Generalization processing protection method, device and system of cloud engineering quotation system

Abstract

The invention relates to the technical field of project quotation, in particular to a generalization processing protection method, device and system for a cloud project quotation system, and the method comprises the steps: obtaining project list information of all project projects which need to be subjected to batch project quotation and policy document information of the corresponding project projects, forming a project data set, obtaining the quotation error of each quotation task, and recording the system response time of each quotation task; determining a dimension reduction efficiency coefficient of each quotation task; determining a resource scheduling coefficient of each quotation task; and performing hierarchical scheduling processing on different quotation tasks based on the resource scheduling coefficient. According to the method, dynamic priority scheduling can be realized, the average response speed of the quotation task is improved by identifying an emergency quotation task demand and implementing inclined supply of computing resources for a key quotation task, and efficient parallel operation of a complex quotation task is realized on the premise of ensuring data security.

Description

Technical Field

[0001] The present application relates to the technical field of engineering quotation, and in particular to a generalized processing protection method, device and system for a cloud-based engineering quotation system. Background Art

[0002] With the deepening of digital transformation in the engineering industry, the cloud-based engineering quotation system can integrate market dynamic data and historical data through elastic computing and centralized storage capabilities, realize real-time information updating and sharing, and solve the problem of traditional engineering cost information islands.

[0003] When existing cloud-based engineering quotation systems process multidimensional data in batch engineering projects, they lack the ability to generalize and integrate multimodal data, and the strong coupling and high redundancy between features lead to an explosion in the feature space dimension. At the same time, the direct participation of raw data in calculations can easily expose sensitive information, which leads to excessive consumption of computing resources and delays in real-time quotation responses. It is impossible to balance computing efficiency and feature interpretability while ensuring data security. Summary of the Invention

[0004] In order to solve the above technical problems, a generalized processing protection method, device and system for a cloud-based engineering quotation system are provided to solve the existing problems.

[0005] The solution to the technical problem of this application is to provide a generalized processing protection method, device and system for a cloud-based engineering quotation system, including the following steps:

[0006] In a first aspect, an embodiment of the present application provides a generalized processing protection method for a cloud-based engineering quotation system, the method comprising the following steps:

[0007] After converting the data types of the project list information and the corresponding project policy documents of all projects that require batch project quotations, a project data set is formed. Quotations are then generated for each project, the quotation error for each quotation task is calculated, and the system response time for each quotation task is recorded.

[0008] Perform dimensionality reduction analysis on the engineering data set, extract the principal components, analyze the importance of different principal components corresponding to each quotation task, and their contribution to the original data information, and determine the dimensionality reduction efficiency coefficient of each quotation task;

[0009] Determine the resource scheduling coefficient of each quotation task by combining the correlation between the system response time of each quotation task and the dimensionality reduction efficiency coefficient, as well as the distribution density of the dimensionality reduction efficiency coefficients between different quotation tasks and the dimensionality reduction efficiency coefficient;

[0010] Based on the resource scheduling coefficient, different quotation tasks are scheduled in different levels.

[0011] Preferably, the quotation error is obtained by:

[0012] The cloud-based engineering quotation system predicts the engineering quotation for each project and obtains the total quotation amount for the quotation task corresponding to each project;

[0013] The calculation formula for the quotation error of each quotation task is:

[0014] Preferably, performing dimensionality reduction analysis on the engineering data set and extracting principal components includes: using the PCA method to perform dimensionality reduction on all data in the engineering data set of each quotation task, and extracting the eigenvector and variance contribution rate of each principal component.

[0015] Preferably, the further measurement process of the importance is: taking the bidding error of each bidding task and the eigenvectors of all principal components as inputs of the random forest model to obtain the importance score of each principal component.

[0016] Preferably, the dimension reduction efficiency coefficient is the sum of the products of the importance scores and the variance contribution rates of all principal components in each quotation task.

[0017] Preferably, the related changes are further measured by regression coefficients, and the specific process is:

[0018] The system response time of each quotation task and the dimension reduction efficiency coefficient are combined into a two-dimensional array;

[0019] Perform linear regression analysis on the two-dimensional arrays corresponding to all quotation tasks to obtain the regression coefficients.

