Project budget intelligent management system and method based on cloud computing

Abstract

The present application relates to the field of intelligent control, and specifically discloses a cloud computing-based project budget intelligent management system and method, which obtains the budget information and actual expenditure data of the project, wherein the budget information of the project includes the project plan, budget allocation, and budget execution cycle, and the actual expenditure data includes the actual expenses incurred by the project, expenditure records, and expense types, and uses deep learning technology to perform semantic understanding analysis and association on the budget information and actual expenditure data of the project, thereby generating a visual progress image of the current project budget execution. In this way, it can help users intuitively understand the budget execution of the project, discover problems and risks in a timely manner, and thus help users to adjust budget strategies and take measures in a timely manner to ensure the effective execution of the project budget.

Description

Technical Field

[0001] The present application relates to the field of intelligent management, and more specifically, to a project budget intelligent management system and method based on cloud computing. Background Art

[0002] Project budget management refers to the process of planning, allocating, executing and monitoring the project budget during the project life cycle. This includes determining the cost of the resources required for the project, developing a budget plan, allocating budgets to various activities, monitoring actual expenditures, and making adjustments as needed to ensure that the project is completed on time and within budget.

[0003] However, the traditional method usually requires manual collection, organization and analysis of project budget data, which is time-consuming and labor-intensive, and prone to errors and omissions. Secondly, the traditional method usually presents budget progress information in the form of static reports or tables, lacking comprehensive real-time data analysis and visual presentation, which is not conducive to managers quickly understanding the progress of the project and cannot comprehensively evaluate the budget execution of the project, resulting in low accuracy of budget management.

[0004] Therefore, an optimized cloud computing-based project budget intelligent management system is expected. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a cloud computing-based project budget intelligent management system and method, which obtains the budget information and actual expenditure data of the project, wherein the budget information of the project includes the project plan, budget allocation, and budget execution cycle, and the actual expenditure data includes the actual expenses incurred by the project, expenditure records, and expense types, and uses deep learning technology to perform semantic understanding analysis and association on the budget information and actual expenditure data of the project, thereby generating a visual progress image of the current project budget execution. In this way, it can help users intuitively understand the budget execution of the project, discover problems and risks in a timely manner, thereby helping users to adjust budget strategies and take measures in a timely manner to ensure the effective implementation of the project budget.

[0006] According to one aspect of the present application, a cloud computing-based project budget intelligent management system is provided, which includes:

[0007] The project budget data collection module is used to obtain the budget information and actual expenditure data of the project, wherein the budget information of the project includes the project plan, budget allocation, and budget execution cycle, and the actual expenditure data includes the actual expenses incurred by the project, expenditure records, and expense types;

[0008] A budget information context encoding module, used for performing word segmentation processing on the budget information of the project and then performing budget information context encoding to obtain a budget information context encoding feature matrix;

[0009] An actual expenditure data context encoding module, used for performing word segmentation processing on the actual expenditure data and then performing actual expenditure data context encoding to obtain an actual expenditure data context encoding feature matrix;

[0010] An information fusion module, used for fusing the budget information context encoding feature matrix and the actual expenditure data context encoding feature matrix to obtain a project budget execution status feature matrix;

[0011] A project budget execution feature extraction module, used for extracting project budget execution features from the project budget execution feature matrix to obtain a project budget execution enhanced feature vector;

[0012] A coherent interference correction module, used for performing coherent interference correction on the enhanced feature vector of the project budget execution status based on the category probability value to obtain a corrected enhanced feature vector of the project budget execution status;

[0013] The visualization progress image generation module is used to generate a visualization progress image of the current project budget execution based on the corrected project budget execution status enhancement feature vector.

[0014] In the above-mentioned cloud computing-based project budget intelligent management system, the budget information context encoding module includes: a budget information word embedding unit, which is used to input the budget information of the project into a word embedding layer after word segmentation to obtain a sequence of budget information word embedding vectors; and a budget information encoding unit, which is used to input the sequence of budget information word embedding vectors into a converter-based budget information context encoder to obtain the budget information context encoding feature matrix.

[0015] In the above-mentioned cloud computing-based project budget intelligent management system, the budget information encoding unit includes: a context budget information extraction subunit, which is used to input the sequence of the budget information word embedding vectors into the converter-based budget information context encoder to obtain multiple context budget information feature vectors; and a two-dimensional arrangement subunit, which is used to arrange the multiple context budget information feature vectors in two dimensions to obtain the budget information context encoding feature matrix.

[0016] In the above-mentioned cloud computing-based project budget intelligent management system, the actual expenditure data context encoding module includes: an actual expenditure data word embedding unit, which is used to input the actual expenditure data into the word embedding layer after word segmentation to obtain a sequence of actual expenditure data word embedding vectors; and an actual expenditure data encoding unit, which is used to input the sequence of actual expenditure data word embedding vectors into the converter-based actual expenditure data context encoder to obtain the actual expenditure data context encoding feature matrix.

