Intelligent engineering monitoring method and system based on multi-sensing information correction

Abstract

The application discloses a kind of intelligent engineering monitoring method and system based on multi-sensing information correction, which comprises the following steps: obtaining a plurality of sensing information of target engineering area through a plurality of sensors;According to the correction rule between the sensing information value, each sensing information is corrected to obtain the corresponding corrected sensing information;According to the corresponding engineering type of the target engineering area, the corresponding prediction neural network is determined;According to the prediction neural network and all the corrected sensing information, the corresponding engineering risk information of the target engineering area is predicted.It can be seen that the application can more efficiently and accurately predict and analyze engineering risk information, improve the engineering risk monitoring effect, and provide more accurate data guidance for engineering construction.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a smart engineering monitoring method and system based on multi-sensor information correction. Background Technology

[0002] With increasing demands in the construction industry, the number of construction projects is also growing. In particular, construction projects involve numerous factors such as personnel, machinery, materials, and the environment, making monitoring challenging. Existing manufacturers have begun to explore the concept of smart engineering to achieve intelligent monitoring. However, current technologies generally rely on single-sensor information for monitoring, lacking a system for cross-checking and synergistic effects among multiple sensors to achieve effective project monitoring. Therefore, the monitoring results are poor. Clearly, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by this invention is to provide a smart engineering monitoring method and system based on multi-sensor information correction, which can more efficiently and accurately predict and analyze engineering hazard information, improve the effect of engineering hazard monitoring, and provide more accurate data guidance for engineering construction.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a smart engineering monitoring method based on multi-sensor information correction, the method comprising:

[0005] Multiple sensor information of the target engineering area is acquired through multiple sensors;

[0006] According to the correction rules between the sensor information values, each of the sensor information is corrected to obtain the corresponding corrected sensor information;

[0007] Based on the type of project corresponding to the target project area, determine the corresponding prediction neural network;

[0008] Based on the predictive neural network and all the corrective sensing information, the engineering hazard information corresponding to the target engineering area is predicted.

[0009] As an optional implementation, in the first aspect of the present invention, the sensing information is temperature sensing information, humidity sensing information, light intensity sensing information, precipitation sensing information, infrared sensing information, or image sensing information.

[0010] As an optional implementation, in the first aspect of the present invention, the engineering type is an electrical engineering, waterway engineering, decoration engineering, wall engineering, or building structure engineering.

[0011] As an optional implementation, in the first aspect of the present invention, the step of correcting each of the sensing information according to the correction rules between the sensing information values ​​to obtain corresponding corrected sensing information includes:

[0012] For any two pieces of sensor information, the correlation parameter between the information types of the two pieces of sensor information is determined according to the preset correlation relationship between information types;

[0013] Based on the historical data corresponding to the information types of the two sensor information, a mathematical relationship model of the information values ​​of the two sensor information is established;

[0014] Based on the mathematical relationship model of the information values ​​and the correlation parameter, the correction sensing information corresponding to the two sensing information is determined.

[0015] As an optional implementation, in the first aspect of the present invention, determining the correction sensing information corresponding to the two sensing information pieces based on the mathematical relationship model of the information values ​​and the correlation parameter. As an optional implementation, in the first aspect of the present invention, determining the corresponding prediction neural network based on the engineering type corresponding to the target engineering area includes:

[0016] Determine the type of project corresponding to the target project area;

[0017] For each candidate neural network, calculate the similarity between the project type label in the training dataset of the candidate neural network and the project type;

[0018] The candidate neural network with the highest similarity is determined as the prediction neural network corresponding to the target engineering area; the prediction neural network is trained using a training dataset that includes multiple training sensor data and corresponding engineering risk type labels.

[0019] As an optional implementation, in the first aspect of the present invention, determining the project type corresponding to the target project area includes:

[0020] Each of the aforementioned correction sensor information is input into the trained engineering type classifier network to obtain the corresponding engineering type prediction result; the engineering type classifier network is trained using a training dataset that includes multiple training sensor information and corresponding engineering type labels;

[0021] Calculate the mode of all predicted results for the project types to obtain the project type corresponding to the target project area.

