An information-based engineering supervision method and system based on big data

Abstract

The present invention relates to the technical field of engineering supervision, and provides an information-based engineering supervision method and system based on big data. The method includes: through text analysis of big data in supervision diary data, identifying the characteristics of engineering supervision situations contained in the big data of types and time occurrence points, and generating corresponding dynamic discrimination frequencies based on the time occurrence characteristics of various engineering supervision situations, so as to enable efficient identification when subsequently judging engineering supervision situations for videos, improve the model identification efficiency, and save computing power costs.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering supervision, and particularly relates to an information-based engineering supervision method and system based on big data. Background Art

[0002] For construction engineering projects, engineering supervision is required to control and record the construction quality and site. However, it is difficult for supervision engineers to conduct comprehensive supervision during on-site inspections, and the efficiency of supervision through videos is low, and the consumption of computing power is extremely high. Summary of the Invention

[0003] The present invention provides an information-based engineering supervision method based on big data, which is used to solve the problem of low efficiency of engineering supervision in the prior art.

[0004] The first aspect of the present invention provides an information-based engineering supervision method based on big data, including:

[0005] Obtain supervision diary data, perform text analysis on the supervision diary data, identify the types of engineering supervision situations existing and the time occurrence points of various engineering supervision situations; aggregate the time points of the same type of engineering supervision situations to obtain multiple concentrated time periods of engineering supervision situations and the number of engineering supervision situations occurring in each concentrated time period;

[0006] Generate a dynamic discrimination frequency of engineering supervision situations according to the concentrated time periods corresponding to each engineering supervision situation and the number of engineering supervision situations;

[0007] Obtain engineering supervision videos, use the recognition models corresponding to each engineering supervision situation preset, and identify the engineering supervision videos according to the dynamic discrimination frequency of engineering supervision situations, and judge and record the existing engineering supervision situations.

[0008] Optionally, the generating a dynamic discrimination frequency of engineering supervision situations according to the concentrated time periods corresponding to each engineering supervision situation and the number of engineering supervision situations is specifically:

[0009] Substitute the concentrated time periods corresponding to each engineering supervision situation and the number of engineering supervision situations into the frequency correction model to obtain the dynamic discrimination frequency of engineering supervision situations in each concentrated time period, and the frequency correction model is specifically:

[0010]

[0011] where f n is the corrected frequency of the nth concentrated time period, f 0 is the standard monitoring frequency, T is the total daily working duration, t n is the duration of the nth concentrated time period, A is the total number of current engineering supervision situations, and a n is the number of engineering supervision situations in the nth concentrated time period.

[0012] Optionally, after generating the new supervision diary data, it further includes:

[0013] When the number of identified engineering supervision problems exceeds the threshold, based on the time points of the new engineering supervision problems, the aggregation interval is corrected, and a frequency correction model is regenerated.

[0014] The second aspect of this application provides an information-based engineering supervision system based on big data, including:

[0015] A data processing module, configured to obtain supervision diary data, perform text analysis on the supervision diary data, identify the types of existing engineering supervision situations and the time occurrence points of various engineering supervision situations; aggregate the time points of the same type of engineering supervision situations to obtain multiple concentrated time periods of engineering supervision situations and the number of engineering supervision situations occurring in each concentrated time period;

[0016] A frequency correction module, configured to generate a dynamic discrimination frequency of engineering supervision situations according to the concentrated time periods and the number of engineering supervision situations corresponding to each engineering supervision situation;

[0017] An engineering supervision module, configured to obtain an engineering supervision video, use the recognition models corresponding to each preset engineering supervision situation, and identify the engineering supervision video at the dynamic discrimination frequency of the engineering supervision situation to judge and record the existing engineering supervision situations.

