Construction material management method, system and medium based on big data

Abstract

The present invention discloses a construction material management method, system and medium for construction projects based on big data. The method includes: when receiving a supervision request triggered by a preset supervision cycle corresponding to the construction materials, predicting the predicted usage of the next preset supervision cycle based on the usage and remaining amount of the construction materials in the preset supervision cycle, and the storage loss rate, and combining the engineering parameters of the construction project in the next preset supervision cycle; when receiving a retrieval application, determining the materials to be shipped from each storage material according to the material code carried therein for inspection; after analyzing that the materials to be shipped meet the preset shipping standards based on the inspection data, generating shipping information output based on the inspection data, the predicted usage and the material code. The present invention realizes precise management of construction materials for construction projects based on big data processing and analysis from multiple aspects, such as accurate prediction of usage in the preset monitoring cycle, inspection before shipping, and orderly management based on material codes.

Description

Technical Field

[0001] The present invention relates to the field of big data processing technology, and in particular to a construction material management method, system and medium based on big data. Background Art

[0002] Construction projects encompass a wide range of categories, including the construction, renovation, and expansion of roads, bridges, stations, railways, and various industrial and civil structures. Regardless of the type of construction project, a wide variety of materials are required, including various types of steel, wood, bamboo, stone, cement, concrete, bricks and tiles, ceramics, glass, engineering plastics, composite materials, as well as specialized materials for waterproofing, moisture-proofing, corrosion resistance, fireproofing, flame retardancy, sound insulation, heat insulation, thermal insulation, sealing, and various decorative materials.

[0003] Construction projects require a wide variety of materials in large quantities. Procuring all of them all at once would not only be costly, but would also require storage space and risk spoilage. Therefore, materials are typically procured according to the project's progress. However, even with this approach, precise management of these materials can be challenging. First, the quantity of materials purchased is crucial. Procuring too much can lead to the aforementioned issues, while purchasing too little can cause work stoppages due to material shortages, impacting the project schedule. Second, the timing of procurement: Procuring too early can also lead to inventory backlogs, while purchasing too late can also easily cause shortages. Finally, there's the issue of disorganized storage of various materials in warehouses, and the potential for these materials to deteriorate, potentially causing quality issues. Therefore, precise management of construction materials is a pressing technical challenge. Summary of the Invention

[0004] The main purpose of the present invention is to provide a construction material management method, system and medium for construction projects based on big data, aiming to solve the technical problem of how to accurately manage the construction materials of construction projects in the existing technology.

[0005] To achieve the above objectives, the present invention provides a construction material management method for construction projects based on big data, which sets preset supervision cycles for various types of construction materials in construction projects and stores the corresponding relationship between construction materials and preset supervision cycles in a preset database;

[0006] The construction material management method for a building project comprises:

[0007] Upon receiving a supervision request triggered by a preset supervision period corresponding to any construction material in a construction project, obtaining the usage and remaining quantity of the construction material in the preset supervision period, as well as the storage loss rate of the construction material in the warehouse corresponding to the construction project;

[0008] Predicting the usage of the construction materials in the next preset supervision period based on the usage, remaining amount, storage loss rate, and engineering parameters of the construction project in the next preset supervision period;

[0009] receiving a retrieval application initiated based on the predicted usage, and determining the material to be shipped from each of the stored materials according to the material code carried in the retrieval application and the material code corresponding to each of the stored materials in the warehouse in a preset database;

[0010] Randomly selecting materials to be inspected from the materials to be shipped based on a preset random algorithm, and analyzing whether the materials to be shipped meet preset shipping standards based on inspection data obtained from inspecting the materials to be inspected;

[0011] If the preset outbound standard is met, outbound information corresponding to the material to be outbound is generated based on the inspection data, the predicted usage and the material code, and the outbound information is output.

[0012] Preferably, the step of outputting the outbound information includes:

[0013] After receiving the information that the shipment is completed, the remaining storage quantity of the materials to be shipped in the warehouse is updated, and whether the conditions for generating a purchase order are met according to the updated remaining storage quantity is determined;

[0014] If the conditions for generating a procurement order are met, determining a construction mode for the construction project and generating a time weight and a cost weight corresponding to the construction mode;

[0015] Acquire supply data corresponding to the material to be shipped from a preset database, calculate a supply coefficient based on the supply data, the time weight, and the cost weight, and generate the purchase instruction based on the supply coefficient, wherein the calculation formula of the supply coefficient is:

[0016]

[0017] Among them, Xj represents the supply coefficient of the jth supplier, Wt and Wc represent the time weight and cost weight respectively. and t j They represent the maximum, minimum and average time required to purchase the materials to be shipped from supplier j contained in the supply data, and c j represents the maximum, minimum and average cost of the materials to be shipped from supplier j in the supply data, r represents the correction coefficient corresponding to the materials to be shipped in the construction project in the supply data, h j and ej They respectively represent the acceptance qualification rate and historical failure rate corresponding to the supplier j contained in the supply data and the materials to be shipped.

[0018] Preferably, the step of outputting the outbound information includes:

[0019] Acquire a warehouse image of the material to be shipped out of the warehouse, and recognize the warehouse image based on a preset recognition model to determine a frame area in the warehouse image;

[0020] Extracting a first image to be identified that is located within the frame area and a second image to be identified that is located outside the frame area;

[0021] Recognize the first image to be recognized and the second image to be recognized based on the preset recognition model, and determine whether there are first-category storage materials that do not meet the storage standards, and whether there are second-category storage materials that are placed beyond the boundary.

[0022] If the first category of storage materials and / or the second category of storage materials exist, a storage abnormality prompt message is output.

[0023] Preferably, the step of identifying the warehouse image based on a preset recognition model and determining a border area in the warehouse image includes:

[0024] Dividing the warehouse image into a plurality of grids based on a preset recognition model, and generating a plurality of bounding boxes corresponding to each of the grids;

[0025] For each of the bounding boxes, obtaining inner frame pixel values ​​and outer frame pixel values ​​adjacent to the bounding box, and determining a predicted box in the warehouse image based on a difference between the inner frame pixel values ​​and the outer frame pixel values;

[0026] The category of the items in the predicted frame is identified based on a preset recognition model to determine the frame area in the warehouse image.

[0027] Preferably, before the step of identifying the warehouse image based on a preset recognition model and determining the border area in the warehouse image, the step includes:

[0028] Obtaining preset image samples, and training a preset initial model based on the preset image samples;

[0029] When the preset initial model is trained for a preset number of times, the loss function value of the preset initial model is calculated based on the training result generated by the last training, and the calculation formula is:

[0030]

[0031] Among them, L represents the loss function value, N represents the number of preset image samples, and H k Indicates the center point height difference between the training prediction box generated by the k-th preset image sample in the training result and the real box corresponding to the k-th preset image sample, (x0 k ,y0 k ) represents the center coordinate value of the real frame, (x k ,y k ) represents the center coordinate value of the training prediction box, (w0 k , h0 k ) represents the width and height of the real frame, (w k , h k ) represents the width and height of the training prediction box, α represents the preset shape loss attention coefficient, Used to calculate the angle loss of the training prediction box, Function b is used to calculate the shape loss of the training prediction box, and f(·) is used to calculate the item category loss. k Indicates the item category result generated by the k-th preset image sample in the training result, b0 k Indicates the true category result corresponding to the k-th preset image sample;

[0032] Determine whether the loss function value is less than a preset function threshold, and if so, generate the preset initial model as a preset recognition model;

[0033] If the loss function value is greater than or equal to the preset function threshold, the step of training the preset initial model based on the preset image sample is executed until the loss function value is less than the preset function threshold.

[0034] Preferably, the step of predicting the predicted usage amount of the construction material in the next preset supervision period based on the usage amount, remaining amount, storage loss rate and the next project parameters of the construction project in the next preset supervision period includes:

[0035] Obtaining current project parameters and next project parameters of the construction project in a preset supervision period and a next preset supervision period, respectively, wherein the current project parameters and the next project parameters each include at least one of project process parameters, project geological parameters, and project personnel parameters;

[0036] generating a similarity value between the current engineering parameter and the next engineering parameter, and determining whether the similarity value is greater than a preset similarity threshold; if so, predicting the next usage in the next preset period based on the current engineering parameter, the usage, and the next engineering parameter;

[0037] A preset reserve ratio of the construction material is obtained, and the next usage is updated according to the preset reserve ratio, the remaining amount, and the storage loss rate to obtain the predicted usage.

[0038] Preferably, the step of randomly selecting materials to be inspected from the materials to be shipped out based on a preset random algorithm, and analyzing whether the materials to be shipped out meet preset shipping standards based on inspection data obtained from inspecting the materials to be inspected includes:

[0039] Searching a preset database for the most recent historical inspection data of the material to be shipped, and determining a generation date of the historical inspection data;

[0040] Generate the generation date as an inspection interval, and determine whether the inspection interval exceeds a preset inspection period. If it exceeds the preset inspection period, generate a random code based on a preset random algorithm, and screen the materials to be inspected from the materials to be shipped out according to the random code;

[0041] Acquiring inspection data generated by inspecting the materials to be inspected, and analyzing whether the materials to be shipped meet preset shipping standards based on the inspection data;

[0042] If the inspection time does not exceed the preset time, the historical inspection data is used as inspection data to analyze whether the materials to be shipped meet the preset shipping standards.

