Constructional engineering quality inspection result identification method, device and system and storage medium

Abstract

The invention discloses a construction engineering quality inspection result identification method, device and system, and a storage medium. The method comprises the steps of obtaining a to-be-processed video of a target construction engineering; performing gesture recognition on the to-be-processed video to obtain gesture information contained in the to-be-processed video; and obtaining a quality inspection result in the target building engineering based on the gesture information. Through the method, the quality inspection efficiency of the constructional engineering can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of construction engineering processing, and in particular to a method, device, system and storage medium for identifying construction engineering quality inspection results. Background Art

[0002] In project management, in order to improve construction quality, reduce costs, optimize processes and prevent safety accidents, personnel are usually required to conduct on-site inspections and record the quality inspection results of the construction site. For example, examples with good quality inspection results can be used as excellent construction cases for reference by subsequent similar projects to promote continuous improvement of construction quality; and during the inspection process, if potential safety hazards are found in a certain area, they also need to be recorded for subsequent rectification.

[0003] The existing practice is to have personnel conduct on-site inspections and take photos of the situations that need to be recorded and send them to the WeChat group for relevant personnel to review. However, since the content of the photos is not marked during the photo-taking process, the personnel receiving the photos are unclear about the meaning of the photos. Therefore, after receiving the photos, the relevant personnel need to review and verify the photos one by one, resulting in low quality inspection efficiency of the project. Summary of the invention

[0004] The present application provides a method, device, system and storage medium for identifying quality inspection results of construction projects. It can identify gesture information in a video to be processed and obtain quality inspection results in a target construction project based on the meaning represented by the gesture, thereby improving the quality inspection efficiency of the construction project.

[0005] In a first aspect, the present application provides a method for identifying quality inspection results of a construction project, the method comprising:

[0006] Obtain the video to be processed of the target construction project;

[0007] Perform gesture recognition on the video to be processed to obtain gesture information contained in the video to be processed;

[0008] Based on the gesture information, the quality inspection results in the target construction project are obtained.

[0009] A further technical solution is that after obtaining the to-be-processed video of the target construction project, the method further comprises:

[0010] Preprocess the video to be processed to obtain a panoramic image corresponding to each frame of the original image in the video to be processed;

[0011] Perform gesture recognition on the video to be processed to obtain gesture information contained in the video to be processed, including:

[0012] Perform gesture recognition on the panorama corresponding to each frame of the original image in the processed video to obtain a target panorama containing gesture information.

[0013] A further technical solution is to pre-process the video to be processed to obtain a panoramic image corresponding to each frame of the original image in the video to be processed, including:

[0014] Parse the video to be processed to obtain each frame of original image contained in the video to be processed, wherein each frame of original image includes a left fisheye original image and a right fisheye original image;

[0015] The left fisheye original image and the right fisheye original image in each frame of the original image are spliced ​​to obtain a panoramic image corresponding to each frame of the original image.

[0016] A further technical solution is to splice the left fisheye original image and the right fisheye original image in each frame of the original image to obtain a panoramic image corresponding to each frame of the original image, including:

[0017] According to the preset aspect ratio, the left fisheye original image and the right fisheye original image are spliced ​​to obtain the panoramic image corresponding to each frame of the original image.

[0018] A further technical solution is to obtain the quality inspection results of the target construction project based on the gesture information, including:

[0019] The gesture information is matched with the predefined gesture template. If the matching degree is higher than the preset threshold, the quality inspection result of the target construction project is generated according to the meaning corresponding to the gesture information.

[0020] A further technical solution is that the gesture information includes a first gesture, a second gesture and a third gesture;

[0021] After generating the quality inspection result of the target construction project according to the meaning corresponding to the gesture information, the method further includes:

[0022] If the gesture information is the first gesture, the panoramic image corresponding to the gesture information is saved and marked as an excellent case;

[0023] If the gesture information is the second gesture, the panoramic image corresponding to the gesture information is saved and marked as a problem case;

[0024] If the gesture information is the third gesture, the panoramic image corresponding to the gesture information is saved and marked as a problem-solved case.

