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

Abstract

The application discloses a kind of multi-role dynamic cooperation resource allocation method, system, terminal and storage medium based on smart contract, the method includes: obtaining target design draft, current construction progress image and supervision acceptance result, and pre-processing, obtain construction acceptance result;According to construction acceptance result, 3D point cloud comparison processing is carried out, and design restoration degree is obtained;According to the design restoration degree, multi-role contribution quantification calculation is carried out, and multi-role contribution quantification result is obtained;Determine target resource, and according to the multi-role contribution quantification result, dynamic resource allocation is carried out to the target resource, and multi-role resource allocation result is obtained.The design restoration degree after construction is calculated by the application, and the contribution degree of each role is quantified according to the design restoration degree, then, according to multi-role contribution quantification result, target resource is allocated, not only effectively improve the accuracy of each role contribution quantification, also effectively improve resource allocation efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to a multi-role dynamic cooperation resource allocation method and system based on a smart contract, a terminal and a computer readable storage medium. BACKGROUND

[0002] In the existing home decoration industry, a designer (providing a design scheme), a constructor (constructing according to the design scheme provided by the designer) and a supervisor (supervising the construction progress and construction effect of the constructor) are usually included, and the resource allocation is performed according to the contribution degrees of these roles (i.e. the designer, the constructor and the supervisor).

[0003] However, the contribution degree calculation of the roles in the construction process of the existing home decoration industry is not accurate in the prior art, so that the resource allocation is uneven and cannot meet the user demand.

[0004] Therefore, the prior art still needs to be improved and developed. SUMMARY

[0005] The main purpose of the present application is to provide a multi-role dynamic cooperation resource allocation method and system based on a smart contract, a terminal and a computer readable storage medium, which aims to solve the problem that the contribution degree calculation of the roles in the construction process of the existing home decoration industry is not accurate, so that the resource allocation is uneven and cannot meet the user demand.

[0006] To achieve the above-mentioned purpose, the present application provides a multi-role dynamic cooperation resource allocation method based on a smart contract, which comprises the following steps:

[0007] 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;

[0008] According to the construction acceptance result, 3D point cloud comparison processing is performed to obtain a design restoration degree;

[0009] According to the design restoration degree, multi-role contribution degree quantitative calculation is performed to obtain a multi-role contribution degree quantitative result;

[0010] Determine a target resource, and perform dynamic resource allocation on the target resource according to the multi-role contribution degree quantitative result to obtain a multi-role resource allocation result.

[0011] Optionally, the multi-role dynamic collaboration resource allocation method based on the smart contract, wherein the target design draft, the current construction progress image and the supervision acceptance result are acquired, and the target design draft, the current construction progress image and the supervision acceptance result are preprocessed to obtain a construction acceptance result, and the construction acceptance result is obtained.

[0012] The target design draft, the current construction progress image and the supervision acceptance result are acquired.

[0013] The target design draft is converted into a hash value by using a hash function to obtain a design draft CAD hash value.

[0014] The current construction progress image is collected by using an IOT device, wherein the IOT device includes a construction site camera and a sensor.

[0015] A construction detection model is determined, the current construction progress image is input into the construction detection model, and a construction detection result is output.

[0016] The construction acceptance result is constructed according to the design draft CAD hash value, the construction detection result and the supervision acceptance result.

[0017] Optionally, the multi-role dynamic collaboration resource allocation method based on the smart contract, wherein the construction detection model is determined, the current construction progress image is input into the construction detection model, and the construction detection result is output, and the method further comprises the following steps:

[0018] A preset number of home quality inspection pictures are collected, and a data set is divided 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-training model is determined, the pre-training model is trained according to the home quality inspection training set, the pre-training model is fine-tuned according to the home quality inspection test set, and a construction detection model is obtained.

[0020] Optionally, the multi-role dynamic collaboration resource allocation method based on the smart contract, wherein the 3D point cloud comparison processing is performed according to the construction acceptance result to obtain a design restoration degree, and the method comprises the following steps:

[0021] A target home object after construction is completed in the construction acceptance result is acquired, and the target home object is processed by using a 3D scanning device to obtain 3D point cloud data.

[0022] 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.

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

[0024] obtain original point cloud data corresponding to the target design draft, and perform 3D point cloud comparison processing on original point cloud features corresponding to the original point cloud data and the geometric features and the topological features of the target home object to obtain a design restoration degree.