[0022] As an optional implementation, in the first aspect of the present invention, predicting the engineering hazard information corresponding to the target engineering area based on the predictive neural network and all the corrected sensing information includes:

[0023] Each of the corrected sensing information is input into the prediction neural network to obtain the risk prediction value and risk type corresponding to each of the corrected sensing information;

[0024] For each of the corrected sensing information, determine whether the risk prediction value corresponding to the corrected sensing information is greater than a preset threshold. If so, then the corrected sensing information is determined to be dangerous sensing information.

[0025] The location of each hazardous sensing information area and the corresponding risk type are determined as the engineering hazardous information corresponding to the target engineering area.

[0026] A second aspect of this invention discloses a smart engineering monitoring system based on multi-sensor information correction, the system comprising:

[0027] The acquisition module is used to acquire multiple sensor information of the target engineering area through multiple sensors;

[0028] The calibration module is used to calibrate each of the sensor information according to the calibration rules between the sensor information values ​​to obtain the corresponding calibrated sensor information.

[0029] The determination module is used to determine the corresponding prediction neural network based on the engineering type corresponding to the target engineering area;

[0030] The prediction module is used to predict the engineering hazard information corresponding to the target engineering area based on the prediction neural network and all the correction sensing information.

[0031] As an optional implementation, in a second aspect of the present invention, the sensing information is temperature sensing information, humidity sensing information, light intensity sensing information, precipitation sensing information, infrared sensing information, or image sensing information.

[0032] As an optional implementation, in the second aspect of the present invention, the engineering type is an electrical engineering, waterway engineering, decoration engineering, wall engineering, or building structure engineering.

[0033] As an optional implementation, in a second aspect of the invention, the step of correcting each of the sensing information according to a correction rule between the sensing information values ​​to obtain corresponding corrected sensing information includes:

[0034] For any two pieces of sensor information, the correlation parameter between the information types of the two pieces of sensor information is determined according to the preset correlation relationship between information types;

[0035] Based on the historical data corresponding to the information types of the two sensor information, a mathematical relationship model of the information values ​​of the two sensor information is established;

[0036] Based on the mathematical relationship model of the information values ​​and the correlation parameter, the correction sensing information corresponding to the two sensing information is determined.

[0037] As an optional implementation, in a second aspect of the invention, the correction module determines the specific method of the correction sensing information corresponding to the two sensing information pieces based on the mathematical relationship model of the information values ​​and the correlation parameter, including:

[0038] The information value of one of the two sensor information is input into the mathematical relationship model of the information value to obtain the information correction value of the other sensor information;

[0039] Calculate the correction weights that are proportional to the correlation parameter;

[0040] The correction parameter is obtained by multiplying the information correction value and the correction weight.

[0041] Calculate the average value between the information value of each of the sensing information and the corresponding correction parameter to obtain the corrected sensing information corresponding to another sensing information.

[0042] As an optional implementation, in a second aspect of the invention, the determining module determines the specific method of the corresponding predictive neural network based on the engineering type corresponding to the target engineering area, including:

[0043] Determine the type of project corresponding to the target project area;

[0044] For each candidate neural network, calculate the similarity between the project type label in the training dataset of the candidate neural network and the project type;

[0045] The candidate neural network with the highest similarity is determined as the prediction neural network corresponding to the target engineering area; the prediction neural network is trained using a training dataset that includes multiple training sensor data and corresponding engineering risk type labels.

[0046] As an optional implementation, in a second aspect of the invention, the specific method by which the determining module determines the engineering type corresponding to the target engineering area includes:

[0047] Each of the aforementioned correction sensor information is input into the trained engineering type classifier network to obtain the corresponding engineering type prediction result; the engineering type classifier network is trained using a training dataset that includes multiple training sensor information and corresponding engineering type labels;

[0048] Calculate the mode of all predicted results for the project types to obtain the project type corresponding to the target project area.

[0049] As an optional implementation, in a second aspect of the invention, the specific method by which the prediction module predicts the engineering hazard information corresponding to the target engineering area based on the prediction neural network and all the correction sensing information includes:

[0050] Each of the corrected sensing information is input into the prediction neural network to obtain the risk prediction value and risk type corresponding to each of the corrected sensing information;

[0051] For each of the corrected sensing information, determine whether the risk prediction value corresponding to the corrected sensing information is greater than a preset threshold. If so, then the corrected sensing information is determined to be dangerous sensing information.