[0017] In the above-mentioned cloud computing-based project budget intelligent management system, the project budget execution status feature extraction module is used to: input the project budget execution status feature matrix into the project budget execution status feature extractor based on the deep and shallow fusion convolutional network model to obtain the project budget execution status enhanced feature matrix, and then expand the project budget execution status enhanced feature matrix to obtain the project budget execution status enhanced feature vector.

[0018] In the above-mentioned cloud computing-based project budget intelligent management system, the coherent interference correction module includes: an activation unit, which is used to pass the project budget execution status enhancement feature vector through an activation function to obtain a category probability feature vector; a covariance matrix calculation unit, which is used to calculate the covariance matrix between the project budget execution status enhancement feature vector and the category probability feature vector; an autocorrelation covariance calculation unit, which is used to calculate the autocorrelation covariance matrix of the project budget execution status enhancement feature vector; an interference correction unit, which is used to calculate the interference correction matrix based on the covariance matrix and the autocorrelation covariance matrix; and a feature correction unit, which is used to correct the project budget execution status enhancement feature vector based on the interference correction matrix to obtain the corrected project budget execution status enhancement feature vector.

[0019] In the above-mentioned cloud computing-based project budget intelligent management system, the interference correction unit is used to: calculate the interference correction matrix based on the covariance matrix and the autocorrelation covariance matrix using the following correction formula; wherein the correction formula is:

[0020] S = Cov(x, P)*(Cov(x)+εI) -1

[0021] Among them, x represents the enhanced feature vector of the project budget execution, P represents the category probability feature vector, Cov(x, P) represents the covariance matrix between the enhanced feature vector of the project budget execution and the category probability feature vector, Cov(x) represents the autocorrelation covariance matrix of the enhanced feature vector of the project budget execution, I represents the unit matrix, ε represents the predetermined hyperparameter, and S represents the interference correction matrix.

[0022] In the above-mentioned cloud computing-based project budget intelligent management system, the visual progress image generation module is used to: input the corrected project budget execution status enhanced feature vector into a generator to generate a visual progress image of the current project budget execution.

[0023] According to another aspect of the present application, a cloud computing-based project budget intelligent management method is provided, which includes:

[0024] Obtaining the budget information and actual expenditure data of the project, wherein the budget information of the project includes the project plan, budget allocation, and budget execution cycle, and the actual expenditure data includes the actual expenses incurred by the project, expenditure records, and expense types;

[0025] After word segmentation processing is performed on the budget information of the project, budget information context encoding is performed to obtain a budget information context encoding feature matrix;

[0026] After word segmentation processing is performed on the actual expenditure data, actual expenditure data context encoding is performed to obtain an actual expenditure data context encoding feature matrix;

[0027] The budget information context encoding feature matrix and the actual expenditure data context encoding feature matrix are integrated to obtain a project budget execution status feature matrix;

[0028] Extracting project budget execution features from the project budget execution feature matrix to obtain a project budget execution enhanced feature vector;

[0029] Performing coherent interference correction based on the category probability value on the enhanced feature vector of the project budget execution to obtain a corrected enhanced feature vector of the project budget execution;

[0030] Based on the corrected project budget execution status enhanced feature vector, a visual progress image of the current project budget execution is generated.

[0031] In the above-mentioned cloud computing-based project budget intelligent management method, the budget information of the project is subjected to word segmentation processing and then budget information context encoding is performed to obtain a budget information context encoding feature matrix, including: inputting the budget information of the project into a word embedding layer after word segmentation processing to obtain a sequence of budget information word embedding vectors; and inputting the sequence of budget information word embedding vectors into a converter-based budget information context encoder to obtain the budget information context encoding feature matrix.

[0032] Compared with the prior art, the present application provides a cloud computing-based project budget intelligent management system and method, which obtains the budget information and actual expenditure data of the project, wherein the budget information of the project includes the project plan, budget allocation, and budget execution cycle, and the actual expenditure data includes the actual expenses incurred by the project, expenditure records, and expense types, and uses deep learning technology to perform semantic understanding analysis and association on the budget information and actual expenditure data of the project, thereby generating a visual progress image of the current project budget execution. In this way, it can help users intuitively understand the budget execution of the project, discover problems and risks in a timely manner, and thus help users adjust budget strategies and take measures in a timely manner to ensure the effective execution of the project budget. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0034] Figure 1 The block diagram is a cloud computing-based project budget intelligent management system according to an embodiment of the present application.

[0035] Figure 2 Schematic diagram of the architecture of a cloud computing-based project budget intelligent management system according to an embodiment of the present application.

