Intelligent Optimization Methods for Regeneration Construction Schemes of Old Industrial Buildings Based on the Internet of Things

Abstract

This disclosure relates to an intelligent optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things (IoT), belonging to the field of dynamic construction scheme technology. The method includes: receiving real-time construction data corresponding to a target construction area sent by a data acquisition terminal; determining the current conventional construction risk parameters and current environmental risk parameters of the target construction area based on the real-time construction data; adjusting the current conventional construction risk parameters and current environmental risk parameters according to a preset risk parameter weight matrix to obtain target conventional construction risk parameters and target environmental risk parameters; determining a comprehensive risk parameter based on the target conventional construction risk parameters and target environmental risk parameters; and dynamically adjusting the current construction scheme of the target construction area based on the comprehensive risk parameter to obtain the target construction scheme. This disclosure achieves dynamic adjustment of the construction scheme.

Description

Technical Field

[0001] This disclosure relates to the field of dynamic prediction technology for construction schemes, specifically to an intelligent optimization method and device for the regeneration construction scheme of old industrial buildings based on the Internet of Things (IoT). Background Technology

[0002] In the existing process of determining specific construction plans, they can be pre-formulated based on data from the construction area; however, this method is inefficient and cannot be dynamically adjusted.

[0003] It should be noted that the information in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] The purpose of this disclosure is to provide an intelligent optimization method for the regeneration construction of old industrial buildings based on the Internet of Things, thereby overcoming, to at least some extent, the problems of inefficiency and inability to make dynamic adjustments due to the limitations and defects of related technologies.

[0005] According to one aspect of this disclosure, an intelligent optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things is provided, comprising: receiving real-time construction data corresponding to a target construction area sent by a data acquisition terminal; determining current conventional construction risk parameters and current environmental risk parameters of the target construction area based on the real-time construction data; adjusting the current conventional construction risk parameters and current environmental risk parameters according to a preset risk parameter weight matrix to obtain target conventional construction risk parameters and target environmental risk parameters; determining a comprehensive risk parameter based on the target conventional construction risk parameters and target environmental risk parameters; and dynamically adjusting the current construction scheme of the target construction area based on the comprehensive risk parameter to obtain a target construction scheme.

[0006] In an exemplary embodiment of this disclosure, determining the current conventional construction risk parameters and current environmental risk parameters of the target construction area based on the current real-time construction data includes: parsing the current real-time construction data to obtain conventional construction data collected by conventional construction sensors and construction environment data collected by environmental sensors; determining the current conventional construction risk parameters of the target construction area based on the conventional construction data; wherein the current conventional construction risk parameters include at least one of machinery operating speed, construction safety distance, construction operation height, current equipment status of protective equipment, voltage fluctuation range, and grounding resistance; and determining the current environmental risk parameters of the target construction area based on the construction environment data; wherein the current environmental risk parameters include at least one of soil heavy metal concentration, volatile organic compound concentration, wall crack width, pipeline corrosion degree, fine particulate matter concentration, and dust diffusion rate.

[0007] In one exemplary embodiment of this disclosure, adjusting the current conventional construction risk parameters and the current environmental risk parameters according to a preset risk parameter weight matrix to obtain target conventional construction risk parameters and target environmental risk parameters includes: determining the current construction status identification result of the target construction area, and matching the current construction status identification result with a preset risk parameter weight matrix corresponding to the target construction area; determining the current weather data of the target construction area, and determining the environmental condition correction coefficient corresponding to the target construction area based on the current weather data; adjusting the current conventional construction risk parameters according to the preset risk parameter weight matrix to obtain target conventional construction risk parameters, and adjusting the current environmental risk parameters according to the environmental condition correction coefficient and the preset risk parameter weight matrix to obtain target environmental risk parameters.

[0008] In one exemplary embodiment of this disclosure, determining comprehensive risk parameters based on target conventional construction risk parameters and target environmental risk parameters includes: determining conventional construction risk values ​​based on the target conventional construction risk parameters; wherein the conventional construction risk values ​​include at least one of mechanical injury risk values, fall from height risk values, and electric shock risk values; determining construction environmental risk values ​​based on the target environmental risk parameters; wherein the construction environmental risk values ​​include chemical exposure risk values, structural damage risk values, and dust exposure risk values; determining a first weight value and a second weight value for the conventional construction risk values ​​and the construction environmental risk values, and performing a weighted summation of the conventional construction risk values, the first weight value, the construction environmental risk values, and the second weight value to obtain comprehensive risk parameters for the target construction area.

[0009] In one exemplary embodiment of this disclosure, determining the conventional construction risk value based on the target conventional construction risk parameters includes: determining the machinery injury risk value based on the target machinery operating speed and target safety distance in the target conventional construction risk parameters; determining the fall-from-height risk value based on the target working height and target protective facility integrity rate in the target conventional construction risk parameters; determining the electric shock risk value based on the target voltage fluctuation value and target grounding resistance in the target conventional construction risk parameters; and determining the conventional construction risk value based on the machinery injury risk value, the fall-from-height risk value, and the electric shock risk value.

[0010] In one exemplary embodiment of this disclosure, determining the construction environment risk value based on the target environmental risk parameters includes: determining a chemical exposure risk value based on the target soil heavy metal concentration and the target volatile organic compound concentration in the target environmental risk parameters; determining a structural damage risk value based on the target wall crack width and the target pipeline corrosion degree in the target environmental risk parameters; determining a dust exposure risk value based on the target fine particulate matter concentration and the target dust diffusion rate in the target environmental risk parameters; and determining the construction environment risk value based on the chemical exposure risk value, the structural damage risk value, and the dust exposure value.

[0011] In one exemplary embodiment of this disclosure, dynamically adjusting the current construction plan of the target construction area according to the comprehensive risk parameters to obtain a target construction plan includes: assigning a region identifier to the target construction area according to the comprehensive risk parameters, and determining the plan adjustment priority of the target construction area according to the region identifier; determining the region to be adjusted from the target construction area based on the plan adjustment priority, and locating the risk cause of the region to be adjusted based on the reasoning process of the comprehensive risk parameters to obtain a risk cause location result; obtaining a standard construction plan corresponding to the risk cause location result, and inputting the standard construction plan, the risk cause location result, and the current construction plan into a preset content generation large model to obtain the target construction plan.

[0012] In one exemplary embodiment of this disclosure, the preset content generation model includes an embedding mapping layer, an encoding layer, and a hybrid expert model. The process of inputting the standard construction plan, risk cause location results, and the current construction plan into the preset content generation model to obtain the target construction plan includes: generating basic information to be predicted based on the standard construction plan, risk cause location results, and the current construction plan; generating context information to be predicted based on preset parameter prompts; performing embedding mapping processing on the basic information to be predicted based on the embedding mapping layer to obtain features of the region to be adjusted; performing embedding mapping processing on the context information to be predicted based on the embedding mapping layer to obtain a context marker sequence; encoding the features of the region to be adjusted and the context marker sequence based on the encoding layer to obtain an overall context representation; and generating content based on the context marker sequence and the overall context representation using the hybrid expert model to obtain the target construction plan.