[0052] The location of each hazardous sensing information area and the corresponding risk type are determined as the engineering hazardous information corresponding to the target engineering area.

[0053] A third aspect of this invention discloses another intelligent engineering monitoring system based on multi-sensor information correction, the system comprising:

[0054] Memory containing executable program code;

[0055] A processor coupled to the memory;

[0056] The processor calls the executable program code stored in the memory to execute some or all of the steps in the intelligent engineering monitoring method based on multi-sensor information correction disclosed in the first aspect of the present invention.

[0057] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the intelligent engineering monitoring method based on multi-sensor information correction disclosed in the first aspect of the present invention.

[0058] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0059] This invention can correct multiple sensor information of the target engineering area of ​​the target mouse acquired by multiple sensors based on correction rules, and then determine the corresponding prediction neural network through the engineering type corresponding to the target engineering area. Based on the corrected sensor information, accurate engineering hazard prediction can be achieved, thereby enabling more efficient and accurate prediction and analysis of engineering hazard information, improving the engineering hazard monitoring effect, and providing more accurate data guidance for engineering construction. Attached Figure Description

[0060] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0061] Figure 1 This is a flowchart illustrating a smart engineering monitoring method based on multi-sensor information correction disclosed in an embodiment of the present invention.

[0062] Figure 2 This is a schematic diagram of the structure of a smart engineering monitoring system based on multi-sensor information correction disclosed in an embodiment of the present invention.

[0063] Figure 3 This is a schematic diagram of another intelligent engineering monitoring system based on multi-sensor information correction disclosed in an embodiment of the present invention. Detailed Implementation

[0064] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0065] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0066] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0067] This invention discloses a smart engineering monitoring method and system based on multi-sensor information correction. It can correct multiple sensor information acquired from multiple sensors regarding a target engineering area of ​​a target mouse based on correction rules. Then, it determines the corresponding prediction neural network based on the engineering type corresponding to the target engineering area. This allows for accurate prediction of engineering hazards based on the corrected sensor information, thus enabling more efficient and accurate prediction and analysis of engineering hazard information, improving the effectiveness of engineering hazard monitoring, and providing more precise data guidance for engineering construction. Detailed explanations follow.

[0068] Example 1

[0069] Please see Figure 1 , Figure 1 This is a flowchart illustrating a smart engineering monitoring method based on multi-sensor information correction disclosed in an embodiment of the present invention. Figure 1 The described intelligent engineering monitoring method based on multi-sensor information correction can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 1 As shown, this intelligent engineering monitoring method based on multi-sensor information correction may include the following operations:

[0070] 101. Acquire multiple sensor information of the target engineering area through multiple sensors.

[0071] 102. Based on the correction rules between the sensor information values, each sensor information is corrected to obtain the corresponding corrected sensor information.

[0072] 103. Determine the corresponding prediction neural network based on the project type corresponding to the target project area.

[0073] 104. Based on the predictive neural network and all corrective sensor information, predict the engineering hazard information corresponding to the target engineering area.

[0074] As can be seen, the above-described embodiments of the invention can correct multiple sensor information of the target engineering area of ​​the target mouse obtained by multiple sensors based on correction rules, and then determine the corresponding prediction neural network through the engineering type corresponding to the target engineering area, so as to achieve accurate engineering hazard prediction based on the corrected sensor information. This enables more efficient and accurate prediction and analysis of engineering hazard information, improves the engineering hazard monitoring effect, and provides more accurate data guidance for engineering construction.

[0075] As an optional embodiment, the sensing information in the above steps can be temperature sensing information, humidity sensing information, light intensity sensing information, precipitation sensing information, infrared sensing information, or image sensing information.

[0076] As can be seen, the content of the sensing information is clearly defined through the above optional embodiments, which can more comprehensively characterize the situation of various aspects of the project, so as to facilitate accurate prediction of engineering hazards in the future, assist in more efficient and accurate prediction and analysis of engineering hazard information, improve the effect of engineering hazard monitoring, and provide more accurate data guidance for engineering construction.