[0025] Optionally, the multi-role dynamic collaboration resource allocation method based on a smart contract, wherein the multi-role contribution quantification calculation according to the design restoration degree to obtain a multi-role contribution quantification result specifically includes:

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

[0027]

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

[0029] obtain a restoration error of the design restoration degree, and compare the restoration 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 according to the design restoration degree and the dynamic weight of each role to obtain a multi-role contribution quantification result, wherein the multi-role contribution quantification result includes design contribution degree, construction contribution degree, and supervision contribution degree;

[0031] the expression of the contribution quantification model is:

[0032]

[0033] wherein α i is the total contribution degree of role i, i is a role, including a designer, a constructor, and a supervisor, k is an index, n is the total number of indexes, ω ik is the dynamic weight of each role ω i (t) in the dynamic weight of each role, m ik is the design restoration degree of role i, m min，k is the minimum reference value of index k, and m max，k is the maximum reference value of index k.

[0034] Optionally, the multi-role dynamic collaboration resource allocation method based on a smart contract, wherein the expression of the dynamic resource allocation is:

[0035]

[0036] Wherein, the V i is the resource allocation result of the role i, V is the target resource, and a j is the sum of the contribution degrees of all roles.

[0037] In addition, to achieve the above object, the application further provides a multi-role dynamic collaboration resource allocation system based on a smart contract, wherein the multi-role dynamic collaboration resource allocation system based on a smart contract comprises:

[0038] A data preprocessing module is configured to acquire 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 configured to perform 3D point cloud comparison processing according to the construction acceptance result to obtain a design restoration degree.

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

[0041] A dynamic resource allocation module is configured to determine a target resource, and perform dynamic resource allocation on the target resource according to the multi-role contribution degree quantification result to obtain a multi-role resource allocation result.

[0042] In addition, to achieve the above object, the application further provides a terminal, wherein the terminal comprises a memory, a processor, and a multi-role dynamic collaboration resource allocation program based on a smart contract stored in the memory and executable on the processor, and the multi-role dynamic collaboration resource allocation program based on a smart contract implements the steps of the multi-role dynamic collaboration resource allocation method based on a smart contract when executed by the processor.

[0043] In addition, to achieve the above object, the application further provides a computer readable storage medium, wherein the computer readable storage medium stores a multi-role dynamic collaboration resource allocation program based on a smart contract, and the multi-role dynamic collaboration resource allocation program based on a smart contract implements the steps of the multi-role dynamic collaboration resource allocation method based on a smart contract when executed by a processor.

[0044] In the present application, 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 preprocessed to obtain a construction acceptance result; the construction acceptance result is subjected to 3D point cloud comparison processing to obtain a design restoration degree; the design restoration degree is subjected to multi-role contribution quantification calculation to obtain a multi-role contribution quantification result; a target resource is determined, and the target resource is subjected to dynamic resource allocation according to the multi-role contribution quantification result to obtain a multi-role resource allocation result. The construction acceptance result of home decoration construction is obtained, and the design restoration degree of the construction result and the expected scheme is obtained by comparison calculation according to the construction acceptance result, and then the contribution degree corresponding to each role is quantified according to the design restoration degree, and finally the dynamic allocation of the target resource is realized according to the contribution degree. Not only the accuracy of multi-role contribution quantification is effectively improved, but also the reasonable and effective accurate allocation of the target resource is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 is a flowchart of a preferred embodiment of the multi-role dynamic collaboration resource allocation method based on the smart contract of the present application;

[0046] Figure 2 is a system architecture schematic diagram of a preferred embodiment of the multi-role dynamic collaboration resource allocation method based on the smart contract of the present application;

[0047] Figure 3 is a whole operation flow schematic diagram of a preferred embodiment of the multi-role dynamic collaboration resource allocation method based on the smart contract of the present application;

[0048] Figure 4 is a structure diagram of a preferred embodiment of the multi-role dynamic collaboration resource allocation system based on the smart contract of the present application;

[0049] Figure 5 is a structure diagram of a preferred embodiment of the terminal of the present application. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical scheme and advantages of the present application more clear and definite, the present application will be further described in detail below with reference to the drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0051] In the existing home decoration industry, it usually includes a designer (providing a design scheme), a constructor (constructing according to the design scheme provided by the designer) and a supervisor (supervising the construction progress and construction effect of the constructor), and the resource allocation is performed according to the contribution degree of these roles (i.e. the designer, the constructor and the supervisor).

[0052] However, the contribution degree calculation of the roles in the construction process of the home decoration industry in the prior art is not accurate, thereby leading to uneven resource allocation and failing to meet user demand.

[0053] To solve the above problems, the present application provides a multi-role dynamic collaboration resource allocation method based on smart contract, which combines the contribution degree model with smart contract to quantitatively design the contribution degree weight of construction and supervision, effectively solves the problem of uneven resource allocation, and improves the resource allocation efficiency and accuracy.

