Multi-role dynamic cooperation resource allocation method and system based on smart contract, terminal and storage medium

Abstract

The invention discloses a multi-role dynamic cooperation resource allocation method and system based on an intelligent contract, a terminal and a storage medium, and the method comprises the steps: obtaining a target design draft, a current construction progress image and a supervision acceptance result, and carrying out the preprocessing, and obtaining a construction acceptance result; performing 3D point cloud comparison processing according to a construction acceptance result to obtain a design reduction degree; performing multi-role contribution degree quantitative calculation according to the design reduction degree to obtain a multi-role contribution degree quantitative result; and determining a target resource, and carrying out dynamic resource allocation on the target resource according to the multi-role contribution degree quantification result to obtain a multi-role resource allocation result. According to the method, the design reduction degree after construction is calculated, quantitative calculation is performed on the contribution degree of each role according to the design reduction degree, and then the target resources are allocated according to the quantitative result of the contribution degrees of the multiple roles, so that the contribution quantification accuracy of each role is effectively improved, and the resource allocation efficiency is also effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a multi-role dynamic collaborative resource allocation method, system, terminal and computer-readable storage medium based on smart contracts. Background Art

[0002] In the existing home improvement industry, it usually includes designers (who provide design plans), constructors (who carry out construction according to the design plans provided by designers) and supervisors (who supervise the construction progress and construction results of the constructors), and resources are allocated according to the contribution of these roles (i.e. designers, constructors and supervisors).

[0003] However, the existing technology does not accurately calculate the contribution of roles in the construction process of the home improvement industry, which leads to uneven resource allocation and fails to meet user needs.

[0004] Therefore, the existing technology still needs to be improved and developed. Summary of the Invention

[0005] The main purpose of the present invention is to provide a multi-role dynamic collaborative resource allocation method, system, terminal and computer-readable storage medium based on smart contracts, aiming to solve the problem in the existing technology that the contribution calculation of roles in the construction process of the home improvement industry is not accurate, resulting in uneven resource allocation and failure to meet user needs.

[0006] To achieve the above objectives, the present invention provides a multi-role dynamic collaborative resource allocation method based on smart contracts, the multi-role dynamic collaborative resource allocation method based on smart contracts comprising the following steps:

[0007] Obtaining a target design draft, a current construction progress image, and a supervision acceptance result, and preprocessing the target design draft, the current construction progress image, and the supervision acceptance result to obtain a construction acceptance result;

[0008] Perform 3D point cloud comparison processing based on the construction acceptance results to obtain the design restoration degree;

[0009] Performing a multi-role contribution quantification calculation based on the design restoration degree to obtain a multi-role contribution quantification result;

[0010] Target resources are determined, and dynamic resource allocation is performed on the target resources according to the multi-role contribution quantification result to obtain a multi-role resource allocation result.

[0011] Optionally, the multi-role dynamic collaborative resource allocation method based on smart contracts, wherein the step of obtaining a target design draft, a current construction progress image, and a supervision acceptance result, and pre-processing the target design draft, the current construction progress image, and the supervision acceptance result to obtain a construction acceptance result, specifically includes:

[0012] Obtain target design draft, current construction progress image and supervision acceptance results;

[0013] A hash function is used to perform hash value conversion on the target design draft to obtain the design draft CAD hash value;

[0014] Collecting images of the current construction progress through IoT devices, wherein the IoT devices include construction site cameras and sensors;

[0015] Determine a construction detection model, input the current construction progress image into the construction detection model, and output a construction detection result;

[0016] The construction acceptance result is constructed based on the design draft CAD hash value, the construction inspection result and the supervision acceptance result.

[0017] Optionally, the multi-role dynamic collaborative resource allocation method based on smart contracts, wherein the step of determining a construction detection model, inputting the current construction progress image into the construction detection model, and outputting a construction detection result, further comprises:

[0018] Collecting a preset number of home quality inspection pictures, and dividing the data set according to the home quality inspection pictures to obtain a home quality inspection data set, wherein the home quality inspection data set includes a home quality inspection training set and a home quality inspection test set;

[0019] A pre-trained model is determined, model training is performed on the pre-trained model according to the home quality inspection training set, and model fine-tuning is performed on the pre-trained model according to the home quality inspection test set to obtain a construction inspection model.

[0020] Optionally, the multi-role dynamic collaborative resource allocation method based on smart contracts, wherein the 3D point cloud comparison processing is performed according to the construction acceptance result to obtain the design restoration degree, specifically includes:

[0021] Obtaining the target household object after construction completion in the construction acceptance result, and performing 3D scanning processing on the target household object using a 3D scanning device to obtain 3D point cloud data;

[0022] Reprocessing the 3D point cloud data to obtain target 3D point cloud data, wherein the reprocessing includes format conversion processing, denoising processing, and data registration processing;

[0023] Performing feature extraction processing on the target 3D point cloud data to obtain geometric features and topological features of the target household object;

[0024] The original point cloud data corresponding to the target design draft is obtained, and the original point cloud features corresponding to the original point cloud data are compared with the geometric features and the topological features of the target home object to obtain the design restoration degree.