[0013] In one exemplary embodiment of this disclosure, the hybrid expert model includes a gated network model and multiple expert neural network models. The process of generating a target construction scheme based on the context flag sequence and the overall context representation using the hybrid expert model includes: determining, based on the context flag sequence, first model weights for performing the scheme generation task in the construction safety dimension and second model weights for performing the scheme generation task in the construction efficiency dimension from the multiple expert neural network models; determining, based on the first and second model weights, a first target neural network model required for performing the scheme generation task in the construction safety dimension and a second target neural network model required for performing the scheme generation task in the construction efficiency dimension from the multiple expert neural network models; inputting the context flag sequence and the overall context representation into the first and second target neural network models respectively to obtain a first prediction result in the construction safety dimension and a second prediction result in the construction efficiency dimension, and obtaining the target construction scheme based on the first and second prediction results.

[0014] According to one aspect of this disclosure, an intelligent optimization device for the regeneration construction scheme of old industrial buildings based on the Internet of Things is provided, comprising: a real-time construction data receiving module, used to receive current real-time construction data corresponding to a target construction area sent by a data acquisition terminal; a current risk parameter determination module, used to determine the current conventional construction risk parameters and current environmental risk parameters of the target construction area based on the current real-time construction data; a target risk parameter determination module, used to adjust the current conventional construction risk parameters and current environmental risk parameters according to a preset risk parameter weight matrix to obtain target conventional construction risk parameters and target environmental risk parameters; and a construction scheme dynamic adjustment module, used to determine a comprehensive risk parameter based on the target conventional construction risk parameters and target environmental risk parameters, and dynamically adjust the current construction scheme of the target construction area based on the comprehensive risk parameter to obtain a target construction scheme.

[0015] This disclosure provides an intelligent optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things. On the one hand, it receives real-time construction data corresponding to the target construction area from a data acquisition terminal, and then determines the current conventional construction risk parameters and current environmental risk parameters of the target construction area based on the real-time construction data. Then, it adjusts the current conventional construction risk parameters and current environmental risk parameters according to a preset risk parameter weight matrix to obtain the target conventional construction risk parameters and target environmental risk parameters. Finally, it determines the comprehensive risk parameters based on the target conventional construction risk parameters and target environmental risk parameters, and dynamically adjusts the current construction scheme of the target construction area based on the comprehensive risk parameters to obtain the target construction scheme. This achieves automatic generation of the construction scheme, thereby solving the problem of low efficiency in the prior art. On the other hand, because the construction scheme can be dynamically adjusted, it solves the problem of the inability to make dynamic adjustments in the prior art.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0018] Figure 1 The diagram illustrates a flowchart of an intelligent optimization method for the regeneration construction of old industrial buildings based on the Internet of Things, according to an exemplary embodiment of the present disclosure.

[0019] Figure 2 The diagram schematically illustrates a structural example of an IoT-based intelligent optimization system for the regeneration of old industrial buildings according to an exemplary embodiment of this disclosure.

[0020] Figure 3 The diagram schematically illustrates a structural example of a preset content generation large model according to an exemplary embodiment of the present disclosure.

[0021] Figure 4 The diagram schematically illustrates a structural example of a hybrid expert model in a content generation large model according to an exemplary embodiment of the present disclosure.

[0022] Figure 5 An example diagram illustrating a region identification result obtained according to an exemplary embodiment of the present disclosure is shown.

[0023] Figure 6 The diagram schematically illustrates a scenario example of one priority according to an exemplary embodiment of the present disclosure.

[0024] Figure 7 An example diagram illustrating an area to be adjusted obtained according to an exemplary embodiment of this disclosure is shown.

[0025] Figure 8 The illustration shows an example scenario of dynamically adjusting a current construction plan according to an exemplary embodiment of the present disclosure.

[0026] Figure 9 The diagram schematically illustrates a structural example of an IoT-based intelligent optimization device for the regeneration construction of old industrial buildings according to an exemplary embodiment of this disclosure.

[0027] Figure 10 The diagram schematically illustrates an example electronic device for implementing an intelligent optimization method for the regeneration construction scheme of old industrial buildings based on an exemplary embodiment of the present disclosure. Detailed Implementation

[0028] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0029] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0030] Current construction risk assessments primarily employ a static assessment and periodic inspection model. Specifically, the core technical approaches can include: Firstly, experience-based qualitative assessment methods, such as the Safety Checklist (SCL) and Likelihood Exposure Consequence (LEC) methods. The implementation involves managers scoring risk levels on-site using a pre-set risk list or risk coefficients (exposure rate L, injury severity E, and probability of hazard occurrence C). However, this method relies on human experience and is suitable for preliminary risk screening in routine construction scenarios, but not for final solution generation. Secondly, quantitative assessment systems based on fixed parameters: some solutions introduce sensors (such as dust concentration sensors and noise sensors) to collect data on single or small risk factors, combined with pre-set thresholds to determine the risk status. This method does not consider actual conditions and cannot dynamically adjust the assessment for the construction team.

[0031] To address the aforementioned issues, risk assessments for regeneration operations in old industrial areas often refer to conventional building construction standards. Some studies have attempted to incorporate environmental damage factors for correction; for example, by adding a weight to the assessment model for "soil pollution level." However, this still does not overcome the problem of a static framework with fixed parameters and regular updates, which requires regular manual input of test data and has a long update cycle.

[0032] As can be seen from the above-described solutions, the existing solutions have significant shortcomings: Firstly, the lag in risk assessment leads to a lag in solution determination. Specifically, because they rely on manual data entry (daily or weekly updates), they cannot capture the dynamic changes in risks under environmental damage conditions in real time. For example, the risks caused by sudden cracks in walls in old industrial areas or leaks in underground pipelines require several hours to several days for static assessment, resulting in low accuracy of the solutions. Secondly, incomplete coverage of risk factors leads to incomplete solution coverage. Specifically, existing technologies mostly focus on conventional risks such as "mechanical injury and falls from heights," failing to fully integrate environmental damage risk factors specific to old industrial areas (such as heavy metals in soil, volatile organic compounds (VOCs), and wall cracking risks). This results in a large deviation rate in the assessment results, leading to low accuracy of the solutions. Thirdly, the assessment model has poor adaptability. Specifically, existing technologies use fixed weight coefficients (such as the probability of hazard occurrence C being fixed at 0.5 in the LEC method), which cannot dynamically adjust parameters according to the construction stage and environmental conditions (such as rainy days or high temperatures). This results in a high rate of missed detection in high-risk scenarios, leading to low accuracy of the solutions.

[0033] Based on the problems described above, this exemplary embodiment first provides an intelligent optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things. This method can run on servers, server clusters, or cloud servers, etc. Of course, those skilled in the art can also run the method disclosed herein on other platforms as needed, and this exemplary embodiment does not make any special limitations on this. Specifically, refer to... Figure 1 As shown, the intelligent optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things may include the following steps:

[0034] Step S110. Receive the current real-time construction data corresponding to the target construction area sent by the data acquisition terminal;

[0035] Step S120. Determine the current conventional construction risk parameters and current environmental risk parameters of the target construction area based on the current real-time construction data;

[0036] Step S130. Adjust the current conventional construction risk parameters and the current environmental risk parameters according to the preset risk parameter weight matrix to obtain the target conventional construction risk parameters and the target environmental risk parameters;

[0037] Step S140. Determine the comprehensive risk parameters based on the target conventional construction risk parameters and the target environmental risk parameters, and dynamically adjust the current construction plan for the target construction area based on the comprehensive risk parameters to obtain the target construction plan.