[0054] The multi-role dynamic collaboration resource allocation method based on smart contract according to the preferred embodiment of the present application, as shown in Figure 1 The multi-role dynamic collaboration resource allocation method based on smart contract includes the following steps:

[0055] Step S10, 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 preprocessed to obtain the construction acceptance result.

[0056] As shown in Figure 2 In the present application, a data collection layer is provided: the construction progress data (design draft CAD hash value, construction progress image and supervision acceptance result obtained after preprocessing) is collected through IoT devices (IoT devices including construction site cameras, sensors). Moreover, a data synchronization mechanism (real-time on-chain of on-site video collection, sensor data, etc., collaborative AI quality inspection linkage) is also provided in the present application: the design draft version number is bound with the blockchain hash value to ensure the consistency of multi-party data, and the incremental data is stored through IPFS to reduce the storage cost on the chain.

[0057] Specifically, the target design draft, the current construction progress image and the supervision acceptance result are obtained; the target design draft is processed by a hash function for hash value on-chain conversion to obtain a design draft CAD hash value; the current construction progress image is collected through an IOT device, wherein the IOT device includes a construction site camera and a sensor.

[0058] Firstly, the process of data collection and verification, the collected construction progress data includes target design draft, current construction progress image and supervision acceptance result, then, the target design draft and the current construction progress image are pretreated, wherein, the processing process of the target design draft (convert the design draft submission format) is as follows: the CAD / BIM file of the target design draft is converted into a fixed length unique string (such as 64-bit hexadecimal), and the hash value is written into the blockchain. Among them, the conversion method adopts the hash value on-chain conversion processing, and the original data (i.e. the target design draft in the application, which can also be other files, texts) of arbitrary length is converted into design draft CAD hash value through a hash function (such as SHA-256). By converting the target design draft into a hash value on-chain, the data is unique, tamper-proof and traceable.

[0059] For the processing of the current construction progress image: first, the daily construction progress image needs to be obtained (obtained through the camera and AI recognition on site, 3 times of construction progress data are obtained every day, which includes AI quality inspection report). Further, in addition to the 3 times of construction progress data obtained every day, the specific progress of the current construction (specifically, what step of construction is it) can also be obtained through the camera and sensor on the construction site, and the construction personnel who handle each construction link can also be identified through face recognition, and various data such as the amount of materials consumed at present can be identified through AI, so as to calculate the percentage of each construction link in the entire construction progress, the percentage of the quality of the link completed in the design landing, and the proportion of the material used in the total material.

[0060] A predetermined number of home inspection pictures are collected, and a data set is divided according to the home inspection pictures to obtain a home inspection data set, wherein the home inspection data set includes a home inspection training set and a home inspection test set; a pre-training model is determined, the pre-training model is trained according to the home inspection training set, and the pre-training model is fine-tuned according to the home inspection test set to obtain a construction detection model. Determine the construction detection model, input the current construction progress image into the construction detection model, and output the construction detection result; the construction acceptance result is obtained according to the design draft CAD hash value, the construction detection result and the supervision acceptance result.

[0061] Further, after the current construction progress image is collected in the application, it is necessary to determine whether the current construction result meets the requirements, and the detection of the construction result in the application includes two parts, the first part is to identify and judge the collected current construction progress image through the pre-trained large model, so as to determine whether the current construction result meets the requirements. In addition, the supervision data result of the supervisor is also received in the application, and the result of the large model identification is combined with the supervision data result collected by the supervisor, so as to obtain the specific construction acceptance result.

[0062] Among them, for the process of identifying and judging according to the collected current construction progress image by the pre-trained large model, the AI quality inspection algorithm is used in the application, and the specific implementation steps are as follows: 1, obtaining a pre-trained model: the application 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 10000 home quality inspection pictures (i.e. the preset number of home quality inspection pictures in the application) for comparison and adjustment, after model training and fine-tuning, a construction detection model is obtained, and through subsequent experimental determination, the test level accuracy of the final construction detection model reaches more than 96%. 3, edge deployment: after the construction detection model is constructed, the construction detection model is loaded to NVIDA Jetson Nano, which is deployed on the edge, and the construction detection model deployed on the edge takes ≤0.5 seconds to infer.

[0063] For example, the construction detection model deployed on the edge can monitor the following items: 1, project name: ceramic tile hollow; detection item: whether the hollow area is ≤5%; detection accuracy is 98%. 2, project name: wall flatness; detection item: whether 2M ruler deviation is ≤2mm; detection accuracy is 95%. 3, project name: water and electricity wiring; detection item: whether it meets GB50303-2015 standard; detection accuracy is 100%.

