Health assessment method of beam bridge based on disease information big data

Abstract

The present invention discloses a health assessment method for beam bridges based on disease information big data, comprising obtaining non-standard disease record information uploaded by staff of a target beam bridge; using the non-standard disease record information as input according to a pre-trained matching model based on big data deep learning, and outputting standard disease record information; generating a corresponding standard beam bridge model according to the bridge type of the target beam bridge; inputting the standard disease record information into the standard beam bridge model to obtain a standard disease model, obtaining a local image of the disease point and sending it to the staff for confirmation, and calculating the health assessment grade of the standard disease model according to preset calculation rules after the confirmation is completed.

Description

Technical Field

[0001] The present invention belongs to the technical field of big data processing, and in particular relates to a health assessment method for a beam bridge based on disease information big data. Background Art

[0002] As the earliest bridges in ancient China, the daily management and maintenance of beam bridges has become a problem as the number of beam bridges in China gradually increases. At present, the existing technology adopts the method of regularly inspecting the quality of beam bridges, recording disease information, and conducting health assessments based on the disease information. However, the scheme adopted by the existing technology when recording disease information is to digitize the disease characteristics, and then have the on-site inspection personnel standardize the disease record information according to the digital standardized filling method. However, this method relies on manual judgment of non-standard data and then standardizes the standard data entry, which requires a high knowledge reserve of the inspection personnel and is inefficient. There is also a problem of high error rate due to subjective blindness in manual judgment. Summary of the invention

[0003] In view of this, the object of the present invention is to provide a health assessment method for beam bridges based on disease information big data to solve the above problems.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] A health assessment method for beam bridges based on disease information big data, including:

[0006] Obtain irregular disease record information uploaded by staff of target beam bridges;

[0007] According to the pre-trained matching model based on big data deep learning, the non-standard disease record information is used as input, and the standard disease record information is output;

[0008] According to the bridge type of the target beam bridge, a corresponding standard beam bridge model is generated;

[0009] Input the standard defect record information into the standard beam bridge model to obtain the standard defect model, obtain the local picture of the defect point and send it to the staff for confirmation. After the confirmation is completed, the health assessment level of the standard defect model is calculated according to the preset calculation rules.

[0010] Furthermore, the irregular disease record information uploaded by the staff of the target beam bridge is obtained, including:

[0011] Obtain the unique bridge body number of the beam bridge to be evaluated, and determine the target beam bridge according to the unique bridge body number;

[0012] Obtain the irregular defect record information uploaded by the staff corresponding to the target bridge, including manual record information, photo information and marking information.

[0013] Furthermore, according to the pre-trained matching model based on big data deep learning, the non-standard disease record information is used as input, and the standard disease record information is output, including:

[0014] Obtain pre-trained matching models based on big data deep learning, including text semantic matching models based on deep learning and image matching models based on deep learning;

[0015] Obtain non-standard disease record information, disassemble and analyze the text non-standard disease record information, input it into the text semantic matching model based on deep learning, and obtain the first standard disease record information;

[0016] Obtain irregular disease record information, disassemble and analyze the irregular disease record information of the image, input it into the image matching model based on deep learning, and obtain the standard matching image;

[0017] Obtaining the marking information in the standard matching image to obtain the second standard disease record information;

[0018] Among them, the standardized defect record information includes: beam bridge defect structure number, beam bridge defect structure location number, beam bridge defect type code and beam bridge defect severity code.

[0019] Furthermore, according to the bridge type of the target beam bridge, a corresponding standard beam bridge model is generated, including:

[0020] According to a preset beam bridge classification method, the type of the target beam bridge is classified to obtain the bridge type of the target beam bridge;

[0021] A number of beam bridge structures of a bridge type corresponding to the target beam bridge are obtained, and based on a three-dimensional bridge modeling method, corresponding standard beam bridge models are generated according to the number of beam bridge structures.