[0043] Preferably, upon receiving a supervision request triggered by a preset supervision period corresponding to any construction material in the construction project, before obtaining the usage amount and remaining amount of the construction material, and the storage loss rate of the construction material in the warehouse corresponding to the construction project, the step includes:

[0044] Obtaining the design quantity and design cost of the construction materials at each construction stage of the construction project, as well as storage price information and transportation price information corresponding to the construction materials;

[0045] For each construction stage, a cost cycle function is constructed based on the construction design quantity, quantity design cost, and the storage price information and transportation price information of the construction stage, and the preset supervision period is determined based on the cost cycle function. The cost cycle function is:

[0046]

[0047] Among them, U represents the usage design cost, U1 represents the fixed storage cost in the storage price information, T represents the number of supervisions corresponding to the construction stage, K1 represents the time coefficient corresponding to the fixed storage cost, Q represents the construction design usage, U2 represents the unit storage cost in the storage price information, K2 represents the time coefficient corresponding to the unit storage cost, U3 represents the fixed transportation cost in the transportation price information, K3 represents the time coefficient corresponding to the fixed transportation cost, U4 represents the unit transportation cost in the transportation price information, and K4 represents the time coefficient corresponding to the unit transportation cost.

[0048] Furthermore, to achieve the above-mentioned object, the present invention also provides a construction material management system based on big data, the construction material management system based on big data comprising a storage, a processor, a communication bus, and a control program stored on the storage:

[0049] The communication bus is used to realize the connection and communication between the processor and the storage;

[0050] The processor is used to execute the control program to implement the steps of the construction material management method based on big data as described above.

[0051] Furthermore, to achieve the above-mentioned purpose, the present invention also provides a medium, which is a readable storage medium, and a control program is stored on the readable storage medium. When the control program is executed by the processor, the steps of the construction material management method based on big data as described above are implemented.

[0052] The present invention is based on a method, system and medium for managing construction materials for construction projects based on big data. Preset supervision cycles are set for various types of construction materials required for construction projects. If a supervision request is received based on the preset supervision cycle corresponding to any construction material, it indicates that the supervision time for this type of construction material has arrived, thereby obtaining the usage and remaining amount of this type of construction material in the preset supervision cycle, as well as the storage loss rate of the construction material in the warehouse corresponding to the construction project; and then, based on the obtained usage, remaining amount, storage loss rate and engineering parameters of the construction project in the next preset supervision cycle, predicting the construction material in the next preset supervision cycle. The system predicts usage during the supervision cycle. After receiving a retrieval request based on the predicted usage, the system determines the materials to be shipped from the storage materials based on the material code carried in the retrieval request and the material code corresponding to each storage material in the preset database. The system then randomly extracts materials to be inspected from the materials to be shipped using a preset random algorithm, obtains inspection data, and uses it to analyze whether the materials to be shipped meet the preset shipping standards. If the preset shipping standards are met, the system generates and outputs shipping information corresponding to the materials to be shipped based on the inspection data, predicted usage, and material code, so that the materials to be shipped can be shipped based on the shipping information. In this way, by setting a corresponding preset supervision cycle for each construction material based on its own characteristics, if a construction material reaches its preset supervision cycle, the system predicts its usage in the next cycle based on its usage and remaining amount in the current preset supervision cycle, as well as its storage loss rate, thereby ensuring the accuracy of the predicted usage. This ensures that the construction materials shipped based on the predicted usage during the preset supervision cycle are accurate in both quantity and time. Furthermore, before shipment, a random sample of construction materials is inspected, and only shipped after passing inspection. This ensures that the shipped materials have not undergone any quality changes, which in turn contributes to the quality and safety of the construction project. Furthermore, each material stored in the warehouse is assigned a corresponding material code, which facilitates the orderly management of each stored material. This enables precise management of construction materials for construction projects based on big data in many ways. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a flow chart of a first embodiment of a method for managing construction materials for a building project based on big data according to the present invention;

[0054] Figure 2 This is a flow chart of a second embodiment of the construction material management method for construction projects based on big data of the present invention;

[0055] Figure 3 This is a flow chart of a third embodiment of the construction material management method for construction projects based on big data of the present invention;

[0056] Figure 4This is a flow chart of a fourth embodiment of the construction material management method for construction projects based on big data of the present invention;

[0057] Figure 5 This is a structural diagram of the hardware operating environment involved in an embodiment of the construction material management system for construction projects based on big data of the present invention.

[0058] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0059] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0060] The present invention provides a construction material management method for construction projects based on big data, which sets preset supervision cycles for various types of construction materials in construction projects and stores the corresponding relationship between construction materials and preset supervision cycles in a preset database. Figure 1 , Figure 1 This is a flow chart of the first embodiment of the construction material management method for construction projects based on big data of the present invention.

[0061] The present invention provides an embodiment of a method for managing construction materials based on big data. It should be noted that although a logical sequence is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order. Specifically, the method for managing construction materials based on big data in this embodiment includes:

[0062] Step S10, when receiving a supervision request triggered by a preset supervision period corresponding to any construction material in the construction project, obtain the usage and remaining amount of the construction material in the preset supervision period, and the storage loss rate of the construction material in the warehouse corresponding to the construction project.

[0063] In this embodiment, the big data-based construction material management method for construction projects is applied to a server. The server is in communication with a preset database, which stores various types of data related to multiple construction projects in a coded manner, including but not limited to project design data, project cost data, construction material data, and construction phase data. Each construction project is assigned a unique code, and all data associated with each construction project carries this code to distinguish it from data associated with other construction projects. Furthermore, the various types of construction materials required for a construction project are typically purchased based on the construction phase, and the types and quantities of materials required vary across different construction phases. Based on this, preset supervision periods are pre-set for each type of construction material. For example, a preset supervision period of 60 days is set for construction material A, while a preset supervision period of 30 days is set for another type of construction material B. The corresponding relationship between each type of construction material and its respective preset supervision period is stored in the preset database, allowing the server to supervise each type of construction material according to each preset supervision period.

[0064] Specifically, the database's monitoring thread monitors the preset monitoring cycles for various types of construction materials to determine whether any of them have reached their preset monitoring cycle. If any of these materials have reached their preset monitoring cycle, it indicates that these materials currently require monitoring, and thus triggers a monitoring request to the server. Upon receiving this monitoring request, the server retrieves the usage and remaining quantity of the construction materials during the preset monitoring cycle. For each type of construction material, a predicted usage quantity for the next preset monitoring cycle is generated during each preset monitoring cycle. For example, for construction material A with a preset monitoring cycle of 60 days, the initial usage quantity is set based on the design documents. After reaching the first preset monitoring cycle of 60 days, a usage quantity is predicted for the second preset monitoring cycle. Furthermore, after reaching 60 days after the second preset monitoring cycle, a usage quantity is predicted for the third preset monitoring cycle. Therefore, the usage quantity for a preset monitoring cycle represents the actual amount of the construction material used during the current preset monitoring cycle, while the remaining quantity represents the amount of the construction material remaining after the predicted usage quantity for the previous preset monitoring cycle has been actually used during the current preset monitoring cycle.

[0065] Furthermore, construction materials are usually stored in warehouses. The storage conditions such as humidity and temperature in the warehouses may cause the performance of some construction materials to change, making them unsuitable for the construction of construction projects. Construction materials with changed performance are regarded as loss materials, and the number of loss materials in the historical preset supervision period is counted, and then a loss rate is generated as the storage loss rate of construction materials in the warehouse corresponding to the construction project and stored in the preset database. This storage loss rate reflects the number of materials that cannot be used for construction due to quality changes, and should be excluded from the usage forecast for the next preset monitoring period. It should be noted that not all types of construction materials will undergo performance changes during storage in the warehouse, or no performance changes have been found in the early stages of construction. Therefore, for construction materials that trigger a supervision request, the database is checked to see if there is a corresponding storage loss rate. If so, the storage loss rate is obtained. If not, an empirical value is obtained as the storage loss rate.

[0066] Step S20 , predicting the predicted usage of the construction material in the next preset supervision cycle based on the usage, remaining amount, storage loss rate and engineering parameters of the construction project in the next preset supervision cycle.

[0067] Furthermore, the amount of construction materials used is closely related to the progress of the construction project. The progress of the project includes construction technology and construction efficiency. Different construction technologies have different requirements for the type and quantity of construction materials. The construction efficiency will affect the demand for construction materials. The higher the construction efficiency, the greater the demand for construction materials, and vice versa. Therefore, the usage, remaining and storage loss rate of the obtained construction materials can be combined with the engineering parameters of the construction project in the next preset supervision cycle to predict the preset usage of the construction materials in the next preset supervision cycle. Specifically, the step of predicting the predicted usage of the construction materials in the next preset supervision cycle based on the usage, remaining, storage loss rate and the next engineering parameters of the construction project in the next preset supervision cycle includes:

[0068] Step S21, obtaining current project parameters and next project parameters of the construction project in a preset supervision period and a next preset supervision period, respectively, wherein the current project parameters and the next project parameters each include at least one of engineering process parameters, engineering geological parameters, and engineering personnel parameters;

[0069] Step S22: Generate a similarity value between the current project parameter and the next project parameter, and determine whether the similarity value is greater than a preset similarity threshold. If so, predict the next usage in the next preset period based on the current project parameter, the usage, and the next project parameter.