[0025] Optionally, the multi-role dynamic collaborative resource allocation method based on smart contracts, wherein the multi-role contribution quantification calculation is performed according to the design restoration degree to obtain the multi-role contribution quantification result, specifically including:

[0026] The dynamic weight algorithm is used to calculate the dynamic weight of each role, wherein the expression of the dynamic weight algorithm is:

[0027]

[0028] Among them, ω i (t) is the dynamic weight of each role, t is time, ω i0 is the initial weight of each role, λ is the time decay factor, s ij (t) is the contribution score of role i in task j, and N is the total number of tasks;

[0029] Obtaining a restoration degree error of the designed restoration degree, and comparing the restoration degree error with a preset threshold;

[0030] If the restoration error is less than the preset threshold, a contribution quantification model is used to perform multi-role contribution quantification calculation based on the design restoration and the dynamic weights of each role to obtain a multi-role contribution quantification result, wherein the multi-role contribution quantification result includes the design contribution, the construction contribution, and the supervision contribution;

[0031] The contribution quantification model is expressed as follows:

[0032]

[0033] Among them, α i is the total contribution of role i, i is the role, including designer, constructor and supervisor, k is the indicator, n is the total number of indicators, ω ik is the dynamic weight ω of each role i The dynamic weight corresponding to role i in (t), m ik is the design restoration degree of character i, m min，k is the minimum reference value of indicator k, m max，k is the maximum reference value of indicator k.

[0034] Optionally, in the multi-role dynamic collaborative resource allocation method based on smart contracts, the expression for the dynamic resource allocation is:

[0035]

[0036] Among them, the V i is the resource allocation result of role i, V is the target resource, α j The sum of all characters' contributions.

[0037] In addition, to achieve the above-mentioned purpose, the present invention further provides a multi-role dynamic collaborative resource allocation system based on smart contracts, wherein the multi-role dynamic collaborative resource allocation system based on smart contracts includes:

[0038] A data preprocessing module is used to obtain a target design draft, a current construction progress image, and a supervision acceptance result, and preprocess the target design draft, the current construction progress image, and the supervision acceptance result to obtain a construction acceptance result;

[0039] A design restoration degree calculation module is used to perform 3D point cloud comparison processing based on the construction acceptance results to obtain the design restoration degree;

[0040] A multi-role contribution quantification module is used to perform multi-role contribution quantification calculation according to the design restoration degree to obtain a multi-role contribution quantification result;

[0041] The dynamic resource allocation module is used to determine the target resource and dynamically allocate the target resource according to the multi-role contribution quantification result to obtain the multi-role resource allocation result.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a multi-role dynamic collaborative resource allocation program based on a smart contract stored on the memory and runnable on the processor. When the multi-role dynamic collaborative resource allocation program based on a smart contract is executed by the processor, the steps of the multi-role dynamic collaborative resource allocation method based on a smart contract as described above are implemented.

[0043] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a multi-role dynamic collaborative resource allocation program based on a smart contract, and when the multi-role dynamic collaborative resource allocation program based on a smart contract is executed by a processor, the steps of the multi-role dynamic collaborative resource allocation method based on a smart contract as described above are implemented.

[0044] In the present invention, the target design draft, the current construction progress image and the supervision acceptance result are obtained, and the target design draft, the current construction progress image and the supervision acceptance result are pre-processed to obtain the construction acceptance result; 3D point cloud comparison processing is performed based on the construction acceptance result to obtain the design restoration degree; multi-role contribution quantification calculation is performed based on the design restoration degree to obtain the multi-role contribution quantification result; target resources are determined, and dynamic resource allocation is performed on the target resources based on the multi-role contribution quantification result to obtain the multi-role resource allocation result. The present invention obtains the construction acceptance result of the home improvement construction, and compares and calculates the design restoration degree of the construction result and the expected scheme based on the construction acceptance result, and then quantifies the contribution degree corresponding to each role according to the design restoration degree, and finally realizes the dynamic allocation of target resources according to the contribution degree. It not only effectively improves the accuracy of the multi-role contribution quantification, but also ensures the reasonable and effective precise allocation of target resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a flow chart of a preferred embodiment of the multi-role dynamic collaborative resource allocation method based on smart contracts of the present invention;

[0046] Figure 2 This is a schematic diagram of the system architecture of a preferred embodiment of the multi-role dynamic collaborative resource allocation method based on smart contracts of the present invention;

[0047] Figure 3 This is a schematic diagram of the overall operation flow of a preferred embodiment of the multi-role dynamic collaborative resource allocation method based on smart contracts of the present invention;

[0048] Figure 4 This is a structural diagram of a preferred embodiment of the multi-role dynamic collaborative resource allocation system based on smart contracts of the present invention;

[0049] Figure 5 FIG. 4 is a structural diagram of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of the present invention more clear and distinct, the present invention is further described in detail below with reference to the accompanying drawings and examples. 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.

[0051] In the existing home improvement industry, it usually includes designers (who provide design plans), constructors (who carry out construction according to the design plans provided by designers) and supervisors (who supervise the construction progress and construction results of the constructors), and resources are allocated according to the contribution of these roles (i.e. designers, constructors and supervisors).

[0052] However, the existing technology does not accurately calculate the contribution of roles in the construction process of the home improvement industry, which leads to uneven resource allocation and fails to meet user needs.