[0022] Furthermore, input the standard defect record information into the standard beam bridge model to obtain the standard defect model, and obtain the local picture of the defect point and send it to the staff for confirmation, including:

[0023] Obtaining standard defect record information, classifying the standard defect record information according to the beam bridge defect structure number and the beam bridge defect structure position number, and obtaining defect parameters of different beam bridge structures;

[0024] Input the disease parameters of different beam bridge structures into the corresponding beam bridge structure in the standard beam bridge model to obtain a standard disease model;

[0025] According to the preset multi-dimensional recording method, local pictures of all disease points in the standard disease model are obtained and recorded, and sent to the corresponding staff who uploaded the non-standard disease record information for confirmation and verification of the disease information.

[0026] Furthermore, a health assessment method for beam bridges based on disease information big data also includes:

[0027] When there is a problem in the disease information verification, obtain the beam bridge structure corresponding to any local picture with the problem;

[0028] Sending the corresponding preset prompt words of the beam bridge structure to the staff for prompt word selection;

[0029] Obtaining modification opinions on problematic disease parameters uploaded by staff; wherein, modification opinions on problematic disease parameters include prompt words selected by staff, independent modification opinions uploaded by staff, and irregular disease record information of corresponding beam bridge structure uploaded again by staff;

[0030] According to the preset keyword extraction rules, keywords are extracted from the autonomous modification opinions to obtain the opinion keywords;

[0031] According to the non-standard defect record information uploaded again for the corresponding beam bridge structure, the secondary standard defect record information is determined;

[0032] According to the standard defect record information, prompt words and opinion keywords of the corresponding beam bridge structure, the secondary standard defect record information is adjusted to obtain the adjusted standard defect record information;

[0033] According to the adjustment of the standard defect record information, the corresponding beam bridge structure in the standard defect model is adjusted to generate a new standard defect model.

[0034] Furthermore, according to the standard defect record information, prompt words and opinion keywords of the corresponding beam bridge structure, the secondary standard defect record information is adjusted to obtain the adjusted standard defect record information, including:

[0035] Obtain prompt words corresponding to the beam bridge structure, including the beam bridge defect deviation position, beam bridge defect deviation type and beam bridge defect deviation severity;

[0036] Obtain the key words of the opinions of the corresponding beam bridge structure, including the additional descriptions of the beam bridge disease deviation location, beam bridge disease deviation type and beam bridge disease deviation severity by the staff;

[0037] According to the prompt words and the key words of the opinions, the standardized disease record information is adjusted accordingly to obtain the comparison record information;

[0038] Determine whether the similarity between the comparison record information and the secondary standard disease record information is greater than a preset threshold;

[0039] If the similarity between the comparison record information and the secondary standard disease record information is not greater than the preset threshold, a new standard disease model is determined based on the secondary standard disease record information, and a local image of the corresponding disease point in the new standard disease model is obtained and sent to the corresponding staff who uploaded the non-standard disease record information for confirmation and verification of the disease information. At the same time, the modification opinions on the problematic disease parameters uploaded by the corresponding staff are obtained for processing to determine whether the similarity between the new comparison record information and the new secondary standard disease record information is greater than the preset threshold;

[0040] If the similarity between the compared record information and the secondary standard defect record information is greater than a preset threshold, the record information is compared with the standard defect record information of several beam bridge structures identical to the corresponding beam bridge structure in the bridge big data database to adjust the rationality of the beam bridge defect and obtain the adjusted standard defect record information.

[0041] Furthermore, after confirmation, the health assessment level of the standard disease model is calculated according to the preset calculation rules, including:

[0042] When the verification result of the damage information is correct, the neural network model pre-trained and generated based on the damage information big data and the preset calculation rules of the beam and bridge health assessment agency is called to calculate the health assessment level of the standard damage model according to the damage parameters and damage correlation relationships of each beam and bridge structure in the standard damage model.