[0077] As an optional embodiment, the engineering type in the above steps is electrical engineering, waterway engineering, decoration engineering, wall engineering, or building structure engineering.

[0078] As can be seen, the above optional embodiments clarify the project type, enabling a more comprehensive characterization of the characteristics of different projects. This facilitates accurate prediction of project hazards, helps to achieve more efficient and precise prediction and analysis of project hazard information, improves the effectiveness of project hazard monitoring, and provides more accurate data guidance for project construction.

[0079] As an optional embodiment, the step described above, which involves correcting each piece of sensor information according to a correction rule between sensor information values ​​to obtain corresponding corrected sensor information, includes:

[0080] For any two pieces of sensor information, the correlation parameter between the information types of the two pieces of sensor information is determined according to the preset correlation relationship between the information types.

[0081] Based on the historical data corresponding to the information types of the two sensor information, establish a mathematical relationship model of the information values ​​of the two sensor information.

[0082] Based on the mathematical relationship model of information values ​​and the correlation parameter, the corresponding correction sensing information for the two sensing information is determined.

[0083] As can be seen, through the above optional embodiments, by determining the correlation parameter and mathematical relationship model between the information types of two sensing information, it is possible to correct the two sensing information to obtain more valuable sensing data, so as to facilitate accurate engineering hazard prediction in the future, assist in more efficient and accurate prediction and analysis of engineering hazard information, improve the effect of engineering hazard monitoring, and provide more accurate data guidance for engineering construction.

[0084] As can be seen, through the above optional embodiments, the corrected weight can be accurately calculated based on the correlation parameter, and the reasonable corresponding value of the information value can be determined through the mathematical relationship model of information value. Finally, more valuable sensor data can be obtained based on the average calculation, so as to facilitate accurate prediction of engineering hazards in the future, assist in more efficient and accurate prediction and analysis of engineering hazard information, improve the effect of engineering hazard monitoring, and provide more accurate data guidance for engineering construction.

[0085] As an optional embodiment, the step above, determining the corresponding predictive neural network based on the engineering type corresponding to the target engineering area, includes:

[0086] Determine the type of project corresponding to the target project area;

[0087] For each candidate neural network, calculate the similarity between the project type label and the project type in the training dataset of that candidate neural network;

[0088] The candidate neural network with the highest similarity is determined as the prediction neural network corresponding to the target engineering area; the prediction neural network is trained using a training dataset that includes multiple training sensor data and corresponding engineering risk type labels.

[0089] As can be seen, through the above optional embodiments, it is possible to select predictive neural networks in the training dataset that are closer to the engineering type in the engineering area, so as to achieve accurate engineering hazard prediction in the future, assist in more efficient and accurate prediction and analysis of engineering hazard information, improve the effect of engineering hazard monitoring, and provide more accurate data guidance for engineering construction.

[0090] As an optional embodiment, the step of determining the project type corresponding to the target project area in the above steps includes:

[0091] Each correction sensor information is input into the trained engineering type classifier network to obtain the corresponding engineering type prediction result; optionally, the engineering type classifier network is trained using a training dataset that includes multiple training sensor information and corresponding engineering type labels.

[0092] Calculate the mode of the prediction results for all project types to obtain the project type corresponding to the target project area.

[0093] As can be seen, through the above optional embodiments, the engineering type corresponding to each sensing information can be predicted by the trained engineering type classifier network, and the engineering type corresponding to the engineering area can be obtained more accurately by calculating the mode term, so as to realize accurate engineering hazard prediction in the future, assist in realizing more efficient and accurate prediction and analysis of engineering hazard information, improve the engineering hazard monitoring effect, and provide more accurate data guidance for engineering construction.

[0094] As an optional embodiment, the step above, predicting the engineering hazard information corresponding to the target engineering area based on the predictive neural network and all corrective sensor information, includes:

[0095] Each correction sensor information is input into the prediction neural network to obtain the risk prediction value and risk type corresponding to each correction sensor information.

