with the best mode for carrying out the invention.

[0173] According to an embodiment of the present invention, by automating digital work authorization and work execution tasks using robotic process automation (RPA) and artificial intelligence technologies, work errors can be minimized and repetitive tasks can be automatically processed.

[0174] According to an embodiment of the present invention, the process of directly managing work permits and work performance through documents at a work site can be digitized to ensure safe and efficient processing.

Claims

1. In the digital work permit management system, A work permit approval request receiving unit that receives data requesting work permit approval to perform work; A work permit decision unit that determines whether to approve or reject the work permit using the first robotic process automation (RPA) and automation recommendation model for the above work permit approval request data; An access permit token issuing unit that issues an access permit token when the above work permit approval is decided; An access permission approval request receiving unit for receiving data requesting approval of access to the work area for entry into the work area; A safety measure verification unit that photographs workers present in the entry area and verifies safety measures using a second robotic process automation (RPA) and safety measure verification model; and An access permission decision unit that receives data from the above access permission approval request receiving unit and the above safety measure verification unit and determines whether to allow a worker to enter using the second robot process automation. A digital work permit management system that includes .

2. In paragraph 1, The above automated recommendation model automates the classification of approval or rejection of the work permit through artificial intelligence learning on the work permit request data. Digital work permit management system.

3. In paragraph 2, The above automated recommendation model is, A work permit record data collection unit that collects the above work permit record data; A work permit classification unit that classifies the work permit of the work permit record data using the artificial intelligence; An automation candidate work permit selection unit that selects a candidate work permit that can be automated from among the above-mentioned classifications; and The Work Permit Decision Automation Department determines the group for which the above work permit approval or rejection is automated. A digital work permit management system that includes .

4. In paragraph 3, The above work permit classification department is classified into the always approved group, the conditionally approved group and the always rejected group. The above automation target candidate work permit selection unit selects the above always approved group and the above always rejected group for which automation is possible. Digital work permit management system.

5. In paragraph 2, The above safety measure verification model automates the approval or rejection classification of the entry permit through artificial intelligence learning on the video taken by the safety measure verification unit. Digital work permit management system.

6. In paragraph 5, The above safety measure verification model is: A worker video collection unit that collects videos taken by the above safety measure verification unit; A safety attribute classification unit that classifies the safety attributes of the image using the artificial intelligence; and An access permit decision automation unit that determines the group for which the access permit approval or rejection is automated based on the above attribute classification. A digital work permit management system that includes .

7. In paragraph 6, The above safety attribute classification section is classified into a safety helmet wearing group, a work clothing wearing group, and a safety shoe wearing group. Digital work permit management system.

8. In paragraph 1, A work permit review unit that receives data from the work permit approval request receiving unit and performs a review of the work permit; A work information collection unit that collects work information including work permit information; and A work information analysis and storage unit that analyzes and stores work information including the above work information, the above work permit approval information, and the above entry permit approval information. A digital work permit management system that includes more.

9. In paragraph 8, The above work permit approval request receiving unit, the work permit review unit, and the work permit decision unit are implemented with the first robotic process automation (RPA), The above safety measure verification unit and the above entry permission decision unit are implemented with the second robotic process automation (RPA). Digital work permit management system.

10. In paragraph 1, After the above work permit approval is completed, safety measure information is automatically generated based on the pre-work safety review meeting (TBM) form. Digital work permit management system.

11. In the method of managing digital work permits, A step of receiving data requesting approval for a work permit to perform work; A step of determining whether to approve or reject the work permit using the first robotic process automation (RPA) and automation recommendation model for the received work permit approval request data; Step of issuing an entry permit token when the above work permit approval is decided; A step of requesting approval for entry into the work area for entering the work area; A step of photographing workers present in the entry area and verifying safety measures using a second robotic process automation (RPA) and safety measure verification model; and A step of receiving data from the above entry permission approval request step and the above safety measure verification step and determining worker entry permission using the second robotic process automation (RPA). A method for managing digital work authorization, including:

12. In paragraph 11, The steps for deciding whether to approve or reject the above work permit are: A step of analyzing the work permit record data of the subject of the work permit approval request; A step of identifying an automation target using the automated recommendation model for the above analysis data; and A step of confirming the above automation target and determining whether to execute automation of the above work permit decision; and A step for deciding whether to approve or reject a work permit based on the results of the automated execution of the above work permit decision. A method for managing digital work authorization, including:

13. In paragraph 12, The steps for deciding whether to approve or reject the above work permit are: If the above work permit automation is possible, a step for determining automatic approval or rejection; and If the above work permit automation is not possible, the step of recognizing the work permit as requiring a decision on review and approval and sending a review and approval request message to the approval manager A method for managing digital work authorization, including:

14. In paragraph 11, The step of verifying safety measures using the above second robotic process automation (RPA) and safety measure verification model is as follows: A step of scanning the above entry permission token; A step of confirming whether a worker is permitted to enter the work area based on work permit information and worker information by area; A step of determining whether the worker is eligible for entry based on the above-mentioned confirmed information; A step of verifying the safety measures taken by the worker present in the access area using the above safety measures verification model; After verifying the performance of the above safety measures, a step of determining whether the safety measures have been completed; and Step to decide whether to approve or reject entry permission based on the results of completion of the above safety measures A method for managing digital work authorization, including:

Images