[0036] Figure 3 The block diagram is a budget information context encoding module in a cloud computing-based project budget intelligent management system according to an embodiment of the present application.

[0037] Figure 4 The present invention is a block diagram of a budget information encoding unit in a cloud computing-based project budget intelligent management system according to an embodiment of the present application.

[0038] Figure 5 The present invention is a flowchart of a method for intelligently managing project budgets based on cloud computing according to an embodiment of the present application. DETAILED DESCRIPTION

[0039] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, but rather these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0040] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0041] It should be noted that the terms "first\second\third" involved in the embodiments of the present application are only used to distinguish similar objects, and do not represent a specific order for the objects. It is understandable that the specific order or sequence of "first\second\third" can be interchanged where permitted. It should be understood that the objects distinguished by "first\second\third" can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0042] As shown in the present disclosure and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0043] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0044] Project budget management refers to the process of planning, allocating, executing and monitoring the project budget during the project life cycle. This includes determining the cost of the resources required for the project, developing a budget plan, allocating budgets to various activities, monitoring actual expenditures, and making adjustments as needed to ensure that the project is completed on time and within budget.

[0045] However, the traditional method usually requires manual collection, organization and analysis of project budget data, which is time-consuming and labor-intensive, and prone to errors and omissions. Secondly, the traditional method usually presents budget progress information in the form of static reports or tables, lacking comprehensive real-time data analysis and visual presentation, which is not conducive to managers quickly understanding the progress of the project and cannot comprehensively evaluate the budget execution of the project, resulting in low accuracy of budget management.

[0046] It should be understood that cloud computing is a technology that allocates computing resources on demand through the network. It includes applications, servers, data storage, development tools, network functions, etc., which are hosted in remote data centers managed by cloud service providers. Cloud computing helps reduce costs, improve agility, scalability and ease. Cloud computing is increasingly used in project budgeting. Specifically, cloud computing platforms provide flexible billing models that can pay according to actual usage, helping companies better control budgets and avoid waste and unnecessary expenses. Cloud computing platforms also provide resource monitoring and management tools that can help companies understand resource usage in real time, optimize resource allocation, and improve resource utilization, thereby reducing costs. Therefore, the application of cloud computing in project budget management can help companies achieve cost optimization, resource management, flexibility and scalability, improve data analysis and prediction capabilities, and enhance security and reliability, so as to more effectively manage project budgets and achieve project goals.

[0047] Therefore, an optimized cloud computing-based project budget intelligent management system is desired, which obtains the budget information and actual expenditure data of the project, wherein the budget information of the project includes the project plan, budget allocation, and budget execution cycle, and the actual expenditure data includes the actual expenses incurred by the project, expenditure records, and expense types, and uses deep learning technology to perform semantic understanding analysis and association on the budget information and actual expenditure data of the project, thereby generating a visual progress image of the current project budget execution. In this way, users can intuitively understand the budget execution of the project, discover problems and risks in a timely manner, and thus help users to adjust budget strategies and take measures in a timely manner to ensure the effective execution of the project budget.

[0048] Figure 1 The block diagram is a cloud computing-based project budget intelligent management system according to an embodiment of the present application. Figure 2 FIG. 1 is a schematic diagram of the architecture of a cloud computing-based project budget intelligent management system according to an embodiment of the present application. Figure 1 and Figure 2As shown, according to the cloud computing-based project budget intelligent management system 100 of the embodiment of the present application, it includes: a project budget data acquisition module 110, which is used to obtain the budget information and actual expenditure data of the project, wherein the budget information of the project includes the project plan, budget allocation, and budget execution cycle, and the actual expenditure data includes the actual expenses incurred by the project, expenditure records, and expense types; a budget information context encoding module 120, which is used to perform word segmentation processing on the budget information of the project and then perform budget information context encoding to obtain a budget information context encoding feature matrix; an actual expenditure data context encoding module 130, which is used to perform word segmentation processing on the actual expenditure data and then perform actual expenditure data context encoding to obtain an actual expenditure data context encoding feature matrix an information fusion module 140 for fusing the budget information context encoding feature matrix and the actual expenditure data context encoding feature matrix to obtain a project budget execution feature matrix; a project budget execution feature extraction module 150 for performing project budget execution feature extraction on the project budget execution feature matrix to obtain a project budget execution enhanced feature vector; a coherent interference correction module 160 for performing coherent interference correction on the project budget execution enhanced feature vector based on a class probability value to obtain a corrected project budget execution enhanced feature vector; and a visual progress image generation module 170 for generating a visual progress image of the current project budget execution based on the corrected project budget execution enhanced feature vector.