[0096] For each correction sensor information, determine whether the risk prediction value corresponding to the correction sensor information is greater than a preset threshold. If so, the correction sensor information is identified as a hazard sensor information.

[0097] The location of each hazard sensor signal and the corresponding risk type are identified as the engineering hazard information for the target engineering area.

[0098] As can be seen, through the above optional embodiments, the risk prediction value and risk type corresponding to each correction sensor information can be predicted by the predictive neural network to screen out the location and risk type of dangerous areas, thereby achieving accurate engineering hazard prediction. This enables more efficient and accurate prediction and analysis of engineering hazard information, improves the effect of engineering hazard monitoring, and provides more accurate data guidance for engineering construction.

[0099] Example 2

[0100] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a smart engineering monitoring system based on multi-sensor information correction, as disclosed in an embodiment of the present invention. Figure 2 The described intelligent engineering monitoring system based on multi-sensor information correction can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 2 As shown, the intelligent engineering monitoring system based on multi-sensor information correction may include:

[0101] The acquisition module 201 is used to acquire multiple sensing information of the target engineering area through multiple sensors.

[0102] The calibration module 202 is used to calibrate each sensor information according to the calibration rules between sensor information values ​​to obtain the corresponding calibrated sensor information.

[0103] The determination module 203 is used to determine the corresponding prediction neural network based on the engineering type corresponding to the target engineering area.

[0104] The prediction module 204 is used to predict the engineering hazard information corresponding to the target engineering area based on the prediction neural network and all correction sensor information.

[0105] As can be seen, the above-described embodiments of the invention can correct multiple sensor information of the target engineering area of ​​the target mouse obtained by multiple sensors based on correction rules, and then determine the corresponding prediction neural network through the engineering type corresponding to the target engineering area, so as to achieve accurate engineering hazard prediction based on the corrected sensor information. This enables more efficient and accurate prediction and analysis of engineering hazard information, improves the engineering hazard monitoring effect, and provides more accurate data guidance for engineering construction.

[0106] As an optional embodiment, the sensing information is temperature sensing information, humidity sensing information, light intensity sensing information, precipitation sensing information, infrared sensing information, or image sensing information.

[0107] As can be seen, the content of the sensing information is clearly defined through the above optional embodiments, which can more comprehensively characterize the situation of various aspects of the project, so as to facilitate accurate prediction of engineering hazards in the future, assist in more efficient and accurate prediction and analysis of engineering hazard information, improve the effect of engineering hazard monitoring, and provide more accurate data guidance for engineering construction.

[0108] As an optional embodiment, the project type is electrical engineering, waterway engineering, decoration engineering, wall engineering, or building structure engineering.

[0109] As can be seen, the above optional embodiments clarify the project type, enabling a more comprehensive characterization of the characteristics of different projects. This facilitates accurate prediction of project hazards, helps to achieve more efficient and precise prediction and analysis of project hazard information, improves the effectiveness of project hazard monitoring, and provides more accurate data guidance for project construction.

[0110] As an optional embodiment, each piece of sensor information is corrected according to a correction rule between sensor information values ​​to obtain corresponding corrected sensor information, including:

[0111] For any two pieces of sensor information, the correlation parameter between the information types of the two pieces of sensor information is determined according to the preset correlation relationship between the information types.

[0112] Based on the historical data corresponding to the information types of the two sensor information, establish a mathematical relationship model of the information values ​​of the two sensor information.

[0113] Based on the mathematical relationship model of information values ​​and the correlation parameter, the corresponding correction sensing information for the two sensing information is determined.

[0114] As can be seen, through the above optional embodiments, by determining the correlation parameter and mathematical relationship model between the information types of two sensing information, it is possible to correct the two sensing information to obtain more valuable sensing data, so as to facilitate accurate engineering hazard prediction in the future, assist in more efficient and accurate prediction and analysis of engineering hazard information, improve the effect of engineering hazard monitoring, and provide more accurate data guidance for engineering construction.

[0115] As an optional embodiment, the correction module determines the specific method of correcting the sensing information corresponding to the two sensing information based on the mathematical relationship model of the information values ​​and the correlation parameter.