[0070] Step S23: obtaining a preset reserve ratio of the construction material, and updating the next usage amount according to the preset reserve ratio, the remaining amount, and the storage loss rate to obtain the predicted usage amount.

[0071] Furthermore, the current engineering parameters of the construction project in the preset supervision cycle and the next engineering parameters in the next preset supervision cycle are obtained. The current engineering parameters and the next engineering parameters contain the same parameter type, but belong to different engineering cycles, and include at least one of the following: engineering process parameters, engineering geological parameters, and engineering personnel parameters. Among them, the engineering process parameters reflect the difference in process between the current and next preset supervision cycles, the engineering geological parameters reflect the difference in geological soil layers between the current and next preset supervision cycles, and the engineering personnel parameters reflect the difference in construction personnel between the current and next preset supervision cycles.

[0072] Furthermore, the current project parameters and the next project parameters reflect the difference in construction material usage between the current and next preset monitoring cycles. Generally speaking, if the process and geological soil layer differences are not significant, the usage differences are also not significant. Therefore, a similarity value can be generated between the current project parameters and the next project parameters. Specifically, sub-similarity values ​​can be generated for the engineering process parameters, sub-similarity values ​​for the engineering geological parameters, and sub-similarity values ​​for the engineering personnel parameters. Each sub-similarity value is then averaged to obtain the similarity value between the current and next project parameters. Furthermore, to reflect the degree of similarity between the two, a preset similarity threshold is pre-set. The generated similarity value is compared with the preset similarity threshold to determine whether the similarity value exceeds the preset similarity threshold. If it exceeds the preset similarity threshold, it indicates a high degree of similarity between the current and next project parameters. Therefore, based on the current project parameters and usage during the preset monitoring cycle, combined with the next project parameters during the next preset monitoring cycle, the required construction material usage during the next preset monitoring cycle can be predicted, and the predicted usage can be used as the next usage.

[0073] Conversely, if the comparison determines that the similarity value is less than or equal to the preset similarity threshold, it indicates that the similarity between the current project parameters and the next project parameters is not high, and the usage in the current preset supervision cycle cannot be used to accurately predict the usage in the next preset supervision cycle. In this case, the similarity values ​​between the historical project parameters of other historical preset supervision cycles and the next project parameters can be used to find historical project parameters with high similarity. Then, based on the historical usage of construction materials in the historical preset supervision cycles corresponding to these historical project parameters, the next usage for the next preset project can be predicted.

[0074] It should be noted that, whether the next usage is predicted by the current preset monitoring cycle or the historical preset monitoring cycle, it is necessary to correct and update it through the remaining amount and the storage loss rate to obtain an accurate predicted usage. Among them, the remaining amount is the amount of construction materials that can be used in the next preset monitoring cycle during the current preset monitoring cycle, and the storage loss rate is the loss ratio of construction materials due to warehouse storage. Therefore, the correction method for the next usage by both can be to first perform a difference operation between the next usage and the remaining amount to obtain a difference operation result, and then multiply the difference operation result by the storage loss rate to obtain a product operation result, and then add the product operation result and the difference operation result to obtain a correction result for the next usage by both.

[0075] In addition, considering that construction materials will be lost during daily use, and the loss amount of different types of construction materials is different. Based on past experience, a reserve ratio is set in advance for each type of construction material to make up for the loss amount. For the construction materials that trigger the supervision request, the corresponding preset reserve ratio is obtained, and the preset reserve ratio is multiplied by the above-mentioned correction result to obtain the reserve amount of the construction material, and then the reserve amount is added to the correction result to obtain the predicted usage amount required for the construction material in the next preset period. Because the predicted usage is not only obtained by combining the similarity between the engineering parameters of the construction project in the current and next preset supervision cycles, but also corrected and updated by storing losses, usage losses and remaining amounts, the predicted usage is more accurate.

[0076] Step S30, receiving a retrieval application initiated based on the predicted usage, and determining the materials to be shipped from each storage material according to the material code carried in the retrieval application and the material code corresponding to each storage material in the warehouse in the preset database.

[0077] Furthermore, after predicting the usage of construction materials in the next preset supervision cycle, a retrieval application can be initiated based on the predicted usage to apply for the construction materials. The retrieval application can be initiated automatically by the server, or it can be initiated after the predicted usage is output for review by relevant management personnel of the construction project. In addition, in order to facilitate the management of various types of construction materials in the warehouse, the warehouse is divided into multiple areas, one area corresponding to a type of construction material, which is used to store this type of construction material. At the same time, a material code representing each type of construction material is pre-set to indicate its uniqueness. The material information such as the model and quantity of each type of construction material, the regional location in the warehouse, and the material code are stored in the form of data pairs in a preset database. The retrieval application contains a material code indicating the category of the construction material. After receiving the retrieval application, the server identifies the material code carried therein and compares it with the material code corresponding to each storage material stored in the warehouse in the preset database, and searches for the target material code among the material codes that matches the material code carried by the retrieval application. Among them, the various storage materials in the warehouse are various types of construction materials, and the material codes corresponding to the various storage materials in the preset database are the material codes corresponding to the various types of construction materials.

[0078] Furthermore, after comparing and determining the target material code that matches the material code carried in the retrieval application, the construction materials corresponding to the target material code and the regional location of the construction materials in the warehouse are searched as the materials to be shipped out from the various storage materials stored in the warehouse.

[0079] Step S40: randomly selecting materials to be inspected from the materials to be shipped out based on a preset random algorithm, and analyzing whether the materials to be shipped out meet preset shipping standards based on inspection data obtained from inspecting the materials to be inspected.

[0080] Furthermore, to ensure the performance of the materials to be shipped in the construction project, they must be inspected before they are shipped. Specifically, a preset random algorithm is pre-set for generating random codes. After the random codes are generated by the preset random algorithm, the materials to be inspected are screened from the materials to be shipped based on the random codes. Relevant inspectors then extract such materials to be inspected from the materials to be shipped stored in the warehouse for inspection, generating inspection data to determine whether the materials to be shipped meet the preset shipping standards. The preset shipping standards are the standards by which the materials to be shipped can be released after passing the inspection. If the inspection results of the inspection data are qualified, it is determined that the preset shipping standards are met; otherwise, it is determined that the preset shipping standards are not met.

[0081] It should be noted that the materials to be shipped stored in the warehouse may have been inspected recently, and re-inspection is not necessary. In this case, the inspection data of the recent inspection can be used to determine whether the materials to be shipped meet the preset shipping standards. Therefore, the steps of randomly selecting materials to be inspected from the materials to be shipped based on a preset random algorithm and analyzing whether the materials to be shipped meet the preset shipping standards based on the inspection data obtained from the inspection of the materials to be shipped include:

[0082] Step S41, searching a preset database for the most recent historical inspection data of the material to be shipped, and determining a generation date of the historical inspection data;

[0083] Step S42: Generate the generated date as an inspection interval, and determine whether the inspection interval exceeds a preset inspection period. If it exceeds the preset inspection period, generate a random code based on a preset random algorithm, and select the materials to be inspected from the materials to be shipped out according to the random code;

[0084] Step S43, obtaining inspection data generated by inspecting the materials to be inspected, and analyzing whether the materials to be shipped meet preset shipping standards based on the inspection data;

[0085] Step S44: If the inspection time does not exceed the preset time, the historical inspection data is used as inspection data to analyze whether the materials to be shipped meet the preset shipping standards.

[0086] Furthermore, the inspection data generated during each release inspection of stored materials in the warehouse is stored in a preset database. The inspection data can be arranged in an array in the preset database in chronological order of inspection time. The server can search the preset database for the array corresponding to the materials to be released and find the data ranked first in the array; this data is the most recent historical inspection data for the materials to be released. The server then identifies the date on which this historical inspection data was generated and determines the time interval between this date and the current time as the inspection interval. By comparing the inspection interval with a preset inspection period, it is determined whether the inspection interval exceeds the preset inspection period. The preset inspection period is a pre-set maximum inspection interval supported by the materials to be released. If the inspection interval generated by the inspection time and the current time exceeds the preset inspection period, it indicates that the most recent inspection time for the materials to be released was too long, and the materials to be released may have undergone quality changes during the inspection interval, necessitating re-inspection of the materials to be released.

[0087] Specifically, the area divided in the warehouse can be subdivided into multiple sub-areas, for example, 12 sub-areas of 3*4, 16 sub-areas of 4*4, etc., and the sub-areas can extend in the vertical direction, for example, 48 sub-areas of 3*4*4, and each area is provided with a corresponding area code, for example, a code from 1 to 12. After the preset random algorithm generates a random code, the random code is used as the area code to screen out the materials to be inspected from the materials to be shipped out. The materials to be inspected are materials for inspection among the materials to be shipped out stored in the warehouse, and the generated random code is used as the area code, and the materials stored in the area code are the materials to be inspected. In this way, the random code generated by the preset random algorithm can realize the random sampling of materials to be inspected from the materials to be shipped out for inspection, so that the inspection of the materials to be shipped out is more accurate, ensuring the performance of the materials to be shipped out, and thus benefiting the quality and safety of the entire construction project.