[0053] To solve the above problems, the present invention proposes a multi-role dynamic collaborative resource allocation method based on smart contracts. The contribution model is combined with smart contracts to quantify the contribution weights of design, construction and supervision, which can effectively solve the problem of uneven resource allocation and improve the efficiency and accuracy of resource allocation.

[0054] The multi-role dynamic collaborative resource allocation method based on smart contract described in the preferred embodiment of the present invention is as follows Figure 1 As shown, the multi-role dynamic collaborative resource allocation method based on smart contracts includes the following steps:

[0055] Step S10: Obtain a target design draft, a current construction progress image, and a supervision acceptance result, and pre-process the target design draft, the current construction progress image, and the supervision acceptance result to obtain a construction acceptance result.

[0056] like Figure 2 As shown, the present invention provides a data acquisition layer for collecting construction progress data (pre-processed to obtain the design draft CAD hash value, construction progress images, and supervision and acceptance results) through IoT devices (IoT devices include construction site cameras and sensors). In addition, the present invention also provides a data synchronization mechanism (on-site video acquisition, real-time uploading of sensor and other data to the blockchain, and collaborative AI quality inspection linkage): for binding the design draft version number to the blockchain hash value to ensure multi-party data consistency, and storing incremental data through IPFS to reduce on-chain storage costs.

[0057] Specifically, the target design draft, the current construction progress image and the supervision acceptance result are obtained; the hash value of the target design draft is converted to the chain using a hash function to obtain the CAD hash value of the design draft; the current construction progress image is collected through the IOT device, wherein the IOT device includes a construction site camera and a sensor.

[0058] The first is the process of data collection and verification. The collected construction progress data includes the target design draft, the current construction progress image and the supervision acceptance results. Then, the target design draft and the current construction progress image are pre-processed. The processing process of the target design draft (converting the design draft submission format) is as follows: convert the CAD / BIM file of the target design draft into a unique string of fixed length (such as 64-bit hexadecimal), and write this hash value into the blockchain. Among them, the conversion method adopts the hash value on-chain conversion processing, and the original data of any length (that is, the target design draft in the present invention, or other files, texts) is converted into the design draft CAD hash value through a hash function (such as SHA-256). By converting the target design draft into a hash value on the chain, the data can be made unique, tamper-proof and traceable.

[0059] Regarding the processing of current construction progress images: First, it is necessary to obtain daily construction progress images (obtained through on-site cameras and AI recognition, with construction progress data obtained three times a day, including AI quality inspection reports). Furthermore, in addition to the three times of construction progress data obtained daily, the specific progress of the current construction (specific construction steps) can also be obtained through cameras and sensors at the construction site. Facial recognition can also be used to determine which construction worker is handling each construction link, and AI can be used to identify the amount of currently consumed materials and other data. In this way, the percentage of each construction link in the entire construction progress, the percentage of the completion quality of that link in the design implementation, and the proportion of materials used in the total material consumption can be calculated.

[0060] A preset number of home quality inspection images are collected and data sets are divided based on the home quality inspection images to obtain a home quality inspection data set, wherein the home quality inspection data set includes a home quality inspection training set and a home quality inspection test set; a pre-trained model is determined, the pre-trained model is trained based on the home quality inspection training set, and the pre-trained model is fine-tuned based on the home quality inspection test set to obtain a construction inspection model. A construction inspection model is determined, and the current construction progress image is input into the construction inspection model to output a construction inspection result; a construction acceptance result is constructed based on the design draft CAD hash value, the construction inspection result, and the supervision acceptance result.

[0061] Furthermore, after collecting the current construction progress image, the present invention needs to determine whether the current construction results meet the requirements. The detection of construction results in the present invention includes two parts. The first part is to use a pre-trained large model to identify and judge based on the collected current construction progress image to determine whether the current construction results meet the requirements. In addition, the present invention also receives the supervision data results of the supervisor. The results of the large model recognition are combined with the supervision data results collected by the supervisor to obtain the specific construction acceptance results.

[0062] The present invention uses an AI quality inspection algorithm to identify and judge the current construction progress images collected using a pre-trained large model. The specific implementation steps are as follows: 1. Obtaining a pre-trained model: The present invention trains ResNet-50 based on existing standard specification data to obtain a pre-trained model. 2. Fine-tuning the pre-trained model: Using more than 10,000 home quality inspection images (i.e., the preset number of home quality inspection images in the present invention) for comparison and adjustment, the model training and fine-tuning are completed to obtain a construction inspection model. After subsequent experimental measurements, the final test-level accuracy of the construction inspection model reaches over 96%. 3. Edge deployment: After constructing the construction inspection model, the construction inspection model is loaded onto the NVIDA Jetson Nano for deployment at the edge. The construction inspection model deployed at the edge takes ≤0.5 seconds to perform inference.

[0063] For example, a construction inspection model deployed at the edge can monitor the following items: 1. Project Name: Ceramic Tile Hollowing; Inspection Item: Is the hollowing area ≤ 5%?; Detection Accuracy: 98%. 2. Project Name: Wall Flatness; Inspection Item: Is the deviation of a 2M ruler ≤ 2mm?; Detection Accuracy: 95%. 3. Project Name: Plumbing and Electrical Wiring; Inspection Item: Compliance with the GB50303-2015 standard?; Detection Accuracy: 100%.