[0018] Optionally, in the frequency correction module, generating the dynamic discrimination frequency of engineering supervision situations according to the concentrated time periods and the number of engineering supervision situations corresponding to each engineering supervision situation is specifically:

[0019] Substitute the concentrated time periods and the number of engineering supervision situations corresponding to each engineering supervision situation into the frequency correction model to obtain the dynamic discrimination frequency of the engineering supervision situation in each concentrated time period. The frequency correction model is specifically:

[0020]

[0021] where f n is the corrected frequency of the nth concentrated time period, f 0 is the standard monitoring frequency, T is the total daily working hours, t n is the duration of the nth concentrated time period, A is the total number of current engineering supervision situations, and a n is the number of engineering supervision situations in the nth concentrated time period.

[0022] Optionally, in the engineering supervision module, after generating the new supervision diary data, it further includes:

[0023] After the number of identified engineering supervision problems exceeds the threshold, the aggregation interval is corrected based on the time points of the new engineering supervision problems, and a frequency correction model is regenerated.

[0024] The third aspect of the present application provides an information-based engineering supervision method and device based on big data. The device includes a processor and a memory:

[0025] The memory is used to store program codes and transmit the program codes to the processor;

[0026] The processor is used to execute an information-based engineering supervision method according to any one of the first aspect of the present invention according to the instructions in the program codes.

[0027] The fourth aspect of the present application provides a computer-readable storage medium, which is used to store program codes, and the program codes are used to execute an information-based engineering supervision method according to any one of the first aspect of the present invention.

[0028] As can be seen from the above technical solutions, the present invention has the following advantages: By performing text analysis on the big data in the supervision diary data, identifying the characteristics of the engineering supervision situations contained in the big data of the types and time occurrence points, and generating corresponding dynamic discrimination frequencies based on the occurrence time characteristics of various engineering supervision situations, it enables efficient identification when judging the engineering supervision situations of videos subsequently, improves the model identification efficiency, and saves computing power costs. Description of the Drawings

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0030] Figure 1 It is a flowchart of an information-based engineering supervision method based on big data;

[0031] Figure 2 It is a structure diagram of an information-based engineering supervision system based on big data. Detailed Embodiments

[0032] In order to make the objectives, features, and advantages of the present invention more apparent and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the embodiments described below are only a part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0033] The present invention provides an information-based project supervision method based on big data, which is used to solve the problem of low efficiency of project supervision in the prior art.

[0034] Please refer to Figure 1 , Figure 1 which is the first flowchart of an information-based project supervision method based on big data provided by an embodiment of the present invention.

[0035] S100, obtain supervision diary data, perform text analysis on the supervision diary data, identify the types of project supervision situations existing and the time occurrence points of various project supervision situations; aggregate the time points of the same type of project supervision situations to obtain multiple concentrated time periods of project supervision situations and the number of project supervision situations occurring in each concentrated time period;

[0036] It should be noted that the project supervision content recorded by the supervision engineer is stored in the database in digital form. The supervision diary records the time of each project supervision situation, the attendance personnel, the construction location, and the specific content of the project supervision situation. The supervision log will be jointly completed by the project supervision agency. Each supervision personnel fills in the supervision log of the day in their responsible work scope continuously day by day, and it is summarized and filled in by the supervision personnel designated by the chief supervisor. The records in the supervision diary are required to use professional terms and standard language. Therefore, text analysis and recognition can be carried out based on the keywords of various project supervision situations to identify the time points and specific situation types of various project supervision situations recorded in the supervision diary. The classification of project supervision situations includes schedule delay mismatch, unqualified construction quality, non-compliance with construction safety standards, etc. Aggregate the time occurrence points of project supervision situations belonging to the same type. Algorithms such as k-means clustering algorithm or hierarchical clustering can be used to obtain multiple concentrated time periods of project supervision situations. For example, the project supervision situations of non-compliance with construction safety standards may occur more in the middle of working hours. Construction workers will pay attention to wearing safety helmets when they first go to work and near the end of work. For example, during the period from 13:00 to 15:00, which is the time when the temperature is the highest on that day, there are concentrated project supervision situations of non-compliance with construction safety standards where workers do not wear safety helmets. Then, the clustering algorithm aggregates multiple time points to obtain the concentrated time periods of project supervision situations, and each concentrated time period of project supervision situations has the corresponding number of project supervision situations occurring, that is, the total number of recorded corresponding project supervision situations within that time period. And some discrete time points of project supervision situations are regarded as special situations that do not reflect the overall situation occurrence characteristics and are not included in the concentrated time periods of project supervision situations by the clustering algorithm.