[0020] Preferably, determining the resource scheduling coefficient of each quotation task includes:

[0021] Clustering the dimension reduction efficiency coefficients of all quotation tasks to obtain the local density corresponding to each quotation task; performing positive mapping on the dimension reduction efficiency coefficients;

[0022] The resource scheduling coefficient is the product of the forward mapping result corresponding to each bidding task, the regression coefficient, and the local density.

[0023] Preferably, the hierarchical scheduling of different quotation tasks includes:

[0024] Based on the resource scheduling coefficients of all quotation tasks, a kernel density estimation curve is constructed. The kernel density estimation curve is used to calculate the resource scheduling coefficients corresponding to when the cumulative distribution function reaches a preset first value and a preset second value, respectively, which are recorded as the first split threshold and the second split threshold, wherein the preset second value is greater than the preset first value;

[0025] Based on the first segmentation threshold and the second segmentation threshold, the multi-level feedback queue is divided into a high priority queue, a medium priority queue, and a low priority queue;

[0026] Assign quotation tasks with different resource scheduling coefficients to corresponding priority teams for resource scheduling.

[0027] In a second aspect, an embodiment of the present application further provides a generalized processing protection device for a cloud-based engineering quotation system, wherein the device stores a computer program, and when the computer program is executed by a processor, the steps of any one of the generalized processing protection methods for a cloud-based engineering quotation system described above are implemented.

[0028] In a third aspect, an embodiment of the present application also provides a generalized processing protection system for a cloud-based engineering quotation system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the system implements the steps of any one of the above-mentioned generalized processing protection methods for a cloud-based engineering quotation system.

[0029] This application has at least the following beneficial effects:

[0030] This application reduces the dimensionality of the data in the high-dimensional space of each quotation task, extracts the principal components, analyzes the importance characteristics of different principal components, and the original information volume contained in the principal components, and calculates the dimensionality reduction efficiency coefficient of each quotation task. Its beneficial effect is that it takes into account the influence of the information contained in the data in the low-dimensional space after dimensionality reduction on the evaluation of the final project quotation, reflects the information interpretation ability of high-dimensional data after dimensionality reduction, and can provide high information density and low redundancy information interpretation ability for project quotation while eliminating the direct exposure of original sensitive data, balancing the dual needs of computing efficiency and privacy protection; clustering the dimensionality reduction efficiency coefficients of all quotation tasks, dividing quotation tasks with similar dimensionality reduction efficiency into one category, and then through the correlation changes between the dimensionality reduction efficiency coefficient and the system response time, to reflect the high dimensionality reduction efficiency. The impact of the quotation task with a coefficient on the real-time response delay is determined; the resource scheduling coefficient of each quotation task is determined, which has the beneficial effect of taking into account the dynamic balance between dimensionality reduction of high-dimensional data and resource competition, eliminating the monopoly of resources by extreme quotation tasks, and identifying high-value quotation tasks and resource-intensive job tasks by integrating dimensionality reduction efficiency and cluster density characteristics, effectively preventing extremely complex quotations from monopolizing computing resources; based on the resource scheduling coefficient, different quotation tasks are hierarchically scheduled, which has the beneficial effect of dividing the multi-level feedback queues into three categories of high, medium and low priority queues to achieve dynamic priority scheduling, and by identifying urgent quotation task requirements, implementing a tilted supply of computing resources for key quotation tasks, thereby improving the average response speed of quotation tasks, and achieving efficient parallel computing of complex quotation tasks under the premise of ensuring data security. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The generalized processing protection method of the cloud engineering quotation system of the present application is further described in detail below with reference to the accompanying drawings.

[0032] Figure 1 A flowchart of the steps of the generalized processing protection method of the cloud engineering quotation system provided in the embodiment of the present application;

[0033] Figure 2 A flowchart of the steps of the method for obtaining the resource scheduling coefficient of each quotation task provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] To make the objectives, technical solutions, and advantages of this application more clearly understood, the following, in conjunction with the accompanying drawings and implementation examples, further describes in detail the generalized processing and protection method, device, and system for the cloud-based engineering quotation system proposed in this application. It should be understood that the specific embodiments described herein are merely for the purpose of explaining this application and are not intended to limit this application.