[0064] The second part is the process of supervision and acceptance: the supervisor needs to detect 5 key nodes in the construction process (including water and electricity, mud and wood, and paint), and obtain the supervision and acceptance result.

[0065] After obtaining the construction detection result output by the construction detection model and the supervision and acceptance result uploaded by the supervisor, the design draft CAD hash value can be combined, and the three together constitute the construction acceptance result, which can be used to calculate the design restoration degree of construction.

[0066] Step S20, according to the construction acceptance result, 3D point cloud comparison processing is carried out, and the design restoration degree is obtained.

[0067] For the design restoration degree calculation of the construction acceptance result, the application is realized by 3D point cloud comparison, which mainly judges the error between the target home object after construction in the construction acceptance result and the designed home object in the design draft. The error tolerance is generally set to ±2% (generally, the pilot standard rate is about 95%).

[0068] Specifically, the target home object after construction is obtained in the construction acceptance result, and a 3D scanning device is used to perform 3D scanning processing on the target home 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; the target 3D point cloud data is subjected to feature extraction processing to obtain geometric features and topological features of the target home object; the original point cloud data corresponding to the target design draft is obtained, and 3D point cloud comparison processing is performed on the original point cloud features corresponding to the original point cloud data and the geometric features and topological features of the target home object to obtain a design restoration degree.

[0069] The specific process of 3D point cloud comparison processing is as follows: 1. Data acquisition: using a 3D scanning device to scan the target home object after construction to obtain its 3D point cloud data. 2. Format conversion: converting the scanned 3D point cloud data into a unified format such as PLY, OBJ, etc. to obtain first 3D point cloud data for subsequent processing. 3. Denoising processing: using filtering algorithms such as Gaussian filtering, median filtering, etc. to remove noise points in the point cloud data to obtain second 3D point cloud data. 4. Data registration: if there are multi-angle scanning data, use ICP algorithm (Iterative Closest Point, ICP algorithm is a classic algorithm for point cloud registration, widely used in 3D scanning, robot navigation, SLAM (Simultaneous Localization and Mapping) and other fields. The core idea of ICP algorithm is to iteratively calculate the spatial position between two point clouds until they match as much as possible) to register point cloud data from different angles to the same coordinate system to obtain target 3D point cloud data. 5. Extracting geometric features and topological features of target 3D point cloud data. 6. Point cloud comparison: comparing the original point cloud features in the target design draft with the geometric features and topological features of the target home object (including distance, feature, deformation, etc. Parameters are compared). 6. Visual analysis: display the comparison results through 3D visualization software, so that users can intuitively observe the differences between design and reality. 7. Quantitative evaluation: according to the comparison results of distance, feature similarity, etc., set a threshold to judge whether the design restoration degree meets the requirements.

[0070] In addition, the present application can also include construction progress deviation and material consumption monitoring in the calculation of design restoration degree, wherein 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 identifies the amount of building materials, whether the error is ≤3%, which can be deployed through NVIDIA Jetson device to identify building material types, quantities and other data.

[0071] Step S30, according to the design reduction degree, the multi-role contribution degree quantification calculation is carried out, and the multi-role contribution degree quantification result is obtained.

[0072] Specifically, the dynamic weight algorithm is used to calculate the dynamic weight of each role, and the expression of the dynamic weight algorithm is: Wherein, ω i (t) is the dynamic weight of each role, t is the time, ω i0 is the initial weight of each role, λ is the time attenuation factor, s ij (t) is the contribution degree score of role i in task j, and N is the total number of tasks. The reduction error of the design reduction degree is obtained, and the reduction error is compared with the preset threshold value; if the reduction error is less than the preset threshold value, the contribution degree quantification model is used to calculate the multi-role contribution degree quantification according to the design reduction degree and the dynamic weight of each role, and the multi-role contribution degree quantification result is obtained, wherein the multi-role contribution degree quantification result includes design contribution degree, construction contribution degree and supervision contribution degree; the expression of the contribution degree quantification model is: Wherein, α i is the total contribution degree of role i, i is the role, including the designer, the constructor and the supervisor, k is the index, n is the total number of indexes, ω ik is the dynamic weight corresponding to role i, m ik is the design reduction degree of role i, m min，k is the minimum reference value of index k, and m max，k is the maximum reference value of index k.

