Data analysis method and device for infrastructure project, computer equipment, readable storage medium and program product

Abstract

The invention relates to a data analysis method and device for an infrastructure project, computer equipment, a readable storage medium and a program product, and relates to the technical field of data analysis. The method comprises the following steps: in response to a data analysis instruction for a target capital construction project, obtaining a data analysis index indicated by the data analysis instruction; performing complexity analysis on the data analysis indexes to obtain index complexity of the data analysis indexes; performing model matching based on the index complexity to obtain a data analysis model matched with the index complexity; and inputting the capital construction project data of the target capital construction project under the data analysis index into the data analysis model, and performing data analysis on the target capital construction project to obtain a data analysis result of the target capital construction project. By adopting the method, the accuracy of capital construction project data analysis can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of data analysis, and in particular to a data analysis method, device, computer equipment, readable storage medium and program product for infrastructure projects. Background Art

[0002] With the continuous development of information technology, the management of infrastructure projects is becoming increasingly digital and intelligent. However, the current management of infrastructure projects still faces many challenges, such as incomplete data collection, untimely processing, unscientific object evaluation, and imprecise management, which makes it difficult to control project progress, unreasonable resource allocation, and difficult to predict and control safety risks.

[0003] At present, data analysis of infrastructure projects mainly relies on manual analysis. However, this method is prone to analysis errors, resulting in low accuracy of data analysis of infrastructure projects. Summary of the invention

[0004] Based on this, it is necessary to provide a data analysis method, device, computer equipment, computer-readable storage medium and computer program product for infrastructure projects that can improve the accuracy of infrastructure project data analysis in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a data analysis method for infrastructure projects, comprising: in response to a data analysis instruction for a target infrastructure project, obtaining a data analysis indicator indicated by the data analysis instruction; performing complexity analysis on the data analysis indicator to obtain the indicator complexity of the data analysis indicator; performing model matching based on the indicator complexity to obtain a data analysis model that matches the indicator complexity; inputting the infrastructure project data of the target infrastructure project under the data analysis indicator into the data analysis model, performing data analysis on the target infrastructure project, and obtaining a data analysis result of the target infrastructure project.

[0006] In one of the embodiments, a complexity analysis is performed on a data analysis indicator to obtain the indicator complexity of the data analysis indicator, including: obtaining a data analysis parameter corresponding to the data analysis indicator; and performing a complexity analysis on the data analysis indicator based on a correlation between the data analysis indicator and the data analysis parameter, and the number of parameters of the data analysis parameter, to obtain the indicator complexity of the data analysis indicator.

[0007] In one of the embodiments, model matching is performed based on indicator complexity to obtain a data analysis model that matches the indicator complexity, including: based on the indicator complexity, algorithm matching is performed among candidate data analysis algorithms to obtain a target data analysis algorithm that matches the indicator complexity; according to the target data analysis algorithm, a data analysis model that matches the target data analysis algorithm is screened out from multiple candidate analysis models.

[0008] In one of the embodiments, the method further includes: based on data analysis indicators, performing data queries on multiple data source platforms respectively to obtain source project data of the target infrastructure project on each data source platform; performing data structure conversion on the source project data by a data structure conversion method that matches the data type of each source project data to obtain intermediate project data; and performing data fusion on the intermediate project data to obtain infrastructure project data of the target infrastructure project under the data analysis indicators.

[0009] In one of the embodiments, the method also includes: establishing an initial analysis model corresponding to each candidate data analysis algorithm; screening out a target analysis model that matches the target complexity in each initial analysis model based on the target complexity of each sample analysis indicator; obtaining the indicator weight of the sample analysis indicator and the sample project data of the sample infrastructure project under the sample analysis indicator; inputting the sample project data and the indicator weight into the target analysis model, performing data analysis on the sample project data, and obtaining a sample analysis result of the sample project data; adjusting the parameters of the target analysis model based on a target comparison result between the sample analysis result and the expected analysis result of the sample project data, and obtaining a candidate analysis model corresponding to each candidate data analysis algorithm.

[0010] In one embodiment, obtaining the indicator weight of the sample analysis indicator includes: obtaining the indicator attribute of the sample analysis indicator, performing importance analysis on the sample analysis indicator based on the indicator attribute to obtain the importance of the sample analysis indicator; and determining the indicator weight that matches the importance for the sample analysis indicator.

[0011] On the second aspect, the present application also provides a data analysis device for infrastructure projects, including: an indicator acquisition module, used to respond to a data analysis instruction for a target infrastructure project and acquire a data analysis indicator indicated by the data analysis instruction; a complexity analysis module, used to perform complexity analysis on the data analysis indicator and obtain the indicator complexity of the data analysis indicator; a model matching module, used to perform model matching based on the indicator complexity and obtain a data analysis model that matches the indicator complexity; a data analysis module, used to input the infrastructure project data of the target infrastructure project under the data analysis indicator into the data analysis model, perform data analysis on the target infrastructure project, and obtain the data analysis result of the target infrastructure project.

[0012] On the third aspect, the present application also provides a computer device, including a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program: in response to a data analysis instruction for a target infrastructure project, obtaining a data analysis indicator indicated by the data analysis instruction; performing complexity analysis on the data analysis indicator to obtain the indicator complexity of the data analysis indicator; performing model matching based on the indicator complexity to obtain a data analysis model that matches the indicator complexity; inputting the infrastructure project data of the target infrastructure project under the data analysis indicator into the data analysis model, performing data analysis on the target infrastructure project, and obtaining the data analysis result of the target infrastructure project.

[0013] In a fourth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, which implements the following steps when the computer program is executed by a processor: in response to a data analysis instruction for a target infrastructure project, obtain a data analysis indicator indicated by the data analysis instruction; perform complexity analysis on the data analysis indicator to obtain the indicator complexity of the data analysis indicator; perform model matching based on the indicator complexity to obtain a data analysis model that matches the indicator complexity; input the infrastructure project data of the target infrastructure project under the data analysis indicator into the data analysis model, perform data analysis on the target infrastructure project, and obtain the data analysis result of the target infrastructure project.