[0088] The server then outputs the code for the material to be inspected. Relevant personnel retrieve the material to be inspected corresponding to the inspection code and perform inspections on it according to various pre-defined inspection methods. This generated inspection data is then transmitted to the server. The inspection data includes the inspection results corresponding to each of the various inspection methods. Upon receiving this inspection data, the server analyzes the inspection results to determine whether the material to be shipped meets the pre-defined standards for shipping. If all inspection results in the inspection data are qualified, the pre-defined standards for shipping are determined to be met. Otherwise, if any inspection result fails, the pre-defined standards for shipping are determined to be unsatisfactory.

[0089] Furthermore, if the comparison determines that the inspection interval does not exceed the preset inspection period, the likelihood of quality change in the materials to be shipped is low. Based on the most recent historical inspection data, the materials to be shipped can be analyzed to determine whether they meet the preset shipping standards. Furthermore, analysis can be performed directly by obtaining the most recent determination of whether the materials to be shipped meet the preset shipping standards, simplifying the analysis process and improving efficiency.

[0090] Step S50: If the preset outbound standard is met, outbound information corresponding to the material to be outbound is generated based on the inspection data, the predicted usage and the material code, and the outbound information is output.

[0091] Furthermore, if analysis determines that the materials to be shipped meet the shipping standards, the inspection data, predicted usage and material code will be generated together as shipping information corresponding to the materials to be shipped, and the shipping information will be output to facilitate relevant personnel to process the materials to be shipped according to the shipping information, and complete the precise management of construction materials in construction projects from usage prediction, to shipping retrieval application, to inspection and shipping.

[0092] The construction material management method for construction projects based on big data implemented in this invention sets corresponding preset supervision cycles for various types of construction materials needed for construction projects in advance. If a supervision request triggered by the preset supervision cycle corresponding to any construction material is received, it means that the supervision time of this type of construction material has arrived, thereby obtaining the usage and remaining quantity of this type of construction material in the preset supervision cycle, as well as the storage loss rate of the construction material in the warehouse corresponding to the construction project; and then predicting the construction material in the next preset supervision cycle based on the obtained usage, remaining quantity, storage loss rate and engineering parameters of the construction project in the next preset supervision cycle. The system predicts the usage of the period; after receiving a retrieval application based on the predicted usage, the system determines the materials to be shipped from the storage materials based on the material code carried in the retrieval application and the material code corresponding to each storage material in the preset database; then, a preset random algorithm is used to randomly extract materials to be inspected from the materials to be shipped for inspection, and the inspection data is obtained to analyze whether the materials to be shipped meet the preset shipping standards; if the preset shipping standards are met, the system generates and outputs shipping information corresponding to the materials to be shipped based on the inspection data, the predicted usage, and the material code, so that the materials to be shipped can be shipped according to the shipping information. In this way, by setting a corresponding preset supervision period for each construction material according to its own characteristics, if a construction material reaches its preset supervision period, the system predicts the usage of the next period based on its usage and remaining amount in the current preset supervision period, as well as its storage loss rate, to ensure the accuracy of the predicted usage, so that the construction materials shipped according to the predicted usage in the preset supervision period are accurate in quantity and time. Furthermore, before shipment, a random sample of construction materials is inspected, and only shipped after passing inspection. This ensures that the shipped materials have not undergone any quality changes, which in turn contributes to the quality and safety of the construction project. Furthermore, each material stored in the warehouse is assigned a corresponding material code, which facilitates the orderly management of each stored material. This enables precise management of construction materials for construction projects based on big data in many ways.

[0093] For further information, please refer to Figure 2 Based on the first embodiment of the construction material management method for construction projects based on big data of the present invention, a second embodiment of the construction material management method for construction projects based on big data of the present invention is proposed.

[0094] The second embodiment of the construction material management method based on big data differs from the first embodiment of the construction material management method based on big data in that, after the step of outputting the outbound information, the following steps are included:

[0095] Step S60: after receiving the information that the shipment is completed, updating the remaining storage quantity of the materials to be shipped in the warehouse, and determining whether the conditions for generating a purchase order are met based on the updated remaining storage quantity;

[0096] Step S70: If the conditions for generating a procurement order are met, the construction mode of the construction project is determined, and a time weight and a cost weight corresponding to the construction mode are generated;

[0097] Step S80: Obtain supply data corresponding to the materials to be shipped from a preset database, calculate a supply coefficient according to the supply data, the time weight, and the cost weight, and generate the purchase instruction based on the supply coefficient.

[0098] Understandably, the storage volume of various materials in the warehouse decreases with each shipment. To avoid impacting subsequent construction projects, the remaining storage volume must be updated after each shipment, and purchases must be made when the storage volume falls below a certain threshold. Specifically, after the relevant personnel have shipped the materials to be shipped, they upload a completion message to the server and add the shipment volume (i.e., the predicted usage) to this message. Upon receiving this message, the server updates the remaining volume of the materials to be shipped in the warehouse based on the predicted usage. The updated remaining volume is then compared with a preset remaining threshold to determine whether it is less than the preset remaining threshold. This preset remaining threshold indicates that the storage volume of the materials to be shipped is low, potentially impacting the construction progress of the next preset monitoring period. A purchase order instructs the purchase of the materials to be shipped. The comparison between the remaining volume and the preset remaining threshold determines whether the conditions for generating a purchase order have been met.

[0099] Furthermore, if the updated remaining quantity is determined to be greater than or equal to a preset remaining threshold, the inventory of materials to be shipped is relatively large and procurement is not currently required, thus not meeting the conditions for generating a purchase order. Conversely, if the updated remaining quantity is determined to be less than the preset remaining threshold, the inventory of materials to be shipped is relatively small, potentially impacting construction supervision during the next preset supervision period and necessitating procurement. However, considering that subsequent construction processes may require less materials to be shipped, the updated remaining quantity may still meet this demand. Therefore, the determination of whether the conditions for generating a purchase order are met is based on the demand for the materials to be shipped in subsequent processes. Specifically, a preset database stores construction processes for each stage of a construction project, as well as the types and quantities of construction materials required in each process. The server retrieves construction processes after the current preset supervision period, along with the types and quantities of construction materials for each construction process, and checks whether any of the construction materials include the materials to be shipped. If so, it calculates the usage. The server then compares the calculated usage with the updated remaining quantity to determine whether it is less than the updated remaining quantity. If the remaining quantity is less than the updated remaining quantity, there is no need to purchase the materials to be shipped, and the conditions for generating a purchase order are not met. If the remaining quantity is greater than or equal to the updated remaining quantity, the materials to be shipped need to be purchased, and the conditions for generating a purchase order are met.

[0100] Furthermore, if the conditions for generating a procurement order are met, the construction mode of the construction project is determined. Construction modes include normal mode, rush mode, and savings mode. Normal mode indicates that the construction project is constructed according to the normal design plan, rush mode indicates that the construction project needs to be accelerated, and savings mode indicates that the construction project needs to be constructed cost-effectively. Different construction modes have different requirements for time and cost. The normal mode balances time and cost, the rush mode focuses on time, and the savings mode focuses on cost. Therefore, to reflect the time and cost requirements of different construction modes, time weights and cost weights corresponding to the construction mode are generated. Specifically, different time weight and cost weight values ​​can be pre-set based on the degree of balance between time and cost. After determining the construction mode of the construction project, the corresponding time weight and cost weight values ​​are read based on the degree of balance between time and cost in the construction mode, as the time weight and cost weight corresponding to the construction mode.

[0101] Understandably, to ensure the timely supply of construction materials for a construction project, multiple suppliers are typically selected, and the supply data for each supplier's available construction materials is stored in a pre-set database. For materials to be shipped, the corresponding supply data is retrieved from the pre-set database and combined with the time and cost weights to calculate the supply coefficient. The specific calculation formula can be found in Equation (1) below.

[0102]

[0103] Among them, Xj represents the supply coefficient of the jth supplier, Wt and Wc represent the time weight and cost weight respectively. and t j The maximum, minimum, and average values ​​of the time required to procure the materials to be shipped from supplier j, as contained in the supply data, are respectively. The maximum and minimum values ​​are the longest and shortest supply times promised by supplier j, and the average value is the average time generated based on the time supplier j has previously supplied the materials to be shipped. and c j represents the maximum, minimum, and average costs of purchasing the materials to be shipped from supplier j as contained in the supply data; the maximum and minimum values ​​are the highest and lowest prices that supplier j promises to supply, and are both related to the supply time. The shorter the supply time, the higher the price, and vice versa. The average value is the average price generated based on the prices of the materials to be shipped supplied by supplier j in the past; r represents the correction coefficient corresponding to the materials to be shipped in the construction project contained in the supply data, which is used to reflect the urgency of the actual demand for the materials to be shipped in the construction project in other preset supervision cycles; h j and e j Respectively representing the acceptance rate and historical failure rate for supplier j and the materials to be shipped, as included in the supply data, they reflect the acceptance rate and actual failure rate of the materials to be shipped supplied by supplier j, reflecting the quality of the materials to be shipped. Thus, the calculated supply coefficient uses time and cost weights to represent the time and cost emphasis of different suppliers in supplying materials to be shipped. Combined with the correction coefficient, the acceptance rate and historical failure rate are corrected, ensuring that the supply coefficient accurately reflects this emphasis while also reflecting the quality of the materials to be shipped supplied by different suppliers.

[0104] Furthermore, after calculating and obtaining the supply coefficients for each supplier, the supply coefficients are compared to determine the one with the highest value. This highest supply coefficient indicates that the materials to be shipped supplied by the supplier are most compatible with the construction model of the construction project. The supplier generating this supply coefficient is then searched for, and the supplier's relevant information is generated as a purchase order to purchase the products to be shipped from this supplier.