[0073] In the specific implementation process, the home decoration construction scheme is introduced in the present application, generally, the design contribution degree can be calculated according to the following formula: α D =0.4×design reduction degree+0.6×score result; wherein, α D is the design contribution degree, the weight is added according to the hard decoration, the soft decoration and each function area, and the proportion of the score value in the whole design is recorded as the design reduction degree. The design contribution degree can be obtained by combining the design reduction degree and the score result uploaded by the user. The score result uploaded by the user can be the score result of the owner according to the satisfaction table, the problem options are set according to the effect picture delivered to the owner and the function, space scale, color, lighting and other angles after completion, each option is given different score value, and finally the score value of each problem is weighted and averaged to obtain the score result uploaded by the user. Generally, the construction contribution degree can be calculated according to the following formula: α C =0.5×duration compliance rate+0.5×cost control rate; wherein, α C is the construction contribution degree; in addition, the calculation expression of the duration compliance rate is: The expression of the cost control rate is:

[0074] Since the contribution level can change due to variations in weights (including design weight, construction weight, and supervision weight; for example, the design weight will decrease if the design does not meet requirements, and the construction weight will increase if the construction period is completed ahead of schedule), this invention employs a dynamic weighting algorithm to calculate the dynamic weights corresponding to different roles. The expression is as follows: Where, ω i (t) represents the dynamic weights of each role, where t is time and ω is the dynamic weight. i0 Here are the initial weights for each role, λ is the time decay factor, and s ij (t) represents 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 can be dynamically calculated. The mathematical model for the contribution calculation is as follows (i.e., the contribution quantification model in this invention): ω ik Let ω be the dynamic weight corresponding to role i (e.g., design weight = 0.4, construction weight = 0.5, supervision weight = 0.1), where ω ik For the preset weights and Σω ik =1.

[0076] The dynamic adjustment rules for weights are as follows: 1. Scoring results affect weights: for every 1-star decrease, the designer's weight decreases by 10%; for every 1-star increase, the designer's weight increases by 10%. 2. For every day the construction period is completed ahead of schedule, the construction team's weight increases by 5%; for every day the construction period is delayed, the construction team's weight decreases by 5%. 3. If the supervisor's acceptance fails (after obtaining the supervisor's acceptance result, it is still necessary to review the supervisor's acceptance result), the supervisor's weight is reset to zero.

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

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

[0079] like Figure 2 As shown, this invention also includes a consensus-reaching mechanism (i.e. Figure 2(Consensus optimization mechanism in the code): When there is a dispute over the contribution coefficient, the PBFT consensus mechanism is activated to update the allocation status based on the verification results of the majority of nodes. The consensus optimization mechanism includes: 1. Using PBFT consensus to verify contribution data, with the effect of fault tolerance rate ≥33%; 2. Data on-chain latency ≤2 seconds (better than the 5 seconds of traditional BFT).

[0080] In its specific implementation, this invention takes home decoration construction as an example, and automatically executes the payment based on a smart contract. The payment triggering conditions are shown in Table 1 below:

[0081] Table 1: Payment Triggering Conditions for Each Stage

[0082]

[0083] Furthermore, this invention also includes a contribution adjustment mechanism, wherein the expression for the historical decay of contribution is: in, The historical average contribution level is calculated using the average of the past 12 months. Additionally, this invention includes a performance-based elimination system: construction teams with a quarterly rating of <4 stars are prohibited from accepting orders for 6 months.

[0084] Step S40: 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.

[0085] Specifically, the expression for the dynamic resource allocation is: Wherein, the V i Let V be the resource allocation result for role i, and α be the target resource. j The sum of contributions from all characters.

[0086] The following is an example (for a pilot project):

[0087] Existing technologies suffer from the following problems: 1. Rigid traditional resource allocation: Fixed-ratio resource allocation (e.g., 20% for design, 70% for construction, and 10% for supervision) fails to reflect actual contributions, leading to uneven resource distribution and high dispute rates; 2. Lack of data transparency: Construction progress and quality acceptance rely on manual records, which are easily tampered with. By adopting the multi-role dynamic collaborative resource allocation method based on smart contracts of 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 Allocation Table for Each Role

[0089]

[0090] like Figure 3As shown, the specific operation process of the embodiment of the present application is as follows: 1, the customer signs a contract and pays a prepayment to the contract address (the contract agrees to the common management account); 2, the designer submits a scheme, and the construction team uploads the progress according to the node (each work node completed by the project, not less than several nodes agreed in the contract). 3, after supervision and acceptance, the contract allocates resources according to the contribution degree; when there is objection to resource allocation, dynamic weight calculation is carried out under the guarantee of consensus optimization mechanism, and resources are re-allocated. The efficiency and accuracy of resource allocation are effectively improved, and the resource allocation time is shortened from 7 days to 2 hours, and the customer complaint rate is reduced by 65%.

[0091] The technical effects of the present application include: 1, the intelligent contract executes resource allocation error rate from 15% to 3%; 2, when the resource allocation is uneven, the re-allocation efficiency of the resource is shortened from 30 days to 3 days; 3, the cooperation efficiency is improved by 40%.