[0014] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the following steps when executed by a processor: in response to a data analysis instruction for a target infrastructure project, obtain a data analysis indicator indicated by the data analysis instruction; perform complexity analysis on the data analysis indicator to obtain the indicator complexity of the data analysis indicator; perform model matching based on the indicator complexity to obtain a data analysis model that matches the indicator complexity; input the infrastructure project data of the target infrastructure project under the data analysis indicator into the data analysis model, perform data analysis on the target infrastructure project, and obtain the data analysis result of the target infrastructure project.

[0015] The data analysis method, device, computer equipment, computer-readable storage medium and computer program product for the above-mentioned infrastructure project, in response to the data analysis instruction for the target infrastructure project, first obtain the data analysis index indicated by the data analysis instruction, so as to perform complexity analysis on the data analysis index, obtain the index complexity of the data analysis index, and then perform model matching to obtain a data analysis model that matches the index complexity. Then, the infrastructure project data of the target infrastructure project under the data analysis index is input into the data analysis model to perform data analysis on the target infrastructure project and obtain the data analysis result of the target infrastructure project. On the one hand, the present application effectively improves the accuracy of data analysis by using a data analysis model to replace the current manual analysis. On the other hand, the present application matches a suitable data analysis model according to the complexity of the data analysis index to achieve targeted data analysis, which not only ensures the comprehensiveness and accuracy of the data analysis, but also further improves the efficiency of the data analysis, thereby providing comprehensive, real-time and refined data support for subsequent infrastructure project management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A diagram showing an application environment of a data analysis method for an infrastructure project in an embodiment;

[0018] Figure 2 A schematic diagram of a flow chart of a data analysis method for an infrastructure project in one embodiment;

[0019] Figure 3 A schematic diagram of a process of analyzing the complexity of an indicator in one embodiment;

[0020] Figure 4 A schematic diagram of a model matching process in an embodiment;

[0021] Figure 5 A schematic diagram of a flow chart of data processing of an infrastructure project in an embodiment;

[0022] Figure 6 A schematic diagram of a process of model training in one embodiment;

[0023] Figure 7 A specific architecture diagram of infrastructure project data analysis in one embodiment;

[0024] Figure 8A schematic diagram of an interface for visual configuration of an infrastructure project in one embodiment;

[0025] Fig. 9 A schematic diagram of a quantitative evaluation of an infrastructure project in one embodiment;

[0026] Fig.10 is a structural block diagram of a data analysis device for an infrastructure project in an embodiment;

[0027] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0029] With the continuous development of information technology, the management of infrastructure projects is increasingly tending towards digitalization and intelligence. However, the current management of infrastructure projects still faces many challenges, such as incomplete data collection, untimely processing, unscientific object assessment, and imprecise management, which make it difficult to control project progress, unreasonable resource allocation, and difficult to predict and control safety risks. Therefore, there is an urgent need for a data analysis method for infrastructure projects to quantitatively evaluate infrastructure projects, thereby providing data support for comprehensive, real-time, and refined digital management of infrastructure projects. In the prior art, data analysis of infrastructure projects is usually achieved by relying on manual analysis. However, this method is not only prone to analysis errors, resulting in low accuracy of data analysis of infrastructure projects, but also time-consuming and labor-intensive, affecting the efficiency of data analysis of infrastructure projects.

[0030] The data analysis method for infrastructure projects provided in the embodiments of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Specifically, the server 104 responds to the data analysis instruction for the target infrastructure project initiated by the terminal 102, obtains the data analysis index indicated by the data analysis instruction; performs complexity analysis on the data analysis index to obtain the index complexity of the data analysis index; based on the index complexity, performs model matching to obtain a data analysis model that matches the index complexity; inputs the infrastructure project data of the target infrastructure project under the data analysis index into the data analysis model, performs data analysis on the target infrastructure project, and obtains the data analysis result of the target infrastructure project. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers and Internet of Things devices. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0031] In an exemplary embodiment, Figure 2 As shown, a data analysis method for infrastructure projects is provided. Figure 1 The server 104 in FIG. 1 is used as an example to illustrate, including:

[0032] Step S202, in response to a data analysis instruction for a target infrastructure project, obtaining a data analysis indicator indicated by the data analysis instruction.

[0033] Among them, infrastructure projects refer to operating projects of infrastructure projects, and target infrastructure projects refer to infrastructure projects that require data analysis. Data analysis instructions refer to instructions for data analysis of target infrastructure projects. Data analysis indicators refer to indicators for data analysis of target infrastructure projects. In one example, data analysis indicators include but are not limited to operating plan indicators, which are used to evaluate the accuracy of operating plans and temporary plans for medium and high-risk projects, personnel in place indicators, which are used to evaluate the attendance accuracy of project operators, management personnel attendance accuracy, supervision personnel attendance accuracy, and owner personnel attendance accuracy, personnel violation indicators, which are used to evaluate the violation rate, number of violations, and major accident rate during project operations, enterprise resource indicators, which are used to evaluate the enterprise strength of the construction enterprise corresponding to the target infrastructure project, the enterprise key position staffing compliance rate, and the enterprise credit, and project site supervision indicators, which are used to evaluate the on-site construction equipment startup rate and construction equipment online rate of the target infrastructure project.

[0034] For example, when the server receives a data analysis instruction for a target infrastructure project, it may first parse the data analysis instruction to obtain various data analysis indicators indicated in the data analysis instruction, so as to facilitate subsequent data analysis based on these data analysis indicators.

[0035] Step S204, performing complexity analysis on the data analysis indicators to obtain the indicator complexity of the data analysis indicators.

[0036] Among them, complexity analysis refers to the process of analyzing the complexity of data analysis indicators. It is understandable that the complexity of each data analysis indicator is not the same. For example, a certain data analysis indicator requires more data analysis parameters, or there is a correlation between a certain data analysis indicator and its corresponding data analysis parameters. These factors will affect the complexity of the data analysis indicator. In this embodiment, the complexity analysis of the data analysis indicators is performed to match the optimal data analysis model for each data analysis indicator.

[0037] For example, after parsing each data analysis indicator from the data analysis instruction, the server may further evaluate the complexity of each data analysis indicator in order to improve the accuracy of the data analysis, thereby obtaining the indicator complexity of each data analysis, and the indicator complexity is used for data analysis model matching.

[0038] Step S206, performing model matching based on the indicator complexity to obtain a data analysis model that matches the indicator complexity.