[0049] In an embodiment of the present application, the project budget indicates that the data acquisition module 110 is used to obtain the budget information and actual expenditure data of the project, wherein the budget information of the project includes the project plan, budget allocation, and budget execution cycle, and the actual expenditure data includes the actual expenses incurred by the project, expenditure records, and expense types. It should be understood that the budget information of the project includes the project plan, budget allocation, and budget execution cycle. The actual expenditure data includes the actual expenses incurred by the project, expenditure records, and expense types. These data provide a basis and support for the current visualization of the project budget, which is crucial for project management and budget control. Based on this, in the technical solution of the present application, the budget information and actual expenditure data of the project are obtained, wherein the budget information of the project includes the project plan, budget allocation, and budget execution cycle, and the actual expenditure data includes the actual expenses incurred by the project, expenditure records, and expense types. The budget information and actual expenditure data of the project are semantically analyzed and correlated with each other, so that the progress of the project can be understood in real time, and whether the project execution is in line with expectations, so as to adjust the budget and resource allocation in time to ensure that the project proceeds smoothly as planned, thereby helping the project team to clarify the budget limits and allocations, helping managers to understand the input-output ratio of the project, and providing a reference basis for future project decisions to ensure that the project is implemented smoothly and achieves the expected goals.

[0050] In the embodiment of the present application, the budget information context encoding module 120 is used to perform budget information context encoding after word segmentation processing on the budget information of the project to obtain a budget information context encoding feature matrix. Figure 3 is a block diagram of a budget information context encoding module in a cloud computing-based project budget intelligent management system according to an embodiment of the present application. Specifically, in the embodiment of the present application, Figure 3 As shown, the budget information context encoding module 120 includes: a budget information word embedding unit 121, which is used to input the budget information of the project into a word embedding layer after word segmentation to obtain a sequence of budget information word embedding vectors; and a budget information encoding unit 122, which is used to input the sequence of budget information word embedding vectors into a converter-based budget information context encoder to obtain the budget information context encoding feature matrix.

[0051] Specifically, in an embodiment of the present application, the budget information word embedding unit 121 is used to input the budget information of the project into the word embedding layer after word segmentation processing to obtain a sequence of budget information word embedding vectors. Accordingly, considering that the budget information of the project contains a large amount of text content, and these contents are composed of multiple words or phrases, therefore, in the technical solution of the present application, the budget information of the project is word segmented to divide a large paragraph of text into multiple words or phrases for subsequent processing. Further, in natural language processing, it is necessary to convert these multiple words or phrases into vector form. And word embedding is a representation form that maps discrete words to continuous high-dimensional vector space. That is, through word embedding, each word or phrase can be represented as a dense vector, which is conducive to the deep learning model to achieve better results in text processing tasks. Based on this, in the technical solution of the present application, the budget information of the project after word segmentation processing is input into the word embedding layer to obtain a sequence of budget information word embedding vectors, so as to better understand and analyze the budget information of the project after word segmentation processing.

[0052] Specifically, in the embodiment of the present application, the budget information encoding unit 122 is used to input the sequence of the budget information word embedding vectors into the budget information context encoder based on the converter to obtain the budget information context encoding feature matrix. It should be understood that, considering that there is a semantic association relationship between the sequences of the budget information word embedding vectors about the context of the budget information, and the budget information context encoder based on the converter has a good feature capture ability for the long-distance dependent semantics in the sequence, therefore, in the technical solution of the present application, the sequence of the budget information word embedding vectors is input into the budget information context encoder based on the converter to obtain the budget information context encoding feature matrix, so that the model can model the context information in the text sequence, so as to better understand the context and association of each word in the budget information in the entire budget information, thereby improving the model's ability to understand the budget information.

[0053] Figure 4 is a block diagram of a budget information encoding unit in a cloud computing-based project budget intelligent management system according to an embodiment of the present application. More specifically, in the embodiment of the present application, Figure 4 As shown, the budget information encoding unit 122 includes: a context budget information extraction subunit 1221, which is used to input the sequence of the budget information word embedding vectors into the converter-based budget information context encoder to obtain multiple context budget information feature vectors; and a two-dimensional arrangement subunit 1222, which is used to arrange the multiple context budget information feature vectors in two dimensions to obtain the budget information context encoding feature matrix.

[0054] In the embodiment of the present application, the actual expenditure data context encoding module 130 is used to perform actual expenditure data context encoding on the actual expenditure data after word segmentation processing to obtain an actual expenditure data context encoding feature matrix. Specifically, in the embodiment of the present application, the actual expenditure data context encoding module includes: an actual expenditure data word embedding unit, which is used to input the actual expenditure data into the word embedding layer after word segmentation processing to obtain a sequence of actual expenditure data word embedding vectors; and an actual expenditure data encoding unit, which is used to input the sequence of actual expenditure data word embedding vectors into a converter-based actual expenditure data context encoder to obtain the actual expenditure data context encoding feature matrix.