[0043] The beneficial effects of the present invention are:

[0044] The present invention provides a health assessment method for beam bridges based on disease information big data. The beam bridge big data health assessment center processes the non-standard disease records uploaded by the staff and determines the standard disease records, which reduces the requirements for the knowledge reserve of the staff for the standard digital standard disease records in the prior art and improves the efficiency and accuracy of scheduled inspections. At the same time, by allowing the staff to confirm the local pictures of the model for review, the errors caused by data recognition are reduced, and the picture comparison and recognition method can enable the staff to review the scheduled inspection information more efficiently than the data comparison and recognition method, thereby improving the review efficiency.

[0045] Other advantages, objectives and features of the present invention will be described in the following description and will be apparent to those skilled in the art to some extent, or they may be taught from the practice of the present invention. The purposes and other advantages of the present invention may be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0046] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0048] Figure 1 It is a method flow chart of a health assessment method of a beam bridge based on disease information big data in an embodiment of the present invention;

[0049] Figure 2 A flowchart of determining a defect point in a health assessment method for a beam bridge based on defect information big data in an embodiment of the present invention;

[0050] Figure 3 The present invention is a flowchart of checking defect points in a health assessment method for a beam bridge based on defect information big data in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0052] See also Figure 1 The present invention provides a health assessment method for beam bridges based on disease information big data, comprising:

[0053] S101, obtaining irregular disease record information uploaded by staff of the target beam bridge;

[0054] S102, using the pre-trained matching model based on big data deep learning, using the non-standard disease record information as input, and outputting the standard disease record information;

[0055] S103, generating a corresponding standard beam bridge model according to the bridge type of the target beam bridge;

[0056] S104, input the standard disease record information into the standard beam bridge model to obtain the standard disease model, obtain the local picture of the disease point and send it to the staff for confirmation. After the confirmation is completed, the health assessment level of the standard disease model is calculated according to the preset calculation rules;

[0057] The working principle of the above technical solution is as follows: the target beam bridge is determined according to the monitoring demand data, and the monitoring demand data is preferably based on the beam bridge regular inspection time period data. After the target beam bridge is determined, the staff is dispatched to the site to perform regular inspection of the beam bridge disease. The staff performs inspection operations on the target beam bridge through the regular inspection equipment, and uploads the irregular disease record information obtained through the communication terminal carried. After the beam bridge big data health assessment center obtains the irregular disease record information, it uses the pre-trained matching model based on big data deep learning and uses the irregular disease record information as input to output the standardized disease record information. After determining the target beam bridge and the number, the bridge type of the target beam bridge is determined according to the bridge big data database, and the corresponding standard beam bridge three-dimensional model is generated. At the same time, the standard disease record information is transferred to the standard beam bridge model to obtain the standard disease model, and the local picture of the disease point is obtained and sent to the staff for confirmation. After the confirmation is completed, the health assessment level of the standard disease model is calculated according to the preset calculation rules, and the health assessment level is sent to the corresponding demand terminal. At the same time, the healthy beam bridge big data health assessment center records this assessment operation according to the assessment time and sends it to the bridge big data database for storage;

[0058] The beneficial effects of the above technical solution are as follows: through the above technical solution, the Liangqiao Big Data Health Assessment Center processes the non-standard disease records uploaded by the staff, determines the standardized disease records, reduces the requirements for the knowledge reserve of the staff in the standard digital standardized disease records in the existing technology, and improves the efficiency and accuracy of scheduled inspections; at the same time, by allowing the staff to confirm the local pictures of the model for review, the errors caused by data recognition are reduced, and the picture comparison and recognition method can enable the staff to review the scheduled inspection information more efficiently than the data comparison and recognition method, thereby improving the review efficiency.

[0059] In one embodiment, obtaining the irregular disease record information uploaded by the staff of the target beam bridge includes:

[0060] Obtain the unique bridge body number of the beam bridge to be evaluated, and determine the target beam bridge according to the unique bridge body number;

[0061] Obtain the irregular disease record information uploaded by the staff of the target bridge, including manual record information, photo information and marking information;

[0062] The working principle of the above technical solution is as follows: after determining the beam bridge to be evaluated through the beam bridge regular inspection time period data, determine the unique bridge body number of the beam bridge to be evaluated through the bridge big data database, and determine the target beam bridge according to the unique bridge body number; obtain the irregular disease record information uploaded by the staff corresponding to the target bridge, including manual record information, photo information and marking information;

[0063] The beneficial effect of the above technical solution is: through the above technical solution, each beam bridge to be evaluated is determined according to the regular inspection cycle, and staff are arranged to collect and record data, which is beneficial to form a good health maintenance management strategy for the beam bridge.