[0038] In the aforementioned intelligent optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things, on the one hand, it receives real-time construction data corresponding to the target construction area from a data acquisition terminal; then, it determines the current conventional construction risk parameters and current environmental risk parameters of the target construction area based on the real-time construction data; furthermore, it adjusts the current conventional construction risk parameters and current environmental risk parameters according to a preset risk parameter weight matrix to obtain the target conventional construction risk parameters and target environmental risk parameters; finally, it determines the comprehensive risk parameters based on the target conventional construction risk parameters and target environmental risk parameters, and dynamically adjusts the current construction scheme of the target construction area based on the comprehensive risk parameters to obtain the target construction scheme, thereby realizing the automatic generation of the construction scheme and solving the problem of low efficiency in the prior art; on the other hand, since the construction scheme can be dynamically adjusted, it solves the problem of the inability to make dynamic adjustments in the prior art.

[0039] The following will provide a detailed explanation and description of the intelligent optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things, as described in the exemplary embodiments of this disclosure, with reference to the accompanying drawings.

[0040] First, the application scenarios and technical implementation principles of the exemplary embodiments of this disclosure are explained and described. Specifically, the intelligent optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things described in the exemplary embodiments of this disclosure is applicable to the regeneration operation scenario of old industrial areas under environmental damage conditions. It can realize real-time monitoring and dynamic assessment of the occupational exposure risks of construction workers during the transformation of old industrial areas, providing data support and decision-making basis for construction safety management. Furthermore, the regeneration operation of old industrial areas is affected by environmental damage factors such as aging of the original building structure, pollution of environmental media (such as heavy metals in the soil and volatile organic compounds), and limited construction space. The occupational exposure risks faced by construction workers (such as mechanical injury, exposure to chemical toxins, dust inhalation, etc.) have the characteristics of suddenness, superposition, and timeliness. Existing static assessment methods are difficult to meet the risk management needs in this scenario. This disclosure proposes a solution to this technical pain point in a specific field. Furthermore, the solutions described in the exemplary embodiments of this disclosure aim to address three core problems of existing occupational exposure risk assessment methods and systems in the context of regeneration operations in old industrial areas: on the one hand, risk assessment is lagging and cannot respond in real time to dynamic changes in risk under environmental damage conditions; on the other hand, risk factors are not fully covered and do not integrate environmental damage risk factors unique to old industrial areas; and on the third hand, the assessment model has poor adaptability and cannot dynamically adjust parameter weights according to construction stages and environmental conditions, leading to misjudgment and omission of risks.

[0041] Secondly, the intelligent optimization system for the regeneration construction scheme of old industrial buildings based on the Internet of Things involved in the exemplary embodiments of this disclosure will be explained and described. Specifically, refer to... Figure 2 As shown, the intelligent optimization system for the regeneration construction scheme of old industrial buildings based on the Internet of Things (IoT) may include a data acquisition terminal 210, an edge server 220, and a cloud server 230. The data acquisition terminal connects to the edge server via IoT; the edge server communicates with the cloud server via wired or wireless networks. In practical applications, the data acquisition terminal can be used to collect real-time construction data; the edge server and cloud server can be used to implement the intelligent optimization method for the regeneration construction scheme of old industrial buildings based on IoT as described in the exemplary embodiments of this disclosure. The data acquisition terminal described herein may include IoT terminal devices, such as various sensors with different functions; it may also include mobile terminals (such as mobile phones, tablets, or personal computers) or fixed terminals (such as desktop computers), etc., and this example does not impose any special limitations on this.

[0042] In one example embodiment, the data acquisition terminal described above may include a wireless sensor array, a positioning module, and a manual input interface. The wireless sensor array is deployed in the construction area and includes sensors with different functional categories, such as mechanical speed sensors, heavy metal sensors, VOCs (Volatile Organic Compounds) sensors, and PM2.5 sensors. In practical applications, the mechanical speed sensor has a measurement range of 0-10 m / s and an accuracy controlled within ±0.1 m / s; the heavy metal sensor has a detection range of 0-100 mg / kg and an accuracy controlled within ±0.5 mg / kg; the VOCs sensor has a detection range of 0-500 ppm and an accuracy of ±1 ppm; and the PM2.5 sensor has a detection range of 0-1000 μg / m³ and an accuracy of ±5 μg / m³. Furthermore, the wireless sensor array supports battery power (≥72 hours of battery life) and solar power replenishment; the positioning module uses BeiDou + GPS (Global Positioning System). The Positioning System (GPS) dual-mode positioning, with a positioning accuracy of ≤5 meters, is used to acquire position data of sensors and workers' smart safety helmets; the manual input interface allows managers to input parameters such as wall crack width and protective facility integrity rate through a mobile application, and the data is synchronized to the edge server in real time.

[0043] In one example embodiment, the edge server performs the following functions: receiving real-time construction data corresponding to the target construction area sent by the data acquisition terminal, and determining the current conventional construction risk parameters and current environmental risk parameters of the target construction area based on the real-time construction data; the cloud server performs the following functions: adjusting the current conventional construction risk parameters and current environmental risk parameters according to a preset risk parameter weight matrix to obtain target conventional construction risk parameters and target environmental risk parameters; determining comprehensive risk parameters based on the target conventional construction risk parameters and target environmental risk parameters, and dynamically adjusting the current construction plan of the target construction area based on the comprehensive risk parameters to obtain the target construction plan. Based on this, the following technical problems can be solved: on the one hand, reducing the computational burden of the cloud server, thereby improving the efficiency of construction plan adjustment; on the other hand, reducing the bandwidth resource consumption caused during data transmission; that is, the data acquisition terminal does not need to transmit all data to the cloud server, but can perform corresponding data processing functions on the edge server, thereby improving the utilization rate of the edge server. It should also be noted that the cloud server described here can adopt a distributed computing architecture, supporting parallel processing of 1000+ data entries per second, and possessing model calculation and data storage functions.

[0044] Furthermore, the preset content generation model involved in the exemplary embodiments of this disclosure will be explained and described. Specifically, refer to... Figure 3 As shown, the preset content generation model described herein may include an embedding mapping layer 310, an encoding layer 320, and a hybrid expert model 330; furthermore, the hybrid expert model described herein includes a gating network model and multiple expert neural network models, for details please refer to Figure 4 As shown. The roles of each model layer in the content generation process will be detailed later, and will not be repeated here.

[0045] The following will combine Figures 2-4 right Figure 1 The intelligent optimization method for the IoT-based regeneration construction scheme of old industrial buildings shown will be further explained and illustrated. Specifically:

[0046] In step S110, the current real-time construction data corresponding to the target construction area is received from the data acquisition terminal.