[0055] Specifically, in an embodiment of the present application, the actual expenditure data word embedding unit is used to input the actual expenditure data into the word embedding layer after word segmentation processing to obtain a sequence of actual expenditure data word embedding vectors. Similarly, considering that the actual expenditure data contains a large amount of text information, and this information is composed of multiple words or phrases, therefore, in the technical solution of the present application, the actual expenditure data is word segmented to divide a large section of actual expenditure data text into multiple words or phrases for subsequent processing. Further, in natural language processing, it is necessary to convert these multiple words or phrases into vectors in order to better understand the semantics of each word or phrase. And word embedding is a representation form that maps discrete words to a continuous high-dimensional vector space. Therefore, through word embedding, each word or phrase can be represented as a dense vector. Based on this, in the technical solution of the present application, the actual expenditure data after word segmentation processing is input into the word embedding layer to obtain a sequence of actual expenditure data word embedding vectors, so as to better understand and analyze the actual expenditure data after word segmentation processing in the future.

[0056] Specifically, in an embodiment of the present application, the actual expenditure data encoding unit is used to input the sequence of the actual expenditure data word embedding vectors into the actual expenditure data context encoder based on the converter to obtain the actual expenditure data context encoding feature matrix. Accordingly, considering that there is a semantic association relationship between the sequences of the actual expenditure data word embedding vectors about the context of the actual expenditure data, and the budget information context encoder based on the converter has a good feature perception ability between the long-distance dependent semantics in the text sequence, therefore, in the technical solution of the present application, the sequence of the actual expenditure data word embedding vectors is input into the actual expenditure data context encoder based on the converter to obtain the actual expenditure data context encoding feature matrix, so that the model can model the actual expenditure context information in the actual expenditure data text sequence, so as to better understand the context and association of each word in the actual expenditure data in the entire actual expenditure data, thereby improving the model's understanding of the actual expenditure data.

[0057] In an embodiment of the present application, the information fusion module 140 is used to fuse the budget information context encoding feature matrix and the actual expenditure data context encoding feature matrix to obtain a project budget execution feature matrix. It should be understood that both budget information and actual expenditure data are very important information in project management. By fusing the feature matrices of the two, the budget arrangement and actual execution of the project can be comprehensively considered to help understand the financial status of the project more comprehensively. Therefore, in the technical solution of the present application, the budget information context encoding feature matrix and the actual expenditure data context encoding feature matrix are fused to obtain a project budget execution feature matrix, that is, the budget information and the actual expenditure data are fused, and a comparative analysis can be performed to find out the differences and deviations between the budget and the actual expenditure, which helps to evaluate the efficiency and quality of project execution, so as to better understand and predict the budget execution of the project.

[0058] In an embodiment of the present application, the project budget execution status feature extraction module 150 is used to perform project budget execution status feature extraction on the project budget execution status feature matrix to obtain a project budget execution status enhanced feature vector. Specifically, in an embodiment of the present application, the project budget execution status feature extraction module is used to: input the project budget execution status feature matrix into a project budget execution status feature extractor based on a deep and shallow fusion convolutional network model to obtain a project budget execution status enhanced feature matrix, and then expand the project budget execution status enhanced feature matrix to obtain the project budget execution status enhanced feature vector. Accordingly, considering that the deep and shallow fusion convolutional network model can extract local features through the convolution layer, the step-by-step abstraction of features is achieved through the deep network structure. Such a structure can help the model extract higher-level and more abstract feature information from the project budget execution status feature matrix. Therefore, in the technical solution of the present application, the project budget execution feature matrix is ​​input into a project budget execution feature extractor based on a deep and shallow fusion convolutional network model to obtain a project budget execution enhanced feature matrix. This can help extract key feature information in the project budget execution feature matrix and obtain a project budget execution enhanced feature matrix with better representation and generalization capabilities, thereby better supporting subsequent budget execution analysis and decision making.