[0039] Among them, the data analysis model is a model for data analysis that is pre-established based on different data analysis algorithms. In this embodiment, the data analysis algorithms include a linear regression algorithm and a polynomial regression algorithm. Of course, in practical applications, other data analysis algorithms can also be used according to actual conditions.

[0040] In one example, the linear regression algorithm assumes that there is a linear relationship between the target variable and the input variable, and finds the best fitting line by minimizing the residual sum of squares between the predicted value and the actual value. The error between the predicted value and the actual value is minimized by adjusting the parameters of the linear model. The linear regression algorithm has high computational efficiency and can usually give good prediction results for data sets that meet the linear assumption. In this embodiment, this algorithm can be used for data analysis indicators with lower complexity.

[0041] In one example, the polynomial regression algorithm is a regression analysis method for establishing a nonlinear relationship between a dependent variable target and an independent variable feature. The polynomial function is used to fit the sample data, the coefficients of the polynomial are determined using the least squares method, and the optimal coefficient solution is obtained by minimizing the square of the error. In this embodiment, this algorithm can be used for data analysis indicators with a higher degree of complexity.

[0042] Exemplarily, the server has pre-configured the optimal data analysis algorithm for each indicator complexity, thereby establishing a corresponding data analysis model. Therefore, after the server analyzes the indicator complexity of the current data analysis indicator, it can match the corresponding data analysis algorithm according to the indicator complexity, and then determine the data analysis model corresponding to the data analysis algorithm.

[0043] Step S208, inputting the infrastructure project data of the target infrastructure project under the data analysis index into the data analysis model, performing data analysis on the target infrastructure project, and obtaining the data analysis result of the target infrastructure project.

[0044] The infrastructure project data refers to the operation data of the target infrastructure project, including but not limited to project data, operation status, personnel data, personnel attendance status, personnel training status, violation records, etc. In this embodiment, the infrastructure project data corresponds to the data analysis index, that is, the server obtains the infrastructure project data corresponding to the data analysis index.

[0045] Exemplarily, after parsing the data analysis indicator indicated by the data analysis instruction, the server can obtain the infrastructure project data corresponding to the data analysis indicator, and input the infrastructure project data into the matched data analysis model to perform data analysis on the target infrastructure project, thereby obtaining the data analysis result of the target infrastructure project under the data analysis indicator.

[0046] It should be noted that the data analysis results can be used to quantitatively evaluate the target infrastructure project. Quantitative evaluation refers to the quantitative description and analysis of the development process and results of things. In this embodiment, it refers to describing the project situation of the target infrastructure project from the perspective of various data analysis results. That is, the data analysis models established by various data analysis algorithms can be integrated to obtain a quantitative evaluation model for the target infrastructure project. The quantitative evaluation can include but is not limited to personnel portraits, dynamic scoring, capability evaluation, carrying capacity evaluation, etc. For example, a dynamic quantitative evaluation model of an enterprise corresponding to a target infrastructure project can be established. The enterprise dynamic quantitative evaluation model can include multiple sub-models, which are data analysis models established based on different data analysis algorithms. Each sub-model corresponds to the data analysis indicators required for the dynamic quantitative evaluation of the enterprise. For example, the data analysis indicators required for the dynamic quantitative evaluation of the enterprise may include the enterprise basic strength evaluation value, the enterprise key position staffing evaluation value, the enterprise credit, the enterprise violation evaluation value, the enterprise project personnel in place rate, the enterprise project personnel training rate, the enterprise operation plan accuracy rate, the enterprise medium and high risk operation plan accuracy rate, the enterprise medium and high risk temporary plan rate, the enterprise carrying capacity evaluation value, and the violation behavior evaluation value. Each data analysis indicator can be configured with a suitable data analysis algorithm, i.e., a linear regression algorithm or a polynomial regression algorithm, according to its indicator complexity, so as to establish a corresponding data analysis model. After the data analysis results obtained by each data analysis model are summarized, they can be used as the enterprise dynamic quantitative evaluation results of the target infrastructure project.

[0047] In this embodiment, the server responds to the data analysis instruction for the target infrastructure project, first obtains the data analysis indicator indicated by the data analysis instruction, performs complexity analysis on the data analysis indicator, obtains the indicator complexity of the data analysis indicator, and then performs model matching to obtain a data analysis model that matches the indicator complexity. Then, the infrastructure project data of the target infrastructure project under the data analysis indicator is input into the data analysis model to perform data analysis on the target infrastructure project and obtain the data analysis result of the target infrastructure project. On the one hand, the present application effectively improves the accuracy of data analysis by using a data analysis model to replace the current manual analysis. On the other hand, the present application matches the appropriate data analysis model according to the complexity of the data analysis indicator to achieve targeted data analysis, which not only ensures the comprehensiveness and accuracy of the data analysis, but also further improves the efficiency of the data analysis, thereby providing comprehensive, real-time and refined data support for subsequent infrastructure project management.

[0048] In an exemplary embodiment, Figure 3 As shown, the complexity of the data analysis indicators is analyzed to obtain the indicator complexity of the data analysis indicators, including:

[0049] Step S302, obtaining data analysis parameters corresponding to the data analysis indicators.

[0050] Step S304, performing complexity analysis on the data analysis indicator according to the correlation between the data analysis indicator and the data analysis parameter, and the number of parameters of the data analysis parameter, to obtain the indicator complexity of the data analysis indicator.

[0051] Among them, data analysis parameters refer to the relevant parameters required for data analysis under the data analysis indicators. For example, for data analysis indicator A, it is necessary to conduct a combined analysis from the perspectives of data analysis parameter a1, data analysis parameter a2 and data analysis parameter a3, while for data analysis indicator B, it is only necessary to analyze from the perspective of data analysis parameter b1. That is, there are one or more data analysis parameters corresponding to the data analysis indicator. The correlation relationship refers to the mathematical relationship between the data analysis indicator and the data analysis parameter, which can be a linear relationship or a nonlinear relationship in this embodiment. The number of parameters refers to the total number of data analysis parameters.

[0052] Exemplarily, for each data analysis indicator, the server obtains the data analysis parameters required to analyze the target infrastructure project under the data analysis indicator, and performs complexity analysis on the data analysis indicator based on the correlation relationship between the data analysis parameter and the data analysis indicator, i.e., whether it is a linear relationship or a nonlinear relationship, and the number of data analysis parameters, thereby obtaining the indicator complexity of the data analysis indicator.