[0116] As can be seen, through the above optional embodiments, the corrected weight can be accurately calculated based on the correlation parameter, and the reasonable corresponding value of the information value can be determined through the mathematical relationship model of information value. Finally, more valuable sensor data can be obtained based on the average calculation, so as to facilitate accurate prediction of engineering hazards in the future, assist in more efficient and accurate prediction and analysis of engineering hazard information, improve the effect of engineering hazard monitoring, and provide more accurate data guidance for engineering construction.

[0117] As an optional embodiment, the determining module determines the specific method of the corresponding predictive neural network based on the project type corresponding to the target project area, including:

[0118] Determine the type of project corresponding to the target project area;

[0119] For each candidate neural network, calculate the similarity between the project type label and the project type in the training dataset of that candidate neural network;

[0120] The candidate neural network with the highest similarity is determined as the prediction neural network corresponding to the target engineering area; the prediction neural network is trained using a training dataset that includes multiple training sensor data and corresponding engineering risk type labels.

[0121] As can be seen, through the above optional embodiments, it is possible to select predictive neural networks in the training dataset that are closer to the engineering type in the engineering area, so as to achieve accurate engineering hazard prediction in the future, assist in more efficient and accurate prediction and analysis of engineering hazard information, improve the effect of engineering hazard monitoring, and provide more accurate data guidance for engineering construction.

[0122] As an optional embodiment, the specific method by which the determining module determines the project type corresponding to the target project area includes:

[0123] Each correction sensor information is input into the trained engineering type classifier network to obtain the corresponding engineering type prediction result; optionally, the engineering type classifier network is trained using a training dataset that includes multiple training sensor information and corresponding engineering type labels.

[0124] Calculate the mode of the prediction results for all project types to obtain the project type corresponding to the target project area.

[0125] As can be seen, through the above optional embodiments, the engineering type corresponding to each sensing information can be predicted by the trained engineering type classifier network, and the engineering type corresponding to the engineering area can be obtained more accurately by calculating the mode term, so as to realize accurate engineering hazard prediction in the future, assist in realizing more efficient and accurate prediction and analysis of engineering hazard information, improve the engineering hazard monitoring effect, and provide more accurate data guidance for engineering construction.

[0126] As an optional embodiment, the prediction module predicts the engineering hazard information corresponding to the target engineering area based on the prediction neural network and all correction sensor information in the following specific ways:

[0127] Each correction sensor information is input into the prediction neural network to obtain the risk prediction value and risk type corresponding to each correction sensor information.

[0128] For each correction sensor information, determine whether the risk prediction value corresponding to the correction sensor information is greater than a preset threshold. If so, the correction sensor information is identified as a hazard sensor information.

[0129] The location of each hazard sensor signal and the corresponding risk type are identified as the engineering hazard information for the target engineering area.

[0130] As can be seen, through the above optional embodiments, the risk prediction value and risk type corresponding to each correction sensor information can be predicted by the predictive neural network to screen out the location and risk type of dangerous areas, thereby achieving accurate engineering hazard prediction. This enables more efficient and accurate prediction and analysis of engineering hazard information, improves the effect of engineering hazard monitoring, and provides more accurate data guidance for engineering construction.

[0131] Example 3

[0132] Please see Figure 3 , Figure 3 This is another intelligent engineering monitoring system based on multi-sensor information correction disclosed in the embodiments of the present invention. Figure 3The described intelligent engineering monitoring system based on multi-sensor information correction is applied in data processing systems / data processing equipment / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 3 As shown, the intelligent engineering monitoring system based on multi-sensor information correction may include:

[0133] Memory 301 storing executable program code;

[0134] Processor 302 coupled to memory 301;

[0135] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the intelligent engineering monitoring method based on multi-sensor information correction described in Embodiment 1.

[0136] Example 4

[0137] This invention discloses a computer read storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps of the intelligent engineering monitoring method based on multi-sensor information correction described in Embodiment 1.

[0138] Example 5

[0139] This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the smart engineering monitoring method based on multi-sensor information correction described in Embodiment 1.