[0059] In an embodiment of the present application, the coherent interference correction module 160 is used to perform coherent interference correction based on the category probability value on the project budget execution enhancement feature vector to obtain the corrected project budget execution enhancement feature vector. In particular, in the above technical solution, there may be data quality problems, such as wrong records, missing values ​​or inaccurate information, in the processing of budget information and actual expenditure data. These data quality problems may cause the generated feature vector to contain noise or interference, which is irrelevant to the generation task. In the feature extraction process, there may be errors or inaccuracies in the feature extractor, resulting in the extracted features not being completely related to the generation task. If the feature extractor does not correctly capture the features related to the generation task, the generated project budget execution enhancement feature vector will contain some information irrelevant to the generation task. If the project budget execution enhancement feature vector contains a large amount of information irrelevant to the generation task, the generator will be disturbed when generating the image, which may cause the quality of the generated image to deteriorate, or the generated image will not match the actual situation. The presence of irrelevant information may confuse the generator when generating the image, increasing the risk that the generated image does not match the actual situation. The generator may be affected by noise or interference, resulting in deviations in the generated image, thereby affecting the accuracy of the generation. Including information irrelevant to the generation task will reduce the generalization ability of the generation model for new samples, because the model pays too much attention to noise or interference rather than features that are truly relevant to the generation task. This will affect the quality and accuracy of the generated images in practical applications. Therefore, in order to solve this problem, in the technical solution of the present application, the project budget execution enhanced feature vector is corrected by coherent interference based on the category probability value to obtain a corrected project budget execution enhanced feature vector, thereby reducing the impact of noise and interference, so as to improve the accuracy and reliability of traffic scene data processing, thereby more effectively identifying and processing abnormal traffic events, and improving the performance and efficiency of the traffic monitoring system.

[0060] Specifically, in an embodiment of the present application, the coherent interference correction module includes: an activation unit, used to pass the project budget execution status enhancement feature vector through an activation function to obtain a category probability feature vector; a covariance matrix calculation unit, used to calculate the covariance matrix between the project budget execution status enhancement feature vector and the category probability feature vector; an autocorrelation covariance calculation unit, used to calculate the autocorrelation covariance matrix of the project budget execution status enhancement feature vector; an interference correction unit, used to calculate an interference correction matrix based on the covariance matrix and the autocorrelation covariance matrix; and a feature correction unit, used to correct the project budget execution status enhancement feature vector based on the interference correction matrix to obtain the corrected project budget execution status enhancement feature vector.

[0061] More specifically, in an embodiment of the present application, the interference correction unit is used to calculate the interference correction matrix based on the covariance matrix and the autocorrelation covariance matrix using the following correction formula; wherein the correction formula is:

[0062] S = Cov(x, P)*(Cov(x)+εI) -1

[0063] Among them, x represents the enhanced feature vector of the project budget execution, P represents the category probability feature vector, Cov(x, P) represents the covariance matrix between the enhanced feature vector of the project budget execution and the category probability feature vector, Cov(x) represents the autocorrelation covariance matrix of the enhanced feature vector of the project budget execution, I represents the unit matrix, ε represents a predetermined hyperparameter used to ensure the reversibility of the covariance matrix, and S represents the interference correction matrix.

[0064] It should be understood that, in view of the above technical problems, in the technical solution of the present application, the project budget execution situation reinforcement feature vector is subjected to coherent interference correction based on the category probability value to obtain the corrected project budget execution situation reinforcement feature vector, which removes the information in the category probability value that is irrelevant to the generation task through coherent interference correction. First, the category probability feature vector is obtained through the activation function, that is, the probability of each category is predicted. Subsequently, the covariance matrix between the project budget execution situation reinforcement feature vector and the category probability feature vector and the autocorrelation covariance matrix of the project budget execution situation reinforcement feature vector are calculated to understand the relationship and degree of change between them. Based on the covariance matrix and the autocorrelation covariance matrix, the interference correction matrix is ​​further calculated. The role of this correction matrix is ​​to remove the information in the category probability value that is irrelevant to the generation task, and retain and highlight the features related to the generation task. Further, the interference correction matrix is ​​applied to the project budget execution situation reinforcement feature vector to obtain the corrected project budget execution situation reinforcement feature vector, and the corrected project budget execution situation reinforcement feature vector will only contain information related to the generation task, so that it can focus on the truly important features, thereby improving the performance of the generation model.

[0065] In an embodiment of the present application, the visual progress image generation module 170 is used to generate a visual progress image of the current project budget execution based on the enhanced feature vector of the corrected project budget execution. Specifically, in an embodiment of the present application, the visual progress image generation module is used to: input the enhanced feature vector of the corrected project budget execution into a generator to generate a visual progress image of the current project budget execution. That is, the visual progress image of the current project budget execution is generated by classifying and processing the enhanced feature vector of the corrected project budget execution. In this way, it can help users intuitively understand the budget execution of the project, find problems and risks in time, and thus help users adjust budget strategies and take measures in time to ensure the effective execution of the project budget. In particular, in a specific embodiment of the present application, the visual progress image of the current project budget execution can use various forms of visualization tools and charts to intuitively display the project budget execution. For example, a line chart can show the trend of the project budget execution over time, compare the difference between actual expenditure and budget arrangement, and through the line chart, the actual situation of the project budget execution can be clearly seen. Pie charts can compare budget allocation and actual expenditure, showing the proportion of each expenditure, helping observers to intuitively understand the proportion of each expenditure. These visual forms of presenting the progress of project budget execution can more intuitively help managers and related personnel understand and analyze the financial status of the project.

