An artificial intelligence-based building facade damage detection report automatic generation method and system

Abstract

The application discloses a kind of building facade damage detection report automatic generation method and system based on artificial intelligence, method includes steps: (S1) setting project report specification, formulating initial report template;(S2) reading project metadata information, text information and picture information are filled into initial report template;(S3) the API query instruction of artificial intelligence detection model is generated;(S4) calling API query instruction reads damage detection result, extracts damage information details, and damage picture and damage detection result data are written into initial report template;(S5) based on damage information details, the damage statistical information of project is calculated, and the summary content and overview content in initial report template are generated by calling summary interface;(S6) adjust initial report template to generate final damage detection report;System includes template construction module, information reading module and report generation module, the report of the application is automatically generated, saves time and manpower cost, avoids artificial error.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of report automation, in particular to a building facade damage detection report automatic generation method and system based on artificial intelligence. BACKGROUND

[0002] The types of building facade damage are various, and the positions and forms are complex. The traditional manual detection method is time-consuming and laborious. In recent years, the building damage detection method based on artificial intelligence has developed rapidly. The front-end tool such as unmanned aerial vehicle (UAV) flies to take photos of the building, and the artificial intelligence model trained in advance is used for prediction. After the building damage information is predicted, the building facade damage report needs to be generated according to the detection results. Since the number of photos taken by the UAV is large, and the amount of information of the detection results is large, the method of generating the report by manual work not only needs a large amount of time and labor cost, but also is very easy to make statistical errors. Therefore, it is urgent to provide a building facade damage detection report automatic generation method and system based on artificial intelligence. SUMMARY

[0003] One of the purposes of the present application is to provide a building facade damage detection report automatic generation method based on artificial intelligence, which can automatically generate, save time and labor cost, and avoid manual errors.

[0004] The second purpose of the present application is to provide a building facade damage detection report automatic generation system based on artificial intelligence, which can automatically generate, save time and labor cost, and avoid manual errors.

[0005] To achieve the above purpose, the present application provides a building facade damage detection report automatic generation method based on artificial intelligence, which comprises the following steps:

[0006] (S1) setting a project report specification, and formulating an initial report template according to the project report specification;

[0007] (S2) reading project metadata information, and filling text information and picture information into the initial report template;

[0008] (S3) generating an API query instruction of an artificial intelligence detection model according to the project metadata information;

[0009] (S4) calling the API query instruction of the artificial intelligence detection model in step (S3) to read the damage detection results, extracting damage information details, and writing damage pictures and damage detection result data into the initial report template;

[0010] (S5) calculating damage statistical information of the project based on the damage information details written in step (S4), and calling a summary interface in the artificial intelligence detection model to generate summary content and overview content in the initial report template;

[0011] (S6) Adjusting the initial report template according to the project report specification to generate a final damage detection report.

[0012] Preferably, in step (S1) of the present application, the preparation of the initial report template is completed using Word software, and the content of the initial report template includes cover, table of contents, project summary, project basic information, and damage detection results. The initial report template is formatted and laid out according to the project report specification.

[0013] Preferably, in step (S2) of the present application, the project metadata information is read, the COM interface of Word is called, and the text information and picture information are written into the initial report template.

[0014] Preferably, in the present application, the text information includes the client, the building location, the basic information, the damage detection time, and the equipment information used, and the picture information includes the appearance picture and the design picture of the building.

[0015] Preferably, in step (S3) of the present application, the project metadata information is obtained according to the picture information, and the command sequence of the API query instruction of the artificial intelligence detection model is generated according to the project metadata information.

[0016] Preferably, in step (S4) of the present application, the API query instruction of the artificial intelligence detection model is called to extract the damage detection result data of the detailed damage information, the damage detection result includes the specific type of damage, the number of damage pictures, the location, the detection time, and the damage state, the COM interface of Word is called to fill the damage pictures and the damage detection result data into the initial report template.

[0017] Preferably, in step (S5) of the present application, the damage statistical information is calculated according to the detailed damage information, the COM interface of Word is called to input the damage statistical information, the summary interface of the artificial intelligence detection model is called, and the natural language large model is used to combine the damage statistical information and the text information to generate the summary and the overview content in the initial report template.