[0064] In one embodiment, according to a pre-trained matching model based on big data deep learning, the non-standard disease record information is used as input, and the standard disease record information is output, including:

[0065] Obtain pre-trained matching models based on big data deep learning, including text semantic matching models based on deep learning and image matching models based on deep learning;

[0066] Obtain non-standard disease record information, disassemble and analyze the text non-standard disease record information, input it into the text semantic matching model based on deep learning, and obtain the first standard disease record information;

[0067] Obtain irregular disease record information, disassemble and analyze the irregular disease record information of the image, input it into the image matching model based on deep learning, and obtain the standard matching image;

[0068] Obtaining the marking information in the standard matching image to obtain the second standard disease record information;

[0069] Among them, the standardized defect record information includes: beam bridge defect structure number, beam bridge defect structure location number, beam bridge defect type code and beam bridge defect severity code;

[0070] The working principle of the above technical solution is as follows: after the non-standard disease record information data is uploaded to the beam bridge big data health assessment center, a pre-trained matching model based on big data deep learning is obtained, including a text semantic matching model based on deep learning and an image matching model based on deep learning; the training data source is the beam bridge disease record data in the bridge big data database; the non-standard disease record information is obtained, the text non-standard disease record information is obtained by disassembling and analyzing, and the text semantic matching model based on deep learning is input to obtain the first standard disease record information; the non-standard disease record information is obtained, the image non-standard disease record information is obtained by disassembling and analyzing, and the image non-standard disease record information is input to the image matching model based on deep learning to obtain the standard matching image; the marking information in the standard matching image is obtained to obtain the second standard disease record information; wherein, the standard disease record information includes: beam bridge disease structure number, beam bridge disease structure location number, beam bridge disease type code and beam bridge disease severity code;

[0071] The beneficial effect of the above technical solution is: through the above technical solution, the deep learning matching model is used to quickly process the disease records uploaded by the staff, which is beneficial to improving the efficiency of disease statistics and reducing the error rate of disease statistics.

[0072] In one embodiment, according to the bridge type of the target beam bridge, a corresponding standard beam bridge model is generated, including:

[0073] According to a preset beam bridge classification method, the type of the target beam bridge is classified to obtain the bridge type of the target beam bridge; preferably, the type of the beam bridge is divided according to a static system;

[0074] Acquire several beam bridge structures of the bridge type corresponding to the target beam bridge, and generate corresponding standard beam bridge models according to the several beam bridge structures based on the bridge three-dimensional modeling method; that is, generate corresponding three-dimensional bridge models at the time of initial construction according to corresponding beam bridge technical data;

[0075] The beneficial effect of the above technical solution is: through the above technical solution, the design of the standard beam bridge model is completed, providing reliable data support for subsequent disease re-inspection.

[0076] See also Figure 2 In one embodiment, the standard defect record information is input into the standard beam bridge model to obtain the standard defect model, and a local image of the defect point is obtained and sent to the staff for confirmation, including:

[0077] S201, obtaining standard disease record information, classifying the standard disease record information according to the beam bridge disease structure number and the beam bridge disease structure position number, and obtaining disease parameters of different beam bridge structures; that is, the disease parameters of each beam bridge structure include the beam bridge disease type and the beam bridge disease severity;

[0078] S202, inputting the disease parameters of different beam bridge structures into the corresponding beam bridge structures in the standard beam bridge model to obtain a standard disease model;

[0079] S203, according to the preset multi-dimensional recording method, obtain and record the local pictures of all the disease points in the standard disease model, send them to the corresponding staff who uploaded the non-standard disease record information for confirmation, and check the disease information; wherein the preset multi-dimensional recording method is preferably a multi-angle recording method;

[0080] The beneficial effect of the above technical solution is: through the above technical solution, by allowing staff to confirm the review of local pictures of the model, the error caused by data recognition is reduced.