[0025] A further technical solution is to obtain the video to be processed of the target construction project, including:

[0026] A 360 camera or a hard hat with a 360 camera is used to obtain a video to be processed of the target construction project.

[0027] In a second aspect, the present application provides a device for identifying quality inspection results of a construction project, the identification device comprising:

[0028] An acquisition unit, used for acquiring a to-be-processed video of a target construction project;

[0029] A recognition unit, used for performing gesture recognition on the video to be processed to obtain gesture information contained in the video to be processed;

[0030] The analysis unit is used to obtain the quality inspection result of the target construction project based on the gesture information.

[0031] In a third aspect, the present application provides a system for identifying quality inspection results of construction projects. The system for identifying quality inspection results of construction projects includes a memory and a processor. The memory is used to store program data, and the processor is used to execute program data to implement the steps of any of the above methods.

[0032] In a fourth aspect, the present application provides a computer-readable storage medium, which is used to store a computer program, and when the computer program is executed by a processor, it is used to implement the steps of any of the above methods.

[0033] The beneficial effect of the present application is as follows: Different from the prior art, the present application directly obtains the video to be processed of the target construction project. Since the video to be processed contains gesture information, and information such as the type and position of the gesture can represent specific quality inspection results and corresponding specific areas, therefore, by identifying the gesture information in the video to be processed, it can be automatically associated with the quality inspection results in the target construction project according to the meaning represented by the gesture. In this way, the relevant personnel receiving the photos can directly understand the meaning of a certain frame of image in the video to be processed based on the gesture information, without having to check and verify the taken photos one by one as in the prior art, which helps to reduce the time of manual operation and improve work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0035] Figure 1 It is a flowchart of the first embodiment of the method for identifying the quality inspection results of a construction project provided by the present application;

[0036] Figure 2 It is a structural schematic diagram of an embodiment of a computer-readable storage medium provided by the present application. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It will be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only some but not all structures related to the present application are shown in the drawings. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0038] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0039] In project management, in order to improve construction quality, reduce costs, optimize processes and prevent safety accidents, personnel are usually required to conduct on-site inspections and record the quality inspection results of the construction site. For example, examples with good quality inspection results can be used as excellent construction cases for reference by subsequent similar projects to promote continuous improvement of construction quality; and during the inspection process, if potential safety hazards are found in a certain area, they also need to be recorded for subsequent rectification.

[0040] There are currently two common practices: the first is to send photos taken on site to the relevant responsible persons via WeChat; the second is to use a special application (APP) to record the problem.

[0041] For the first method, since the content of the photos is not marked during the process of taking photos, the person receiving the photos is not clear about the meaning of the photos. Therefore, the relevant personnel need to check and verify the photos one by one after receiving them, resulting in low work efficiency. In addition, the photos taken are difficult to archive automatically, and there is a lack of systematic recording and tracking mechanism, which is not conducive to subsequent data analysis, making it difficult for managers to grasp the progress and effect of problem rectification.

[0042] Although the second method is more formal than WeChat and provides more detailed recording options, the process of recording problems is cumbersome and usually takes several minutes for the relevant personnel to complete the recording of a problem. In addition, when recording problems, it is often difficult to fully describe the details of the problem, especially the lack of accurate location information, which makes it difficult for relevant personnel to accurately locate the area where the problem occurred.

[0043] Therefore, in order to solve the above-mentioned technical problems, the present application provides a method for identifying the quality inspection results of a construction project. Please refer to the following embodiments for details.

[0044] See also Figure 1 , Figure 1 1 is a flow chart of the first embodiment of the method for identifying the quality inspection results of a construction project provided by the present application. The method comprises:

[0045] Step 110: Obtain the video to be processed of the target construction project.

[0046] The video to be processed may be an on-site surveillance video or a specially recorded inspection video.

[0047] Step 120: Perform gesture recognition on the video to be processed to obtain gesture information contained in the video to be processed.