[0037] S200. Generate the dynamic discrimination frequency of project supervision situations according to the concentrated time periods corresponding to each project supervision situation and the number of project supervision situations.

[0038] It should be noted that the probability of project supervision situations occurring is relatively low during non-concentrated time periods, while during the concentrated time periods aggregated in the previous step S100, the probability of corresponding project supervision problem situations occurring is higher. And calculate the frequency of project supervision situations occurring within the time period. The higher the frequency, the higher the probability of project supervision situations occurring in this concentrated time period. The detection frequency can be dynamically adjusted adaptively based on the concentrated time period and the number of project supervision situations. Adjust the discrimination frequency corresponding to the probability during the concentrated time period with a high probability of project supervision situations occurring, and maintain the standard discrimination frequency during non-concentrated time periods.

[0039] S300. Obtain the project supervision video, use the recognition models corresponding to each project supervision situation preset, and identify the project supervision video with the dynamic discrimination frequency of project supervision situations to judge the existing project supervision situations and record them.

[0040] It should be noted that monitoring cameras can be installed at the construction site of a construction project to obtain real-time images of the construction site. Supervisors can remotely observe the real-time images of the construction site to understand the working status of construction workers and the progress of the project. For various project supervision situations, corresponding neural network recognition models can be pre-trained. For example, the GPNN graph neural network model can be trained to identify the interaction between people in the construction process and operation procedures in the image to determine whether there are situations where the construction quality does not meet the standards. The neural network human body recognition model can be trained to determine whether a person is wearing a safety helmet, and the GRUs can be trained to generate a scene graph or the F-net can decompose the graph into subgraphs to generate a scene relationship graph to determine whether the construction workers in the image are performing construction operations.

[0041] If the recognition model is continuously used to discriminate each frame of the project supervision video, although it can ensure that every project supervision situation is recorded, it consumes a large amount of computing resources, and there is a great deal of waste of computing power during non-concentrated time periods. Therefore, the preset recognition model can be used to discriminate project supervision situations based on the dynamic discrimination frequency of project supervision situations generated in the foregoing step S200. When the high probability of project supervision situations occurs during the concentrated time period, the corresponding dynamic discrimination frequency is used to increase the discrimination frequency. During non-concentrated time periods, the standard discrimination frequency used may be to perform image discrimination every few minutes, while the probability of project supervision situations during the concentrated time period is high, and the corresponding frequency can reach the discrimination frequency of several seconds each time. After identifying the existing project supervision situations, record the corresponding occurrence time, store it in the supervision diary database, and issue a notification prompt for the occurred project supervision situations to warn of the existing risks.

[0042] Furthermore, image features for enabling the preset model to make judgments can be set in the project supervision video. For example, after detecting that a human body appears in the project supervision image, the neural network model corresponding to the construction safety standards is used for discrimination, reducing the consumption of computing power of the neural network model. And the above-mentioned dynamic discrimination frequency of project supervision situations can be changed from the startup frequency of the preset neural network model to the frequency of starting feature image recognition.

[0043] In this embodiment, through text analysis of the big data in the supervision diary data, the project supervision situation features contained in the big data of the recognition type and time occurrence points are identified, and the corresponding dynamic discrimination frequency is generated based on the occurrence time characteristics of various project supervision situations, enabling efficient identification when subsequently judging project supervision situations in the video, improving the model recognition efficiency, and saving computing power costs.

[0044] The above is the detailed description of the first embodiment of an information-based project supervision method based on big data provided by this application. The following is the detailed description of the second embodiment of an information-based project supervision method based on big data provided by this application.