[0081] See also Figure 3 In one embodiment, a health assessment method for a beam bridge based on disease information big data further includes:

[0082] S301, when there is a problem in the disease information verification, obtaining a beam bridge structure corresponding to any partial image with the problem;

[0083] S302, sending the corresponding preset prompt words of the beam bridge structure to the staff for prompt word selection;

[0084] S303, obtaining the modification opinions of the problem disease parameters uploaded by the staff; wherein the modification opinions of the problem disease parameters include the prompt words selected by the staff, the independent modification opinions uploaded by the staff, and the irregular disease record information of the corresponding beam bridge structure uploaded again by the staff;

[0085] S304, extracting keywords from the autonomous modification opinions according to preset keyword extraction rules to obtain opinion keywords;

[0086] S305, determining secondary standard disease record information according to the non-standard disease record information for the corresponding beam bridge structure uploaded again;

[0087] S306, adjusting the secondary standard defect record information according to the standard defect record information, prompt words and opinion keywords of the corresponding beam bridge structure to obtain adjusted standard defect record information;

[0088] S307, adjusting the corresponding beam bridge structure in the standard disease model according to the adjustment specification disease record information, and generating a new standard disease model;

[0089] The working principle and beneficial effects of the above technical solution are as follows: when there is a problem in the verification of the defect information, the beam bridge structure corresponding to any local picture with the problem is obtained, and the corresponding preset prompt words of the beam bridge structure are sent to the staff for prompt word selection, and the prompt words include the deviation position information, deviation type information and deviation severity information of the defect record information; then the modification opinions of the problem defect parameters uploaded by the staff are obtained; wherein the modification opinions of the problem defect parameters include the prompt words selected by the staff, the autonomous modification opinions uploaded by the staff and the non-standard defect record information of the corresponding beam bridge structure uploaded by the staff again, and according to the preset keyword extraction rules, the autonomous modification opinions are subjected to keyword extraction to obtain the opinion keywords, and the opinions Keywords are additional descriptions of deviation position information, deviation type information and deviation severity information; secondary standard defect record information is determined based on the non-standard defect record information for the corresponding beam bridge structure uploaded again; data is adjusted on the secondary standard defect record information based on the standard defect record information, prompt words and opinion keywords of the corresponding beam bridge structure to obtain adjusted standard defect record information; finally, the corresponding beam bridge structure in the standard defect model is adjusted based on the adjusted standard defect record information to generate a new standard defect model; through the above technical solution, a review method is adopted to ensure the reliability of the evaluation data source, and by recommending adjustment opinions, the number of useless non-standard defect record information uploaded by staff after review is reduced, thereby improving the review efficiency.

[0090] In one embodiment, according to the standard defect record information, prompt words and opinion keywords of the corresponding beam bridge structure, the secondary standard defect record information is adjusted to obtain the adjusted standard defect record information, including:

[0091] Obtain prompt words corresponding to the beam bridge structure, including the beam bridge defect deviation position, beam bridge defect deviation type and beam bridge defect deviation severity;

[0092] Obtain the key words of the opinions of the corresponding beam bridge structure, including the additional descriptions of the beam bridge disease deviation location, beam bridge disease deviation type and beam bridge disease deviation severity by the staff;

[0093] According to the prompt words and the key words of the opinions, the standardized disease record information is adjusted accordingly to obtain the comparison record information;

[0094] Determine whether the similarity between the comparison record information and the secondary standard disease record information is greater than a preset threshold;

[0095] If the similarity between the comparison record information and the secondary standard disease record information is not greater than the preset threshold, a new standard disease model is determined based on the secondary standard disease record information, and a local image of the corresponding disease point in the new standard disease model is obtained and sent to the corresponding staff who uploaded the non-standard disease record information for confirmation and verification of the disease information. At the same time, the modification opinions on the problematic disease parameters uploaded by the corresponding staff are obtained for processing to determine whether the similarity between the new comparison record information and the new secondary standard disease record information is greater than the preset threshold;