[0047] In this example, the edge server receives real-time construction data corresponding to the target construction area from the data acquisition terminal. Specifically, the real-time construction data recorded here may include data uploaded by the wireless sensor array, such as machinery operating speed data, construction safety distance data, construction working height data, voltage fluctuation range, grounding resistance, soil heavy metal concentration, volatile organic compound concentration, pipeline corrosion degree, fine particulate matter concentration, and dust diffusion speed, etc.; or, for example, wall crack width data and protective facility integrity rate data uploaded through the supplementary input interface, etc. It should also be noted that the current real-time construction data acquisition frequency is set to 1 time / minute, but other frequencies are also possible. The specific frequency can be adaptively adjusted according to the construction intensity, with a maximum of 1 time / 10 seconds. This example does not impose any special restrictions on this.

[0048] In step S120, the current conventional construction risk parameters and current environmental risk parameters of the target construction area are determined based on the current real-time construction data.

[0049] Specifically, the determination process for current conventional construction risk parameters and current environmental risk parameters can be achieved as follows: Analyze the current real-time construction data to obtain conventional construction data collected by conventional construction sensors and construction environment data collected by environmental sensors; determine the current conventional construction risk parameters for the target construction area based on the conventional construction data; wherein, the current conventional construction risk parameters recorded here include machinery operating speed, construction safety distance, construction working height, current equipment status of protective equipment, voltage fluctuation range, and grounding resistance, etc.; determine the current environmental risk parameters for the target construction area based on the construction environment data; wherein, the current environmental risk parameters recorded here include soil heavy metal concentration, volatile organic compound concentration, wall crack width, pipeline corrosion degree, fine particulate matter concentration, and dust diffusion rate, etc. Specifically, in practical applications, after receiving real-time construction data, the edge server first needs to perform data cleaning. During data cleaning, abnormal sensor data can be corrected using a moving average method or simply ignored. For example, when the data collected by a sensor exceeds three times the safety threshold, the system automatically marks the data as abnormal and ignores it, while recording the abnormal data collection time and sensor number for subsequent adjustment, debugging, or replacement of the sensor. Furthermore, after data cleaning, the current routine construction risk parameters and current environmental risk parameters can be determined from the cleaned construction data. Finally, the current routine construction risk parameters and current environmental risk parameters are sent to the cloud server for subsequent dynamic adjustment of the construction plan.

[0050] In step S130, the current conventional construction risk parameters and the current environmental risk parameters are adjusted according to the preset risk parameter weight matrix to obtain the target conventional construction risk parameters and the target environmental risk parameters.

[0051] Specifically, the parameter adjustment process is as follows: determine the current construction status identification result of the target construction area, and match the preset risk parameter weight matrix corresponding to the target construction area based on the current construction status identification result; determine the current weather data of the target construction area, and determine the environmental condition correction coefficient corresponding to the target construction area based on the current weather data; adjust the current conventional construction risk parameters according to the preset risk parameter weight matrix to obtain the target conventional construction risk parameters; and adjust the current environmental risk parameters according to the environmental condition correction coefficient and the preset risk parameter weight matrix to obtain the target environmental risk parameters. Specifically, in practical applications, the current construction status identification result can include the demolition stage, the cleaning stage, and the reconstruction stage. Under this premise, different preset risk parameter weight matrices can be configured for each different stage in advance. The preset risk parameter weight matrices recorded here can be set by expert experience or determined by the corresponding weight prediction model. Furthermore, the environmental condition correction coefficients recorded here can be determined according to the weather conditions. For example, the rain correction coefficient K (rainy day) = 0.8; the high temperature correction coefficient K (high temperature) = 1.2. Of course, they can also be set according to the actual situation. This example does not impose any special restrictions on this.

[0052] In one possible example embodiment, the weight prediction model described herein may be a convolutional neural network model, a recurrent neural network model, a decision tree model, a large language model, or a BERT model; this example does not impose any special limitations on this.

[0053] In one possible example embodiment, assuming the target construction area is currently in the demolition phase, the "structural damage risk weight" can be set to 0.3 (higher than 0.1 in the reconstruction phase), and the "dust exposure risk weight" can be set to 0.25 (higher than 0.15 in the cleanup phase). Furthermore, in rainy weather, the "fall from height risk weight" is automatically multiplied by K (rainy weather) to reduce the probability of misjudgment. It should also be noted that this embodiment only illustrates the weight of one or several parameters. The weights of other parameters are specifically referred to in the corresponding risk parameter weight matrix. This example does not impose any special restrictions on this. The specific calculation formula for the target conventional construction risk parameters can be shown in the following formula (1); at the same time, the specific calculation formula for the target environmental risk parameters can be shown in the following formula (2).

[0054] ; Formula (1)

[0055] in, For the m-th target, the conventional construction risk parameters are... This represents the actual collected value of the m-th current routine construction risk parameter. This is the preset threshold for the m-th current routine construction risk parameter, which can be determined according to the construction safety manual. The weight is the m-th current conventional construction risk parameter.

[0056] ; Formula (2)

[0057] in, For the nth target environmental risk parameter, For n current environmental risk parameters, This is the preset threshold for the nth current environmental risk parameter, which can be determined according to the construction safety manual. The weight of the risk parameter for the nth current environmental parameter. This is the environmental condition correction factor. The construction safety manual mentioned here may be, for example, the "Environmental Noise Emission Standard for Construction Site Boundary" (GB12523-2011) and the "Occupational Exposure Limits for Hazardous Factors in the Workplace" (GBZ2.1-2019), etc. You can choose according to your actual needs. This example does not impose any special restrictions on this.

[0058] In step S140, a comprehensive risk parameter is determined based on the target conventional construction risk parameter and the target environmental risk parameter, and the current construction plan for the target construction area is dynamically adjusted based on the comprehensive risk parameter to obtain the target construction plan.

[0059] In this example embodiment, firstly, a comprehensive risk parameter is determined based on the target conventional construction risk parameters and the target environmental risk parameters. Specifically, this can be achieved as follows: A conventional construction risk value is determined based on the target conventional construction risk parameters; wherein, the conventional construction risk value recorded here may include, but is not limited to, mechanical injury risk value, fall from height risk value, and electric shock risk value, etc.; A construction environmental risk value is determined based on the target environmental risk parameters; wherein, the construction environmental risk value recorded here may include, but is not limited to, chemical exposure risk value, structural damage risk value, and dust exposure risk value, etc.; A first weight value and a second weight value are determined for the conventional construction risk value and the construction environmental risk value, and the conventional construction risk value, the first weight value, the construction environmental risk value, and the second weight value are weighted and summed to obtain the comprehensive risk parameter of the target construction area.