[0053] In one example, when there is a linear relationship between the data analysis parameter and the data analysis index and / or the number of data analysis parameters is small, it can be considered that the index complexity of the data analysis index is low, so a linear regression algorithm is selected, and a corresponding data analysis model is established based on the linear regression algorithm. When there is a nonlinear relationship between the data analysis parameter and the data analysis index and / or the number of data analysis parameters is large, it can be considered that the index complexity of the data analysis index is high, so a polynomial regression algorithm is selected, and a corresponding data analysis model is established based on the polynomial regression algorithm.

[0054] In this embodiment, the complexity analysis of the data analysis indicators is performed from the perspective of the correlation between the data analysis indicators and the corresponding data analysis parameters, as well as the number of parameters of the data analysis parameters, which improves the accuracy of the complexity analysis of the data analysis indicators, thereby improving the accuracy of subsequent model matching, and further improving the accuracy of the data analysis results.

[0055] In an exemplary embodiment, Figure 4 As shown, based on the complexity of the indicators, model matching is performed to obtain a data analysis model that matches the complexity of the indicators, including:

[0056] Step S402, based on the indicator complexity, algorithm matching is performed among the candidate data analysis algorithms to obtain a target data analysis algorithm that matches the indicator complexity.

[0057] Step S404: According to the target data analysis algorithm, a data analysis model matching the target data analysis algorithm is screened out from a plurality of candidate analysis models.

[0058] Among them, the candidate data analysis algorithm refers to a plurality of pre-set data analysis algorithms, including a linear regression algorithm and a polynomial regression algorithm. Of course, in actual application, other data analysis algorithms can also be preset. The candidate analysis model refers to an analysis model established in advance based on the candidate data analysis algorithm, including an analysis model established based on a linear regression algorithm and an analysis model established based on a polynomial regression algorithm. Of course, it can also include an analysis model established based on other data analysis algorithms.

[0059] Exemplarily, after analyzing the indicator complexity of the data analysis indicator, the server matches the indicator complexity with each preset candidate data analysis algorithm to obtain a target data analysis algorithm that matches the indicator complexity, and then further matches the target data analysis algorithm with each preset candidate analysis model to obtain a data analysis model that matches the target data analysis algorithm. The data analysis model can then be used to analyze the situation of the target infrastructure project under the data analysis indicator, and then the target infrastructure project can be quantitatively evaluated based on the results of the analysis.

[0060] In this embodiment, algorithm matching and model matching are used to match each data analysis indicator to the optimal data analysis model, thereby improving the accuracy of the data analysis results, and further improving the accuracy of the quantitative evaluation of the target infrastructure project, providing accurate data support for the management of infrastructure projects.

[0061] In an exemplary embodiment, Figure 5 As shown in the figure, the process of acquiring infrastructure project data includes:

[0062] Step S502 , based on the data analysis indicators, respectively perform data query on multiple data source platforms to obtain source project data of the target infrastructure project on each data source platform.

[0063] The data source platform refers to the data source platform of the target infrastructure project. It is understandable that the project data of the target infrastructure project may exist in multiple data platforms. In order to ensure the accuracy and completeness of data analysis, in this embodiment, the infrastructure project data is obtained from multiple data source platforms. The source project data refers to the project data of the target infrastructure project that exists in the data source platform and corresponds to the data analysis indicators.

[0064] Exemplarily, for each data analysis indicator, the server performs a data query in each data source platform to query the source project data corresponding to the data analysis indicator of the target infrastructure project existing in the data source platform, until all data analysis indicators and all data source platforms are queried.

[0065] Step S504, performing data structure conversion on the source project data by using a data structure conversion method that matches the data type of each source project data to obtain intermediate project data.

[0066] The data structure conversion method refers to the method of converting the data structure of the source project data, which may include but is not limited to ETL (Extract Transform Load) tools, SQL (Structured Query Language) scripts or manual conversion. Depending on the data type, the source project data can be matched with a suitable data structure conversion method to improve the efficiency of the data structure conversion. Intermediate project data refers to the data obtained after the data structure conversion of the source project data.

[0067] Exemplarily, after querying and obtaining the source project data on each data source platform, the server obtains the data type of the source project data, such as video data, picture data, text data, table data, etc., for each source project data. Thus, according to the data type of the source project data, a suitable data structure conversion method is matched. For example, the structure of video data is relatively complex, and ETL data can be used for data structure conversion to improve the conversion accuracy. For example, the structure of text data is relatively simple, so SQL scripts or manual conversion methods can be used. Thus, the intermediate project data after each source project data conversion is obtained, and the data structure of each intermediate project data is unified.

[0068] In actual applications, before converting the data structure, the server can first perform data cleaning and data missing processing on each source project data to obtain complete source project data without abnormal values.

[0069] Step S506, merging the data of each intermediate project to obtain the infrastructure project data of the target infrastructure project under the data analysis index.

[0070] Exemplarily, the server finally fuses the data of each intermediate project, and uses the fused data set as the infrastructure project data of the target infrastructure project under the data analysis index for subsequent data analysis.

[0071] In this embodiment, data query is performed from multiple data source platforms to ensure the integrity and accuracy of data analysis. Through further data structure conversion and data fusion, the data structure is unified, the heterogeneity between multi-source data is overcome, and the accuracy of infrastructure project data is improved.

[0072] In an exemplary embodiment, Figure 6 As shown in the figure, the process of model building and training includes:

[0073] Step S602: establishing an initial analysis model corresponding to each candidate data analysis algorithm.

[0074] It is understandable that the server can determine multiple candidate data analysis algorithms in advance, and establish a data analysis model corresponding to each candidate data analysis algorithm, namely the initial analysis model. Subsequently, according to the sample complexity, the server matches the appropriate analysis model for each sample analysis indicator and performs model training.

[0075] Step S604, based on the target complexity of each sample analysis indicator, a target analysis model matching the target complexity is screened out from each initial analysis model.

[0076] The sample analysis index refers to the pre-set sample index used for data analysis.

[0077] Exemplarily, the server matches a corresponding target analysis model from multiple initial analysis models according to the sample complexity of each sample analysis indicator. The sample complexity analysis process is the same as step S302 and step S304, and the target analysis model matching process is the same as step S402 and step S404, which will not be repeated here.