[0105] After the materials to be shipped are shipped, this embodiment determines whether to generate a purchase order based on the remaining storage volume in the warehouse and the demand for the materials to be shipped in subsequent construction processes. This ensures more accurate procurement of the materials to be shipped. Furthermore, after generating the purchase order for the materials to be shipped, the system calculates each supplier's supply coefficient based on the time and cost priorities of the materials to be shipped, as reflected in the construction project's construction model, and combines the supply data of each supplier. A purchase order is then generated based on the maximum value of each supply coefficient. Because the supply coefficient represents the time and cost priorities of different suppliers supplying the materials to be shipped through time and cost weights, and combined with correction coefficients, acceptance rates, and historical failure rates, the supply coefficient accurately reflects these priorities while also taking into account the quality of the materials to be shipped supplied by different suppliers. This ensures that the purchase order generated based on the supply coefficient matches the construction project's construction model to the greatest extent possible, achieving accurate procurement of materials to be shipped while meeting the construction model.

[0106] For further information, please refer to Figure 3 Based on the first and second embodiments of the construction material management method based on big data of the present invention, a third embodiment of the construction material management method based on big data of the present invention is proposed.

[0107] The third embodiment of the construction material management method based on big data is different from the first and second embodiments of the construction material management method based on big data in that, after the step of outputting the outbound information, the following steps are included:

[0108] Step S90, obtaining a warehouse image of the materials to be shipped out of the warehouse, and recognizing the warehouse image based on a preset recognition model to determine a frame area in the warehouse image;

[0109] It is understandable that after the relevant personnel have shipped out the materials to be shipped, there may be materials that are not stored in a standardized manner among the various types of storage materials stored in the warehouse. For example, due to temporary displacement, the storage materials are not placed in the set location area, or the storage materials are placed in a messy manner and there may be a risk of scattering. In order to avoid the occurrence of such situations, this embodiment obtains warehouse images after the materials to be shipped are shipped out of the warehouse. At the same time, a preset recognition model for image recognition is pre-trained, and the obtained warehouse image is recognized by the preset recognition model to determine the border area in the warehouse image, so as to determine whether there are storage materials placed outside the border area, and storage materials that are within the border area but placed in a messy manner based on the recognized border area. Among them, the steps of recognizing the warehouse image based on the preset recognition model and determining the border area in the warehouse image include:

[0110] Step S91: dividing the warehouse image into a plurality of grids based on a preset recognition model, and generating a plurality of bounding boxes corresponding to each of the grids;

[0111] Step S92: for each of the bounding boxes, obtaining inner frame pixel values ​​and outer frame pixel values ​​adjacent to the bounding box, and determining a predicted box in the warehouse image based on the difference between the inner frame pixel values ​​and the outer frame pixel values;

[0112] Step S93: Identify the category of items in the predicted frame based on a preset recognition model, and determine the frame area in the warehouse image.

[0113] Specifically, a preset recognition model is used to divide the warehouse image into multiple grids, where one pixel corresponds to one grid. Multiple bounding boxes are then generated for each grid. Each grid is used as the center, and the grids are expanded outward in ascending order to generate multiple bounding boxes corresponding to the grids. For example, the first bounding box is a box surrounded by 3*3 pixels around the grid, the second bounding box is a box surrounded by 5*5 pixels extending outward from the 3*3 pixels and adjacent to the 3*3 pixels, and the third bounding box is a box surrounded by 7*7 pixels extending outward from the 5*5 pixels and adjacent to the 5*5 pixels, etc.

[0114] Furthermore, after forming multiple bounding boxes corresponding to each grid, the accuracy of the boundaries defined by the bounding boxes is determined. Accuracy includes two aspects: whether the bounding box contains the imaged object, and whether the imaged object is completely contained within the bounding box. Therefore, accuracy can be determined based on the change in pixel values ​​inside and outside the bounding box. For each bounding box, the inner and outer frame pixel values ​​are obtained, starting from the smallest bounding box and ending with the largest. For example, for a 5x5 bounding box, the inner frame pixel values ​​are the values ​​of the 3x3 pixels within the bounding box, while the outer frame pixel values ​​are the values ​​of the 7x7 pixels outside the bounding box. The inner and outer frame pixel values ​​are then compared to determine the difference between them. Based on this difference, the bounding box with the most accurate boundary is determined from each bounding box. A larger difference indicates a greater difference in pixel change between the inner and outer bounding boxes, indicating that the inner and outer bounding boxes are not the same object, and the bounding box's boundaries are accurate. Conversely, a smaller difference indicates that the same object is imaged within the bounding boxes, and the bounding box's boundaries are inaccurate. Furthermore, a bounding box with accurate boundary division is determined as a prediction box in the warehouse image to indicate that the imaging of the object within the box needs to be predicted.

[0115] It should be noted that the border area in the warehouse image is usually a regular shape, so its imaging is also usually a regular shape, so that the pixels outside the surrounding area are greatly different from itself. Therefore, the difference between the inner frame pixel value and the outer frame pixel value can be expressed by the size relationship of the pixel values ​​of the corresponding pixels. The inner frame pixel value is the pixel value of each pixel in the inner frame, and the outer frame pixel value is the pixel value of each pixel in the outer frame. Based on each pixel in the inner frame, according to the correspondence between each pixel in the inner frame and each pixel in the outer frame, the size relationship between the pixel values ​​of each pixel in the inner frame and the pixel values ​​of each pixel in the outer frame is determined one by one. For example, for the above-mentioned 3*3 inner frame pixel value and 7*7 outer frame pixel value, in essence, it is the pixel value of the pixels included in the four edges of the top, bottom, left and right. The upper 3 pixel values ​​included in the inner frame pixel value correspond to the upper 3-5 pixel values ​​included in the outer frame pixel value. The same is true for the bottom and left and right edges. Therefore, during the comparison, the first, second, and third pixel values ​​at the top, bottom, left, and right of the inner frame pixel values ​​are compared with the third, fourth, and fifth pixel values ​​at the top, bottom, left, and right of the outer frame pixel values, respectively, to determine the size relationship between them. The size relationship is then used to determine the difference between the inner and outer frame pixel values. Specifically, a preset threshold can be set. If the pixel value of the inner frame pixel point is greater than the pixel value of its corresponding outer frame pixel point by more than the preset threshold, it indicates that the pixel value difference between the inner and outer frames is significant, and the overall difference between the inner and outer frame pixel values ​​is large, and the bounding box is determined as the predicted box.

[0116] In addition, a mean value comparison method can be configured. This involves performing a mean calculation between the inner frame pixel values ​​to obtain the inner frame pixel mean, and performing a mean calculation between the outer frame pixel values ​​to obtain the outer frame pixel mean. A difference calculation is then performed between the inner and outer frame pixel mean values ​​to obtain a difference calculation result representing the difference between the inner and outer frame pixel values. This difference calculation result is then compared with a preset threshold to determine whether it exceeds the preset threshold. If so, this indicates a significant difference between the inner and outer pixel values, indicating that the inner and outer pixel values ​​belong to different objects, and the bounding box can be accurately demarcated. Therefore, the bounding box is determined as the predicted box. Conversely, if the comparison determines that the difference value is not greater than the preset threshold, this indicates that the difference between adjacent inner and outer pixels is not significant, indicating that the pixels belong to the same object, and the bounding box cannot be accurately demarcated. In this case, the next larger bounding box adjacent to the bounding box is selected, and the difference value between its inner and outer adjacent pixels is obtained for further evaluation. This process continues until all bounding boxes generated by each grid have been compared and determined.

[0117] Furthermore, after all bounding boxes generated by each grid are compared, multiple prediction boxes can be screened out, and there are prediction boxes with high overlap among the multiple prediction boxes. For such prediction boxes with high overlap, the difference operation results obtained by each calculation can be compared to determine the result with the largest difference. The result with the largest difference is the prediction box with the most accurate boundary, and other prediction boxes that overlap with the prediction box are eliminated. After the accurate prediction box of the warehouse image is eliminated, the category of the items within the prediction box is identified through a preset recognition model to determine the border area in the warehouse image. The preset recognition model is pre-identified and generated using a large number of border area image samples and construction material image samples, and has the ability to identify border areas and construction materials. For the determined prediction box, the preset recognition model is used to extract the features of the item imaging therein, and the extracted features are analyzed to determine the category to which it belongs. After the prediction box containing the border area is determined, the position of the prediction box in the warehouse image is the position of the border area in the warehouse image.

[0118] Step S100, extracting a first image to be identified located within the frame area and a second image to be identified located outside the frame area;

[0119] Step S110, identifying the first image to be identified and the second image to be identified based on the preset recognition model, and determining whether there are first-category storage materials that do not meet the storage standards, and whether there are second-category storage materials that are placed beyond the boundary.

[0120] Step S120: If the first category of storage materials and / or the second category of storage materials exist, output storage abnormality prompt information.

[0121] Furthermore, after determining the border region of the warehouse image, the warehouse image is divided based on the border region into an inner region within the border region and an outer region outside the border region. The image of the warehouse image located in the inner region is then extracted as the first image to be identified, and the image of the warehouse image located in the outer region is extracted as the second image to be identified. In addition to being trained to identify border regions, the preset recognition model can also identify whether various types of construction materials are neatly and orderly placed within the border region. Therefore, this embodiment can identify the first image to be identified and the second image to be identified based on the preset recognition model.