[0018] Preferably, in the present application, the damage statistical information includes the total number of pictures, the number of pictures containing damage, and the number of pictures of each type of damage, and the content of the summary and the overview includes the overall project damage degree evaluation, the next work to be done, and the points to be noted.

[0019] Preferably, in step (S6) of the present application, according to the damage statistical information, the content of the summary and the overview, and according to the project report specification, the initial report template is adjusted in detail, including highlighting of the points and adding or deleting of the content, to generate a final detection report.

[0020] This invention also provides an artificial intelligence-based automatic generation system for building facade damage detection reports, comprising:

[0021] The template building module is used to acquire images of building facades and to build an artificial intelligence detection model using these images.

[0022] The information reading module is used to read, detect, and statistically analyze damage images of building facades using an artificial intelligence detection model.

[0023] The report generation module is used to automatically generate an inspection report based on the damage detection results generated by the information reading module, thus completing the automatic generation of the building facade damage inspection report.

[0024] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0025] The present invention provides an artificial intelligence-based method and system for automatically generating building facade damage detection reports, which realizes the automated generation of detection reports, greatly saves time and labor costs, avoids human error, and improves the accuracy of detection reports. Attached Figure Description

[0026] Figure 1 This is a flowchart of the artificial intelligence-based automatic generation method for building facade damage detection reports according to the present invention.

[0027] Figure 2 This is the cover image of the building facade damage detection report of the present invention;

[0028] Figure 3 This is a diagram of the AI-based automatic generation system for building facade damage detection reports according to the present invention. Detailed Implementation

[0029] To illustrate the technical content and structural features of the present invention in detail, the following description, in conjunction with the embodiments and accompanying drawings, provides further explanation. Obviously, the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0030] Combination Figures 1-2 As shown, the artificial intelligence-based method for automatically generating building facade damage detection reports of the present invention includes the following steps:

[0031] (S1) Set the project report specification, and formulate an initial report template according to the project report specification. Specifically, in step (S1), the formulation of the initial report template is completed by using Word software. The content of the initial report template includes the cover, table of contents, project summary, project basic information, and damage detection results. The initial report template is formatted and typeset according to the project report specification.

[0032] (S2) Read the project metadata information, and fill in the text information and picture information into the initial report template. Specifically, in step (S2), the project metadata information is read, the COM interface of Word is called, and the text information and picture information are written into the initial report template. More specifically, the text information includes the principal, building location, basic information, damage detection time, and equipment information used. The picture information includes the appearance diagram and design diagram of the building.

[0033] (S3) Generate an API query instruction of the artificial intelligence detection model according to the project metadata information. Specifically, in step (S3), the project metadata information is collected according to the picture information, and the command sequence of the API query instruction of the artificial intelligence detection model is generated according to the project metadata information.

[0034] (S4) Call the API query instruction of the artificial intelligence detection model in step (S3) to read the damage detection results, extract the damage information details, and write the damage pictures and damage detection result data into the initial report template. Specifically, in step (S4), the API query instruction of the artificial intelligence detection model is called, the damage detection result data of the damage information details is extracted, the damage detection results include the specific type of damage, the number of damage pictures, the location, the detection time, and the damage state, and the COM interface of Word is called to fill in the damage pictures and damage detection result data into the initial report template.

[0035] (S5) Calculate the damage statistical information of the project based on the damage information details written in step (S4), and call the summary interface in the artificial intelligence detection model to generate the summary content and the overview content in the initial report template. Specifically, in step (S5), the damage statistical information is calculated according to the damage information details, the COM interface of Word is called to input the damage statistical information, and the summary interface of the artificial intelligence detection model is called to combine the damage statistical information and the text information to generate the summary and the overview content in the initial report template using the natural language large model. More specifically, the damage statistical information includes the total number of pictures, the number of pictures containing damage, and the number of pictures of each type of damage. The content of the summary and the overview includes the overall assessment of the damage degree of the project, the work to be done next, and the points to be noted.