[0078] Step S606, obtaining the indicator weight of the sample analysis indicator and the sample project data of the sample infrastructure project under the sample analysis indicator.

[0079] The indicator weight refers to the weight of the sample analysis indicator in the process of model training. The sample infrastructure project refers to multiple sample infrastructure projects used for model training. The sample project data refers to the project data corresponding to the sample analysis indicator of the sample infrastructure project existing in multiple data source platforms.

[0080] Exemplarily, the server performs data query in multiple data source platforms for the sample analysis indicators, obtains the sample project data corresponding to the sample analysis indicators of the sample infrastructure projects existing in each data source platform, and obtains the indicator weights of the sample analysis indicators, thereby performing subsequent model training based on the sample project data and the indicator weights.

[0081] In practical applications, the indicator weight can be determined according to the indicator attribute. Therefore, in one embodiment, obtaining the indicator weight of the sample analysis indicator includes: obtaining the indicator attribute of the sample analysis indicator, performing importance analysis on the sample analysis indicator based on the indicator attribute, and obtaining the importance of the sample analysis indicator; for the sample analysis indicator, determining the indicator weight that matches the importance.

[0082] Among them, indicator attributes refer to the basic attributes of sample analysis indicators, including but not limited to data analysis scenarios, indicator usage, indicator description, business attributes corresponding to indicators, etc. Importance is used to characterize the importance of sample analysis indicators. The higher the importance, the higher the weight can be configured, and the lower the importance, the lower the weight can be configured accordingly.

[0083] Exemplarily, the server obtains the indicator attributes of each sample analysis indicator, and then performs importance analysis on the sample analysis indicator according to the indicator attributes to obtain the importance of the sample analysis indicator, thereby configuring a suitable indicator weight for it.

[0084] Step S608: input the sample project data and the indicator weights into the target analysis model, perform data analysis on the sample project data, and obtain sample analysis results of the sample project data.

[0085] Step S610, adjusting parameters of a target analysis model according to a target comparison result between the sample analysis result and an expected analysis result of the sample project data, to obtain a candidate analysis model corresponding to each candidate data analysis algorithm.

[0086] Exemplarily, sample project data and indicator weights are input into a target analysis model to perform data analysis on the sample project data to obtain a sample analysis result corresponding to the sample project data, and the sample analysis result is compared with an expected analysis result preset for the sample project data. The target comparison result obtained may refer to an error value between the two analysis results, thereby continuously adjusting parameters of the target analysis model based on the target comparison result. The parameter adjustment may include optimizing indicator weights and adjusting data analysis algorithms, i.e., configuring other data analysis algorithms, until the error value is lower than a preset error threshold, and then stopping training to obtain a candidate analysis model.

[0087] It should be noted that the model training process in this embodiment can also be configured in a visual way, that is, the user can configure the required model parameters in the front-end interface, such as the monitoring period of the sample analysis index, including real-time or monthly, data analysis algorithm and index weight, so as to carry out continuous model iteration optimization, and the user can intuitively understand the model training process and output results, so as to dynamically adjust the model parameters. Of course, in the subsequent actual data analysis application, the actual data analysis results can still be combined with the actual application needs for comparative analysis, so as to further optimize the data analysis model.

[0088] In this embodiment, a more accurate data analysis model is obtained through continuous model training, and visualization methods can be combined to provide real-time model configuration. Users can intuitively understand the model training process and output results, thereby optimizing the model, making the data analysis model more in line with user needs and more flexible in configuration.

[0089] In a specific embodiment, the data analysis method of infrastructure projects can be applied to Figure 7The application architecture shown in the figure. The application architecture includes the front-end, presentation layer, business layer, data processing and source data. The front-end includes Html (HyperTextMarkup Language), CSS (Cascading Style Sheets), jQuery and pictures. Html is a standard markup language used to describe the structure and content of a web page. Html documents can be parsed and rendered into web pages by browsers, and users can view and interact with web pages in browsers. CSS is a computer language used to describe the style of HTML or XML (Extensible Markup Language) documents, including derivative languages ​​such as SVG (Scalable Vector Graphics, a language for describing two-dimensional graphics) and MathML (a markup language for writing mathematical formulas in web pages). CSS describes how to render elements in media such as screens, paper, and audio. It can not only modify web pages statically, but also dynamically format various elements of web pages in conjunction with various scripting languages. jQuery is a fast and concise JavaScript framework. It encapsulates the commonly used functional codes of JavaScript and provides a simple JavaScript design mode. It is mainly used to optimize HTML document operations, event processing, animation design and Ajax (Asynchronous Javascript And XML) interaction. Ajax is a technology used to create fast and dynamic web pages. Through Ajax, web applications can quickly present incremental updates on the user interface without reloading (refreshing) the entire page, which enables web applications to respond to user operations faster and provide a richer interactive experience. The presentation layer includes template engine rendering, Ajax interaction, POST request and GET request. Template engine rendering is an implementation mechanism of a programming language that allows developers to render and generate the final web page or document by combining HTML code with data. POST request is an HTTP (Hypertext Transfer Protocol) method used to submit data or send requests to the server. POST request sends data in the message body of the request. GET request is one of the most commonly used request methods in the HTTP protocol. When a browser or other client wants to obtain a resource from the server, it will issue a GET request. The business layer integrates various quantitative evaluation businesses of infrastructure projects, including organizational scoring, quantitative management, quantitative data interface services (used to provide transmission interfaces for quantitative data), carrying capacity evaluation, organizational rectification, etc.Data processing is the architecture layer used for data processing and data analysis of infrastructure projects, including data cleaning, data caching, data analysis indicators, data analysis models, read and write data source platforms, etc. Source data is the architecture layer for storing infrastructure project data, including data such as work plans, personnel attendance, personnel violations, corporate organizations, projects, equipment data, project progress, personnel training, etc.