[0064] The second part is the supervision and acceptance process: the supervisor needs to inspect the five key nodes in the construction process (including water and electricity, mud and wood, and paint, etc.) and obtain the supervision and acceptance results.

[0065] After obtaining the construction inspection results output by the construction inspection model and the supervision acceptance results uploaded by the supervisor, the CAD hash value of the design draft can be combined. These three together constitute the construction acceptance results, and the design restoration degree of the construction can be calculated subsequently based on the construction acceptance results.

[0066] Step S20: Perform 3D point cloud comparison processing based on the construction acceptance result to obtain the design restoration degree.

[0067] The design restoration degree calculation of the construction acceptance results is achieved through 3D point cloud comparison in the present invention. It is mainly to judge the error between the target household objects after construction completion in the construction acceptance results and the household objects designed in the design draft. The general error tolerance is set at ±2% (under normal circumstances, the pilot compliance rate is around 95%).

[0068] Specifically, the target household object after construction is completed in the construction acceptance result is obtained, and a 3D scanning device is used to perform 3D scanning processing on the target household object to obtain 3D point cloud data; the 3D point cloud data is reprocessed to obtain target 3D point cloud data, wherein the reprocessing includes format conversion processing, denoising processing and data registration processing; feature extraction processing is performed on the target 3D point cloud data to obtain the geometric features and topological features of the target household object; the original point cloud data corresponding to the target design draft is obtained, and the original point cloud features corresponding to the original point cloud data are compared with the geometric features and the topological features of the target household object to obtain the design restoration degree.

[0069] The specific process of 3D point cloud comparison processing is as follows: 1. Data acquisition: Use a 3D scanning device to scan the completed target household object to obtain its 3D point cloud data. 2. Format conversion: Convert the scanned 3D point cloud data into a unified format, such as PLY or OBJ, to obtain the first 3D point cloud data for subsequent processing. 3. Denoising: Use filtering algorithms, such as Gaussian filtering and median filtering, to remove noise points from the point cloud data to obtain the second 3D point cloud data. 4. Data registration: If multi-view scan data is available, use the ICP algorithm (Iterative Closest Point). The ICP algorithm is a classic algorithm for point cloud registration and is widely used in 3D scanning, robot navigation, SLAM (simultaneous localization and mapping) and other fields. The core idea of the ICP algorithm is to iteratively calculate the spatial position between two point clouds until they match as closely as possible. The point cloud data from different perspectives is registered and unified into the same coordinate system to obtain the target 3D point cloud data. 5. Extract the geometric and topological features of the target 3D point cloud data. 6. Perform point cloud comparison: Perform 3D point cloud comparison processing on the original point cloud features corresponding to the original point cloud data in the target design draft and the geometric features and topological features of the target home objects (including comparison of parameters such as distance, features, and deformation). 6. Visualization Analysis: Display the comparison results through 3D visualization software, allowing users to intuitively observe the differences between the design and the actual. 7. Quantitative Evaluation: Based on the comparison results such as distance and feature similarity, set thresholds to determine whether the design restoration meets the requirements. Only those that meet the design restoration requirements will be evaluated.

[0070] In addition, the present invention can also incorporate construction progress deviation and material consumption monitoring into the calculation of design restoration degree. Among them, the detection of construction progress deviation includes: whether the construction delay rate is ≤5% (generally, the construction delay rate is 2.8%); the detection of material consumption monitoring includes: AI identification of building material usage, whether the error is ≤3%, which can be deployed through NVIDA Jetson equipment to identify building material type, quantity and other data.

[0071] Step S30: performing multi-role contribution quantification calculation according to the design restoration degree to obtain a multi-role contribution quantification result.

[0072] Specifically, a dynamic weight algorithm is used to calculate the dynamic weight of each role, wherein the expression of the dynamic weight algorithm is: Among them, ω i (t) is the dynamic weight of each role, t is time, ω i0 is the initial weight of each role, λ is the time decay factor, s ij (t) is the contribution score of role i in task j, and N is the total number of tasks; the restoration error of the design restoration degree is obtained, and the restoration error is compared with a preset threshold; if the restoration error is less than the preset threshold, a contribution quantification model is used to perform multi-role contribution quantification calculation based on the design restoration degree and the dynamic weights of each role to obtain a multi-role contribution quantification result, wherein the multi-role contribution quantification result includes design contribution, construction contribution, and supervision contribution; the expression of the contribution quantification model is: Among them, α i is the total contribution of role i, i is the role, including designer, constructor and supervisor, k is the indicator, n is the total number of indicators, ω ik is the dynamic weight corresponding to role i, m ik is the design restoration degree of character i, m min，k is the minimum reference value of indicator k, m max，k is the maximum reference value of indicator k.