[0060] In one example embodiment, determining the conventional construction risk value based on the target conventional construction risk parameters can be achieved as follows: The mechanical injury risk value is determined based on the target machinery operating speed and target safety distance in the target conventional construction risk parameters; the fall-from-height risk value is determined based on the target working height and target protective facility integrity rate in the target conventional construction risk parameters; the electric shock risk value is determined based on the target voltage fluctuation value and target grounding resistance in the target conventional construction risk parameters; and the conventional construction risk value is determined based on the mechanical injury risk value, the fall-from-height risk value, and the electric shock risk value. Specifically, the conventional construction risk value described here can be obtained by directly summing the mechanical injury risk value, the fall-from-height risk value, and the electric shock risk value, or by calculating the average value, or by weighted summation; this example does not impose any special limitations on this.

[0061] In one example embodiment, determining the construction environment risk value based on the target environmental risk parameters can be achieved as follows: A chemical exposure risk value is determined based on the target soil heavy metal concentration and the target volatile organic compound concentration from the target environmental risk parameters; a structural damage risk value is determined based on the target wall crack width and the target pipeline corrosion degree from the target environmental risk parameters; a dust exposure risk value is determined based on the target fine particulate matter concentration and the target dust diffusion rate from the target environmental risk parameters; and the construction environment risk value is determined based on the chemical exposure risk value, the structural damage risk value, and the dust exposure risk value. Specifically, the construction environment risk value described herein can be obtained by directly summing the chemical exposure risk value, the structural damage risk value, and the dust exposure risk value, or by calculating the average value, or by weighted summation; this example does not impose any special limitations on this.

[0062] The following will further explain and illustrate the specific process for determining the comprehensive risk parameters. Specifically, the calculation process for the comprehensive risk parameters can be shown in the following formula (3):

[0063] ; Formula (3)

[0064] in, To comprehensively assess risk parameters, This is the standard construction risk value. This is the first weight value; This represents the construction environment risk value. The first and second weight values ​​can be set by the user based on expert experience or predicted by a corresponding weight value prediction model. This example does not impose any special restrictions on this. For example, the first weight value can be 0.4 and the second weight value can be 0.6. Of course, other values ​​are also possible. This example does not impose any special restrictions on this.

[0065] Secondly, the current construction plan for the target construction area is dynamically adjusted based on the comprehensive risk parameters to obtain the target construction plan. Specifically, this can be achieved as follows: A region identifier is assigned to the target construction area based on the comprehensive risk parameters, and the adjustment priority of the plan for the target construction area is determined based on the region identifier; Based on the adjustment priority, the area to be adjusted is determined from the target construction area, and based on the reasoning process of the comprehensive risk parameters, the risk causes of the area to be adjusted are located to obtain the risk cause location result; A standard construction plan corresponding to the risk cause location result is obtained, and the standard construction plan, the risk cause location result, and the current construction plan are input into a preset content generation model to obtain the target construction plan.

[0066] In practical applications, target construction areas corresponding to different comprehensive risk parameters have different risk levels, and different risk levels have different area identifiers. For example, if the comprehensive risk parameter is less than 0.3, the risk level of the target construction area is determined to be low risk (Level 1); if the comprehensive risk parameter is greater than or equal to 0.3 and less than 0.5, the risk level is determined to be low-to-medium risk (Level 2); if the comprehensive risk parameter is greater than or equal to 0.5 and less than 0.7, the risk level is determined to be medium risk (Level 3); if the comprehensive risk parameter is greater than or equal to 0.7 and less than 0.9, the risk level is determined to be high risk (Level 4); and if the comprehensive risk parameter is greater than or equal to 0.9, the risk level is determined to be extremely high risk (Level 5). Levels 1 and 2 can be identified using green; Level 3 can be identified using yellow; Level 4 can be identified using orange; and Level 5 can be identified using red. In practical applications, the real-time risk distribution can be displayed on the corresponding interface, and users can click on risk areas to view detailed factor data and historical trends. Based on this, the obtained area identification results can be used as a reference. Figure 5 As shown. Furthermore, the higher the corresponding risk level, the higher the priority of the plan adjustment; for example, the priority of level 5 ≥ the priority of level 4 ≥ the priority of level 3 ≥ the priority of level 2 ≥ the priority of level 1, etc. For details, please refer to... Figure 6 As shown.

[0067] In this embodiment, the example diagram of the area to be adjusted can be referred to. Figure 7 As shown, for example, it could be the highest priority area. Based on this, the standard construction plan, risk cause location results, and current construction plan of this area can be input into a preset content generation model to obtain the target construction plan. Specifically, the content generation model described here can include an embedding mapping layer, an encoding layer, and a hybrid expert model. Based on this, the specific determination process of the target construction plan can be implemented as follows: generate basic information to be predicted based on the standard construction plan, risk cause location results, and current construction plan, and generate context information to be predicted based on preset parameter prompts; perform embedding mapping processing on the basic information to be predicted based on the embedding mapping layer to obtain the features of the area to be adjusted; perform embedding mapping processing on the context information to be predicted based on the embedding mapping layer to obtain the context flag sequence; perform encoding processing on the features of the area to be adjusted and the context flag sequence based on the encoding layer to obtain the overall context representation; generate content based on the context flag sequence and the overall context representation using the hybrid expert model to obtain the target construction plan.

[0068] In one example embodiment, the hybrid expert model described above includes a gated network model and multiple expert neural network models. The target construction plan is generated based on the context flag sequence and the overall context representation using the hybrid expert model. This can be achieved as follows: Based on the context flag sequence, the hybrid expert model determines the first model weights of the multiple expert neural network models for performing the plan generation task in the construction safety dimension and the second model weights for performing the plan generation task in the construction efficiency dimension. Based on the first and second model weights, the first target neural network model required for performing the plan generation task in the construction safety dimension and the second target neural network model required for performing the plan generation task in the construction efficiency dimension are determined from the multiple expert neural network models. The context flag sequence and the overall context representation are input into the first and second target neural network models respectively to obtain a first prediction result in the construction safety dimension and a second prediction result in the construction efficiency dimension. Based on the first and second prediction results, the target construction plan is obtained. A specific example diagram of the dynamic adjustment scenario can be found in the following diagram. Figure 8 As shown.

[0069] In one example embodiment, the specific determination process of the risk cause localization result described above can be implemented based on a corresponding feature extraction model. Specifically, the feature extraction model described herein may include, in one example embodiment, an embedding layer, a position encoding module, a rotation feature encoding module, a feature decoding module, a linear transformation layer, and a classification layer. Under this premise, based on the reasoning process of the comprehensive risk parameters, the risk cause of the region to be adjusted is located to obtain the risk cause localization result, which can be achieved as follows: the reasoning process of the comprehensive risk parameters is embedded based on the embedding layer to obtain a first embedding vector, and the reasoning process of the comprehensive risk parameters is encoded based on the position encoding module to obtain a first position vector; the first embedding vector and the first position vector are superimposed to obtain a first input vector, and the first input vector is encoded based on the rotation feature encoding module to obtain a first encoding result; the first encoding result is decoded based on the feature decoding module to obtain a first encoding matrix, and the first encoding matrix is ​​transformed based on the linear transformation layer to obtain a first logical matrix; the first logical matrix is ​​mapped based on the classification layer to obtain the risk cause localization result.