[0048] Among them, AI algorithms can be used to recognize gestures, thereby extracting gesture information that appears in the video to be processed. These gestures can represent different meanings. For example, a specific gesture may indicate the location, type or severity of a quality problem.

[0049] Step 130: Obtain quality inspection results of the target construction project based on the gesture information.

[0050] In some implementations, a thumbs-up gesture, an “OK” gesture, a hand-shaking gesture, a stomping gesture, an “X” gesture, etc. may be used.

[0051] For example, if a thumbs-up gesture appears in a frame of the video to be processed, it can indicate that this part is well done and can be used as an excellent case for reference by other parts or future projects.

[0052] For another example, if an "OK" gesture appears in a certain frame of the video to be processed, it may mean that there was a problem in this part before, and it was found during this inspection that the problem has been solved, and the inspector made a corresponding confirmation gesture (such as an "OK" gesture), indicating that the previous problem has been properly handled.

[0053] For another example, if an "X" gesture appears in a frame of the video to be processed, it may indicate that there is a potential safety hazard in this part and subsequent rectification is required.

[0054] This embodiment directly obtains the video to be processed of the target construction project. Since the video to be processed contains gesture information, and information such as the type and position of the gesture can represent specific quality inspection results and corresponding specific areas, by identifying the gesture information in the video to be processed, it can be automatically associated with the quality inspection results in the target construction project according to the meaning represented by the gesture. In this way, the relevant personnel who receive the photos can directly understand the meaning of a certain frame of image in the video to be processed based on the gesture information, without having to check and verify the taken photos one by one as in the prior art, which helps to reduce the time of manual operation and improve work efficiency.

[0055] In some implementations, a 360-degree camera or a hard hat with a 360-degree camera may be used to acquire a video to be processed of the target construction project.

[0056] Among them, relevant personnel can conduct on-site inspections by holding a 360 camera or wearing a safety helmet equipped with a 360 camera.

[0057] For example, relevant personnel wear a safety helmet equipped with a 360 camera and inspect a building under construction. During the on-site inspection, if they walk into the kitchen and find that the cabinets are installed well, they can stop and make a thumbs-up gesture. Then the staff continues to walk, and if they walk into the bedroom and find that there is a problem with the placement of the bed, they can stop by the bed and make an "X" gesture, and so on. After the entire building is inspected, a video to be processed can be generated for the building, and the recorded video file can be transferred from the camera to a computer or server, so that the system can obtain the video to be processed of the target construction project.

[0058] Since 360 ​​cameras have 360-degree panoramic cameras, and 360-degree panoramic cameras can capture a complete view of the entire construction site, using 360 cameras or hard hats with 360 cameras can more comprehensively capture the situation on the construction site, including potential problem areas. Secondly, by using 360 cameras or hard hats with 360 cameras, inspectors can complete a larger range of inspections in a shorter time without having to move or adjust the camera position multiple times, thus saving time and energy.

[0059] Refer to the second embodiment of the method for identifying the quality inspection results of a construction project provided in this application. The method includes:

[0060] Step 210: Obtain the video to be processed of the target construction project.

[0061] Step 220: pre-process the video to be processed to obtain a panoramic image corresponding to each frame of the original image in the video to be processed.

[0062] Among them, the preprocessing may include parsing processing and stitching processing. The collected video to be processed is parsed to decompose the video to be processed into a series of continuous image frames; and then the decomposed image frames are stitched using an image stitching algorithm to obtain a panoramic image corresponding to each frame of the original image.

[0063] In some embodiments, preprocessing may also include image correction, such as brightness and contrast adjustment, and noise removal, to improve the accuracy and efficiency of subsequent processing.

[0064] For example, the captured video may be segmented to decompose it into a series of consecutive image frames.

[0065] Step 240: Perform gesture recognition on the panoramic image corresponding to each frame of the original image in the video to be processed to obtain a target panoramic image containing gesture information.