[0073] In the specific implementation process, the present invention is introduced with the home decoration construction plan. Generally, the design contribution can be calculated according to the following formula: D =0.4×design restoration degree+0.6×score result; where α D For design contribution, weights are assigned to hard decoration, soft decoration and each functional area, and the proportion of the score to the whole design is recorded as design restoration. The design contribution can be obtained by combining the design restoration and the scoring results uploaded by the user. Among them, the scoring results uploaded by the user can be the owner's score based on the satisfaction list, and the question options are set according to the renderings delivered to the owner and the functions, space scale, color, lighting and other angles after completion. Each option is assigned a different score, and finally the weighted average of the scores of each question is obtained to obtain the scoring result uploaded by the user. Generally, the construction contribution can be calculated according to the following formula: α C =0.5×construction period compliance rate+0.5×cost control rate; where, α C is the construction contribution; in addition, the calculation expression of the construction period compliance rate is: The expression of cost control rate is:

[0074] Since the contribution will change with the change of weights (including design weight, construction weight and supervision weight, for example, when the design does not meet the requirements, the design weight will decrease, and when the construction period is completed ahead of schedule, the construction weight will increase, etc.), a dynamic weight algorithm is set in the present invention to calculate the dynamic weights corresponding to different roles. The expression is as follows: Among them, ω i (t) is the dynamic weight of each role, t is time, ω i0 is the initial weight of each role, λ is the time decay factor, s ij (t) is the contribution score of role i in task j, and N is the total number of tasks.

[0075] Furthermore, after obtaining the dynamic weights corresponding to different roles, the contribution degree can be dynamically calculated. The mathematical model corresponding to the contribution degree calculation is as follows (i.e., the contribution quantification model in the present invention): ω ik is the dynamic weight corresponding to role i (e.g., design weight = 0.4, construction weight = 0.5, supervision weight = 0.1), where ω ik is the preset weight and Σω ik =1.

[0076] The dynamic weight adjustment rules are as follows: 1. Rating results affect weight: For every 1-star decrease in the rating, the designer's weight decreases by 10%; for every 1-star increase, the designer's weight increases by 10%; 2. For every day of advance on the construction date, the construction team's weight increases by 5%, and for every day of delay, the construction team's weight decreases by 5%. 3. If the supervisor fails the acceptance inspection (after receiving the supervisor's acceptance results, they must be reviewed), the supervisor's weight will be reset to zero.

[0077] The preset weight ω ik The dynamic adjustment rules include: ikt =ω ik (t-1)+Δω; where Δω=0.05×change in scoring result-0.03×construction period deviation rate.

[0078] Furthermore, when the multi-role contribution quantification result is in a dispute state, a consensus-reaching mechanism is used to update the multi-role contribution quantification result to obtain an updated multi-role contribution quantification result.

[0079] like Figure 2 As shown, the present invention also provides a consensus reaching mechanism (i.e. Figure 2Consensus optimization mechanism in the blockchain): When a contribution coefficient dispute occurs, the PBFT consensus mechanism is activated, and the distribution status is updated based on the majority of node verification results. The consensus optimization mechanism includes: 1. Contribution data is verified using PBFT consensus, resulting in a fault tolerance rate of ≥33%; 2. Data on-chain latency is ≤2 seconds (better than the 5 seconds of traditional BFT).

[0080] In the specific implementation process, the present invention takes home improvement construction as an example and automatically executes according to the smart contract. The payment trigger conditions are shown in Table 1 below:

[0081] Table 1: Payment trigger conditions for each stage

[0082]

[0083] Furthermore, the present invention also provides a contribution adjustment mechanism, wherein the expression for the historical attenuation of contribution is: in, The historical average contribution is the average of the past 12 months. In addition, the present invention also provides a scoring elimination system: construction teams with a quarterly score of less than 4 stars are prohibited from accepting orders for 6 months.

[0084] Step S40: Determine target resources, and dynamically allocate resources to the target resources according to the multi-role contribution quantification result to obtain a multi-role resource allocation result.

[0085] Specifically, the expression of the dynamic resource allocation is: Among them, the V i is the resource allocation result of role i, V is the target resource, α j The sum of all characters' contributions.

[0086] The examples are as follows (for pilot projects):

[0087] The existing technology has the following problems: 1. Rigid traditional resource allocation: fixed proportions of allocated resources (such as 20% for design, 70% for construction, and 10% for supervision) cannot reflect actual contributions, resulting in uneven resource allocation and high dispute rates; 2. Data opacity: construction progress and quality inspection rely on manual records, which are easily tampered with. By adopting the multi-role dynamic collaborative resource allocation method based on smart contracts in this invention, the contribution and weight of each role can be accurately calculated, as shown in Table 2 below:

[0088] Table 2: Dynamic contribution weight distribution table for each role:

[0089]

[0090] like Figure 3As shown, the specific operational process of the present invention is as follows: 1. The customer signs the contract and pays the advance payment to the contract address (the co-managed account agreed in the contract); 2. The designer submits the plan, and the construction team uploads the progress according to the milestones (each work milestone of the project is completed, no less than the number of points agreed in the contract). 3. After the supervisor's acceptance, the contract allocates resources according to the contribution level; if there is any objection to the resource allocation, dynamic weight calculation is performed under the protection of the consensus optimization mechanism, and resources are reallocated. This effectively improves the efficiency and accuracy of resource allocation, shortening the resource allocation time from 7 days to 2 hours, and reducing the customer complaint rate by 65%.