[0066] In summary, the cloud computing-based project budget intelligent management system 100 based on the embodiment of the present application is explained, which obtains the budget information and actual expenditure data of the project, wherein the budget information of the project includes the project plan, budget allocation, and budget execution cycle, and the actual expenditure data includes the actual expenses incurred by the project, expenditure records, and expense types, and uses deep learning technology to perform semantic understanding analysis and association on the budget information and actual expenditure data of the project, thereby generating a visual progress image of the current project budget execution. In this way, it can help users intuitively understand the budget execution of the project, discover problems and risks in a timely manner, and thus help users adjust budget strategies and take measures in a timely manner to ensure the effective execution of the project budget.

[0067] Figure 5 FIG. 1 is a flow chart of a project budget intelligent management method based on cloud computing according to an embodiment of the present application. Figure 5As shown, according to the cloud computing-based project budget intelligent management method of the embodiment of the present application, the method includes: S110, obtaining the budget information and actual expenditure data of the project, wherein the budget information of the project includes the project plan, budget allocation, and budget execution cycle, and the actual expenditure data includes the actual expenses incurred by the project, expenditure records, and expense types; S120, performing word segmentation processing on the budget information of the project and then performing budget information context encoding to obtain a budget information context encoding feature matrix; S130, performing word segmentation processing on the actual expenditure data and then performing actual expenditure data context encoding to obtain an actual expenditure data context encoding feature matrix matrix; S140, fusing the budget information context encoding feature matrix and the actual expenditure data context encoding feature matrix to obtain a project budget execution feature matrix; S150, performing project budget execution feature extraction on the project budget execution feature matrix to obtain a project budget execution enhanced feature vector; S160, performing coherent interference correction on the project budget execution enhanced feature vector based on the category probability value to obtain a corrected project budget execution enhanced feature vector; and, S170, generating a visual progress image of the current project budget execution based on the corrected project budget execution enhanced feature vector.

[0068] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned cloud computing-based project budget intelligent management method have been referred to above. Figures 1 to 4 The description of the cloud computing-based project budget intelligent management system has been introduced in detail, and therefore, its repeated description will be omitted.

[0069] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A cloud computing-based project budget intelligent management system, characterized in that: include: The project budget data collection module is used to obtain the budget information and actual expenditure data of the project, wherein the budget information of the project includes the project plan, budget allocation, and budget execution cycle, and the actual expenditure data includes the actual expenses incurred by the project, expenditure records, and expense types; A budget information context encoding module, used for performing word segmentation processing on the budget information of the project and then performing budget information context encoding to obtain a budget information context encoding feature matrix; An actual expenditure data context encoding module, used for performing word segmentation processing on the actual expenditure data and then performing actual expenditure data context encoding to obtain an actual expenditure data context encoding feature matrix; An information fusion module, used for fusing the budget information context encoding feature matrix and the actual expenditure data context encoding feature matrix to obtain a project budget execution status feature matrix; A project budget execution feature extraction module, used for extracting project budget execution features from the project budget execution feature matrix to obtain a project budget execution enhanced feature vector; A coherent interference correction module, used for performing coherent interference correction on the enhanced feature vector of the project budget execution status based on the category probability value to obtain a corrected enhanced feature vector of the project budget execution status; A visualization progress image generation module, used to generate a visualization progress image of the current project budget execution based on the corrected project budget execution status enhancement feature vector; Wherein, the coherent interference correction module comprises: An activation unit, used for passing the project budget execution status reinforcement feature vector through an activation function to obtain a category probability feature vector; A covariance matrix calculation unit, used to calculate the covariance matrix between the project budget execution reinforcement feature vector and the category probability feature vector; An autocorrelation covariance calculation unit, used to calculate the autocorrelation covariance matrix of the enhanced feature vector of the project budget execution; An interference correction unit, configured to calculate an interference correction matrix based on the covariance matrix and the autocorrelation covariance matrix; A feature correction unit, configured to correct the enhanced feature vector of the project budget execution status based on the interference correction matrix to obtain the corrected enhanced feature vector of the project budget execution status; Wherein, the interference correction unit is used to: calculate the interference correction matrix based on the covariance matrix and the autocorrelation covariance matrix using the following correction formula; Wherein, the correction formula is: S=Cov(x,P)*(Cov(x)+εI) -1 Among them, x represents the enhanced feature vector of the project budget execution, P represents the category probability feature vector, Cov(x, P) represents the covariance matrix between the enhanced feature vector of the project budget execution and the category probability feature vector, Cov(x) represents the autocorrelation covariance matrix of the enhanced feature vector of the project budget execution, I represents the unit matrix, ε represents the predetermined hyperparameter, and S represents the interference correction matrix.