[0066] For example, the video to be processed includes 50 frames of original images. After obtaining the panoramas corresponding to the 50 frames of original images, the system can perform gesture recognition on the 50 frames of panoramas to obtain a target panorama containing gesture information. For example, the 12th frame of panorama, the 26th frame of panorama, the 32nd frame of panorama, the 35th frame of panorama, and the 46th frame of panorama all contain gesture information, then the 12th frame of panorama, the 26th frame of panorama, the 32nd frame of panorama, the 35th frame of panorama, and the 46th frame of panorama can be used as target panoramas.

[0067] Step 260: Obtaining a quality inspection result of the target construction project based on the gesture information in the target panoramic image.

[0068] For example, if the target panoramic image is a kitchen range hood and there is an "X" gesture at the range hood, then it can be concluded that the quality inspection result of the range hood is improper installation and needs to be reinstalled.

[0069] In this way, by preprocessing the video to be processed to obtain a panoramic image corresponding to each frame of the original image in the video to be processed, and performing gesture recognition based on the panoramic image, the situation at the construction site can be recorded more comprehensively and accurately, the inspection efficiency and accuracy can be improved, the digitization and intelligence of project management can be promoted, and the quality and safety of the entire construction project can be improved.

[0070] Refer to the third embodiment of the method for identifying the quality inspection results of a construction project provided in this application. The method includes:

[0071] Step 310: Obtain the video to be processed of the target construction project.

[0072] Step 320: Parse the video to be processed to obtain each frame of original image contained in the video to be processed.

[0073] Each frame of the original image includes a left fisheye original image and a right fisheye original image.

[0074] Since the panoramic camera uses two fisheye lenses to capture images, each frame of the captured original image includes a left fisheye original image and a right fisheye original image.

[0075] Step 330: splicing the left fisheye original image and the right fisheye original image in each frame of the original image to obtain a panoramic image corresponding to each frame of the original image.

[0076] In some implementations, the following process may be used for splicing:

[0077] 1) Perform preliminary correction on the left fisheye original image and the right fisheye original image to remove lens distortion.

[0078] 2) Use the SI FT algorithm to detect key points in the two original images, the left fisheye original image and the right fisheye original image.

[0079] 3) Find matching point pairs by comparing the descriptors of key points in the left fisheye original image and the right fisheye original image.

[0080] 4) The RANSAC algorithm or other methods may be used to estimate the transformation matrix (such as affine transformation, rigid body transformation, etc.) between the left fisheye original image and the right fisheye original image.

[0081] 5) The two images are fused into the same coordinate system according to the estimated transformation matrix.

[0082] 6) Handle pixel conflicts in overlapping areas and select the most appropriate pixel value (through averaging, weighted averaging or other strategies).

[0083] 7) If there are holes or missing parts, the missing pixels can be supplemented by using boundary extension or interpolation filling methods.

[0084] In this way, a complete panoramic image, namely a panoramic image, can be obtained by splicing the left fisheye original image and the right fisheye original image.

[0085] In some implementations, the left fisheye original image and the right fisheye original image may be spliced ​​according to a preset aspect ratio to obtain a panoramic image corresponding to each frame of the original image.

[0086] Among them, the preset aspect ratio may be 2:1.

[0087] Step 340: Perform gesture recognition on the panoramic image corresponding to each frame of the original image in the video to be processed to obtain a target panoramic image containing gesture information.

[0088] Step 350: Obtain quality inspection results of the target construction project based on the gesture information.

[0089] Refer to the fourth embodiment of the method for identifying the quality inspection results of a construction project provided by this application. The method includes:

[0090] Step 410: Obtain the video to be processed of the target construction project.

[0091] Step 420: parse the video to be processed to obtain each frame of original image contained in the video to be processed.

[0092] Wherein, each frame of original image includes a left fisheye original image and a right fisheye original image;

[0093] Step 430: splicing the left fisheye original image and the right fisheye original image in each frame of the original image to obtain a panoramic image corresponding to each frame of the original image.

[0094] Step 440: Perform gesture recognition on the panoramic image corresponding to each frame of the original image in the video to be processed to obtain a target panoramic image containing gesture information.