[0096] If the similarity between the compared record information and the secondary standard defect record information is greater than a preset threshold, the record information is compared with the standard defect record information of several beam bridge structures identical to the corresponding beam bridge structure in the bridge big data database to adjust the beam bridge defect rationality, and obtain the adjusted standard defect record information;

[0097] The beneficial effects of the above technical solution are: through the above technical solution, the review of disease record information is determined, the number of times staff repeatedly uploads non-standard disease records is reduced, accurate review is achieved, review efficiency is improved, and the efficiency of subsequent health level assessment is improved.

[0098] In one embodiment, after the confirmation is completed, the health assessment level of the standard disease model is calculated according to the preset calculation rules, including:

[0099] When the verification result of the disease information is correct, the neural network model pre-trained and generated based on the disease information big data and the preset calculation rules of the beam bridge health assessment agency is called to calculate the health assessment level of the standard disease model according to the disease parameters and disease correlation relationship of each beam bridge structure in the standard disease model;

[0100] The working principle and beneficial effects of the above technical solution are as follows: when the verification result of the disease information is correct, a neural network model pre-trained and generated based on the disease information big data and the preset calculation rules of the beam bridge health assessment agency is called. The neural network model is preferably a BP neural network model with 3 hidden layers. According to the disease parameters and disease correlation relationships of each beam bridge structure in the standard disease model, the health assessment level of the standard disease model is calculated. Through the above technical solution, the health level assessment of the standard disease model is completed.

[0101] Finally, it should be noted that the above preferred embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail through the above preferred embodiments, those skilled in the art should understand that various changes can be made in form and details without departing from the scope defined by the claims of the present invention.

Claims

1. A health assessment method for beam bridges based on disease information big data, It is characterized in that include: Obtain irregular disease record information uploaded by staff of target beam bridges; According to the pre-trained matching model based on big data deep learning, the non-standard disease record information is used as input, and the standard disease record information is output; According to the bridge type of the target beam bridge, a corresponding standard beam bridge model is generated; Input the standard disease record information into the standard beam bridge model to obtain the standard disease model, obtain the local picture of the disease point and send it to the staff for confirmation. After confirmation, calculate the health assessment level of the standard disease model according to the preset calculation rules; Among them, according to the pre-trained matching model based on big data deep learning, the non-standard disease record information is used as input, and the standardized disease record information is output, including: Obtain pre-trained matching models based on big data deep learning, including text semantic matching models based on deep learning and image matching models based on deep learning; Obtain non-standard disease record information, disassemble and analyze the text non-standard disease record information, input it into the text semantic matching model based on deep learning, and obtain the first standard disease record information; Obtain irregular disease record information, disassemble and analyze the irregular disease record information of the image, input it into the image matching model based on deep learning, and obtain the standard matching image; Obtaining the marking information in the standard matching image to obtain the second standard disease record information; Among them, the standardized defect record information includes: beam bridge defect structure number, beam bridge defect structure location number, beam bridge defect type code and beam bridge defect severity code.

2. According to claim 1, a health assessment method for beam bridges based on disease information big data, It is characterized in that Obtain irregular disease record information uploaded by target beam bridge staff, including: Obtain the unique bridge body number of the beam bridge to be evaluated, and determine the target beam bridge according to the unique bridge body number; Obtain the irregular defect record information uploaded by the staff corresponding to the target bridge, including manual record information, photo information and marking information.

3. According to the health assessment method of beam bridge based on disease information big data according to claim 1, It is characterized in that According to the bridge type of the target beam bridge, the corresponding standard beam bridge model is generated, including: According to a preset beam bridge classification method, the type of the target beam bridge is classified to obtain the bridge type of the target beam bridge; A number of beam bridge structures of a bridge type corresponding to the target beam bridge are obtained, and based on a three-dimensional bridge modeling method, corresponding standard beam bridge models are generated according to the number of beam bridge structures.