[0122] Furthermore, the content of the first image to be identified includes at least whether the type of construction materials placed in the inner area is accurate, and whether the construction materials are neatly and orderly stored in the inner area, or whether they are scattered. Using the accurate type of construction materials and neat and orderly storage as storage standards, the first image to be identified is used to determine whether any of the stored materials contain first-category storage materials that do not meet the storage standards. The content of the second image to be identified includes at least whether construction materials exist in the outer area, that is, whether any construction materials exist beyond the boundary. Thus, the second image to be identified is used to determine whether any second-category storage materials exist beyond the boundary.

[0123] Furthermore, if the construction materials actually placed in the inner area are determined to be inconsistent with the theoretically intended type of construction materials, or if the construction materials are scattered and piled in the inner area, or if both situations exist, then the stored materials are determined to contain Category 1 materials that do not meet the storage standards. Furthermore, if the construction materials are identified in the outer area, then Category 2 materials are determined to be placed beyond the boundaries. For the determination that Category 1 or Category 2 materials exist, or both, a corresponding storage anomaly warning message is output to prompt relevant personnel to promptly address the issue, ensuring the orderly storage of all types of storage materials in the warehouse.

[0124] Furthermore, the function of accurately identifying the border area and the function of identifying whether various types of construction materials are neatly and orderly placed within the border area, which are possessed by the preset recognition model, can be formed by training with different image samples, or by training with different annotations on the same image samples. This embodiment preferably trains with different image samples. Specifically, with respect to the training of the function of accurately identifying the border area, the step of identifying the warehouse image based on the preset recognition model and determining the border area in the warehouse image includes:

[0125] Step S94: obtaining a preset image sample, and training a preset initial model based on the preset image sample;

[0126] Step S95, when the preset initial model is trained for a preset number of times, the loss function value of the preset initial model is calculated according to the training result generated by the last training;

[0127] Step S96, determining whether the loss function value is less than a preset function threshold; if so, generating the preset initial model as a preset recognition model;

[0128] Step S97: If the loss function value is greater than or equal to the preset function threshold, the step of training the preset initial model based on the preset image sample is executed until the loss function value is less than the preset function threshold.

[0129] Furthermore, a large number of pre-labeled preset image samples are obtained, and the preset image samples at least include border area image samples. The preset initial model is trained with such preset image samples to train the preset initial model to have the ability to accurately identify border areas. In addition, a preset number of times is set in advance based on empirical values. The preset initial model processes all preset image samples once to obtain relevant processing results, which is considered as one training. When the number of training times reaches the preset number, the loss function value of the preset initial model is calculated based on the training results generated by the training that reaches the preset number of times. The loss function value represents the difference between the training results generated by the preset initial model when processing the preset image samples and the reference results labeled by each preset image sample. The smaller the difference, the closer the result obtained by the preset initial model processing the preset image samples is to the reference result, and the better the recognition performance of the preset initial model.

[0130] Furthermore, whether the preset recognition model can accurately identify the bounding box area mainly includes whether it can accurately demarcate the prediction box and whether it can accurately identify the type of object within the prediction box. Correspondingly, its loss function value also includes these two parts. The specific calculation formula of the loss function value can be found in the following formula (2).

[0131]

[0132] Among them, L represents the loss function value, N represents the number of preset image samples, and H k Indicates the center point height difference between the training prediction box generated by the k-th preset image sample in the training result and the real box corresponding to the k-th preset image sample, (x0 k ,y0 k ) represents the center coordinate value of the real frame, (x k ,y k ) represents the center coordinate value of the training prediction box, (w0 k , h0 k ) represents the width and height of the real frame, (w k , h k ) represents the width and height of the training prediction box, α represents the preset shape loss attention coefficient, Used to calculate the angle loss of the training prediction box, that is, the position difference between the prediction box and the real box; It is used to calculate the shape loss of the training prediction box, that is, the difference in shape and size between the prediction box and the real box; f(·) is used to calculate the function of item category loss, bk represents the item category result generated by the kth preset image sample in the training result, that is, the recognition result of the category recognition of the item in the prediction box, b0 k Represents the true category result corresponding to the k-th preset image sample. This refers to the category result labeled for the k-th preset image sample. By combining the position and shape of the prediction box with the loss of the item category within the prediction box, the loss function is calculated. This allows the preset initial model to accurately delineate the prediction box and accurately identify the item type within the prediction box through training.

[0133] Furthermore, in order to reflect the magnitude of the error reflected by the loss function value, a preset function threshold is pre-set, and the calculated loss function value is compared with the preset function threshold to determine whether the loss function value is less than the preset function threshold. If it is less than the preset function threshold, it means that the error reflected by the loss function value is small, and the preset initial model can accurately identify the border area, thereby generating the preset initial model as the preset recognition model. Conversely, if the loss function value is determined to be greater than or equal to the preset function threshold through comparison, it means that the accuracy of the preset initial model in identifying the border area is low. At this time, the preset initial model is iteratively trained based on the preset image samples until the calculated loss function value is less than the preset function threshold, and then the preset initial model is generated as the preset recognition model.

[0134] It should be noted that the generated preset recognition model can be used to accurately identify the border area of ​​the warehouse image, and to identify whether various types of construction materials are stored neatly and orderly in the border area, the generated preset recognition model can be updated and trained through relevant annotated image samples to obtain an updated preset recognition model, which can be used to accurately identify the border area of ​​the warehouse image while also accurately identifying the neatness and orderliness of the construction materials.

[0135] In this embodiment, after the materials to be shipped out are shipped out, the warehouse image is obtained and recognized by a pre-trained preset recognition model to ensure that all storage materials in the warehouse are neatly and orderly stored in their respective corresponding storage areas. This is conducive to the orderly storage and retrieval of various types of construction materials, and also prevents the risks that may be caused by scattered stacking, thereby realizing the safe and orderly management of various types of construction materials in the warehouse.

[0136] For further information, please refer to Figure 4 Based on the first, second and third embodiments of the construction material management method based on big data of the present invention, the fourth embodiment of the construction material management method based on big data of the present invention is proposed.

[0137] The fourth embodiment of the method for managing construction materials for construction projects based on big data differs from the first, second, and third embodiments of the method for managing construction materials for construction projects based on big data in that, upon receiving a supervision request triggered by a preset supervision period corresponding to any construction material in a construction project, before the step of obtaining the usage and remaining amount of the construction material, and the storage loss rate of the construction material in the warehouse corresponding to the construction project, the method includes:

[0138] Step S130, obtaining the construction design quantity and design cost of the construction materials at each construction stage of the construction project, as well as storage price information and transportation price information corresponding to the construction materials;

[0139] Step S140, for each of the construction stages, construct a cost cycle function based on the construction design quantity, quantity design cost, and the storage price information and transportation price information of the construction stage, and determine the preset supervision period based on the cost cycle function.

[0140] Furthermore, the construction project can be divided into a number of different construction phases, and different construction durations are set for different construction phases. The demand for the same construction material is different in different construction phases. In this embodiment, the preset supervision cycle for controlling the construction materials is divided according to the different construction phases. Specifically, the construction design quantity and quantity design cost of the construction materials in each construction phase of the construction project have been set during the design process of the construction project, and the construction design quantity and quantity design cost of each construction phase are obtained. Among them, each construction phase corresponds to a construction design quantity and quantity design cost, which are used to represent the quantity of construction materials required according to the design at each construction phase, and the cost corresponding to the quantity. At the same time, the storage price information and transportation price information corresponding to the construction materials are obtained. The storage price information is the price information corresponding to the storage of construction materials, and the transportation price information is the price information corresponding to the transportation of construction materials. Both can be set in the preset database based on the historical prices of the storage and transportation of construction materials in the past, or they can be the quotation information of the relevant material suppliers.

[0141] Furthermore, the construction design quantity and quantity design cost of each construction phase are combined with storage price information and transportation price information to construct a cost cycle function. The preset supervision period is determined by calculating the cost cycle function. The constructed cost cycle function can be seen in the following formula (3).

[0142]

[0143] Among them, U represents the usage design cost, U1 represents the fixed storage cost in the storage price information, T represents the number of supervisions corresponding to the construction stage, K1 represents the time coefficient corresponding to the fixed storage cost, Q represents the construction design usage, U2 represents the unit storage cost in the storage price information, K2 represents the time coefficient corresponding to the unit storage cost, U3 represents the fixed transportation cost in the transportation price information, K3 represents the time coefficient corresponding to the fixed transportation cost, U4 represents the unit transportation cost in the transportation price information, and K4 represents the time coefficient corresponding to the unit transportation cost.

[0144] It should be noted that the warehousing fixed cost U1 and the transportation fixed cost U3 are fixed costs incurred for each warehousing and transportation operation. The greater the number of supervision times T, the higher the cumulative warehousing fixed cost U1 and transportation fixed cost U3. The time coefficients K1, K2, K3, and K4 are all related to the time interval corresponding to the number of supervision times. Their specific values ​​can be pre-set based on changes in warehousing fixed cost, unit warehousing cost, transportation fixed cost, and unit transportation cost over previous time periods. For example, if market factors affect warehousing fixed cost during certain time periods, resulting in a larger time coefficient k1, this indicates higher warehousing fixed cost during that period. Alternatively, if market factors affect unit transportation cost during other time periods, resulting in a larger time coefficient k2, this indicates higher unit transportation cost during that period. By adjusting the number of supervision times, the cumulative warehousing fixed cost U1 and transportation fixed cost U3 can be reduced, and by adjusting the relevant time coefficients, the overall price can be reduced to a level lower than the total design cost for the construction phase.