[0091] The technical effects of this invention include: 1. The error rate of resource allocation in smart contract execution is reduced from 15% to 3%; 2. When resources are unevenly distributed, the cycle of resource redistribution efficiency is shortened from 30 days to 3 days; 3. Collaboration efficiency is improved by 40%.

[0092] In summary, the innovations of this invention include: 1. Dynamic contribution model: quantifying role contributions through indicators such as design fidelity, construction deadline compliance rate, and acceptance pass rate; 2. Automatic resource allocation by smart contracts: real-time resource allocation based on contribution weights, with trigger conditions including construction deadline nodes and quality acceptance; 3. Consensus mechanism: When the contribution coefficient is in dispute, the PBFT consensus mechanism is activated, and the allocation status is updated based on the verification results of the majority of nodes.

[0093] The present invention discloses a multi-role dynamic collaborative resource allocation method based on smart contracts. By quantifying the contribution weights of design, construction, and supervision, the method solves the technical problems of poor real-time resource allocation, unverifiable collaboration status, and delayed dynamic adjustment caused by data silos in multi-role collaborative scenarios. The present invention can achieve a resource allocation error rate of ≤3% and a resource reallocation cycle of ≤3 days. The method is suitable for multi-role collaborative scenarios such as construction and e-commerce.

[0094] Further, if Figure 4 As shown, based on the above-mentioned multi-role dynamic collaborative resource allocation method based on smart contracts, the present invention also provides a multi-role dynamic collaborative resource allocation system based on smart contracts, wherein the multi-role dynamic collaborative resource allocation system based on smart contracts includes:

[0095] The data preprocessing module 51 is used to obtain the target design draft, the current construction progress image and the supervision acceptance result, and preprocess the target design draft, the current construction progress image and the supervision acceptance result to obtain the construction acceptance result;

[0096] A design restoration degree calculation module 52 is used to perform 3D point cloud comparison processing based on the construction acceptance results to obtain the design restoration degree;

[0097] A multi-role contribution quantification module 53 is configured to perform multi-role contribution quantification calculation according to the design restoration degree to obtain a multi-role contribution quantification result;

[0098] The dynamic resource allocation module 54 is configured to determine target resources and dynamically allocate the target resources according to the multi-role contribution quantification result to obtain a multi-role resource allocation result.

[0099] Furthermore, if Figure 5 As shown, based on the above-mentioned smart contract-based multi-role dynamic collaborative resource allocation method and system, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Figure 5 Only some of the components of the terminal are shown, but it should be understood that implementation of all of the shown components is not required, and more or fewer components may be implemented instead.

[0100] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Furthermore, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a multi-role dynamic collaborative resource allocation program 40 based on a smart contract is stored on the memory 20, and the multi-role dynamic collaborative resource allocation program 40 based on a smart contract can be executed by the processor 10, thereby realizing the multi-role dynamic collaborative resource allocation method based on a smart contract in this application.

[0101] In some embodiments, the processor 10 can be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the multi-role dynamic collaborative resource allocation method based on smart contracts.

[0102] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch screen, etc. The display 30 is used to display information on the terminal and to display a visual user interface.

[0103] In one embodiment, when the processor 10 executes the smart contract-based multi-role dynamic collaborative resource allocation program 40 in the memory 20, the following steps are implemented:

[0104] Obtaining a target design draft, a current construction progress image, and a supervision acceptance result, and preprocessing the target design draft, the current construction progress image, and the supervision acceptance result to obtain a construction acceptance result;

[0105] Perform 3D point cloud comparison processing based on the construction acceptance results to obtain the design restoration degree;

[0106] Performing a multi-role contribution quantification calculation based on the design restoration degree to obtain a multi-role contribution quantification result;

[0107] Target resources are determined, and dynamic resource allocation is performed on the target resources according to the multi-role contribution quantification result to obtain a multi-role resource allocation result.

[0108] The step of obtaining the target design draft, the current construction progress image, and the supervision acceptance result, and pre-processing the target design draft, the current construction progress image, and the supervision acceptance result to obtain the construction acceptance result specifically includes:

[0109] Obtain target design draft, current construction progress image and supervision acceptance results;

[0110] A hash function is used to perform hash value conversion on the target design draft to obtain the design draft CAD hash value;

[0111] Collecting images of the current construction progress through IoT devices, wherein the IoT devices include construction site cameras and sensors;

[0112] Determine a construction detection model, input the current construction progress image into the construction detection model, and output a construction detection result;

[0113] The construction acceptance result is constructed based on the design draft CAD hash value, the construction inspection result and the supervision acceptance result.

[0114] The step of determining a construction detection model, inputting the current construction progress image into the construction detection model, and outputting a construction detection result may also include:

[0115] Collecting a preset number of home quality inspection pictures, and dividing the data set according to the home quality inspection pictures to obtain a home quality inspection data set, wherein the home quality inspection data set includes a home quality inspection training set and a home quality inspection test set;

[0116] A pre-trained model is determined, model training is performed on the pre-trained model according to the home quality inspection training set, and model fine-tuning is performed on the pre-trained model according to the home quality inspection test set to obtain a construction inspection model.