[0092] In summary, the innovation points of the present application include: 1, dynamic contribution degree model: quantifying the contribution of the role through design restoration degree, project completion rate, acceptance pass rate, etc.; 2, intelligent contract automatically executes resource allocation: real-time resource allocation based on contribution weight, trigger conditions include project node, quality acceptance; 3, consensus reaching mechanism: when the contribution coefficient is disputed, start the PBFT consensus reaching mechanism, and update the allocation state according to the majority node verification result.

[0093] The present application discloses a kind of multi-role dynamic cooperation resource allocation method based on smart contract, by quantifying the contribution weight of design, construction, supervision, solve the technical problems that real-time resource allocation is poor in multi-role cooperation scene due to data island, cooperation state is not verifiable, dynamic adjustment is lagging, the present application can realize resource allocation error rate ≤3%, resource re-allocation period ≤3 days, applicable to multi-role cooperation scene such as building, e-commerce.

[0094] Further, as Figure 4 As shown, based on the above multi-role dynamic cooperation resource allocation method based on smart contract, the present application also correspondingly provides a kind of multi-role dynamic cooperation resource allocation system based on smart contract, wherein the multi-role dynamic cooperation resource allocation system based on smart contract includes:

[0095] Data preprocessing module 51 is used to obtain target design, current construction progress image and supervision and acceptance result, and pre-processes the target design, the current construction progress image and the supervision and acceptance result to obtain construction acceptance result;

[0096] Design restoration degree calculation module 52 is used to carry out 3D point cloud comparison processing according to the construction acceptance result to obtain design restoration degree;

[0097] The multi-role contribution quantification module 53 is configured to perform multi-role contribution quantification calculation according to the design restoration degree, and obtain a multi-role contribution quantification result.

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

[0099] Further, as shown in the figure, Figure 5 Based on the above-mentioned multi-role dynamic collaboration resource allocation method and system based on smart contract, the application further provides a terminal, which comprises a processor 10, a memory 20 and a display 30. Figure 5 Only part of the components of the terminal are shown, but it should be understood that all the shown components are not required, and more or less components can be alternatively implemented.

[0100] The memory 20 can be an internal storage unit of the terminal in some embodiments, such as a hard disk or a memory of the terminal. The memory 20 can also be an external storage device of the terminal in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 20 can include both the internal storage unit and the external storage device of the terminal. The memory 20 is used to store application software and various data installed on the terminal, such as program codes of the terminal, etc. The memory 20 can also be used to temporarily store data that has been output or will be output. In an embodiment, the memory 20 stores a multi-role dynamic collaboration resource allocation program 40 based on smart contract, which can be executed by the processor 10, so as to implement the multi-role dynamic collaboration resource allocation method based on smart contract in the application.

[0101] The processor 10 can be a central processing unit (CPU), a microprocessor or other data processing chip in some embodiments, which is used to run program codes or process data stored in the memory 20, such as to execute the multi-role dynamic collaboration resource allocation method based on smart contract, etc.

[0102] The display 30 can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, etc. in some embodiments. The display 30 is used to display information at the terminal and to display a visualized user interface.

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

[0104] 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;

[0105] Perform 3D point cloud comparison processing according to the construction acceptance result to obtain a design restoration degree;

[0106] Perform multi-role contribution quantification calculation according to the design restoration degree to obtain a multi-role contribution quantification result;

[0107] Determine a target resource, and perform dynamic resource allocation on the target resource according to the multi-role contribution quantification result to obtain a multi-role resource allocation result.

[0108] The obtaining of the target design draft, the current construction progress image, and the supervision acceptance result, and the preprocessing of the target design draft, the current construction progress image, and the supervision acceptance result to obtain the construction acceptance result specifically include:

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

[0110] Perform hash value on-chain conversion processing on the target design draft by using a hash function to obtain a design draft CAD hash value;

[0111] Collect a current construction progress image through an IOT device, wherein the IOT device includes a construction site camera and a sensor;

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

[0113] Construct a construction acceptance result according to the design draft CAD hash value, the construction detection result, and the supervision acceptance result.

[0114] The determining of the construction detection model, and the inputting of the current construction progress image into the construction detection model to output the construction detection result further include:

[0115] collecting a preset number of home quality inspection pictures, and performing dataset division according to the home quality inspection pictures to obtain a home quality inspection dataset, wherein the home quality inspection dataset includes a home quality inspection training set and a home quality inspection test set;

[0116] determining a pre-training model, performing model training on the pre-training model according to the home quality inspection training set, and performing model fine-tuning on the pre-training model according to the home quality inspection test set to obtain a construction detection model.