[0090] The specific process of the data analysis method for infrastructure projects is as follows:

[0091] S1: Establish initial analysis models corresponding to the linear regression algorithm and the polynomial regression algorithm respectively. Determine the sample analysis parameters corresponding to each sample analysis indicator, and analyze the complexity of the sample analysis indicator according to the parameter quantity of the sample analysis parameter and the correlation relationship between the sample analysis indicator and the sample analysis parameter, i.e., linear relationship or nonlinear relationship. And select the target analysis model that matches the complexity in each initial analysis model. Obtain the indicator attributes of the sample analysis indicator, analyze the importance of the sample analysis indicator based on the indicator attributes, and determine the indicator weight that matches the importance. Input the indicator weight and the sample project data of the sample infrastructure project under the sample analysis indicator into the target analysis model to perform data analysis on the sample project data and obtain the sample analysis results of the sample project data. According to the error value between the sample analysis results and the expected analysis results of the sample project data, adjust the parameters of the target analysis model to obtain the candidate analysis model corresponding to each candidate data analysis algorithm. The model training process can be configured in a visual way, that is, the user can configure the required model parameters in the front-end interface by himself, such as Figure 8 As shown, the interface displays indicator subdivision items, indicator items, descriptions, trigger condition data sources, preset scores, i.e. expected scores, score calculations, i.e. evaluation scores for quantitative evaluations, key parameter values, and single highest scores. Users can click on parameter adjustment to adjust model parameters, such as the monitoring period of sample analysis indicators, including real-time or monthly, data analysis algorithms, and indicator weights, in order to perform continuous iterative optimization of the model. Users can intuitively understand the model training process and output results, and thus dynamically adjust model parameters.

[0092] S2: In response to the data analysis instruction for the target infrastructure project, parse and obtain multiple data analysis indicators indicated by the data analysis instruction, obtain the data analysis parameters corresponding to each data analysis indicator, and perform complexity analysis on the data analysis indicator according to the correlation between the data analysis indicator and the data analysis parameter, as well as the number of parameters of the data analysis parameter, to obtain the indicator complexity of the data analysis indicator. Based on the indicator complexity, perform algorithm matching in the linear regression algorithm and the polynomial regression algorithm to obtain a target data analysis algorithm that matches the indicator complexity, and select a data analysis model that matches the target data analysis algorithm from multiple candidate analysis models.

[0093] S3: Using mainstream data processing and distributed structured storage technologies including SQL, MONGDB, Hadoop, etc., data queries are performed on multiple data source platforms respectively, and the source project data corresponding to the data analysis indicators stored on each data source platform of the target infrastructure project are obtained. Among them, MongoDB is a database based on distributed file storage, which provides a high-performance and scalable data storage solution, especially suitable for Web applications. Hadoop is a distributed system infrastructure, mainly used for the storage of massive data and the analysis and calculation of massive data. Data cleaning and missing value processing are performed on each source project data. Data cleaning refers to the data normalization processing of source project data, which is an important link in the data preprocessing process. The purpose is to remove or correct the noise, errors or inconsistencies in the data set to improve the quality of the source project data, thereby ensuring the accuracy and effectiveness of the data analysis results. Then, the source project data is converted into a data structure through a data structure conversion method that matches the data type of each source project data to obtain intermediate project data, and the intermediate project data is merged to obtain the infrastructure project data of the target infrastructure project under the data analysis indicators.

[0094] S4: Input the infrastructure project data into the data analysis model, perform data analysis on the target infrastructure project, and obtain the data analysis results of the target infrastructure project. The data analysis results can be used to conduct quantitative evaluation of the target infrastructure project, such as Fig. 9 As shown, the server performs data analysis on various data analysis indicators, namely, operation plan accuracy indicator, personnel presence indicator, personnel training indicator, enterprise resource allocation indicator, and project monitoring indicator, based on the source project data, and then conducts quantitative evaluation of the target infrastructure project based on the data analysis results, and visualizes the output of quantitative evaluation results, namely, statistical report, enterprise carrying capacity, enterprise evaluation, organizational evaluation and improvement, personnel evaluation, and equipment evaluation.

[0095] In this embodiment, in response to a data analysis instruction for a target infrastructure project, the data analysis indicator indicated by the data analysis instruction is first obtained to perform a complexity analysis on the data analysis indicator to obtain the indicator complexity of the data analysis indicator, thereby performing model matching to obtain a data analysis model that matches the indicator complexity. The infrastructure project data of the target infrastructure project under the data analysis indicator is then input into the data analysis model to perform data analysis on the target infrastructure project to obtain the data analysis results of the target infrastructure project. On the one hand, the present application effectively improves the accuracy of data analysis by using a data analysis model to replace the current manual analysis. On the other hand, the present application matches a suitable data analysis model according to the complexity of the data analysis indicator to achieve targeted data analysis, which not only ensures the comprehensiveness and accuracy of the data analysis, but also further improves the efficiency of the data analysis, thereby providing comprehensive, real-time and refined data support for subsequent infrastructure project management.

[0096] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0097] Based on the same inventive concept, the embodiment of the present application also provides a data analysis device for infrastructure projects for implementing the data analysis method for infrastructure projects involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the data analysis device for one or more infrastructure projects provided below can refer to the limitations of the data analysis method for infrastructure projects above, and will not be repeated here.

[0098] In an exemplary embodiment, Fig.10As shown, a data analysis device for infrastructure projects is provided, including: an indicator acquisition module 1002, used to respond to a data analysis instruction for a target infrastructure project and acquire a data analysis indicator indicated by the data analysis instruction; a complexity analysis module 1004, used to perform complexity analysis on the data analysis indicator to obtain the indicator complexity of the data analysis indicator; a model matching module 1006, used to perform model matching based on the indicator complexity to obtain a data analysis model that matches the indicator complexity; a data analysis module 1008, used to input the infrastructure project data of the target infrastructure project under the data analysis indicator into the data analysis model, perform data analysis on the target infrastructure project, and obtain the data analysis result of the target infrastructure project.

[0099] In one embodiment, the complexity analysis module 1004 is also used to: obtain data analysis parameters corresponding to the data analysis indicators; perform complexity analysis on the data analysis indicators according to the correlation between the data analysis indicators and the data analysis parameters, and the number of parameters of the data analysis parameters, to obtain the indicator complexity of the data analysis indicators.

[0100] In one embodiment, the model matching module 1006 is also used to: perform algorithm matching among candidate data analysis algorithms based on indicator complexity to obtain a target data analysis algorithm that matches the indicator complexity; and screen out a data analysis model that matches the target data analysis algorithm from multiple candidate analysis models based on the target data analysis algorithm.