[0140] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0141] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0142] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0143] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0144] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0145] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0146] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0147] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0148] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0149] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0150] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0151] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0152] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0153] Finally, it should be noted that the intelligent engineering monitoring method and system based on multi-sensor information correction disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A smart engineering monitoring method based on multi-sensor information correction, characterized in that, The method includes: Multiple sensor information of the target engineering area is acquired through multiple sensors; According to the correction rules between the sensor information values, each of the sensor information is corrected to obtain the corresponding corrected sensor information; Based on the project type corresponding to the target project area, a corresponding prediction neural network is determined, including: Each of the aforementioned correction sensor information is input into the trained engineering type classifier network to obtain the corresponding engineering type prediction result; the engineering type classifier network is trained using a training dataset that includes multiple training sensor information and corresponding engineering type labels; Calculate the mode of all predicted results for the project types to obtain the project type corresponding to the target project area; the project type is power engineering, waterway engineering, decoration engineering, wall engineering, or main building engineering. For each candidate neural network, calculate the similarity between the project type label in the training dataset of the candidate neural network and the project type; The candidate neural network with the highest similarity is determined as the prediction neural network corresponding to the target engineering area; the prediction neural network is trained using a training dataset that includes multiple training sensor data and corresponding engineering risk type annotations; Based on the predictive neural network and all the corrective sensing information, the engineering hazard information corresponding to the target engineering area is predicted.

2. The intelligent engineering monitoring method based on multi-sensor information correction according to claim 1, characterized in that, The sensing information includes temperature sensing information, humidity sensing information, light intensity sensing information, precipitation sensing information, infrared sensing information, or image sensing information.

3. The intelligent engineering monitoring method based on multi-sensor information correction according to claim 1, characterized in that, The step of correcting each piece of sensor information according to the correction rules between sensor information values ​​to obtain corresponding corrected sensor information includes: For any two pieces of sensor information, the correlation parameter between the information types of the two pieces of sensor information is determined according to the preset correlation relationship between information types; Based on the historical data corresponding to the information types of the two sensor information, a mathematical relationship model of the information values ​​of the two sensor information is established; Based on the mathematical relationship model of the information values ​​and the correlation parameter, the correction sensing information corresponding to the two sensing information is determined.

4. The intelligent engineering monitoring method based on multi-sensor information correction according to claim 1, characterized in that, The step of predicting the engineering hazard information corresponding to the target engineering area based on the prediction neural network and all the correction sensor information includes: Each of the corrected sensing information is input into the prediction neural network to obtain the risk prediction value and risk type corresponding to each of the corrected sensing information; For each of the corrected sensing information, determine whether the risk prediction value corresponding to the corrected sensing information is greater than a preset threshold. If so, then the corrected sensing information is determined to be dangerous sensing information. The location of each hazardous sensing information area and the corresponding risk type are determined as the engineering hazardous information corresponding to the target engineering area.

5. A smart engineering monitoring system based on multi-sensor information correction, characterized in that, The system includes: The acquisition module is used to acquire multiple sensor information of the target engineering area through multiple sensors; The calibration module is used to calibrate each of the sensor information according to the calibration rules between the sensor information values ​​to obtain the corresponding calibrated sensor information. The determination module is used to determine the corresponding prediction neural network based on the engineering type corresponding to the target engineering area, including: Each of the aforementioned correction sensor information is input into the trained engineering type classifier network to obtain the corresponding engineering type prediction result; the engineering type classifier network is trained using a training dataset that includes multiple training sensor information and corresponding engineering type labels; Calculate the mode of all predicted results for the project types to obtain the project type corresponding to the target project area; the project type is power engineering, waterway engineering, decoration engineering, wall engineering, or main building engineering. For each candidate neural network, calculate the similarity between the project type label in the training dataset of the candidate neural network and the project type; The candidate neural network with the highest similarity is determined as the prediction neural network corresponding to the target engineering area; the prediction neural network is trained using a training dataset that includes multiple training sensor data and corresponding engineering risk type annotations; The prediction module is used to predict the engineering hazard information corresponding to the target engineering area based on the prediction neural network and all the correction sensing information.

6. A smart engineering monitoring system based on multi-sensor information correction, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent engineering monitoring method based on multi-sensor information correction as described in any one of claims 1-4.

Images