4. According to claim 1, a health assessment method for beam bridges based on disease information big data, It is characterized in that Input the standard defect record information into the standard beam bridge model to obtain the standard defect model, and obtain the local picture of the defect point and send it to the staff for confirmation, including: Obtaining standard defect record information, classifying the standard defect record information according to the beam bridge defect structure number and the beam bridge defect structure position number, and obtaining defect parameters of different beam bridge structures; Input the disease parameters of different beam bridge structures into the corresponding beam bridge structure in the standard beam bridge model to obtain a standard disease model; According to the preset multi-dimensional recording method, local pictures of all disease points in the standard disease model are obtained and recorded, and sent to the corresponding staff who uploaded the non-standard disease record information for confirmation and verification of the disease information.

5. According to claim 4, a health assessment method for beam bridges based on disease information big data, It is characterized in that Also includes: When there is a problem in the disease information verification, obtain the beam bridge structure corresponding to any local picture with the problem; Sending the corresponding preset prompt words of the beam bridge structure to the staff for prompt word selection; Obtain the modification opinions of the problematic disease parameters uploaded by the staff; the modification opinions of the problematic disease parameters include the prompt words selected by the staff, the independent modification opinions uploaded by the staff, and the irregular disease record information of the corresponding beam bridge structure uploaded again by the staff; According to the preset keyword extraction rules, keywords are extracted from the autonomous modification opinions to obtain the opinion keywords; According to the non-standard defect record information uploaded again for the corresponding beam bridge structure, the secondary standard defect record information is determined; According to the standard defect record information, prompt words and opinion keywords of the corresponding beam bridge structure, the secondary standard defect record information is adjusted to obtain the adjusted standard defect record information; According to the adjustment of the standard defect record information, the corresponding beam bridge structure in the standard defect model is adjusted to generate a new standard defect model.

6. According to claim 5, a health assessment method for beam bridges based on disease information big data, It is characterized in that According to the standard defect record information, prompt words and opinion keywords of the corresponding beam bridge structure, the secondary standard defect record information is adjusted to obtain the adjusted standard defect record information, including: Obtain prompt words corresponding to the beam bridge structure, including the beam bridge defect deviation position, beam bridge defect deviation type and beam bridge defect deviation severity; Obtain the key words of the opinions of the corresponding beam bridge structure, including the additional descriptions of the beam bridge disease deviation location, beam bridge disease deviation type and beam bridge disease deviation severity by the staff; According to the prompt words and the key words of the opinions, the standardized disease record information is adjusted accordingly to obtain the comparison record information; Determine whether the similarity between the comparison record information and the secondary standard disease record information is greater than a preset threshold; If the similarity between the comparison record information and the secondary standard disease record information is not greater than the preset threshold, a new standard disease model is determined based on the secondary standard disease record information, and a local image of the corresponding disease point in the new standard disease model is obtained and sent to the corresponding staff who uploaded the non-standard disease record information for confirmation and verification of the disease information. At the same time, the modification opinions on the problematic disease parameters uploaded by the corresponding staff are obtained for processing to determine whether the similarity between the new comparison record information and the new secondary standard disease record information is greater than the preset threshold; If the similarity between the compared record information and the secondary standard defect record information is greater than a preset threshold, the record information is compared with the standard defect record information of several beam bridge structures identical to the corresponding beam bridge structure in the bridge big data database to adjust the rationality of the beam bridge defect and obtain the adjusted standard defect record information.

7. According to claim 1, a health assessment method for beam bridges based on disease information big data, It is characterized in that After confirmation, the health assessment level of the standard disease model is calculated according to the preset calculation rules, including: When the verification result of the damage information is correct, the neural network model pre-trained and generated based on the damage information big data and the preset calculation rules of the beam and bridge health assessment agency is called to calculate the health assessment level of the standard damage model according to the damage parameters and damage correlation relationships of each beam and bridge structure in the standard damage model.

Images