[0101] In one embodiment, the data analysis device for infrastructure projects is also used to: based on data analysis indicators, perform data queries on multiple data source platforms respectively to obtain source project data of the target infrastructure project on each data source platform; perform data structure conversion on the source project data by a data structure conversion method that matches the data type of each source project data to obtain intermediate project data; and perform data fusion on the intermediate project data to obtain the infrastructure project data of the target infrastructure project under the data analysis indicators.

[0102] In one embodiment, the data analysis device for infrastructure projects is also used to: establish an initial analysis model corresponding to each candidate data analysis algorithm; screen out a target analysis model that matches the target complexity in each initial analysis model according to the target complexity of each sample analysis indicator; obtain the indicator weight of the sample analysis indicator, and the sample project data of the sample infrastructure project under the sample analysis indicator; input the sample project data and the indicator weight into the target analysis model, perform data analysis on the sample project data, and obtain a sample analysis result of the sample project data; adjust the parameters of the target analysis model according to the target comparison result between the sample analysis result and the expected analysis result of the sample project data, and obtain a candidate analysis model corresponding to each candidate data analysis algorithm.

[0103] In one embodiment, the data analysis device of the infrastructure project is also used to: obtain the indicator attributes of the sample analysis indicators, perform importance analysis on the sample analysis indicators based on the indicator attributes, and obtain the importance of the sample analysis indicators; for the sample analysis indicators, determine the indicator weights that match the importance.

[0104] Each module in the above-mentioned data analysis device for infrastructure projects can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0105] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.11 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data analysis data of infrastructure projects. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a data analysis method for infrastructure projects is implemented.

[0106] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0107] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: in response to a data analysis instruction for a target infrastructure project, obtaining a data analysis indicator indicated by the data analysis instruction; performing complexity analysis on the data analysis indicator to obtain the indicator complexity of the data analysis indicator; performing model matching based on the indicator complexity to obtain a data analysis model that matches the indicator complexity; inputting the infrastructure project data of the target infrastructure project under the data analysis indicator into the data analysis model, performing data analysis on the target infrastructure project, and obtaining the data analysis result of the target infrastructure project.

[0108] In one embodiment, when the processor executes the computer program, it also implements the following steps: obtaining data analysis parameters corresponding to the data analysis indicators; performing complexity analysis on the data analysis indicators based on the correlation between the data analysis indicators and the data analysis parameters, and the number of parameters of the data analysis parameters, to obtain the indicator complexity of the data analysis indicators.

[0109] In one embodiment, when the processor executes the computer program, the following steps are also implemented: based on the indicator complexity, algorithm matching is performed among the candidate data analysis algorithms to obtain a target data analysis algorithm that matches the indicator complexity; based on the target data analysis algorithm, a data analysis model that matches the target data analysis algorithm is screened out from multiple candidate analysis models.

[0110] In one embodiment, the processor also implements the following steps when executing the computer program: based on the data analysis indicators, respectively perform data query on multiple data source platforms to obtain the source project data of the target infrastructure project on each data source platform; perform data structure conversion on the source project data by a data structure conversion method that matches the data type of each source project data to obtain intermediate project data; perform data fusion on the intermediate project data to obtain the infrastructure project data of the target infrastructure project under the data analysis indicators.

[0111] In one embodiment, the processor also implements the following steps when executing the computer program: establishing an initial analysis model corresponding to each candidate data analysis algorithm; screening out a target analysis model that matches the target complexity in each initial analysis model based on the target complexity of each sample analysis indicator; obtaining the indicator weight of the sample analysis indicator and the sample project data of the sample infrastructure project under the sample analysis indicator; inputting the sample project data and the indicator weight into the target analysis model, performing data analysis on the sample project data, and obtaining a sample analysis result of the sample project data; adjusting the parameters of the target analysis model based on a target comparison result between the sample analysis result and the expected analysis result of the sample project data, and obtaining a candidate analysis model corresponding to each candidate data analysis algorithm.

[0112] In one embodiment, when the processor executes the computer program, the following steps are also implemented: obtaining indicator attributes of the sample analysis indicators, performing importance analysis on the sample analysis indicators based on the indicator attributes, and obtaining the importance of the sample analysis indicators; and determining indicator weights that match the importance for the sample analysis indicators.

[0113] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: in response to a data analysis instruction for a target infrastructure project, a data analysis indicator indicated by the data analysis instruction is obtained; complexity analysis is performed on the data analysis indicator to obtain the indicator complexity of the data analysis indicator; based on the indicator complexity, model matching is performed to obtain a data analysis model that matches the indicator complexity; infrastructure project data of the target infrastructure project under the data analysis indicator is input into the data analysis model, data analysis is performed on the target infrastructure project, and data analysis results of the target infrastructure project are obtained.

[0114] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining data analysis parameters corresponding to the data analysis indicators; performing complexity analysis on the data analysis indicators based on the correlation between the data analysis indicators and the data analysis parameters, and the number of parameters of the data analysis parameters, to obtain the indicator complexity of the data analysis indicators.

[0115] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the indicator complexity, algorithm matching is performed among the candidate data analysis algorithms to obtain a target data analysis algorithm that matches the indicator complexity; based on the target data analysis algorithm, a data analysis model that matches the target data analysis algorithm is screened out from multiple candidate analysis models.

[0116] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the data analysis indicators, data queries are performed on multiple data source platforms respectively to obtain the source project data of the target infrastructure project on each data source platform; the source project data is converted into a data structure by a data structure conversion method that matches the data type of each source project data to obtain intermediate project data; the intermediate project data are merged to obtain the infrastructure project data of the target infrastructure project under the data analysis indicators.

[0117] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: establishing an initial analysis model corresponding to each candidate data analysis algorithm; screening out a target analysis model that matches the target complexity in each initial analysis model based on the target complexity of each sample analysis indicator; obtaining the indicator weight of the sample analysis indicator and the sample project data of the sample infrastructure project under the sample analysis indicator; inputting the sample project data and the indicator weight into the target analysis model, performing data analysis on the sample project data, and obtaining a sample analysis result of the sample project data; adjusting the parameters of the target analysis model based on a target comparison result between the sample analysis result and the expected analysis result of the sample project data, and obtaining a candidate analysis model corresponding to each candidate data analysis algorithm.