[0045] In this embodiment, a further information - based project supervision method based on big data is provided. In the foregoing step S200, generating a dynamic discrimination frequency of project supervision situations according to the concentrated time periods corresponding to each project supervision situation and the number of project supervision situations specifically includes:

[0046] Substitute the concentrated time periods corresponding to each project supervision situation and the number of project supervision situations into the frequency correction model to obtain the dynamic discrimination frequency of project supervision situations for each concentrated time period. The frequency correction model is specifically:

[0047]

[0048] where f n is the corrected frequency of the n - th concentrated time period, f 0 is the standard monitoring frequency, T is the total daily working hours, t n is the duration of the n - th concentrated time period, A is the total number of current project supervision situations, and a n is the number of project supervision situations in the n - th concentrated time period; the standard monitoring frequency should correspond to the situation where project supervision situations are evenly distributed within the daily complete working hours, the daily working hours are basically the same, or directly consider a duration of 24 hours. Under the same number of project supervision situations, the shorter the duration of the concentrated time period, the denser the project supervision situations, and the higher the corresponding corrected frequency required. Under the concentrated time periods of the same duration, the more the number of project supervision situations, the denser the project supervision situations, and the higher the corresponding corrected frequency required. The n - th concentrated time period can be the n - th after numbering the time periods of all types of project supervision situations, and the total number of current project supervision situations should be the total number of this type of project supervision situation obtained in the foregoing step S100 under the project supervision situation type corresponding to the n - th concentrated time period.

[0049] Further, after generating the new supervision diary data in the foregoing step S300, it further includes: when the number of identified project supervision problems exceeds the threshold, based on the time points of the new project supervision problems, correct the aggregation interval and regenerate the frequency correction model; it should be noted that after executing the information - based project supervision method of big data in the foregoing step S300 for a period of time, new project supervision problems that occur can be identified. When the number of these project supervision problems exceeds the threshold to a certain extent, the concentrated time period may need to be updated, the dynamic discrimination frequency can be corrected again, and the steps are cycled, and then return to step S100 to aggregate the time points of the same type of project supervision situations to obtain the concentrated time periods of multiple project supervision situations and the number of project supervision situations occurring in each concentrated time period.

[0050] The above is a detailed description of a big data-based informatization project supervision method provided by the present application. The following is a detailed description of an embodiment of a big data-based informatization project supervision system provided by the second aspect of the present application.

[0051] Please refer to Figure 2 , Figure 2 which is a structure diagram of a big data-based informatization project supervision system. This embodiment provides a big data-based informatization project supervision system, including:

[0052] A data processing module 10, configured to obtain supervision diary data, perform text analysis on the supervision diary data, identify the types of project supervision situations existing and the time occurrence points of various project supervision situations; aggregate the time points of the same type of project supervision situations to obtain multiple concentrated time periods of project supervision situations and the number of project supervision situations occurring in each concentrated time period;

[0053] A frequency correction module 20, configured to generate a dynamic discrimination frequency of project supervision situations according to the concentrated time periods corresponding to each project supervision situation and the number of project supervision situations;

[0054] A project supervision module 30, configured to obtain project supervision videos, use the recognition models corresponding to each preset project supervision situation, and identify the project supervision videos with the dynamic discrimination frequency of project supervision situations to judge the existing project supervision situations and record them.

[0055] Further, in the frequency correction module 20, generating a dynamic discrimination frequency of project supervision situations according to the concentrated time periods corresponding to each project supervision situation and the number of project supervision situations is specifically:

[0056] Substitute the concentrated time periods corresponding to each project supervision situation and the number of project supervision situations into the frequency correction model to obtain the dynamic discrimination frequency of project supervision situations for each concentrated time period. The frequency correction model is specifically:

[0057]

[0058] where f n is the correction frequency of the nth concentrated time period, f 0 is the standard monitoring frequency, T is the total daily working hours, t n is the duration of the nth concentrated time period, A is the total number of current project supervision situations, and a n is the number of project supervision situations in the nth concentrated time period.