[0035] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0036] See also Figure 1 , which shows a flowchart of the steps of a generalized processing protection method for a cloud engineering quotation system provided by an embodiment of the present application, the method includes the following steps:

[0037] Step 1: After converting the data types of the project list information of all projects that require batch engineering quotations and the policy document information of their corresponding projects, a project data set is formed. Then, engineering quotations are made for each project, the quotation error of each quotation task is calculated, and the system response time of each quotation task is recorded.

[0038] Extract the project list information and corresponding project policy document information of all projects that require batch project quotation from the cloud-based project quotation system. Based on the project list information and policy information, quote all projects through the cloud-based project quotation system. Calculate the quotation error for each quotation task based on the total quotation of each project and the actual cost of the corresponding project. Record the system response time of the cloud-based project quotation system for each quotation task. The quotation error is calculated as follows:

[0039] It should be noted that the project list information includes but is not limited to material properties, construction parameters, and environmental variables. Material properties include categorical data such as steel brand and concrete water resistance grade; construction parameters include template turnover times and machine shift combinations, such as 2 excavators and 3 mixers, and other numerical time series data; environmental variables include document descriptions of the geological conditions of the project location and temperature and humidity data of the climate zone in which it is located; secondly, policy document information includes the environmental tax adjustment coefficients for different materials or construction processes contained in the environmental tax coefficient PDF text, as well as regional quota difference table data, which describes the quota adjustments for labor costs, material costs, etc. in different regions.

[0040] Since the data types of project list information and its policy information are inconsistent, all the acquired data are preprocessed as follows:

[0041] Hash coding maps text descriptions, category labels, and discrete values into fixed-dimensional numerical vectors, eliminating semantic differences and ensuring consistency in the feature space. This process not only ensures data uniformity but also protects data privacy through hash coding, preventing direct exposure of original sensitive data and enhancing data security.

[0042] For information data such as policy documents and geological reports, a global vectorization strategy based on word frequency statistics uniformly represents the content as a standardized bag-of-words vector, preserving the density of key information.

[0043] For numerical data, we combine binning and discretization with equal-frequency segmentation to convert it into discrete interval numbers aligned with the hash coding dimension, ensuring that the numerical distribution characteristics are preserved.

[0044] After all the data are converted, they are standardized and formed into engineering data sets. Through the above processing process, not only the processability of the data is improved, but also the security risks of sensitive data during transmission and storage are reduced, thus ensuring the security of the data.

[0045] In this embodiment, Z-score normalization is used for processing, wherein Z-score normalization is a well-known technology and will not be described in detail here.

[0046] Therefore, the engineering dataset and quotation error of each quotation task are obtained, as well as the system response time of each quotation task.

[0047] Step 2: Perform dimensionality reduction analysis on the engineering data set, extract the principal components, analyze the importance of different principal components corresponding to each quotation task, and their contribution to the original data information, and determine the dimensionality reduction efficiency coefficient of each quotation task.

[0048] Due to the strong coupling and high redundancy between the data in the engineering dataset, for example, the concrete strength has a strong positive correlation with the cement grade and aggregate particle size, and the dynamic correlation between the construction process parameters and the ambient temperature and humidity, it will lead to the explosion of feature space dimensions and information overlap, resulting in problems such as excessive consumption of computing resources and delays in real-time quotation response, resulting in the collected data showing complex distribution characteristics with high noise and low interpretability.

[0049] Based on the above analysis, a dimensionality reduction analysis is performed on the engineering dataset, specifically:

[0050] Perform dimensionality reduction on all data in the engineering dataset for each quotation task, and extract the eigenvectors and variance contribution rates of each principal component;

[0051] In this embodiment, the principal component analysis (PCA) method is used for dimensionality reduction. The PCA method is a well-known technology and will not be described in detail here. The first plurality of principal components with cumulative variance contribution rates greater than or equal to 85% are extracted. As other implementation methods, the implementer can set them according to actual conditions.