[0070] In one example embodiment, the rotation feature encoding module described above includes a first multi-head self-attention module, a first residual connection and normalization module, a first feedforward neural network, and a second residual connection and normalization module. The first encoding result obtained by encoding the first input vector based on the rotation feature encoding module can be achieved as follows: a first attention mechanism is calculated based on the first multi-head self-attention module, and the first attention mechanism is subjected to residual connection and normalization processing based on the first residual connection and normalization module to obtain a first normalization result; the first normalization result is linearized based on the first feedforward neural network to obtain a first linearization result; and the first linearization result is subjected to residual connection and normalization processing based on the second residual connection and normalization module to obtain the first encoding result.

[0071] In one example embodiment, the first attention mechanism based on the first multi-head self-attention module to calculate the first input vector can be implemented as follows: linearly fuse the first input vector to obtain a first query vector, a first key vector, and a first value vector; adjust the relative angles of the first query vector and the first key vector based on a preset first rotation matrix to obtain adjusted first query vector and adjusted first key vector; calculate the first outer product vector of the adjusted first query vector and the adjusted first key vector to obtain a first similarity between the adjusted first query vector and the adjusted first key vector; normalize the first similarity to obtain a first weight matrix; and calculate the second outer product vector of the first weight matrix and the first value vector to obtain the first attention mechanism.

[0072] Thus, the intelligent optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things, as described in the exemplary embodiments of this disclosure, has been fully implemented.

[0073] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein. For details not disclosed in the apparatus embodiments of this disclosure, please refer to the embodiments of the method disclosed herein.

[0074] This disclosure also provides an intelligent optimization device for the regeneration construction scheme of old industrial buildings based on the Internet of Things. Specifically, refer to... Figure 9 As shown, the IoT-based intelligent optimization device for the regeneration construction scheme of old industrial buildings may include a real-time construction data receiving module 910, a current risk parameter determination module 920, a target risk parameter determination module 930, and a construction scheme dynamic adjustment module 940.

[0075] The real-time construction data receiving module 910 can be used to receive the current real-time construction data corresponding to the target construction area sent by the data acquisition terminal; the current risk parameter determination module 920 can be used to determine the current conventional construction risk parameters and current environmental risk parameters of the target construction area based on the current real-time construction data; the target risk parameter determination module 930 can be used to adjust the current conventional construction risk parameters and current environmental risk parameters according to a preset risk parameter weight matrix to obtain the target conventional construction risk parameters and target environmental risk parameters; the construction plan dynamic adjustment module 940 can be used to determine the comprehensive risk parameters based on the target conventional construction risk parameters and target environmental risk parameters, and dynamically adjust the current construction plan of the target construction area based on the comprehensive risk parameters to obtain the target construction plan.

[0076] In an exemplary embodiment of this disclosure, determining the current conventional construction risk parameters and current environmental risk parameters of the target construction area based on the current real-time construction data includes: parsing the current real-time construction data to obtain conventional construction data collected by conventional construction sensors and construction environment data collected by environmental sensors; determining the current conventional construction risk parameters of the target construction area based on the conventional construction data; wherein the current conventional construction risk parameters include at least one of machinery operating speed, construction safety distance, construction operation height, current equipment status of protective equipment, voltage fluctuation range, and grounding resistance; and determining the current environmental risk parameters of the target construction area based on the construction environment data; wherein the current environmental risk parameters include at least one of soil heavy metal concentration, volatile organic compound concentration, wall crack width, pipeline corrosion degree, fine particulate matter concentration, and dust diffusion rate.

[0077] In one exemplary embodiment of this disclosure, adjusting the current conventional construction risk parameters and the current environmental risk parameters according to a preset risk parameter weight matrix to obtain target conventional construction risk parameters and target environmental risk parameters includes: determining the current construction status identification result of the target construction area, and matching the current construction status identification result with a preset risk parameter weight matrix corresponding to the target construction area; determining the current weather data of the target construction area, and determining the environmental condition correction coefficient corresponding to the target construction area based on the current weather data; adjusting the current conventional construction risk parameters according to the preset risk parameter weight matrix to obtain target conventional construction risk parameters, and adjusting the current environmental risk parameters according to the environmental condition correction coefficient and the preset risk parameter weight matrix to obtain target environmental risk parameters.

[0078] In one exemplary embodiment of this disclosure, determining comprehensive risk parameters based on target conventional construction risk parameters and target environmental risk parameters includes: determining conventional construction risk values ​​based on the target conventional construction risk parameters; wherein the conventional construction risk values ​​include at least one of mechanical injury risk values, fall from height risk values, and electric shock risk values; determining construction environmental risk values ​​based on the target environmental risk parameters; wherein the construction environmental risk values ​​include chemical exposure risk values, structural damage risk values, and dust exposure risk values; determining a first weight value and a second weight value for the conventional construction risk values ​​and the construction environmental risk values, and performing a weighted summation of the conventional construction risk values, the first weight value, the construction environmental risk values, and the second weight value to obtain comprehensive risk parameters for the target construction area.

[0079] In one exemplary embodiment of this disclosure, determining the conventional construction risk value based on the target conventional construction risk parameters includes: determining the machinery injury risk value based on the target machinery operating speed and target safety distance in the target conventional construction risk parameters; determining the fall-from-height risk value based on the target working height and target protective facility integrity rate in the target conventional construction risk parameters; determining the electric shock risk value based on the target voltage fluctuation value and target grounding resistance in the target conventional construction risk parameters; and determining the conventional construction risk value based on the machinery injury risk value, the fall-from-height risk value, and the electric shock risk value.

[0080] In one exemplary embodiment of this disclosure, determining the construction environment risk value based on the target environmental risk parameters includes: determining a chemical exposure risk value based on the target soil heavy metal concentration and the target volatile organic compound concentration in the target environmental risk parameters; determining a structural damage risk value based on the target wall crack width and the target pipeline corrosion degree in the target environmental risk parameters; determining a dust exposure risk value based on the target fine particulate matter concentration and the target dust diffusion rate in the target environmental risk parameters; and determining the construction environment risk value based on the chemical exposure risk value, the structural damage risk value, and the dust exposure value.

[0081] In one exemplary embodiment of this disclosure, dynamically adjusting the current construction plan of the target construction area according to the comprehensive risk parameters to obtain a target construction plan includes: assigning a region identifier to the target construction area according to the comprehensive risk parameters, and determining the plan adjustment priority of the target construction area according to the region identifier; determining the region to be adjusted from the target construction area based on the plan adjustment priority, and locating the risk cause of the region to be adjusted based on the reasoning process of the comprehensive risk parameters to obtain a risk cause location result; obtaining a standard construction plan corresponding to the risk cause location result, and inputting the standard construction plan, the risk cause location result, and the current construction plan into a preset content generation large model to obtain the target construction plan.

[0082] In one exemplary embodiment of this disclosure, the preset content generation model includes an embedding mapping layer, an encoding layer, and a hybrid expert model. The process of inputting the standard construction plan, risk cause location results, and the current construction plan into the preset content generation model to obtain the target construction plan includes: generating basic information to be predicted based on the standard construction plan, risk cause location results, and the current construction plan; generating context information to be predicted based on preset parameter prompts; performing embedding mapping processing on the basic information to be predicted based on the embedding mapping layer to obtain features of the region to be adjusted; performing embedding mapping processing on the context information to be predicted based on the embedding mapping layer to obtain a context marker sequence; encoding the features of the region to be adjusted and the context marker sequence based on the encoding layer to obtain an overall context representation; and generating content based on the context marker sequence and the overall context representation using the hybrid expert model to obtain the target construction plan.