[0117] The 3D point cloud comparison processing is performed based on the construction acceptance results to obtain the design restoration degree, specifically including:

[0118] Obtaining the target household object after construction completion in the construction acceptance result, and performing 3D scanning processing on the target household object using a 3D scanning device to obtain 3D point cloud data;

[0119] Reprocessing the 3D point cloud data to obtain target 3D point cloud data;

[0120] Original point cloud data is obtained, and 3D point cloud comparison processing is performed based on the original point cloud data and the target 3D point cloud data to obtain a design restoration degree.

[0121] The reprocessing includes format conversion, denoising and data registration.

[0122] The reprocessing of the 3D point cloud data to obtain target 3D point cloud data specifically includes:

[0123] Performing format conversion processing on the 3D point cloud data to obtain first 3D point cloud data;

[0124] Performing denoising on the first 3D point cloud data using a filtering algorithm to obtain second 3D point cloud data, wherein the filtering algorithm includes Gaussian filtering and median filtering;

[0125] The ICP algorithm is used to perform data registration processing on the second 3D point cloud data to obtain target 3D point cloud data.

[0126] The step of obtaining the original point cloud data and performing 3D point cloud comparison processing on the original point cloud data and the target 3D point cloud data to obtain the design restoration degree specifically includes:

[0127] Performing feature extraction processing on the target 3D point cloud data to obtain geometric features and topological features of the target household object;

[0128] The original point cloud data corresponding to the target design draft is obtained, and the original point cloud features corresponding to the original point cloud data are compared with the geometric features and the topological features of the target home object to obtain the design restoration degree.

[0129] The multi-role contribution quantification calculation is performed according to the design restoration degree to obtain the multi-role contribution quantification result, which specifically includes:

[0130] Obtaining a restoration error of the designed restoration degree, and comparing the restoration error with a preset threshold;

[0131] If the restoration error is less than the preset threshold, a contribution quantification model is used to perform multi-role contribution quantification calculation based on the design restoration and the dynamic weights of each role to obtain a multi-role contribution quantification result, wherein the multi-role contribution quantification result includes the design contribution, the construction contribution, and the supervision contribution;

[0132] The contribution quantification model is expressed as follows:

[0133]

[0134] Among them, α i is the total contribution of role i, i is the role, including designer, constructor and supervisor, k is the indicator, n is the total number of indicators, ω ik is the dynamic weight corresponding to role i, m ik is the design restoration degree of character i, m min，k is the minimum reference value of indicator k, m max，k is the maximum reference value of indicator k.

[0135] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a multi-role dynamic collaborative resource allocation program based on a smart contract, and when the multi-role dynamic collaborative resource allocation program based on a smart contract is executed by a processor, the steps of the multi-role dynamic collaborative resource allocation method based on a smart contract as described above are implemented.

[0136] In summary, the present invention provides a multi-role dynamic collaborative resource allocation method, system, terminal and storage medium based on smart contracts, the method comprising: obtaining a target design draft, a current construction progress image and a supervision acceptance result, and pre-processing the target design draft, the current construction progress image and the supervision acceptance result to obtain a construction acceptance result; performing 3D point cloud comparison processing according to the construction acceptance result to obtain a design restoration degree; performing multi-role contribution quantification calculation according to the design restoration degree to obtain a multi-role contribution quantification result; determining target resources, and dynamically allocating resources to the target resources according to the multi-role contribution quantification result to obtain a multi-role resource allocation result. The present invention obtains the construction acceptance result of home improvement construction, and compares and calculates the design restoration degree of the construction result and the expected scheme according to the construction acceptance result, and then quantifies the contribution degree corresponding to each role according to the design restoration degree, and finally realizes the dynamic allocation of target resources according to the contribution degree. Not only does it effectively improve the accuracy of multi-role contribution quantification, but it also ensures the reasonable and effective precise allocation of target resources.

[0137] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or terminal comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or terminal comprising the element.

[0138] Of course, those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware (such as a processor, controller, etc.) through a computer program. The program can be stored in a computer-readable storage medium that can be read by a computer. When the program is executed, it can include the processes in the above-described method embodiments. The computer-readable storage medium can be a memory, a magnetic disk, an optical disk, etc.

[0139] It should be understood that the application of the present invention is not limited to the above examples. For those skilled in the art, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A multi-role dynamic collaborative resource allocation method based on smart contracts, characterized in that: The multi-role dynamic collaborative resource allocation method based on smart contracts includes: Obtaining a target design draft, a current construction progress image, and a supervision acceptance result, and preprocessing the target design draft, the current construction progress image, and the supervision acceptance result to obtain a construction acceptance result; Perform 3D point cloud comparison processing based on the construction acceptance results to obtain the design restoration degree; Performing a multi-role contribution quantification calculation based on the design restoration degree to obtain a multi-role contribution quantification result; Target resources are determined, and dynamic resource allocation is performed on the target resources according to the multi-role contribution quantification result to obtain a multi-role resource allocation result.

2. The multi-role dynamic collaborative resource allocation method based on smart contracts according to claim 1 is characterized in that: The acquiring of the target design draft, the current construction progress image, and the supervision acceptance result, and pre-processing the target design draft, the current construction progress image, and the supervision acceptance result to obtain the construction acceptance result specifically includes: Obtain target design draft, current construction progress image and supervision acceptance results; A hash function is used to perform hash value conversion on the target design draft to obtain the design draft CAD hash value; Collecting images of the current construction progress through IoT devices, wherein the IoT devices include construction site cameras and sensors; Determine a construction detection model, input the current construction progress image into the construction detection model, and output a construction detection result; The construction acceptance result is constructed based on the design draft CAD hash value, the construction inspection result and the supervision acceptance result.