[0036] (S6) Adjusting the initial report template according to the project report specification to generate a final damage detection report, specifically, in step (S6), according to the damage statistical information, the content of the summary part and the overview part, the initial report template is adjusted in details according to the project report specification, including highlighting of the main points and adding or deleting the content, to generate the final detection report.

[0037] In combination Figure 3 As shown in the drawings, the present application also provides an artificial intelligence-based building facade damage detection report automatic generation system, comprising: a template construction module for acquiring a building facade image and constructing an artificial intelligence detection model using the building facade image; an information reading module for reading, detecting and damage information statistics on the building facade damage image using the artificial intelligence detection model; a report generation module for automatically generating a detection report according to the damage detection result generated by the information reading module, to complete the automatic generation of the building facade damage detection report.

[0038] Compared with the prior art, the present application has the following beneficial effects:

[0039] The artificial intelligence-based building facade damage detection report automatic generation method and system of the present application realize the automatic generation of the detection report, greatly save time and labor cost, avoid manual errors, and improve the accuracy of the detection report.

[0040] The above disclosure is only the preferred embodiment of the present application, and cannot limit the scope of the right of the present application, therefore, the equivalent changes made according to the claims of the present application all belong to the scope covered by the present application.

Claims

1. A method for automatically generating building facade damage detection reports based on artificial intelligence, characterized in that, The method comprises the following steps: (S1) setting a project report specification, and formulating an initial report template according to the project report specification, wherein the formulation of the initial report template is completed by using Word software, and the content of the initial report template includes a cover, a table of contents, a project summary, project basic information and damage detection results, and the initial report template is subjected to format design and layout according to the project report specification; (S2) reading project metadata information, calling a COM interface of Word, and writing text information and picture information into the initial report template; (S3) generating an API query instruction of an artificial intelligence detection model according to the project metadata information, wherein the project metadata information is collected according to the picture information, and the command sequence of the API query instruction of the artificial intelligence detection model is generated according to the project metadata information; (S4) calling the API query instruction of the artificial intelligence detection model in the step (S3) to read damage detection results, extracting damage information details, and writing damage pictures and damage detection result data into the initial report template, wherein the API query instruction of the artificial intelligence detection model is called, the damage detection result data of the damage information details is extracted, the damage detection results include specific types of damage, numbers, positions, detection times and damage states of the damage pictures, the COM interface of Word is called, and the damage pictures and the damage detection result data are filled into the initial report template; (S5) calculating damage statistical information of a project based on the damage information details written in the step (S4), and generating summary content and overview content in the initial report template by calling a summary interface in the artificial intelligence detection model, wherein the damage statistical information is calculated according to the damage information details, the COM interface of Word is called, the damage statistical information is input, the summary interface of the artificial intelligence detection model is called, the damage statistical information and text information are combined to generate the summary and the overview content in the initial report template by using a natural language large model; (S6) adjusting the initial report template to generate a final damage detection report according to the project report specification, wherein the initial report template is subjected to detail adjustment according to the damage statistical information, the content of the summary part and the overview part, including highlighting of main points and adding or deleting of contents, to generate a final detection report. 2.The artificial intelligence-based building facade damage detection report automatic generation method of claim 1, wherein The text information includes a consignor, a building location, basic information, damage detection time and equipment information used, and the picture information includes an appearance picture and a design picture of the building. 3.The artificial intelligence-based building facade damage detection report automatic generation method of claim 1, wherein, The damage statistical information includes a total number of pictures, a number of pictures containing damage, and a number of pictures of each type of damage, and the content of the summary part and the overview part includes an overall project damage degree evaluation, next work to be performed and points to be noted.

4. A system based on the artificial intelligence-based building facade damage detection report automatic generation method according to any one of claims 1 to 3, characterized in that, The method comprises the following steps: a template construction module, configured to acquire a building facade image, and construct an artificial intelligence detection model by using the building facade image; The information reading module is configured to read, detect and count damage information of the building facade damage image by using an artificial intelligence detection model. The report generation module is configured to automatically generate a detection report according to the damage detection result generated by the information reading module, and complete automatic generation of the building facade damage detection report.

Images