[0083] In one exemplary embodiment of this disclosure, the hybrid expert model includes a gated network model and multiple expert neural network models. The process of generating a target construction scheme based on the context flag sequence and the overall context representation using the hybrid expert model includes: determining, based on the context flag sequence, first model weights for performing the scheme generation task in the construction safety dimension and second model weights for performing the scheme generation task in the construction efficiency dimension from the multiple expert neural network models; determining, based on the first and second model weights, a first target neural network model required for performing the scheme generation task in the construction safety dimension and a second target neural network model required for performing the scheme generation task in the construction efficiency dimension from the multiple expert neural network models; inputting the context flag sequence and the overall context representation into the first and second target neural network models respectively to obtain a first prediction result in the construction safety dimension and a second prediction result in the construction efficiency dimension, and obtaining the target construction scheme based on the first and second prediction results.

[0084] The specific details of each module in the aforementioned IoT-based intelligent optimization device for the regeneration construction of old industrial buildings have already been described in detail in the corresponding IoT-based intelligent optimization method for the regeneration construction of old industrial buildings, and therefore will not be repeated here. It should be noted that although several modules or units of the equipment used for action execution have been mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0085] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0086] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0087] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0088] The following reference Figure 10 To describe an electronic device 1000 according to such an embodiment of the present disclosure. Figure 10 The electronic device 1000 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0089] like Figure 10 As shown, the electronic device 1000 is manifested in the form of a general-purpose computing device. The components of the electronic device 1000 may include, but are not limited to: at least one processing unit 1010, at least one storage unit 1020, a bus 1030 connecting different system components (including storage unit 1020 and processing unit 1010), and a display unit 1040.

[0090] The storage unit stores program code that can be executed by the processing unit 1010, causing the processing unit 1010 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 1010 can perform actions such as... Figure 1The steps shown are as follows: Step S110: Receive the current real-time construction data corresponding to the target construction area sent by the data acquisition terminal; Step S120: Determine the current conventional construction risk parameters and current environmental risk parameters of the target construction area based on the current real-time construction data; Step S130: Adjust the current conventional construction risk parameters and current environmental risk parameters according to the preset risk parameter weight matrix to obtain the target conventional construction risk parameters and target environmental risk parameters; Step S140: Determine the comprehensive risk parameters based on the target conventional construction risk parameters and target environmental risk parameters, and dynamically adjust the current construction plan of the target construction area based on the comprehensive risk parameters to obtain the target construction plan.

[0091] Storage unit 1020 may include readable media in the form of volatile storage units, such as random access memory (RAM) 10201 and / or cache memory 10202, and may further include read-only memory (ROM) 10203.

[0092] Storage unit 1020 may also include a program / utility 10204 having a set (at least one) program module 10205, such program module 10205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0093] Bus 1030 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the multiple bus structures.

[0094] Electronic device 1000 can also communicate with one or more external devices 1100 (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with electronic device 1000, and / or any device that enables electronic device 1000 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 1050. Furthermore, electronic device 1000 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 1060. As shown, network adapter 1060 communicates with other modules of electronic device 1000 via bus 1030. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 1000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0095] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0096] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible implementations, various aspects of this disclosure may also be implemented as a program product including program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of this disclosure described in the "Exemplary Methods" section above.

[0097] The program product for implementing the above-described method according to embodiments of the present disclosure may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0098] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0099] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0100] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0101] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0102] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0103] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention described herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not invented by this disclosure. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

Claims

1. A smart optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things, characterized in that, include: The system receives real-time construction data corresponding to the target construction area from a data acquisition terminal. The real-time construction data includes at least one of the following: mechanical operating speed data, construction safety distance data, construction working height data, voltage fluctuation range, grounding resistance, soil heavy metal concentration, volatile organic compound concentration, pipeline corrosion degree, fine particulate matter concentration, and dust diffusion rate. Determine the current conventional construction risk parameters and current environmental risk parameters of the target construction area based on the current real-time construction data. Adjusting the current conventional construction risk parameters and current environmental risk parameters according to a preset risk parameter weight matrix to obtain target conventional construction risk parameters and target environmental risk parameters includes: determining the current construction status identification result of the target construction area, and matching the current construction status identification result with a preset risk parameter weight matrix corresponding to the target construction area; determining the current weather data of the target construction area, and determining the environmental condition correction coefficient corresponding to the target construction area based on the current weather data; adjusting the current conventional construction risk parameters according to the preset risk parameter weight matrix to obtain target conventional construction risk parameters, and adjusting the current environmental risk parameters according to the environmental condition correction coefficient and the preset risk parameter weight matrix to obtain target environmental risk parameters. A comprehensive risk parameter is determined based on the target conventional construction risk parameter and the target environmental risk parameter. The current construction plan for the target construction area is then dynamically adjusted based on the comprehensive risk parameter to obtain the target construction plan. The target construction plan is obtained as follows: A region identifier is assigned to the target construction area based on the comprehensive risk parameter, and the adjustment priority of the plan for the target construction area is determined based on the region identifier; Based on the adjustment priority, a region to be adjusted is determined from the target construction area, and based on the reasoning process of the comprehensive risk parameter, the risk causes of the region to be adjusted are located to obtain the risk cause location result; A standard construction plan corresponding to the risk cause location result is obtained, and the standard construction plan, the risk cause location result, and the current construction plan are input into a preset content generation model to obtain the target construction plan; The preset content generation model includes an embedded mapping layer, an encoding layer, and a hybrid expert model. The target construction plan is determined as follows: Basic information to be predicted is generated based on the standard construction plan, risk cause location results, and the current construction plan; context information to be predicted is generated based on preset parameter prompts; the basic information to be predicted is embedded and mapped using the embedding mapping layer to obtain features of the region to be adjusted; the context information to be predicted is then embedded and mapped using the embedding mapping layer to obtain a context flag sequence; the features of the region to be adjusted and the context flag sequence are encoded using the encoding layer to obtain an overall context representation; and the context flag sequence and the overall context representation are then generated using a hybrid expert model to obtain the target construction plan.

2. The intelligent optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things as described in claim 1, characterized in that, Based on current real-time construction data, determine the current conventional construction risk parameters and current environmental risk parameters for the target construction area, including: The current real-time construction data is analyzed to obtain conventional construction data collected by conventional construction sensors and construction environment data collected by environmental sensors. Based on the aforementioned conventional construction data, the current conventional construction risk parameters for the target construction area are determined; wherein, the current conventional construction risk parameters include at least one of the following: machinery operating speed, construction safety distance, construction working height, voltage fluctuation range, grounding resistance, and the current equipment status of protective equipment; Based on the construction environment data, the current environmental risk parameters of the target construction area are determined; wherein, the current environmental risk parameters include at least one of the following: soil heavy metal concentration, volatile organic compound concentration, wall crack width, pipeline corrosion degree, fine particulate matter concentration, and dust diffusion rate.