[0095] Step 450: Match the gesture information in the target panoramic image with the predefined gesture template. If the matching degree is higher than a preset threshold, generate the quality inspection result in the target construction project according to the meaning corresponding to the gesture information.

[0096] The predefined gesture template may include a gesture diagram and a quality inspection result corresponding to the gesture. For example, the predefined gesture template may be the following Table 1:

[0097] Table 1

[0098]

[0099]

[0100] In some embodiments, a key point detection algorithm (such as OpenPose, MediaPipe Hands, etc.) can be used to detect key points of the hand, such as fingertips, joints, etc., and a gesture feature vector is constructed based on the position information of the key points. Then, the similarity between the current gesture feature vector and the predefined gesture template is calculated.

[0101] The similarity between the current gesture feature vector and the predefined gesture template may be calculated using a distance metric (such as Euclidean distance), a correlation coefficient, or the like.

[0102] In other implementations, a trained AI model may be used for gesture recognition to automatically identify the gesture type in the video to be processed.

[0103] In some implementations, the gesture information includes a first gesture, a second gesture, and a third gesture. After generating the quality inspection result of the target construction project according to the meaning corresponding to the gesture information, the following steps may also be included:

[0104] Step 510: If the gesture information is the first gesture, the panoramic image corresponding to the gesture information is saved and marked as an excellent case.

[0105] Among them, the first gesture can be a thumbs-up gesture, a “yeah” gesture, etc.

[0106] Step 520: If the gesture information is the second gesture, the panoramic image corresponding to the gesture information is saved and marked as a problem case.

[0107] Among them, the second gesture can be a tap gesture, an "X" gesture, a shaking hand gesture, etc.

[0108] Step 530: If the gesture information is the third gesture, the panoramic image corresponding to the gesture information is saved and marked as a problem-solved case.

[0109] Among them, the third gesture may be an “OK” gesture.

[0110] It should be noted that the type and meaning of the gesture can be flexibly set according to actual conditions to meet the quality inspection requirements in different scenarios, and this application does not limit this.

[0111] Based on the above embodiments, this application adopts a gesture recognition method, which enables quality inspectors to quickly give a building quality evaluation through simple gestures, without the need to record additional text or use complex software tools. The evaluation can be completed by making specific gestures, which helps to simplify the operation process and improve the efficiency of quality inspection work. Secondly, the relevant personnel who receive the video to be processed can automatically identify the gesture information contained in the video to be processed through the system, and can automatically record and classify the target panorama containing the gesture information for later viewing and analysis, which helps to improve the intelligent level of data management.

[0112] Corresponding to the method for identifying the construction project quality inspection results in the above embodiment, the present application also provides a device for identifying the construction project quality inspection results, and the device for identifying the construction project quality inspection results includes an acquisition unit, an identification unit and an analysis unit.

[0113] The acquisition unit is used to acquire the to-be-processed video of the target construction project;

[0114] The recognition unit is used to perform gesture recognition on the video to be processed to obtain gesture information contained in the video to be processed;

[0115] The analysis unit is used to obtain the quality inspection result of the target construction project based on the gesture information.

[0116] It can be understood that the device for identifying construction project quality inspection results can also include other units to implement the technical solution of any embodiment in the present application.

[0117] The present application also provides a system for identifying construction project quality inspection results, the system comprising a memory and a processor, wherein a computer program is stored on the memory; and the processor is used to implement the following method steps when executing the computer program:

[0118] Obtain the video to be processed of the target construction project;

[0119] Perform gesture recognition on the video to be processed to obtain gesture information contained in the video to be processed;

[0120] Based on the gesture information, the quality inspection results of the target construction project are obtained.

[0121] It can be understood that when the processor is used to execute a computer program, it is also used to implement the technical solution of any embodiment in the present application.

[0122] See also Figure 2 , Figure 2 The structure of an embodiment of a computer-readable storage medium provided by the present application is shown in FIG. 7 . The computer-readable storage medium 70 is used to store a computer program 71. When the computer program 71 is executed by a processor, it is used to implement the following method steps:

[0123] Obtain the video to be processed of the target construction project;

[0124] Perform gesture recognition on the video to be processed to obtain gesture information contained in the video to be processed;

[0125] Based on the gesture information, the quality inspection results of the target construction project are obtained.