[0145] Furthermore, a preset supervision cycle is determined based on the adjusted number of supervisions and the construction duration set for the construction phase. If multiple supervision times all satisfy the requirement that the overall price is less than the total design cost, the supervision time with the lowest overall price can be selected as the final supervision time to maximize cost reduction. The preset supervision cycle can be set with balanced time intervals, i.e., multiple periods of equal time intervals are divided according to the construction duration and number of supervisions. For example, if the construction duration is 60 days and the number of supervisions is 3, the preset supervision cycle is 20 days. Furthermore, uneven time intervals can be set, specifically based on the time coefficients corresponding to k1, k2, k3, and k4, to further reduce the overall price. For example, for a construction phase with a construction duration of 60 days and 3 supervisions, if k1, k2, k3, and k4 are all relatively low for the first 30 days and k1, k2, and k3 are relatively low for the last 20 days, the first preset supervision cycle can be 30 days, the second preset supervision cycle 20 days, and the final preset supervision cycle 10 days.

[0146] This embodiment reduces costs to the greatest extent by constructing a cost cycle function and adjusting the number of supervisions in the cost cycle function, thereby determining an appropriate preset supervision cycle to rationally manage construction materials.

[0147] In addition, the present invention also provides a construction material management system based on big data. Figure 5 , Figure 5 This is a structural diagram of the equipment hardware operating environment involved in the implementation scheme of the construction material management system based on big data of the present invention.

[0148] like Figure 5 As shown, the construction material management system based on big data may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a storage 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 1003 may optionally include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The storage 1005 may be a high-speed RAM storage, or a stable storage (non-volatile memory), such as a disk storage. The storage 1005 may also be a storage device independent of the aforementioned processor 1001.

[0149] Those skilled in the art will understand that Figure 5 The hardware structure of the construction material management system based on big data shown in the figure does not constitute a limitation of the construction material management system based on big data, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0150] like Figure 5 As shown, the storage medium 1005 may include an operating system, a network communication module, a user interface module, and a control program. The operating system is a program that manages and controls the big data-based construction material management system and software resources, supporting the operation of the network communication module, the user interface module, the control program, and other programs or software. The network communication module is used to manage and control the network interface 1004; the user interface module is used to manage and control the user interface 1003.

[0151] exist Figure 5In the hardware structure of the big data-based construction material management system shown, the network interface 1004 is mainly used to connect to other system servers and communicate data with them; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; the processor 1001 can call the control program stored in the memory 1005 and perform the following operations:

[0152] Upon receiving a supervision request triggered by a preset supervision period corresponding to any construction material in a construction project, obtaining the usage and remaining quantity of the construction material in the preset supervision period, as well as the storage loss rate of the construction material in the warehouse corresponding to the construction project;

[0153] Predicting the usage of the construction materials in the next preset supervision period based on the usage, remaining amount, storage loss rate, and engineering parameters of the construction project in the next preset supervision period;

[0154] receiving a retrieval application initiated based on the predicted usage, and determining the material to be shipped from each of the stored materials according to the material code carried in the retrieval application and the material code corresponding to each of the stored materials in the warehouse in a preset database;

[0155] Randomly selecting materials to be inspected from the materials to be shipped based on a preset random algorithm, and analyzing whether the materials to be shipped meet preset shipping standards based on inspection data obtained from inspecting the materials to be inspected;

[0156] If the preset outbound standard is met, outbound information corresponding to the material to be outbound is generated based on the inspection data, the predicted usage and the material code, and the outbound information is output.

[0157] Furthermore, after the step of outputting the delivery information, the processor 1001 may call the control program stored in the storage 1005 and perform the following operations:

[0158] After receiving the information that the shipment is completed, the remaining storage quantity of the materials to be shipped in the warehouse is updated, and whether the conditions for generating a purchase order are met according to the updated remaining storage quantity is determined;

[0159] If the conditions for generating a procurement order are met, determining a construction mode for the construction project and generating a time weight and a cost weight corresponding to the construction mode;

[0160] Acquire supply data corresponding to the material to be shipped from a preset database, calculate a supply coefficient based on the supply data, the time weight, and the cost weight, and generate the purchase instruction based on the supply coefficient, wherein the calculation formula of the supply coefficient is:

[0161]

[0162] Among them, Xj represents the supply coefficient of the jth supplier, Wt and Wc represent the time weight and cost weight respectively. and t j They represent the maximum, minimum and average time required to purchase the materials to be shipped from supplier j contained in the supply data, and c j represents the maximum, minimum and average cost of the materials to be shipped from supplier j in the supply data, r represents the correction coefficient corresponding to the materials to be shipped in the construction project in the supply data, h j and e j They respectively represent the acceptance qualification rate and historical failure rate corresponding to the supplier j contained in the supply data and the materials to be shipped.

[0163] Furthermore, after the step of outputting the delivery information, the processor 1001 may call the control program stored in the storage 1005 and perform the following operations:

[0164] Acquire a warehouse image of the material to be shipped out of the warehouse, and recognize the warehouse image based on a preset recognition model to determine a frame area in the warehouse image;

[0165] Extracting a first image to be identified that is located within the frame area and a second image to be identified that is located outside the frame area;

[0166] Recognize the first image to be recognized and the second image to be recognized based on the preset recognition model, and determine whether there are first-category storage materials that do not meet the storage standards, and whether there are second-category storage materials that are placed beyond the boundary.

[0167] If the first category of storage materials and / or the second category of storage materials exist, a storage abnormality prompt message is output.

[0168] Furthermore, the step of identifying the warehouse image based on a preset recognition model and determining a border area in the warehouse image includes:

[0169] Dividing the warehouse image into a plurality of grids based on a preset recognition model, and generating a plurality of bounding boxes corresponding to each of the grids;

[0170] For each of the bounding boxes, obtaining inner frame pixel values ​​and outer frame pixel values ​​adjacent to the bounding box, and determining a predicted box in the warehouse image based on a difference between the inner frame pixel values ​​and the outer frame pixel values;

[0171] The category of the items in the predicted frame is identified based on a preset recognition model to determine the frame area in the warehouse image.

[0172] Furthermore, before the step of identifying the warehouse image based on the preset recognition model and determining the border area in the warehouse image, the processor 1001 may call the control program stored in the storage 1005 and perform the following operations:

[0173] Obtaining preset image samples, and training a preset initial model based on the preset image samples;

[0174] When the preset initial model is trained for a preset number of times, the loss function value of the preset initial model is calculated based on the training result generated by the last training, and the calculation formula is:

[0175]

[0176] Among them, L represents the loss function value, N represents the number of preset image samples, and H k Indicates the center point height difference between the training prediction box generated by the k-th preset image sample in the training result and the real box corresponding to the k-th preset image sample, (x0 k ,y0 k ) represents the center coordinate value of the real frame, (x k ,y k ) represents the center coordinate value of the training prediction box, (w0 k , h0 k ) represents the width and height of the real frame, (w k , h k ) represents the width and height of the training prediction box, α represents the preset shape loss attention coefficient, Used to calculate the angle loss of the training prediction box, Function b is used to calculate the shape loss of the training prediction box, and f(·) is used to calculate the item category loss. k Indicates the item category result generated by the k-th preset image sample in the training result, b0 k Indicates the true category result corresponding to the k-th preset image sample;

[0177] Determine whether the loss function value is less than a preset function threshold, and if so, generate the preset initial model as a preset recognition model;

[0178] If the loss function value is greater than or equal to the preset function threshold, the step of training the preset initial model based on the preset image sample is executed until the loss function value is less than the preset function threshold.

[0179] Furthermore, the step of predicting the predicted usage amount of the construction material in the next preset supervision cycle based on the usage amount, remaining amount, storage loss rate and the next project parameters of the construction project in the next preset supervision cycle includes:

[0180] Obtaining current project parameters and next project parameters of the construction project in a preset supervision period and a next preset supervision period, respectively, wherein the current project parameters and the next project parameters each include at least one of project process parameters, project geological parameters, and project personnel parameters;

[0181] generating a similarity value between the current engineering parameter and the next engineering parameter, and determining whether the similarity value is greater than a preset similarity threshold; if so, predicting the next usage in the next preset period based on the current engineering parameter, the usage, and the next engineering parameter;

[0182] A preset reserve ratio of the construction material is obtained, and the next usage is updated according to the preset reserve ratio, the remaining amount, and the storage loss rate to obtain the predicted usage.

[0183] Furthermore, the step of randomly selecting materials to be inspected from the materials to be shipped based on a preset random algorithm, and analyzing whether the materials to be shipped meet preset shipping standards based on inspection data obtained from inspecting the materials to be inspected includes:

[0184] Searching a preset database for the most recent historical inspection data of the material to be shipped, and determining a generation date of the historical inspection data;

[0185] Generate the generation date as an inspection interval, and determine whether the inspection interval exceeds a preset inspection period. If it exceeds the preset inspection period, generate a random code based on a preset random algorithm, and screen the materials to be inspected from the materials to be shipped out according to the random code;

[0186] Acquiring inspection data generated by inspecting the materials to be inspected, and analyzing whether the materials to be shipped meet preset shipping standards based on the inspection data;

[0187] If the inspection time does not exceed the preset time, the historical inspection data is used as inspection data to analyze whether the materials to be shipped meet the preset shipping standards.