[0052] It should be noted that by extracting principal components through dimensionality reduction, it is ensured that the low-dimensional space after dimensionality reduction can not only retain key business information, but also be generalized to be applicable to multi-dimensional dynamically changing quotation scenarios. The PCA method extracts the orthogonal projection direction with the largest variance from massive heterogeneous data, and maps high-dimensional features to low-dimensional space by compressing redundant dimensions and eliminating multicollinearity interference. This not only reduces the resource load of real-time computing in the cloud system, but also reduces the risk of direct exposure of sensitive original data through feature concentration, thereby indirectly enhancing data security protection.

[0053] Furthermore, the importance of each principal component to the prediction of quotation error is evaluated through the eigenvector of each principal component, specifically:

[0054] The bid error of each bid task and the eigenvectors of all principal components are used as inputs to the random forest model to obtain the importance score of each principal component.

[0055] It should be noted that the random forest model is trained by collecting a large number of engineering data sets from historical engineering projects. The process of performing feature importance analysis through the random forest model is a well-known technology and will not be repeated here. Secondly, the influence weight of the orthogonalized comprehensive features on the quotation error is quantified by the random forest, and the key driving factors are extracted from the privacy-protected generalized feature space, which not only avoids the redundancy of the original data and the risk of sensitive information being exposed, but also provides an explainable basis for the dynamic optimization of the quotation strategy.

[0056] Furthermore, based on the variance contribution rate and the importance score, the dimensionality reduction efficiency coefficient is calculated, specifically:

[0057] The sum of the products of the importance scores and the variance contribution rates of all principal components in each quotation task is used as the dimensionality reduction efficiency coefficient of each quotation task;

[0058] It should be noted that the variance contribution rate reflects the explanatory power of the principal component for the original high-dimensional data. The larger the variance contribution rate, the more original information features the principal component retains, indicating that the principal component contains more information affecting the project quotation. The importance score reflects the correlation or causal relationship between the principal component and the quotation error, and quantifies the predictive power of the principal component for the quotation error. The larger the importance score, the stronger the predictive power of the principal component for the quotation error. The dimensionality reduction efficiency coefficient evaluates the retention of the original information in the low-dimensional space after dimensionality reduction, and the quantitative coupling results of the correlation with the quotation error, and describes the comprehensive driving efficiency of the privacy protection feature space on the quotation error in the cloud-based engineering quotation system. The larger the dimensionality reduction efficiency coefficient, the stronger the influence of the data information in the low-dimensional space after dimensionality reduction on the comprehensive evaluation of the quotation error. It can provide high information density and low redundancy information interpretation capabilities for engineering quotations while eliminating the direct exposure of the original sensitive data, and balance the dual needs of computational efficiency and privacy protection.

[0059] At this point, the dimensionality reduction efficiency coefficient of each quotation task is obtained.

[0060] Step 3: Determine the resource scheduling coefficient of each quotation task by combining the dimensionality reduction efficiency coefficient with the correlation changes between the system response time and the dimensionality reduction efficiency coefficient of each quotation task, as well as the distribution density of the dimensionality reduction efficiency coefficients between different quotation tasks.

[0061] The flowchart of the method for obtaining the resource scheduling coefficient of each quotation task provided in the embodiment of the present application is as follows: Figure 2 shown.

[0062] Furthermore, in the cloud-based engineering quotation system, when quoting multiple engineering projects continuously, the complex coupling relationship of its high-dimensional feature space and the uneven distribution of resource consumption will lead to a significant delay in the real-time response to engineering quotations, causing the computing load of the cloud-based engineering quotation system to show highly volatile and locally intensive characteristics.

[0063] Therefore, we cluster the dimensionality reduction efficiency coefficients and analyze the resource consumption patterns of the cloud engineering quotation system during the operation of different quotation tasks, and then quantify the demand for centralized allocation of computing resources. Specifically,

[0064] The system response time of each quotation task and the dimension reduction efficiency coefficient are combined into a two-dimensional array;

[0065] Perform linear regression analysis on all two-dimensional arrays and obtain regression coefficients;

[0066] It should be noted that linear regression analysis is a well-known technology and will not be described in detail here.

[0067] Clustering the dimension reduction efficiency coefficients of all quotation tasks to obtain the local density corresponding to each quotation task;

[0068] In this embodiment, the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm is used for clustering. The DBSCAN clustering algorithm is a well-known technology and will not be described in detail here. The neighborhood radius ε of the DBSCAN clustering algorithm is set to 0.5, and the minimum number of samples MinPts is set to 10. As other implementation methods, the implementer can set them according to actual conditions.