[0126] It can be understood that when the computer program 71 is executed by the processor, it is also used to implement the technical solution of any embodiment of the present application.

[0127] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only illustrative, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as two units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0128] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on two network units. Some or all of the units may be selected according to actual needs to achieve the purpose of this embodiment.

[0129] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0130] If the integrated units in the above other embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-On l yMemory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0131] The above are only implementation methods of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for identifying quality inspection results of a construction project, characterized in that: The method comprises: Obtain the video to be processed of the target construction project; Performing gesture recognition on the video to be processed to obtain gesture information contained in the video to be processed; Based on the gesture information, a quality inspection result of the target construction project is obtained.

2. The method for identifying construction engineering quality inspection results according to claim 1, characterized in that: After obtaining the to-be-processed video of the target construction project, the method further includes: Preprocessing the video to be processed to obtain a panoramic image corresponding to each frame of the original image in the video to be processed; The performing gesture recognition on the video to be processed to obtain gesture information contained in the video to be processed includes: Perform gesture recognition on the panoramic image corresponding to each frame of the original image in the video to be processed to obtain a target panoramic image containing the gesture information.

3. The method for identifying construction engineering quality inspection results according to claim 2, characterized in that: The preprocessing of the video to be processed to obtain a panoramic image corresponding to each frame of the original image in the video to be processed includes: Parsing the video to be processed to obtain each frame of original image contained in the video to be processed, wherein each frame of the original image includes a left fisheye original image and a right fisheye original image; The left fisheye original image and the right fisheye original image in each frame of the original image are spliced ​​to obtain a panoramic image corresponding to each frame of the original image.

4. The method for identifying construction engineering quality inspection results according to claim 3, characterized in that: The step of splicing the left fisheye original image and the right fisheye original image in each frame of the original image to obtain a panoramic image corresponding to each frame of the original image includes: According to a preset aspect ratio, the left fisheye original image and the right fisheye original image are spliced ​​to obtain a panoramic image corresponding to each frame of the original image.

5. The method for identifying construction engineering quality inspection results according to claim 1, characterized in that: The obtaining of the quality inspection result of the target construction project based on the gesture information includes: The gesture information is matched with a predefined gesture template, and if the matching degree is higher than a preset threshold, a quality inspection result of the target construction project is generated according to the meaning corresponding to the gesture information.

6. The method for identifying construction engineering quality inspection results according to claim 5, characterized in that: The gesture information includes a first gesture, a second gesture and a third gesture; After generating the quality inspection result of the target construction project according to the meaning corresponding to the gesture information, the method further includes: If the gesture information is the first gesture, the panoramic image corresponding to the gesture information is saved and marked as an excellent case; If the gesture information is the second gesture, the panoramic image corresponding to the gesture information is saved and marked as a problem case; If the gesture information is the third gesture, the panoramic image corresponding to the gesture information is saved and marked as a problem-solved case.

7. The method for identifying construction engineering quality inspection results according to claim 1, characterized in that: The step of obtaining the to-be-processed video of the target construction project includes: The video to be processed of the target construction project is acquired using a 360 camera or a hard hat with a 360 camera.

8. A device for identifying quality inspection results of construction projects, characterized in that: The identification device comprises: An acquisition unit, used for acquiring a to-be-processed video of a target construction project; A recognition unit, configured to perform gesture recognition on the video to be processed to obtain gesture information contained in the video to be processed; An analysis unit is used to obtain a quality inspection result of the target construction project based on the gesture information.

9. A system for identifying quality inspection results of construction projects, characterized in that: The system for identifying the construction project quality inspection results includes a memory and a processor, the memory is used to store program data, and the processor is used to execute the program data to implement the method for identifying the construction project quality inspection results as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program data, and when the program data is executed by a processor, it is used to implement the method for identifying the quality inspection results of a construction project as described in any one of claims 1-7.

Images