2. The cloud computing-based project budget intelligent management system according to claim 1 is characterized in that: The budget information context encoding module includes: A budget information word embedding unit, used to perform word segmentation processing on the budget information of the project and then input it into the word embedding layer to obtain a sequence of budget information word embedding vectors; The budget information encoding unit is used to input the sequence of the budget information word embedding vectors into a converter-based budget information context encoder to obtain the budget information context encoding feature matrix.

3. The cloud computing-based project budget intelligent management system according to claim 2, characterized in that: The budget information encoding unit includes: a contextual budget information extraction subunit, configured to input the sequence of the budget information word embedding vectors into the converter-based budget information context encoder to obtain a plurality of contextual budget information feature vectors; The two-dimensional arrangement subunit is used to perform two-dimensional arrangement on the multiple context budget information feature vectors to obtain the budget information context coding feature matrix.

4. The cloud computing-based project budget intelligent management system according to claim 3 is characterized in that: The actual expenditure data context encoding module comprises: An actual expenditure data word embedding unit, used for inputting the actual expenditure data into a word embedding layer after word segmentation processing to obtain a sequence of actual expenditure data word embedding vectors; The actual expenditure data encoding unit is used to input the sequence of the actual expenditure data word embedding vectors into the converter-based actual expenditure data context encoder to obtain the actual expenditure data context encoding feature matrix.

5. The cloud computing-based project budget intelligent management system according to claim 4, characterized in that: The project budget execution status feature extraction module is used to: input the project budget execution status feature matrix into the project budget execution status feature extractor based on the deep and shallow fusion convolutional network model to obtain the project budget execution status enhanced feature matrix, and then expand the project budget execution status enhanced feature matrix to obtain the project budget execution status enhanced feature vector.

6. The cloud computing-based project budget intelligent management system according to claim 5, characterized in that: The visualized progress image generation module is used to: input the corrected project budget execution status enhanced feature vector into a generator to generate a visualized progress image of the current project budget execution.

7. A project budget intelligent management method based on cloud computing, characterized in that: include: Obtaining the budget information and actual expenditure data of the project, wherein the budget information of the project includes the project plan, budget allocation, and budget execution cycle, and the actual expenditure data includes the actual expenses incurred by the project, expenditure records, and expense types; After word segmentation processing is performed on the budget information of the project, budget information context encoding is performed to obtain a budget information context encoding feature matrix; After word segmentation processing is performed on the actual expenditure data, actual expenditure data context encoding is performed to obtain an actual expenditure data context encoding feature matrix; The budget information context encoding feature matrix and the actual expenditure data context encoding feature matrix are integrated to obtain a project budget execution status feature matrix; Extracting project budget execution features from the project budget execution feature matrix to obtain a project budget execution enhanced feature vector; Performing coherent interference correction based on the category probability value on the enhanced feature vector of the project budget execution to obtain a corrected enhanced feature vector of the project budget execution; Based on the corrected enhanced feature vector of the project budget execution, a visual progress image of the current project budget execution is generated; The step of performing a coherent interference correction based on a class probability value on the enhanced feature vector of the project budget execution to obtain a corrected enhanced feature vector of the project budget execution includes: The project budget execution status reinforcement feature vector is passed through an activation function to obtain a category probability feature vector; Calculate the covariance matrix between the project budget execution reinforcement feature vector and the category probability feature vector; Calculate the autocorrelation covariance matrix of the enhanced eigenvector of the budget execution of the project; Calculating an interference correction matrix based on the covariance matrix and the autocorrelation covariance matrix; Correcting the project budget execution status enhancement feature vector based on the interference correction matrix to obtain the corrected project budget execution status enhancement feature vector; Wherein, calculating the interference correction matrix based on the covariance matrix and the autocorrelation covariance matrix includes: calculating the interference correction matrix based on the covariance matrix and the autocorrelation covariance matrix using the following correction formula; Wherein, the correction formula is: S=Cov(x,P)*(Cov(x)+εI) -1 Among them, x represents the enhanced feature vector of the project budget execution, P represents the category probability feature vector, Cov(x, P) represents the covariance matrix between the enhanced feature vector of the project budget execution and the category probability feature vector, Cov(x) represents the autocorrelation covariance matrix of the enhanced feature vector of the project budget execution, I represents the unit matrix, ε represents the predetermined hyperparameter, and S represents the interference correction matrix.

8. The cloud computing-based project budget intelligent management method according to claim 7, characterized in that: After word segmentation processing is performed on the budget information of the project, budget information context encoding is performed to obtain a budget information context encoding feature matrix, including: The budget information of the project is segmented and then input into a word embedding layer to obtain a sequence of budget information word embedding vectors; The sequence of the budget information word embedding vectors is input into a transformer-based budget information context encoder to obtain the budget information context encoding feature matrix.

Images