[0069] Performing positive mapping on the dimensionality reduction efficiency coefficient;

[0070] In this embodiment, the positive mapping process is: the dimensionality reduction efficiency coefficient is positively mapped by a logarithmic function. Assuming that the dimensionality reduction efficiency coefficient of the nth quotation task is A n , then log(A n +1) is used as the result of the positive mapping, so that the result of the positive mapping is greater than or equal to 0, where log() is a logarithmic function with base 10.

[0071] It should be noted that the logarithmic function of A n Perform nonlinear smoothing to suppress the impact of data distribution skew caused by high-dimensional data discretization and word frequency statistics, avoid the dominance of extreme dimensionality reduction efficiency quotations on resource scheduling strategies, and quantify the information density and interpretability contribution of multi-source data to engineering cost forecasting after dimensionality reduction.

[0072] The product of the positive mapping result, the regression coefficient and the local density corresponding to each bidding task is used as the resource scheduling coefficient of each bidding task;

[0073] In this embodiment, the calculation formula for the resource scheduling coefficient of the nth quotation task is:

[0074] B n =α×β n ×log(A n +1)

[0075] Among them, B n is the resource scheduling coefficient of the nth quotation task, α is the regression coefficient, β n The local density of the nth quotation task, An is the dimensionality reduction efficiency coefficient of the nth quotation task, and log() is the logarithmic function with base 10.

[0076] It should be noted that the regression coefficient reflects the strength of the linear relationship between the dimensionality reduction efficiency coefficient and the system response time. The larger the regression coefficient, the higher the global linear influence of the dimensionality reduction efficiency coefficient of the data after hash coding and bag-of-words vectorization preprocessing on the real-time response delay. The correlation between the privacy protection feature space after quantified PCA dimensionality reduction and system resource consumption is quantified. The larger the regression coefficient, the higher the cost of data security protection to avoid exposure of original sensitive data at the cost of higher computing delay. The local density reflects the resource competition of quotation tasks with similar dimensionality reduction efficiency. The larger the local density, the easier it is to trigger resource competition and data access conflicts. The resource scheduling coefficient measures the comprehensive efficiency of privacy protection dimensionality reduction processing and resource consumption pattern of multimodal data in the cloud engineering quotation system. The larger the resource scheduling coefficient, the more low-redundancy calculation is achieved through high information density features under low sensitive data exposure, and resources need to be allocated first to reduce real-time response delay.

[0077] At this point, the resource scheduling coefficient of each quotation task is obtained.

[0078] Step 4: Based on the resource scheduling coefficient, perform hierarchical scheduling processing on different quotation tasks.

[0079] Furthermore, based on the resource scheduling coefficient, a dynamic preemptive scheduling mechanism for GPU / CPU hybrid computing resources is constructed. Quotation tasks are hierarchically processed using the resource scheduling coefficient. Asynchronous pipeline parallelization technology is employed to achieve load balancing for high-dimensional matrix operations, ultimately generating a real-time quotation strategy after error compensation. A modular and layered architecture is employed to support efficient data processing and resource scheduling. At the hardware level, the cloud-based engineering quotation system integrates a GPU / CPU hybrid computing architecture, where the GPU is responsible for accelerating high-dimensional matrix operations and the CPU is responsible for task scheduling and logical control. At the software level, the cloud-based engineering quotation system decouples computational processes such as feature dimensionality reduction, model inference, and error correction through a dynamic preemptive scheduling mechanism and asynchronous pipeline parallelization technology, achieving dynamic task allocation and load balancing. Furthermore, the cloud-based engineering quotation system utilizes Linux Cgroups container isolation technology to ensure resource isolation and data security between different tasks, preventing data leakage or contamination caused by resource competition or task cross-compatibility. Block matrix operations, mixed-precision computation, and asynchronous pipeline parallelization are all well-known techniques in this field and will not be elaborated upon here.