[0117] The 3D point cloud comparison processing according to the construction acceptance result to obtain the design restoration degree specifically includes:

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

[0119] performing reprocessing on the 3D point cloud data to obtain target 3D point cloud data;

[0120] obtaining 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.

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

[0122] The reprocessing on 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 processing on the first 3D point cloud data by using a filtering algorithm to obtain second 3D point cloud data, wherein the filtering algorithm includes Gaussian filtering and median filtering;

[0125] performing data registration processing on the second 3D point cloud data by using an ICP algorithm to obtain target 3D point cloud data.

[0126] The obtaining of the original point cloud data and the 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 home object;

[0128] Obtain the original point cloud data corresponding to the target design draft, and perform 3D point cloud comparison processing on the original point cloud features corresponding to the original point cloud data and the geometric features and the topological features of the target home object to obtain a design restoration degree.

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

[0130] Obtain a restoration error of the design restoration degree, and compare the restoration error with a preset threshold value.

[0131] If the restoration error is less than the preset threshold value, a contribution quantification model is used to perform multi-role contribution quantification calculation according to the design restoration degree and the dynamic weights of the roles to obtain a multi-role contribution quantification result, wherein the multi-role contribution quantification result includes design contribution degree, construction contribution degree and supervision contribution degree.

[0132] The expression of the contribution quantification model is:

[0133]

[0134] wherein, alpha i is the total contribution degree of role i, i is a role, including a designer, a constructor and a supervisor, k is an index, n is the total number of indexes, omega ik is the dynamic weight corresponding to role i, m ik is the design restoration degree of role i, m min，k is the minimum reference value of index k, m max，k is the maximum reference value of index k.

[0135] The application further provides a computer readable storage medium, wherein the computer readable storage medium stores a multi-role dynamic collaboration resource allocation program based on a smart contract, and the multi-role dynamic collaboration resource allocation program based on the smart contract, when executed by a processor, implements the steps of the multi-role dynamic collaboration resource allocation method based on the smart contract.

[0136] To sum up, the application provides a multi-role dynamic cooperation resource allocation method and system based on a smart contract, a terminal and a storage medium, the method comprising: acquiring 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; 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 a target resource, and performing dynamic resource allocation on the target resource according to the multi-role contribution quantification result to obtain a multi-role resource allocation result. The application acquires the construction acceptance result of home decoration construction, and performs comparison calculation on the construction acceptance result to obtain the design restoration degree of the construction result and the expected scheme, and then quantifies the contribution degree of each role according to the design restoration degree, and finally realizes dynamic allocation of the target resource according to the contribution degree. Not only the accuracy of multi-role contribution quantification is effectively improved, but also the target resource is reasonably and effectively allocated accurately.

[0137] It should be noted that in this document, the terms "comprising", "including", or any other variant thereof are intended to cover a non-exclusive inclusion, such that processes, methods, articles, or terminals that comprise a list of elements do not only include those elements, but can also include other elements that are not expressly listed or inherent to such processes, methods, articles, or terminals. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article, or terminal that includes the element.

[0138] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing relevant hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable computer-readable storage medium, and the program can include the processes of the above-mentioned method embodiments when executed. The computer-readable storage medium can be a memory, a magnetic disc, an optical disc, etc.

[0139] It should be understood that the application is not limited to the above examples, and those skilled in the art can improve or change it according to the above description, and all these improvements and changes should belong to the protection scope of the claims of the application.