[0188] Furthermore, upon receiving a supervision request triggered by a preset supervision cycle corresponding to any construction material in the construction project, before obtaining the usage and remaining amount of the construction material, as well as the storage loss rate of the construction material in the warehouse corresponding to the construction project, the processor 1001 may call the control program stored in the storage 1005 and perform the following operations:

[0189] Obtaining the design quantity and design cost of the construction materials at each construction stage of the construction project, as well as storage price information and transportation price information corresponding to the construction materials;

[0190] For each construction stage, a cost cycle function is constructed based on the construction design quantity, quantity design cost, and the storage price information and transportation price information of the construction stage, and the preset supervision period is determined based on the cost cycle function. The cost cycle function is:

[0191]

[0192] Among them, U represents the usage design cost, U1 represents the fixed storage cost in the storage price information, T represents the number of supervisions corresponding to the construction stage, K1 represents the time coefficient corresponding to the fixed storage cost, Q represents the construction design usage, U2 represents the unit storage cost in the storage price information, K2 represents the time coefficient corresponding to the unit storage cost, U3 represents the fixed transportation cost in the transportation price information, K3 represents the time coefficient corresponding to the fixed transportation cost, U4 represents the unit transportation cost in the transportation price information, and K4 represents the time coefficient corresponding to the unit transportation cost.

[0193] The specific implementation of the construction material management system based on big data of the present invention is basically the same as the various embodiments of the construction material management method based on big data described above, and will not be repeated here.

[0194] The embodiment of the present invention further provides a medium. The medium is a readable storage medium having a control program stored thereon. When the control program is executed by a processor, the steps of the above-mentioned method for managing construction materials based on big data are implemented.

[0195] The readable storage medium of the present invention can be a computer-readable storage medium, and its implementation method is basically the same as the above-mentioned embodiments of the construction material management method based on big data, and will not be repeated here.

[0196] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of the present invention, or directly or indirectly used in other related technical fields, all fall within the protection of the present invention.

Claims

1. A construction material management method based on big data, characterized in that: Preset supervision cycles are set for various types of construction materials in the construction project, and the corresponding relationship between the construction materials and the preset supervision cycles is stored in a preset database; The construction material management method for a building project comprises: Upon receiving a supervision request triggered by a preset supervision period corresponding to any construction material in a construction project, obtaining the usage and remaining quantity of the construction material in the preset supervision period, as well as the storage loss rate of the construction material in the warehouse corresponding to the construction project; Predicting the usage of the construction materials in the next preset supervision period based on the usage, remaining amount, storage loss rate, and engineering parameters of the construction project in the next preset supervision period; receiving a retrieval application initiated based on the predicted usage, and determining a material to be shipped from each of the stored materials according to a material code carried in the retrieval application and a material code corresponding to each of the stored materials in the warehouse in a preset database; Randomly selecting materials to be inspected from the materials to be shipped based on a preset random algorithm, and analyzing whether the materials to be shipped meet preset shipping standards based on inspection data obtained from inspecting the materials to be inspected; If the preset outbound standard is met, outbound information corresponding to the material to be outbound is generated based on the inspection data, the predicted usage and the material code, and the outbound information is output; Wherein, the step of outputting the outbound information includes: Acquire a warehouse image of the material to be shipped out of the warehouse, and recognize the warehouse image based on a preset recognition model to determine a frame area in the warehouse image; Extracting a first image to be identified that is located within the frame area and a second image to be identified that is located outside the frame area; Recognize the first image to be recognized and the second image to be recognized based on the preset recognition model, and determine whether there are first-category storage materials that do not meet the storage standards, and whether there are second-category storage materials that are placed beyond the boundary. If the first category of storage materials and / or the second category of storage materials exist, a storage abnormality prompt message is output.

2. The construction material management method for a building project according to claim 1, wherein: The step of outputting the outbound information includes: After receiving the information that the shipment is completed, the remaining storage quantity of the materials to be shipped in the warehouse is updated, and whether the conditions for generating a purchase order are met according to the updated remaining storage quantity is determined; If the conditions for generating a procurement order are met, determining a construction mode for the construction project and generating a time weight and a cost weight corresponding to the construction mode; Acquire supply data corresponding to the material to be shipped from a preset database, calculate a supply coefficient based on the supply data, the time weight, and the cost weight, and generate the purchase instruction based on the supply coefficient, wherein the calculation formula of the supply coefficient is: Among them, Xj represents the supply coefficient of the jth supplier, Wt and Wc represent the time weight and cost weight respectively. and t j They represent the maximum, minimum and average time required to purchase the materials to be shipped from supplier j contained in the supply data, and c j represents the maximum, minimum and average cost of the materials to be shipped from supplier j in the supply data, r represents the correction coefficient corresponding to the materials to be shipped in the construction project in the supply data, h j and e j They respectively represent the historical failure rate and acceptance rate corresponding to the supplier j included in the supply data and the materials to be shipped.

3. The construction material management method of construction engineering according to claim 1, characterized in that: The step of identifying the warehouse image based on a preset recognition model and determining a border area in the warehouse image includes: Dividing the warehouse image into a plurality of grids based on a preset recognition model, and generating a plurality of bounding boxes corresponding to each of the grids; For each of the bounding boxes, obtaining inner frame pixel values ​​and outer frame pixel values ​​adjacent to the bounding box, and determining a predicted box in the warehouse image based on a difference between the inner frame pixel values ​​and the outer frame pixel values; The category of the items in the predicted frame is identified based on a preset recognition model to determine the frame area in the warehouse image.

4. The construction material management method for a construction project according to any one of claims 1 to 3, characterized in that: The step of predicting the predicted usage amount of the construction material in the next preset supervision period based on the usage amount, remaining amount, storage loss rate and the next project parameters of the construction project in the next preset supervision period includes: Obtaining current project parameters and next project parameters of the construction project in a preset supervision period and a next preset supervision period, respectively, wherein the current project parameters and the next project parameters each include at least one of project process parameters, project geological parameters, and project personnel parameters; Generate a similarity value between the current project parameter and the next project parameter, and determine whether the similarity value is greater than a preset similarity threshold; if so, predict the next usage in the next preset monitoring period based on the current project parameter, the usage, and the next project parameter; A preset reserve ratio of the construction material is obtained, and the next usage is updated according to the preset reserve ratio, the remaining amount, and the storage loss rate to obtain the predicted usage.

5. The construction material management method for a construction project according to any one of claims 1 to 3, characterized in that: The step of randomly selecting materials to be inspected from the materials to be shipped based on a preset random algorithm, and analyzing whether the materials to be shipped meet preset shipping standards based on inspection data obtained from inspecting the materials to be inspected includes: Searching a preset database for the most recent historical inspection data of the material to be shipped, and determining a generation date of the historical inspection data; Generate the generation date as an inspection interval, and determine whether the inspection interval exceeds a preset inspection period. If it exceeds the preset inspection period, generate a random code based on a preset random algorithm, and screen the materials to be inspected from the materials to be shipped out according to the random code; Acquiring inspection data generated by inspecting the materials to be inspected, and analyzing whether the materials to be shipped meet preset shipping standards based on the inspection data; If the inspection interval does not exceed the preset inspection period, the historical inspection data is used as inspection data to analyze whether the materials to be shipped meet the preset shipping standards.

6. The construction material management method for a construction project according to any one of claims 1 to 3, characterized in that: The step of obtaining the usage and remaining amount of the construction material and the storage loss rate of the construction material in the warehouse corresponding to the construction project upon receiving a supervision request triggered by a preset supervision period corresponding to any construction material in the construction project includes: Obtaining the design quantity and design cost of the construction materials at each construction stage of the construction project, as well as storage price information and transportation price information corresponding to the construction materials; For each construction stage, a cost cycle function is constructed based on the construction design quantity, quantity design cost, and the storage price information and transportation price information of the construction stage, and the preset supervision period is determined based on the cost cycle function. The cost cycle function is: Among them, U represents the usage design cost, U1 represents the fixed storage cost in the storage price information, T represents the number of supervisions corresponding to the construction stage, K1 represents the time coefficient corresponding to the fixed storage cost, Q represents the construction design usage, U2 represents the unit storage cost in the storage price information, K2 represents the time coefficient corresponding to the unit storage cost, U3 represents the fixed transportation cost in the transportation price information, K3 represents the time coefficient corresponding to the fixed transportation cost, U4 represents the unit transportation cost in the transportation price information, and K4 represents the time coefficient corresponding to the unit transportation cost.

7. A construction material management system based on big data, characterized in that: The construction material management system based on big data includes a memory, a processor, a communication bus, and a control program stored in the memory: The communication bus is used to realize the connection and communication between the processor and the storage; The processor is used to execute the control program to implement the steps of the construction material management method based on big data as described in any one of claims 1 to 6.

8. A medium, characterized in that The medium is a readable storage medium, on which a control program is stored. When the control program is executed by a processor, the steps of the construction material management method based on big data as described in any one of claims 1 to 6 are implemented.

Images