[0118] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining indicator attributes of the sample analysis indicators, performing importance analysis on the sample analysis indicators based on the indicator attributes, and obtaining the importance of the sample analysis indicators; and determining indicator weights that match the importance for the sample analysis indicators.

[0119] In one embodiment, a computer program product is provided, including a computer program, which implements the following steps when executed by a processor: in response to a data analysis instruction for a target infrastructure project, obtaining a data analysis indicator indicated by the data analysis instruction; performing complexity analysis on the data analysis indicator to obtain the indicator complexity of the data analysis indicator; performing model matching based on the indicator complexity to obtain a data analysis model that matches the indicator complexity; inputting the infrastructure project data of the target infrastructure project under the data analysis indicator into the data analysis model, performing data analysis on the target infrastructure project, and obtaining a data analysis result of the target infrastructure project.

[0120] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining data analysis parameters corresponding to the data analysis indicators; performing complexity analysis on the data analysis indicators based on the correlation between the data analysis indicators and the data analysis parameters, and the number of parameters of the data analysis parameters, to obtain the indicator complexity of the data analysis indicators.

[0121] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the indicator complexity, algorithm matching is performed among the candidate data analysis algorithms to obtain a target data analysis algorithm that matches the indicator complexity; based on the target data analysis algorithm, a data analysis model that matches the target data analysis algorithm is screened out from multiple candidate analysis models.

[0122] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the data analysis indicators, data queries are performed on multiple data source platforms respectively to obtain the source project data of the target infrastructure project on each data source platform; the source project data is converted into a data structure by a data structure conversion method that matches the data type of each source project data to obtain intermediate project data; the intermediate project data are merged to obtain the infrastructure project data of the target infrastructure project under the data analysis indicators.

[0123] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: establishing an initial analysis model corresponding to each candidate data analysis algorithm; screening out a target analysis model that matches the target complexity in each initial analysis model based on the target complexity of each sample analysis indicator; obtaining the indicator weight of the sample analysis indicator and the sample project data of the sample infrastructure project under the sample analysis indicator; inputting the sample project data and the indicator weight into the target analysis model, performing data analysis on the sample project data, and obtaining a sample analysis result of the sample project data; adjusting the parameters of the target analysis model based on a target comparison result between the sample analysis result and the expected analysis result of the sample project data, and obtaining a candidate analysis model corresponding to each candidate data analysis algorithm.

[0124] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining indicator attributes of the sample analysis indicators, performing importance analysis on the sample analysis indicators based on the indicator attributes, and obtaining the importance of the sample analysis indicators; and determining indicator weights that match the importance for the sample analysis indicators.

[0125] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0126] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0127] The technical features of the above embodiments may 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 application.

[0128] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A data analysis method for an infrastructure project, characterized in that: The method comprises: In response to a data analysis instruction for a target infrastructure project, obtaining a data analysis indicator indicated by the data analysis instruction; Performing complexity analysis on the data analysis indicator to obtain the indicator complexity of the data analysis indicator; Based on the complexity of the indicator, model matching is performed to obtain a data analysis model that matches the complexity of the indicator; The infrastructure project data of the target infrastructure project under the data analysis index is input into the data analysis model, and data analysis is performed on the target infrastructure project to obtain the data analysis result of the target infrastructure project.

2. The method according to claim 1, characterized in that The performing complexity analysis on the data analysis indicator to obtain the indicator complexity of the data analysis indicator includes: Obtaining data analysis parameters corresponding to the data analysis indicators; According to the correlation between the data analysis indicator and the data analysis parameter, and the number of parameters of the data analysis parameter, the complexity analysis is performed on the data analysis indicator to obtain the indicator complexity of the data analysis indicator.

3. The method according to claim 1, characterized in that The performing of model matching based on the indicator complexity to obtain a data analysis model matching the indicator complexity includes: Based on the complexity of the indicator, algorithm matching is performed among the candidate data analysis algorithms to obtain a target data analysis algorithm that matches the complexity of the indicator; According to the target data analysis algorithm, a data analysis model matching the target data analysis algorithm is screened out from a plurality of candidate analysis models.

4. The method according to claim 1, characterized in that: The method further comprises: Based on the data analysis indicators, data queries are performed on multiple data source platforms respectively to obtain source project data of the target infrastructure project on each of the data source platforms; By using a data structure conversion method that matches the data type of each source project data, the source project data is converted into a data structure to obtain intermediate project data; The intermediate project data are fused to obtain the infrastructure project data of the target infrastructure project under the data analysis index.

5. The method according to claim 1, characterized in that The method further comprises: Establishing an initial analysis model corresponding to each candidate data analysis algorithm; According to the target complexity of each sample analysis indicator, a target analysis model matching the target complexity is screened out from each of the initial analysis models; Obtaining the indicator weight of the sample analysis indicator and the sample project data of the sample infrastructure project under the sample analysis indicator; Inputting the sample project data and the indicator weight into the target analysis model, performing data analysis on the sample project data, and obtaining a sample analysis result of the sample project data; According to the target comparison result between the sample analysis result and the expected analysis result of the sample project data, the parameters of the target analysis model are adjusted to obtain the candidate analysis model corresponding to each candidate data analysis algorithm.

6. The method according to claim 5, characterized in that The obtaining of the indicator weight of the sample analysis indicator includes: Acquiring an indicator attribute of the sample analysis indicator, and performing importance analysis on the sample analysis indicator based on the indicator attribute to obtain the importance of the sample analysis indicator; For the sample analysis indicator, determine the indicator weight that matches the importance.

7. A data analysis device for infrastructure projects, characterized in that: The device comprises: An indicator acquisition module, configured to respond to a data analysis instruction for a target infrastructure project and acquire a data analysis indicator indicated by the data analysis instruction; A complexity analysis module, used to perform complexity analysis on the data analysis indicator to obtain the indicator complexity of the data analysis indicator; A model matching module, used to perform model matching based on the indicator complexity to obtain a data analysis model that matches the indicator complexity; The data analysis module is used to input the infrastructure project data of the target infrastructure project under the data analysis index into the data analysis model, perform data analysis on the target infrastructure project, and obtain the data analysis result of the target infrastructure project.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images