[0059] Further, in the project supervision module 30, after generating new supervision diary data, it further includes:

[0060] When the number of identified engineering supervision problems exceeds the threshold, based on the time points of the new engineering supervision problems, the aggregation interval is corrected, and a frequency correction model is regenerated.

[0061] The third aspect of this application also provides an information-based engineering supervision method device based on big data, including a processor and a memory: wherein the memory is used to store program codes and transmit the program codes to the processor; the processor is used to execute the above-mentioned information-based engineering supervision method based on big data according to the instructions in the program codes.

[0062] The fourth aspect of this application provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program codes, and the program codes are used to execute the above-mentioned information-based engineering supervision method based on big data.

[0063] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0064] In several embodiments provided by this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0065] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0066] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0067] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0068] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An information-based engineering supervision method based on big data, characterized in that include: Obtain supervision diary data, perform text analysis on the supervision diary data, identify the types of engineering supervision situations that exist and the time points when various types of engineering supervision situations occur; Aggregate the time points of the same type of engineering supervision situations to obtain the concentrated time periods of multiple engineering supervision situations and the number of engineering supervision situations occurring in each concentrated time period; Generate the dynamic identification frequency of the project supervision situation according to the concentrated time period and the number of project supervision situations corresponding to each project supervision situation; Acquire the engineering supervision video, use the preset recognition model corresponding to each engineering supervision situation, identify the engineering supervision video with the dynamic discrimination frequency of the engineering supervision situation, determine the existing engineering supervision situation and record it.

2. According to the information-based engineering supervision method based on big data according to claim 1, it is characterized in that: The dynamic identification frequency of the engineering supervision situation is generated according to the concentrated time period and the number of engineering supervision situations corresponding to each engineering supervision situation, specifically: Substitute the concentrated time period and the number of engineering supervision situations corresponding to each engineering supervision situation into the frequency correction model to obtain the dynamic discrimination frequency of the engineering supervision situation in each concentrated time period. The frequency correction model is specifically: Among them, f n is the correction frequency of the nth concentrated time period, f0 is the standard monitoring frequency, T is the total daily working time, t n is the duration of the nth concentrated time period, A is the total number of current project supervision situations, a n is the number of engineering supervision situations in the nth concentrated time period.

3. An information-based engineering supervision system based on big data, characterized in that: include: The data processing module is used to obtain the supervision diary data, perform text analysis on the supervision diary data, identify the existing types of engineering supervision situations and the time points at which various types of engineering supervision situations occur; aggregate the time points of engineering supervision situations of the same type to obtain the concentrated time periods of multiple engineering supervision situations, and the number of engineering supervision situations occurring in each concentrated time period; The frequency correction module is used to generate the dynamic identification frequency of the engineering supervision situation according to the concentrated time period and the number of engineering supervision situations corresponding to each engineering supervision situation; The engineering supervision module is used to obtain engineering supervision videos, adopt the preset recognition models corresponding to each engineering supervision situation, identify the engineering supervision videos with the dynamic discrimination frequency of the engineering supervision situation, determine the existing engineering supervision situation and record it.

4. According to the information-based engineering supervision system based on big data as described in claim 3, it is characterized in that: In the frequency correction module, the dynamic identification frequency of the engineering supervision situation is generated according to the concentrated time period and the number of engineering supervision situations corresponding to each engineering supervision situation, specifically: Substitute the concentrated time period and the number of engineering supervision situations corresponding to each engineering supervision situation into the frequency correction model to obtain the dynamic discrimination frequency of the engineering supervision situation in each concentrated time period. The frequency correction model is specifically: Among them, f n is the correction frequency of the nth concentrated time period, f0 is the standard monitoring frequency, T is the total daily working time, t n is the duration of the nth concentrated time period, A is the total number of current project supervision situations, a n is the number of engineering supervision situations in the nth concentrated time period.

5. An information-based engineering supervision device based on big data, characterized in that: The device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute an information-based engineering supervision method based on big data as described in any one of claims 1-2 according to the instructions in the program code.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program code, and the program code is used to execute the information-based engineering supervision method based on big data as described in any one of claims 1-2.

Images