[0080] In the cloud-based engineering quotation system, to optimize resource allocation and scheduling efficiency, quotation tasks are assigned to different processing queues based on their priorities, and corresponding resources are allocated. By building a dynamic priority-driven parallel computing optimization mechanism, all quotation tasks are hierarchically scheduled, thereby implementing a dynamic preemptive scheduling mechanism. Specifically,

[0081] Based on the resource scheduling coefficients of all bidding tasks, a kernel density estimation curve is constructed. The kernel density estimation curve is used to calculate the resource scheduling coefficients corresponding to when the cumulative distribution function (CDF) reaches a preset first value and a preset second value, respectively. These coefficients are recorded as the first split threshold and the second split threshold, where the preset second value is greater than the preset first value.

[0082] In this embodiment, the first value is preset to 20% and the second value is preset to 70%. As other implementation methods, the implementer can set them according to actual conditions; therefore, the resource scheduling coefficient corresponding to when the cumulative distribution function reaches 20% is recorded as the first split threshold, and the resource scheduling coefficient corresponding to when the cumulative distribution function reaches 70% is recorded as the second split threshold.

[0083] It should be noted that the kernel density estimation curve and the cumulative distribution function are well-known technologies and will not be described in detail here; among them, the horizontal axis of the kernel density estimation curve is the resource scheduling coefficient, and the vertical axis is the probability density; secondly, since the kernel density estimation curve reflects the probability density distribution of the resource scheduling coefficient, and CDF is the integral of the kernel density estimation curve, reflecting the probability that the resource scheduling coefficient is less than or equal to a certain value, therefore, 20% of the CDF in the kernel density estimation curve corresponds to the 20th percentile of the resource scheduling coefficient. When the CDF reaches 20%, it means that 20% of the quotation tasks have a resource scheduling coefficient less than or equal to the first segmentation threshold. The resource requirements of these 20% quotation tasks with a resource scheduling coefficient less than or equal to the first segmentation threshold are relatively low.

[0084] Based on the first segmentation threshold and the second segmentation threshold, the multi-level feedback queue is divided into a high priority queue, a medium priority queue, and a low priority queue;

[0085] Assign the quotation tasks whose resource scheduling coefficient is less than or equal to the first segmentation threshold to the low priority queue; assign the quotation tasks whose resource scheduling coefficient is greater than the first judgment threshold and less than or equal to the second segmentation threshold to the medium priority queue; and assign the quotation tasks whose resource scheduling coefficient is greater than the second segmentation threshold to the high priority queue;

[0086] It should be noted that the multi-stage feedback queue is a well-known technology and will not be described in detail here.

[0087] Therefore, the quotation tasks with different resource scheduling coefficients are assigned to the corresponding priority queues for resource scheduling, and resources are allocated preferentially to the quotation tasks in the high-priority queue.

[0088] The above-mentioned dynamic preemptive scheduling mechanism effectively solves the core problem of high-dimensional data information computing resource overload in the cloud-based engineering quotation system, realizes accurate hierarchical scheduling of computing resources, combines GPU TensorCore acceleration and mixed-precision block matrix calculation to reduce the time consumption of high-dimensional feature calculations and reduce GPU memory usage; decouples feature dimensionality reduction, model reasoning and error correction links through asynchronous pipeline parallel technology to achieve multi-task load balancing. On the basis of ensuring privacy and security, a breakthrough in the computing efficiency and accuracy of complex engineering quotation tasks has been achieved, reducing the response delay of real-time quotation. On the premise of ensuring the security and integrity of enterprise data, the cloud-based engineering quotation system can adaptively handle complex scenarios such as regional quota differences, policy changes and multimodal engineering data coupling, reducing the quotation error rate. Among them, block matrix operation, mixed-precision calculation and asynchronous pipeline parallel technology are all technologies well known to people in this field of technology and will not be repeated here.

[0089] An embodiment of the present application also provides a generalized processing protection device for a cloud-based engineering quotation system, wherein the device stores a computer program, and when the computer program is executed by a processor, the steps of any one of the generalized processing protection methods for the cloud-based engineering quotation system are implemented.

[0090] Based on the same inventive concept as the above method, an embodiment of the present application also provides a generalized processing and protection system for a cloud-based engineering quotation system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned generalized processing and protection methods for the cloud-based engineering quotation system are implemented.