Claims

1. A method for multi-role dynamic collaboration resource allocation based on smart contract, characterized in that, The multi-role dynamic cooperation resource allocation method based on the smart contract comprises the following steps: 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; According to the construction acceptance result, 3D point cloud comparison processing is performed to obtain a design restoration degree; According to the design restoration degree, multi-role contribution quantification calculation is performed to obtain a multi-role contribution quantification result; A target resource is determined, and dynamic resource allocation is performed on the target resource according to the multi-role contribution quantification result to obtain a multi-role resource allocation result; The multi-role contribution quantification calculation according to the design restoration degree to obtain the multi-role contribution quantification result specifically comprises the following steps: A dynamic weight algorithm is used to calculate the dynamic weight of each role, wherein the expression of the dynamic weight algorithm is: ； wherein, is a dynamic weight for each role, is a time, is an initial weight for each role, is a time decay factor, is a role contribution score for a task , and is a total number of tasks; Obtain the restoration error of the design restoration degree, and compare the restoration error with a preset threshold value; If the restoration error is less than the preset threshold value, a contribution quantification model is used to perform multi-role contribution quantification calculation according to the design restoration degree and the dynamic weight of each role to obtain a multi-role contribution quantification result, wherein the multi-role contribution quantification result comprises a design contribution degree, a construction contribution degree, and a supervision contribution degree; The expression of the contribution quantification model is: ； wherein, is the total contribution degree of the role, is the design restoration degree of the role, is the role, including a designer, a constructor, and a supervisor, is the index, is the total number of the indexes, is the dynamic weight of the role is the dynamic weight of the role corresponding to the role, is the design restoration degree of the role, is the design restoration degree of the role, is the minimum reference value of the index is the minimum reference value of the index, is the maximum reference value of the index is the maximum reference value of the index. 2.The smart contract-based multi-role dynamic collaboration resource allocation method of claim 1, wherein, 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 preprocessed to obtain a construction acceptance result, specifically comprising the following steps: Obtain a target design draft, a current construction progress image, and a supervision acceptance result; A hash function is used to perform hash value on-chain conversion processing on the target design draft to obtain a design draft CAD hash value; A current construction progress image is collected through an IOT device, wherein the IOT device comprises a construction site camera and a sensor; A construction detection model is determined, and the current construction progress image is input into the construction detection model to output a construction detection result; The construction acceptance result is constructed according to the design draft CAD hash value, the construction detection result, and the supervision acceptance result. 3.The smart contract-based multi-role dynamic collaboration resource allocation method of claim 2, wherein, Before the construction detection model is determined and the current construction progress image is input into the construction detection model to output a construction detection result, the following steps are further included: A preset number of home quality inspection pictures are collected, and a home quality inspection dataset is obtained through dataset division according to the home quality inspection pictures, wherein the home quality inspection dataset comprises a home quality inspection training set and a home quality inspection test set; A pre-training model is determined, the pre-training model is trained according to the home quality inspection training set, and the pre-training model is fine-tuned according to the home quality inspection test set to obtain a construction detection model. 4.The smart contract-based multi-role dynamic collaboration resource allocation method of claim 2, wherein, The 3D point cloud comparison processing according to the construction acceptance result to obtain the design restoration degree specifically comprises the following steps: A target home 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 home 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; The target 3D point cloud data is subjected to feature extraction processing to obtain geometric features and topological features of the target home object; Original point cloud data corresponding to the target design draft is obtained, and 3D point cloud comparison processing is performed on original point cloud features corresponding to the original point cloud data and the geometric features and the topological features of the target home object to obtain a design restoration degree. 5.The smart contract based multi-role dynamic collaboration resource allocation method of claim 1, wherein, The design restoration degree is used to perform multi-role contribution quantification calculation to obtain a multi-role contribution quantification result, and then the method further includes: When the multi-role contribution quantification result is in a controversial state, a consensus reaching mechanism is used to update the multi-role contribution quantification result to obtain an updated multi-role contribution quantification result. 6.The smart contract based multi-role dynamic collaboration resource allocation method of claim 1, wherein, The expression of the dynamic resource allocation is: ； Among them, the For the role The results of resource allocation For target resources, The sum of contributions from all characters. 7.A multi-role dynamic collaboration resource allocation system based on smart contract, characterized in that, The multi-role dynamic collaboration resource allocation system based on the smart contract is applied to the multi-role dynamic collaboration resource allocation method based on the smart contract in any one of claims 1-6, and the multi-role dynamic collaboration resource allocation system based on the smart contract includes: A data preprocessing module is configured to obtain a target design draft, a current construction progress image, and a supervision and acceptance result, and to preprocess the target design draft, the current construction progress image, and the supervision and acceptance result to obtain a construction acceptance result; A design restoration degree calculation module is configured to perform 3D point cloud comparison processing on the construction acceptance result to obtain a design restoration degree; A multi-role contribution quantification module is configured to perform multi-role contribution quantification calculation on the design restoration degree to obtain a multi-role contribution quantification result; A dynamic resource allocation module is configured to determine a target resource, and to perform dynamic resource allocation on the target resource according to the multi-role contribution quantification result to obtain a multi-role resource allocation result.

8. A terminal, characterized by comprising: The terminal includes a memory, a processor, and a multi-role dynamic collaboration resource allocation program based on the smart contract stored on the memory and executable on the processor, and the multi-role dynamic collaboration resource allocation program based on the smart contract implements the steps of the multi-role dynamic collaboration resource allocation method based on the smart contract in any one of claims 1-6 when executed by the processor.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a multi-role dynamic collaboration resource allocation program based on the smart contract, and the multi-role dynamic collaboration resource allocation program based on the smart contract implements the steps of the multi-role dynamic collaboration resource allocation method based on the smart contract in any one of claims 1-6 when executed by the processor.

Images