3. The intelligent optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things as described in claim 1, characterized in that, The comprehensive risk parameters are determined based on the target's conventional construction risk parameters and target environmental risk parameters, including: The conventional construction risk value is determined based on the target conventional construction risk parameters; wherein, the conventional construction risk value includes at least one of the following: mechanical injury risk value, fall from height risk value, and electric shock risk value; The construction environment risk value is determined based on the target environmental risk parameters; wherein, the construction environment risk value includes chemical exposure risk value, structural damage risk value, and dust exposure risk value; The first weight value and the second weight value of the conventional construction risk value and the construction environment risk value are determined, and the conventional construction risk value, the first weight value, the construction environment risk value and the second weight value are weighted and summed to obtain the comprehensive risk parameters of the target construction area.

4. The intelligent optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things as described in claim 3, characterized in that, Determining the conventional construction risk value based on the target conventional construction risk parameters includes: Based on the target machinery operating speed and target safety distance in the target conventional construction risk parameters, the machinery injury risk value is determined, and based on the target working height and target protective facility integrity rate in the target conventional construction risk parameters, the fall from height risk value is determined. The electric shock risk value is determined based on the target voltage fluctuation value and the target grounding resistance in the target conventional construction risk parameters, and the conventional construction risk value is determined based on the mechanical injury risk value, the fall from height risk value, and the electric shock risk value.

5. The intelligent optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things as described in claim 3, characterized in that, Determining the construction environment risk value based on the target environmental risk parameters includes: Based on the target soil heavy metal concentration and target volatile organic compound concentration in the target environmental risk parameters, the chemical exposure risk value is determined, and based on the target wall crack width and target pipeline corrosion degree in the target environmental risk parameters, the structural damage risk value is determined. The dust exposure risk value is determined based on the target fine particulate matter concentration and target dust diffusion rate in the target environmental risk parameters, and the construction environmental risk value is determined based on the chemical exposure risk value, structural damage risk value and dust exposure risk value.

6. The intelligent optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things as described in claim 1, characterized in that, Based on the reasoning process of the comprehensive risk parameters, the risk causes of the area to be adjusted are located to obtain the risk cause location results, including: Based on a preset feature extraction model, features are extracted from the reasoning process of the comprehensive risk parameters to locate the risk causes in the area to be adjusted, thereby obtaining the risk cause location results. The preset feature extraction model includes an embedding layer, a position encoding module, a rotation feature encoding module, a feature decoding module, a linear transformation layer, and a classification layer. The risk cause localization result is determined as follows: A first embedding vector is obtained by embedding the reasoning process of the comprehensive risk parameters based on the embedding layer; a first position vector is obtained by encoding the reasoning process of the comprehensive risk parameters based on the position encoding module; the first embedding vector and the first position vector are superimposed to obtain a first input vector; the first input vector is encoded based on the rotation feature encoding module to obtain a first encoding result; the first encoding result is decoded based on the feature decoding module to obtain a first encoding matrix; the first encoding matrix is ​​transformed based on the linear transformation layer to obtain a first logical matrix; and the first logical matrix is ​​mapped based on the classification layer to obtain the risk cause localization result.

7. The intelligent optimization method for the regeneration construction scheme of old industrial buildings based on the Internet of Things as described in claim 1, characterized in that, Hybrid expert models include gated network models and multiple expert neural network models; Among them, based on the hybrid expert model, content generation is performed on the contextual marker sequence and the overall contextual representation to obtain the target construction plan, including: Based on the contextual flag sequence, the first model weights of multiple expert neural network models are determined for the scheme generation task in the construction safety dimension and the second model weights for the scheme generation task in the construction efficiency dimension, according to the hybrid expert model. Based on the first model weight and the second model weight, the first target neural network model required for the scheme generation task in the construction safety dimension and the second target neural network model required for the scheme generation task in the construction efficiency dimension are determined from multiple expert neural network models. The context flag sequence and the overall context representation are input into the first target neural network model and the second target neural network model, respectively, to obtain the first prediction result in the construction safety dimension and the second prediction result in the construction efficiency dimension. Based on the first prediction result and the second prediction result, the target construction scheme is obtained.

8. A smart optimization device for the regeneration construction scheme of old industrial buildings based on the Internet of Things, characterized in that, include: The real-time construction data receiving module is used to receive the current real-time construction data corresponding to the target construction area sent by the data acquisition terminal. The current real-time construction data includes at least one of the following: machinery operating speed data, construction safety distance data, construction operation height data, voltage fluctuation range, grounding resistance, soil heavy metal concentration, volatile organic compound concentration, pipeline corrosion degree, fine particulate matter concentration, and dust diffusion rate. The current risk parameter determination module is used to determine the current conventional construction risk parameters and current environmental risk parameters of the target construction area based on the current real-time construction data. The target risk parameter determination module is used to adjust the current conventional construction risk parameters and the current environmental risk parameters according to a preset risk parameter weight matrix to obtain target conventional construction risk parameters and target environmental risk parameters. This includes: determining the current construction status identification result of the target construction area, and matching the current construction status identification result with a preset risk parameter weight matrix corresponding to the target construction area; determining the current weather data of the target construction area, and determining an environmental condition correction coefficient corresponding to the target construction area based on the current weather data; adjusting the current conventional construction risk parameters according to the preset risk parameter weight matrix to obtain target conventional construction risk parameters; and adjusting the current environmental risk parameters according to the environmental condition correction coefficient and the preset risk parameter weight matrix to obtain target environmental risk parameters. The construction plan dynamic adjustment module is used to determine comprehensive risk parameters based on target conventional construction risk parameters and target environmental risk parameters, and to dynamically adjust the current construction plan of the target construction area according to the comprehensive risk parameters to obtain the target construction plan. The target construction plan is obtained through the following methods: assigning a region identifier to the target construction area based on the comprehensive risk parameters, and determining the plan adjustment priority of the target construction area based on the region identifier; determining the area to be adjusted from the target construction area based on the plan adjustment priority, and locating the risk causes of the area to be adjusted based on the reasoning process of the comprehensive risk parameters to obtain the risk cause location result; obtaining the standard construction plan corresponding to the risk cause location result, and inputting the standard construction plan, the risk cause location result, and the current construction plan into a preset content generation model to obtain the target construction plan; the preset content generation model includes an embedded mapping layer, an encoding layer, and a hybrid expert model. The target construction plan is determined as follows: Basic information to be predicted is generated based on the standard construction plan, risk cause location results, and the current construction plan; context information to be predicted is generated based on preset parameter prompts; the basic information to be predicted is embedded and mapped using the embedding mapping layer to obtain features of the region to be adjusted; the context information to be predicted is then embedded and mapped using the embedding mapping layer to obtain a context flag sequence; the features of the region to be adjusted and the context flag sequence are encoded using the encoding layer to obtain an overall context representation; and the context flag sequence and the overall context representation are then generated using a hybrid expert model to obtain the target construction plan.

Images