[0091] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0092] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0093] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the present application. It should be noted that a person skilled in the art can make various modifications and improvements without departing from the spirit of the present application. Therefore, any simple modifications, equivalent variations, and modifications to the above embodiments made in accordance with the technical essence of the present application without departing from the content of the present application's technical solution fall within the scope of protection of the present application's technical solution.

Claims

1. A generalized processing and protection method for a cloud-based engineering quotation system, characterized in that: The method comprises the following steps: After converting the data types of the project list information and the corresponding project policy documents of all projects that require batch project quotations, a project data set is formed. Quotations are then generated for each project, the quotation error for each quotation task is calculated, and the system response time for each quotation task is recorded. Perform dimensionality reduction analysis on the engineering data set, extract the principal components, analyze the importance of different principal components corresponding to each quotation task, and their contribution to the original data information, and determine the dimensionality reduction efficiency coefficient of each quotation task; Determine the resource scheduling coefficient of each quotation task by combining the correlation between the system response time of each quotation task and the dimensionality reduction efficiency coefficient, as well as the distribution density of the dimensionality reduction efficiency coefficients between different quotation tasks and the dimensionality reduction efficiency coefficient; Based on the resource scheduling coefficient, different quotation tasks are scheduled in different levels.

2. The generalized processing protection method of the cloud engineering quotation system according to claim 1, characterized in that: The process of obtaining the quotation error is as follows: The cloud-based engineering quotation system predicts the engineering quotation for each project and obtains the total quotation amount for the quotation task corresponding to each project; The calculation formula for the quotation error of each quotation task is:

3. The generalized processing protection method of the cloud engineering quotation system according to claim 1, characterized in that: The performing dimensionality reduction analysis on the engineering data set and extracting the principal components includes: using the PCA method to perform dimensionality reduction on all data in the engineering data set of each quotation task, and extracting the eigenvector and variance contribution rate of each principal component.

4. The generalized processing protection method of the cloud engineering quotation system according to claim 3, characterized in that: The further measurement process of the importance is: taking the quotation error of each quotation task and the eigenvectors of all principal components as inputs of the random forest model to obtain the importance score of each principal component.

5. The generalized processing protection method of the cloud engineering quotation system according to claim 4, characterized in that: The dimension reduction efficiency coefficient is the sum of the products of the importance scores and the variance contribution rates of all principal components in each quotation task.

6. The generalized processing protection method of the cloud engineering quotation system according to claim 1, characterized in that: The related changes are further measured by regression coefficients, and the specific process is: The system response time of each quotation task and the dimension reduction efficiency coefficient are combined into a two-dimensional array; Perform linear regression analysis on the two-dimensional arrays corresponding to all quotation tasks to obtain the regression coefficients.

7. The generalized processing protection method of the cloud engineering quotation system according to claim 6, characterized in that: Determining the resource scheduling coefficient of each quotation task includes: Clustering the dimension reduction efficiency coefficients of all quotation tasks to obtain the local density corresponding to each quotation task; performing positive mapping on the dimension reduction efficiency coefficients; The resource scheduling coefficient is the product of the forward mapping result corresponding to each bidding task, the regression coefficient, and the local density.

8. The generalized processing protection method of the cloud engineering quotation system according to claim 1, characterized in that: The hierarchical scheduling of different quotation tasks includes: Based on the resource scheduling coefficients of all quotation tasks, a kernel density estimation curve is constructed. The kernel density estimation curve is used to calculate the resource scheduling coefficients corresponding to when the cumulative distribution function reaches a preset first value and a preset second value, respectively, which are recorded as the first split threshold and the second split threshold, wherein the preset second value is greater than the preset first value; Based on the first segmentation threshold and the second segmentation threshold, the multi-level feedback queue is divided into a high priority queue, a medium priority queue, and a low priority queue; Assign quotation tasks with different resource scheduling coefficients to corresponding priority teams for resource scheduling.

9. A generalized processing protection device for a cloud-based engineering quotation system, wherein the device stores a computer program, characterized in that: When the computer program is executed by a processor, the steps of the generalized processing protection method of the cloud engineering quotation system as described in any one of claims 1 to 8 are implemented.

10. A generalized processing protection system for a cloud engineering quotation system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the generalized processing protection method of the cloud engineering quotation system as described in any one of claims 1 to 8 are implemented.

Images