3. The multi-role dynamic collaborative resource allocation method based on smart contracts according to claim 2 is characterized in that: The step of determining a construction detection model, inputting the current construction progress image into the construction detection model, and outputting a construction detection result further includes: Collecting a preset number of home quality inspection pictures, and dividing the data set according to the home quality inspection pictures to obtain a home quality inspection data set, wherein the home quality inspection data set includes a home quality inspection training set and a home quality inspection test set; A pre-trained model is determined, model training is performed on the pre-trained model according to the home quality inspection training set, and model fine-tuning is performed on the pre-trained model according to the home quality inspection test set to obtain a construction inspection model.

4. The multi-role dynamic collaborative resource allocation method based on smart contracts according to claim 2 is characterized in that: The 3D point cloud comparison processing is performed based on the construction acceptance results to obtain the design restoration degree, specifically including: Obtaining the target household object after construction completion in the construction acceptance result, and performing 3D scanning processing on the target household object using a 3D scanning device to obtain 3D point cloud data; Reprocessing the 3D point cloud data to obtain target 3D point cloud data, wherein the reprocessing includes format conversion processing, denoising processing, and data registration processing; Performing feature extraction processing on the target 3D point cloud data to obtain geometric features and topological features of the target household object; The original point cloud data corresponding to the target design draft is obtained, and the original point cloud features corresponding to the original point cloud data are compared with the geometric features and the topological features of the target home object to obtain the design restoration degree.

5. The multi-role dynamic collaborative resource allocation method based on smart contracts according to claim 1 is characterized in that: The multi-role contribution quantification calculation is performed according to the design restoration degree to obtain the multi-role contribution quantification result, specifically including: The dynamic weight algorithm is used to calculate the dynamic weight of each role, wherein the expression of the dynamic weight algorithm is: Among them, ω i (t) is the dynamic weight of each role, t is time, ω i0 is the initial weight of each role, λ is the time decay factor, s ij (t) is the contribution score of role i in task j, and N is the total number of tasks; Obtaining a restoration degree error of the designed restoration degree, and comparing the restoration degree error with a preset threshold; If the restoration error is less than the preset threshold, a contribution quantification model is used to perform multi-role contribution quantification calculation based on the design restoration and the dynamic weights of each role to obtain a multi-role contribution quantification result, wherein the multi-role contribution quantification result includes the design contribution, the construction contribution, and the supervision contribution; The contribution quantification model is expressed as follows: Among them, α i is the total contribution of role i, i is the role, including designer, constructor and supervisor, k is the indicator, n is the total number of indicators, ω ik is the dynamic weight ω of each role i The dynamic weight corresponding to role i in (t), m ik is the design restoration degree of character i, m min，k is the minimum reference value of indicator k, m max，k is the maximum reference value of indicator k.

6. The multi-role dynamic collaborative resource allocation method based on smart contracts according to claim 1 is characterized in that: The multi-role contribution quantification calculation is performed according to the design restoration degree to obtain the multi-role contribution quantification result, and then further includes: When the multi-role contribution quantification result is in a dispute state, a consensus-reaching mechanism is used to update the multi-role contribution quantification result to obtain an updated multi-role contribution quantification result.

7. The multi-role dynamic collaborative resource allocation method based on smart contracts according to claim 5 is characterized in that: The expression of the dynamic resource allocation is: Among them, the V i is the resource allocation result of role i, V is the target resource, α j The sum of all characters' contributions.

8. A multi-role dynamic collaborative resource allocation system based on smart contracts, characterized by: The multi-role dynamic collaborative resource allocation system based on smart contracts includes: A data preprocessing module is used to obtain a target design draft, a current construction progress image, and a supervision acceptance result, and preprocess the target design draft, the current construction progress image, and the supervision acceptance result to obtain a construction acceptance result; A design restoration degree calculation module is used to perform 3D point cloud comparison processing based on the construction acceptance results to obtain the design restoration degree; A multi-role contribution quantification module is used to perform multi-role contribution quantification calculation according to the design restoration degree to obtain a multi-role contribution quantification result; The dynamic resource allocation module is used to determine the target resource and dynamically allocate the target resource according to the multi-role contribution quantification result to obtain the multi-role resource allocation result.

9. A terminal, characterized in that: The terminal includes: a memory, a processor, and a multi-role dynamic collaborative resource allocation program based on a smart contract stored in the memory and runnable on the processor. When the multi-role dynamic collaborative resource allocation program based on a smart contract is executed by the processor, the steps of the multi-role dynamic collaborative resource allocation method based on a smart contract are implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a multi-role dynamic collaborative resource allocation program based on a smart contract. When the multi-role dynamic collaborative resource allocation program based on a smart contract is executed by a processor, the steps of the multi-role dynamic collaborative resource allocation method based on a smart contract are implemented as described in any one of claims 1 to 7.

Images